From 4b9ec74922f2f04ad830d07ba8c3bc95b8a0d826 Mon Sep 17 00:00:00 2001 From: David Galiffi Date: Fri, 9 Aug 2024 15:02:51 -0400 Subject: [PATCH 01/29] Check Python version on application launch (#393) * Check that the minimum required Python (3.8) version is used. Prints a descriptive error message, rather than a cryptic import failure, if minimum Python version is not met. Internal ticket SWDEV-477233. * Disable the RPM mangling of shebangs. The are changing the `#!/usr/bin/python3` to `#!/usr/libexec/platform-python`. With this set, omniperf is always using the platform installed version of python, which is python 3.6 on RHEL 8. Using virtual environments, like conda, did not work. * Fix pylint issues --------- Signed-off-by: David Galiffi [ROCm/rocprofiler-compute commit: 75a4b51d0d6dab082e01fb61f8a577b532f07201] --- projects/rocprofiler-compute/CMakeLists.txt | 1 + .../docs/install/core-install.rst | 24 ++++++++-- projects/rocprofiler-compute/src/omniperf | 45 ++++++++++++------- 3 files changed, 51 insertions(+), 19 deletions(-) diff --git a/projects/rocprofiler-compute/CMakeLists.txt b/projects/rocprofiler-compute/CMakeLists.txt index 9a1632a112..b945bc9b5b 100644 --- a/projects/rocprofiler-compute/CMakeLists.txt +++ b/projects/rocprofiler-compute/CMakeLists.txt @@ -416,6 +416,7 @@ set(CPACK_RPM_PACKAGE_PROVIDES "${CPACK_PACKAGE_NAME}") set(CPACK_RPM_COMPONENT_INSTALL ON) set(CPACK_RPM_PACKAGE_RELEASE_DIST ON) set(CPACK_RPM_FILE_NAME "RPM-DEFAULT") +set(CPACK_RPM_SPEC_MORE_DEFINE "%undefine __brp_mangle_shebangs") if(DEFINED CPACK_PACKAGING_INSTALL_PREFIX) set(CPACK_RPM_EXCLUDE_FROM_AUTO_FILELIST_ADDITION "${CPACK_PACKAGING_INSTALL_PREFIX}") diff --git a/projects/rocprofiler-compute/docs/install/core-install.rst b/projects/rocprofiler-compute/docs/install/core-install.rst index 1d28b07b5d..7629644dc8 100644 --- a/projects/rocprofiler-compute/docs/install/core-install.rst +++ b/projects/rocprofiler-compute/docs/install/core-install.rst @@ -32,7 +32,7 @@ right for you. :width: 800 .. _core-install: - + Core installation ================= @@ -44,6 +44,12 @@ installation. * CMake ``>= 3.19`` * ROCm ``>= 5.7.1`` +.. note:: + + Omniperf will use the first version of ``Python3`` found in your system's + ``PATH``. If the default version of Python3 is older than 3.8, you may need to + update your system's ``PATH`` to point to a newer version of Python3. + Omniperf depends on a number of Python packages documented in the top-level ``requirements.txt`` file. Install these *before* configuring Omniperf. @@ -66,6 +72,16 @@ following steps illustrate how to install the necessary Python dependencies using `pip `_ and Omniperf into a shared location controlled by the ``INSTALL_DIR`` environment variable. +.. tip:: + + To always run Omniperf with a particular version of python, you can create a + bash alias. For example, to run Omniperf with Python 3.10, you can run the + following command: + + .. code-block:: shell + + alias omniperf-mypython="/usr/bin/python3.10 /opt/rocm/bin/omniperf" + .. _core-install-cmake-vars: Configuration variables @@ -208,21 +224,21 @@ software stack. .. code-block:: shell $ sudo apt install omniperf - $ pip install -r /opt/rocm/libexec/omniperf/requirements.txt + $ python3 -m pip install -r /opt/rocm/libexec/omniperf/requirements.txt .. tab-item:: Red Hat Enterprise Linux .. code-block:: shell $ sudo dnf install omniperf - $ pip install -r /opt/rocm/libexec/omniperf/requirements.txt + $ python3 -m pip install -r /opt/rocm/libexec/omniperf/requirements.txt .. tab-item:: SUSE Linux Enterprise Server .. code-block:: shell $ sudo zypper install omniperf - $ pip install -r /opt/rocm/libexec/omniperf/requirements.txt + $ python3 -m pip install -r /opt/rocm/libexec/omniperf/requirements.txt .. _core-install-rocprof-var: diff --git a/projects/rocprofiler-compute/src/omniperf b/projects/rocprofiler-compute/src/omniperf index 6977b54cb5..1acff5f077 100755 --- a/projects/rocprofiler-compute/src/omniperf +++ b/projects/rocprofiler-compute/src/omniperf @@ -1,5 +1,7 @@ #!/usr/bin/env python3 +"""Main entry point for omniperf""" + ##############################################################################bl # MIT License # @@ -24,23 +26,24 @@ # SOFTWARE. ##############################################################################el -import logging +# import logging import os import sys -from pip._internal.req import parse_requirements -from pathlib import Path -from importlib import import_module, metadata import re try: + from pathlib import Path + from importlib import metadata from omniperf_base import Omniperf from utils.utils import console_error -except: +except ImportError as e: + # print("Failed to import required modules: " + str(e)) pass def verify_deps_version(localVer, desiredVer, operator): - """Check package version strings with simple operators used in companion requirements.txt file""" + """Check package version strings with simple operators used in companion + requirements.txt file""" if operator == "==": return localVer == desiredVer elif operator == ">=": @@ -56,15 +59,24 @@ def verify_deps_version(localVer, desiredVer, operator): def verify_deps(): - """Utility to read library dependencies from requirements.txt and endeavor to load them within current execution environment. - Used in top-level omniperf to provide error messages if necessary dependencies are not available. """ + """Utility to read library dependencies from requirements.txt and endeavor + to load them within current execution environment. + Used in top-level omniperf to provide error messages if necessary + dependencies are not available.""" + + # Check which version of python is being used + if sys.version_info[0] < 3 or (sys.version_info[0] == 3 and sys.version_info[1] < 8): + print("[ERROR] Python 3.8 or higher is required to run omniperf." + f" The current version is {sys.version_info[0]}.{sys.version_info[1]}.") + sys.exit(1) + bindir = Path(__file__).resolve().parent depsLocation = ["requirements.txt", "../requirements.txt"] for location in depsLocation: checkFile = os.path.join(bindir, location) if os.path.exists(checkFile): - with open(checkFile, "r") as file_in: + with open(checkFile, "r", encoding="utf-8") as file_in: dependencies = file_in.read().splitlines() error = False @@ -84,8 +96,8 @@ def verify_deps(): except metadata.PackageNotFoundError: error = True print( - "[ERROR] The '%s' package was not found in the current execution environment." - % dependency + f"[ERROR] The '{dependency}' package was not found " + "in the current execution environment." ) # check version requirement @@ -95,8 +107,8 @@ def verify_deps(): localVersion, desiredVersion, operator ): print( - "[ERROR] the '%s' distribution does not meet version requirements to use omniperf." - % dependency + f"[ERROR] the '{dependency}' distribution does " + "not meet version requirements to use omniperf." ) print(" --> version installed :", localVersion) error = True @@ -104,15 +116,18 @@ def verify_deps(): if error: print("") print( - "Please verify all of the python dependencies called out in the requirements file" + "Please verify all of the python dependencies called out " + "in the requirements file" ) print("are installed locally prior to running omniperf.") print("") - print("See: %s" % checkFile) + print(f"See: {checkFile}") sys.exit(1) return + def main(): + '''Main function for omniperf''' # verify required python dependencies verify_deps() From 3565b2ee4636f1482a3aaf79723918e1f7326036 Mon Sep 17 00:00:00 2001 From: David Galiffi Date: Mon, 12 Aug 2024 10:32:33 -0400 Subject: [PATCH 02/29] Remove `dev` and `main` branch from workflows. (#404) * Remove `dev` and `main` branch from workflows. Update links in documentation. Signed-off-by: David Galiffi * `amd-staging` -> `amd-mainline` in docs Signed-off-by: Peter Jun Park --------- Signed-off-by: David Galiffi Signed-off-by: Peter Jun Park Co-authored-by: Peter Jun Park [ROCm/rocprofiler-compute commit: 68e5db2dbd2bc35a3d2b8fc7f60befa8f70ef737] --- .../.github/workflows/docs.yml | 2 +- .../.github/workflows/formatting.yml | 4 ++-- .../.github/workflows/mi-rhel9.yml | 2 +- .../.github/workflows/rhel-8.yml | 4 ++-- .../.github/workflows/tarball.yml | 2 +- .../.github/workflows/ubuntu-jammy.yml | 4 ++-- .../docs/archive/docs-1.x/analysis.md | 2 +- .../docs/archive/docs-2.x/analysis.md | 2 +- .../docs/archive/docs-2.x/performance_model.md | 16 ++++++++-------- projects/rocprofiler-compute/docs/conf.py | 2 +- .../docs/how-to/analyze/cli.rst | 2 +- .../docs/how-to/profile/mode.rst | 2 +- .../vector-memory-operation-counting.rst | 2 +- .../docs/tutorial/profiling-by-example.rst | 2 +- 14 files changed, 24 insertions(+), 24 deletions(-) diff --git a/projects/rocprofiler-compute/.github/workflows/docs.yml b/projects/rocprofiler-compute/.github/workflows/docs.yml index 81a46cf8b0..f6dcbd9a04 100644 --- a/projects/rocprofiler-compute/.github/workflows/docs.yml +++ b/projects/rocprofiler-compute/.github/workflows/docs.yml @@ -2,7 +2,7 @@ name: Documentation on: push: - branches: [ main, amd-mainline ] + branches: [ amd-mainline ] paths: - 'docs/archive/docs-2.x/**' - 'docs/archive/docs-1.x/**' diff --git a/projects/rocprofiler-compute/.github/workflows/formatting.yml b/projects/rocprofiler-compute/.github/workflows/formatting.yml index 8f4bda4453..9d9e125f04 100644 --- a/projects/rocprofiler-compute/.github/workflows/formatting.yml +++ b/projects/rocprofiler-compute/.github/workflows/formatting.yml @@ -3,9 +3,9 @@ name: Formatting on: push: - branches: [ main, dev, amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging ] pull_request: - branches: [ main, dev, amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging ] concurrency: group: ${{ github.workflow }}-${{ github.ref }} diff --git a/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml b/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml index a500d2bc02..157241521f 100644 --- a/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml +++ b/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml @@ -2,7 +2,7 @@ name: mi-rhel9 on: push: - branches: [ main, amd-mainline ] + branches: [ amd-mainline ] # Allows manual execution workflow_dispatch: diff --git a/projects/rocprofiler-compute/.github/workflows/rhel-8.yml b/projects/rocprofiler-compute/.github/workflows/rhel-8.yml index 278fbaa5f2..59ba244186 100644 --- a/projects/rocprofiler-compute/.github/workflows/rhel-8.yml +++ b/projects/rocprofiler-compute/.github/workflows/rhel-8.yml @@ -5,9 +5,9 @@ name: RHEL 8 # Controls when the workflow will run on: push: - branches: [ main, dev, amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging ] pull_request: - branches: [ main, dev, amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging ] # Allows you to run this workflow manually from the Actions tab workflow_dispatch: diff --git a/projects/rocprofiler-compute/.github/workflows/tarball.yml b/projects/rocprofiler-compute/.github/workflows/tarball.yml index 8958c076d7..1724a01f96 100644 --- a/projects/rocprofiler-compute/.github/workflows/tarball.yml +++ b/projects/rocprofiler-compute/.github/workflows/tarball.yml @@ -2,7 +2,7 @@ name: tarball on: push: - branches: [ main, amd-mainline ] + branches: [ amd-mainline ] pull_request: concurrency: diff --git a/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml b/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml index cb76dd4977..cf29d809d5 100644 --- a/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml +++ b/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml @@ -4,9 +4,9 @@ name: Ubuntu 22.04 on: push: - branches: [ main, dev, amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging ] pull_request: - branches: [ main, dev, amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging ] # Allows you to run this workflow manually from the Actions tab workflow_dispatch: diff --git a/projects/rocprofiler-compute/docs/archive/docs-1.x/analysis.md b/projects/rocprofiler-compute/docs/archive/docs-1.x/analysis.md index e8e18fe906..126364dbd6 100644 --- a/projects/rocprofiler-compute/docs/archive/docs-1.x/analysis.md +++ b/projects/rocprofiler-compute/docs/archive/docs-1.x/analysis.md @@ -171,7 +171,7 @@ $ omniperf analyze -p workloads/vcopy/mi200/ --list-metrics gfx90a ├─────────┼─────────────────────────────┤ ... ``` - 2. Choose your own customized subset of metrics with `-b` (a.k.a. `--metric`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/main/src/omniperf_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light). + 2. Choose your own customized subset of metrics with `-b` (a.k.a. `--metric`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/amd-mainline/src/omniperf_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light). ```shell-session $ omniperf analyze -p workloads/vcopy/mi200/ -b 2 -------- diff --git a/projects/rocprofiler-compute/docs/archive/docs-2.x/analysis.md b/projects/rocprofiler-compute/docs/archive/docs-2.x/analysis.md index 471fc31725..22fa72e392 100644 --- a/projects/rocprofiler-compute/docs/archive/docs-2.x/analysis.md +++ b/projects/rocprofiler-compute/docs/archive/docs-2.x/analysis.md @@ -181,7 +181,7 @@ Analysis mode = cli 2.1.30 -> L1I Fetch Latency ... ``` -3. Choose your own customized subset of metrics with `-b` (a.k.a. `--block`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/main/src/omniperf_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light). +3. Choose your own customized subset of metrics with `-b` (a.k.a. `--block`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/amd-mainline/src/omniperf_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light). ```shell-session $ omniperf analyze -p workloads/vcopy/MI200/ -b 2 -------- diff --git a/projects/rocprofiler-compute/docs/archive/docs-2.x/performance_model.md b/projects/rocprofiler-compute/docs/archive/docs-2.x/performance_model.md index 1f564084fc..df761cf0df 100644 --- a/projects/rocprofiler-compute/docs/archive/docs-2.x/performance_model.md +++ b/projects/rocprofiler-compute/docs/archive/docs-2.x/performance_model.md @@ -2178,7 +2178,7 @@ A good discussion of coarse and fine grained memory allocations and what type of (VALU_inst_mix_example)= ## VALU Arithmetic Instruction Mix -For this example, we consider the [instruction mix sample](https://github.com/ROCm/omniperf/blob/dev/sample/instmix.hip) distributed as a part of Omniperf. +For this example, we consider the [instruction mix sample](https://github.com/ROCm/omniperf/blob/amd-mainline/sample/instmix.hip) distributed as a part of Omniperf. ```{note} This example is expected to work on all CDNA accelerators, however the results in this section were collected on an [MI2XX](2xxnote) accelerator @@ -2269,7 +2269,7 @@ shows that we have exactly one of each type of VALU arithmetic instruction, by c (Fabric_transactions_example)= ## Infinity-Fabric(tm) transactions -For this example, we consider the [Infinity Fabric(tm) sample](https://github.com/ROCm/omniperf/blob/dev/sample/fabric.hip) distributed as a part of Omniperf. +For this example, we consider the [Infinity Fabric(tm) sample](https://github.com/ROCm/omniperf/blob/amd-mainline/sample/fabric.hip) distributed as a part of Omniperf. This code launches a simple read-only kernel, e.g.: ```c++ @@ -2826,7 +2826,7 @@ On an AMD [MI2XX](2xxnote) accelerator, for FP32 values this will generate a `gl (flatmembench)= ### Global / Generic (FLAT) -For this example, we consider the [vector-memory sample](https://github.com/ROCm/omniperf/blob/dev/sample/vmem.hip) distributed as a part of Omniperf. +For this example, we consider the [vector-memory sample](https://github.com/ROCm/omniperf/blob/amd-mainline/sample/vmem.hip) distributed as a part of Omniperf. This code launches many different versions of a simple read/write/atomic-only kernels targeting various address spaces, e.g. below is our simple `global_write` kernel: ```c++ @@ -2976,7 +2976,7 @@ The assembly in these experiments were generated for an [MI2XX](2xxnote) acceler Next, we examine a generic write. As discussed [previously](Flat_design), our `generic_write` kernel uses an address space cast to _force_ the compiler to choose our desired address space, regardless of other optimizations that may be possible. -We also note that the `filter` parameter passed in as a kernel argument (see [example](https://github.com/ROCm/omniperf/blob/dev/sample/vmem.hip), or [design note](Flat_design)) is set to zero on the host, such that we always write to the 'local' (LDS) memory allocation `lds`. +We also note that the `filter` parameter passed in as a kernel argument (see [example](https://github.com/ROCm/omniperf/blob/amd-mainline/sample/vmem.hip), or [design note](Flat_design)) is set to zero on the host, such that we always write to the 'local' (LDS) memory allocation `lds`. Examining this kernel in the VMEM Instruction Mix table yields: @@ -3339,7 +3339,7 @@ Next we examine the use of 'Spill/Scratch' memory. On current CDNA accelerators such as the [MI2XX](2xxnote), this is implemented using the [private](mspace) memory space, which maps to ['scratch' memory](https://llvm.org/docs/AMDGPUUsage.html#amdgpu-address-spaces) in AMDGPU hardware terminology. This type of memory can be accessed via different instructions depending on the specific architecture targeted. However, current CDNA accelerators such as the [MI2XX](2xxnote) use so called `buffer` instructions to access private memory in a simple (and typically) coalesced manner. See [Sec. 9.1, 'Vector Memory Buffer Instructions' of the CDNA2 ISA guide](https://www.amd.com/system/files/TechDocs/instinct-mi200-cdna2-instruction-set-architecture.pdf) for further reading on this instruction type. -We develop a [simple kernel](https://github.com/ROCm/omniperf/blob/dev/sample/stack.hip) that uses stack memory: +We develop a [simple kernel](https://github.com/ROCm/omniperf/blob/amd-mainline/sample/stack.hip) that uses stack memory: ```c++ #include __global__ void knl(int* out, int filter) { @@ -3404,7 +3404,7 @@ Here we see a single write to the stack (10.3.6), which corresponds to an L1-L2 (IPC_example)= ## Instructions-per-cycle and Utilizations example -For this section, we use the instructions-per-cycle (IPC) [example](https://github.com/ROCm/omniperf/blob/dev/sample/ipc.hip) included with Omniperf. +For this section, we use the instructions-per-cycle (IPC) [example](https://github.com/ROCm/omniperf/blob/amd-mainline/sample/ipc.hip) included with Omniperf. This example is compiled using `c++17` support: @@ -3824,7 +3824,7 @@ Finally, we note that our branch utilization (11.2.5) has increased slightly fro ## LDS Examples -For this example, we consider the [LDS sample](https://github.com/ROCm/omniperf/blob/dev/sample/lds.hip) distributed as a part of Omniperf. +For this example, we consider the [LDS sample](https://github.com/ROCm/omniperf/blob/amd-mainline/sample/lds.hip) distributed as a part of Omniperf. This code contains two kernels to explore how both [LDS](lds) bandwidth and bank conflicts are calculated in Omniperf. This example was compiled and run on an MI250 accelerator using ROCm v5.6.0, and Omniperf v2.0.0. @@ -4037,7 +4037,7 @@ The bank conflict rate linearly increases with the number of work-items within a ## Occupancy Limiters Example -In this [example](https://github.com/ROCm/omniperf/blob/dev/sample/occupancy.hip), we will investigate the use of the resource allocation panel in the [Workgroup Manager](SPI)'s metrics section to determine occupancy limiters. +In this [example](https://github.com/ROCm/omniperf/blob/amd-mainline/sample/occupancy.hip), we will investigate the use of the resource allocation panel in the [Workgroup Manager](SPI)'s metrics section to determine occupancy limiters. This code contains several kernels to explore how both various kernel resources impact achieved occupancy, and how this is reported in Omniperf. This example was compiled and run on a MI250 accelerator using ROCm v5.6.0, and Omniperf v2.0.0: diff --git a/projects/rocprofiler-compute/docs/conf.py b/projects/rocprofiler-compute/docs/conf.py index b38ce2e5cf..f74f95ecd2 100644 --- a/projects/rocprofiler-compute/docs/conf.py +++ b/projects/rocprofiler-compute/docs/conf.py @@ -55,7 +55,7 @@ external_projects_current_project = "omniperf" # frequently used external resources extlinks = { - "dev-sample": ("https://github.com/ROCm/omniperf/blob/dev/sample/%s", "%s"), + "dev-sample": ("https://github.com/ROCm/omniperf/blob/amd-mainline/sample/%s", "%s"), "prod-page": ( "https://www.amd.com/en/products/accelerators/instinct/%s.html", "%s", diff --git a/projects/rocprofiler-compute/docs/how-to/analyze/cli.rst b/projects/rocprofiler-compute/docs/how-to/analyze/cli.rst index 15faff8fc1..82185cd417 100644 --- a/projects/rocprofiler-compute/docs/how-to/analyze/cli.rst +++ b/projects/rocprofiler-compute/docs/how-to/analyze/cli.rst @@ -186,7 +186,7 @@ Walkthrough 3. Choose your own customized subset of metrics with the ``-b`` (or ``--block``) option. Or, build your own configuration following - `config_template `_. + `config_template `_. The following snippet shows how to generate a report containing only metric 2 (:doc:`System Speed-of-Light `). diff --git a/projects/rocprofiler-compute/docs/how-to/profile/mode.rst b/projects/rocprofiler-compute/docs/how-to/profile/mode.rst index de23a801ba..5bc0ad6a7c 100644 --- a/projects/rocprofiler-compute/docs/how-to/profile/mode.rst +++ b/projects/rocprofiler-compute/docs/how-to/profile/mode.rst @@ -38,7 +38,7 @@ Run ``omniperf profile -h`` for more details. See Profiling example ----------------- -The ``__ repository +The ``__ repository includes source code for a sample GPU compute workload, ``vcopy.cpp``. A copy of this file is available in the ``share/sample`` subdirectory after a normal Omniperf installation, or via the ``$OMNIPERF_SHARE/sample`` directory when diff --git a/projects/rocprofiler-compute/docs/tutorial/includes/vector-memory-operation-counting.rst b/projects/rocprofiler-compute/docs/tutorial/includes/vector-memory-operation-counting.rst index e3dd0deb4a..2797ed8f26 100644 --- a/projects/rocprofiler-compute/docs/tutorial/includes/vector-memory-operation-counting.rst +++ b/projects/rocprofiler-compute/docs/tutorial/includes/vector-memory-operation-counting.rst @@ -623,7 +623,7 @@ manner. See for further reading on this instruction type. We develop a `simple -kernel `__ +kernel `__ that uses stack memory: .. code-block:: cpp diff --git a/projects/rocprofiler-compute/docs/tutorial/profiling-by-example.rst b/projects/rocprofiler-compute/docs/tutorial/profiling-by-example.rst index 8a9c85c03b..e39239b9d1 100644 --- a/projects/rocprofiler-compute/docs/tutorial/profiling-by-example.rst +++ b/projects/rocprofiler-compute/docs/tutorial/profiling-by-example.rst @@ -7,7 +7,7 @@ Profiling by example ******************** The following examples refer to sample :doc:`HIP ` code located in -:fab:`github` :dev-sample:`ROCm/omniperf/blob/dev/sample <>` and distributed +:fab:`github` :dev-sample:`ROCm/omniperf/blob/amd-mainline/sample <>` and distributed as part of Omniperf. .. include:: ./includes/valu-arithmetic-instruction-mix.rst From 519a737d573387bc4b586677458e6e4258a9e3ab Mon Sep 17 00:00:00 2001 From: David Galiffi Date: Mon, 12 Aug 2024 10:44:22 -0400 Subject: [PATCH 03/29] Update dependabot.yml target-branch Signed-off-by: David Galiffi [ROCm/rocprofiler-compute commit: ae6ed4c8a941d653ccb8b40c086f787edd773beb] --- projects/rocprofiler-compute/.github/workflows/dependabot.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/projects/rocprofiler-compute/.github/workflows/dependabot.yml b/projects/rocprofiler-compute/.github/workflows/dependabot.yml index 48d6228bad..90f2d871e9 100644 --- a/projects/rocprofiler-compute/.github/workflows/dependabot.yml +++ b/projects/rocprofiler-compute/.github/workflows/dependabot.yml @@ -10,7 +10,7 @@ updates: open-pull-requests-limit: 10 schedule: interval: "daily" - target-branch: "dev" + target-branch: "amd-staging" labels: - "documentation" - "dependencies" From 205209c0fd9ecf33f76f7742b3eefd13200b6601 Mon Sep 17 00:00:00 2001 From: David Galiffi Date: Tue, 13 Aug 2024 18:05:03 -0400 Subject: [PATCH 04/29] Run Workflows on Release Branches (#409) Signed-off-by: David Galiffi [ROCm/rocprofiler-compute commit: 3499b8571d8ea807dbc94e62aea497b13783bfde] --- projects/rocprofiler-compute/.github/workflows/formatting.yml | 4 ++-- projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml | 2 +- projects/rocprofiler-compute/.github/workflows/rhel-8.yml | 4 ++-- projects/rocprofiler-compute/.github/workflows/tarball.yml | 2 +- .../rocprofiler-compute/.github/workflows/ubuntu-jammy.yml | 4 ++-- 5 files changed, 8 insertions(+), 8 deletions(-) diff --git a/projects/rocprofiler-compute/.github/workflows/formatting.yml b/projects/rocprofiler-compute/.github/workflows/formatting.yml index 9d9e125f04..55b2129b18 100644 --- a/projects/rocprofiler-compute/.github/workflows/formatting.yml +++ b/projects/rocprofiler-compute/.github/workflows/formatting.yml @@ -3,9 +3,9 @@ name: Formatting on: push: - branches: [ amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging, release/** ] pull_request: - branches: [ amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging, release/** ] concurrency: group: ${{ github.workflow }}-${{ github.ref }} diff --git a/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml b/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml index 157241521f..4cc54454f9 100644 --- a/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml +++ b/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml @@ -2,7 +2,7 @@ name: mi-rhel9 on: push: - branches: [ amd-mainline ] + branches: [ amd-mainline, release/** ] # Allows manual execution workflow_dispatch: diff --git a/projects/rocprofiler-compute/.github/workflows/rhel-8.yml b/projects/rocprofiler-compute/.github/workflows/rhel-8.yml index 59ba244186..01dfad5910 100644 --- a/projects/rocprofiler-compute/.github/workflows/rhel-8.yml +++ b/projects/rocprofiler-compute/.github/workflows/rhel-8.yml @@ -5,9 +5,9 @@ name: RHEL 8 # Controls when the workflow will run on: push: - branches: [ amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging, release/** ] pull_request: - branches: [ amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging, release/** ] # Allows you to run this workflow manually from the Actions tab workflow_dispatch: diff --git a/projects/rocprofiler-compute/.github/workflows/tarball.yml b/projects/rocprofiler-compute/.github/workflows/tarball.yml index 1724a01f96..9ad5cfc9e9 100644 --- a/projects/rocprofiler-compute/.github/workflows/tarball.yml +++ b/projects/rocprofiler-compute/.github/workflows/tarball.yml @@ -2,7 +2,7 @@ name: tarball on: push: - branches: [ amd-mainline ] + branches: [ amd-mainline, release/** ] pull_request: concurrency: diff --git a/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml b/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml index cf29d809d5..1dbf06b59c 100644 --- a/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml +++ b/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml @@ -4,9 +4,9 @@ name: Ubuntu 22.04 on: push: - branches: [ amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging, release/** ] pull_request: - branches: [ amd-mainline, amd-staging ] + branches: [ amd-mainline, amd-staging, release/** ] # Allows you to run this workflow manually from the Actions tab workflow_dispatch: From 1e1c7430d4951856e145086207bc6abef2b257d9 Mon Sep 17 00:00:00 2001 From: Peter Jun Park Date: Tue, 13 Aug 2024 12:29:32 -0400 Subject: [PATCH 05/29] mv changes to changelog.md Signed-off-by: Peter Jun Park [ROCm/rocprofiler-compute commit: 92cfd5149aac6eed5570784d3250cf71a43ae996] --- .../{CHANGES => CHANGELOG.md} | 39 ++++++++++++------- 1 file changed, 24 insertions(+), 15 deletions(-) rename projects/rocprofiler-compute/{CHANGES => CHANGELOG.md} (87%) diff --git a/projects/rocprofiler-compute/CHANGES b/projects/rocprofiler-compute/CHANGELOG.md similarity index 87% rename from projects/rocprofiler-compute/CHANGES rename to projects/rocprofiler-compute/CHANGELOG.md index ceb7547007..310397fe11 100644 --- a/projects/rocprofiler-compute/CHANGES +++ b/projects/rocprofiler-compute/CHANGELOG.md @@ -1,11 +1,20 @@ -Version 2.0.1 (03 Jun 2024) +# Changelog for Omniperf - * new option to force hardware target via OMNIPERF_ARCH_OVERRIDE global (#370) +Full documentation for Omniperf is available at [https://rocm.docs.amd.com/projects/omniperf/en/latest/](https://rocm.docs.amd.com/projects/omniperf/en/latest/). + +## Omniperf 2.0.1 for ROCm 6.2.0 + +### Changes + + * new option to force hardware target via `OMNIPERF_ARCH_OVERRIDE` global (#370) * CI/CD support for MI300 hardware (#373) - * cmake build improvements (#374) * support for MI308X hardware (#375) -Version 2.0.0 (17 May 2024) +### Optimizations + + * cmake build improvements (#374) + +## Omniperf 2.0.0 (17 May 2024) * improved logging than spans all modes (#177) (#317) (#335) (#341) * overhauled CI/CD that spans all modes (#179) @@ -20,7 +29,7 @@ Version 2.0.0 (17 May 2024) * new --quiet option will suppress verbose output and show a progress bar (#308) * roofline support for Ubuntu 22.04 (#319) -Version 1.1.0-PR1 (13 Oct 2023) +## Omniperf 1.1.0-PR1 (13 Oct 2023) * standardize headers to use 'avg' instead of 'mean' * add color code thresholds to standalone gui to match grafana @@ -29,11 +38,11 @@ Version 1.1.0-PR1 (13 Oct 2023) * patch grafana plugin module to address a known issue in the latest version (#186) * enhanced communication between analyze mode kernel flags (#187) -Version 1.0.10 (22 Aug 2023) +## Omniperf 1.0.10 (22 Aug 2023) * critical patch for detection of llvm in rocm installs on SLURM systems -Version 1.0.9 (17 Aug 2023) +## Omniperf 1.0.9 (17 Aug 2023) * add units to L2 per-channel panel (#133) * new quickstart guide for Grafana setup in docs (#135) @@ -45,7 +54,7 @@ Version 1.0.9 (17 Aug 2023) * general metric updates and enhancements (#144, #155, #159) * add min/max/avg breakdown to instruction mix panel (#154) -Version 1.0.8 (30 May 2023) +## Omniperf 1.0.8 (30 May 2023) * add `--kernel-names` option to toggle kernelName overlay in standalone roofline plot (#93) * remove unused python modules (#96) @@ -66,7 +75,7 @@ Version 1.0.8 (30 May 2023) * manually merge rocprof runs, overriding default rocprofiler implementation (#125) * fixed compatibility issues with Python 3.11 (#131) -Version 1.0.8-PR2 (17 Apr 2023) +## Omniperf 1.0.8-PR2 (17 Apr 2023) * ux improvements in standalone GUI (#101) * enhanced readability for filtering dropdowns in standalone GUI (#102) @@ -75,14 +84,14 @@ Version 1.0.8-PR2 (17 Apr 2023) * adding dockerfiles for all supported Linux distros * new examples for `--roof-only` and `--kernel` options added to documentation -Version 1.0.8-PR1 (13 Mar 2023) +## Omniperf 1.0.8-PR1 (13 Mar 2023) * add `--kernel-names` option to toggle kernelName overlay in standalone roofline plot (#93) * remove unused python modules (#96) * fix empirical roofline calculation for single dispatch workloads (#97) * match color of arithmetic intensity points to corresponding bw lines -Version 1.0.7 (21 Feb 2023) +## Omniperf 1.0.7 (21 Feb 2023) * update documentation (#52, #64) * improved detection of invalid command line arguments (#58, #76) @@ -96,12 +105,12 @@ Version 1.0.7 (21 Feb 2023) * improve error message when no GPU(s) detected (#85) * separate CI tests by Linux distro and add status badges -Version 1.0.6 (21 Dec 2022) +## Omniperf 1.0.6 (21 Dec 2022) * CI update: documentation now published via github action (#22) * better error detection for incomplete ROCm installs (#56) -Version 1.0.5 (13 Dec 2022) +## Omniperf 1.0.5 (13 Dec 2022) * store application command-line parameters in profiling output (#27) * enable additional normalizations in CLI mode (#30) @@ -112,7 +121,7 @@ Version 1.0.5 (13 Dec 2022) * enhanced subprocess logging to identify critical errors in rocprofiler (#50) * maintain git sha in production installs from tarball (#53) -Version 1.0.4 (11 Nov 2022) +## Omniperf 1.0.4 (11 Nov 2022) * update python requirements.txt with minimum versions for numpy and pandas * addition of progress bar indicator in web-based GUI (#8) @@ -121,6 +130,6 @@ Version 1.0.4 (11 Nov 2022) * variety of documentation updates * added an optional argument to vcopy.cpp workload example to specify device id -Version 1.0.3 (07 Nov 2022) +## Omniperf 1.0.3 (07 Nov 2022) * initial Omniperf release From 9efb9fd3434e000062ff3bf66dcf7a0d545dc1c2 Mon Sep 17 00:00:00 2001 From: Cole Ramos Date: Fri, 16 Aug 2024 13:09:06 -0500 Subject: [PATCH 06/29] Add omniperf suffix to MOD_INSTALL_PATH in docs (#414) If we don't add the suffix omniperf to the install path then the subsequent instruction of module load omniperf will not work Signed-off-by: coleramos425 [ROCm/rocprofiler-compute commit: 68e2cf09737eb22dadf7cc5cec19963a93b222f8] --- projects/rocprofiler-compute/docs/install/core-install.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/projects/rocprofiler-compute/docs/install/core-install.rst b/projects/rocprofiler-compute/docs/install/core-install.rst index 7629644dc8..8cbb2e0630 100644 --- a/projects/rocprofiler-compute/docs/install/core-install.rst +++ b/projects/rocprofiler-compute/docs/install/core-install.rst @@ -142,7 +142,7 @@ Install from source cd build cmake -DCMAKE_INSTALL_PREFIX=${INSTALL_DIR}/{{ config.version }} \ -DPYTHON_DEPS=${INSTALL_DIR}/python-libs \ - -DMOD_INSTALL_PATH=${INSTALL_DIR}/modulefiles .. + -DMOD_INSTALL_PATH=${INSTALL_DIR}/modulefiles/omniperf .. # install make install From a9935ea9a5bf8d97d3e891b18c0bd0d4df006397 Mon Sep 17 00:00:00 2001 From: coleramos425 Date: Thu, 22 Aug 2024 18:32:16 +0000 Subject: [PATCH 07/29] Rollback Grafana version in Docker container to enable deprecated Angular plugin (#416) Signed-off-by: coleramos425 [ROCm/rocprofiler-compute commit: 2aee85cb06fa68e310ed82e06c0d4dd3d25e30d6] --- projects/rocprofiler-compute/grafana/Dockerfile | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/projects/rocprofiler-compute/grafana/Dockerfile b/projects/rocprofiler-compute/grafana/Dockerfile index 1d08e1753f..2227f487f7 100644 --- a/projects/rocprofiler-compute/grafana/Dockerfile +++ b/projects/rocprofiler-compute/grafana/Dockerfile @@ -18,13 +18,11 @@ ENV NODE_VERSION 20.12.2 ADD plugins/omniperf_plugin /var/lib/grafana/plugins/omniperf_plugin # Install Grafana and MongoDB Community Edition +# Note: Grafana install is stubbed to 10.4.3 RUN apt-get update && \ - apt-get install -y apt-transport-https software-properties-common wget && \ - mkdir -p /etc/apt/keyrings/ && \ - wget -q -O - https://apt.grafana.com/gpg.key | gpg --dearmor | tee /etc/apt/keyrings/grafana.gpg > /dev/null && \ - echo "deb [signed-by=/etc/apt/keyrings/grafana.gpg] https://apt.grafana.com stable main" | tee -a /etc/apt/sources.list.d/grafana.list && \ - apt-get update && \ - apt-get install -y grafana && \ + apt-get install -y adduser libfontconfig1 musl wget && \ + wget -q https://dl.grafana.com/enterprise/release/grafana-enterprise_10.4.3_amd64.deb && \ + dpkg -i grafana-enterprise_10.4.3_amd64.deb && \ apt-get install -y gnupg curl && \ curl -fsSL https://www.mongodb.org/static/pgp/server-7.0.asc | gpg -o /usr/share/keyrings/mongodb-server-7.0.gpg --dearmor && \ echo "deb [ arch=amd64,arm64 signed-by=/usr/share/keyrings/mongodb-server-7.0.gpg ] https://repo.mongodb.org/apt/ubuntu jammy/mongodb-org/7.0 multiverse" | tee /etc/apt/sources.list.d/mongodb-org-7.0.list && \ @@ -72,4 +70,4 @@ RUN sed -i "s/^;http_port = 3000/http_port = 4000/" /etc/grafana/grafana.ini && # Starts mongo and grafana-server at startup COPY docker-entrypoint.sh /docker-entrypoint.sh -ENTRYPOINT [ "/docker-entrypoint.sh" ] +ENTRYPOINT [ "/docker-entrypoint.sh" ] \ No newline at end of file From d99f2c7626cd8bbceed01630da345cae5fa2ccce Mon Sep 17 00:00:00 2001 From: coleramos425 Date: Wed, 28 Aug 2024 16:41:05 +0000 Subject: [PATCH 08/29] Fix typo and CHANGELOG modification After meeting with the DevOps team, I've added the Unreleased keyword to new CHANGELOG section per their request Signed-off-by: coleramos425 [ROCm/rocprofiler-compute commit: bc4d3866838459c45c32ee8ccbc2d6a06fcf5ab7] --- projects/rocprofiler-compute/CHANGELOG.md | 2 +- projects/rocprofiler-compute/src/utils/roofline_calc.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/projects/rocprofiler-compute/CHANGELOG.md b/projects/rocprofiler-compute/CHANGELOG.md index 310397fe11..455c8965fc 100644 --- a/projects/rocprofiler-compute/CHANGELOG.md +++ b/projects/rocprofiler-compute/CHANGELOG.md @@ -2,7 +2,7 @@ Full documentation for Omniperf is available at [https://rocm.docs.amd.com/projects/omniperf/en/latest/](https://rocm.docs.amd.com/projects/omniperf/en/latest/). -## Omniperf 2.0.1 for ROCm 6.2.0 +## (Unreleased) Omniperf 2.0.1 for ROCm 6.2.0 ### Changes diff --git a/projects/rocprofiler-compute/src/utils/roofline_calc.py b/projects/rocprofiler-compute/src/utils/roofline_calc.py index 012884540d..a07c8482a1 100644 --- a/projects/rocprofiler-compute/src/utils/roofline_calc.py +++ b/projects/rocprofiler-compute/src/utils/roofline_calc.py @@ -113,7 +113,7 @@ def calc_ceilings(roofline_parameters, dtype, benchmark_data): peakOps = float(benchmark_data[dtype + "Flops"][roofline_parameters["device_id"]]) for i in range(0, len(cacheHierarchy)): # Plot BW line - console_debug("roofline" "Current cache level is %s" % cacheHierarchy[i]) + console_debug("roofline", "Current cache level is %s" % cacheHierarchy[i]) curr_bw = cacheHierarchy[i] + "Bw" peakBw = float(benchmark_data[curr_bw][roofline_parameters["device_id"]]) From 86b6c772eea2567006839325943ceff181bd727a Mon Sep 17 00:00:00 2001 From: Peter Park Date: Wed, 4 Sep 2024 13:30:40 -0400 Subject: [PATCH 09/29] update package manager install docs to include omniperf in PATH (#420) Signed-off-by: Peter Jun Park [ROCm/rocprofiler-compute commit: ecd69d109bc7afe4336f732559adf31e46685ade] --- .../rocprofiler-compute/docs/install/core-install.rst | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/projects/rocprofiler-compute/docs/install/core-install.rst b/projects/rocprofiler-compute/docs/install/core-install.rst index 8cbb2e0630..f33b976225 100644 --- a/projects/rocprofiler-compute/docs/install/core-install.rst +++ b/projects/rocprofiler-compute/docs/install/core-install.rst @@ -224,6 +224,9 @@ software stack. .. code-block:: shell $ sudo apt install omniperf + # Include omniperf in your system PATH + $ sudo update-alternatives --install /usr/bin/omniperf omniperf /opt/rocm/bin/omniperf 0 + # Install Python dependencies $ python3 -m pip install -r /opt/rocm/libexec/omniperf/requirements.txt .. tab-item:: Red Hat Enterprise Linux @@ -231,6 +234,9 @@ software stack. .. code-block:: shell $ sudo dnf install omniperf + # Include omniperf in your system PATH + $ sudo update-alternatives --install /usr/bin/omniperf omniperf /opt/rocm/bin/omniperf 0 + # Install Python dependencies $ python3 -m pip install -r /opt/rocm/libexec/omniperf/requirements.txt .. tab-item:: SUSE Linux Enterprise Server @@ -238,6 +244,9 @@ software stack. .. code-block:: shell $ sudo zypper install omniperf + # Include omniperf in your system PATH + $ sudo update-alternatives --install /usr/bin/omniperf omniperf /opt/rocm/bin/omniperf 0 + # Install Python dependencies $ python3 -m pip install -r /opt/rocm/libexec/omniperf/requirements.txt .. _core-install-rocprof-var: From 92d8dddb60c82bc13924ac129a1288345a535deb Mon Sep 17 00:00:00 2001 From: Daniel Su Date: Mon, 23 Sep 2024 12:28:23 -0400 Subject: [PATCH 10/29] External CI: enable CI triggers (#426) Signed-off-by: Daniel Su [ROCm/rocprofiler-compute commit: 7ff385a105422a3e8aa7ed8365976af8ffad0db8] --- .../.azuredevops/rocm-ci.yml | 46 +++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100644 projects/rocprofiler-compute/.azuredevops/rocm-ci.yml diff --git a/projects/rocprofiler-compute/.azuredevops/rocm-ci.yml b/projects/rocprofiler-compute/.azuredevops/rocm-ci.yml new file mode 100644 index 0000000000..dad6d85927 --- /dev/null +++ b/projects/rocprofiler-compute/.azuredevops/rocm-ci.yml @@ -0,0 +1,46 @@ +resources: + repositories: + - repository: pipelines_repo + type: github + endpoint: ROCm + name: ROCm/ROCm + +variables: +- group: common +- template: /.azuredevops/variables-global.yml@pipelines_repo + +trigger: + batch: true + branches: + include: + - amd-staging + - amd-mainline + paths: + exclude: + - .github + - docs + - '.*.y*ml' + - '*.md' + - AUTHORS + - LICENSE + - VERSION + +pr: + autoCancel: true + branches: + include: + - amd-staging + - amd-mainline + paths: + exclude: + - .github + - docs + - '.*.y*ml' + - '*.md' + - AUTHORS + - LICENSE + - VERSION + drafts: false + +jobs: + - template: ${{ variables.CI_COMPONENT_PATH }}/omniperf.yml@pipelines_repo From 19e9154d109a6ce182129375b444dbdcd9366900 Mon Sep 17 00:00:00 2001 From: xuchen-amd Date: Tue, 24 Sep 2024 16:53:36 -0400 Subject: [PATCH 11/29] Add the ability to determine GPU model from Chip ID (#423) * Add the ability to determine GPU model from Chip ID for distinguishing MI300 systems by using a built-in dictionary. Signed-off-by: xuchen-amd * Add support for MI300X_A1 Signed-off-by: xuchen-amd * Remove MI308X identification using num CUs, and format Python using black. Signed-off-by: xuchen-amd * Add Read the Docs Signed-off-by: xuchen-amd * Add sphinx requirement Signed-off-by: xuchen-amd * Remove gpu_model identification using gpu_arch Signed-off-by: xuchen-amd * Remove OMNIPERF_ARCH_OVERRIDE and its usage. Determining MI300 gpu model solely based on chip id. Signed-off-by: xuchen-amd * Fix Python formatting using black. Signed-off-by: xuchen-amd --------- Signed-off-by: xuchen-amd [ROCm/rocprofiler-compute commit: c48e6e31cf92a3f09b944e6d245f70d8c34c1db2] --- .../rocprofiler-compute/src/omniperf_base.py | 6 ++++ .../src/omniperf_soc/soc_base.py | 36 +++++-------------- .../rocprofiler-compute/src/utils/specs.py | 7 ++++ 3 files changed, 22 insertions(+), 27 deletions(-) diff --git a/projects/rocprofiler-compute/src/omniperf_base.py b/projects/rocprofiler-compute/src/omniperf_base.py index 39b8494657..50a6cf00ef 100644 --- a/projects/rocprofiler-compute/src/omniperf_base.py +++ b/projects/rocprofiler-compute/src/omniperf_base.py @@ -55,6 +55,12 @@ SUPPORTED_ARCHS = { "gfx942": {"mi300": ["MI300A_A1", "MI300X_A1"]}, } +MI300_CHIP_IDS = { + "29856": "MI300A_A1", + "29857": "MI300X_A1", + "29858": "MI308X", +} + class Omniperf: def __init__(self): diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_base.py b/projects/rocprofiler-compute/src/omniperf_soc/soc_base.py index 446c6a82a5..8a48087269 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_base.py +++ b/projects/rocprofiler-compute/src/omniperf_soc/soc_base.py @@ -34,6 +34,7 @@ from pathlib import Path from collections import OrderedDict from omniperf_base import SUPPORTED_ARCHS +from omniperf_base import MI300_CHIP_IDS class OmniSoC_Base: @@ -100,11 +101,6 @@ class OmniSoC_Base: # assume no SoC specific options and return empty list by default return [] - def check_arch_override(self): - if "OMNIPERF_ARCH_OVERRIDE" in os.environ.keys(): - return os.environ["OMNIPERF_ARCH_OVERRIDE"] - return "" - @demarcate def populate_mspec(self): from utils.specs import search, run, total_sqc, total_xcds @@ -156,6 +152,11 @@ class OmniSoC_Base: self._mspec.workgroup_max_size = key continue + key = search(r"^\s*Chip ID:\s+ ([a-zA-Z0-9]+)\s*", linetext) + if key != None: + self._mspec.chip_id = key + continue + key = search(r"^\s*Max Waves Per CU:\s+ ([a-zA-Z0-9]+)\s*", linetext) if key != None: self._mspec.max_waves_per_cu = key @@ -181,28 +182,9 @@ class OmniSoC_Base: 0 ].upper() if self._mspec.gpu_model == "MI300": - self._mspec.gpu_model = list(SUPPORTED_ARCHS[self._mspec.gpu_arch].values())[ - 0 - ][0] - if self._mspec.gpu_arch == "gfx942": - if ( - "MI300A" in "\n".join(self._mspec._rocminfo) - or "MI300A" in self.check_arch_override() - ): - self._mspec.gpu_model = "MI300A_A1" - elif ( - "MI300X" in "\n".join(self._mspec._rocminfo) - or "MI300X" in self.check_arch_override() - ): - self._mspec.gpu_model = "MI300X_A1" - # We need to distinguish MI308X by peeking reported num CUs - elif self._mspec.cu_per_gpu == "80" or "MI308X" in self.check_arch_override(): - self._mspec.gpu_model = "MI308X" - else: - console_error( - "Cannot parse MI300 details from rocminfo. Please verify output or set the arch using (e.g.,) " - 'export OMNIPERF_ARCH_OVERRIDE="MI300A"' - ) + # Use Chip ID to distinguish MI300 gpu model using the built-in dictionary + if self._mspec.chip_id in MI300_CHIP_IDS: + self._mspec.chip_id = MI300_CHIP_IDS[self._mspec.chip_id] self._mspec.num_xcd = str( total_xcds(self._mspec.gpu_model, self._mspec.compute_partition) diff --git a/projects/rocprofiler-compute/src/utils/specs.py b/projects/rocprofiler-compute/src/utils/specs.py index 02f58489a6..07938bcf18 100644 --- a/projects/rocprofiler-compute/src/utils/specs.py +++ b/projects/rocprofiler-compute/src/utils/specs.py @@ -403,6 +403,13 @@ class MachineSpecs: "name": "Workgroup Max Size", }, ) + chip_id: str = field( + default=None, + metadata={ + "doc": "<>", + "name": "Chip ID", + }, + ) max_waves_per_cu: str = field( default=None, metadata={ From ae0ad6560b5363d7bf749fe9afd49768fb25f2b1 Mon Sep 17 00:00:00 2001 From: Cole Ramos Date: Tue, 24 Sep 2024 14:17:43 -0700 Subject: [PATCH 12/29] Tarball on rocm tags and MAINTAINERS guide (#402) * Package release tarball on rocm tags and add a MAINTAINERS guide to outline release procedure Signed-off-by: coleramos425 * Apply linting feedback Signed-off-by: coleramos425 * Update links in MAINTAINERS for new branches Signed-off-by: coleramos425 * Update MAINTAINERS.md for changelog formatting Signed-off-by: coleramos425 * Update Omniperf ver checker to allow tags with rocm- prefix Signed-off-by: coleramos425 * Add step to packaging workflow to upload release tarball to release Signed-off-by: coleramos425 * Synax change for release name in packaging action Signed-off-by: coleramos425 * Update MAINTAINERS for instuctions on ROCm releases Signed-off-by: coleramos425 * Update softprops pluvin to v2 and remove release name Removing the release name enables us to modify an existing release with the matching tag Signed-off-by: coleramos425 * Remove draft option on softprops plugin Signed-off-by: coleramos425 --------- Signed-off-by: coleramos425 [ROCm/rocprofiler-compute commit: 0d15023f693cd301ef2e0cff755f99b7a3a2d2a2] --- .../.github/workflows/packaging.yml | 17 +++++++++++ projects/rocprofiler-compute/MAINTAINERS.md | 29 +++++++++++++++++++ .../rocprofiler-compute/utils/ver_check.py | 3 ++ 3 files changed, 49 insertions(+) create mode 100644 projects/rocprofiler-compute/MAINTAINERS.md diff --git a/projects/rocprofiler-compute/.github/workflows/packaging.yml b/projects/rocprofiler-compute/.github/workflows/packaging.yml index f1244bcd8b..2b64bbd5d0 100644 --- a/projects/rocprofiler-compute/.github/workflows/packaging.yml +++ b/projects/rocprofiler-compute/.github/workflows/packaging.yml @@ -4,6 +4,7 @@ on: push: tags: - "v[1-9].[0-9]+.[0-9]+*" + - "rocm-[0-9]+.[0-9]+.[0-9]+*" concurrency: group: ${{ github.workflow }}-${{ github.ref }} @@ -42,3 +43,19 @@ jobs: with: name: omniperf-${{github.ref_name}}.tar.gz path: build/omniperf-${{github.ref_name}}.tar.gz + - name: Set version + run: echo "VERSION=$(cat VERSION)" >> $GITHUB_ENV + - name: Determine release name + run: | + if [[ ${{github.ref_name}} == rocm-* ]]; then + echo "RELEASE_NAME=Omniperf ${{ env.VERSION }} for ${{github.ref_name}}" + else + echo "RELEASE_NAME=Omniperf ${{ env.VERSION }}" + fi >> $GITHUB_ENV + - name: Upload tarball Release Asset + uses: softprops/action-gh-release@v2 + if: startsWith(github.ref, 'refs/tags/') && github.repository == 'ROCm/omniperf' + with: + fail_on_unmatched: True + files: | + build/omniperf-${{github.ref_name}}.tar.gz diff --git a/projects/rocprofiler-compute/MAINTAINERS.md b/projects/rocprofiler-compute/MAINTAINERS.md new file mode 100644 index 0000000000..0ee7f23dab --- /dev/null +++ b/projects/rocprofiler-compute/MAINTAINERS.md @@ -0,0 +1,29 @@ +# Maintainers Guide to Omniperf + +## Publishing a release + +Before publishing a new Omniperf release, please review this checklist to ensure all prerequisites are met: + +1) **Ensure [VERSION](VERSION) file is updated** to reflect your desired release version. +2) **Sync `amd-mainline` with `amd-staging`**. A rebase may be required to pull all the desired patches from the development branch to our stable mainline. Click [here](https://github.com/ROCm/omniperf/compare/amd-mainline...amd-staging) to begin that process. +3) **Update [CHANGES](CHANGES)** to reflect all major modifications to the codebase since the last release. When modifying [CHANGES](CHANGES) please ensure formatting is consistent with the rest of the ROCm software stack. See [this template](https://github.com/ROCm/hipTensor/blob/develop/CHANGELOG.md) for reference. +4) **Confirm all CI tests are passing**. You can easily confirm this by peeking the passing status of all GitHub continuous integration tests. +5) **Create a tag from `amd-mainline`**. More information on tagging can be found at [Git Docs - Tagging](https://git-scm.com/book/en/v2/Git-Basics-Tagging). + +> [!NOTE] +Note: A successful tag should trigger the [packaging action](.github/workflows/packaging.yml) which will produce a tarball artifact. **This artifact needs to be included as an asset in your release**. Please find that the [packaging action](.github/workflows/packaging.yml) will automatically create a draft release with your tarball attached. + +Once you've completed the above checklist, you are ready to publish your release. Please ensure you follow formatting from [past Omniperf releases](https://github.com/ROCm/omniperf/releases) for consistency. Some important aspects of our release formatting include: + +- Date of release is included in "Release Title". +- Updates are called out in "Release Description". Updates should mirror those listed in [CHANGES](CHANGES). +- Links to documentation and associated release tarball are called out in "Release Description". +- The tarball artifact from the corresponding tag is added to "Release Assets". + +### Publishing a release for ROCm + +If you are preparing for a new ROCm release, note that the [rocm-ci](https://github.com/rocm-ci) bot managed by DevOps will be triggering a tag automatically. This tag will follow the format `rocm-X.X.X`. + +Traditionally, we will bump the Omniperf [VERSION](VERSION) with a new ROCm release. When we bump the version and reach the prerequisite step (5) above, try tagging with `vX.X.X` to validate the release tarball generated by the [packaging action](.github/workflows/packaging.yml). + +In addition to the prerequisites mentioned above, please make sure that all changes have been merged from `amd-staging` -> `release/rocm-rel-X.X.X` to ensure that the "rocm-ci" bot will capture all your changes. It is easiest to file a single pull request ahead of the ROCm release. diff --git a/projects/rocprofiler-compute/utils/ver_check.py b/projects/rocprofiler-compute/utils/ver_check.py index 13bf9dbab3..c50fcdf265 100755 --- a/projects/rocprofiler-compute/utils/ver_check.py +++ b/projects/rocprofiler-compute/utils/ver_check.py @@ -28,6 +28,9 @@ if repoCheck == tag: elif tag.startswith(repoCheck + "-"): print("OK: allowed match with extra delimiter") exit(0) +elif tag.startswith("rocm-"): + print("OK: allowed match with 'rocm-' prefix") + exit(0) else: print("FAIL: no match - double check top-level VERSION file") exit(1) From 72877f55444c6ae896d11955732425ba7c0d1564 Mon Sep 17 00:00:00 2001 From: cfallows-amd Date: Fri, 27 Sep 2024 17:10:31 -0400 Subject: [PATCH 13/29] Update VERSION, CHANGELOG, and README citation for next release (#433) Signed-off-by: Carrie Fallows [ROCm/rocprofiler-compute commit: ba4429d7453a52aced87ece1909dac6b613f33f9] --- projects/rocprofiler-compute/CHANGELOG.md | 24 ++++++++++++++++++++++- projects/rocprofiler-compute/README.md | 6 +++--- projects/rocprofiler-compute/VERSION | 2 +- 3 files changed, 27 insertions(+), 5 deletions(-) diff --git a/projects/rocprofiler-compute/CHANGELOG.md b/projects/rocprofiler-compute/CHANGELOG.md index 455c8965fc..c6d3edc1cd 100644 --- a/projects/rocprofiler-compute/CHANGELOG.md +++ b/projects/rocprofiler-compute/CHANGELOG.md @@ -2,7 +2,29 @@ Full documentation for Omniperf is available at [https://rocm.docs.amd.com/projects/omniperf/en/latest/](https://rocm.docs.amd.com/projects/omniperf/en/latest/). -## (Unreleased) Omniperf 2.0.1 for ROCm 6.2.0 +## (Unreleased) Omniperf 2.1.0 for ROCm 6.2.2 + +### Changes + + * enable rocprofv1 for MI300 hardware (#391) + * refactoring and updating documemtation (#362, #394, #398, #414, #420) + * branch renaming and workflow updates (#389, #404, #409) + * bug fix for analysis output + * add dependency checks on application launch (#393) + * patch for profiling multi-process/multi-GPU applications (#376, #396) + * packaging updates (#386) + * rename CHANGES to CHANGELOG.md (#410) + * rollback Grafana version in Dockerfile for Angular plugin compatibility (#416) + * enable CI triggers for Azure CI (#426) + * add GPU model distinction for MI300 systems (#423) + * new MAINTAINERS.md guide for omniperf publishing procedures (#402) + +### Optimizations + + * reduced running time of Omniperf when profiling (#384) + * console logging improvements + +## Omniperf 2.0.1 for ROCm 6.2.0 ### Changes diff --git a/projects/rocprofiler-compute/README.md b/projects/rocprofiler-compute/README.md index adbcb9ce3c..c2b696b276 100644 --- a/projects/rocprofiler-compute/README.md +++ b/projects/rocprofiler-compute/README.md @@ -50,11 +50,11 @@ style reference is provided below for convenience: Keith Lowery and Nicholas Curtis and Cristian Di Pietrantonio}, - title = {AMDResearch/omniperf: v2.0.1 (03 June 2024)}, - month = june, + title = {AMDResearch/omniperf: v2.1.0 (27 Sept 2024)}, + month = sept, year = 2024, publisher = {Zenodo}, - version = {v2.0.1}, + version = {v2.1.0}, doi = {10.5281/zenodo.7314631}, url = {https://doi.org/10.5281/zenodo.7314631} } diff --git a/projects/rocprofiler-compute/VERSION b/projects/rocprofiler-compute/VERSION index 38f77a65b3..7ec1d6db40 100644 --- a/projects/rocprofiler-compute/VERSION +++ b/projects/rocprofiler-compute/VERSION @@ -1 +1 @@ -2.0.1 +2.1.0 From 967dc81a87a2b415c15f699d7d616072b1296e62 Mon Sep 17 00:00:00 2001 From: coleramos425 Date: Fri, 27 Sep 2024 21:15:15 +0000 Subject: [PATCH 14/29] Remove unrelease prefix from CHANGELOG Signed-off-by: coleramos425 [ROCm/rocprofiler-compute commit: 5d7af74f85ae0c802d5a4f3f7f61385b47d28b9e] --- projects/rocprofiler-compute/CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/projects/rocprofiler-compute/CHANGELOG.md b/projects/rocprofiler-compute/CHANGELOG.md index c6d3edc1cd..2721d3749e 100644 --- a/projects/rocprofiler-compute/CHANGELOG.md +++ b/projects/rocprofiler-compute/CHANGELOG.md @@ -2,7 +2,7 @@ Full documentation for Omniperf is available at [https://rocm.docs.amd.com/projects/omniperf/en/latest/](https://rocm.docs.amd.com/projects/omniperf/en/latest/). -## (Unreleased) Omniperf 2.1.0 for ROCm 6.2.2 +## Omniperf 2.1.0 for ROCm 6.2.2 ### Changes From b7d4dd023d8d9afb1f35fc981fe53c7024cdd29b Mon Sep 17 00:00:00 2001 From: coleramos425 Date: Mon, 30 Sep 2024 16:45:42 +0000 Subject: [PATCH 15/29] Update issue template Signed-off-by: coleramos425 [ROCm/rocprofiler-compute commit: faaf5bdcfe5c839765bff94b1eb7cfc0c99765bb] --- .../.github/ISSUE_TEMPLATE/bug_report.md | 33 ----- .../.github/ISSUE_TEMPLATE/bug_report.yaml | 131 ++++++++++++++++++ .../.github/ISSUE_TEMPLATE/feature_request.md | 20 --- .../ISSUE_TEMPLATE/feature_request.yaml | 45 ++++++ .../.github/ISSUE_TEMPLATE/question.md | 14 -- .../.github/ISSUE_TEMPLATE/question.yaml | 23 +++ 6 files changed, 199 insertions(+), 67 deletions(-) delete mode 100644 projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.md create mode 100644 projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.yaml delete mode 100644 projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/feature_request.md create mode 100644 projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/feature_request.yaml delete mode 100644 projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/question.md create mode 100644 projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/question.yaml diff --git a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.md b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.md deleted file mode 100644 index 4dec4e1b16..0000000000 --- a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.md +++ /dev/null @@ -1,33 +0,0 @@ ---- -name: Bug report -about: Report a bug you've encountered for further investigation -title: '' -labels: bug -assignees: '' - ---- - -**Describe the bug** -A clear and concise description of what the bug is. - -**Development Environment:** - - Linux Distribution: [e.g. Ubuntu20.04, RHEL8] - - Omniperf Version: [e.g. try `omniperf --version`] - - GPU: [e.g. Mi100, Mi200] - - Custer (if applicable): [e.g. Crusher, ] - -**To Reproduce** -Steps to reproduce the behavior: -1. Run '...' -2. Go to '...' -2. Click on '....' -4. See error - -**Expected behavior** -A clear and concise description of what you expected to happen. - -**Screenshots** -If applicable, add screenshots to help explain your problem. - -**Additional context** -Add any other context about the problem here. diff --git a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.yaml b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.yaml new file mode 100644 index 0000000000..fd42b0ed20 --- /dev/null +++ b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.yaml @@ -0,0 +1,131 @@ +name: Bug Report +description: Report a bug you've encountered for further investigation +title: "[Bug]: " +labels: ["bug", "triage"] +assignees: + - njobypet +body: + - type: markdown + attributes: + value: | + Please complete the following form. + + - type: textarea + id: bug-description + attributes: + label: Describe the bug + description: A clear and concise description of what the bug is. + placeholder: e.g. I found the following error when trying to... + validations: + required: true + + - type: markdown + attributes: + value: | + ## Development Environment + + - type: input + id: linux-distro + attributes: + label: Linux Distribution + description: | + What operating system are you using? Hint: + ```shell + echo "OS:" && cat /etc/os-release | grep -E "^(NAME=|VERSION=)" + ``` + placeholder: e.g. Ubuntu 22.04 + validations: + required: true + + - type: input + id: omniperf-version + attributes: + label: Omniperf Version + description: | + What version of Omniperf are you using? Hint: + ```shell + omniperf --version + ``` + placeholder: e.g. 2.1.0 + validations: + required: true + + - type: input + id: gpu + attributes: + label: GPU + description: | + What GPU(s) did you encounter the issue on? Hint: + ```shell + echo "GPU:" && /opt/rocm/bin/rocminfo | grep -E "^\s*(Name|Marketing Name)" + ``` + placeholder: e.g. AMD MI250, AMD MI300X + validations: + required: true + + - type: input + id: rocm-version + attributes: + label: ROCm Version + description: | + What version(s) of ROCm did you encounter the issue on? Deduce from: + ```shell + readlink -f $(which rocprof) + ``` + placeholder: e.g. ROCm 6.0.2 + + - type: input + id: cluster + attributes: + label: Cluster name (if applicable) + description: What is the name of the cluster you are using? + placeholder: e.g. Frontier, El Capitan, etc. + + - type: markdown + attributes: + value: | + ## To Reproduce + + - type: textarea + id: reproducer + attributes: + label: Reproducer + description: Steps to reproduce the behavior + placeholder: | + 1. Run '...' + 2. Go to '...' + 3. Click on '....' + 4. See error + validations: + required: true + + - type: textarea + id: expected-behav + attributes: + label: Expected behavior + description: A clear and concise description of what you expected to happen. + placeholder: e.g. I expected the following to happen... + + - type: markdown + attributes: + value: | + ## Other + + - type: textarea + id: logs + attributes: + label: Relevant log output + description: Please copy and paste Omniperf's `log.txt` file. This will be automatically formatted into code, so no need for backticks. + render: shell + + - type: textarea + id: screenshots + attributes: + label: Screenshots + description: If applicable, add screenshots to help explain your problem. + + - type: textarea + id: context + attributes: + label: Additional Context + description: Add any other context about the problem here. \ No newline at end of file diff --git a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/feature_request.md b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/feature_request.md deleted file mode 100644 index 11fc491ef1..0000000000 --- a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/feature_request.md +++ /dev/null @@ -1,20 +0,0 @@ ---- -name: Feature request -about: Suggest an idea for this project -title: '' -labels: enhancement -assignees: '' - ---- - -**Is your feature request related to a problem? Please describe.** -A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] - -**Describe the solution you'd like** -A clear and concise description of what you want to happen. - -**Describe alternatives you've considered** -A clear and concise description of any alternative solutions or features you've considered. - -**Additional context** -Add any other context or screenshots about the feature request here. diff --git a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/feature_request.yaml b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/feature_request.yaml new file mode 100644 index 0000000000..d94601b85f --- /dev/null +++ b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/feature_request.yaml @@ -0,0 +1,45 @@ +name: Feature Request +description: Suggest an idea for this project +title: "[Req]: " +labels: ["enhancement", "triage"] +assignees: + - njobypet +body: + - type: markdown + attributes: + value: | + Please complete the following form. + + - type: textarea + id: problem + attributes: + label: Is your feature request related to a problem? + description: A clear and concise description of what the problem is. + placeholder: e.g. I'm always frustrated when... + validations: + required: true + + - type: textarea + id: solution + attributes: + label: Describe the solution you'd like + description: A clear and concise description of what you want to happen. + placeholder: e.g. I propose that... + validations: + required: true + + - type: textarea + id: alternatives + attributes: + label: Describe any alternatives you've considered + description: Walk through your thought process and how you arrived at your solution. + placeholder: | + e.g. Some alternative approaches might be: + 1. ... + 2. ... + + - type: textarea + id: context + attributes: + label: Additional context + description: Add any other context or screenshots about the feature request here. \ No newline at end of file diff --git a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/question.md b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/question.md deleted file mode 100644 index 7429e6325e..0000000000 --- a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/question.md +++ /dev/null @@ -1,14 +0,0 @@ ---- -name: Question -about: 'Clarifying questions and uncertainties ' -title: '' -labels: question -assignees: '' - ---- - -**Describe your question** -A clear and concise description of your question and how it came up. - -**Additional context** -Add any other context or screenshots about the question here. diff --git a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/question.yaml b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/question.yaml new file mode 100644 index 0000000000..03595df99b --- /dev/null +++ b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/question.yaml @@ -0,0 +1,23 @@ +name: Question +description: Clarifying questions and uncertainties +labels: ["question"] +body: + - type: markdown + attributes: + value: | + Please complete the following form. + + - type: textarea + id: question + attributes: + label: Describe your question + description: A clear and concise description of your question and how it came up. + placeholder: I was unsure how to ... + validations: + required: true + + - type: textarea + id: context + attributes: + label: Additional context + description: Add any other context or screenshots about the question here. \ No newline at end of file From 83de3f34ae67f2eb816a528d82584a18beb8a25b Mon Sep 17 00:00:00 2001 From: Cole Ramos Date: Tue, 1 Oct 2024 14:59:38 -0500 Subject: [PATCH 16/29] Add smart name and notes to triggered releases (#438) Signed-off-by: coleramos425 [ROCm/rocprofiler-compute commit: c8a1add54b62751fd580c2258db8cbd94c30edaf] --- projects/rocprofiler-compute/.github/workflows/packaging.yml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/projects/rocprofiler-compute/.github/workflows/packaging.yml b/projects/rocprofiler-compute/.github/workflows/packaging.yml index 2b64bbd5d0..2bf3e8f069 100644 --- a/projects/rocprofiler-compute/.github/workflows/packaging.yml +++ b/projects/rocprofiler-compute/.github/workflows/packaging.yml @@ -57,5 +57,9 @@ jobs: if: startsWith(github.ref, 'refs/tags/') && github.repository == 'ROCm/omniperf' with: fail_on_unmatched: True + generate_release_notes: True + draft: False # toggle for debugging files: | build/omniperf-${{github.ref_name}}.tar.gz + name: ${{ env.RELEASE_NAME }} + From 4da8b0dc4604a55621d350f2ee9f2f11eb6754da Mon Sep 17 00:00:00 2001 From: Ben Richard <143630488+benrichard-amd@users.noreply.github.com> Date: Thu, 3 Oct 2024 11:27:55 -0400 Subject: [PATCH 17/29] Skip output lines that have UTF8 decoding error (#441) * Avoid crash if non-UTF8 character is encountered in output Signed-off-by: benrichard-amd * Ignore lines with non-UTF-8 characters. Do not print error. Signed-off-by: benrichard-amd * Remove trailing whitespace Signed-off-by: benrichard-amd --------- Signed-off-by: benrichard-amd [ROCm/rocprofiler-compute commit: fb210abcd0133586b0b96bbb99678b6ea8491ef0] --- .../rocprofiler-compute/src/utils/utils.py | 20 +++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/projects/rocprofiler-compute/src/utils/utils.py b/projects/rocprofiler-compute/src/utils/utils.py index a4b1a10b33..4175fdab2e 100644 --- a/projects/rocprofiler-compute/src/utils/utils.py +++ b/projects/rocprofiler-compute/src/utils/utils.py @@ -205,14 +205,18 @@ def capture_subprocess_output(subprocess_args, new_env=None, profileMode=False): buf = io.StringIO() def handle_output(stream, mask): - # Because the process' output is line buffered, there's only ever one - # line to read when this function is called - line = stream.readline() - buf.write(line) - if profileMode: - console_log(rocprof_cmd, line.strip(), indent_level=1) - else: - console_log(line.strip()) + try: + # Because the process' output is line buffered, there's only ever one + # line to read when this function is called + line = stream.readline() + buf.write(line) + if profileMode: + console_log(rocprof_cmd, line.strip(), indent_level=1) + else: + console_log(line.strip()) + except UnicodeDecodeError: + # Skip this line + pass # Register callback for an "available for read" event from subprocess' stdout stream selector = selectors.DefaultSelector() From a83747166a05ad2222810706bee9793e0b89fda6 Mon Sep 17 00:00:00 2001 From: vstempen <147086176+vstempen@users.noreply.github.com> Date: Mon, 7 Oct 2024 15:53:48 -0400 Subject: [PATCH 18/29] Documented Docker container OpenSSL abilities being affected by Host network proxy services (#440) * Documented Docker container OpenSSL abilities being affected by host network proxy services, causing network certificates verification problem during Docker container build stage of Grafana server setup. Signed-off-by: Vladimir Stempen * Update docs/install/grafana-setup.rst Co-authored-by: Peter Park Signed-off-by: vstempen <147086176+vstempen@users.noreply.github.com> --------- Signed-off-by: Vladimir Stempen Signed-off-by: vstempen <147086176+vstempen@users.noreply.github.com> Co-authored-by: Peter Park [ROCm/rocprofiler-compute commit: ba94cb8370e47f1a4a1e4ffc107359fe6677827d] --- .../rocprofiler-compute/docs/install/grafana-setup.rst | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/projects/rocprofiler-compute/docs/install/grafana-setup.rst b/projects/rocprofiler-compute/docs/install/grafana-setup.rst index a7486d286d..39dca6e888 100644 --- a/projects/rocprofiler-compute/docs/install/grafana-setup.rst +++ b/projects/rocprofiler-compute/docs/install/grafana-setup.rst @@ -79,6 +79,13 @@ directory to begin. $ sudo docker-compose build $ sudo docker-compose up -d +.. note:: + + To troubleshoot Docker container build failures related to certificate verification, try + disabling any network proxy services on the host system. These proxy services can interfere + with OpenSSL's ability to retrieve a correct certificate chain when the container accesses + external websites. + The TCP ports for Grafana (``4000``) and MongoDB (``27017``) in the Docker container are mapped to ``14000`` and ``27018``, respectively, on the host side. From 38df31b863f543425b99387394da5c0d0c1287f4 Mon Sep 17 00:00:00 2001 From: coleramos425 Date: Fri, 11 Oct 2024 20:25:43 +0000 Subject: [PATCH 19/29] Update CODEOWNERS for product team Signed-off-by: coleramos425 [ROCm/rocprofiler-compute commit: e633d17372546152e4e3fd93e267b42886003a0a] --- projects/rocprofiler-compute/.github/CODEOWNERS | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/projects/rocprofiler-compute/.github/CODEOWNERS b/projects/rocprofiler-compute/.github/CODEOWNERS index 56098b9c73..effb470abb 100644 --- a/projects/rocprofiler-compute/.github/CODEOWNERS +++ b/projects/rocprofiler-compute/.github/CODEOWNERS @@ -1,7 +1,13 @@ -* @koomie @coleramos425 +* @coleramos425 @feizheng10 @dgaliffiAMD # Documentation files docs/ @ROCm/rocm-documentation *.md @ROCm/rocm-documentation *.rst @ROCm/rocm-documentation .readthedocs.yaml @ROCm/rocm-documentation + +# Packaging +cmake/ @koomie +tests/ @koomie +CMakeLists.txt @koomie +utils/ @koomie \ No newline at end of file From 6b0195f83e549daaa9daf953a79608a392281fc8 Mon Sep 17 00:00:00 2001 From: Ben Richard <143630488+benrichard-amd@users.noreply.github.com> Date: Wed, 16 Oct 2024 15:41:11 -0400 Subject: [PATCH 20/29] Use MI300 chip_id instead of model to detect XCD count (#448) In a previous change we started using "MI300" for gpu_model instead of the full "MI300X_A0" or "MI300X_A1", etc. The XCD detection code was using gpu_model and expecting the full name, causing the XCD count = 1. Passing chip_id fixes the issue. Signed-off-by: benrichard-amd [ROCm/rocprofiler-compute commit: a236fe0412194a18bdb9ce0dbe609ce8255b2129] --- projects/rocprofiler-compute/src/omniperf_soc/soc_base.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_base.py b/projects/rocprofiler-compute/src/omniperf_soc/soc_base.py index 8a48087269..db8ce9a224 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_base.py +++ b/projects/rocprofiler-compute/src/omniperf_soc/soc_base.py @@ -187,7 +187,7 @@ class OmniSoC_Base: self._mspec.chip_id = MI300_CHIP_IDS[self._mspec.chip_id] self._mspec.num_xcd = str( - total_xcds(self._mspec.gpu_model, self._mspec.compute_partition) + total_xcds(self._mspec.chip_id, self._mspec.compute_partition) ) @demarcate From e188429f060f55af3eff1fcad29585871b666cec Mon Sep 17 00:00:00 2001 From: Ossian O'Reilly Date: Mon, 21 Oct 2024 09:10:12 -0700 Subject: [PATCH 21/29] Change argparser help from '--list-kernels' (deprecated) to '--list-stats'. (#449) Signed-off-by: OReilly, Ossian [ROCm/rocprofiler-compute commit: 5f3c0f04298f487cbe166466f2609cff5b153e07] --- projects/rocprofiler-compute/src/argparser.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/projects/rocprofiler-compute/src/argparser.py b/projects/rocprofiler-compute/src/argparser.py index 1e02a849f7..0b15043157 100644 --- a/projects/rocprofiler-compute/src/argparser.py +++ b/projects/rocprofiler-compute/src/argparser.py @@ -416,7 +416,7 @@ Examples: dest="gpu_kernel", nargs="+", action="append", - help="\t\tSpecify kernel id(s) from --list-kernels for filtering.", + help="\t\tSpecify kernel id(s) from --list-stats for filtering.", ) analyze_group.add_argument( "-d", From 3328cf8d6c2c564f2674327bd0f0f79949c0dd3b Mon Sep 17 00:00:00 2001 From: zichguan-amd Date: Thu, 24 Oct 2024 13:00:36 -0400 Subject: [PATCH 22/29] Enable baseline comparison between workloads from the same path (#447) * Enable baseline comparison between workloads from the same path Signed-off-by: zichguan-amd * Formatting Signed-off-by: zichguan-amd * Change test to verify baseline works with same path Signed-off-by: zichguan-amd * Add three-way comparison test case Signed-off-by: zichguan-amd --------- Signed-off-by: zichguan-amd [ROCm/rocprofiler-compute commit: 13a06f51318c7862858ae90957263d7f1e93d035] --- .../src/omniperf_analyze/analysis_base.py | 25 +- .../src/omniperf_analyze/analysis_cli.py | 22 +- .../src/omniperf_analyze/analysis_webui.py | 16 +- .../tests/test_analyze_commands.py | 50 +++- .../multikernel/MI200/SQ_IFETCH_LEVEL.csv | 8 + .../multikernel/MI200/SQ_INST_LEVEL_LDS.csv | 8 + .../multikernel/MI200/SQ_INST_LEVEL_SMEM.csv | 8 + .../multikernel/MI200/SQ_INST_LEVEL_VMEM.csv | 8 + .../multikernel/MI200/SQ_LEVEL_WAVES.csv | 8 + .../tests/workloads/multikernel/MI200/log.txt | 270 ++++++++++++++++++ .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 + .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 + .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 + .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 + .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 + .../multikernel/MI200/perfmon/pmc_perf_0.txt | 5 + .../multikernel/MI200/perfmon/pmc_perf_1.txt | 5 + .../multikernel/MI200/perfmon/pmc_perf_2.txt | 5 + .../multikernel/MI200/perfmon/pmc_perf_3.txt | 5 + .../multikernel/MI200/perfmon/pmc_perf_4.txt | 5 + .../multikernel/MI200/perfmon/pmc_perf_5.txt | 5 + .../multikernel/MI200/perfmon/pmc_perf_6.txt | 5 + .../multikernel/MI200/perfmon/pmc_perf_7.txt | 5 + .../multikernel/MI200/perfmon/pmc_perf_8.txt | 5 + .../multikernel/MI200/perfmon/pmc_perf_9.txt | 5 + .../multikernel/MI200/perfmon/timestamps.txt | 5 + .../multikernel/MI200/pmc_dispatch_info.csv | 8 + .../workloads/multikernel/MI200/pmc_perf.csv | 8 + .../workloads/multikernel/MI200/roofline.csv | 4 + .../workloads/multikernel/MI200/sysinfo.csv | 2 + .../multikernel/MI200/timestamps.csv | 8 + 31 files changed, 492 insertions(+), 41 deletions(-) create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_IFETCH_LEVEL.csv create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_LDS.csv create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_SMEM.csv create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_VMEM.csv create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_LEVEL_WAVES.csv create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/log.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_LEVEL_WAVES.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_0.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_1.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_2.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_3.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_4.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_5.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_6.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_7.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_8.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_9.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/timestamps.txt create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_dispatch_info.csv create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_perf.csv create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/roofline.csv create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/sysinfo.csv create mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/timestamps.csv diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_base.py b/projects/rocprofiler-compute/src/omniperf_analyze/analysis_base.py index c80489972d..eb0a67225d 100644 --- a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_base.py +++ b/projects/rocprofiler-compute/src/omniperf_analyze/analysis_base.py @@ -151,7 +151,7 @@ class OmniAnalyze_Base: self.load_options(normalization_filter) - for d in self.__args.path: + for i, d in enumerate(self.__args.path): w = schema.Workload() w.sys_info = file_io.load_sys_info(Path(d[0], "sysinfo.csv")) arch = w.sys_info.iloc[0]["gpu_arch"] @@ -161,7 +161,7 @@ class OmniAnalyze_Base: w.avail_ips = w.sys_info["ip_blocks"].item().split("|") w.dfs = copy.deepcopy(self._arch_configs[arch].dfs) w.dfs_type = self._arch_configs[arch].dfs_type - self._runs[d[0]] = w + self._runs[i] = w return self._runs @@ -184,15 +184,6 @@ class OmniAnalyze_Base: # validate profiling data is_workload_empty(dir[0]) - # no using same paths - occurances = set() - for dir in self.__args.path: - dir = dir[0] - if dir in occurances: - console_error("You cannot provide the same path twice.") - else: - occurances.add(dir) - # ---------------------------------------------------- # Required methods to be implemented by child classes # ---------------------------------------------------- @@ -211,20 +202,20 @@ class OmniAnalyze_Base: # set filters if self.__args.gpu_kernel: - for d, gk in zip(self.__args.path, self.__args.gpu_kernel): - self._runs[d[0]].filter_kernel_ids = gk + for i, gk in enumerate(self.__args.gpu_kernel): + self._runs[i].filter_kernel_ids = gk if self.__args.gpu_id: if len(self.__args.gpu_id) == 1 and len(self.__args.path) != 1: for i in range(len(self.__args.path) - 1): self.__args.gpu_id.extend(self.__args.gpu_id) - for d, gi in zip(self.__args.path, self.__args.gpu_id): - self._runs[d[0]].filter_gpu_ids = gi + for i, gi in enumerate(self.__args.gpu_id): + self._runs[i].filter_gpu_ids = gi if self.__args.gpu_dispatch_id: if len(self.__args.gpu_dispatch_id) == 1 and len(self.__args.path) != 1: for i in range(len(self.__args.path) - 1): self.__args.gpu_dispatch_id.extend(self.__args.gpu_dispatch_id) - for d, gd in zip(self.__args.path, self.__args.gpu_dispatch_id): - self._runs[d[0]].filter_dispatch_ids = gd + for i, gd in enumerate(self.__args.gpu_dispatch_id): + self._runs[i].filter_dispatch_ids = gd @abstractmethod def run_analysis(self): diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_cli.py b/projects/rocprofiler-compute/src/omniperf_analyze/analysis_cli.py index 36fbbf8c5a..549653c62c 100644 --- a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_cli.py +++ b/projects/rocprofiler-compute/src/omniperf_analyze/analysis_cli.py @@ -38,27 +38,25 @@ class cli_analysis(OmniAnalyze_Base): super().pre_processing() if self.get_args().random_port: console_error("--gui flag is required to enable --random-port") - for d in self.get_args().path: + for i, d in enumerate(self.get_args().path): file_io.create_df_kernel_top_stats( raw_data_dir=d[0], - filter_gpu_ids=self._runs[d[0]].filter_gpu_ids, - filter_dispatch_ids=self._runs[d[0]].filter_dispatch_ids, + filter_gpu_ids=self._runs[i].filter_gpu_ids, + filter_dispatch_ids=self._runs[i].filter_dispatch_ids, time_unit=self.get_args().time_unit, max_stat_num=self.get_args().max_stat_num, kernel_verbose=self.get_args().kernel_verbose, ) # create 'mega dataframe' - self._runs[d[0]].raw_pmc = file_io.create_df_pmc( + self._runs[i].raw_pmc = file_io.create_df_pmc( d[0], self.get_args().kernel_verbose, self.get_args().verbose ) # demangle and overwrite original 'Kernel_Name' - kernel_name_shortener( - self._runs[d[0]].raw_pmc, self.get_args().kernel_verbose - ) + kernel_name_shortener(self._runs[i].raw_pmc, self.get_args().kernel_verbose) # create the loaded table parser.load_table_data( - workload=self._runs[d[0]], + workload=self._runs[i], dir=d[0], is_gui=False, debug=self.get_args().debug, @@ -73,17 +71,13 @@ class cli_analysis(OmniAnalyze_Base): tty.show_kernel_stats( self.get_args(), self._runs, - self._arch_configs[ - self._runs[self.get_args().path[0][0]].sys_info.iloc[0]["gpu_arch"] - ], + self._arch_configs[self._runs[0].sys_info.iloc[0]["gpu_arch"]], self._output, ) else: tty.show_all( self.get_args(), self._runs, - self._arch_configs[ - self._runs[self.get_args().path[0][0]].sys_info.iloc[0]["gpu_arch"] - ], + self._arch_configs[self._runs[0].sys_info.iloc[0]["gpu_arch"]], self._output, ) diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_webui.py b/projects/rocprofiler-compute/src/omniperf_analyze/analysis_webui.py index 54645cbbba..bdf7ff782b 100644 --- a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_webui.py +++ b/projects/rocprofiler-compute/src/omniperf_analyze/analysis_webui.py @@ -274,20 +274,20 @@ class webui_analysis(OmniAnalyze_Base): args = self.get_args() file_io.create_df_kernel_top_stats( raw_data_dir=self.dest_dir, - filter_gpu_ids=self._runs[self.dest_dir].filter_gpu_ids, - filter_dispatch_ids=self._runs[self.dest_dir].filter_dispatch_ids, + filter_gpu_ids=self._runs[0].filter_gpu_ids, + filter_dispatch_ids=self._runs[0].filter_dispatch_ids, time_unit=args.time_unit, max_stat_num=args.max_stat_num, kernel_verbose=self.get_args().kernel_verbose, ) # create 'mega dataframe' - self._runs[self.dest_dir].raw_pmc = file_io.create_df_pmc( + self._runs[0].raw_pmc = file_io.create_df_pmc( self.dest_dir, self.get_args().kernel_verbose, args.verbose ) # create the loaded kernel stats - parser.load_kernel_top(self._runs[self.dest_dir], self.dest_dir) + parser.load_kernel_top(self._runs[0], self.dest_dir) # set architecture - self.arch = self._runs[self.dest_dir].sys_info.iloc[0]["gpu_arch"] + self.arch = self._runs[0].sys_info.iloc[0]["gpu_arch"] else: console_error( @@ -300,9 +300,9 @@ class webui_analysis(OmniAnalyze_Base): super().run_analysis() args = self.get_args() input_filters = { - "kernel": self._runs[self.dest_dir].filter_kernel_ids, - "gpu": self._runs[self.dest_dir].filter_gpu_ids, - "dispatch": self._runs[self.dest_dir].filter_dispatch_ids, + "kernel": self._runs[0].filter_kernel_ids, + "gpu": self._runs[0].filter_gpu_ids, + "dispatch": self._runs[0].filter_dispatch_ids, "normalization": args.normal_unit, "top_n": args.max_stat_num, } diff --git a/projects/rocprofiler-compute/tests/test_analyze_commands.py b/projects/rocprofiler-compute/tests/test_analyze_commands.py index 5a0e7aec81..303e60b0a9 100644 --- a/projects/rocprofiler-compute/tests/test_analyze_commands.py +++ b/projects/rocprofiler-compute/tests/test_analyze_commands.py @@ -1136,7 +1136,7 @@ def test_baseline(): ], ): omniperf.main() - assert e.value.code == 1 + assert e.value.code == 0 with pytest.raises(SystemExit) as e: with patch( @@ -1151,7 +1151,53 @@ def test_baseline(): ], ): omniperf.main() - assert e.value.code == 1 + assert e.value.code == 0 + + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + [ + "omniperf", + "analyze", + "--path", + "tests/workloads/multikernel/MI200", + "-k", + "0", + "--path", + "tests/workloads/multikernel/MI200", + "-k", + "1", + "--path", + "tests/workloads/multikernel/MI200", + "-k", + "2", + ], + ): + omniperf.main() + assert e.value.code == 0 + + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + [ + "omniperf", + "analyze", + "--path", + "tests/workloads/multikernel/MI200", + "-k", + "0", + "--path", + "tests/workloads/multikernel/MI200", + "-k", + "1", + "--path", + "tests/workloads/vcopy/MI100", + "-k", + "0", + ], + ): + omniperf.main() + assert e.value.code == 0 @pytest.mark.misc diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_IFETCH_LEVEL.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..cb500c7561 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,8 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TCC_CYCLE[0],TCC_RW_REQ[0],TCC_HIT[0],TCC_MISS[0],TCC_CYCLE[1],TCC_RW_REQ[1],TCC_HIT[1],TCC_MISS[1],TCC_CYCLE[2],TCC_RW_REQ[2],TCC_HIT[2],TCC_MISS[2],TCC_CYCLE[3],TCC_RW_REQ[3],TCC_HIT[3],TCC_MISS[3],TCC_CYCLE[4],TCC_RW_REQ[4],TCC_HIT[4],TCC_MISS[4],TCC_CYCLE[5],TCC_RW_REQ[5],TCC_HIT[5],TCC_MISS[5],TCC_CYCLE[6],TCC_RW_REQ[6],TCC_HIT[6],TCC_MISS[6],TCC_CYCLE[7],TCC_RW_REQ[7],TCC_HIT[7],TCC_MISS[7],TCC_CYCLE[8],TCC_RW_REQ[8],TCC_HIT[8],TCC_MISS[8],TCC_CYCLE[9],TCC_RW_REQ[9],TCC_HIT[9],TCC_MISS[9],TCC_CYCLE[10],TCC_RW_REQ[10],TCC_HIT[10],TCC_MISS[10],TCC_CYCLE[11],TCC_RW_REQ[11],TCC_HIT[11],TCC_MISS[11],TCC_CYCLE[12],TCC_RW_REQ[12],TCC_HIT[12],TCC_MISS[12],TCC_CYCLE[13],TCC_RW_REQ[13],TCC_HIT[13],TCC_MISS[13],TCC_CYCLE[14],TCC_RW_REQ[14],TCC_HIT[14],TCC_MISS[14],TCC_CYCLE[15],TCC_RW_REQ[15],TCC_HIT[15],TCC_MISS[15],TCC_CYCLE[16],TCC_RW_REQ[16],TCC_HIT[16],TCC_MISS[16],TCC_CYCLE[17],TCC_RW_REQ[17],TCC_HIT[17],TCC_MISS[17],TCC_CYCLE[18],TCC_RW_REQ[18],TCC_HIT[18],TCC_MISS[18],TCC_CYCLE[19],TCC_RW_REQ[19],TCC_HIT[19],TCC_MISS[19],TCC_CYCLE[20],TCC_RW_REQ[20],TCC_HIT[20],TCC_MISS[20],TCC_CYCLE[21],TCC_RW_REQ[21],TCC_HIT[21],TCC_MISS[21],TCC_CYCLE[22],TCC_RW_REQ[22],TCC_HIT[22],TCC_MISS[22],TCC_CYCLE[23],TCC_RW_REQ[23],TCC_HIT[23],TCC_MISS[23],TCC_CYCLE[24],TCC_RW_REQ[24],TCC_HIT[24],TCC_MISS[24],TCC_CYCLE[25],TCC_RW_REQ[25],TCC_HIT[25],TCC_MISS[25],TCC_CYCLE[26],TCC_RW_REQ[26],TCC_HIT[26],TCC_MISS[26],TCC_CYCLE[27],TCC_RW_REQ[27],TCC_HIT[27],TCC_MISS[27],TCC_CYCLE[28],TCC_RW_REQ[28],TCC_HIT[28],TCC_MISS[28],TCC_CYCLE[29],TCC_RW_REQ[29],TCC_HIT[29],TCC_MISS[29],TCC_CYCLE[30],TCC_RW_REQ[30],TCC_HIT[30],TCC_MISS[30],TCC_CYCLE[31],TCC_RW_REQ[31],TCC_HIT[31],TCC_MISS[31],CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,GRBM_COUNT,GRBM_GUI_ACTIVE,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789017,789017,256,256,0,0,12,4,32,64,0x0,0x7fc39b83d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,15492,15492,9586176074970,9595697581667,9595697588067,9586194080958 +1,"global_write(int*, int) [clone .kd]",2,0,1,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b805200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,14214,14214,9586194431757,9595697981345,9595697983585,9586195534149 +2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789017,789017,1,1,4096,0,4,4,48,64,0x0,0x7fc39b805240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16792,16792,9586194965600,9595697989025,9595697991265,9586196424752 +3,"global_read(int*, int) [clone .kd]",2,0,3,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b805280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,17066,17066,9586195545500,9595698033025,9595698035745,9586197503640 +4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b8052c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16835,16835,9586196089011,9595698039905,9595698042305,9586198594409 +5,"global_atomic(int*, int) [clone .kd]",2,0,5,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b805300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16490,16490,9586196678469,9595698072385,9595698076225,9586199643230 +6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789017,789017,1,1,4096,0,4,4,48,64,0x0,0x7fc39b805340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,17235,17235,9586197190792,9595698076225,9595698080065,9586200731796 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_LDS.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_LDS.csv new file mode 100644 index 0000000000..1a975cb385 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_LDS.csv @@ -0,0 +1,8 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TCC_REQ[0],TCC_READ[0],TCC_WRITE[0],TCC_ATOMIC[0],TCC_REQ[1],TCC_READ[1],TCC_WRITE[1],TCC_ATOMIC[1],TCC_REQ[2],TCC_READ[2],TCC_WRITE[2],TCC_ATOMIC[2],TCC_REQ[3],TCC_READ[3],TCC_WRITE[3],TCC_ATOMIC[3],TCC_REQ[4],TCC_READ[4],TCC_WRITE[4],TCC_ATOMIC[4],TCC_REQ[5],TCC_READ[5],TCC_WRITE[5],TCC_ATOMIC[5],TCC_REQ[6],TCC_READ[6],TCC_WRITE[6],TCC_ATOMIC[6],TCC_REQ[7],TCC_READ[7],TCC_WRITE[7],TCC_ATOMIC[7],TCC_REQ[8],TCC_READ[8],TCC_WRITE[8],TCC_ATOMIC[8],TCC_REQ[9],TCC_READ[9],TCC_WRITE[9],TCC_ATOMIC[9],TCC_REQ[10],TCC_READ[10],TCC_WRITE[10],TCC_ATOMIC[10],TCC_REQ[11],TCC_READ[11],TCC_WRITE[11],TCC_ATOMIC[11],TCC_REQ[12],TCC_READ[12],TCC_WRITE[12],TCC_ATOMIC[12],TCC_REQ[13],TCC_READ[13],TCC_WRITE[13],TCC_ATOMIC[13],TCC_REQ[14],TCC_READ[14],TCC_WRITE[14],TCC_ATOMIC[14],TCC_REQ[15],TCC_READ[15],TCC_WRITE[15],TCC_ATOMIC[15],TCC_REQ[16],TCC_READ[16],TCC_WRITE[16],TCC_ATOMIC[16],TCC_REQ[17],TCC_READ[17],TCC_WRITE[17],TCC_ATOMIC[17],TCC_REQ[18],TCC_READ[18],TCC_WRITE[18],TCC_ATOMIC[18],TCC_REQ[19],TCC_READ[19],TCC_WRITE[19],TCC_ATOMIC[19],TCC_REQ[20],TCC_READ[20],TCC_WRITE[20],TCC_ATOMIC[20],TCC_REQ[21],TCC_READ[21],TCC_WRITE[21],TCC_ATOMIC[21],TCC_REQ[22],TCC_READ[22],TCC_WRITE[22],TCC_ATOMIC[22],TCC_REQ[23],TCC_READ[23],TCC_WRITE[23],TCC_ATOMIC[23],TCC_REQ[24],TCC_READ[24],TCC_WRITE[24],TCC_ATOMIC[24],TCC_REQ[25],TCC_READ[25],TCC_WRITE[25],TCC_ATOMIC[25],TCC_REQ[26],TCC_READ[26],TCC_WRITE[26],TCC_ATOMIC[26],TCC_REQ[27],TCC_READ[27],TCC_WRITE[27],TCC_ATOMIC[27],TCC_REQ[28],TCC_READ[28],TCC_WRITE[28],TCC_ATOMIC[28],TCC_REQ[29],TCC_READ[29],TCC_WRITE[29],TCC_ATOMIC[29],TCC_REQ[30],TCC_READ[30],TCC_WRITE[30],TCC_ATOMIC[30],TCC_REQ[31],TCC_READ[31],TCC_WRITE[31],TCC_ATOMIC[31],CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,GRBM_SPI_BUSY,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789206,789206,256,256,0,0,12,4,32,64,0x0,0x7f092c135800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,7832,9586813518158,9595697581667,9595697588067,9586831878942 +1,"global_write(int*, int) [clone .kd]",2,0,1,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f9200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,4807,9586832277231,9595697981345,9595697983585,9586833234169 +2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789206,789206,1,1,4096,0,4,4,48,64,0x0,0x7f092c0f9240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6147,9586832819029,9595697989025,9595697991265,9586834206386 +3,"global_read(int*, int) [clone .kd]",2,0,3,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f9280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6439,9586833482506,9595698033025,9595698035745,9586835298047 +4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f92c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6821,9586834006330,9595698039905,9595698042305,9586836377766 +5,"global_atomic(int*, int) [clone .kd]",2,0,5,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f9300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6708,9586834769875,9595698072385,9595698076225,9586837446956 +6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789206,789206,1,1,4096,0,4,4,48,64,0x0,0x7f092c0f9340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,7838,9586835336510,9595698076225,9595698080065,9586838514602 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_SMEM.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_SMEM.csv new file mode 100644 index 0000000000..8eae1c5875 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_SMEM.csv @@ -0,0 +1,8 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789393,789393,256,256,0,0,12,4,32,64,0x0,0x7f96ea49d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587521927328,9595697581667,9595697588067,9587540188696 +1,"global_write(int*, int) [clone .kd]",2,0,1,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea465200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587540565083,9595697981345,9595697983585,9587541639562 +2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789393,789393,1,1,4096,0,4,4,48,64,0x0,0x7f96ea465240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587541115507,9595697989025,9595697991265,9587542609585 +3,"global_read(int*, int) [clone .kd]",2,0,3,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea465280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587541696489,9595698033025,9595698035745,9587543620214 +4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea4652c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587542237877,9595698039905,9595698042305,9587544716895 +5,"global_atomic(int*, int) [clone .kd]",2,0,5,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea465300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587542873531,9595698072385,9595698076225,9587545756779 +6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789393,789393,1,1,4096,0,4,4,48,64,0x0,0x7f96ea465340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587543404819,9595698076225,9595698080065,9587546843111 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_VMEM.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_VMEM.csv new file mode 100644 index 0000000000..c4c4af793c --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_VMEM.csv @@ -0,0 +1,8 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCC_EA_ATOMIC[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_ATOMIC_LEVEL[0],TCC_EA_ATOMIC[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_ATOMIC_LEVEL[1],TCC_EA_ATOMIC[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_ATOMIC_LEVEL[2],TCC_EA_ATOMIC[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_ATOMIC_LEVEL[3],TCC_EA_ATOMIC[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_ATOMIC_LEVEL[4],TCC_EA_ATOMIC[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_ATOMIC_LEVEL[5],TCC_EA_ATOMIC[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_ATOMIC_LEVEL[6],TCC_EA_ATOMIC[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_ATOMIC_LEVEL[7],TCC_EA_ATOMIC[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_ATOMIC_LEVEL[8],TCC_EA_ATOMIC[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_ATOMIC_LEVEL[9],TCC_EA_ATOMIC[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_ATOMIC_LEVEL[10],TCC_EA_ATOMIC[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_ATOMIC_LEVEL[11],TCC_EA_ATOMIC[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_ATOMIC_LEVEL[12],TCC_EA_ATOMIC[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_ATOMIC_LEVEL[13],TCC_EA_ATOMIC[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_ATOMIC_LEVEL[14],TCC_EA_ATOMIC[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_ATOMIC_LEVEL[15],TCC_EA_ATOMIC[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_ATOMIC_LEVEL[16],TCC_EA_ATOMIC[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_ATOMIC_LEVEL[17],TCC_EA_ATOMIC[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_ATOMIC_LEVEL[18],TCC_EA_ATOMIC[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_ATOMIC_LEVEL[19],TCC_EA_ATOMIC[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_ATOMIC_LEVEL[20],TCC_EA_ATOMIC[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_ATOMIC_LEVEL[21],TCC_EA_ATOMIC[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_ATOMIC_LEVEL[22],TCC_EA_ATOMIC[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_ATOMIC_LEVEL[23],TCC_EA_ATOMIC[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_ATOMIC_LEVEL[24],TCC_EA_ATOMIC[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_ATOMIC_LEVEL[25],TCC_EA_ATOMIC[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_ATOMIC_LEVEL[26],TCC_EA_ATOMIC[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_ATOMIC_LEVEL[27],TCC_EA_ATOMIC[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_ATOMIC_LEVEL[28],TCC_EA_ATOMIC[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_ATOMIC_LEVEL[29],TCC_EA_ATOMIC[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_ATOMIC_LEVEL[30],TCC_EA_ATOMIC[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ_LEVEL[31],TCC_EA_ATOMIC_LEVEL[31],CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789581,789581,256,256,0,0,12,4,32,64,0x0,0x7fa983c4d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588165999404,9595697581667,9595697588067,9588184873222 +1,"global_write(int*, int) [clone .kd]",2,0,1,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c15200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588185231295,9595697981345,9595697983585,9588186170961 +2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789581,789581,1,1,4096,0,4,4,48,64,0x0,0x7fa983c15240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588185747445,9595697989025,9595697991265,9588187051836 +3,"global_read(int*, int) [clone .kd]",2,0,3,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c15280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588186416192,9595698033025,9595698035745,9588187966405 +4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c152c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588186956707,9595698039905,9595698042305,9588188690015 +5,"global_atomic(int*, int) [clone .kd]",2,0,5,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c15300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588187589306,9595698072385,9595698076225,9588189838613 +6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789581,789581,1,1,4096,0,4,4,48,64,0x0,0x7fa983c15340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588188228397,9595698076225,9595698080065,9588190792135 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_LEVEL_WAVES.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..ba72ca8515 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,8 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],CPC_ME1_BUSY_FOR_PACKET_DECODE,CPC_CPC_UTCL2IU_STALL,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,GRBM_COUNT,GRBM_GUI_ACTIVE,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789767,789767,256,256,0,0,12,4,32,64,0x0,0x7f0b7a335800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,15256,15256,9588800635588,9595697581667,9595697588067,9588818795995 +1,"global_write(int*, int) [clone .kd]",2,0,1,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a319200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,14215,14215,9588819151083,9595697981345,9595697983585,9588820066433 +2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789767,789767,1,1,4096,0,4,4,48,64,0x0,0x7f0b7a319240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,16303,16303,9588819631105,9595697989025,9595697991265,9588820711946 +3,"global_read(int*, int) [clone .kd]",2,0,3,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a319280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17633,17633,9588820290945,9595698033025,9595698035745,9588821548468 +4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a3192c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,16725,16725,9588820914807,9595698039905,9595698042305,9588822390240 +5,"global_atomic(int*, int) [clone .kd]",2,0,5,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a319300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17452,17452,9588821374712,9595698072385,9595698076225,9588823186356 +6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789767,789767,1,1,4096,0,4,4,48,64,0x0,0x7f0b7a319340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17418,17418,9588822047877,9595698076225,9595698080065,9588824015775 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/log.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/log.txt new file mode 100644 index 0000000000..2b99bd0b4e --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/log.txt @@ -0,0 +1,270 @@ +Omniperf version: 2.1.0 +Profiler choice: rocprofv1 +Path: /home/zichguan/omniperf_test/omniperf/tests/workloads/multikernel/MI210 +Target: MI200 +Command: ./sample/vmem +Kernel Selection: None +Dispatch Selection: None +Hardware Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '241022_154555' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154555_788857' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154555_788857/input0_results_241022_154555' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154555_788857/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 152 metrics + |-> [rocprof] SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES, SQ_BUSY_CU_CYCLES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TCC_CYCLE[0], TCC_RW_REQ[0], TCC_HIT[0], TCC_MISS[0], TCC_CYCLE[1], TCC_RW_REQ[1], TCC_HIT[1], TCC_MISS[1], TCC_CYCLE[2], TCC_RW_REQ[2], TCC_HIT[2], TCC_MISS[2], TCC_CYCLE[3], TCC_RW_REQ[3], TCC_HIT[3], TCC_MISS[3], TCC_CYCLE[4], TCC_RW_REQ[4], TCC_HIT[4], TCC_MISS[4], TCC_CYCLE[5], TCC_RW_REQ[5], TCC_HIT[5], TCC_MISS[5], TCC_CYCLE[6], TCC_RW_REQ[6], TCC_HIT[6], TCC_MISS[6], TCC_CYCLE[7], TCC_RW_REQ[7], TCC_HIT[7], TCC_MISS[7], TCC_CYCLE[8], TCC_RW_REQ[8], TCC_HIT[8], TCC_MISS[8], TCC_CYCLE[9], TCC_RW_REQ[9], TCC_HIT[9], TCC_MISS[9], TCC_CYCLE[10], TCC_RW_REQ[10], TCC_HIT[10], TCC_MISS[10], TCC_CYCLE[11], TCC_RW_REQ[11], TCC_HIT[11], TCC_MISS[11], TCC_CYCLE[12], TCC_RW_REQ[12], TCC_HIT[12], TCC_MISS[12], TCC_CYCLE[13], TCC_RW_REQ[13], TCC_HIT[13], TCC_MISS[13], TCC_CYCLE[14], TCC_RW_REQ[14], TCC_HIT[14], TCC_MISS[14], TCC_CYCLE[15], TCC_RW_REQ[15], TCC_HIT[15], TCC_MISS[15], TCC_CYCLE[16], TCC_RW_REQ[16], TCC_HIT[16], TCC_MISS[16], TCC_CYCLE[17], TCC_RW_REQ[17], TCC_HIT[17], TCC_MISS[17], TCC_CYCLE[18], TCC_RW_REQ[18], TCC_HIT[18], TCC_MISS[18], TCC_CYCLE[19], TCC_RW_REQ[19], TCC_HIT[19], TCC_MISS[19], TCC_CYCLE[20], TCC_RW_REQ[20], TCC_HIT[20], TCC_MISS[20], TCC_CYCLE[21], TCC_RW_REQ[21], TCC_HIT[21], TCC_MISS[21], TCC_CYCLE[22], TCC_RW_REQ[22], TCC_HIT[22], TCC_MISS[22], TCC_CYCLE[23], TCC_RW_REQ[23], TCC_HIT[23], TCC_MISS[23], TCC_CYCLE[24], TCC_RW_REQ[24], TCC_HIT[24], TCC_MISS[24], TCC_CYCLE[25], TCC_RW_REQ[25], TCC_HIT[25], TCC_MISS[25], TCC_CYCLE[26], TCC_RW_REQ[26], TCC_HIT[26], TCC_MISS[26], TCC_CYCLE[27], TCC_RW_REQ[27], TCC_HIT[27], TCC_MISS[27], TCC_CYCLE[28], TCC_RW_REQ[28], TCC_HIT[28], TCC_MISS[28], TCC_CYCLE[29], TCC_RW_REQ[29], TCC_HIT[29], TCC_MISS[29], TCC_CYCLE[30], TCC_RW_REQ[30], TCC_HIT[30], TCC_MISS[30], TCC_CYCLE[31], TCC_RW_REQ[31], TCC_HIT[31], TCC_MISS[31], CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, GRBM_COUNT, GRBM_GUI_ACTIVE + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154555_788857/input0_results_241022_154555 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '241022_154556' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154556_789045' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154556_789045/input0_results_241022_154556' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154556_789045/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 151 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TCC_REQ[0], TCC_READ[0], TCC_WRITE[0], TCC_ATOMIC[0], TCC_REQ[1], TCC_READ[1], TCC_WRITE[1], TCC_ATOMIC[1], TCC_REQ[2], TCC_READ[2], TCC_WRITE[2], TCC_ATOMIC[2], TCC_REQ[3], TCC_READ[3], TCC_WRITE[3], TCC_ATOMIC[3], TCC_REQ[4], TCC_READ[4], TCC_WRITE[4], TCC_ATOMIC[4], TCC_REQ[5], TCC_READ[5], TCC_WRITE[5], TCC_ATOMIC[5], TCC_REQ[6], TCC_READ[6], TCC_WRITE[6], TCC_ATOMIC[6], TCC_REQ[7], TCC_READ[7], TCC_WRITE[7], TCC_ATOMIC[7], TCC_REQ[8], TCC_READ[8], TCC_WRITE[8], TCC_ATOMIC[8], TCC_REQ[9], TCC_READ[9], TCC_WRITE[9], TCC_ATOMIC[9], TCC_REQ[10], TCC_READ[10], TCC_WRITE[10], TCC_ATOMIC[10], TCC_REQ[11], TCC_READ[11], TCC_WRITE[11], TCC_ATOMIC[11], TCC_REQ[12], TCC_READ[12], TCC_WRITE[12], TCC_ATOMIC[12], TCC_REQ[13], TCC_READ[13], TCC_WRITE[13], TCC_ATOMIC[13], TCC_REQ[14], TCC_READ[14], TCC_WRITE[14], TCC_ATOMIC[14], TCC_REQ[15], TCC_READ[15], TCC_WRITE[15], TCC_ATOMIC[15], TCC_REQ[16], TCC_READ[16], TCC_WRITE[16], TCC_ATOMIC[16], TCC_REQ[17], TCC_READ[17], TCC_WRITE[17], TCC_ATOMIC[17], TCC_REQ[18], TCC_READ[18], TCC_WRITE[18], TCC_ATOMIC[18], TCC_REQ[19], TCC_READ[19], TCC_WRITE[19], TCC_ATOMIC[19], TCC_REQ[20], TCC_READ[20], TCC_WRITE[20], TCC_ATOMIC[20], TCC_REQ[21], TCC_READ[21], TCC_WRITE[21], TCC_ATOMIC[21], TCC_REQ[22], TCC_READ[22], TCC_WRITE[22], TCC_ATOMIC[22], TCC_REQ[23], TCC_READ[23], TCC_WRITE[23], TCC_ATOMIC[23], TCC_REQ[24], TCC_READ[24], TCC_WRITE[24], TCC_ATOMIC[24], TCC_REQ[25], TCC_READ[25], TCC_WRITE[25], TCC_ATOMIC[25], TCC_REQ[26], TCC_READ[26], TCC_WRITE[26], TCC_ATOMIC[26], TCC_REQ[27], TCC_READ[27], TCC_WRITE[27], TCC_ATOMIC[27], TCC_REQ[28], TCC_READ[28], TCC_WRITE[28], TCC_ATOMIC[28], TCC_REQ[29], TCC_READ[29], TCC_WRITE[29], TCC_ATOMIC[29], TCC_REQ[30], TCC_READ[30], TCC_WRITE[30], TCC_ATOMIC[30], TCC_REQ[31], TCC_READ[31], TCC_WRITE[31], TCC_ATOMIC[31], CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, GRBM_SPI_BUSY + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154556_789045/input0_results_241022_154556 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '241022_154556' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154556_789233' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154556_789233/input0_results_241022_154556' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154556_789233/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 150 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31], CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154556_789233/input0_results_241022_154556 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '241022_154557' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154557_789421' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154557_789421/input0_results_241022_154557' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154557_789421/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 148 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCC_EA_ATOMIC[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_ATOMIC_LEVEL[0], TCC_EA_ATOMIC[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_ATOMIC_LEVEL[1], TCC_EA_ATOMIC[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_ATOMIC_LEVEL[2], TCC_EA_ATOMIC[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_ATOMIC_LEVEL[3], TCC_EA_ATOMIC[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_ATOMIC_LEVEL[4], TCC_EA_ATOMIC[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_ATOMIC_LEVEL[5], TCC_EA_ATOMIC[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_ATOMIC_LEVEL[6], TCC_EA_ATOMIC[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_ATOMIC_LEVEL[7], TCC_EA_ATOMIC[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_ATOMIC_LEVEL[8], TCC_EA_ATOMIC[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_ATOMIC_LEVEL[9], TCC_EA_ATOMIC[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_ATOMIC_LEVEL[10], TCC_EA_ATOMIC[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_ATOMIC_LEVEL[11], TCC_EA_ATOMIC[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_ATOMIC_LEVEL[12], TCC_EA_ATOMIC[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_ATOMIC_LEVEL[13], TCC_EA_ATOMIC[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_ATOMIC_LEVEL[14], TCC_EA_ATOMIC[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_ATOMIC_LEVEL[15], TCC_EA_ATOMIC[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_ATOMIC_LEVEL[16], TCC_EA_ATOMIC[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_ATOMIC_LEVEL[17], TCC_EA_ATOMIC[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_ATOMIC_LEVEL[18], TCC_EA_ATOMIC[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_ATOMIC_LEVEL[19], TCC_EA_ATOMIC[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_ATOMIC_LEVEL[20], TCC_EA_ATOMIC[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_ATOMIC_LEVEL[21], TCC_EA_ATOMIC[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_ATOMIC_LEVEL[22], TCC_EA_ATOMIC[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_ATOMIC_LEVEL[23], TCC_EA_ATOMIC[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_ATOMIC_LEVEL[24], TCC_EA_ATOMIC[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_ATOMIC_LEVEL[25], TCC_EA_ATOMIC[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_ATOMIC_LEVEL[26], TCC_EA_ATOMIC[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_ATOMIC_LEVEL[27], TCC_EA_ATOMIC[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_ATOMIC_LEVEL[28], TCC_EA_ATOMIC[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_ATOMIC_LEVEL[29], TCC_EA_ATOMIC[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_ATOMIC_LEVEL[30], TCC_EA_ATOMIC[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ_LEVEL[31], TCC_EA_ATOMIC_LEVEL[31], CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154557_789421/input0_results_241022_154557 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '241022_154558' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154558_789607' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154558_789607/input0_results_241022_154558' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154558_789607/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 148 metrics + |-> [rocprof] SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], CPC_ME1_BUSY_FOR_PACKET_DECODE, CPC_CPC_UTCL2IU_STALL, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, GRBM_COUNT, GRBM_GUI_ACTIVE + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154558_789607/input0_results_241022_154558 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '241022_154558' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154558_789792' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154558_789792/input0_results_241022_154558' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154558_789792/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 114 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_FLAT, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_CYCLE_sum, CPC_ME1_DC0_SPI_BUSY, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154558_789792/input0_results_241022_154558 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '241022_154559' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154559_789978' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154559_789978/input0_results_241022_154559' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154559_789978/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_ANY, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum, TCC_NC_REQ_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154559_789978/input0_results_241022_154559 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '241022_154600' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154600_790176' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154600_790176/input0_results_241022_154600' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154600_790176/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum, TCC_REQ_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154600_790176/input0_results_241022_154600 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '241022_154600' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154600_790361' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154600_790361/input0_results_241022_154600' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154600_790361/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 18 metrics + |-> [rocprof] SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum, TCC_READ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154600_790361/input0_results_241022_154600 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '241022_154601' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154601_790548' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154601_790548/input0_results_241022_154601' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154601_790548/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum, TCC_EA_WRREQ_sum + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154601_790548/input0_results_241022_154601 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '241022_154602' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154602_790732' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154602_790732/input0_results_241022_154602' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154602_790732/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum, TCC_EA_WRREQ_STALL_sum + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154602_790732/input0_results_241022_154602 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '241022_154602' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154602_790917' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154602_790917/input0_results_241022_154602' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154602_790917/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154602_790917/input0_results_241022_154602 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '241022_154603' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154603_791101' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154603_791101/input0_results_241022_154603' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154603_791101/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154603_791101/input0_results_241022_154603 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '241022_154603' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154603_791285' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154603_791285/input0_results_241022_154603' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154603_791285/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154603_791285/input0_results_241022_154603 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '241022_154604' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154604_791469' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154604_791469/input0_results_241022_154604' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154604_791469/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154604_791469/input0_results_241022_154604 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/timestamps.txt + |-> [rocprof] RPL: on '241022_154605' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' + |-> [rocprof] RPL: profiling '""./sample/vmem""' + |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154605_791667' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154605_791667/input0_results_241022_154605' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154605_791667/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154605_791667/input0_results_241022_154605 + |-> [rocprof] File 'tests/workloads/multikernel/MI210/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/multikernel/MI210 +[roofline] No roofline data found. Generating... diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt new file mode 100644 index 0000000000..bde9fa9462 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES SQ_BUSY_CU_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TCC_CYCLE[0] TCC_RW_REQ[0] TCC_HIT[0] TCC_MISS[0] TCC_CYCLE[1] TCC_RW_REQ[1] TCC_HIT[1] TCC_MISS[1] TCC_CYCLE[2] TCC_RW_REQ[2] TCC_HIT[2] TCC_MISS[2] TCC_CYCLE[3] TCC_RW_REQ[3] TCC_HIT[3] TCC_MISS[3] TCC_CYCLE[4] TCC_RW_REQ[4] TCC_HIT[4] TCC_MISS[4] TCC_CYCLE[5] TCC_RW_REQ[5] TCC_HIT[5] TCC_MISS[5] TCC_CYCLE[6] TCC_RW_REQ[6] TCC_HIT[6] TCC_MISS[6] TCC_CYCLE[7] TCC_RW_REQ[7] TCC_HIT[7] TCC_MISS[7] TCC_CYCLE[8] TCC_RW_REQ[8] TCC_HIT[8] TCC_MISS[8] TCC_CYCLE[9] TCC_RW_REQ[9] TCC_HIT[9] TCC_MISS[9] TCC_CYCLE[10] TCC_RW_REQ[10] TCC_HIT[10] TCC_MISS[10] TCC_CYCLE[11] TCC_RW_REQ[11] TCC_HIT[11] TCC_MISS[11] TCC_CYCLE[12] TCC_RW_REQ[12] TCC_HIT[12] TCC_MISS[12] TCC_CYCLE[13] TCC_RW_REQ[13] TCC_HIT[13] TCC_MISS[13] TCC_CYCLE[14] TCC_RW_REQ[14] TCC_HIT[14] TCC_MISS[14] TCC_CYCLE[15] TCC_RW_REQ[15] TCC_HIT[15] TCC_MISS[15] TCC_CYCLE[16] TCC_RW_REQ[16] TCC_HIT[16] TCC_MISS[16] TCC_CYCLE[17] TCC_RW_REQ[17] TCC_HIT[17] TCC_MISS[17] TCC_CYCLE[18] TCC_RW_REQ[18] TCC_HIT[18] TCC_MISS[18] TCC_CYCLE[19] TCC_RW_REQ[19] TCC_HIT[19] TCC_MISS[19] TCC_CYCLE[20] TCC_RW_REQ[20] TCC_HIT[20] TCC_MISS[20] TCC_CYCLE[21] TCC_RW_REQ[21] TCC_HIT[21] TCC_MISS[21] TCC_CYCLE[22] TCC_RW_REQ[22] TCC_HIT[22] TCC_MISS[22] TCC_CYCLE[23] TCC_RW_REQ[23] TCC_HIT[23] TCC_MISS[23] TCC_CYCLE[24] TCC_RW_REQ[24] TCC_HIT[24] TCC_MISS[24] TCC_CYCLE[25] TCC_RW_REQ[25] TCC_HIT[25] TCC_MISS[25] TCC_CYCLE[26] TCC_RW_REQ[26] TCC_HIT[26] TCC_MISS[26] TCC_CYCLE[27] TCC_RW_REQ[27] TCC_HIT[27] TCC_MISS[27] TCC_CYCLE[28] TCC_RW_REQ[28] TCC_HIT[28] TCC_MISS[28] TCC_CYCLE[29] TCC_RW_REQ[29] TCC_HIT[29] TCC_MISS[29] TCC_CYCLE[30] TCC_RW_REQ[30] TCC_HIT[30] TCC_MISS[30] TCC_CYCLE[31] TCC_RW_REQ[31] TCC_HIT[31] TCC_MISS[31] CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL SPI_CSN_WINDOW_VALID SPI_CSN_BUSY GRBM_COUNT GRBM_GUI_ACTIVE + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt new file mode 100644 index 0000000000..487719a26f --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TCC_REQ[0] TCC_READ[0] TCC_WRITE[0] TCC_ATOMIC[0] TCC_REQ[1] TCC_READ[1] TCC_WRITE[1] TCC_ATOMIC[1] TCC_REQ[2] TCC_READ[2] TCC_WRITE[2] TCC_ATOMIC[2] TCC_REQ[3] TCC_READ[3] TCC_WRITE[3] TCC_ATOMIC[3] TCC_REQ[4] TCC_READ[4] TCC_WRITE[4] TCC_ATOMIC[4] TCC_REQ[5] TCC_READ[5] TCC_WRITE[5] TCC_ATOMIC[5] TCC_REQ[6] TCC_READ[6] TCC_WRITE[6] TCC_ATOMIC[6] TCC_REQ[7] TCC_READ[7] TCC_WRITE[7] TCC_ATOMIC[7] TCC_REQ[8] TCC_READ[8] TCC_WRITE[8] TCC_ATOMIC[8] TCC_REQ[9] TCC_READ[9] TCC_WRITE[9] TCC_ATOMIC[9] TCC_REQ[10] TCC_READ[10] TCC_WRITE[10] TCC_ATOMIC[10] TCC_REQ[11] TCC_READ[11] TCC_WRITE[11] TCC_ATOMIC[11] TCC_REQ[12] TCC_READ[12] TCC_WRITE[12] TCC_ATOMIC[12] TCC_REQ[13] TCC_READ[13] TCC_WRITE[13] TCC_ATOMIC[13] TCC_REQ[14] TCC_READ[14] TCC_WRITE[14] TCC_ATOMIC[14] TCC_REQ[15] TCC_READ[15] TCC_WRITE[15] TCC_ATOMIC[15] TCC_REQ[16] TCC_READ[16] TCC_WRITE[16] TCC_ATOMIC[16] TCC_REQ[17] TCC_READ[17] TCC_WRITE[17] TCC_ATOMIC[17] TCC_REQ[18] TCC_READ[18] TCC_WRITE[18] TCC_ATOMIC[18] TCC_REQ[19] TCC_READ[19] TCC_WRITE[19] TCC_ATOMIC[19] TCC_REQ[20] TCC_READ[20] TCC_WRITE[20] TCC_ATOMIC[20] TCC_REQ[21] TCC_READ[21] TCC_WRITE[21] TCC_ATOMIC[21] TCC_REQ[22] TCC_READ[22] TCC_WRITE[22] TCC_ATOMIC[22] TCC_REQ[23] TCC_READ[23] TCC_WRITE[23] TCC_ATOMIC[23] TCC_REQ[24] TCC_READ[24] TCC_WRITE[24] TCC_ATOMIC[24] TCC_REQ[25] TCC_READ[25] TCC_WRITE[25] TCC_ATOMIC[25] TCC_REQ[26] TCC_READ[26] TCC_WRITE[26] TCC_ATOMIC[26] TCC_REQ[27] TCC_READ[27] TCC_WRITE[27] TCC_ATOMIC[27] TCC_REQ[28] TCC_READ[28] TCC_WRITE[28] TCC_ATOMIC[28] TCC_REQ[29] TCC_READ[29] TCC_WRITE[29] TCC_ATOMIC[29] TCC_REQ[30] TCC_READ[30] TCC_WRITE[30] TCC_ATOMIC[30] TCC_REQ[31] TCC_READ[31] TCC_WRITE[31] TCC_ATOMIC[31] CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE GRBM_SPI_BUSY + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt new file mode 100644 index 0000000000..fff8e8f692 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt new file mode 100644 index 0000000000..9e8e854092 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TCC_EA_ATOMIC[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_ATOMIC_LEVEL[0] TCC_EA_ATOMIC[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_ATOMIC_LEVEL[1] TCC_EA_ATOMIC[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_ATOMIC_LEVEL[2] TCC_EA_ATOMIC[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_ATOMIC_LEVEL[3] TCC_EA_ATOMIC[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_ATOMIC_LEVEL[4] TCC_EA_ATOMIC[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_ATOMIC_LEVEL[5] TCC_EA_ATOMIC[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_ATOMIC_LEVEL[6] TCC_EA_ATOMIC[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_ATOMIC_LEVEL[7] TCC_EA_ATOMIC[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_ATOMIC_LEVEL[8] TCC_EA_ATOMIC[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_ATOMIC_LEVEL[9] TCC_EA_ATOMIC[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_ATOMIC_LEVEL[10] TCC_EA_ATOMIC[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_ATOMIC_LEVEL[11] TCC_EA_ATOMIC[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_ATOMIC_LEVEL[12] TCC_EA_ATOMIC[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_ATOMIC_LEVEL[13] TCC_EA_ATOMIC[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_ATOMIC_LEVEL[14] TCC_EA_ATOMIC[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_ATOMIC_LEVEL[15] TCC_EA_ATOMIC[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_ATOMIC_LEVEL[16] TCC_EA_ATOMIC[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_ATOMIC_LEVEL[17] TCC_EA_ATOMIC[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_ATOMIC_LEVEL[18] TCC_EA_ATOMIC[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_ATOMIC_LEVEL[19] TCC_EA_ATOMIC[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_ATOMIC_LEVEL[20] TCC_EA_ATOMIC[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_ATOMIC_LEVEL[21] TCC_EA_ATOMIC[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_ATOMIC_LEVEL[22] TCC_EA_ATOMIC[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_ATOMIC_LEVEL[23] TCC_EA_ATOMIC[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_ATOMIC_LEVEL[24] TCC_EA_ATOMIC[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_ATOMIC_LEVEL[25] TCC_EA_ATOMIC[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_ATOMIC_LEVEL[26] TCC_EA_ATOMIC[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_ATOMIC_LEVEL[27] TCC_EA_ATOMIC[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_ATOMIC_LEVEL[28] TCC_EA_ATOMIC[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_ATOMIC_LEVEL[29] TCC_EA_ATOMIC[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_ATOMIC_LEVEL[30] TCC_EA_ATOMIC[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ_LEVEL[31] TCC_EA_ATOMIC_LEVEL[31] CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_LEVEL_WAVES.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_LEVEL_WAVES.txt new file mode 100644 index 0000000000..91c1452d0b --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] CPC_ME1_BUSY_FOR_PACKET_DECODE CPC_CPC_UTCL2IU_STALL SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN GRBM_COUNT GRBM_GUI_ACTIVE + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_0.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..157b0fa30a --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_FLAT SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY SQ_WAIT_INST_ANY TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_CYCLE_sum CPC_ME1_DC0_SPI_BUSY SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_1.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..b621588d2b --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum TCC_NC_REQ_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_2.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..c385f7a070 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum TCC_REQ_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_3.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..c201a09ec6 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum TCC_READ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_4.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..dae1577474 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum TCC_EA_WRREQ_sum + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_5.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..6c5efd1c95 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum TCC_EA_WRREQ_STALL_sum + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_6.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..512ffbd896 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_7.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..e7479b0f45 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_8.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..4afa81372a --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_9.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_9.txt new file mode 100644 index 0000000000..5b7d3f8529 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_9.txt @@ -0,0 +1,5 @@ +pmc: TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/timestamps.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/timestamps.txt new file mode 100644 index 0000000000..676cca1b80 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/timestamps.txt @@ -0,0 +1,5 @@ +pmc: + +gpu: +range: +kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_dispatch_info.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..4c84144877 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_dispatch_info.csv @@ -0,0 +1,8 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,__amd_rocclr_fillBufferAligned.kd,2 +1,"global_write(int*, int) [clone .kd]",2 +2,"generic_write(int*, int, int) [clone .kd]",2 +3,"global_read(int*, int) [clone .kd]",2 +4,"generic_read(int*, int, int) [clone .kd]",2 +5,"global_atomic(int*, int) [clone .kd]",2 +6,"generic_atomic(int*, int, int) [clone .kd]",2 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_perf.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_perf.csv new file mode 100644 index 0000000000..b50d5c38f9 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_perf.csv @@ -0,0 +1,8 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,TCC_EA_WRREQ_sum,wave_size_1,obj_1,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,SQ_ACTIVE_INST_ANY,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,TCC_NC_REQ_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_3,obj_3,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,TCC_REQ_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_4,obj_4,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,TCC_READ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_5,obj_5,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,wave_size_6,obj_6,SQ_INSTS_VALU_INT64,SQ_INSTS_FLAT,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_CYCLE_sum,CPC_ME1_DC0_SPI_BUSY,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_7,obj_7,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,wave_size_8,obj_8,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_9,obj_9,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,TCC_EA_WRREQ_STALL_sum,wave_size_10,obj_10,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_11,obj_11,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES_11,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TCC_CYCLE[0],TCC_RW_REQ[0],TCC_HIT[0],TCC_MISS[0],TCC_CYCLE[1],TCC_RW_REQ[1],TCC_HIT[1],TCC_MISS[1],TCC_CYCLE[2],TCC_RW_REQ[2],TCC_HIT[2],TCC_MISS[2],TCC_CYCLE[3],TCC_RW_REQ[3],TCC_HIT[3],TCC_MISS[3],TCC_CYCLE[4],TCC_RW_REQ[4],TCC_HIT[4],TCC_MISS[4],TCC_CYCLE[5],TCC_RW_REQ[5],TCC_HIT[5],TCC_MISS[5],TCC_CYCLE[6],TCC_RW_REQ[6],TCC_HIT[6],TCC_MISS[6],TCC_CYCLE[7],TCC_RW_REQ[7],TCC_HIT[7],TCC_MISS[7],TCC_CYCLE[8],TCC_RW_REQ[8],TCC_HIT[8],TCC_MISS[8],TCC_CYCLE[9],TCC_RW_REQ[9],TCC_HIT[9],TCC_MISS[9],TCC_CYCLE[10],TCC_RW_REQ[10],TCC_HIT[10],TCC_MISS[10],TCC_CYCLE[11],TCC_RW_REQ[11],TCC_HIT[11],TCC_MISS[11],TCC_CYCLE[12],TCC_RW_REQ[12],TCC_HIT[12],TCC_MISS[12],TCC_CYCLE[13],TCC_RW_REQ[13],TCC_HIT[13],TCC_MISS[13],TCC_CYCLE[14],TCC_RW_REQ[14],TCC_HIT[14],TCC_MISS[14],TCC_CYCLE[15],TCC_RW_REQ[15],TCC_HIT[15],TCC_MISS[15],TCC_CYCLE[16],TCC_RW_REQ[16],TCC_HIT[16],TCC_MISS[16],TCC_CYCLE[17],TCC_RW_REQ[17],TCC_HIT[17],TCC_MISS[17],TCC_CYCLE[18],TCC_RW_REQ[18],TCC_HIT[18],TCC_MISS[18],TCC_CYCLE[19],TCC_RW_REQ[19],TCC_HIT[19],TCC_MISS[19],TCC_CYCLE[20],TCC_RW_REQ[20],TCC_HIT[20],TCC_MISS[20],TCC_CYCLE[21],TCC_RW_REQ[21],TCC_HIT[21],TCC_MISS[21],TCC_CYCLE[22],TCC_RW_REQ[22],TCC_HIT[22],TCC_MISS[22],TCC_CYCLE[23],TCC_RW_REQ[23],TCC_HIT[23],TCC_MISS[23],TCC_CYCLE[24],TCC_RW_REQ[24],TCC_HIT[24],TCC_MISS[24],TCC_CYCLE[25],TCC_RW_REQ[25],TCC_HIT[25],TCC_MISS[25],TCC_CYCLE[26],TCC_RW_REQ[26],TCC_HIT[26],TCC_MISS[26],TCC_CYCLE[27],TCC_RW_REQ[27],TCC_HIT[27],TCC_MISS[27],TCC_CYCLE[28],TCC_RW_REQ[28],TCC_HIT[28],TCC_MISS[28],TCC_CYCLE[29],TCC_RW_REQ[29],TCC_HIT[29],TCC_MISS[29],TCC_CYCLE[30],TCC_RW_REQ[30],TCC_HIT[30],TCC_MISS[30],TCC_CYCLE[31],TCC_RW_REQ[31],TCC_HIT[31],TCC_MISS[31],CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_12,obj_12,SQ_CYCLES,SQ_WAVES_12,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES_12,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],CPC_ME1_BUSY_FOR_PACKET_DECODE,CPC_CPC_UTCL2IU_STALL,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,GRBM_COUNT_12,GRBM_GUI_ACTIVE_12,wave_size_13,obj_13,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES_13,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TCC_REQ[0],TCC_READ[0],TCC_WRITE[0],TCC_ATOMIC[0],TCC_REQ[1],TCC_READ[1],TCC_WRITE[1],TCC_ATOMIC[1],TCC_REQ[2],TCC_READ[2],TCC_WRITE[2],TCC_ATOMIC[2],TCC_REQ[3],TCC_READ[3],TCC_WRITE[3],TCC_ATOMIC[3],TCC_REQ[4],TCC_READ[4],TCC_WRITE[4],TCC_ATOMIC[4],TCC_REQ[5],TCC_READ[5],TCC_WRITE[5],TCC_ATOMIC[5],TCC_REQ[6],TCC_READ[6],TCC_WRITE[6],TCC_ATOMIC[6],TCC_REQ[7],TCC_READ[7],TCC_WRITE[7],TCC_ATOMIC[7],TCC_REQ[8],TCC_READ[8],TCC_WRITE[8],TCC_ATOMIC[8],TCC_REQ[9],TCC_READ[9],TCC_WRITE[9],TCC_ATOMIC[9],TCC_REQ[10],TCC_READ[10],TCC_WRITE[10],TCC_ATOMIC[10],TCC_REQ[11],TCC_READ[11],TCC_WRITE[11],TCC_ATOMIC[11],TCC_REQ[12],TCC_READ[12],TCC_WRITE[12],TCC_ATOMIC[12],TCC_REQ[13],TCC_READ[13],TCC_WRITE[13],TCC_ATOMIC[13],TCC_REQ[14],TCC_READ[14],TCC_WRITE[14],TCC_ATOMIC[14],TCC_REQ[15],TCC_READ[15],TCC_WRITE[15],TCC_ATOMIC[15],TCC_REQ[16],TCC_READ[16],TCC_WRITE[16],TCC_ATOMIC[16],TCC_REQ[17],TCC_READ[17],TCC_WRITE[17],TCC_ATOMIC[17],TCC_REQ[18],TCC_READ[18],TCC_WRITE[18],TCC_ATOMIC[18],TCC_REQ[19],TCC_READ[19],TCC_WRITE[19],TCC_ATOMIC[19],TCC_REQ[20],TCC_READ[20],TCC_WRITE[20],TCC_ATOMIC[20],TCC_REQ[21],TCC_READ[21],TCC_WRITE[21],TCC_ATOMIC[21],TCC_REQ[22],TCC_READ[22],TCC_WRITE[22],TCC_ATOMIC[22],TCC_REQ[23],TCC_READ[23],TCC_WRITE[23],TCC_ATOMIC[23],TCC_REQ[24],TCC_READ[24],TCC_WRITE[24],TCC_ATOMIC[24],TCC_REQ[25],TCC_READ[25],TCC_WRITE[25],TCC_ATOMIC[25],TCC_REQ[26],TCC_READ[26],TCC_WRITE[26],TCC_ATOMIC[26],TCC_REQ[27],TCC_READ[27],TCC_WRITE[27],TCC_ATOMIC[27],TCC_REQ[28],TCC_READ[28],TCC_WRITE[28],TCC_ATOMIC[28],TCC_REQ[29],TCC_READ[29],TCC_WRITE[29],TCC_ATOMIC[29],TCC_REQ[30],TCC_READ[30],TCC_WRITE[30],TCC_ATOMIC[30],TCC_REQ[31],TCC_READ[31],TCC_WRITE[31],TCC_ATOMIC[31],CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,GRBM_SPI_BUSY,wave_size_14,obj_14,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES_14,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCC_EA_ATOMIC[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_ATOMIC_LEVEL[0],TCC_EA_ATOMIC[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_ATOMIC_LEVEL[1],TCC_EA_ATOMIC[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_ATOMIC_LEVEL[2],TCC_EA_ATOMIC[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_ATOMIC_LEVEL[3],TCC_EA_ATOMIC[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_ATOMIC_LEVEL[4],TCC_EA_ATOMIC[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_ATOMIC_LEVEL[5],TCC_EA_ATOMIC[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_ATOMIC_LEVEL[6],TCC_EA_ATOMIC[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_ATOMIC_LEVEL[7],TCC_EA_ATOMIC[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_ATOMIC_LEVEL[8],TCC_EA_ATOMIC[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_ATOMIC_LEVEL[9],TCC_EA_ATOMIC[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_ATOMIC_LEVEL[10],TCC_EA_ATOMIC[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_ATOMIC_LEVEL[11],TCC_EA_ATOMIC[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_ATOMIC_LEVEL[12],TCC_EA_ATOMIC[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_ATOMIC_LEVEL[13],TCC_EA_ATOMIC[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_ATOMIC_LEVEL[14],TCC_EA_ATOMIC[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_ATOMIC_LEVEL[15],TCC_EA_ATOMIC[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_ATOMIC_LEVEL[16],TCC_EA_ATOMIC[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_ATOMIC_LEVEL[17],TCC_EA_ATOMIC[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_ATOMIC_LEVEL[18],TCC_EA_ATOMIC[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_ATOMIC_LEVEL[19],TCC_EA_ATOMIC[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_ATOMIC_LEVEL[20],TCC_EA_ATOMIC[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_ATOMIC_LEVEL[21],TCC_EA_ATOMIC[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_ATOMIC_LEVEL[22],TCC_EA_ATOMIC[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_ATOMIC_LEVEL[23],TCC_EA_ATOMIC[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_ATOMIC_LEVEL[24],TCC_EA_ATOMIC[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_ATOMIC_LEVEL[25],TCC_EA_ATOMIC[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_ATOMIC_LEVEL[26],TCC_EA_ATOMIC[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_ATOMIC_LEVEL[27],TCC_EA_ATOMIC[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_ATOMIC_LEVEL[28],TCC_EA_ATOMIC[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_ATOMIC_LEVEL[29],TCC_EA_ATOMIC[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_ATOMIC_LEVEL[30],TCC_EA_ATOMIC[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ_LEVEL[31],TCC_EA_ATOMIC_LEVEL[31],CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,Start_Timestamp,End_Timestamp +0,__amd_rocclr_fillBufferAligned.kd,2,256,256,0,0,12,4,32,64,0x7fb019e7d800,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c4bd800,0.0,0.0,64,0x7fe35344d800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93ecdd800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b64bd800,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501f115800,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc510b5800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b4a5800,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410dc0d800,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353b15800,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea49d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b83d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,15492,15492,64,0x7f0b7a335800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,15256,15256,64,0x7f092c135800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,7832,64,0x7fa983c4d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595697581667,9595697588067 +1,"global_write(int*, int) [clone .kd]",2,1,1,0,0,4,4,16,64,0x7fb019e4d200,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d200,0.0,0.0,64,0x7fe353429200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca5200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d200,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe1200,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc51079200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d200,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e1200,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af1200,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea465200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b805200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,14214,14214,64,0x7f0b7a319200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,14215,14215,64,0x7f092c0f9200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,4807,64,0x7fa983c15200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595697981345,9595697983585 +2,"generic_write(int*, int, int) [clone .kd]",2,1,1,4096,0,4,4,48,64,0x7fb019e4d240,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d240,0.0,0.0,64,0x7fe353429240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca5240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d240,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe1240,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc51079240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d240,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e1240,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af1240,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea465240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b805240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16792,16792,64,0x7f0b7a319240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,16303,16303,64,0x7f092c0f9240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6147,64,0x7fa983c15240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595697989025,9595697991265 +3,"global_read(int*, int) [clone .kd]",2,1,1,0,0,4,4,16,64,0x7fb019e4d280,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d280,0.0,0.0,64,0x7fe353429280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca5280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d280,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe1280,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc51079280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d280,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e1280,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af1280,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea465280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b805280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,17066,17066,64,0x7f0b7a319280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17633,17633,64,0x7f092c0f9280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6439,64,0x7fa983c15280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595698033025,9595698035745 +4,"generic_read(int*, int, int) [clone .kd]",2,1,1,0,0,4,4,16,64,0x7fb019e4d2c0,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d2c0,0.0,0.0,64,0x7fe3534292c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca52c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d2c0,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe12c0,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc510792c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d2c0,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e12c0,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af12c0,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea4652c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b8052c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16835,16835,64,0x7f0b7a3192c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,16725,16725,64,0x7f092c0f92c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6821,64,0x7fa983c152c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595698039905,9595698042305 +5,"global_atomic(int*, int) [clone .kd]",2,1,1,0,0,4,4,16,64,0x7fb019e4d300,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d300,0.0,0.0,64,0x7fe353429300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca5300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d300,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe1300,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc51079300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d300,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e1300,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af1300,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea465300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b805300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16490,16490,64,0x7f0b7a319300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17452,17452,64,0x7f092c0f9300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6708,64,0x7fa983c15300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595698072385,9595698076225 +6,"generic_atomic(int*, int, int) [clone .kd]",2,1,1,4096,0,4,4,48,64,0x7fb019e4d340,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d340,0.0,0.0,64,0x7fe353429340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca5340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d340,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe1340,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc51079340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d340,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e1340,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af1340,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea465340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b805340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,17235,17235,64,0x7f0b7a319340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17418,17418,64,0x7f092c0f9340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,7838,64,0x7fa983c15340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595698076225,9595698080065 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/roofline.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/roofline.csv new file mode 100644 index 0000000000..6ec250343a --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/roofline.csv @@ -0,0 +1,4 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1392.4641,1391.8217,1393.1066,5012.8921,4999.646,5026.1382,9233.5303,9232.7051,9234.3555,21014.016,21012.709,21015.322,20999.16,20998.666,20999.654,20187.006,19967.416,20406.596,170734.45,170729.66,170739.25,165067.44,165061.97,165072.91,41480.547,41479.074,41482.02,41303.828,40844.742,41762.914,166839.7,166833.48,166845.92 +1,1391.9521,1391.3705,1392.5338,5005.9937,4997.5942,5014.3931,9197.5605,9196.7617,9198.3594,20984.785,20983.42,20986.15,20944.287,20943.701,20944.873,20222.557,20221.738,20223.375,170379.27,170372.45,170386.08,164480.19,164473.75,164486.62,41338.699,41336.965,41340.434,41397.539,41395.738,41399.34,166265.69,166259,166272.38 +2,1383.8199,1367.1714,1400.4685,5018.9521,5012.7114,5025.1929,9215.9326,9215.2646,9216.6006,21009.275,21007.996,21010.555,20973.949,20973.555,20974.344,20256.393,20255.896,20256.889,170535.72,170531.75,170539.69,164753.2,164748.77,164757.64,41403.738,41402.945,41404.531,41465.727,41464.988,41466.465,166533.73,166531.06,166536.41 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/sysinfo.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/sysinfo.csv new file mode 100644 index 0000000000..5ac906c7d1 --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/sysinfo.csv @@ -0,0 +1,2 @@ +workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,chip_id,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd +multikernel,./sample/vmem,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Tue 22 Oct 2024 03:45:54 PM (CDT),2,dell-rack-10,AMD EPYC 7313 16-Core Processor,Dell Inc.2.2.5,Ubuntu 20.04.6 LTS,5.15.0-122-generic,,527949684,,6.2.1-99,113-D67301-064D,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,29711,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/timestamps.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/timestamps.csv new file mode 100644 index 0000000000..23782c1d1b --- /dev/null +++ b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/timestamps.csv @@ -0,0 +1,8 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,__amd_rocclr_fillBufferAligned.kd,2,0,0,791827,791827,256,256,0,0,12,4,32,64,0x0,0x7fd72f815800,9595697470571,9595697581667,9595697588067,9595697604693 +1,"global_write(int*, int) [clone .kd]",2,0,1,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d9200,9595697964779,9595697981345,9595697983585,9595697985168 +2,"generic_write(int*, int, int) [clone .kd]",2,0,2,791827,791827,1,1,4096,0,4,4,48,64,0x0,0x7fd72e4d9240,9595697979166,9595697989025,9595697991265,9595698006628 +3,"global_read(int*, int) [clone .kd]",2,0,3,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d9280,9595697986791,9595698033025,9595698035745,9595698036745 +4,"generic_read(int*, int, int) [clone .kd]",2,0,4,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d92c0,9595698029551,9595698039905,9595698042305,9595698049348 +5,"global_atomic(int*, int) [clone .kd]",2,0,5,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d9300,9595698036745,9595698072385,9595698076225,9595698076890 +6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,791827,791827,1,1,4096,0,4,4,48,64,0x0,0x7fd72e4d9340,9595698067583,9595698076225,9595698080065,9595698086618 From b0c7f78ca653f1ea91f2f343a76a97ce364c2ad4 Mon Sep 17 00:00:00 2001 From: Ben Richard <143630488+benrichard-amd@users.noreply.github.com> Date: Fri, 25 Oct 2024 18:13:10 -0400 Subject: [PATCH 23/29] Add broken mclk workaround for all arch (#453) * Check for missing mclk, use hard-coded values if needed Signed-off-by: benrichard-amd * Fix typo Signed-off-by: benrichard-amd --------- Signed-off-by: benrichard-amd [ROCm/rocprofiler-compute commit: 2de2faf944a39477ae1a22bb2b106679802cf3b1] --- .../rocprofiler-compute/src/omniperf_soc/soc_gfx908.py | 6 ++++-- .../rocprofiler-compute/src/omniperf_soc/soc_gfx90a.py | 7 +++++++ .../rocprofiler-compute/src/omniperf_soc/soc_gfx942.py | 10 ++++++---- 3 files changed, 17 insertions(+), 6 deletions(-) diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx908.py b/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx908.py index 4d94edd81b..415502a55f 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx908.py +++ b/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx908.py @@ -63,8 +63,10 @@ class gfx908_soc(OmniSoC_Base): self._mspec.lds_banks_per_cu = 32 self._mspec.pipes_per_gpu = 4 # --showmclkrange is broken in Mi100, hardcode freq - self._mspec.max_mclk = 1200 - self._mspec.cur_mclk = 1200 + if self._mspec.gpu_model == "MI100": + if self._mspec.max_mclk == None or self._mspec.cur_mclk == None: + self._mspec.max_mclk = 1200 + self._mspec.cur_mclk = 1200 @demarcate def get_profiler_options(self): diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx90a.py b/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx90a.py index 022404f74b..9e5fbd04e7 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx90a.py +++ b/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx90a.py @@ -71,6 +71,13 @@ class gfx90a_soc(OmniSoC_Base): ) self.roofline_obj = Roofline(args, self._mspec) + # Workaround for broken --showmclkrange + # MI210/MI250/MI250X have 1600MHz mclk + if self._mspec.gpu_model == "MI200": + if self._mspec.max_mclk == None or self._mspec.cur_mclk == None: + self._mspec.max_mclk = 1600 + self._mspec.cur_mclk = 1600 + # Set arch specific specs self._mspec._l2_banks = 32 self._mspec.lds_banks_per_cu = 32 diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx942.py b/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx942.py index d2ad35eb18..606d9a8399 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx942.py +++ b/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx942.py @@ -69,10 +69,12 @@ class gfx942_soc(OmniSoC_Base): ) # self.roofline_obj = Roofline(args, self._mspec) - # --showmclkrange is broken in MI308X, hardcode freq - if self._mspec.gpu_model == "MI308X": - self._mspec.max_mclk = 1300 - self._mspec.cur_mclk = 1300 + # Workaround for broken --showmclkrange + # MI300X/MI300A/MI308X have 1300MHz mclk + if self._mspec.gpu_model == "MI300": + if self._mspec.max_mclk == None or self._mspec.cur_mclk == None: + self._mspec.max_mclk = 1300 + self._mspec.cur_mclk = 1300 # Set arch specific specs self._mspec._l2_banks = 16 From 825440e7ba25df6b49d3ab399650bfe160172c02 Mon Sep 17 00:00:00 2001 From: xuchen-amd Date: Fri, 1 Nov 2024 12:20:21 -0400 Subject: [PATCH 24/29] Rename Omniperf to ROCm Compute Profiler (#428) - Update filenames. - Update executable to `rocprof-compute` - Update update package to `rocprofiler-compute` - Update name in application output and logs - Update name in README files - Update testing and workflows --------- Signed-off-by: Xuan Chen [ROCm/rocprofiler-compute commit: 31b4de1a386e4eb63f6002188c459444f6e21180] --- .../.github/ISSUE_TEMPLATE/bug_report.yaml | 10 +- .../.github/workflows/mi-rhel9.yml | 6 +- .../.github/workflows/packaging.yml | 14 +- .../.github/workflows/rhel-8.yml | 2 +- .../.github/workflows/tarball.yml | 44 +- .../.github/workflows/ubuntu-jammy.yml | 2 +- projects/rocprofiler-compute/AUTHORS | 2 +- projects/rocprofiler-compute/CHANGELOG.md | 4 +- projects/rocprofiler-compute/CMakeLists.txt | 74 +- projects/rocprofiler-compute/CONTRIBUTING.md | 16 +- projects/rocprofiler-compute/MAINTAINERS.md | 10 +- projects/rocprofiler-compute/README.md | 22 +- projects/rocprofiler-compute/cmake/Dockerfile | 6 +- .../rocprofiler-compute/cmake/VERSION.sha.in | 2 +- ...{omniperf.lua.in => rocprofcompute.lua.in} | 16 +- .../docker/build-docker-ci.sh | 4 +- .../docker/build-docker.sh | 2 +- .../docs/archive/docs-1.x/analysis.md | 6 +- .../docs/archive/docs-2.x/analysis.md | 4 +- .../docs/how-to/analyze/cli.rst | 2 +- .../docs/how-to/analyze/standalone-gui.rst | 2 +- .../docs/install/core-install.rst | 35 +- .../docs/install/grafana-setup.rst | 7 - .../docs/sphinx/static/css/o_custom.css | 22 + .../rocprofiler-compute/grafana/Dockerfile | 6 +- .../dashboards/Omniperf_v1.0.3_pub.json | 288 ++--- .../dashboards/Omniperf_v1.0.5_pub.json | 2 +- .../dashboards/Omniperf_v1.0.7_pub.json | 6 +- .../dashboards/Omniperf_v1.0.8_pub.json | 10 +- .../dashboards/Omniperf_v2.0.0_pub.json | 12 +- .../grafana/docker-compose.yml | 8 +- .../grafana/docker-entrypoint.sh | 2 +- .../rocprofiler-compute/grafana/grafana.ini | 2 +- .../grafana/plugins/omniperf_plugin/README.md | 4 +- .../plugins/omniperf_plugin/package.json | 4 +- .../omniperf_plugin/server/mongo-proxy.js | 2 +- ...cle.png => rocprofiler-compute_circle.png} | Bin .../plugins/omniperf_plugin/src/plugin.json | 10 +- projects/rocprofiler-compute/pyproject.toml | 6 +- projects/rocprofiler-compute/src/README.md | 8 +- projects/rocprofiler-compute/src/argparser.py | 64 +- projects/rocprofiler-compute/src/config.py | 4 +- .../src/{omniperf => rocprof-compute} | 24 +- .../analysis_base.py | 27 +- .../analysis_cli.py | 24 +- .../analysis_webui.py | 18 +- .../assets/default.css | 0 .../assets/font-awesome/css/font-awesome.css | 0 .../font-awesome/css/font-awesome.min.css | 0 .../assets/font-awesome/fonts/FontAwesome.otf | Bin .../fonts/fontawesome-webfont.eot | Bin .../fonts/fontawesome-webfont.svg | 0 .../fonts/fontawesome-webfont.ttf | Bin .../fonts/fontawesome-webfont.woff | Bin .../font-awesome/less/bordered-pulled.less | 0 .../assets/font-awesome/less/core.less | 0 .../assets/font-awesome/less/fixed-width.less | 0 .../font-awesome/less/font-awesome.less | 0 .../assets/font-awesome/less/icons.less | 0 .../assets/font-awesome/less/larger.less | 0 .../assets/font-awesome/less/list.less | 0 .../assets/font-awesome/less/mixins.less | 0 .../assets/font-awesome/less/path.less | 0 .../font-awesome/less/rotated-flipped.less | 0 .../assets/font-awesome/less/spinning.less | 0 .../assets/font-awesome/less/stacked.less | 0 .../assets/font-awesome/less/variables.less | 0 .../font-awesome/scss/_bordered-pulled.scss | 0 .../assets/font-awesome/scss/_core.scss | 0 .../font-awesome/scss/_fixed-width.scss | 0 .../assets/font-awesome/scss/_icons.scss | 0 .../assets/font-awesome/scss/_larger.scss | 0 .../assets/font-awesome/scss/_list.scss | 0 .../assets/font-awesome/scss/_mixins.scss | 0 .../assets/font-awesome/scss/_path.scss | 0 .../font-awesome/scss/_rotated-flipped.scss | 0 .../assets/font-awesome/scss/_spinning.scss | 0 .../assets/font-awesome/scss/_stacked.scss | 0 .../assets/font-awesome/scss/_variables.scss | 0 .../font-awesome/scss/font-awesome.scss | 0 .../assets/fontello/css/animation.css | 0 .../assets/fontello/css/fontello-codes.css | 0 .../assets/fontello/css/fontello-embedded.css | 0 .../fontello/css/fontello-ie7-codes.css | 0 .../assets/fontello/css/fontello-ie7.css | 0 .../assets/fontello/css/fontello.css | 0 .../assets/fontello/font/fontello.eot | Bin .../assets/fontello/font/fontello.svg | 0 .../assets/fontello/font/fontello.ttf | Bin .../assets/fontello/font/fontello.woff | Bin .../assets/fonts.css | 0 .../librebaskerville-bold-webfont.eot | Bin .../librebaskerville-bold-webfont.svg | 0 .../librebaskerville-bold-webfont.ttf | Bin .../librebaskerville-bold-webfont.woff | Bin .../librebaskerville-italic-webfont.eot | Bin .../librebaskerville-italic-webfont.svg | 0 .../librebaskerville-italic-webfont.ttf | Bin .../librebaskerville-italic-webfont.woff | Bin .../librebaskerville-regular-webfont.eot | Bin .../librebaskerville-regular-webfont.svg | 0 .../librebaskerville-regular-webfont.ttf | Bin .../librebaskerville-regular-webfont.woff | Bin .../fonts/opensans/OpenSans-Bold-webfont.eot | Bin .../fonts/opensans/OpenSans-Bold-webfont.svg | 0 .../fonts/opensans/OpenSans-Bold-webfont.ttf | Bin .../fonts/opensans/OpenSans-Bold-webfont.woff | Bin .../opensans/OpenSans-BoldItalic-webfont.eot | Bin .../opensans/OpenSans-BoldItalic-webfont.svg | 0 .../opensans/OpenSans-BoldItalic-webfont.ttf | Bin .../opensans/OpenSans-BoldItalic-webfont.woff | Bin .../opensans/OpenSans-ExtraBold-webfont.eot | Bin .../opensans/OpenSans-ExtraBold-webfont.svg | 0 .../opensans/OpenSans-ExtraBold-webfont.ttf | Bin .../opensans/OpenSans-ExtraBold-webfont.woff | Bin .../OpenSans-ExtraBoldItalic-webfont.eot | Bin .../OpenSans-ExtraBoldItalic-webfont.svg | 0 .../OpenSans-ExtraBoldItalic-webfont.ttf | Bin .../OpenSans-ExtraBoldItalic-webfont.woff | Bin .../opensans/OpenSans-Italic-webfont.eot | Bin .../opensans/OpenSans-Italic-webfont.svg | 0 .../opensans/OpenSans-Italic-webfont.ttf | Bin .../opensans/OpenSans-Italic-webfont.woff | Bin .../fonts/opensans/OpenSans-Light-webfont.eot | Bin .../fonts/opensans/OpenSans-Light-webfont.svg | 0 .../fonts/opensans/OpenSans-Light-webfont.ttf | Bin .../opensans/OpenSans-Light-webfont.woff | Bin .../opensans/OpenSans-LightItalic-webfont.eot | Bin .../opensans/OpenSans-LightItalic-webfont.svg | 0 .../opensans/OpenSans-LightItalic-webfont.ttf | Bin .../OpenSans-LightItalic-webfont.woff | Bin .../opensans/OpenSans-Regular-webfont.eot | Bin .../opensans/OpenSans-Regular-webfont.svg | 0 .../opensans/OpenSans-Regular-webfont.ttf | Bin .../opensans/OpenSans-Regular-webfont.woff | Bin .../opensans/OpenSans-Semibold-webfont.eot | Bin .../opensans/OpenSans-Semibold-webfont.svg | 0 .../opensans/OpenSans-Semibold-webfont.ttf | Bin .../opensans/OpenSans-Semibold-webfont.woff | Bin .../OpenSans-SemiboldItalic-webfont.eot | Bin .../OpenSans-SemiboldItalic-webfont.svg | 0 .../OpenSans-SemiboldItalic-webfont.ttf | Bin .../OpenSans-SemiboldItalic-webfont.woff | Bin .../assets/layout.css | 0 .../assets/magnific-popup.css | 0 .../assets/media-queries.css | 0 ...niperf_base.py => rocprof_compute_base.py} | 48 +- .../profiler_base.py | 11 +- .../profiler_rocprof_v1.py | 4 +- .../profiler_rocprof_v2.py | 4 +- .../profiler_rocscope.py | 7 +- .../gfx906/0000_top_stats.yaml | 0 .../gfx906/0100_system_info.yaml | 0 .../gfx906/0200_system-speed-of-light.yaml | 0 .../gfx906/0300_mem_chart.yaml | 0 .../gfx906/0500_command-processor.yaml | 0 .../gfx906/0600_shader-processor-input.yaml | 0 .../gfx906/0700_wavefront-launch.yaml | 0 .../1000_compute-unit-instruction-mix.yaml | 0 .../1100_compute-unit-compute-pipeline.yaml | 0 .../analysis_configs/gfx906/1200_lds.yaml | 0 .../gfx906/1300_instruction-cache.yaml | 0 .../gfx906/1400_constant-cache.yaml | 0 .../gfx906/1500_TA_and_TD.yaml | 0 .../gfx906/1600_L1_cache.yaml | 0 .../gfx906/1700_L2_cache.yaml | 0 .../gfx906/1800_L2_cache_per_channel.yaml | 0 .../gfx908/0000_top_stats.yaml | 0 .../gfx908/0100_system_info.yaml | 0 .../gfx908/0200_system-speed-of-light.yaml | 0 .../gfx908/0300_mem_chart.yaml | 0 .../gfx908/0500_command-processor.yaml | 0 .../gfx908/0600_shader-processor-input.yaml | 0 .../gfx908/0700_wavefront-launch.yaml | 0 .../1000_compute-unit-instruction-mix.yaml | 0 .../1100_compute-unit-compute-pipeline.yaml | 0 .../analysis_configs/gfx908/1200_lds.yaml | 0 .../gfx908/1300_instruction-cache.yaml | 0 .../gfx908/1400_constant-cache.yaml | 0 .../gfx908/1500_TA_and_TD.yaml | 0 .../gfx908/1600_L1_cache.yaml | 0 .../gfx908/1700_L2_cache.yaml | 0 .../gfx908/1800_L2_cache_per_channel.yaml | 0 .../gfx90a/0000_top_stats.yaml | 0 .../gfx90a/0100_system_info.yaml | 0 .../gfx90a/0200_system-speed-of-light.yaml | 0 .../gfx90a/0300_mem_chart.yaml | 0 .../gfx90a/0400_roofline_chart.yaml | 0 .../gfx90a/0500_command-processor.yaml | 0 .../gfx90a/0600_shader-processor-input.yaml | 0 .../gfx90a/0700_wavefront-launch.yaml | 0 .../1000_compute-unit-instruction-mix.yaml | 0 .../1100_compute-unit-compute-pipeline.yaml | 0 .../analysis_configs/gfx90a/1200_lds.yaml | 0 .../gfx90a/1300_instruction-cache.yaml | 0 .../gfx90a/1400_constant-cache.yaml | 0 .../gfx90a/1500_TA_and_TD.yaml | 0 .../gfx90a/1600_L1_cache.yaml | 0 .../gfx90a/1700_L2_cache.yaml | 0 .../gfx90a/1800_L2_cache_per_channel.yaml | 0 .../gfx940/0000_top_stats.yaml | 0 .../gfx940/0100_system_info.yaml | 0 .../gfx940/0200_system-speed-of-light.yaml | 0 .../gfx940/0300_mem_chart.yaml | 0 .../gfx940/0500_command-processor.yaml | 0 .../gfx940/0600_shader-processor-input.yaml | 0 .../gfx940/0700_wavefront-launch.yaml | 0 .../1000_compute-unit-instruction-mix.yaml | 0 .../1100_compute-unit-compute-pipeline.yaml | 0 .../analysis_configs/gfx940/1200_lds.yaml | 0 .../gfx940/1300_instruction-cache.yaml | 0 .../gfx940/1400_constant-cache.yaml | 0 .../gfx940/1500_TA_and_TD.yaml | 0 .../gfx940/1600_L1_cache.yaml | 0 .../gfx940/1700_L2_cache.yaml | 0 .../gfx940/1800_L2_cache_per_channel.yaml | 0 .../gfx941/0000_top_stats.yaml | 0 .../gfx941/0100_system_info.yaml | 0 .../gfx941/0200_system-speed-of-light.yaml | 0 .../gfx941/0300_mem_chart.yaml | 0 .../gfx941/0500_command-processor.yaml | 0 .../gfx941/0600_shader-processor-input.yaml | 0 .../gfx941/0700_wavefront-launch.yaml | 0 .../1000_compute-unit-instruction-mix.yaml | 0 .../1100_compute-unit-compute-pipeline.yaml | 0 .../analysis_configs/gfx941/1200_lds.yaml | 0 .../gfx941/1300_instruction-cache.yaml | 0 .../gfx941/1400_constant-cache.yaml | 0 .../gfx941/1500_TA_and_TD.yaml | 0 .../gfx941/1600_L1_cache.yaml | 0 .../gfx941/1700_L2_cache.yaml | 0 .../gfx941/1800_L2_cache_per_channel.yaml | 0 .../gfx942/0000_top_stats.yaml | 0 .../gfx942/0100_system_info.yaml | 0 .../gfx942/0200_system-speed-of-light.yaml | 0 .../gfx942/0300_mem_chart.yaml | 0 .../gfx942/0500_command-processor.yaml | 0 .../gfx942/0600_shader-processor-input.yaml | 0 .../gfx942/0700_wavefront-launch.yaml | 0 .../1000_compute-unit-instruction-mix.yaml | 0 .../1100_compute-unit-compute-pipeline.yaml | 0 .../analysis_configs/gfx942/1200_lds.yaml | 0 .../gfx942/1300_instruction-cache.yaml | 0 .../gfx942/1400_constant-cache.yaml | 0 .../gfx942/1500_TA_and_TD.yaml | 0 .../gfx942/1600_L1_cache.yaml | 0 .../gfx942/1700_L2_cache.yaml | 0 .../gfx942/1800_L2_cache_per_channel.yaml | 0 .../panel_config_template.yaml | 0 .../profile_configs/gfx900/pmc_cpc_perf.txt | 0 .../profile_configs/gfx900/pmc_cpf_perf.txt | 0 .../profile_configs/gfx900/pmc_spi_perf.txt | 0 .../profile_configs/gfx900/pmc_sq_perf1.txt | 0 .../profile_configs/gfx900/pmc_sq_perf2.txt | 0 .../profile_configs/gfx900/pmc_sq_perf3.txt | 0 .../profile_configs/gfx900/pmc_sq_perf4.txt | 0 .../profile_configs/gfx900/pmc_sq_perf6.txt | 0 .../profile_configs/gfx900/pmc_sq_perf8.txt | 0 .../profile_configs/gfx900/pmc_sqc_perf1.txt | 0 .../profile_configs/gfx900/pmc_ta_perf.txt | 0 .../profile_configs/gfx900/pmc_tcc2_perf.txt | 0 .../profile_configs/gfx900/pmc_tcc_perf.txt | 0 .../profile_configs/gfx900/pmc_tcp_perf.txt | 0 .../profile_configs/gfx900/pmc_td_perf.txt | 0 .../profile_configs/gfx906/pmc_cpc_perf.txt | 0 .../profile_configs/gfx906/pmc_cpf_perf.txt | 0 .../profile_configs/gfx906/pmc_spi_perf.txt | 0 .../profile_configs/gfx906/pmc_sq_perf1.txt | 0 .../profile_configs/gfx906/pmc_sq_perf2.txt | 0 .../profile_configs/gfx906/pmc_sq_perf3.txt | 0 .../profile_configs/gfx906/pmc_sq_perf4.txt | 0 .../profile_configs/gfx906/pmc_sq_perf6.txt | 0 .../profile_configs/gfx906/pmc_sq_perf8.txt | 0 .../profile_configs/gfx906/pmc_sqc_perf1.txt | 0 .../profile_configs/gfx906/pmc_ta_perf.txt | 0 .../profile_configs/gfx906/pmc_tcc2_perf.txt | 0 .../profile_configs/gfx906/pmc_tcc_perf.txt | 0 .../profile_configs/gfx906/pmc_tcp_perf.txt | 0 .../profile_configs/gfx906/pmc_td_perf.txt | 0 .../profile_configs/gfx908/pmc_cpc_perf.txt | 0 .../profile_configs/gfx908/pmc_cpf_perf.txt | 0 .../profile_configs/gfx908/pmc_spi_perf.txt | 0 .../profile_configs/gfx908/pmc_sq_perf1.txt | 0 .../profile_configs/gfx908/pmc_sq_perf2.txt | 0 .../profile_configs/gfx908/pmc_sq_perf3.txt | 0 .../profile_configs/gfx908/pmc_sq_perf4.txt | 0 .../profile_configs/gfx908/pmc_sq_perf6.txt | 0 .../profile_configs/gfx908/pmc_sq_perf8.txt | 0 .../profile_configs/gfx908/pmc_sqc_perf1.txt | 0 .../profile_configs/gfx908/pmc_ta_perf.txt | 0 .../profile_configs/gfx908/pmc_tcc2_perf.txt | 0 .../profile_configs/gfx908/pmc_tcc_perf.txt | 0 .../profile_configs/gfx908/pmc_tcp_perf.txt | 0 .../profile_configs/gfx908/pmc_td_perf.txt | 0 .../profile_configs/gfx908_metrics.xml | 0 .../profile_configs/gfx90a/pmc_cpc_perf.txt | 0 .../profile_configs/gfx90a/pmc_cpf_perf.txt | 0 .../profile_configs/gfx90a/pmc_spi_perf.txt | 0 .../profile_configs/gfx90a/pmc_sq_perf1.txt | 0 .../profile_configs/gfx90a/pmc_sq_perf2.txt | 0 .../profile_configs/gfx90a/pmc_sq_perf3.txt | 0 .../profile_configs/gfx90a/pmc_sq_perf4.txt | 0 .../profile_configs/gfx90a/pmc_sq_perf6.txt | 0 .../profile_configs/gfx90a/pmc_sq_perf8.txt | 0 .../profile_configs/gfx90a/pmc_sqc_perf1.txt | 0 .../profile_configs/gfx90a/pmc_ta_perf.txt | 0 .../profile_configs/gfx90a/pmc_tcc2_perf.txt | 0 .../profile_configs/gfx90a/pmc_tcc_perf.txt | 0 .../profile_configs/gfx90a/pmc_tcp_perf.txt | 0 .../profile_configs/gfx90a/pmc_td_perf.txt | 0 .../gfx90a/roofline/pmc_roof_perf.txt | 0 .../profile_configs/gfx940/pmc_cpc_perf.txt | 0 .../profile_configs/gfx940/pmc_cpf_perf.txt | 0 .../profile_configs/gfx940/pmc_spi_perf.txt | 0 .../profile_configs/gfx940/pmc_sq_perf1.txt | 0 .../profile_configs/gfx940/pmc_sq_perf2.txt | 0 .../profile_configs/gfx940/pmc_sq_perf3.txt | 0 .../profile_configs/gfx940/pmc_sq_perf4.txt | 0 .../profile_configs/gfx940/pmc_sq_perf6.txt | 0 .../profile_configs/gfx940/pmc_sq_perf8.txt | 0 .../profile_configs/gfx940/pmc_sqc_perf1.txt | 0 .../profile_configs/gfx940/pmc_ta_perf.txt | 0 .../profile_configs/gfx940/pmc_tcc2_perf.txt | 0 .../profile_configs/gfx940/pmc_tcc_perf.txt | 0 .../profile_configs/gfx940/pmc_tcp_perf.txt | 0 .../profile_configs/gfx940/pmc_td_perf.txt | 0 .../gfx940/roofline/pmc_roof_perf.txt | 0 .../profile_configs/metrics.xml | 0 .../soc_base.py | 4 +- .../soc_gfx906.py | 6 +- .../soc_gfx908.py | 12 +- .../soc_gfx90a.py | 17 +- .../soc_gfx940.py | 11 +- .../soc_gfx941.py | 11 +- .../soc_gfx942.py | 21 +- projects/rocprofiler-compute/src/roofline.py | 4 +- .../src/utils/db_connector.py | 9 +- .../src/utils/gui_components/header.py | 2 +- .../rocprofiler-compute/src/utils/logger.py | 12 +- .../src/utils/mem_chart.py | 4 +- .../src/utils/resources.py | 2 +- .../rocprofiler-compute/src/utils/specs.py | 13 +- .../rocprofiler-compute/src/utils/utils.py | 20 +- projects/rocprofiler-compute/tests/4gpus.json | 33 +- .../tests/generate_test_analyze_workloads.py | 4 +- .../tests/generate_workloads.sh | 4 +- .../tests/test_analyze_commands.py | 276 ++--- .../tests/test_analyze_workloads.py | 1069 +++++++++++++---- .../tests/test_import_workloads.py | 826 ++++++------- .../tests/test_profile_general.py | 100 +- .../rocprofiler-compute/tests/test_utils.py | 2 +- .../multikernel/MI200/SQ_IFETCH_LEVEL.csv | 8 - .../multikernel/MI200/SQ_INST_LEVEL_LDS.csv | 8 - .../multikernel/MI200/SQ_INST_LEVEL_SMEM.csv | 8 - .../multikernel/MI200/SQ_INST_LEVEL_VMEM.csv | 8 - .../multikernel/MI200/SQ_LEVEL_WAVES.csv | 8 - .../tests/workloads/multikernel/MI200/log.txt | 270 ----- .../MI200/perfmon/SQ_IFETCH_LEVEL.txt | 5 - .../MI200/perfmon/SQ_INST_LEVEL_LDS.txt | 5 - .../MI200/perfmon/SQ_INST_LEVEL_SMEM.txt | 5 - .../MI200/perfmon/SQ_INST_LEVEL_VMEM.txt | 5 - .../MI200/perfmon/SQ_LEVEL_WAVES.txt | 5 - .../multikernel/MI200/perfmon/pmc_perf_0.txt | 5 - .../multikernel/MI200/perfmon/pmc_perf_1.txt | 5 - .../multikernel/MI200/perfmon/pmc_perf_2.txt | 5 - .../multikernel/MI200/perfmon/pmc_perf_3.txt | 5 - .../multikernel/MI200/perfmon/pmc_perf_4.txt | 5 - .../multikernel/MI200/perfmon/pmc_perf_5.txt | 5 - .../multikernel/MI200/perfmon/pmc_perf_6.txt | 5 - .../multikernel/MI200/perfmon/pmc_perf_7.txt | 5 - .../multikernel/MI200/perfmon/pmc_perf_8.txt | 5 - .../multikernel/MI200/perfmon/pmc_perf_9.txt | 5 - .../multikernel/MI200/perfmon/timestamps.txt | 5 - .../multikernel/MI200/pmc_dispatch_info.csv | 8 - .../workloads/multikernel/MI200/pmc_perf.csv | 8 - .../workloads/multikernel/MI200/roofline.csv | 4 - .../workloads/multikernel/MI200/sysinfo.csv | 2 - .../multikernel/MI200/timestamps.csv | 8 - projects/rocprofiler-compute/utils/build.sh | 18 +- 379 files changed, 1976 insertions(+), 1843 deletions(-) rename projects/rocprofiler-compute/cmake/{omniperf.lua.in => rocprofcompute.lua.in} (59%) rename projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/src/img/{omniperf_circle.png => rocprofiler-compute_circle.png} (100%) rename projects/rocprofiler-compute/src/{omniperf => rocprof-compute} (89%) mode change 100755 => 100644 rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/analysis_base.py (90%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/analysis_cli.py (79%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/analysis_webui.py (96%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/default.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/css/font-awesome.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/css/font-awesome.min.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/fonts/FontAwesome.otf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/fonts/fontawesome-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/fonts/fontawesome-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/fonts/fontawesome-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/fonts/fontawesome-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/bordered-pulled.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/core.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/fixed-width.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/font-awesome.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/icons.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/larger.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/list.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/mixins.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/path.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/rotated-flipped.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/spinning.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/stacked.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/less/variables.less (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_bordered-pulled.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_core.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_fixed-width.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_icons.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_larger.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_list.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_mixins.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_path.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_rotated-flipped.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_spinning.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_stacked.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/_variables.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/font-awesome/scss/font-awesome.scss (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fontello/css/animation.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fontello/css/fontello-codes.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fontello/css/fontello-embedded.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fontello/css/fontello-ie7-codes.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fontello/css/fontello-ie7.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fontello/css/fontello.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fontello/font/fontello.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fontello/font/fontello.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fontello/font/fontello.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fontello/font/fontello.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-bold-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-bold-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-bold-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-bold-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-italic-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-italic-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-italic-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-italic-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-regular-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-regular-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-regular-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/librebaskerville/librebaskerville-regular-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Bold-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Bold-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Bold-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Bold-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-BoldItalic-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-BoldItalic-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-BoldItalic-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-BoldItalic-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-ExtraBold-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-ExtraBold-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-ExtraBold-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-ExtraBold-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Italic-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Italic-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Italic-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Italic-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Light-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Light-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Light-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Light-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-LightItalic-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-LightItalic-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-LightItalic-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-LightItalic-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Regular-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Regular-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Regular-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Regular-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Semibold-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Semibold-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Semibold-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-Semibold-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.eot (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.svg (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.ttf (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.woff (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/layout.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/magnific-popup.css (100%) rename projects/rocprofiler-compute/src/{omniperf_analyze => rocprof_compute_analyze}/assets/media-queries.css (100%) rename projects/rocprofiler-compute/src/{omniperf_base.py => rocprof_compute_base.py} (84%) rename projects/rocprofiler-compute/src/{omniperf_profile => rocprof_compute_profile}/profiler_base.py (97%) rename projects/rocprofiler-compute/src/{omniperf_profile => rocprof_compute_profile}/profiler_rocprof_v1.py (96%) rename projects/rocprofiler-compute/src/{omniperf_profile => rocprof_compute_profile}/profiler_rocprof_v2.py (96%) rename projects/rocprofiler-compute/src/{omniperf_profile => rocprof_compute_profile}/profiler_rocscope.py (91%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/0000_top_stats.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/0100_system_info.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/0200_system-speed-of-light.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/0300_mem_chart.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/0500_command-processor.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/0600_shader-processor-input.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/0700_wavefront-launch.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/1000_compute-unit-instruction-mix.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/1100_compute-unit-compute-pipeline.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/1200_lds.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/1300_instruction-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/1400_constant-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/1500_TA_and_TD.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/1600_L1_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/1700_L2_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx906/1800_L2_cache_per_channel.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/0000_top_stats.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/0100_system_info.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/0200_system-speed-of-light.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/0300_mem_chart.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/0500_command-processor.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/0600_shader-processor-input.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/0700_wavefront-launch.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/1000_compute-unit-instruction-mix.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/1100_compute-unit-compute-pipeline.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/1200_lds.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/1300_instruction-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/1400_constant-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/1500_TA_and_TD.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/1600_L1_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/1700_L2_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx908/1800_L2_cache_per_channel.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/0000_top_stats.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/0100_system_info.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/0200_system-speed-of-light.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/0300_mem_chart.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/0400_roofline_chart.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/0500_command-processor.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/0600_shader-processor-input.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/0700_wavefront-launch.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/1000_compute-unit-instruction-mix.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/1100_compute-unit-compute-pipeline.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/1200_lds.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/1300_instruction-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/1400_constant-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/1500_TA_and_TD.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/1600_L1_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/1700_L2_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx90a/1800_L2_cache_per_channel.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/0000_top_stats.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/0100_system_info.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/0200_system-speed-of-light.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/0300_mem_chart.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/0500_command-processor.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/0600_shader-processor-input.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/0700_wavefront-launch.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/1000_compute-unit-instruction-mix.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/1100_compute-unit-compute-pipeline.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/1200_lds.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/1300_instruction-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/1400_constant-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/1500_TA_and_TD.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/1600_L1_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/1700_L2_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx940/1800_L2_cache_per_channel.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/0000_top_stats.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/0100_system_info.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/0200_system-speed-of-light.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/0300_mem_chart.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/0500_command-processor.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/0600_shader-processor-input.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/0700_wavefront-launch.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/1000_compute-unit-instruction-mix.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/1100_compute-unit-compute-pipeline.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/1200_lds.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/1300_instruction-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/1400_constant-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/1500_TA_and_TD.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/1600_L1_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/1700_L2_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx941/1800_L2_cache_per_channel.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/0000_top_stats.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/0100_system_info.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/0200_system-speed-of-light.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/0300_mem_chart.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/0500_command-processor.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/0600_shader-processor-input.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/0700_wavefront-launch.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/1000_compute-unit-instruction-mix.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/1100_compute-unit-compute-pipeline.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/1200_lds.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/1300_instruction-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/1400_constant-cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/1500_TA_and_TD.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/1600_L1_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/1700_L2_cache.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/gfx942/1800_L2_cache_per_channel.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/analysis_configs/panel_config_template.yaml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_cpc_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_cpf_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_spi_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_sq_perf1.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_sq_perf2.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_sq_perf3.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_sq_perf4.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_sq_perf6.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_sq_perf8.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_sqc_perf1.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_ta_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_tcc2_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_tcc_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_tcp_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx900/pmc_td_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_cpc_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_cpf_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_spi_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_sq_perf1.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_sq_perf2.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_sq_perf3.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_sq_perf4.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_sq_perf6.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_sq_perf8.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_sqc_perf1.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_ta_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_tcc2_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_tcc_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_tcp_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx906/pmc_td_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_cpc_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_cpf_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_spi_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_sq_perf1.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_sq_perf2.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_sq_perf3.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_sq_perf4.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_sq_perf6.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_sq_perf8.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_sqc_perf1.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_ta_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_tcc2_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_tcc_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_tcp_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908/pmc_td_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx908_metrics.xml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_cpc_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_cpf_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_spi_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_sq_perf1.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_sq_perf2.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_sq_perf3.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_sq_perf4.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_sq_perf6.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_sq_perf8.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_sqc_perf1.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_ta_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_tcc2_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_tcc_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_tcp_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/pmc_td_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx90a/roofline/pmc_roof_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_cpc_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_cpf_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_spi_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_sq_perf1.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_sq_perf2.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_sq_perf3.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_sq_perf4.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_sq_perf6.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_sq_perf8.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_sqc_perf1.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_ta_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_tcc2_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_tcc_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_tcp_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/pmc_td_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/gfx940/roofline/pmc_roof_perf.txt (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/profile_configs/metrics.xml (100%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/soc_base.py (99%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/soc_gfx906.py (95%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/soc_gfx908.py (90%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/soc_gfx90a.py (88%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/soc_gfx940.py (92%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/soc_gfx941.py (92%) rename projects/rocprofiler-compute/src/{omniperf_soc => rocprof_compute_soc}/soc_gfx942.py (88%) delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_IFETCH_LEVEL.csv delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_LDS.csv delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_SMEM.csv delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_VMEM.csv delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_LEVEL_WAVES.csv delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/log.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_LEVEL_WAVES.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_0.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_1.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_2.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_3.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_4.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_5.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_6.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_7.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_8.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_9.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/timestamps.txt delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_dispatch_info.csv delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_perf.csv delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/roofline.csv delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/sysinfo.csv delete mode 100644 projects/rocprofiler-compute/tests/workloads/multikernel/MI200/timestamps.csv diff --git a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.yaml b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.yaml index fd42b0ed20..cadebb3596 100644 --- a/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.yaml +++ b/projects/rocprofiler-compute/.github/ISSUE_TEMPLATE/bug_report.yaml @@ -38,13 +38,13 @@ body: required: true - type: input - id: omniperf-version + id: rocprofiler-compute-version attributes: - label: Omniperf Version + label: ROCm Compute Profiler Version description: | - What version of Omniperf are you using? Hint: + What version of ROCm Compute Profiler are you using? Hint: ```shell - omniperf --version + rocprof-compute --version ``` placeholder: e.g. 2.1.0 validations: @@ -115,7 +115,7 @@ body: id: logs attributes: label: Relevant log output - description: Please copy and paste Omniperf's `log.txt` file. This will be automatically formatted into code, so no need for backticks. + description: Please copy and paste rocprofiler-compute's `log.txt` file. This will be automatically formatted into code, so no need for backticks. render: shell - type: textarea diff --git a/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml b/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml index 4cc54454f9..01b0c78ae2 100644 --- a/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml +++ b/projects/rocprofiler-compute/.github/workflows/mi-rhel9.yml @@ -85,17 +85,17 @@ jobs: run: | cd build make - srun -N 1 -J omniperf -p $CI_QUEUE -t 00:20:00 ctest -j 4 --resource-spec-file ../tests/4gpus.json --verbose -L profile + srun -N 1 -J rocprof-compute -p $CI_QUEUE -t 00:20:00 ctest -j 4 --resource-spec-file ../tests/4gpus.json --verbose -L profile - name: Run [analyze workloads] mode if: '!cancelled()' run: | cd build - srun -N 1 -J omniperf -p $CI_QUEUE -t 00:10:00 ctest --verbose -R test_analyze_workloads + srun -N 1 -J rocprof-compute -p $CI_QUEUE -t 00:10:00 ctest --verbose -R test_analyze_workloads - name: Run [analyze commands] mode if: '!cancelled()' run: | cd build - srun -N 1 -J omniperf -p $CI_QUEUE -t 00:10:00 ctest --verbose -R test_analyze_commands + srun -N 1 -J rocprof-compute -p $CI_QUEUE -t 00:10:00 ctest --verbose -R test_analyze_commands - name: Publish Test Results uses: EnricoMi/publish-unit-test-result-action/linux@v2 if: always() diff --git a/projects/rocprofiler-compute/.github/workflows/packaging.yml b/projects/rocprofiler-compute/.github/workflows/packaging.yml index 2bf3e8f069..1feeccad7e 100644 --- a/projects/rocprofiler-compute/.github/workflows/packaging.yml +++ b/projects/rocprofiler-compute/.github/workflows/packaging.yml @@ -37,29 +37,29 @@ jobs: cd build make package_source - name: Rename tarball - run: mv build/omniperf-*.tar.gz build/omniperf-${{github.ref_name}}.tar.gz + run: mv build/rocprofiler-compute-*.tar.gz build/rocprofiler-compute-${{github.ref_name}}.tar.gz - name: Archive tarball uses: actions/upload-artifact@v4 with: - name: omniperf-${{github.ref_name}}.tar.gz - path: build/omniperf-${{github.ref_name}}.tar.gz + name: rocprofiler-compute-${{github.ref_name}}.tar.gz + path: build/rocprofiler-compute-${{github.ref_name}}.tar.gz - name: Set version run: echo "VERSION=$(cat VERSION)" >> $GITHUB_ENV - name: Determine release name run: | if [[ ${{github.ref_name}} == rocm-* ]]; then - echo "RELEASE_NAME=Omniperf ${{ env.VERSION }} for ${{github.ref_name}}" + echo "RELEASE_NAME=rocprofiler-compute ${{ env.VERSION }} for ${{github.ref_name}}" else - echo "RELEASE_NAME=Omniperf ${{ env.VERSION }}" + echo "RELEASE_NAME=rocprofiler-compute ${{ env.VERSION }}" fi >> $GITHUB_ENV - name: Upload tarball Release Asset uses: softprops/action-gh-release@v2 - if: startsWith(github.ref, 'refs/tags/') && github.repository == 'ROCm/omniperf' + if: startsWith(github.ref, 'refs/tags/') && github.repository == 'ROCm/rocprofiler-compute' with: fail_on_unmatched: True generate_release_notes: True draft: False # toggle for debugging files: | - build/omniperf-${{github.ref_name}}.tar.gz + build/rocprofiler-compute-${{github.ref_name}}.tar.gz name: ${{ env.RELEASE_NAME }} diff --git a/projects/rocprofiler-compute/.github/workflows/rhel-8.yml b/projects/rocprofiler-compute/.github/workflows/rhel-8.yml index 01dfad5910..16ecc35e28 100644 --- a/projects/rocprofiler-compute/.github/workflows/rhel-8.yml +++ b/projects/rocprofiler-compute/.github/workflows/rhel-8.yml @@ -42,7 +42,7 @@ jobs: run: | mkdir build cd build - cmake -DCMAKE_INSTALL_PREFIX=/opt/omniperf -DPYTEST_NUMPROCS=4 .. + cmake -DCMAKE_INSTALL_PREFIX=/opt/rocprofiler-compute -DPYTEST_NUMPROCS=4 .. make install - name: CTest- Analyze Commands run: | diff --git a/projects/rocprofiler-compute/.github/workflows/tarball.yml b/projects/rocprofiler-compute/.github/workflows/tarball.yml index 9ad5cfc9e9..13cbfcc65b 100644 --- a/projects/rocprofiler-compute/.github/workflows/tarball.yml +++ b/projects/rocprofiler-compute/.github/workflows/tarball.yml @@ -8,7 +8,7 @@ on: concurrency: group: ${{ github.workflow }}-${{ github.ref }} cancel-in-progress: true - + jobs: distbuild: runs-on: ubuntu-latest @@ -47,7 +47,7 @@ jobs: uses: actions/upload-artifact@v4 with: name: tarball-testing - path: build/omniperf-*.tar.gz + path: build/rocprofiler-compute-*.tar.gz retention-days: 3 disttest: runs-on: ubuntu-latest @@ -61,47 +61,47 @@ jobs: with: name: tarball-testing - name: Expand - run: tar xfz omniperf-*.tar.gz; rm omniperf-*.tar.gz + run: tar xfz rocprofiler-compute-*.tar.gz; rm rocprofiler-compute-*.tar.gz - name: Python dependency installs run: | - cd omniperf-* + cd rocprofiler-compute-* python3 -m pip install -t${INSTALL_DIR}/python-libs -r requirements.txt - name: Configure run: | - cd omniperf-* + cd rocprofiler-compute-* mkdir build cd build - cmake -DCMAKE_INSTALL_PREFIX=${INSTALL_DIR}/omniperf \ + cmake -DCMAKE_INSTALL_PREFIX=${INSTALL_DIR}/rocprofiler-compute \ -DPYTHON_DEPS=${INSTALL_DIR}/python-libs .. - name: Install run: | - cd omniperf-* + cd rocprofiler-compute-* cd build make install - name: Verify expected paths run: | # find $INSTALL_DIR - test -d $INSTALL_DIR/omniperf - test -x $INSTALL_DIR/omniperf/bin/omniperf - test -s $INSTALL_DIR/omniperf/libexec/omniperf/VERSION - test -s $INSTALL_DIR/omniperf/libexec/omniperf/VERSION.sha - test -d $INSTALL_DIR/omniperf/libexec/omniperf/omniperf_analyze - test -d $INSTALL_DIR/omniperf/libexec/omniperf/omniperf_profile - test -d $INSTALL_DIR/omniperf/libexec/omniperf/omniperf_soc - test -d $INSTALL_DIR/omniperf/libexec/omniperf/utils - test -s $INSTALL_DIR/omniperf/share/omniperf/sample/vcopy.cpp - test -d $INSTALL_DIR/omniperf/share/omniperf/modulefiles + test -d $INSTALL_DIR/rocprofiler-compute + test -x $INSTALL_DIR/rocprofiler-compute/bin/rocprof-compute + test -s $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/VERSION + test -s $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/VERSION.sha + test -d $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/rocprof_compute_analyze + test -d $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/rocprof_compute_profile + test -d $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/rocprof_compute_soc + test -d $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/utils + test -s $INSTALL_DIR/rocprofiler-compute/share/rocprofiler-compute/sample/vcopy.cpp + test -d $INSTALL_DIR/rocprofiler-compute/share/rocprofiler-compute/modulefiles - name: Query version (setting PYTHONPATH by hand) run: | export PYTHONPATH=${INSTALL_DIR}/python-libs:$PYTHONPATH - $INSTALL_DIR/omniperf/bin/omniperf --version + $INSTALL_DIR/rocprofiler-compute/bin/rocprof-compute --version - name: Install Lmod run: sudo apt-get install -y lmod - - name: Access omniperf using modulefile + - name: Access rocprofiler-compute using modulefile run: | . /etc/profile.d/lmod.sh - module use $INSTALL_DIR/omniperf/share/omniperf/modulefiles - module load omniperf + module use $INSTALL_DIR/rocprofiler-compute/share/rocprofiler-compute/modulefiles + module load rocprofiler-compute module list - omniperf --version + rocprof-compute --version diff --git a/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml b/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml index 1dbf06b59c..9233f55c60 100644 --- a/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml +++ b/projects/rocprofiler-compute/.github/workflows/ubuntu-jammy.yml @@ -41,7 +41,7 @@ jobs: run: | mkdir build cd build - cmake -DCMAKE_INSTALL_PREFIX=/opt/omniperf -DPYTEST_NUMPROCS=4 .. + cmake -DCMAKE_INSTALL_PREFIX=/opt/rocprofiler-compute -DPYTEST_NUMPROCS=4 .. make install - name: CTest- Analyze Commands run: | diff --git a/projects/rocprofiler-compute/AUTHORS b/projects/rocprofiler-compute/AUTHORS index ee4978b2b5..48bc2a9ece 100644 --- a/projects/rocprofiler-compute/AUTHORS +++ b/projects/rocprofiler-compute/AUTHORS @@ -1,4 +1,4 @@ -# This is the list of Omniperf's significant contributors. +# This is the list of ROCm Compute Profiler's significant contributors. # # This does not necessarily list everyone who has contributed code, # especially since many employees of one corporation may be contributing. diff --git a/projects/rocprofiler-compute/CHANGELOG.md b/projects/rocprofiler-compute/CHANGELOG.md index 2721d3749e..5c18aeb8c1 100644 --- a/projects/rocprofiler-compute/CHANGELOG.md +++ b/projects/rocprofiler-compute/CHANGELOG.md @@ -1,6 +1,6 @@ -# Changelog for Omniperf +# Changelog for ROCm Compute Profiler -Full documentation for Omniperf is available at [https://rocm.docs.amd.com/projects/omniperf/en/latest/](https://rocm.docs.amd.com/projects/omniperf/en/latest/). +Full documentation for ROCm Compute Profiler is available at [https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/](https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/). ## Omniperf 2.1.0 for ROCm 6.2.2 diff --git a/projects/rocprofiler-compute/CMakeLists.txt b/projects/rocprofiler-compute/CMakeLists.txt index b945bc9b5b..8f35fbd6a1 100644 --- a/projects/rocprofiler-compute/CMakeLists.txt +++ b/projects/rocprofiler-compute/CMakeLists.txt @@ -16,20 +16,27 @@ message(STATUS "Hostname: ${LOCALHOST}") # Versioning info derived from file file(READ "${CMAKE_CURRENT_SOURCE_DIR}/VERSION" FULL_VERSION_STRING LIMIT_COUNT 1) string(REGEX REPLACE "(\n|\r)" "" FULL_VERSION_STRING "${FULL_VERSION_STRING}") -set(OMNIPERF_FULL_VERSION "${FULL_VERSION_STRING}") -string(REGEX REPLACE "([0-9]+)\.([0-9]+)\.([0-9]+)(.*)" "\\1.\\2.\\3" OMNIPERF_VERSION - "${FULL_VERSION_STRING}") +set(ROCPROFCOMPUTE_FULL_VERSION "${FULL_VERSION_STRING}") +string(REGEX REPLACE "([0-9]+)\.([0-9]+)\.([0-9]+)(.*)" "\\1.\\2.\\3" + ROCPROFCOMPUTE_VERSION "${FULL_VERSION_STRING}") -# string(REGEX REPLACE "(${OMNIPERF_VERSION})(.*)" "\\2" OMNIPERF_VERSION_TWEAK +# string(REGEX REPLACE "(${ROCPROFCOMPUTE_VERSION})(.*)" "\\2" +# ROCPROFCOMPUTE_VERSION_TWEAK # "${FULL_VERSION_STRING}") -# string(REGEX REPLACE "^\\." "" OMNIPERF_VERSION_TWEAK "${OMNIPERF_VERSION_TWEAK}") +# string(REGEX REPLACE "^\\." "" ROCPROFCOMPUTE_VERSION_TWEAK +# "${ROCPROFCOMPUTE_VERSION_TWEAK}") project( - omniperf - VERSION ${OMNIPERF_VERSION} + rocprofiler-compute + VERSION ${ROCPROFCOMPUTE_VERSION} LANGUAGES C - DESCRIPTION "OmniPerf" - HOMEPAGE_URL "https://github.com/ROCm/omniperf") + DESCRIPTION + "A kernel-level profiling tool for machine learning/HPC workloads running on AMD MI GPUs" + HOMEPAGE_URL "https://github.com/ROCm/rocprofiler-compute") + +set(PACKAGE_NAME "rocprofiler-compute") +set(PACKAGE_NAME_UNDERSCORE "rocprofiler_compute") +set(EXECUTABLE_NAME "rocprof-compute") include(ExternalProject) include(GNUInstallDirs) @@ -39,9 +46,9 @@ find_package(Git) if(Git_FOUND AND EXISTS "${PROJECT_SOURCE_DIR}/.git") execute_process( COMMAND git log --pretty=format:%h -n 1 - OUTPUT_VARIABLE OMNIPERF_GIT_REV + OUTPUT_VARIABLE ROCPROFCOMPUTE_GIT_REV OUTPUT_STRIP_TRAILING_WHITESPACE) - message(STATUS "Git revision: ${OMNIPERF_GIT_REV}") + message(STATUS "Git revision: ${ROCPROFCOMPUTE_GIT_REV}") set(GIT_CLONE TRUE) else() set(GIT_CLONE FALSER) @@ -133,18 +140,19 @@ set(MOD_INSTALL_PATH CACHE STRING "Install path for modulefile") message(STATUS "Modulefile install path: ${MOD_INSTALL_PATH}") -set(moduleFileTemplate "omniperf.lua.in") +set(moduleFileTemplate "rocprofcompute.lua.in") configure_file( ${PROJECT_SOURCE_DIR}/cmake/${moduleFileTemplate} - ${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${OMNIPERF_FULL_VERSION}.lua @ONLY) + ${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${ROCPROFCOMPUTE_FULL_VERSION}.lua @ONLY) # Thera mods if(LOCALHOST MATCHES "TheraS01|.*\.thera\.amd\.com|thera-hn") list(APPEND CMAKE_MESSAGE_INDENT " ") message(STATUS "Using thera-specific modulefile modification") file(READ ${PROJECT_SOURCE_DIR}/cmake/modfile.thera.mod mod_additions) - file(APPEND ${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${OMNIPERF_FULL_VERSION}.lua + file(APPEND + ${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${ROCPROFCOMPUTE_FULL_VERSION}.lua ${mod_additions}) list(POP_BACK CMAKE_MESSAGE_INDENT) endif() @@ -274,9 +282,9 @@ add_test( # Install # --------- -# top-level omniperf utility +# top-level rocprofiler-compute utility install( - PROGRAMS src/omniperf + PROGRAMS src/${EXECUTABLE_NAME} DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME} COMPONENT main) # python dependency requirements @@ -286,16 +294,16 @@ install( COMPONENT main) # support files and version info install( - FILES src/argparser.py src/config.py src/omniperf_base.py src/roofline.py VERSION - VERSION.sha + FILES src/argparser.py src/config.py src/rocprof_compute_base.py src/roofline.py + VERSION VERSION.sha DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME} COMPONENT main) -# src/omniperf_analyze +# src/rocprof_compute_analyze install( - DIRECTORY src/omniperf_analyze + DIRECTORY src/rocprof_compute_analyze DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME} COMPONENT main - PATTERN src/omniperf_analyze/tests EXCLUDE + PATTERN src/rocprof_compute_analyze/tests EXCLUDE PATTERN "__pycache__" EXCLUDE) # src/utils install( @@ -310,15 +318,15 @@ install( PROGRAMS ${rooflinebins} DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT main) -# src/omniperf_soc +# src/rocprof_compute_soc install( - DIRECTORY src/omniperf_soc + DIRECTORY src/rocprof_compute_soc DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME} COMPONENT main PATTERN "__pycache__" EXCLUDE) -# src/omniperf_profile +# src/rocprof_compute_profile install( - DIRECTORY src/omniperf_profile + DIRECTORY src/rocprof_compute_profile DESTINATION ${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME} COMPONENT main PATTERN "__pycache__" EXCLUDE) @@ -339,16 +347,16 @@ install( PATTERN "workloads" EXCLUDE) # modulefile install( - FILES ${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${OMNIPERF_FULL_VERSION}.lua + FILES ${PROJECT_BINARY_DIR}/${MOD_INSTALL_PATH}/${ROCPROFCOMPUTE_FULL_VERSION}.lua DESTINATION ${MOD_INSTALL_PATH} COMPONENT main) -# top-level symlink for bin/omniperf +# top-level symlink for bin/rocprof-compute install( CODE "execute_process( COMMAND bash -c \"set -e cd \$ENV{DESTDIR}\${CMAKE_INSTALL_PREFIX} - ln -sf ../${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME}/omniperf ${CMAKE_INSTALL_BINDIR}/omniperf + ln -sf ../${CMAKE_INSTALL_LIBEXECDIR}/${PROJECT_NAME}/${EXECUTABLE_NAME} ${CMAKE_INSTALL_BINDIR}/${EXECUTABLE_NAME} \")" COMPONENT main) @@ -361,7 +369,7 @@ add_custom_target( COMMAND ${PROJECT_SOURCE_DIR}/utils/update_license.py --source ${PROJECT_SOURCE_DIR} --license ${PROJECT_SOURCE_DIR}/LICENSE --file - "src/omniperf,cmake/Dockerfile,cmake/rocm_install.sh,docker/docker-entrypoint.sh,src/omniperf_analyze/convertor/mongodb/convert" + "src/${PACKAGE_NAME},cmake/Dockerfile,cmake/rocm_install.sh,docker/docker-entrypoint.sh,src/rocprof_compute_analyze/convertor/mongodb/convert" ) # TEST collateral @@ -396,9 +404,11 @@ set(CPACK_GENERATOR set(CPACK_PACKAGE_NAME "${PROJECT_NAME}" CACHE STRING "") -set(CPACK_PACKAGE_CONTACT "https://github.com/ROCm/omniperf") -set(CPACK_PACKAGE_DESCRIPTION_SUMMARY "Omniperf: tool for GPU performance profiling") -set(CPACK_RPM_PACKAGE_DESCRIPTION "Omniperf is a performance analysis tool for profiling +set(CPACK_PACKAGE_CONTACT "https://github.com/ROCm/rocprofiler-compute") +set(CPACK_PACKAGE_DESCRIPTION_SUMMARY + "ROCm Compute Profiler: tool for GPU performance profiling") +set(CPACK_RPM_PACKAGE_DESCRIPTION + "ROCm Compute Profiler is a performance analysis tool for profiling machine learning/HPC workloads running on AMD GPUs.") set(CPACK_PACKAGE_VENDOR "Advanced Micro Devices, Inc.") diff --git a/projects/rocprofiler-compute/CONTRIBUTING.md b/projects/rocprofiler-compute/CONTRIBUTING.md index f18ea2ca24..640305b892 100644 --- a/projects/rocprofiler-compute/CONTRIBUTING.md +++ b/projects/rocprofiler-compute/CONTRIBUTING.md @@ -1,11 +1,11 @@ ## How to fork from us -To keep our development fast and conflict free, we recommend you to [fork](https://github.com/ROCm/omniperf/fork) our repository and start your work from our `amd-staging` branch in your private repository. +To keep our development fast and conflict free, we recommend you to [fork](https://github.com/ROCm/rocprofiler-compute/fork) our repository and start your work from our `amd-staging` branch in your private repository. Afterwards, git clone your repository to your local machine. But that is not it! To keep track of the original develop repository, add it as another remote. ``` -git remote add mainline https://github.com/ROCm/omniperf.git +git remote add mainline https://github.com/ROCm/rocprofiler-compute.git git checkout amd-staging ``` @@ -17,23 +17,23 @@ git checkout -b topic- and apply your changes there. -## How to contribute to Omniperf +## How to contribute to ROCm Compute Profiler ### Did you find a bug? -- Ensure the bug was not already reported by searching on GitHub under [Issues](https://github.com/ROCm/omniperf/issues). +- Ensure the bug was not already reported by searching on GitHub under [Issues](https://github.com/ROCm/rocprofiler-compute/issues). -- If you're unable to find an open issue addressing the problem, [open a new one](https://github.com/ROCm/omniperf/issues/new). +- If you're unable to find an open issue addressing the problem, [open a new one](https://github.com/ROCm/rocprofiler-compute/issues/new). ### Did you write a patch that fixes a bug? -- Open a new GitHub [pull request](https://github.com/ROCm/omniperf/compare) with the patch. +- Open a new GitHub [pull request](https://github.com/ROCm/rocprofiler-compute/compare) with the patch. - Ensure the PR description clearly describes the problem and solution. If there is an existing GitHub issue open describing this bug, please include it in the description so we can close it. -- Ensure the PR is based on the `amd-staging` branch of the Omniperf GitHub repository. +- Ensure the PR is based on the `amd-staging` branch of the ROCm Compute Profiler GitHub repository. -- Omniperf requires new commits to include a "Signed-off-by" token in the commit message (typically enabled via the `git commit -s` option), indicating your agreement to the projects's [Developer's Certificate of Origin](https://developercertificate.org/) and compatability with the project [LICENSE](LICENSE): +- ROCm Compute Profiler requires new commits to include a "Signed-off-by" token in the commit message (typically enabled via the `git commit -s` option), indicating your agreement to the projects's [Developer's Certificate of Origin](https://developercertificate.org/) and compatability with the project [LICENSE](LICENSE): > (a) The contribution was created in whole or in part by me and I diff --git a/projects/rocprofiler-compute/MAINTAINERS.md b/projects/rocprofiler-compute/MAINTAINERS.md index 0ee7f23dab..dbf64db3ea 100644 --- a/projects/rocprofiler-compute/MAINTAINERS.md +++ b/projects/rocprofiler-compute/MAINTAINERS.md @@ -1,11 +1,11 @@ -# Maintainers Guide to Omniperf +# Maintainers Guide to ROCm Compute Profiler ## Publishing a release -Before publishing a new Omniperf release, please review this checklist to ensure all prerequisites are met: +Before publishing a new ROCm Compute Profiler release, please review this checklist to ensure all prerequisites are met: 1) **Ensure [VERSION](VERSION) file is updated** to reflect your desired release version. -2) **Sync `amd-mainline` with `amd-staging`**. A rebase may be required to pull all the desired patches from the development branch to our stable mainline. Click [here](https://github.com/ROCm/omniperf/compare/amd-mainline...amd-staging) to begin that process. +2) **Sync `amd-mainline` with `amd-staging`**. A rebase may be required to pull all the desired patches from the development branch to our stable mainline. Click [here](https://github.com/ROCm/rocprofiler-compute/compare/amd-mainline...amd-staging) to begin that process. 3) **Update [CHANGES](CHANGES)** to reflect all major modifications to the codebase since the last release. When modifying [CHANGES](CHANGES) please ensure formatting is consistent with the rest of the ROCm software stack. See [this template](https://github.com/ROCm/hipTensor/blob/develop/CHANGELOG.md) for reference. 4) **Confirm all CI tests are passing**. You can easily confirm this by peeking the passing status of all GitHub continuous integration tests. 5) **Create a tag from `amd-mainline`**. More information on tagging can be found at [Git Docs - Tagging](https://git-scm.com/book/en/v2/Git-Basics-Tagging). @@ -13,7 +13,7 @@ Before publishing a new Omniperf release, please review this checklist to ensure > [!NOTE] Note: A successful tag should trigger the [packaging action](.github/workflows/packaging.yml) which will produce a tarball artifact. **This artifact needs to be included as an asset in your release**. Please find that the [packaging action](.github/workflows/packaging.yml) will automatically create a draft release with your tarball attached. -Once you've completed the above checklist, you are ready to publish your release. Please ensure you follow formatting from [past Omniperf releases](https://github.com/ROCm/omniperf/releases) for consistency. Some important aspects of our release formatting include: +Once you've completed the above checklist, you are ready to publish your release. Please ensure you follow formatting from [past ROCm Compute Profiler releases](https://github.com/ROCm/rocprofiler-compute/releases) for consistency. Some important aspects of our release formatting include: - Date of release is included in "Release Title". - Updates are called out in "Release Description". Updates should mirror those listed in [CHANGES](CHANGES). @@ -24,6 +24,6 @@ Once you've completed the above checklist, you are ready to publish your release If you are preparing for a new ROCm release, note that the [rocm-ci](https://github.com/rocm-ci) bot managed by DevOps will be triggering a tag automatically. This tag will follow the format `rocm-X.X.X`. -Traditionally, we will bump the Omniperf [VERSION](VERSION) with a new ROCm release. When we bump the version and reach the prerequisite step (5) above, try tagging with `vX.X.X` to validate the release tarball generated by the [packaging action](.github/workflows/packaging.yml). +Traditionally, we will bump the ROCm Compute Profiler [VERSION](VERSION) with a new ROCm release. When we bump the version and reach the prerequisite step (5) above, try tagging with `vX.X.X` to validate the release tarball generated by the [packaging action](.github/workflows/packaging.yml). In addition to the prerequisites mentioned above, please make sure that all changes have been merged from `amd-staging` -> `release/rocm-rel-X.X.X` to ensure that the "rocm-ci" bot will capture all your changes. It is easiest to file a single pull request ahead of the ROCm release. diff --git a/projects/rocprofiler-compute/README.md b/projects/rocprofiler-compute/README.md index c2b696b276..217f394edf 100644 --- a/projects/rocprofiler-compute/README.md +++ b/projects/rocprofiler-compute/README.md @@ -1,22 +1,22 @@ -[![Ubuntu 22.04](https://github.com/ROCm/omniperf/actions/workflows/ubuntu-jammy.yml/badge.svg)](https://github.com/ROCm/omniperf/actions/workflows/ubuntu-jammy.yml) -[![RHEL 8](https://github.com/ROCm/omniperf/actions/workflows/rhel-8.yml/badge.svg)](https://github.com/ROCm/omniperf/actions/workflows/rhel-8.yml) -[![Instinct](https://github.com/ROCm/omniperf/actions/workflows/mi-rhel9.yml/badge.svg)](https://github.com/ROCm/omniperf/actions/workflows/mi-rhel9.yml) -[![Docs](https://github.com/ROCm/omniperf/actions/workflows/docs.yml/badge.svg)](https://rocm.github.io/omniperf/) +[![Ubuntu 22.04](https://github.com/ROCm/rocprofiler-compute/actions/workflows/ubuntu-jammy.yml/badge.svg)](https://github.com/ROCm/rocprofiler-compute/actions/workflows/ubuntu-jammy.yml) +[![RHEL 8](https://github.com/ROCm/rocprofiler-compute/actions/workflows/rhel-8.yml/badge.svg)](https://github.com/ROCm/rocprofiler-compute/actions/workflows/rhel-8.yml) +[![Instinct](https://github.com/ROCm/rocprofiler-compute/actions/workflows/mi-rhel9.yml/badge.svg)](https://github.com/ROCm/rocprofiler-compute/actions/workflows/mi-rhel9.yml) +[![Docs](https://github.com/ROCm/rocprofiler-compute/actions/workflows/docs.yml/badge.svg)](https://rocm.github.io/rocprofiler-compute/) [![DOI](https://zenodo.org/badge/561919887.svg)](https://zenodo.org/badge/latestdoi/561919887) -# Omniperf +# ROCm Compute Profiler ## General -Omniperf is a system performance profiling tool for machine +ROCm Compute Profiler is a system performance profiling tool for machine learning/HPC workloads running on AMD MI GPUs. The tool presently targets usage on MI100, MI200, and MI300 accelerators. * For more information on available features, installation steps, and workload profiling and analysis, please refer to the online -[documentation](https://rocm.docs.amd.com/projects/omniperf/en/latest/). +[documentation](https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/). -* Omniperf is an AMD open source research project and is not supported +* ROCm Compute Profiler is an AMD open source research project and is not supported as part of the ROCm software stack. We welcome contributions and feedback from the community. Please see the [CONTRIBUTING.md](CONTRIBUTING.md) file for additional details on our @@ -26,7 +26,7 @@ contribution process. ## Development -Omniperf follows a +ROCm Compute Profiler follows a [main-dev](https://nvie.com/posts/a-successful-git-branching-model/) branching model. As a result, our latest stable release is shipped from the `amd-mainline` branch, while new features are developed in our @@ -50,8 +50,8 @@ style reference is provided below for convenience: Keith Lowery and Nicholas Curtis and Cristian Di Pietrantonio}, - title = {AMDResearch/omniperf: v2.1.0 (27 Sept 2024)}, - month = sept, + title = {ROCm/rocprofiler-compute: v2.1.0 (27 September 2024)}, + month = september, year = 2024, publisher = {Zenodo}, version = {v2.1.0}, diff --git a/projects/rocprofiler-compute/cmake/Dockerfile b/projects/rocprofiler-compute/cmake/Dockerfile index 346e64aa72..b38dd735b3 100644 --- a/projects/rocprofiler-compute/cmake/Dockerfile +++ b/projects/rocprofiler-compute/cmake/Dockerfile @@ -26,16 +26,16 @@ FROM ubuntu:20.04 USER root -COPY rocm_install.sh /omniperf/rocm_install.sh +COPY rocm_install.sh /rocprofiler-compute/rocm_install.sh -ENV PATH="/omniperf:${PATH}" +ENV PATH="/rocprofiler-compute:${PATH}" ENV TZ="US/Chicago" ENV DEBIAN_FRONTEND noninteractive #pyenv dependencies RUN apt update && \ apt-get install -y make build-essential libssl-dev zlib1g-dev libbz2-dev libreadline-dev libsqlite3-dev wget curl llvm libncurses5-dev libncursesw5-dev xz-utils tk-dev libffi-dev liblzma-dev python-openssl -ENV HOME="/omniperf" +ENV HOME="/rocprofiler-compute" WORKDIR $HOME ENV PYENV_ROOT="$HOME/.pyenv" ENV PATH="$PYENV_ROOT/bin:$PATH" diff --git a/projects/rocprofiler-compute/cmake/VERSION.sha.in b/projects/rocprofiler-compute/cmake/VERSION.sha.in index 5b3d301508..def9f78935 100644 --- a/projects/rocprofiler-compute/cmake/VERSION.sha.in +++ b/projects/rocprofiler-compute/cmake/VERSION.sha.in @@ -1 +1 @@ -@OMNIPERF_GIT_REV@ +@ROCPROFCOMPUTE_GIT_REV@ diff --git a/projects/rocprofiler-compute/cmake/omniperf.lua.in b/projects/rocprofiler-compute/cmake/rocprofcompute.lua.in similarity index 59% rename from projects/rocprofiler-compute/cmake/omniperf.lua.in rename to projects/rocprofiler-compute/cmake/rocprofcompute.lua.in index ca55ab6f6d..846be16e0b 100644 --- a/projects/rocprofiler-compute/cmake/omniperf.lua.in +++ b/projects/rocprofiler-compute/cmake/rocprofcompute.lua.in @@ -1,18 +1,18 @@ local help_message = [[ -Omniperf is an open-source performance analysis tool for profiling +ROCm Compute Profiler is an open-source performance analysis tool for profiling machine learning/HPC workloads running on AMD MI GPUs. -Version @OMNIPERF_FULL_VERSION@ +Version @ROCPROFCOMPUTE_FULL_VERSION@ ]] help(help_message,"\n") -whatis("Name: omniperf") -whatis("Version: @OMNIPERF_FULL_VERSION@") +whatis("Name: @PROJECT_NAME@") +whatis("Version: @ROCPROFCOMPUTE_FULL_VERSION@") whatis("Keywords: Profiling, Performance, GPU") whatis("Description: tool for GPU performance profiling") -whatis("URL: https://github.com/ROCm/omniperf") +whatis("URL: https://github.com/ROCm/rocprofiler-compute") -- Export environmental variables local topDir="@CMAKE_INSTALL_PREFIX@" @@ -20,9 +20,9 @@ local binDir="@CMAKE_INSTALL_FULL_BINDIR@" local shareDir="@CMAKE_INSTALL_FULL_DATADIR@" local pythonDeps="@PYTHON_DEPS@" -setenv("OMNIPERF_DIR",topDir) -setenv("OMNIPERF_BIN",binDir) -setenv("OMNIPERF_SHARE",shareDir) +setenv("ROCPROFCOMPUTE_DIR",topDir) +setenv("ROCPROFCOMPUTE_BIN",binDir) +setenv("ROCPROFCOMPUTE_SHARE",shareDir) -- Update relevant PATH variables prepend_path("PATH",binDir) diff --git a/projects/rocprofiler-compute/docker/build-docker-ci.sh b/projects/rocprofiler-compute/docker/build-docker-ci.sh index 8c7029e890..b3dba28a4f 100755 --- a/projects/rocprofiler-compute/docker/build-docker-ci.sh +++ b/projects/rocprofiler-compute/docker/build-docker-ci.sh @@ -137,7 +137,7 @@ do verbose-run docker build . \ ${PULL} \ -f ${DOCKER_FILE} \ - --tag ${USER}/omniperf:ci-base-${DISTRO}-${VERSION} \ + --tag ${USER}/rocprofiler-compute:ci-base-${DISTRO}-${VERSION} \ --build-arg DISTRO=${DISTRO_IMAGE} \ --build-arg VERSION=${VERSION} \ --build-arg PYTHON_VERSIONS=\"${PYTHON_VERSIONS}\" @@ -149,6 +149,6 @@ done if [ "${PUSH}" -gt 0 ]; then for VERSION in ${VERSIONS} do - verbose-run docker push ${USER}/omniperf:ci-base-${DISTRO}-${VERSION} + verbose-run docker push ${USER}/rocprofiler-compute:ci-base-${DISTRO}-${VERSION} done fi \ No newline at end of file diff --git a/projects/rocprofiler-compute/docker/build-docker.sh b/projects/rocprofiler-compute/docker/build-docker.sh index 5d6f2d181d..4da9161fb3 100755 --- a/projects/rocprofiler-compute/docker/build-docker.sh +++ b/projects/rocprofiler-compute/docker/build-docker.sh @@ -159,7 +159,7 @@ do VERSION_PATCH=$(echo ${VERSION} | sed 's/\./ /g' | awk '{print $3}') for ROCM_VERSION in ${ROCM_VERSIONS} do - CONTAINER=${USER}/omniperf:release-base-${DISTRO}-${VERSION}-rocm-${ROCM_VERSION} + CONTAINER=${USER}/rocprofiler-compute:release-base-${DISTRO}-${VERSION}-rocm-${ROCM_VERSION} ROCM_MAJOR=$(echo ${ROCM_VERSION} | sed 's/\./ /g' | awk '{print $1}') ROCM_MINOR=$(echo ${ROCM_VERSION} | sed 's/\./ /g' | awk '{print $2}') ROCM_PATCH=$(echo ${ROCM_VERSION} | sed 's/\./ /g' | awk '{print $3}') diff --git a/projects/rocprofiler-compute/docs/archive/docs-1.x/analysis.md b/projects/rocprofiler-compute/docs/archive/docs-1.x/analysis.md index 126364dbd6..19851c59de 100644 --- a/projects/rocprofiler-compute/docs/archive/docs-1.x/analysis.md +++ b/projects/rocprofiler-compute/docs/archive/docs-1.x/analysis.md @@ -171,7 +171,7 @@ $ omniperf analyze -p workloads/vcopy/mi200/ --list-metrics gfx90a ├─────────┼─────────────────────────────┤ ... ``` - 2. Choose your own customized subset of metrics with `-b` (a.k.a. `--metric`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/amd-mainline/src/omniperf_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light). + 2. Choose your own customized subset of metrics with `-b` (a.k.a. `--metric`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/amd-mainline/src/rocprof_compute_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light). ```shell-session $ omniperf analyze -p workloads/vcopy/mi200/ -b 2 -------- @@ -381,7 +381,7 @@ Analyze Dash is running on http://0.0.0.0:8050/ - * Serving Flask app 'omniperf_analyze.omniperf_analyze' (lazy loading) + * Serving Flask app 'rocprof_compute_analyze.rocprof_compute_analyze' (lazy loading) * Environment: production WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. @@ -767,4 +767,4 @@ Most panels are designed around a specific IP block to thoroughly understand its ###### L2-EA Write Stalls ![L2-EA Write Stalls](images/L2_ea_write_stalls_per_channel.png) ###### L2-EA Write Starvation -![L2-EA Write Starvation](images/L2_ea_write_starvation_per_channel.png) \ No newline at end of file +![L2-EA Write Starvation](images/L2_ea_write_starvation_per_channel.png) diff --git a/projects/rocprofiler-compute/docs/archive/docs-2.x/analysis.md b/projects/rocprofiler-compute/docs/archive/docs-2.x/analysis.md index 22fa72e392..a44e4b63f4 100644 --- a/projects/rocprofiler-compute/docs/archive/docs-2.x/analysis.md +++ b/projects/rocprofiler-compute/docs/archive/docs-2.x/analysis.md @@ -181,7 +181,7 @@ Analysis mode = cli 2.1.30 -> L1I Fetch Latency ... ``` -3. Choose your own customized subset of metrics with `-b` (a.k.a. `--block`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/amd-mainline/src/omniperf_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light). +3. Choose your own customized subset of metrics with `-b` (a.k.a. `--block`), or build your own config following [config_template](https://github.com/ROCm/omniperf/blob/amd-mainline/src/rocprof_compute_analyze/configs/panel_config_template.yaml). Below shows how to generate a report containing only metric 2 (a.k.a. System Speed-of-Light). ```shell-session $ omniperf analyze -p workloads/vcopy/MI200/ -b 2 -------- @@ -407,7 +407,7 @@ Analysis mode = web_ui [analysis] deriving Omniperf metrics... Dash is running on http://0.0.0.0:8050/ - * Serving Flask app 'omniperf_analyze.analysis_webui' (lazy loading) + * Serving Flask app 'rocprof_compute_analyze.analysis_webui' (lazy loading) * Environment: production WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. diff --git a/projects/rocprofiler-compute/docs/how-to/analyze/cli.rst b/projects/rocprofiler-compute/docs/how-to/analyze/cli.rst index 82185cd417..44a014a8b8 100644 --- a/projects/rocprofiler-compute/docs/how-to/analyze/cli.rst +++ b/projects/rocprofiler-compute/docs/how-to/analyze/cli.rst @@ -186,7 +186,7 @@ Walkthrough 3. Choose your own customized subset of metrics with the ``-b`` (or ``--block``) option. Or, build your own configuration following - `config_template `_. + `config_template `_. The following snippet shows how to generate a report containing only metric 2 (:doc:`System Speed-of-Light `). diff --git a/projects/rocprofiler-compute/docs/how-to/analyze/standalone-gui.rst b/projects/rocprofiler-compute/docs/how-to/analyze/standalone-gui.rst index a6a3e26f36..15bd008780 100644 --- a/projects/rocprofiler-compute/docs/how-to/analyze/standalone-gui.rst +++ b/projects/rocprofiler-compute/docs/how-to/analyze/standalone-gui.rst @@ -47,7 +47,7 @@ desired analysis command. For example: [analysis] deriving Omniperf metrics... Dash is running on http://0.0.0.0:8050/ - * Serving Flask app 'omniperf_analyze.analysis_webui' (lazy loading) + * Serving Flask app 'rocprof_compute_analyze.analysis_webui' (lazy loading) * Environment: production WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. diff --git a/projects/rocprofiler-compute/docs/install/core-install.rst b/projects/rocprofiler-compute/docs/install/core-install.rst index f33b976225..1d28b07b5d 100644 --- a/projects/rocprofiler-compute/docs/install/core-install.rst +++ b/projects/rocprofiler-compute/docs/install/core-install.rst @@ -32,7 +32,7 @@ right for you. :width: 800 .. _core-install: - + Core installation ================= @@ -44,12 +44,6 @@ installation. * CMake ``>= 3.19`` * ROCm ``>= 5.7.1`` -.. note:: - - Omniperf will use the first version of ``Python3`` found in your system's - ``PATH``. If the default version of Python3 is older than 3.8, you may need to - update your system's ``PATH`` to point to a newer version of Python3. - Omniperf depends on a number of Python packages documented in the top-level ``requirements.txt`` file. Install these *before* configuring Omniperf. @@ -72,16 +66,6 @@ following steps illustrate how to install the necessary Python dependencies using `pip `_ and Omniperf into a shared location controlled by the ``INSTALL_DIR`` environment variable. -.. tip:: - - To always run Omniperf with a particular version of python, you can create a - bash alias. For example, to run Omniperf with Python 3.10, you can run the - following command: - - .. code-block:: shell - - alias omniperf-mypython="/usr/bin/python3.10 /opt/rocm/bin/omniperf" - .. _core-install-cmake-vars: Configuration variables @@ -142,7 +126,7 @@ Install from source cd build cmake -DCMAKE_INSTALL_PREFIX=${INSTALL_DIR}/{{ config.version }} \ -DPYTHON_DEPS=${INSTALL_DIR}/python-libs \ - -DMOD_INSTALL_PATH=${INSTALL_DIR}/modulefiles/omniperf .. + -DMOD_INSTALL_PATH=${INSTALL_DIR}/modulefiles .. # install make install @@ -224,30 +208,21 @@ software stack. .. code-block:: shell $ sudo apt install omniperf - # Include omniperf in your system PATH - $ sudo update-alternatives --install /usr/bin/omniperf omniperf /opt/rocm/bin/omniperf 0 - # Install Python dependencies - $ python3 -m pip install -r /opt/rocm/libexec/omniperf/requirements.txt + $ pip install -r /opt/rocm/libexec/omniperf/requirements.txt .. tab-item:: Red Hat Enterprise Linux .. code-block:: shell $ sudo dnf install omniperf - # Include omniperf in your system PATH - $ sudo update-alternatives --install /usr/bin/omniperf omniperf /opt/rocm/bin/omniperf 0 - # Install Python dependencies - $ python3 -m pip install -r /opt/rocm/libexec/omniperf/requirements.txt + $ pip install -r /opt/rocm/libexec/omniperf/requirements.txt .. tab-item:: SUSE Linux Enterprise Server .. code-block:: shell $ sudo zypper install omniperf - # Include omniperf in your system PATH - $ sudo update-alternatives --install /usr/bin/omniperf omniperf /opt/rocm/bin/omniperf 0 - # Install Python dependencies - $ python3 -m pip install -r /opt/rocm/libexec/omniperf/requirements.txt + $ pip install -r /opt/rocm/libexec/omniperf/requirements.txt .. _core-install-rocprof-var: diff --git a/projects/rocprofiler-compute/docs/install/grafana-setup.rst b/projects/rocprofiler-compute/docs/install/grafana-setup.rst index 39dca6e888..a7486d286d 100644 --- a/projects/rocprofiler-compute/docs/install/grafana-setup.rst +++ b/projects/rocprofiler-compute/docs/install/grafana-setup.rst @@ -79,13 +79,6 @@ directory to begin. $ sudo docker-compose build $ sudo docker-compose up -d -.. note:: - - To troubleshoot Docker container build failures related to certificate verification, try - disabling any network proxy services on the host system. These proxy services can interfere - with OpenSSL's ability to retrieve a correct certificate chain when the container accesses - external websites. - The TCP ports for Grafana (``4000``) and MongoDB (``27017``) in the Docker container are mapped to ``14000`` and ``27018``, respectively, on the host side. diff --git a/projects/rocprofiler-compute/docs/sphinx/static/css/o_custom.css b/projects/rocprofiler-compute/docs/sphinx/static/css/o_custom.css index b4fe010b59..a6cbe5718f 100644 --- a/projects/rocprofiler-compute/docs/sphinx/static/css/o_custom.css +++ b/projects/rocprofiler-compute/docs/sphinx/static/css/o_custom.css @@ -1,8 +1,30 @@ +:root { + --amd-teal-500: #00C2DE; + --amd-teal-750: #00788E; +} + /* Override PyData Sphinx Theme default colors */ html[data-theme='light'] { + --pst-color-primary: var(--amd-teal-750); + --pst-color-primary-bg: var(--amd-teal-500); --pst-color-table-row-hover-bg: #E2E8F0; } html[data-theme='dark'] { + --pst-color-primary: var(--amd-teal-500); + --pst-color-primary-bg: var(--amd-teal-750); --pst-color-table-row-hover-bg: #1E293B; } + +html[data-theme='light'], +html[data-theme='dark'] { + --pst-color-link: var(--pst-color-primary); +} + +a svg { + color: var(--pst-color-text-base); +} + +a svg:hover { + color: var(--pst-color-link-hover); +} diff --git a/projects/rocprofiler-compute/grafana/Dockerfile b/projects/rocprofiler-compute/grafana/Dockerfile index 2227f487f7..6f7b7f049d 100644 --- a/projects/rocprofiler-compute/grafana/Dockerfile +++ b/projects/rocprofiler-compute/grafana/Dockerfile @@ -1,6 +1,6 @@ # ----------------------------------------------------------------------- # NOTE: -# Dependencies are not included as part of Omniperf. +# Dependencies are not included as part of ROCm Compute Profiler. # It's the user's responsibility to accept any licensing implications # before building the project # ----------------------------------------------------------------------- @@ -15,7 +15,7 @@ ENV TZ "US/Chicago" ENV NVM_DIR /usr/local/nvm ENV NODE_VERSION 20.12.2 -ADD plugins/omniperf_plugin /var/lib/grafana/plugins/omniperf_plugin +ADD plugins/rocprofiler-compute_plugin /var/lib/grafana/plugins/rocprofiler-compute_plugin # Install Grafana and MongoDB Community Edition # Note: Grafana install is stubbed to 10.4.3 @@ -50,7 +50,7 @@ RUN apt-get install -y tzdata systemd apt-utils npm vim net-tools && \ /usr/sbin/grafana-cli plugins install grafana-image-renderer && \ /usr/sbin/grafana-cli plugins install aceiot-svg-panel && \ chown root:grafana /etc/grafana && \ - cd /var/lib/grafana/plugins/omniperf_plugin && \ + cd /var/lib/grafana/plugins/rocprofiler-compute_plugin && \ npm install && \ npm run build && \ apt-get autoremove -y && \ diff --git a/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.3_pub.json b/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.3_pub.json index 5e4c480cca..270366cbec 100644 --- a/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.3_pub.json +++ b/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.3_pub.json @@ -32,7 +32,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -92,7 +92,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -103,7 +103,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -139,7 +139,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -151,7 +151,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -333,7 +333,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -344,7 +344,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -458,7 +458,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -543,7 +543,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "tlh8EwUnk" }, "rawQuery": true, @@ -571,7 +571,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -583,7 +583,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -641,7 +641,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "u5Z2zJhnk" }, "hide": false, @@ -1015,7 +1015,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "HV80ot2nz" }, "rawQuery": true, @@ -1437,7 +1437,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "HV80ot2nz" }, "rawQuery": true, @@ -1504,7 +1504,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -1516,7 +1516,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -1812,7 +1812,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "rawQuery": true, @@ -1822,7 +1822,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "hide": false, @@ -1833,7 +1833,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "hide": false, @@ -1844,7 +1844,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "hide": false, @@ -1855,7 +1855,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "hide": false, @@ -1890,7 +1890,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -1902,7 +1902,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -2488,7 +2488,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "rawQuery": true, @@ -2498,7 +2498,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -2509,7 +2509,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -2520,7 +2520,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -2531,7 +2531,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -2542,7 +2542,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -2553,7 +2553,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -2564,7 +2564,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -2575,7 +2575,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -2586,7 +2586,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "jYrBWHfnz" }, "hide": false, @@ -3175,7 +3175,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -3186,7 +3186,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -3197,7 +3197,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -3208,7 +3208,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -3219,7 +3219,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -3230,7 +3230,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -3241,7 +3241,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -3252,7 +3252,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "LJKvMZank" }, "hide": false, @@ -3263,7 +3263,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "jYrBWHfnz" }, "hide": false, @@ -3274,7 +3274,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "jYrBWHfnz" }, "hide": false, @@ -3292,7 +3292,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -3304,7 +3304,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -3390,7 +3390,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -3400,7 +3400,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -3595,7 +3595,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -3605,7 +3605,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -3658,7 +3658,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -3670,7 +3670,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -3829,7 +3829,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -3839,7 +3839,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -4036,7 +4036,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -4046,7 +4046,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -4098,7 +4098,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -4110,7 +4110,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -4306,7 +4306,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -4316,7 +4316,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -4502,7 +4502,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -4513,7 +4513,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -4568,7 +4568,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -4580,7 +4580,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -4644,7 +4644,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -4654,7 +4654,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -4735,7 +4735,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -4746,7 +4746,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -4825,7 +4825,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -4835,7 +4835,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -4919,7 +4919,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -4929,7 +4929,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -4969,7 +4969,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -4981,7 +4981,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -5052,7 +5052,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -5062,7 +5062,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -5196,7 +5196,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "rawQuery": true, @@ -5206,7 +5206,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -5370,7 +5370,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -5380,7 +5380,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -5477,7 +5477,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "rawQuery": true, @@ -5487,7 +5487,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -5498,7 +5498,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -5509,7 +5509,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -5520,7 +5520,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -5531,7 +5531,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -5542,7 +5542,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -5553,7 +5553,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -5600,7 +5600,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -5612,7 +5612,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -5683,7 +5683,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -5693,7 +5693,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -5875,7 +5875,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -5886,7 +5886,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -5941,7 +5941,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -5953,7 +5953,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -6021,7 +6021,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -6031,7 +6031,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -6131,7 +6131,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "rawQuery": true, @@ -6141,7 +6141,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -6189,7 +6189,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -6201,7 +6201,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -6284,7 +6284,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -6295,7 +6295,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "sY628IJnz" }, "hide": false, @@ -6393,7 +6393,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -6404,7 +6404,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "bhNVuvBnk" }, "hide": false, @@ -6547,7 +6547,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -6558,7 +6558,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -6610,7 +6610,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -6622,7 +6622,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -6709,7 +6709,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -6719,7 +6719,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -6891,7 +6891,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -6901,7 +6901,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -6953,7 +6953,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -6965,7 +6965,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -7032,7 +7032,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -7042,7 +7042,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -7195,7 +7195,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -7205,7 +7205,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -7391,7 +7391,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -7402,7 +7402,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -7558,7 +7558,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "tlh8EwUnk" }, "rawQuery": true, @@ -7635,7 +7635,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -7645,7 +7645,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -7697,7 +7697,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -7709,7 +7709,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -7919,7 +7919,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -7929,7 +7929,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -8067,7 +8067,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -8077,7 +8077,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -8237,7 +8237,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -8248,7 +8248,7 @@ }, { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "hide": false, @@ -8403,7 +8403,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -8420,7 +8420,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -8432,7 +8432,7 @@ { "collapsed": true, "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "gridPos": { @@ -10245,7 +10245,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -10364,7 +10364,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "Zzw1yR27k" }, "rawQuery": true, @@ -12540,7 +12540,7 @@ "targets": [ { "datasource": { - "type": "amd-omniperf-data-plugin", + "type": "amd-rocprofiler-compute-data-plugin", "uid": "oVK0I__nk" }, "refId": "A" @@ -12737,8 +12737,8 @@ { "current": { "selected": false, - "text": "omniperf_asw_mixbench_mi200", - "value": "omniperf_asw_mixbench_mi200" + "text": "rocprofiler-compute_asw_mixbench_mi200", + "value": "rocprofiler-compute_asw_mixbench_mi200" }, "definition": "workload_names.names.aggregate([\n {\"$group\": {\n \"_id\": \"&name\"\n }}\n]);", "hide": 0, @@ -12883,8 +12883,8 @@ { "current": { "selected": false, - "text": "omniperf_asw_mixbench_mi200", - "value": "omniperf_asw_mixbench_mi200" + "text": "rocprofiler-compute_asw_mixbench_mi200", + "value": "rocprofiler-compute_asw_mixbench_mi200" }, "definition": "workload_names.names.aggregate([\n {\"$group\": {\n \"_id\": \"&name\"\n }}\n]);", "hide": 0, @@ -13318,8 +13318,8 @@ }, "timepicker": {}, "timezone": "", - "title": "Omniperf_v1.0.3_pub", - "uid": "Omniperf_v1_0_063020221", + "title": "rocprofiler-compute_v1.0.3_pub", + "uid": "rocprofiler-compute_v1_0_063020221", "version": 4, "weekStart": "" } \ No newline at end of file diff --git a/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.5_pub.json b/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.5_pub.json index 4cbfd4a8ec..d043331136 100644 --- a/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.5_pub.json +++ b/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.5_pub.json @@ -13324,7 +13324,7 @@ }, "timepicker": {}, "timezone": "", - "title": "Omniperf_v1.0.5_pub", + "title": "rocprofiler-compute_v1.0.5_pub", "uid": "MIPerf_v1_0_0630202211", "version": 3, "weekStart": "" diff --git a/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.7_pub.json b/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.7_pub.json index c4b0899796..80e544f3ac 100644 --- a/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.7_pub.json +++ b/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.7_pub.json @@ -12733,8 +12733,8 @@ { "current": { "selected": true, - "text": "omniperf_asw_mix_mi200", - "value": "omniperf_asw_mix_mi200" + "text": "rocprofiler-compute_asw_mix_mi200", + "value": "rocprofiler-compute_asw_mix_mi200" }, "definition": "workload_names.names.aggregate([\n {\"$group\": {\n \"_id\": \"&name\"\n }}\n]);", "hide": 0, @@ -13318,7 +13318,7 @@ }, "timepicker": {}, "timezone": "", - "title": "Omniperf_v1.0.7_pub", + "title": "rocprofiler-compute_v1.0.7_pub", "uid": "MIPerf_v1_0_06302022112", "version": 2, "weekStart": "" diff --git a/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.8_pub.json b/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.8_pub.json index 72df97ef34..570ad31100 100644 --- a/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.8_pub.json +++ b/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v1.0.8_pub.json @@ -12809,8 +12809,8 @@ { "current": { "selected": true, - "text": "omniperf_asw_mixbench_mi200", - "value": "omniperf_asw_mixbench_mi200" + "text": "rocprofiler-compute_asw_mixbench_mi200", + "value": "rocprofiler-compute_asw_mixbench_mi200" }, "definition": "workload_names.names.aggregate([\n {\"$group\": {\n \"_id\": \"&name\"\n }}\n]);", "hide": 0, @@ -12955,8 +12955,8 @@ { "current": { "selected": true, - "text": "omniperf_asw_mixbench_mi200", - "value": "omniperf_asw_mixbench_mi200" + "text": "rocprofiler-compute_asw_mixbench_mi200", + "value": "rocprofiler-compute_asw_mixbench_mi200" }, "definition": "workload_names.names.aggregate([\n {\"$group\": {\n \"_id\": \"&name\"\n }}\n]);", "hide": 0, @@ -13390,7 +13390,7 @@ }, "timepicker": {}, "timezone": "", - "title": "Omniperf_v1.0.8_pub", + "title": "rocprofiler-compute_v1.0.8_pub", "uid": "MIPerf_v1_0_0630202211210", "version": 4, "weekStart": "" diff --git a/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v2.0.0_pub.json b/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v2.0.0_pub.json index 603d52ed7e..1e0cd46eef 100644 --- a/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v2.0.0_pub.json +++ b/projects/rocprofiler-compute/grafana/dashboards/Omniperf_v2.0.0_pub.json @@ -12827,8 +12827,8 @@ { "current": { "selected": true, - "text": "omniperf_pymongo4_Vcopy_gfx90a", - "value": "omniperf_pymongo4_Vcopy_gfx90a" + "text": "rocprofiler-compute_pymongo4_Vcopy_gfx90a", + "value": "rocprofiler-compute_pymongo4_Vcopy_gfx90a" }, "definition": "workload_names.names.aggregate([\n {\"$group\": {\n \"_id\": \"&name\"\n }}\n]);", "hide": 0, @@ -12973,8 +12973,8 @@ { "current": { "selected": false, - "text": "omniperf_pymongo4_Vcopy_gfx908", - "value": "omniperf_pymongo4_Vcopy_gfx908" + "text": "rocprofiler-compute_pymongo4_Vcopy_gfx908", + "value": "rocprofiler-compute_pymongo4_Vcopy_gfx908" }, "definition": "workload_names.names.aggregate([\n {\"$group\": {\n \"_id\": \"&name\"\n }}\n]);", "hide": 0, @@ -13408,8 +13408,8 @@ }, "timepicker": {}, "timezone": "", - "title": "Omniperf_v2.0_pubx", - "uid": "Omniperf_v20x", + "title": "rocprofiler-compute_v2.0_pubx", + "uid": "rocprofiler-compute_v20x", "version": 2, "weekStart": "" } \ No newline at end of file diff --git a/projects/rocprofiler-compute/grafana/docker-compose.yml b/projects/rocprofiler-compute/grafana/docker-compose.yml index 34e03d277b..38c3ebd9b0 100644 --- a/projects/rocprofiler-compute/grafana/docker-compose.yml +++ b/projects/rocprofiler-compute/grafana/docker-compose.yml @@ -1,6 +1,6 @@ # ----------------------------------------------------------------------- # NOTE: -# Dependencies are not included as part of Omniperf. +# Dependencies are not included as part of ROCm Compute Profiler. # It's the user's responsibility to accept any licensing implications # before building the project # ----------------------------------------------------------------------- @@ -9,13 +9,13 @@ version: "3.3" services: web: - image: omniperf-grafana-v1.0 - container_name: omniperf-grafana-v1.0 + image: rocprofiler-compute-grafana-v1.0 + container_name: rocprofiler-compute-grafana-v1.0 restart: always build: . environment: - GF_PATHS_CONFIG="grafana/etc/grafana.ini" - - GF_PLUGINS_ALLOW_LOADING_UNSIGNED_PLUGINS=amd-omniperf-data-plugin + - GF_PLUGINS_ALLOW_LOADING_UNSIGNED_PLUGINS=amd-rocprofiler-compute-data-plugin - GF_DEFAULT_APP_MODE=development ports: - "14000:4000" diff --git a/projects/rocprofiler-compute/grafana/docker-entrypoint.sh b/projects/rocprofiler-compute/grafana/docker-entrypoint.sh index 57ae8fa749..be92ccf6e6 100755 --- a/projects/rocprofiler-compute/grafana/docker-entrypoint.sh +++ b/projects/rocprofiler-compute/grafana/docker-entrypoint.sh @@ -24,7 +24,7 @@ # SOFTWARE. ##############################################################################el -pushd /var/lib/grafana/plugins/omniperf_plugin +pushd /var/lib/grafana/plugins/rocprofiler-compute_plugin npm run server & popd diff --git a/projects/rocprofiler-compute/grafana/grafana.ini b/projects/rocprofiler-compute/grafana/grafana.ini index fcf8b42b05..d2e07ed15f 100644 --- a/projects/rocprofiler-compute/grafana/grafana.ini +++ b/projects/rocprofiler-compute/grafana/grafana.ini @@ -874,7 +874,7 @@ max_days = 7 ;enable_alpha = false ;app_tls_skip_verify_insecure = false # Enter a comma-separated list of plugin identifiers to identify plugins to load even if they are unsigned. Plugins with modified signatures are never loaded. -allow_loading_unsigned_plugins = amd-custom-svg, amd-omniperf-data-plugin +allow_loading_unsigned_plugins = amd-custom-svg, amd-rocprofiler-compute-data-plugin # Enable or disable installing plugins directly from within Grafana. ;plugin_admin_enabled = false ;plugin_admin_external_manage_enabled = false diff --git a/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/README.md b/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/README.md index 32974100ee..e8f47590a1 100644 --- a/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/README.md +++ b/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/README.md @@ -1,6 +1,6 @@ -# Omniperf Data Source Plugin +# ROCm Compute Profiler Data Source Plugin -This plugin allows users of Omniperf to connect their MongoDB database to for visualization in Grafana +This plugin allows users of ROCm Compute Profiler to connect their MongoDB database to for visualization in Grafana ## Info diff --git a/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/package.json b/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/package.json index 36c6c420f7..e68745895d 100644 --- a/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/package.json +++ b/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/package.json @@ -1,5 +1,5 @@ { - "name": "amd-omniperf-data-plugin", + "name": "amd-rocprofiler-compute-data-plugin", "version": "1.0.0", "description": "", "main": "server/mongo-proxy.js", @@ -39,5 +39,5 @@ "mongodb": "^4.12.1", "statman-stopwatch": "^2.7.0" }, - "_comments": "Dependencies are not included as part of Omniperf. It's the user's responsibility to accept any licensing implications before building the project." + "_comments": "Dependencies are not included as part of ROCm Compute Profiler. It's the user's responsibility to accept any licensing implications before building the project." } diff --git a/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/server/mongo-proxy.js b/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/server/mongo-proxy.js index 8fb4df0752..04a489106f 100644 --- a/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/server/mongo-proxy.js +++ b/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/server/mongo-proxy.js @@ -398,7 +398,7 @@ function runAggregateQuery( requestId, queryId, body, queryArgs, res, next ) results = getTimeseriesResults(docs) } - // This is where omniperf will go for most results + // This is where rocprofiler-compute will go for most results else { results = getTableResults(docs) diff --git a/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/src/img/omniperf_circle.png b/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/src/img/rocprofiler-compute_circle.png similarity index 100% rename from projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/src/img/omniperf_circle.png rename to projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/src/img/rocprofiler-compute_circle.png diff --git a/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/src/plugin.json b/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/src/plugin.json index 90647f7648..204e6574be 100644 --- a/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/src/plugin.json +++ b/projects/rocprofiler-compute/grafana/plugins/omniperf_plugin/src/plugin.json @@ -1,6 +1,6 @@ { - "name": "Omniperf Data", - "id": "amd-omniperf-data-plugin", + "name": "ROCm Compute Profiler Data", + "id": "amd-rocprofiler-compute-data-plugin", "type": "datasource", "backend": true, "partials": { @@ -9,14 +9,14 @@ "metrics": true, "annotations": false, "info": { - "description": "An Omniperf datasource build for MongoDB", + "description": "An ROCm Compute Profiler datasource build for MongoDB", "author": { "name": "Audacious Software Group", "url": "" }, "logos": { - "small": "img/omniperf_circle.png", - "large": "img/omniperf_circle.png" + "small": "img/rocprofiler-compute_circle.png", + "large": "img/rocprofiler-compute_circle.png" }, "version": "%VERSION%", "updated": "%TODAY%" diff --git a/projects/rocprofiler-compute/pyproject.toml b/projects/rocprofiler-compute/pyproject.toml index d470c6367d..478ea4da83 100644 --- a/projects/rocprofiler-compute/pyproject.toml +++ b/projects/rocprofiler-compute/pyproject.toml @@ -17,7 +17,7 @@ exclude = ''' | external | .pytest_cache | build - | build-omniperf + | build-rocprof_compute )/ ) ''' @@ -29,9 +29,9 @@ addopts = [ pythonpath = [ ".", "src", - "src/omniperf_soc", + "src/rocprof_compute_soc", "src/utils", - "src/omniperf_analyze/utils", + "src/rocprof_compute_analyze/utils", "tests" ] diff --git a/projects/rocprofiler-compute/src/README.md b/projects/rocprofiler-compute/src/README.md index dc3b92a4c4..2aacb888d4 100644 --- a/projects/rocprofiler-compute/src/README.md +++ b/projects/rocprofiler-compute/src/README.md @@ -1,6 +1,6 @@ -This directory contains all the source code files for the Omniperf project. -The top-level `omniperf` executable is the entry point and defines the flow for subsequent execution modes. +This directory contains all the source code files for the ROCm Compute Profiler project. +The top-level `rocprof-compute` executable is the entry point and defines the flow for subsequent execution modes. -To build Omniperf as a developer (from source) please add this directory to `PATH`. -You will find utilities and logic specific to Omniperf's different execution modes in their +To build ROCm Compute Profiler as a developer (from source) please add this directory to `PATH`. +You will find utilities and logic specific to ROCm Compute Profiler's different execution modes in their respective subdirectories. \ No newline at end of file diff --git a/projects/rocprofiler-compute/src/argparser.py b/projects/rocprofiler-compute/src/argparser.py index 0b15043157..cbfd3ad1c3 100644 --- a/projects/rocprofiler-compute/src/argparser.py +++ b/projects/rocprofiler-compute/src/argparser.py @@ -34,11 +34,14 @@ def print_avail_arch(avail_arch: list): return ret_str -def add_general_group(parser, omniperf_version): +def add_general_group(parser, rocprof_compute_version): general_group = parser.add_argument_group("General Options") general_group.add_argument( - "-v", "--version", action="version", version=omniperf_version["ver_pretty"] + "-v", + "--version", + action="version", + version=rocprof_compute_version["ver_pretty"], ) general_group.add_argument( "-V", @@ -57,14 +60,16 @@ def add_general_group(parser, omniperf_version): ) -def omniarg_parser(parser, omniperf_home, supported_archs, omniperf_version): +def omniarg_parser( + parser, rocprof_compute_home, supported_archs, rocprof_compute_version +): # ----------------------------------------- # Parse arguments (dependent on mode) # ----------------------------------------- ## General Command Line Options ## ---------------------------- - add_general_group(parser, omniperf_version) + add_general_group(parser, rocprof_compute_version) parser._positionals.title = "Modes" parser._optionals.title = "Help" @@ -79,15 +84,15 @@ def omniarg_parser(parser, omniperf_home, supported_archs, omniperf_version): help="Profile the target application", usage=""" -omniperf profile --name [profile options] [roofline options] -- +rocprof-compute profile --name [profile options] [roofline options] -- --------------------------------------------------------------------------------- Examples: -\tomniperf profile -n vcopy_all -- ./vcopy -n 1048576 -b 256 -\tomniperf profile -n vcopy_SPI_TCC -b SQ TCC -- ./vcopy -n 1048576 -b 256 -\tomniperf profile -n vcopy_kernel -k vecCopy -- ./vcopy -n 1048576 -b 256 -\tomniperf profile -n vcopy_disp -d 0 -- ./vcopy -n 1048576 -b 256 -\tomniperf profile -n vcopy_roof --roof-only -- ./vcopy -n 1048576 -b 256 +\trocprof-compute profile -n vcopy_all -- ./vcopy -n 1048576 -b 256 +\trocprof-compute profile -n vcopy_SPI_TCC -b SQ TCC -- ./vcopy -n 1048576 -b 256 +\trocprof-compute profile -n vcopy_kernel -k vecCopy -- ./vcopy -n 1048576 -b 256 +\trocprof-compute profile -n vcopy_disp -d 0 -- ./vcopy -n 1048576 -b 256 +\trocprof-compute profile -n vcopy_roof --roof-only -- ./vcopy -n 1048576 -b 256 --------------------------------------------------------------------------------- """, prog="tool", @@ -98,7 +103,7 @@ Examples: ) profile_parser._optionals.title = "Help" - add_general_group(profile_parser, omniperf_version) + add_general_group(profile_parser, rocprof_compute_version) profile_group = profile_parser.add_argument_group("Profile Options") roofline_group = profile_parser.add_argument_group("Standalone Roofline Options") @@ -194,7 +199,10 @@ Examples: "--use-rocscope", default=False, dest="use_rocscope", help=argparse.SUPPRESS ) profile_group.add_argument( - "--kernel-summaries", default=False, dest="summaries", help=argparse.SUPPRESS + "--kernel-summaries", + default=False, + dest="summaries", + help=argparse.SUPPRESS, ) profile_group.add_argument( "--join-type", @@ -272,14 +280,14 @@ Examples: ## ---------------------------- db_parser = subparsers.add_parser( "database", - help="Interact with Omniperf database", + help="Interact with rocprofiler-compute database", usage=""" - \nomniperf database [connection options] + \nrocprof-compute database [connection options] \n\n------------------------------------------------------------------------------- \nExamples: - \n\tomniperf database --import -H pavii1 -u temp -t asw -w workloads/vcopy/mi200/ - \n\tomniperf database --remove -H pavii1 -u temp -w omniperf_asw_sample_mi200 + \n\trocprof-compute database --import -H pavii1 -u temp -t asw -w workloads/vcopy/mi200/ + \n\trocprof-compute database --remove -H pavii1 -u temp -w rocprofiler-compute_asw_sample_mi200 \n-------------------------------------------------------------------------------\n """, prog="tool", @@ -290,7 +298,7 @@ Examples: ) db_parser._optionals.title = "Help" - add_general_group(db_parser, omniperf_version) + add_general_group(db_parser, rocprof_compute_version) interaction_group = db_parser.add_argument_group("Interaction Type") connection_group = db_parser.add_argument_group("Connection Options") @@ -300,7 +308,7 @@ Examples: required=False, dest="upload", action="store_true", - help="\t\t\t\tImport workload to Omniperf DB", + help="\t\t\t\tImport workload to rocprofiler-compute DB", ) interaction_group.add_argument( "-r", @@ -308,7 +316,7 @@ Examples: required=False, dest="remove", action="store_true", - help="\t\t\t\tRemove a workload from Omniperf DB", + help="\t\t\t\tRemove a workload from rocprofiler-compute DB", ) connection_group.add_argument( @@ -366,13 +374,13 @@ Examples: "analyze", help="Analyze existing profiling results at command line", usage=""" -omniperf analyze --path [analyze options] +rocprof-compute analyze --path [analyze options] ----------------------------------------------------------------------------------- Examples: -\tomniperf analyze -p workloads/vcopy/mi200/ --list-metrics gfx90a -\tomniperf analyze -p workloads/mixbench/mi200/ --dispatch 12 34 --decimal 3 -\tomniperf analyze -p workloads/mixbench/mi200/ --gui +\trocprof-compute analyze -p workloads/vcopy/mi200/ --list-metrics gfx90a +\trocprof-compute analyze -p workloads/mixbench/mi200/ --dispatch 12 34 --decimal 3 +\trocprof-compute analyze -p workloads/mixbench/mi200/ --gui ----------------------------------------------------------------------------------- """, prog="tool", @@ -383,7 +391,7 @@ Examples: ) analyze_parser._optionals.title = "Help" - add_general_group(analyze_parser, omniperf_version) + add_general_group(analyze_parser, rocprof_compute_version) analyze_group = analyze_parser.add_argument_group("Analyze Options") analyze_advanced_group = analyze_parser.add_argument_group("Advanced Options") @@ -454,7 +462,7 @@ Examples: type=int, nargs="?", const=8050, - help="\t\tActivate a GUI to interate with Omniperf metrics.\n\t\tOptionally, specify port to launch application (DEFAULT: 8050)", + help="\t\tActivate a GUI to interate with rocprofiler-compute metrics.\n\t\tOptionally, specify port to launch application (DEFAULT: 8050)", ) analyze_advanced_group.add_argument( "--random-port", @@ -499,7 +507,7 @@ Examples: dest="config_dir", metavar="", help="\t\tSpecify the directory of customized configs.", - default=omniperf_home.joinpath("omniperf_soc/analysis_configs/"), + default=rocprof_compute_home.joinpath("rocprof_compute_soc/analysis_configs/"), ) analyze_advanced_group.add_argument( "--save-dfs", @@ -519,7 +527,9 @@ Examples: "-g", dest="debug", action="store_true", help="\t\tDebug single metric." ) analyze_advanced_group.add_argument( - "--dependency", action="store_true", help="\t\tList the installation dependency." + "--dependency", + action="store_true", + help="\t\tList the installation dependency.", ) analyze_advanced_group.add_argument( "--kernel-verbose", diff --git a/projects/rocprofiler-compute/src/config.py b/projects/rocprofiler-compute/src/config.py index 6cd07ff1c2..1caed50294 100644 --- a/projects/rocprofiler-compute/src/config.py +++ b/projects/rocprofiler-compute/src/config.py @@ -25,5 +25,5 @@ from pathlib import Path # NB: Creating a new module to share global vars across modules -omniperf_home = Path(__file__).resolve().parent -prog = "omniperf" +rocprof_compute_home = Path(__file__).resolve().parent +prog = "rocprofiler-compute" diff --git a/projects/rocprofiler-compute/src/omniperf b/projects/rocprofiler-compute/src/rocprof-compute old mode 100755 new mode 100644 similarity index 89% rename from projects/rocprofiler-compute/src/omniperf rename to projects/rocprofiler-compute/src/rocprof-compute index 1acff5f077..c8d2d0ee6d --- a/projects/rocprofiler-compute/src/omniperf +++ b/projects/rocprofiler-compute/src/rocprof-compute @@ -1,6 +1,6 @@ #!/usr/bin/env python3 -"""Main entry point for omniperf""" +"""Main entry point for rocprof-compute""" ##############################################################################bl # MIT License @@ -34,7 +34,7 @@ import re try: from pathlib import Path from importlib import metadata - from omniperf_base import Omniperf + from rocprof_compute_base import RocProfCompute from utils.utils import console_error except ImportError as e: # print("Failed to import required modules: " + str(e)) @@ -61,12 +61,12 @@ def verify_deps_version(localVer, desiredVer, operator): def verify_deps(): """Utility to read library dependencies from requirements.txt and endeavor to load them within current execution environment. - Used in top-level omniperf to provide error messages if necessary + Used in top-level rocprofiler-compute to provide error messages if necessary dependencies are not available.""" # Check which version of python is being used if sys.version_info[0] < 3 or (sys.version_info[0] == 3 and sys.version_info[1] < 8): - print("[ERROR] Python 3.8 or higher is required to run omniperf." + print("[ERROR] Python 3.8 or higher is required to run rocprofiler-compute." f" The current version is {sys.version_info[0]}.{sys.version_info[1]}.") sys.exit(1) @@ -108,7 +108,7 @@ def verify_deps(): ): print( f"[ERROR] the '{dependency}' distribution does " - "not meet version requirements to use omniperf." + "not meet version requirements to use rocprofiler-compute." ) print(" --> version installed :", localVersion) error = True @@ -119,7 +119,7 @@ def verify_deps(): "Please verify all of the python dependencies called out " "in the requirements file" ) - print("are installed locally prior to running omniperf.") + print("are installed locally prior to running rocprofiler-compute.") print("") print(f"See: {checkFile}") sys.exit(1) @@ -132,17 +132,17 @@ def main(): # verify required python dependencies verify_deps() - omniperf = Omniperf() + rocprof_compute = RocProfCompute() - mode = omniperf.get_mode() + mode = rocprof_compute.get_mode() - # major omniperf execution modes + # major rocprofiler-compute execution modes if mode == "profile": - omniperf.run_profiler() + rocprof_compute.run_profiler() elif mode == "database": - omniperf.update_db() + rocprof_compute.update_db() elif mode == "analyze": - omniperf.run_analysis() + rocprof_compute.run_analysis() else: console_error("Unsupported execution mode") diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_base.py b/projects/rocprofiler-compute/src/rocprof_compute_analyze/analysis_base.py similarity index 90% rename from projects/rocprofiler-compute/src/omniperf_analyze/analysis_base.py rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/analysis_base.py index eb0a67225d..b1fad7712a 100644 --- a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_base.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_analyze/analysis_base.py @@ -151,7 +151,7 @@ class OmniAnalyze_Base: self.load_options(normalization_filter) - for i, d in enumerate(self.__args.path): + for d in self.__args.path: w = schema.Workload() w.sys_info = file_io.load_sys_info(Path(d[0], "sysinfo.csv")) arch = w.sys_info.iloc[0]["gpu_arch"] @@ -161,7 +161,7 @@ class OmniAnalyze_Base: w.avail_ips = w.sys_info["ip_blocks"].item().split("|") w.dfs = copy.deepcopy(self._arch_configs[arch].dfs) w.dfs_type = self._arch_configs[arch].dfs_type - self._runs[i] = w + self._runs[d[0]] = w return self._runs @@ -184,6 +184,15 @@ class OmniAnalyze_Base: # validate profiling data is_workload_empty(dir[0]) + # no using same paths + occurances = set() + for dir in self.__args.path: + dir = dir[0] + if dir in occurances: + console_error("You cannot provide the same path twice.") + else: + occurances.add(dir) + # ---------------------------------------------------- # Required methods to be implemented by child classes # ---------------------------------------------------- @@ -191,7 +200,7 @@ class OmniAnalyze_Base: def pre_processing(self): """Perform initialization prior to analysis.""" console_debug("analysis", "prepping to do some analysis") - console_log("analysis", "deriving Omniperf metrics...") + console_log("analysis", "deriving rocprofiler-compute metrics...") # initalize output file self._output = ( open(self.__args.output_file, "w+") if self.__args.output_file else sys.stdout @@ -202,20 +211,20 @@ class OmniAnalyze_Base: # set filters if self.__args.gpu_kernel: - for i, gk in enumerate(self.__args.gpu_kernel): - self._runs[i].filter_kernel_ids = gk + for d, gk in zip(self.__args.path, self.__args.gpu_kernel): + self._runs[d[0]].filter_kernel_ids = gk if self.__args.gpu_id: if len(self.__args.gpu_id) == 1 and len(self.__args.path) != 1: for i in range(len(self.__args.path) - 1): self.__args.gpu_id.extend(self.__args.gpu_id) - for i, gi in enumerate(self.__args.gpu_id): - self._runs[i].filter_gpu_ids = gi + for d, gi in zip(self.__args.path, self.__args.gpu_id): + self._runs[d[0]].filter_gpu_ids = gi if self.__args.gpu_dispatch_id: if len(self.__args.gpu_dispatch_id) == 1 and len(self.__args.path) != 1: for i in range(len(self.__args.path) - 1): self.__args.gpu_dispatch_id.extend(self.__args.gpu_dispatch_id) - for i, gd in enumerate(self.__args.gpu_dispatch_id): - self._runs[i].filter_dispatch_ids = gd + for d, gd in zip(self.__args.path, self.__args.gpu_dispatch_id): + self._runs[d[0]].filter_dispatch_ids = gd @abstractmethod def run_analysis(self): diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_cli.py b/projects/rocprofiler-compute/src/rocprof_compute_analyze/analysis_cli.py similarity index 79% rename from projects/rocprofiler-compute/src/omniperf_analyze/analysis_cli.py rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/analysis_cli.py index 549653c62c..f3276c476a 100644 --- a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_cli.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_analyze/analysis_cli.py @@ -22,7 +22,7 @@ # SOFTWARE. ##############################################################################el -from omniperf_analyze.analysis_base import OmniAnalyze_Base +from rocprof_compute_analyze.analysis_base import OmniAnalyze_Base from utils.utils import demarcate, console_error from utils import file_io, parser, tty from utils.kernel_name_shortener import kernel_name_shortener @@ -38,25 +38,27 @@ class cli_analysis(OmniAnalyze_Base): super().pre_processing() if self.get_args().random_port: console_error("--gui flag is required to enable --random-port") - for i, d in enumerate(self.get_args().path): + for d in self.get_args().path: file_io.create_df_kernel_top_stats( raw_data_dir=d[0], - filter_gpu_ids=self._runs[i].filter_gpu_ids, - filter_dispatch_ids=self._runs[i].filter_dispatch_ids, + filter_gpu_ids=self._runs[d[0]].filter_gpu_ids, + filter_dispatch_ids=self._runs[d[0]].filter_dispatch_ids, time_unit=self.get_args().time_unit, max_stat_num=self.get_args().max_stat_num, kernel_verbose=self.get_args().kernel_verbose, ) # create 'mega dataframe' - self._runs[i].raw_pmc = file_io.create_df_pmc( + self._runs[d[0]].raw_pmc = file_io.create_df_pmc( d[0], self.get_args().kernel_verbose, self.get_args().verbose ) # demangle and overwrite original 'Kernel_Name' - kernel_name_shortener(self._runs[i].raw_pmc, self.get_args().kernel_verbose) + kernel_name_shortener( + self._runs[d[0]].raw_pmc, self.get_args().kernel_verbose + ) # create the loaded table parser.load_table_data( - workload=self._runs[i], + workload=self._runs[d[0]], dir=d[0], is_gui=False, debug=self.get_args().debug, @@ -71,13 +73,17 @@ class cli_analysis(OmniAnalyze_Base): tty.show_kernel_stats( self.get_args(), self._runs, - self._arch_configs[self._runs[0].sys_info.iloc[0]["gpu_arch"]], + self._arch_configs[ + self._runs[self.get_args().path[0][0]].sys_info.iloc[0]["gpu_arch"] + ], self._output, ) else: tty.show_all( self.get_args(), self._runs, - self._arch_configs[self._runs[0].sys_info.iloc[0]["gpu_arch"]], + self._arch_configs[ + self._runs[self.get_args().path[0][0]].sys_info.iloc[0]["gpu_arch"] + ], self._output, ) diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_webui.py b/projects/rocprofiler-compute/src/rocprof_compute_analyze/analysis_webui.py similarity index 96% rename from projects/rocprofiler-compute/src/omniperf_analyze/analysis_webui.py rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/analysis_webui.py index bdf7ff782b..47a25cf1e3 100644 --- a/projects/rocprofiler-compute/src/omniperf_analyze/analysis_webui.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_analyze/analysis_webui.py @@ -22,7 +22,7 @@ # SOFTWARE. ##############################################################################el -from omniperf_analyze.analysis_base import OmniAnalyze_Base +from rocprof_compute_analyze.analysis_base import OmniAnalyze_Base from utils.utils import demarcate, console_debug, console_error from utils import file_io, parser from utils.gui import build_bar_chart, build_table_chart @@ -274,20 +274,20 @@ class webui_analysis(OmniAnalyze_Base): args = self.get_args() file_io.create_df_kernel_top_stats( raw_data_dir=self.dest_dir, - filter_gpu_ids=self._runs[0].filter_gpu_ids, - filter_dispatch_ids=self._runs[0].filter_dispatch_ids, + filter_gpu_ids=self._runs[self.dest_dir].filter_gpu_ids, + filter_dispatch_ids=self._runs[self.dest_dir].filter_dispatch_ids, time_unit=args.time_unit, max_stat_num=args.max_stat_num, kernel_verbose=self.get_args().kernel_verbose, ) # create 'mega dataframe' - self._runs[0].raw_pmc = file_io.create_df_pmc( + self._runs[self.dest_dir].raw_pmc = file_io.create_df_pmc( self.dest_dir, self.get_args().kernel_verbose, args.verbose ) # create the loaded kernel stats - parser.load_kernel_top(self._runs[0], self.dest_dir) + parser.load_kernel_top(self._runs[self.dest_dir], self.dest_dir) # set architecture - self.arch = self._runs[0].sys_info.iloc[0]["gpu_arch"] + self.arch = self._runs[self.dest_dir].sys_info.iloc[0]["gpu_arch"] else: console_error( @@ -300,9 +300,9 @@ class webui_analysis(OmniAnalyze_Base): super().run_analysis() args = self.get_args() input_filters = { - "kernel": self._runs[0].filter_kernel_ids, - "gpu": self._runs[0].filter_gpu_ids, - "dispatch": self._runs[0].filter_dispatch_ids, + "kernel": self._runs[self.dest_dir].filter_kernel_ids, + "gpu": self._runs[self.dest_dir].filter_gpu_ids, + "dispatch": self._runs[self.dest_dir].filter_dispatch_ids, "normalization": args.normal_unit, "top_n": args.max_stat_num, } diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/default.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/default.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/default.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/default.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/css/font-awesome.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/css/font-awesome.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/css/font-awesome.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/css/font-awesome.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/css/font-awesome.min.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/css/font-awesome.min.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/css/font-awesome.min.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/css/font-awesome.min.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/fonts/FontAwesome.otf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/fonts/FontAwesome.otf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/fonts/FontAwesome.otf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/fonts/FontAwesome.otf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/fonts/fontawesome-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/fonts/fontawesome-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/fonts/fontawesome-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/fonts/fontawesome-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/fonts/fontawesome-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/fonts/fontawesome-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/fonts/fontawesome-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/fonts/fontawesome-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/fonts/fontawesome-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/fonts/fontawesome-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/fonts/fontawesome-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/fonts/fontawesome-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/fonts/fontawesome-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/fonts/fontawesome-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/fonts/fontawesome-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/fonts/fontawesome-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/bordered-pulled.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/bordered-pulled.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/bordered-pulled.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/bordered-pulled.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/core.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/core.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/core.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/core.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/fixed-width.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/fixed-width.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/fixed-width.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/fixed-width.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/font-awesome.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/font-awesome.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/font-awesome.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/font-awesome.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/icons.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/icons.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/icons.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/icons.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/larger.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/larger.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/larger.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/larger.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/list.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/list.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/list.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/list.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/mixins.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/mixins.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/mixins.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/mixins.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/path.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/path.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/path.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/path.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/rotated-flipped.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/rotated-flipped.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/rotated-flipped.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/rotated-flipped.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/spinning.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/spinning.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/spinning.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/spinning.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/stacked.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/stacked.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/stacked.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/stacked.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/variables.less b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/variables.less similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/less/variables.less rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/less/variables.less diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_bordered-pulled.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_bordered-pulled.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_bordered-pulled.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_bordered-pulled.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_core.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_core.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_core.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_core.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_fixed-width.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_fixed-width.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_fixed-width.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_fixed-width.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_icons.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_icons.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_icons.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_icons.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_larger.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_larger.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_larger.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_larger.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_list.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_list.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_list.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_list.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_mixins.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_mixins.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_mixins.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_mixins.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_path.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_path.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_path.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_path.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_rotated-flipped.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_rotated-flipped.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_rotated-flipped.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_rotated-flipped.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_spinning.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_spinning.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_spinning.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_spinning.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_stacked.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_stacked.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_stacked.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_stacked.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_variables.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_variables.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/_variables.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/_variables.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/font-awesome.scss b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/font-awesome.scss similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/font-awesome/scss/font-awesome.scss rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/font-awesome/scss/font-awesome.scss diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/animation.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/animation.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/animation.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/animation.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/fontello-codes.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/fontello-codes.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/fontello-codes.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/fontello-codes.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/fontello-embedded.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/fontello-embedded.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/fontello-embedded.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/fontello-embedded.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/fontello-ie7-codes.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/fontello-ie7-codes.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/fontello-ie7-codes.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/fontello-ie7-codes.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/fontello-ie7.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/fontello-ie7.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/fontello-ie7.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/fontello-ie7.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/fontello.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/fontello.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/css/fontello.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/css/fontello.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/font/fontello.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/font/fontello.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/font/fontello.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/font/fontello.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/font/fontello.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/font/fontello.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/font/fontello.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/font/fontello.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/font/fontello.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/font/fontello.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/font/fontello.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/font/fontello.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/font/fontello.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/font/fontello.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fontello/font/fontello.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fontello/font/fontello.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-bold-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-italic-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/librebaskerville/librebaskerville-regular-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Bold-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-BoldItalic-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBold-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-ExtraBoldItalic-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Italic-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Light-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Light-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Light-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Light-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Light-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Light-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Light-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Light-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Light-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Light-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Light-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Light-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Light-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Light-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Light-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Light-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-LightItalic-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Regular-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-Semibold-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.eot b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.eot similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.eot rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.eot diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.svg b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.svg similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.svg rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.svg diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.ttf b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.ttf similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.ttf rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.ttf diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.woff b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.woff similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.woff rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/fonts/opensans/OpenSans-SemiboldItalic-webfont.woff diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/layout.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/layout.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/layout.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/layout.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/magnific-popup.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/magnific-popup.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/magnific-popup.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/magnific-popup.css diff --git a/projects/rocprofiler-compute/src/omniperf_analyze/assets/media-queries.css b/projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/media-queries.css similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_analyze/assets/media-queries.css rename to projects/rocprofiler-compute/src/rocprof_compute_analyze/assets/media-queries.css diff --git a/projects/rocprofiler-compute/src/omniperf_base.py b/projects/rocprofiler-compute/src/rocprof_compute_base.py similarity index 84% rename from projects/rocprofiler-compute/src/omniperf_base.py rename to projects/rocprofiler-compute/src/rocprof_compute_base.py index 50a6cf00ef..e11ab13211 100644 --- a/projects/rocprofiler-compute/src/omniperf_base.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_base.py @@ -40,7 +40,11 @@ from utils.utils import ( console_error, set_locale_encoding, ) -from utils.logger import setup_console_handler, setup_logging_priority, setup_file_handler +from utils.logger import ( + setup_console_handler, + setup_logging_priority, + setup_file_handler, +) from argparser import omniarg_parser import config import pandas as pd @@ -62,7 +66,7 @@ MI300_CHIP_IDS = { } -class Omniperf: +class RocProfCompute: def __init__(self): self.__args = None self.__profiler_mode = None @@ -98,12 +102,12 @@ class Omniperf: def print_graphic(self): """Log program name as ascii art to terminal.""" ascii_art = r""" - ___ _ __ - / _ \ _ __ ___ _ __ (_)_ __ ___ _ __ / _| -| | | | '_ ` _ \| '_ \| | '_ \ / _ \ '__| |_ -| |_| | | | | | | | | | | |_) | __/ | | _| - \___/|_| |_| |_|_| |_|_| .__/ \___|_| |_| - |_| + __ _ + _ __ ___ ___ _ __ _ __ ___ / _| ___ ___ _ __ ___ _ __ _ _| |_ ___ +| '__/ _ \ / __| '_ \| '__/ _ \| |_ _____ / __/ _ \| '_ ` _ \| '_ \| | | | __/ _ \ +| | | (_) | (__| |_) | | | (_) | _|_____| (_| (_) | | | | | | |_) | |_| | || __/ +|_| \___/ \___| .__/|_| \___/|_| \___\___/|_| |_| |_| .__/ \__,_|\__\___| + |_| |_| """ print(ascii_art) @@ -111,7 +115,7 @@ class Omniperf: return self.__mode def set_version(self): - vData = get_version(config.omniperf_home) + vData = get_version(config.rocprof_compute_home) self.__version["ver"] = vData["version"] self.__version["ver_pretty"] = get_version_display( vData["version"], vData["sha"], vData["mode"] @@ -137,7 +141,7 @@ class Omniperf: else: console_error( "Incompatible profiler: %s. Supported profilers include: %s" - % (rocprof_cmd, get_submodules("omniperf_profile")) + % (rocprof_cmd, get_submodules("rocprof_compute_profile")) ) return @@ -150,7 +154,7 @@ class Omniperf: @demarcate def load_soc_specs(self, sysinfo: dict = None): - """Load OmniSoC instance for Omniperf run""" + """Load OmniSoC instance for RocProfCompute run""" self.__mspec = generate_machine_specs(self.__args, sysinfo) if self.__args.specs: print(self.__mspec) @@ -162,22 +166,22 @@ class Omniperf: if arch not in self.__supported_archs.keys(): console_error("%s is an unsupported SoC" % arch) - soc_module = importlib.import_module("omniperf_soc.soc_" + arch) + soc_module = importlib.import_module("rocprof_compute_soc.soc_" + arch) soc_class = getattr(soc_module, arch + "_soc") self.__soc[arch] = soc_class(self.__args, self.__mspec) return def parse_args(self): parser = argparse.ArgumentParser( - description="Command line interface for AMD's GPU profiler, Omniperf", + description="Command line interface for AMD's GPU profiler, ROCm Compute Profiler", prog="tool", formatter_class=lambda prog: argparse.RawTextHelpFormatter( prog, max_help_position=30 ), - usage="omniperf [mode] [options]", + usage="rocprof-compute [mode] [options]", ) omniarg_parser( - parser, config.omniperf_home, self.__supported_archs, self.__version + parser, config.rocprof_compute_home, self.__supported_archs, self.__version ) self.__args = parser.parse_args() @@ -186,7 +190,9 @@ class Omniperf: print(generate_machine_specs(self.__args)) sys.exit(0) parser.print_help(sys.stderr) - console_error("Omniperf requires you pass a valid mode. Detected None.") + console_error( + "rocprof-compute requires you pass a valid mode. Detected None." + ) return @demarcate @@ -202,19 +208,19 @@ class Omniperf: # instantiate desired profiler if self.__profiler_mode == "rocprofv1": - from omniperf_profile.profiler_rocprof_v1 import rocprof_v1_profiler + from rocprof_compute_profile.profiler_rocprof_v1 import rocprof_v1_profiler profiler = rocprof_v1_profiler( self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch] ) elif self.__profiler_mode == "rocprofv2": - from omniperf_profile.profiler_rocprof_v2 import rocprof_v2_profiler + from rocprof_compute_profile.profiler_rocprof_v2 import rocprof_v2_profiler profiler = rocprof_v2_profiler( self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch] ) elif self.__profiler_mode == "rocscope": - from omniperf_profile.profiler_rocscope import rocscope_profiler + from rocprof_compute_profile.profiler_rocscope import rocscope_profiler profiler = rocscope_profiler( self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch] @@ -262,11 +268,11 @@ class Omniperf: console_log("Analysis mode = %s" % self.__analyze_mode) if self.__analyze_mode == "cli": - from omniperf_analyze.analysis_cli import cli_analysis + from rocprof_compute_analyze.analysis_cli import cli_analysis analyzer = cli_analysis(self.__args, self.__supported_archs) elif self.__analyze_mode == "web_ui": - from omniperf_analyze.analysis_webui import webui_analysis + from rocprof_compute_analyze.analysis_webui import webui_analysis analyzer = webui_analysis(self.__args, self.__supported_archs) else: diff --git a/projects/rocprofiler-compute/src/omniperf_profile/profiler_base.py b/projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_base.py similarity index 97% rename from projects/rocprofiler-compute/src/omniperf_profile/profiler_base.py rename to projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_base.py index 9da4a7c481..44a12af118 100644 --- a/projects/rocprofiler-compute/src/omniperf_profile/profiler_base.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_base.py @@ -45,13 +45,13 @@ import config import pandas as pd -class OmniProfiler_Base: +class RocProfCompute_Base: def __init__(self, args, profiler_mode, soc): self.__args = args self.__profiler = profiler_mode self._soc = soc # OmniSoC obj self.__perfmon_dir = os.path.join( - str(config.omniperf_home), "omniperf_soc", "profile_configs" + str(config.rocprof_compute_home), "rocprof_compute_soc", "profile_configs" ) def get_args(self): @@ -220,7 +220,7 @@ class OmniProfiler_Base: df["End_Timestamp"] = endNs # finally, join the drop key df = df.drop(columns=["key"]) - # save to file and delete old file(s), skip if we're being called outside of Omniperf + # save to file and delete old file(s), skip if we're being called outside of rocprof-compute if type(self.__args.path) == str: df.to_csv(out, index=False) if not self.__args.verbose: @@ -266,7 +266,7 @@ class OmniProfiler_Base: self.__args.remaining = " ".join(self.__args.remaining) else: console_error( - "Profiling command required. Pass application executable after -- at the end of options.\n\t\ti.e. omniperf profile -n vcopy -- ./vcopy -n 1048576 -b 256" + "Profiling command required. Pass application executable after -- at the end of options.\n\t\ti.e. rocprof-compute profile -n vcopy -- ./vcopy -n 1048576 -b 256" ) # verify name meets MongoDB length requirements and no illegal chars @@ -375,7 +375,8 @@ class OmniProfiler_Base: def post_processing(self): """Perform any post-processing steps prior to profiling.""" console_debug( - "profiling", "performing post-processing using %s profiler" % self.__profiler + "profiling", + "performing post-processing using %s profiler" % self.__profiler, ) gen_sysinfo( diff --git a/projects/rocprofiler-compute/src/omniperf_profile/profiler_rocprof_v1.py b/projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_rocprof_v1.py similarity index 96% rename from projects/rocprofiler-compute/src/omniperf_profile/profiler_rocprof_v1.py rename to projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_rocprof_v1.py index 17cf18ba1e..5d70242bd4 100644 --- a/projects/rocprofiler-compute/src/omniperf_profile/profiler_rocprof_v1.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_rocprof_v1.py @@ -24,11 +24,11 @@ import os -from omniperf_profile.profiler_base import OmniProfiler_Base +from rocprof_compute_profile.profiler_base import RocProfCompute_Base from utils.utils import demarcate, replace_timestamps, console_log -class rocprof_v1_profiler(OmniProfiler_Base): +class rocprof_v1_profiler(RocProfCompute_Base): def __init__(self, profiling_args, profiler_mode, soc): super().__init__(profiling_args, profiler_mode, soc) self.ready_to_profile = ( diff --git a/projects/rocprofiler-compute/src/omniperf_profile/profiler_rocprof_v2.py b/projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_rocprof_v2.py similarity index 96% rename from projects/rocprofiler-compute/src/omniperf_profile/profiler_rocprof_v2.py rename to projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_rocprof_v2.py index 3cca9673b3..31bdd2ed98 100644 --- a/projects/rocprofiler-compute/src/omniperf_profile/profiler_rocprof_v2.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_rocprof_v2.py @@ -24,7 +24,7 @@ import os import shlex -from omniperf_profile.profiler_base import OmniProfiler_Base +from rocprof_compute_profile.profiler_base import RocProfCompute_Base from utils.utils import ( demarcate, console_log, @@ -32,7 +32,7 @@ from utils.utils import ( ) -class rocprof_v2_profiler(OmniProfiler_Base): +class rocprof_v2_profiler(RocProfCompute_Base): def __init__(self, profiling_args, profiler_mode, soc): super().__init__(profiling_args, profiler_mode, soc) self.ready_to_profile = ( diff --git a/projects/rocprofiler-compute/src/omniperf_profile/profiler_rocscope.py b/projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_rocscope.py similarity index 91% rename from projects/rocprofiler-compute/src/omniperf_profile/profiler_rocscope.py rename to projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_rocscope.py index 13f08e4926..52b6e6c9ce 100644 --- a/projects/rocprofiler-compute/src/omniperf_profile/profiler_rocscope.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_profile/profiler_rocscope.py @@ -22,11 +22,11 @@ # SOFTWARE. ##############################################################################el -from omniperf_profile.profiler_base import OmniProfiler_Base +from rocprof_compute_profile.profiler_base import RocProfCompute_Base from utils.utils import demarcate, console_log -class rocscope_profiler(OmniProfiler_Base): +class rocscope_profiler(RocProfCompute_Base): def __init__(self, profiling_args, profiler_mode, soc): super().__init__(profiling_args, profiler_mode, soc) @@ -52,6 +52,7 @@ class rocscope_profiler(OmniProfiler_Base): def post_processing(self): """Perform any post-processing steps prior to profiling.""" console_log( - "profiling", "performing post-processing using %s profiler" % self.__profiler + "profiling", + "performing post-processing using %s profiler" % self.__profiler, ) # TODO: Finish implementation diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0000_top_stats.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0000_top_stats.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0000_top_stats.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0000_top_stats.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0100_system_info.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0100_system_info.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0100_system_info.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0100_system_info.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0200_system-speed-of-light.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0200_system-speed-of-light.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0200_system-speed-of-light.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0300_mem_chart.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0300_mem_chart.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0300_mem_chart.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0300_mem_chart.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0500_command-processor.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0500_command-processor.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0500_command-processor.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0500_command-processor.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0600_shader-processor-input.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0600_shader-processor-input.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0600_shader-processor-input.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0600_shader-processor-input.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0700_wavefront-launch.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0700_wavefront-launch.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/0700_wavefront-launch.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0700_wavefront-launch.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1000_compute-unit-instruction-mix.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1000_compute-unit-instruction-mix.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1000_compute-unit-instruction-mix.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1000_compute-unit-instruction-mix.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1100_compute-unit-compute-pipeline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1100_compute-unit-compute-pipeline.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1100_compute-unit-compute-pipeline.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1100_compute-unit-compute-pipeline.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1200_lds.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1200_lds.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1200_lds.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1200_lds.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1300_instruction-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1300_instruction-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1300_instruction-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1300_instruction-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1400_constant-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1400_constant-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1400_constant-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1400_constant-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1500_TA_and_TD.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1500_TA_and_TD.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1500_TA_and_TD.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1500_TA_and_TD.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1600_L1_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1600_L1_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1600_L1_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1600_L1_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1700_L2_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1700_L2_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1700_L2_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1700_L2_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1800_L2_cache_per_channel.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1800_L2_cache_per_channel.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx906/1800_L2_cache_per_channel.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/1800_L2_cache_per_channel.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0000_top_stats.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0000_top_stats.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0000_top_stats.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0000_top_stats.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0100_system_info.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0100_system_info.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0100_system_info.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0100_system_info.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0200_system-speed-of-light.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0200_system-speed-of-light.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0200_system-speed-of-light.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0300_mem_chart.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0300_mem_chart.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0300_mem_chart.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0300_mem_chart.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0500_command-processor.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0500_command-processor.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0500_command-processor.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0500_command-processor.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0600_shader-processor-input.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0600_shader-processor-input.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0600_shader-processor-input.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0600_shader-processor-input.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0700_wavefront-launch.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0700_wavefront-launch.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/0700_wavefront-launch.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0700_wavefront-launch.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1000_compute-unit-instruction-mix.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1000_compute-unit-instruction-mix.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1000_compute-unit-instruction-mix.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1000_compute-unit-instruction-mix.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1100_compute-unit-compute-pipeline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1100_compute-unit-compute-pipeline.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1100_compute-unit-compute-pipeline.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1100_compute-unit-compute-pipeline.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1200_lds.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1200_lds.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1200_lds.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1200_lds.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1300_instruction-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1300_instruction-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1300_instruction-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1300_instruction-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1400_constant-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1400_constant-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1400_constant-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1400_constant-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1500_TA_and_TD.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1500_TA_and_TD.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1500_TA_and_TD.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1500_TA_and_TD.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1600_L1_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1600_L1_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1600_L1_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1600_L1_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1700_L2_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1700_L2_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1700_L2_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1700_L2_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1800_L2_cache_per_channel.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1800_L2_cache_per_channel.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx908/1800_L2_cache_per_channel.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/1800_L2_cache_per_channel.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0000_top_stats.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0000_top_stats.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0000_top_stats.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0000_top_stats.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0100_system_info.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0100_system_info.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0100_system_info.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0100_system_info.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0200_system-speed-of-light.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0200_system-speed-of-light.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0200_system-speed-of-light.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0300_mem_chart.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0300_mem_chart.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0300_mem_chart.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0300_mem_chart.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0400_roofline_chart.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0400_roofline_chart.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0400_roofline_chart.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0400_roofline_chart.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0500_command-processor.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0500_command-processor.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0500_command-processor.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0500_command-processor.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0600_shader-processor-input.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0600_shader-processor-input.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0600_shader-processor-input.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0600_shader-processor-input.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0700_wavefront-launch.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0700_wavefront-launch.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/0700_wavefront-launch.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/0700_wavefront-launch.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1000_compute-unit-instruction-mix.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1000_compute-unit-instruction-mix.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1000_compute-unit-instruction-mix.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1000_compute-unit-instruction-mix.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1100_compute-unit-compute-pipeline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1100_compute-unit-compute-pipeline.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1100_compute-unit-compute-pipeline.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1100_compute-unit-compute-pipeline.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1200_lds.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1200_lds.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1200_lds.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1200_lds.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1300_instruction-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1300_instruction-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1300_instruction-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1300_instruction-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1400_constant-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1400_constant-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1400_constant-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1400_constant-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1500_TA_and_TD.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1500_TA_and_TD.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1500_TA_and_TD.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1500_TA_and_TD.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1600_L1_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1600_L1_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1600_L1_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1600_L1_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1700_L2_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1700_L2_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1700_L2_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1700_L2_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1800_L2_cache_per_channel.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1800_L2_cache_per_channel.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx90a/1800_L2_cache_per_channel.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx90a/1800_L2_cache_per_channel.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0000_top_stats.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0000_top_stats.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0000_top_stats.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0000_top_stats.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0100_system_info.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0100_system_info.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0100_system_info.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0100_system_info.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0200_system-speed-of-light.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0200_system-speed-of-light.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0200_system-speed-of-light.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0300_mem_chart.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0300_mem_chart.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0300_mem_chart.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0300_mem_chart.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0500_command-processor.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0500_command-processor.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0500_command-processor.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0500_command-processor.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0600_shader-processor-input.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0600_shader-processor-input.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0600_shader-processor-input.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0600_shader-processor-input.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0700_wavefront-launch.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0700_wavefront-launch.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/0700_wavefront-launch.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0700_wavefront-launch.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1000_compute-unit-instruction-mix.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1000_compute-unit-instruction-mix.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1000_compute-unit-instruction-mix.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1000_compute-unit-instruction-mix.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1100_compute-unit-compute-pipeline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1100_compute-unit-compute-pipeline.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1100_compute-unit-compute-pipeline.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1100_compute-unit-compute-pipeline.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1200_lds.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1200_lds.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1200_lds.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1200_lds.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1300_instruction-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1300_instruction-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1300_instruction-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1300_instruction-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1400_constant-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1400_constant-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1400_constant-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1400_constant-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1500_TA_and_TD.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1500_TA_and_TD.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1500_TA_and_TD.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1500_TA_and_TD.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1600_L1_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1600_L1_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1600_L1_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1600_L1_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1700_L2_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1700_L2_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1700_L2_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1700_L2_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1800_L2_cache_per_channel.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1800_L2_cache_per_channel.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx940/1800_L2_cache_per_channel.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/1800_L2_cache_per_channel.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0000_top_stats.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0000_top_stats.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0000_top_stats.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0000_top_stats.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0100_system_info.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0100_system_info.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0100_system_info.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0100_system_info.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0200_system-speed-of-light.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0200_system-speed-of-light.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0200_system-speed-of-light.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0300_mem_chart.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0300_mem_chart.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0300_mem_chart.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0300_mem_chart.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0500_command-processor.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0500_command-processor.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0500_command-processor.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0500_command-processor.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0600_shader-processor-input.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0600_shader-processor-input.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0600_shader-processor-input.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0600_shader-processor-input.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0700_wavefront-launch.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0700_wavefront-launch.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/0700_wavefront-launch.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0700_wavefront-launch.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1000_compute-unit-instruction-mix.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1000_compute-unit-instruction-mix.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1000_compute-unit-instruction-mix.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1000_compute-unit-instruction-mix.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1100_compute-unit-compute-pipeline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1100_compute-unit-compute-pipeline.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1100_compute-unit-compute-pipeline.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1100_compute-unit-compute-pipeline.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1200_lds.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1200_lds.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1200_lds.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1200_lds.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1300_instruction-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1300_instruction-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1300_instruction-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1300_instruction-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1400_constant-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1400_constant-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1400_constant-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1400_constant-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1500_TA_and_TD.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1500_TA_and_TD.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1500_TA_and_TD.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1500_TA_and_TD.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1600_L1_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1600_L1_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1600_L1_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1600_L1_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1700_L2_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1700_L2_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1700_L2_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1700_L2_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1800_L2_cache_per_channel.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1800_L2_cache_per_channel.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx941/1800_L2_cache_per_channel.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/1800_L2_cache_per_channel.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0000_top_stats.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0000_top_stats.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0000_top_stats.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0000_top_stats.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0100_system_info.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0100_system_info.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0100_system_info.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0100_system_info.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0200_system-speed-of-light.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0200_system-speed-of-light.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0200_system-speed-of-light.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0300_mem_chart.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0300_mem_chart.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0300_mem_chart.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0300_mem_chart.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0500_command-processor.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0500_command-processor.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0500_command-processor.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0500_command-processor.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0600_shader-processor-input.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0600_shader-processor-input.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0600_shader-processor-input.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0600_shader-processor-input.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0700_wavefront-launch.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0700_wavefront-launch.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/0700_wavefront-launch.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0700_wavefront-launch.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1000_compute-unit-instruction-mix.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1000_compute-unit-instruction-mix.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1000_compute-unit-instruction-mix.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1000_compute-unit-instruction-mix.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1100_compute-unit-compute-pipeline.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1100_compute-unit-compute-pipeline.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1100_compute-unit-compute-pipeline.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1100_compute-unit-compute-pipeline.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1200_lds.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1200_lds.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1200_lds.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1200_lds.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1300_instruction-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1300_instruction-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1300_instruction-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1300_instruction-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1400_constant-cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1400_constant-cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1400_constant-cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1400_constant-cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1500_TA_and_TD.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1500_TA_and_TD.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1500_TA_and_TD.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1500_TA_and_TD.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1600_L1_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1600_L1_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1600_L1_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1600_L1_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1700_L2_cache.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1700_L2_cache.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1700_L2_cache.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1700_L2_cache.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1800_L2_cache_per_channel.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1800_L2_cache_per_channel.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/gfx942/1800_L2_cache_per_channel.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/1800_L2_cache_per_channel.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/panel_config_template.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/panel_config_template.yaml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/analysis_configs/panel_config_template.yaml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/panel_config_template.yaml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_cpc_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_cpc_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_cpc_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_cpc_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_cpf_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_cpf_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_cpf_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_cpf_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_spi_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_spi_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_spi_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_spi_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf1.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf1.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf1.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf1.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf2.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf2.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf2.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf2.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf3.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf3.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf3.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf3.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf4.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf4.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf4.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf4.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf6.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf6.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf6.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf6.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf8.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf8.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sq_perf8.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sq_perf8.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sqc_perf1.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sqc_perf1.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_sqc_perf1.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_sqc_perf1.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_ta_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_ta_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_ta_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_ta_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_tcc2_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_tcc2_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_tcc2_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_tcc2_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_tcc_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_tcc_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_tcc_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_tcc_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_tcp_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_tcp_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_tcp_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_tcp_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_td_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_td_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx900/pmc_td_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx900/pmc_td_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_cpc_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_cpc_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_cpc_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_cpc_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_cpf_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_cpf_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_cpf_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_cpf_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_spi_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_spi_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_spi_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_spi_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf1.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf1.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf1.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf1.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf2.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf2.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf2.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf2.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf3.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf3.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf3.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf3.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf4.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf4.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf4.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf4.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf6.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf6.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf6.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf6.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf8.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf8.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sq_perf8.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sq_perf8.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sqc_perf1.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sqc_perf1.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_sqc_perf1.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_sqc_perf1.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_ta_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_ta_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_ta_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_ta_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_tcc2_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_tcc2_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_tcc2_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_tcc2_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_tcc_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_tcc_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_tcc_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_tcc_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_tcp_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_tcp_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_tcp_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_tcp_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_td_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_td_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx906/pmc_td_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx906/pmc_td_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_cpc_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_cpc_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_cpc_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_cpc_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_cpf_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_cpf_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_cpf_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_cpf_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_spi_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_spi_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_spi_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_spi_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf1.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf1.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf1.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf1.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf2.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf2.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf2.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf2.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf3.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf3.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf3.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf3.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf4.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf4.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf4.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf4.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf6.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf6.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf6.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf6.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf8.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf8.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sq_perf8.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sq_perf8.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sqc_perf1.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sqc_perf1.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_sqc_perf1.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_sqc_perf1.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_ta_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_ta_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_ta_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_ta_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_tcc2_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_tcc2_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_tcc2_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_tcc2_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_tcc_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_tcc_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_tcc_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_tcc_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_tcp_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_tcp_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_tcp_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_tcp_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_td_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_td_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908/pmc_td_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908/pmc_td_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908_metrics.xml b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908_metrics.xml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx908_metrics.xml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx908_metrics.xml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_cpc_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_cpc_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_cpc_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_cpc_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_cpf_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_cpf_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_cpf_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_cpf_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_spi_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_spi_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_spi_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_spi_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf1.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf1.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf1.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf1.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf2.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf2.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf2.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf2.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf3.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf3.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf3.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf3.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf4.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf4.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf4.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf4.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf6.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf6.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf6.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf6.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf8.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf8.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sq_perf8.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sq_perf8.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sqc_perf1.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sqc_perf1.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_sqc_perf1.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_sqc_perf1.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_ta_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_ta_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_ta_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_ta_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_tcc2_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_tcc2_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_tcc2_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_tcc2_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_tcc_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_tcc_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_tcc_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_tcc_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_tcp_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_tcp_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_tcp_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_tcp_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_td_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_td_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/pmc_td_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/pmc_td_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/roofline/pmc_roof_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/roofline/pmc_roof_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx90a/roofline/pmc_roof_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx90a/roofline/pmc_roof_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_cpc_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_cpc_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_cpc_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_cpc_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_cpf_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_cpf_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_cpf_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_cpf_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_spi_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_spi_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_spi_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_spi_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf1.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf1.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf1.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf1.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf2.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf2.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf2.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf2.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf3.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf3.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf3.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf3.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf4.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf4.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf4.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf4.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf6.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf6.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf6.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf6.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf8.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf8.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sq_perf8.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sq_perf8.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sqc_perf1.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sqc_perf1.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_sqc_perf1.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_sqc_perf1.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_ta_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_ta_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_ta_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_ta_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_tcc2_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_tcc2_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_tcc2_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_tcc2_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_tcc_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_tcc_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_tcc_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_tcc_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_tcp_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_tcp_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_tcp_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_tcp_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_td_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_td_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/pmc_td_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/pmc_td_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/roofline/pmc_roof_perf.txt b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/roofline/pmc_roof_perf.txt similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/gfx940/roofline/pmc_roof_perf.txt rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/gfx940/roofline/pmc_roof_perf.txt diff --git a/projects/rocprofiler-compute/src/omniperf_soc/profile_configs/metrics.xml b/projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/metrics.xml similarity index 100% rename from projects/rocprofiler-compute/src/omniperf_soc/profile_configs/metrics.xml rename to projects/rocprofiler-compute/src/rocprof_compute_soc/profile_configs/metrics.xml diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_base.py b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_base.py similarity index 99% rename from projects/rocprofiler-compute/src/omniperf_soc/soc_base.py rename to projects/rocprofiler-compute/src/rocprof_compute_soc/soc_base.py index db8ce9a224..a02198f5c5 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_base.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_base.py @@ -33,8 +33,8 @@ from utils.utils import demarcate, console_debug, console_log, console_error from pathlib import Path from collections import OrderedDict -from omniperf_base import SUPPORTED_ARCHS -from omniperf_base import MI300_CHIP_IDS +from rocprof_compute_base import SUPPORTED_ARCHS +from rocprof_compute_base import MI300_CHIP_IDS class OmniSoC_Base: diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx906.py b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx906.py similarity index 95% rename from projects/rocprofiler-compute/src/omniperf_soc/soc_gfx906.py rename to projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx906.py index ad7dbbb997..2cba83dda0 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx906.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx906.py @@ -24,7 +24,7 @@ import os import config -from omniperf_soc.soc_base import OmniSoC_Base +from rocprof_compute_soc.soc_base import OmniSoC_Base from utils.utils import demarcate, console_error @@ -34,8 +34,8 @@ class gfx906_soc(OmniSoC_Base): self.set_arch("gfx906") self.set_perfmon_dir( os.path.join( - str(config.omniperf_home), - "omniperf_soc", + str(config.rocprof_compute_home), + "rocprof_compute_soc", "profile_configs", self.get_arch(), ) diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx908.py b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx908.py similarity index 90% rename from projects/rocprofiler-compute/src/omniperf_soc/soc_gfx908.py rename to projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx908.py index 415502a55f..5eb30cc0fb 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx908.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx908.py @@ -24,7 +24,7 @@ import os import config -from omniperf_soc.soc_base import OmniSoC_Base +from rocprof_compute_soc.soc_base import OmniSoC_Base from utils.utils import demarcate, console_error @@ -34,8 +34,8 @@ class gfx908_soc(OmniSoC_Base): self.set_arch("gfx908") self.set_perfmon_dir( os.path.join( - str(config.omniperf_home), - "omniperf_soc", + str(config.rocprof_compute_home), + "rocprof_compute_soc", "profile_configs", self.get_arch(), ) @@ -63,10 +63,8 @@ class gfx908_soc(OmniSoC_Base): self._mspec.lds_banks_per_cu = 32 self._mspec.pipes_per_gpu = 4 # --showmclkrange is broken in Mi100, hardcode freq - if self._mspec.gpu_model == "MI100": - if self._mspec.max_mclk == None or self._mspec.cur_mclk == None: - self._mspec.max_mclk = 1200 - self._mspec.cur_mclk = 1200 + self._mspec.max_mclk = 1200 + self._mspec.cur_mclk = 1200 @demarcate def get_profiler_options(self): diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx90a.py b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx90a.py similarity index 88% rename from projects/rocprofiler-compute/src/omniperf_soc/soc_gfx90a.py rename to projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx90a.py index 9e5fbd04e7..7d3e12c2f4 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx90a.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx90a.py @@ -24,7 +24,7 @@ import os import config -from omniperf_soc.soc_base import OmniSoC_Base +from rocprof_compute_soc.soc_base import OmniSoC_Base from utils.utils import demarcate, mibench, console_log from roofline import Roofline @@ -36,8 +36,8 @@ class gfx90a_soc(OmniSoC_Base): if hasattr(self.get_args(), "roof_only") and self.get_args().roof_only: self.set_perfmon_dir( os.path.join( - str(config.omniperf_home), - "omniperf_soc", + str(config.rocprof_compute_home), + "rocprof_compute_soc", "profile_configs", self.get_arch(), "roofline", @@ -46,8 +46,8 @@ class gfx90a_soc(OmniSoC_Base): else: self.set_perfmon_dir( os.path.join( - str(config.omniperf_home), - "omniperf_soc", + str(config.rocprof_compute_home), + "rocprof_compute_soc", "profile_configs", self.get_arch(), ) @@ -71,13 +71,6 @@ class gfx90a_soc(OmniSoC_Base): ) self.roofline_obj = Roofline(args, self._mspec) - # Workaround for broken --showmclkrange - # MI210/MI250/MI250X have 1600MHz mclk - if self._mspec.gpu_model == "MI200": - if self._mspec.max_mclk == None or self._mspec.cur_mclk == None: - self._mspec.max_mclk = 1600 - self._mspec.cur_mclk = 1600 - # Set arch specific specs self._mspec._l2_banks = 32 self._mspec.lds_banks_per_cu = 32 diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx940.py b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx940.py similarity index 92% rename from projects/rocprofiler-compute/src/omniperf_soc/soc_gfx940.py rename to projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx940.py index 77afc0247a..b3d61fcbf4 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx940.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx940.py @@ -24,7 +24,7 @@ import os import config -from omniperf_soc.soc_base import OmniSoC_Base +from rocprof_compute_soc.soc_base import OmniSoC_Base from utils.utils import demarcate, mibench, console_log, console_error from roofline import Roofline @@ -36,8 +36,8 @@ class gfx940_soc(OmniSoC_Base): if hasattr(self.get_args(), "roof_only") and self.get_args().roof_only: self.set_perfmon_dir( os.path.join( - str(config.omniperf_home), - "omniperf_soc", + str(config.rocprof_compute_home), + "rocprof_compute_soc", "profile_configs", "gfx940", "roofline", @@ -47,7 +47,10 @@ class gfx940_soc(OmniSoC_Base): # NB: We're using generalized Mi300 perfmon configs self.set_perfmon_dir( os.path.join( - str(config.omniperf_home), "omniperf_soc", "profile_configs", "gfx940" + str(config.rocprof_compute_home), + "rocprof_compute_soc", + "profile_configs", + "gfx940", ) ) self.set_compatible_profilers(["rocprofv1", "rocprofv2"]) diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx941.py b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx941.py similarity index 92% rename from projects/rocprofiler-compute/src/omniperf_soc/soc_gfx941.py rename to projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx941.py index c7a74081c7..6fe2bd085d 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx941.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx941.py @@ -24,7 +24,7 @@ import os import config -from omniperf_soc.soc_base import OmniSoC_Base +from rocprof_compute_soc.soc_base import OmniSoC_Base from utils.utils import demarcate, mibench, console_log, console_error from roofline import Roofline @@ -36,8 +36,8 @@ class gfx941_soc(OmniSoC_Base): if hasattr(self.get_args(), "roof_only") and self.get_args().roof_only: self.set_perfmon_dir( os.path.join( - str(config.omniperf_home), - "omniperf_soc", + str(config.rocprof_compute_home), + "rocprof_compute_soc", "profile_configs", "gfx940", "roofline", @@ -47,7 +47,10 @@ class gfx941_soc(OmniSoC_Base): # NB: We're using generalized Mi300 perfmon configs self.set_perfmon_dir( os.path.join( - str(config.omniperf_home), "omniperf_soc", "profile_configs", "gfx940" + str(config.rocprof_compute_home), + "rocprof_compute_soc", + "profile_configs", + "gfx940", ) ) self.set_compatible_profilers(["rocprofv1", "rocprofv2"]) diff --git a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx942.py b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx942.py similarity index 88% rename from projects/rocprofiler-compute/src/omniperf_soc/soc_gfx942.py rename to projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx942.py index 606d9a8399..7773f0c966 100644 --- a/projects/rocprofiler-compute/src/omniperf_soc/soc_gfx942.py +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/soc_gfx942.py @@ -24,7 +24,7 @@ import os import config -from omniperf_soc.soc_base import OmniSoC_Base +from rocprof_compute_soc.soc_base import OmniSoC_Base from utils.utils import demarcate, mibench, console_log, console_error from roofline import Roofline @@ -36,8 +36,8 @@ class gfx942_soc(OmniSoC_Base): if hasattr(self.get_args(), "roof_only") and self.get_args().roof_only: self.set_perfmon_dir( os.path.join( - str(config.omniperf_home), - "omniperf_soc", + str(config.rocprof_compute_home), + "rocprof_compute_soc", "profile_configs", "gfx940", "roofline", @@ -47,7 +47,10 @@ class gfx942_soc(OmniSoC_Base): # NB: We're using generalized Mi300 perfmon configs self.set_perfmon_dir( os.path.join( - str(config.omniperf_home), "omniperf_soc", "profile_configs", "gfx940" + str(config.rocprof_compute_home), + "rocprof_compute_soc", + "profile_configs", + "gfx940", ) ) self.set_compatible_profilers(["rocprofv1", "rocprofv2"]) @@ -69,12 +72,10 @@ class gfx942_soc(OmniSoC_Base): ) # self.roofline_obj = Roofline(args, self._mspec) - # Workaround for broken --showmclkrange - # MI300X/MI300A/MI308X have 1300MHz mclk - if self._mspec.gpu_model == "MI300": - if self._mspec.max_mclk == None or self._mspec.cur_mclk == None: - self._mspec.max_mclk = 1300 - self._mspec.cur_mclk = 1300 + # --showmclkrange is broken in MI308X, hardcode freq + if self._mspec.gpu_model == "MI308X": + self._mspec.max_mclk = 1300 + self._mspec.cur_mclk = 1300 # Set arch specific specs self._mspec._l2_banks = 16 diff --git a/projects/rocprofiler-compute/src/roofline.py b/projects/rocprofiler-compute/src/roofline.py index 3efefef746..2ba350fa4c 100644 --- a/projects/rocprofiler-compute/src/roofline.py +++ b/projects/rocprofiler-compute/src/roofline.py @@ -418,7 +418,7 @@ class Roofline: if not self.__args.remaining: console_error( "profiling" - "An is required to run.\nomniperf profile -n test -- " + "An is required to run.\rrocprof-compute profile -n test -- " ) # TODO: Add an equivelent of characterize_app() to run profiling directly out of this module @@ -427,7 +427,7 @@ class Roofline: else: mibench(self.__args, self.__mspec) - # NB: Currently the post_prossesing() method is the only one being used by omniperf, + # NB: Currently the post_prossesing() method is the only one being used by rocprofiler-compute, # we include pre_processing() and profile() methods for those who wish to borrow the roofline module @abstractmethod def post_processing(self): diff --git a/projects/rocprofiler-compute/src/utils/db_connector.py b/projects/rocprofiler-compute/src/utils/db_connector.py index 195ff6be85..4216e01a34 100644 --- a/projects/rocprofiler-compute/src/utils/db_connector.py +++ b/projects/rocprofiler-compute/src/utils/db_connector.py @@ -79,7 +79,12 @@ class DatabaseConnector: ) self.connection_info["db"] = ( - "omniperf_" + str(self.args.team) + "_" + str(name) + "_" + str(soc) + "rocprofiler-compute_" + + str(self.args.team) + + "_" + + str(name) + + "_" + + str(soc) ) @demarcate @@ -157,7 +162,7 @@ class DatabaseConnector: is_full_workload_name = self.args.workload.count("_") >= 3 if not is_full_workload_name: console_error( - "-w/--workload is not valid. Please use full workload name as seen in GUI when removing (i.e. omniperf_asw_vcopy_mi200)" + "-w/--workload is not valid. Please use full workload name as seen in GUI when removing (i.e. rocprofiler-compute_asw_vcopy_mi200)" ) if ( self.connection_info["host"] == None diff --git a/projects/rocprofiler-compute/src/utils/gui_components/header.py b/projects/rocprofiler-compute/src/utils/gui_components/header.py index d8255ae463..7e6a3811a6 100644 --- a/projects/rocprofiler-compute/src/utils/gui_components/header.py +++ b/projects/rocprofiler-compute/src/utils/gui_components/header.py @@ -299,7 +299,7 @@ def get_header(raw_pmc, input_filters, kernel_names): children=[ # Report bug button html.A( - href="https://github.com/ROCm/omniperf/issues", + href="https://github.com/ROCm/rocprofiler-compute/issues", children=[ html.Button( className="report", diff --git a/projects/rocprofiler-compute/src/utils/logger.py b/projects/rocprofiler-compute/src/utils/logger.py index dae4a7a25f..b6285ba008 100644 --- a/projects/rocprofiler-compute/src/utils/logger.py +++ b/projects/rocprofiler-compute/src/utils/logger.py @@ -83,8 +83,8 @@ def setup_console_handler(): setattr(logging, "trace", trace_logger) color_setting = 1 - if "OMNIPERF_COLOR" in os.environ.keys(): - color_setting = int(os.environ["OMNIPERF_COLOR"]) + if "ROCPROFCOMPUTE_COLOR" in os.environ.keys(): + color_setting = int(os.environ["ROCPROFCOMPUTE_COLOR"]) if color_setting == 0: # non-colored @@ -99,7 +99,7 @@ def setup_console_handler(): # no color or levelname for INFO, other log messages entirely in color formatter = ColoredFormatterAll() else: - print("Unsupported setting for OMNIPERF_COLOR - set to 0, 1, 2 or 3.") + print("Unsupported setting for ROCPROFCOMPUTE_COLOR - set to 0, 1, 2 or 3.") sys.exit(1) console_handler = logging.StreamHandler(sys.stdout) @@ -130,8 +130,8 @@ def setup_logging_priority(verbosity, quietmode, appmode): loglevel = levels[min(verbosity, len(levels) - 1)] # cap to last level index # optional: override of default loglevel via env variable which takes precedence - if "OMNIPERF_LOGLEVEL" in os.environ.keys(): - loglevel = os.environ["OMNIPERF_LOGLEVEL"] + if "ROCPROFCOMPUTE_LOGLEVEL" in os.environ.keys(): + loglevel = os.environ["ROCPROFCOMPUTE_LOGLEVEL"] if loglevel in {"DEBUG", "debug"}: loglevel = logging.DEBUG elif loglevel in {"TRACE", "trace"}: @@ -141,7 +141,7 @@ def setup_logging_priority(verbosity, quietmode, appmode): elif loglevel in {"ERROR", "error"}: loglevel = logging.ERROR else: - print("Ignoring unsupported OMNIPERF_LOGLEVEL setting (%s)" % loglevel) + print("Ignoring unsupported ROCPROFCOMPUTE_LOGLEVEL setting (%s)" % loglevel) sys.exit(1) # update console loglevel based on command-line args/env settings diff --git a/projects/rocprofiler-compute/src/utils/mem_chart.py b/projects/rocprofiler-compute/src/utils/mem_chart.py index 8a4dcf1f86..0bf922625f 100644 --- a/projects/rocprofiler-compute/src/utils/mem_chart.py +++ b/projects/rocprofiler-compute/src/utils/mem_chart.py @@ -178,7 +178,9 @@ class Exec(RectFrame): ) canvas.text(self.x_min + 4.0, self.y_max - 13.0, "LDS Alloc:") canvas.text( - self.x_min + 4.0, self.y_max - 14.0, "{val:>13.0f}".format(val=self.lds_alloc) + self.x_min + 4.0, + self.y_max - 14.0, + "{val:>13.0f}".format(val=self.lds_alloc), ) canvas.rect( diff --git a/projects/rocprofiler-compute/src/utils/resources.py b/projects/rocprofiler-compute/src/utils/resources.py index 198684261e..634174e93b 100644 --- a/projects/rocprofiler-compute/src/utils/resources.py +++ b/projects/rocprofiler-compute/src/utils/resources.py @@ -30,6 +30,6 @@ def get_resource_path(relative_path): rel_path = pathlib.Path(relative_path) dev_base_path = ( pathlib.Path(__file__).resolve().parent.parent.parent.parent - ) # omniperf dir (whereas equiv comd in omniperf.py returns src dir) + ) # rocprof_compute dir (whereas equiv comd in rocprof_compute.py returns src dir) base_path = getattr(sys, "_MEIPASS", dev_base_path) return dev_base_path diff --git a/projects/rocprofiler-compute/src/utils/specs.py b/projects/rocprofiler-compute/src/utils/specs.py index 07938bcf18..4cbc55e5b3 100644 --- a/projects/rocprofiler-compute/src/utils/specs.py +++ b/projects/rocprofiler-compute/src/utils/specs.py @@ -58,7 +58,7 @@ VERSION_LOC = [ def detect_arch(_rocminfo): - from omniperf_base import SUPPORTED_ARCHS + from rocprof_compute_base import SUPPORTED_ARCHS for idx1, linetext in enumerate(_rocminfo): gpu_arch = search(r"^\s*Name\s*:\s+ ([a-zA-Z0-9]+)\s*$", linetext) @@ -91,7 +91,7 @@ def generate_machine_specs(args, sysinfo: dict = None): console_error( "Detected mismatch in sysinfo versioning. You need to reprofile to update data." ) - version = get_version(config.omniperf_home)["version"] + version = get_version(config.rocprof_compute_home)["version"] if sysinfo_ver != version[: version.find(".")]: console_error( "Detected mismatch in sysinfo versioning. You need to reprofile to update data." @@ -106,7 +106,7 @@ def generate_machine_specs(args, sysinfo: dict = None): hostname = socket.gethostname() # set specs version - vData = get_version(config.omniperf_home) + vData = get_version(config.rocprof_compute_home) version = vData["version"] # NB: Just taking major as specs version. May want to make this more specific in the future specs_version = version[ @@ -174,7 +174,7 @@ def generate_machine_specs(args, sysinfo: dict = None): ) # Load above SoC specs via module import try: - soc_module = importlib.import_module("omniperf_soc.soc_" + specs.gpu_arch) + soc_module = importlib.import_module("rocprof_compute_soc.soc_" + specs.gpu_arch) except ModuleNotFoundError as e: console_error( "Arch %s marked as supported, but couldn't find class implementation %s." @@ -253,7 +253,8 @@ class MachineSpecs: ## A. Machine Specs ########################################## hostname: str = field( - default=None, metadata={"doc": "The hostname of the machine.", "name": "Hostname"} + default=None, + metadata={"doc": "The hostname of the machine.", "name": "Hostname"}, ) cpu_model: str = field( default=None, @@ -547,7 +548,7 @@ class MachineSpecs: return pd.DataFrame(data, index=[0]) def __repr__(self): - topstr = "Machine Specifications: describing the state of the machine that Omniperf data was collected on.\n" + topstr = "Machine Specifications: describing the state of the machine that ROCm Compute Profiler data was collected on.\n" data = [] for field in fields(self): name = field.name diff --git a/projects/rocprofiler-compute/src/utils/utils.py b/projects/rocprofiler-compute/src/utils/utils.py index 4175fdab2e..c4b26a240b 100644 --- a/projects/rocprofiler-compute/src/utils/utils.py +++ b/projects/rocprofiler-compute/src/utils/utils.py @@ -87,12 +87,12 @@ def trace_logger(message, *args, **kwargs): logging.log(logging.TRACE, message, *args, **kwargs) -def get_version(omniperf_home) -> dict: - """Return Omniperf versioning info""" +def get_version(rocprof_compute_home) -> dict: + """Return ROCm Compute Profiler versioning info""" # symantic version info - note that version file(s) can reside in # two locations depending on development vs formal install - searchDirs = [omniperf_home, omniperf_home.parent] + searchDirs = [rocprof_compute_home, rocprof_compute_home.parent] found = False versionDir = None @@ -110,7 +110,7 @@ def get_version(omniperf_home) -> dict: console_error("Cannot find VERSION file at {}".format(searchDirs)) # git version info - gitDir = os.path.join(omniperf_home.parent, ".git") + gitDir = os.path.join(rocprof_compute_home.parent, ".git") if (shutil.which("git") is not None) and os.path.exists(gitDir): gitQuery = subprocess.run( ["git", "log", "--pretty=format:%h", "-n", "1"], @@ -142,7 +142,7 @@ def get_version_display(version, sha, mode): """Pretty print versioning info""" buf = io.StringIO() print("-" * 40, file=buf) - print("Omniperf version: %s (%s)" % (version, mode), file=buf) + print("rocprofiler-compute version: %s (%s)" % (version, mode), file=buf) print("Git revision: %s" % sha, file=buf) print("-" * 40, file=buf) return buf.getvalue() @@ -400,7 +400,11 @@ def detect_roofline(mspec): rooflineBinary = os.environ["ROOFLINE_BIN"] if os.path.exists(rooflineBinary): console_warning("roofline", "Detected user-supplied binary") - return {"rocm_ver": "override", "distro": "override", "path": rooflineBinary} + return { + "rocm_ver": "override", + "distro": "override", + "path": rooflineBinary, + } else: msg = "user-supplied path to binary not accessible" msg += "--> ROOFLINE_BIN = %s\n" % target_binary @@ -470,8 +474,8 @@ def mibench(args, mspec): # check two potential locations for roofline binaries due to differences in # development usage vs formal install potential_paths = [ - "%s/utils/rooflines/roofline" % config.omniperf_home, - "%s/bin/roofline" % config.omniperf_home.parent.parent, + "%s/utils/rooflines/roofline" % config.rocprof_compute_home, + "%s/bin/roofline" % config.rocprof_compute_home.parent.parent, ] for dir in potential_paths: diff --git a/projects/rocprofiler-compute/tests/4gpus.json b/projects/rocprofiler-compute/tests/4gpus.json index e2cac33e27..6c59d23c43 100644 --- a/projects/rocprofiler-compute/tests/4gpus.json +++ b/projects/rocprofiler-compute/tests/4gpus.json @@ -1,24 +1,15 @@ { - "version": { - "major": 1, - "minor": 0 - }, - "local": [ - { - "gpus": [ + "version": {"major": 1, "minor": 0}, + "local": [ { - "id": "0", - }, - { - "id": "1" - }, - { - "id": "2" - }, - { - "id": "3" - } - ] - } - ] + "gpus": [ + { + "id": "0", + }, + {"id": "1"}, + {"id": "2"}, + {"id": "3"}, + ] + } + ], } diff --git a/projects/rocprofiler-compute/tests/generate_test_analyze_workloads.py b/projects/rocprofiler-compute/tests/generate_test_analyze_workloads.py index 58e2b9f6f8..03fe62e78d 100644 --- a/projects/rocprofiler-compute/tests/generate_test_analyze_workloads.py +++ b/projects/rocprofiler-compute/tests/generate_test_analyze_workloads.py @@ -27,11 +27,11 @@ if __name__ == "__main__": + arch + "():" + "\n\twith pytest.raises(SystemExit) as e:" - + "\n\t\twith patch('sys.argv',['omniperf', 'analyze', '--path', '" + + "\n\t\twith patch('sys.argv',['rocprof-compute', 'analyze', '--path', '" + workload + "/" + arch - + "']):\n\t\t\tomniperf.main()" + + "']):\n\t\t\trocprof_compute.main()" + "\n\tassert e.value.code == 0" ) f.write(test) diff --git a/projects/rocprofiler-compute/tests/generate_workloads.sh b/projects/rocprofiler-compute/tests/generate_workloads.sh index e57b06b1ac..478d4b8e2b 100755 --- a/projects/rocprofiler-compute/tests/generate_workloads.sh +++ b/projects/rocprofiler-compute/tests/generate_workloads.sh @@ -56,6 +56,6 @@ echo "starting" for key in "${!commands[@]}"; do echo profiling $key; command="${commands[$key]}" - echo "$key = ./src/omniperf profile -n $key ${dirs[@]}" - ./src/omniperf profile -n $key $command -p tests/workloads/$key/$soc -- ./tests/vcopy -n 1048576 -b 256 -i 3 ; + echo "$key = ./src/rocprof-compute profile -n $key ${dirs[@]}" + ./src/rocprof-compute profile -n $key $command -p tests/workloads/$key/$soc -- ./tests/vcopy -n 1048576 -b 256 -i 3 ; echo "done" ; done \ No newline at end of file diff --git a/projects/rocprofiler-compute/tests/test_analyze_commands.py b/projects/rocprofiler-compute/tests/test_analyze_commands.py index 303e60b0a9..fde43bc500 100644 --- a/projects/rocprofiler-compute/tests/test_analyze_commands.py +++ b/projects/rocprofiler-compute/tests/test_analyze_commands.py @@ -7,9 +7,9 @@ import shutil import pandas as pd import test_utils -omniperf = SourceFileLoader("omniperf", "src/omniperf").load_module() +rocprof_compute = SourceFileLoader("rocprof-compute", "src/rocprof-compute").load_module() -baseline_opts = ["omniperf", "analyze"] +baseline_opts = ["rocprof-compute", "analyze"] config = {} config["cleanup"] = True if "PYTEST_XDIST_WORKER_COUNT" in os.environ else False @@ -29,9 +29,9 @@ def test_valid_path(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", workload_dir], + ["rocprof-compute", "analyze", "--path", workload_dir], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -45,14 +45,14 @@ def test_list_kernels(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, "--list-stats", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -60,8 +60,10 @@ def test_list_kernels(): @pytest.mark.list_metrics def test_list_metrics_gfx90a(): with pytest.raises(SystemExit) as e: - with patch("sys.argv", ["omniperf", "analyze", "--list-metrics", "gfx90a"]): - omniperf.main() + with patch( + "sys.argv", ["rocprof-compute", "analyze", "--list-metrics", "gfx90a"] + ): + rocprof_compute.main() assert e.value.code == 1 for dir in indirs: @@ -70,7 +72,7 @@ def test_list_metrics_gfx90a(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -78,7 +80,7 @@ def test_list_metrics_gfx90a(): "gfx90a", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -87,8 +89,10 @@ def test_list_metrics_gfx90a(): @pytest.mark.list_metrics def test_list_metrics_gfx906(): with pytest.raises(SystemExit) as e: - with patch("sys.argv", ["omniperf", "analyze", "--list-metrics", "gfx906"]): - omniperf.main() + with patch( + "sys.argv", ["rocprof-compute", "analyze", "--list-metrics", "gfx906"] + ): + rocprof_compute.main() assert e.value.code == 1 for dir in indirs: @@ -97,7 +101,7 @@ def test_list_metrics_gfx906(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -105,7 +109,7 @@ def test_list_metrics_gfx906(): "gfx906", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -114,8 +118,10 @@ def test_list_metrics_gfx906(): @pytest.mark.list_metrics def test_list_metrics_gfx908(): with pytest.raises(SystemExit) as e: - with patch("sys.argv", ["omniperf", "analyze", "--list-metrics", "gfx908"]): - omniperf.main() + with patch( + "sys.argv", ["rocprof-compute", "analyze", "--list-metrics", "gfx908"] + ): + rocprof_compute.main() assert e.value.code == 1 for dir in indirs: @@ -124,7 +130,7 @@ def test_list_metrics_gfx908(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -132,7 +138,7 @@ def test_list_metrics_gfx908(): "gfx908", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -146,7 +152,7 @@ def test_filter_block_1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -154,7 +160,7 @@ def test_filter_block_1(): "1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -168,7 +174,7 @@ def test_filter_block_2(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -176,7 +182,7 @@ def test_filter_block_2(): "5", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -190,7 +196,7 @@ def test_filter_block_3(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -198,7 +204,7 @@ def test_filter_block_3(): "5.2.2", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -212,7 +218,7 @@ def test_filter_block_4(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -220,7 +226,7 @@ def test_filter_block_4(): "6.1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -234,7 +240,7 @@ def test_filter_block_5(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -242,7 +248,7 @@ def test_filter_block_5(): "10", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -256,7 +262,7 @@ def test_filter_block_6(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -264,7 +270,7 @@ def test_filter_block_6(): "100", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -278,7 +284,7 @@ def test_filter_kernel_1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -286,7 +292,7 @@ def test_filter_kernel_1(): "0", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -300,7 +306,7 @@ def test_filter_kernel_2(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -308,7 +314,7 @@ def test_filter_kernel_2(): "1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -322,7 +328,7 @@ def test_filter_kernel_3(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -331,7 +337,7 @@ def test_filter_kernel_3(): "1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -345,7 +351,7 @@ def test_dispatch_1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -353,7 +359,7 @@ def test_dispatch_1(): "0", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -367,7 +373,7 @@ def test_dispatch_2(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -375,7 +381,7 @@ def test_dispatch_2(): "1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -389,7 +395,7 @@ def test_dispatch_3(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -397,7 +403,7 @@ def test_dispatch_3(): "2", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -411,7 +417,7 @@ def test_dispatch_4(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -420,7 +426,7 @@ def test_dispatch_4(): "4", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -434,7 +440,7 @@ def test_dispatch_5(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -443,7 +449,7 @@ def test_dispatch_5(): "6", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -457,7 +463,7 @@ def test_gpu_ids(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -465,7 +471,7 @@ def test_gpu_ids(): "2", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -479,7 +485,7 @@ def test_normal_unit_per_wave(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -487,7 +493,7 @@ def test_normal_unit_per_wave(): "per_wave", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -501,7 +507,7 @@ def test_normal_unit_per_cycle(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -509,7 +515,7 @@ def test_normal_unit_per_cycle(): "per_cycle", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -523,7 +529,7 @@ def test_normal_unit_per_second(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -531,7 +537,7 @@ def test_normal_unit_per_second(): "per_second", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -545,7 +551,7 @@ def test_normal_unit_per_kernel(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -553,7 +559,7 @@ def test_normal_unit_per_kernel(): "per_kernel", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -567,7 +573,7 @@ def test_max_stat_num_1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -575,7 +581,7 @@ def test_max_stat_num_1(): "0", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -589,7 +595,7 @@ def test_max_stat_num_2(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -597,7 +603,7 @@ def test_max_stat_num_2(): "5", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -611,7 +617,7 @@ def test_max_stat_num_3(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -619,7 +625,7 @@ def test_max_stat_num_3(): "10", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -633,7 +639,7 @@ def test_max_stat_num_4(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -641,7 +647,7 @@ def test_max_stat_num_4(): "15", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -655,7 +661,7 @@ def test_time_unit_s(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -663,7 +669,7 @@ def test_time_unit_s(): "s", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -677,7 +683,7 @@ def test_time_unit_ms(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -685,7 +691,7 @@ def test_time_unit_ms(): "ms", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -699,7 +705,7 @@ def test_time_unit_us(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -707,7 +713,7 @@ def test_time_unit_us(): "us", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -721,7 +727,7 @@ def test_time_unit_ns(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -729,7 +735,7 @@ def test_time_unit_ns(): "ns", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -743,7 +749,7 @@ def test_decimal_1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -751,7 +757,7 @@ def test_decimal_1(): "0", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -765,7 +771,7 @@ def test_decimal_2(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -773,7 +779,7 @@ def test_decimal_2(): "1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -787,7 +793,7 @@ def test_decimal_3(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -795,7 +801,7 @@ def test_decimal_3(): "4", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -810,7 +816,7 @@ def test_save_dfs(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -818,7 +824,7 @@ def test_save_dfs(): output_path, ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 files_in_workload = os.listdir(output_path) @@ -843,7 +849,7 @@ def test_save_dfs(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -851,7 +857,7 @@ def test_save_dfs(): output_path, ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 files_in_workload = os.listdir(output_path) @@ -872,7 +878,7 @@ def test_col_1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -880,7 +886,7 @@ def test_col_1(): "0", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -894,7 +900,7 @@ def test_col_2(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -902,7 +908,7 @@ def test_col_2(): "2", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -916,7 +922,7 @@ def test_col_3(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -925,7 +931,7 @@ def test_col_3(): "2", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -939,14 +945,14 @@ def test_g(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, "-g", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -960,7 +966,7 @@ def test_kernel_verbose_0(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -968,7 +974,7 @@ def test_kernel_verbose_0(): "0", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -982,7 +988,7 @@ def test_kernel_verbose_1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -990,7 +996,7 @@ def test_kernel_verbose_1(): "1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -1004,7 +1010,7 @@ def test_kernel_verbose_2(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -1012,7 +1018,7 @@ def test_kernel_verbose_2(): "2", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -1026,7 +1032,7 @@ def test_kernel_verbose_3(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -1034,7 +1040,7 @@ def test_kernel_verbose_3(): "3", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -1048,7 +1054,7 @@ def test_kernel_verbose_4(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -1056,7 +1062,7 @@ def test_kernel_verbose_4(): "4", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -1070,7 +1076,7 @@ def test_kernel_verbose_5(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -1078,7 +1084,7 @@ def test_kernel_verbose_5(): "5", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -1092,7 +1098,7 @@ def test_kernel_verbose_6(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, @@ -1100,7 +1106,7 @@ def test_kernel_verbose_6(): "6", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) @@ -1112,7 +1118,7 @@ def test_baseline(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/vcopy/MI200", @@ -1120,7 +1126,7 @@ def test_baseline(): "tests/workloads/vcopy/MI100", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 with pytest.raises(SystemExit) as e: @@ -1135,8 +1141,8 @@ def test_baseline(): "tests/workloads/vcopy/MI200", ], ): - omniperf.main() - assert e.value.code == 0 + rocprof_compute.main() + assert e.value.code == 1 with pytest.raises(SystemExit) as e: with patch( @@ -1150,54 +1156,8 @@ def test_baseline(): "tests/workloads/vcopy/MI100", ], ): - omniperf.main() - assert e.value.code == 0 - - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - [ - "omniperf", - "analyze", - "--path", - "tests/workloads/multikernel/MI200", - "-k", - "0", - "--path", - "tests/workloads/multikernel/MI200", - "-k", - "1", - "--path", - "tests/workloads/multikernel/MI200", - "-k", - "2", - ], - ): - omniperf.main() - assert e.value.code == 0 - - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - [ - "omniperf", - "analyze", - "--path", - "tests/workloads/multikernel/MI200", - "-k", - "0", - "--path", - "tests/workloads/multikernel/MI200", - "-k", - "1", - "--path", - "tests/workloads/vcopy/MI100", - "-k", - "0", - ], - ): - omniperf.main() - assert e.value.code == 0 + rocprof_compute.main() + assert e.value.code == 1 @pytest.mark.misc @@ -1208,13 +1168,13 @@ def test_dependency_MI100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", workload_dir, "--dependency", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 test_utils.clean_output_dir(config["cleanup"], workload_dir) diff --git a/projects/rocprofiler-compute/tests/test_analyze_workloads.py b/projects/rocprofiler-compute/tests/test_analyze_workloads.py index 2b3605ed7e..c47e59b305 100644 --- a/projects/rocprofiler-compute/tests/test_analyze_workloads.py +++ b/projects/rocprofiler-compute/tests/test_analyze_workloads.py @@ -10,11 +10,10 @@ import shutil import inspect import sys import test_utils -import pytest from unittest.mock import patch from importlib.machinery import SourceFileLoader -omniperf = SourceFileLoader("omniperf", "src/omniperf").load_module() +rocprof_compute = SourceFileLoader("rocprof-compute", "src/rocprof-compute").load_module() ################################################## ## Generated tests ## @@ -24,18 +23,20 @@ omniperf = SourceFileLoader("omniperf", "src/omniperf").load_module() def test_analyze_vcopy_MI100(): with pytest.raises(SystemExit) as e: with patch( - "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/vcopy/MI100"] + "sys.argv", + ["rocprof-compute", "analyze", "--path", "tests/workloads/vcopy/MI100"], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 def test_analyze_vcopy_MI200(): with pytest.raises(SystemExit) as e: with patch( - "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/vcopy/MI200"] + "sys.argv", + ["rocprof-compute", "analyze", "--path", "tests/workloads/vcopy/MI200"], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -43,9 +44,14 @@ def test_analyze_ipblocks_TCP_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCP/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TCP/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -53,9 +59,14 @@ def test_analyze_ipblocks_TCP_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCP/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TCP/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -63,9 +74,14 @@ def test_analyze_ipblocks_TCP_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCP/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TCP/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -73,9 +89,14 @@ def test_analyze_ipblocks_TCP_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCP/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TCP/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -83,9 +104,14 @@ def test_analyze_ipblocks_SQC_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQC/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQC/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -93,9 +119,14 @@ def test_analyze_ipblocks_SQC_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQC/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQC/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -103,9 +134,14 @@ def test_analyze_ipblocks_SQC_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQC/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQC/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -113,9 +149,14 @@ def test_analyze_ipblocks_SQC_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQC/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQC/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -123,9 +164,14 @@ def test_analyze_mem_levels_HBM_LDS_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/mem_levels_HBM_LDS/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/mem_levels_HBM_LDS/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -133,9 +179,14 @@ def test_analyze_ipblocks_TCC_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCC/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TCC/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -143,9 +194,14 @@ def test_analyze_ipblocks_TCC_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCC/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TCC/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -153,9 +209,14 @@ def test_analyze_ipblocks_TCC_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCC/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TCC/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -163,9 +224,14 @@ def test_analyze_ipblocks_TCC_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCC/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TCC/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -173,18 +239,24 @@ def test_analyze_no_roof_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/no_roof/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/no_roof/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 def test_analyze_no_roof_MI100(): with pytest.raises(SystemExit) as e: with patch( - "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/no_roof/MI100"] + "sys.argv", + ["rocprof-compute", "analyze", "--path", "tests/workloads/no_roof/MI100"], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -192,18 +264,24 @@ def test_analyze_no_roof_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/no_roof/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/no_roof/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 def test_analyze_no_roof_MI200(): with pytest.raises(SystemExit) as e: with patch( - "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/no_roof/MI200"] + "sys.argv", + ["rocprof-compute", "analyze", "--path", "tests/workloads/no_roof/MI200"], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -212,13 +290,13 @@ def test_analyze_ipblocks_SQ_CPC_MI300X_A1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_CPC/MI300X_A1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -226,9 +304,14 @@ def test_analyze_ipblocks_SQ_CPC_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_CPC/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ_CPC/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -237,13 +320,13 @@ def test_analyze_ipblocks_SQ_CPC_MI300A_A1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_CPC/MI300A_A1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -251,9 +334,14 @@ def test_analyze_ipblocks_SQ_CPC_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_CPC/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ_CPC/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -261,9 +349,14 @@ def test_analyze_dispatch_0_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_0/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -271,9 +364,14 @@ def test_analyze_dispatch_0_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_0/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -281,9 +379,14 @@ def test_analyze_dispatch_0_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_0/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -291,9 +394,14 @@ def test_analyze_dispatch_0_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_0/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -301,9 +409,14 @@ def test_analyze_join_type_grid_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/join_type_grid/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/join_type_grid/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -311,9 +424,14 @@ def test_analyze_join_type_grid_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/join_type_grid/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/join_type_grid/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -321,9 +439,14 @@ def test_analyze_join_type_grid_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/join_type_grid/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/join_type_grid/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -331,9 +454,14 @@ def test_analyze_join_type_grid_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/join_type_grid/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/join_type_grid/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -341,18 +469,24 @@ def test_analyze_kernel_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 def test_analyze_kernel_MI100(): with pytest.raises(SystemExit) as e: with patch( - "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/kernel/MI100"] + "sys.argv", + ["rocprof-compute", "analyze", "--path", "tests/workloads/kernel/MI100"], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -360,18 +494,24 @@ def test_analyze_kernel_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 def test_analyze_kernel_MI200(): with pytest.raises(SystemExit) as e: with patch( - "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/kernel/MI200"] + "sys.argv", + ["rocprof-compute", "analyze", "--path", "tests/workloads/kernel/MI200"], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -379,9 +519,14 @@ def test_analyze_kernel_substr_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_substr/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_substr/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -389,9 +534,14 @@ def test_analyze_kernel_substr_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_substr/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_substr/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -399,9 +549,14 @@ def test_analyze_kernel_substr_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_substr/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_substr/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -409,9 +564,14 @@ def test_analyze_kernel_substr_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_substr/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_substr/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -419,9 +579,14 @@ def test_analyze_dispatch_7_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_7/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_7/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -429,9 +594,14 @@ def test_analyze_dispatch_7_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_7/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_7/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 @@ -439,9 +609,14 @@ def test_analyze_dispatch_7_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_7/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_7/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -449,9 +624,14 @@ def test_analyze_dispatch_7_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_7/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_7/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 @@ -459,9 +639,14 @@ def test_analyze_kernel_inv_int_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_int/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_inv_int/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -469,9 +654,14 @@ def test_analyze_kernel_inv_int_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_int/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_inv_int/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 @@ -479,9 +669,14 @@ def test_analyze_kernel_inv_int_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_int/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_inv_int/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -489,9 +684,14 @@ def test_analyze_kernel_inv_int_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_int/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_inv_int/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 @@ -499,9 +699,14 @@ def test_analyze_mem_levels_vL1D_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/mem_levels_vL1D/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/mem_levels_vL1D/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -509,9 +714,14 @@ def test_analyze_sort_kernels_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/sort_kernels/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/sort_kernels/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -519,9 +729,14 @@ def test_analyze_kernel_inv_str_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_str/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_inv_str/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -529,9 +744,14 @@ def test_analyze_kernel_inv_str_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_str/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_inv_str/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 @@ -539,9 +759,14 @@ def test_analyze_kernel_inv_str_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_str/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_inv_str/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -549,9 +774,14 @@ def test_analyze_kernel_inv_str_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_str/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_inv_str/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 @@ -560,13 +790,13 @@ def test_analyze_ipblocks_SQ_SPI_MI300X_A1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_SPI/MI300X_A1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -574,9 +804,14 @@ def test_analyze_ipblocks_SQ_SPI_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_SPI/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ_SPI/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -585,13 +820,13 @@ def test_analyze_ipblocks_SQ_SPI_MI300A_A1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_SPI/MI300A_A1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -599,9 +834,14 @@ def test_analyze_ipblocks_SQ_SPI_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_SPI/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ_SPI/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -609,9 +849,14 @@ def test_analyze_dispatch_2_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_2/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_2/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -619,9 +864,14 @@ def test_analyze_dispatch_2_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_2/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_2/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -629,9 +879,14 @@ def test_analyze_dispatch_2_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_2/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_2/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -639,9 +894,14 @@ def test_analyze_dispatch_2_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_2/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_2/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -649,9 +909,14 @@ def test_analyze_dispatch_0_1_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0_1/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_0_1/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -659,9 +924,14 @@ def test_analyze_dispatch_0_1_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0_1/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_0_1/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -669,9 +939,14 @@ def test_analyze_dispatch_0_1_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0_1/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_0_1/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -679,9 +954,14 @@ def test_analyze_dispatch_0_1_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0_1/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_0_1/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -689,9 +969,14 @@ def test_analyze_mem_levels_LDS_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/mem_levels_LDS/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/mem_levels_LDS/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -699,9 +984,14 @@ def test_analyze_ipblocks_TA_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TA/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TA/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -709,9 +999,14 @@ def test_analyze_ipblocks_TA_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TA/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TA/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -719,9 +1014,14 @@ def test_analyze_ipblocks_TA_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TA/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TA/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -729,9 +1029,14 @@ def test_analyze_ipblocks_TA_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TA/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TA/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -739,9 +1044,14 @@ def test_analyze_dispatch_6_8_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_6_8/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_6_8/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -749,9 +1059,14 @@ def test_analyze_dispatch_6_8_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_6_8/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_6_8/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 @@ -759,9 +1074,14 @@ def test_analyze_dispatch_6_8_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_6_8/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_6_8/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -769,9 +1089,14 @@ def test_analyze_dispatch_6_8_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_6_8/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_6_8/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 1 @@ -779,9 +1104,14 @@ def test_analyze_device_inv_int_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/device_inv_int/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/device_inv_int/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -789,9 +1119,14 @@ def test_analyze_device_inv_int_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/device_inv_int/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/device_inv_int/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -799,9 +1134,14 @@ def test_analyze_device_inv_int_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/device_inv_int/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/device_inv_int/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -809,9 +1149,14 @@ def test_analyze_device_inv_int_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/device_inv_int/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/device_inv_int/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -819,9 +1164,14 @@ def test_analyze_ipblocks_SQ_TA_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_TA/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ_TA/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -829,9 +1179,14 @@ def test_analyze_ipblocks_SQ_TA_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_TA/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ_TA/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -839,9 +1194,14 @@ def test_analyze_ipblocks_SQ_TA_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_TA/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ_TA/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -849,9 +1209,14 @@ def test_analyze_ipblocks_SQ_TA_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_TA/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ_TA/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -859,9 +1224,14 @@ def test_analyze_ipblocks_TD_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TD/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TD/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -869,9 +1239,14 @@ def test_analyze_ipblocks_TD_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TD/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TD/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -879,9 +1254,14 @@ def test_analyze_ipblocks_TD_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TD/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TD/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -889,9 +1269,14 @@ def test_analyze_ipblocks_TD_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TD/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_TD/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -899,9 +1284,14 @@ def test_analyze_device_filter_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/device_filter/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/device_filter/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -909,9 +1299,14 @@ def test_analyze_device_filter_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/device_filter/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/device_filter/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -919,9 +1314,14 @@ def test_analyze_device_filter_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/device_filter/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/device_filter/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -929,9 +1329,14 @@ def test_analyze_device_filter_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/device_filter/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/device_filter/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -940,13 +1345,13 @@ def test_analyze_join_type_kernel_MI300X_A1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/join_type_kernel/MI300X_A1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -954,9 +1359,14 @@ def test_analyze_join_type_kernel_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/join_type_kernel/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/join_type_kernel/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -965,13 +1375,13 @@ def test_analyze_join_type_kernel_MI300A_A1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/join_type_kernel/MI300A_A1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -979,9 +1389,14 @@ def test_analyze_join_type_kernel_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/join_type_kernel/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/join_type_kernel/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -990,13 +1405,13 @@ def test_analyze_ipblocks_SQ_SQC_TCP_CPC_MI300X_A1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI300X_A1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1005,13 +1420,13 @@ def test_analyze_ipblocks_SQ_SQC_TCP_CPC_MI100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1020,13 +1435,13 @@ def test_analyze_ipblocks_SQ_SQC_TCP_CPC_MI300A_A1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI300A_A1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1035,13 +1450,13 @@ def test_analyze_ipblocks_SQ_SQC_TCP_CPC_MI200(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1050,13 +1465,13 @@ def test_analyze_mem_levels_L2_vL1d_LDS_MI200(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/mem_levels_L2_vL1d_LDS/MI200", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1064,9 +1479,14 @@ def test_analyze_ipblocks_CPF_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPF/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_CPF/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1074,9 +1494,14 @@ def test_analyze_ipblocks_CPF_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPF/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_CPF/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1084,9 +1509,14 @@ def test_analyze_ipblocks_CPF_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPF/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_CPF/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1094,9 +1524,14 @@ def test_analyze_ipblocks_CPF_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPF/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_CPF/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1104,9 +1539,14 @@ def test_analyze_sort_dispatches_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/sort_dispatches/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/sort_dispatches/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1114,9 +1554,14 @@ def test_analyze_kernel_names_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_names/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/kernel_names/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1125,13 +1570,13 @@ def test_analyze_mem_levels_vL1d_LDS_MI200(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/mem_levels_vL1d_LDS/MI200", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1139,9 +1584,14 @@ def test_analyze_ipblocks_SQ_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1149,9 +1599,14 @@ def test_analyze_ipblocks_SQ_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1159,9 +1614,14 @@ def test_analyze_ipblocks_SQ_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1169,9 +1629,14 @@ def test_analyze_ipblocks_SQ_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1179,9 +1644,14 @@ def test_analyze_mem_levels_L2_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/mem_levels_L2/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/mem_levels_L2/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1189,9 +1659,14 @@ def test_analyze_dispatch_inv_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_inv/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_inv/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1199,9 +1674,14 @@ def test_analyze_dispatch_inv_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_inv/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_inv/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1209,9 +1689,14 @@ def test_analyze_dispatch_inv_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_inv/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_inv/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1219,9 +1704,14 @@ def test_analyze_dispatch_inv_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_inv/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/dispatch_inv/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1229,18 +1719,19 @@ def test_analyze_path_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/path/MI300X_A1"], + ["rocprof-compute", "analyze", "--path", "tests/workloads/path/MI300X_A1"], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 def test_analyze_path_MI100(): with pytest.raises(SystemExit) as e: with patch( - "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/path/MI100"] + "sys.argv", + ["rocprof-compute", "analyze", "--path", "tests/workloads/path/MI100"], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1248,18 +1739,19 @@ def test_analyze_path_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/path/MI300A_A1"], + ["rocprof-compute", "analyze", "--path", "tests/workloads/path/MI300A_A1"], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 def test_analyze_path_MI200(): with pytest.raises(SystemExit) as e: with patch( - "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/path/MI200"] + "sys.argv", + ["rocprof-compute", "analyze", "--path", "tests/workloads/path/MI200"], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1267,9 +1759,14 @@ def test_analyze_ipblocks_CPC_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPC/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_CPC/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1277,9 +1774,14 @@ def test_analyze_ipblocks_CPC_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPC/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_CPC/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1287,9 +1789,14 @@ def test_analyze_ipblocks_CPC_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPC/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_CPC/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1297,9 +1804,14 @@ def test_analyze_ipblocks_CPC_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPC/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_CPC/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1308,13 +1820,13 @@ def test_analyze_ipblocks_SQ_SPI_TA_TCC_CPF_MI300X_A1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI300X_A1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1323,13 +1835,13 @@ def test_analyze_ipblocks_SQ_SPI_TA_TCC_CPF_MI100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1338,13 +1850,13 @@ def test_analyze_ipblocks_SQ_SPI_TA_TCC_CPF_MI300A_A1(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI300A_A1", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1353,13 +1865,13 @@ def test_analyze_ipblocks_SQ_SPI_TA_TCC_CPF_MI200(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "analyze", "--path", "tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200", ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1367,9 +1879,14 @@ def test_analyze_mem_levels_HBM_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/mem_levels_HBM/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/mem_levels_HBM/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1377,9 +1894,14 @@ def test_analyze_ipblocks_SPI_MI300X_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SPI/MI300X_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SPI/MI300X_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1387,9 +1909,14 @@ def test_analyze_ipblocks_SPI_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SPI/MI100"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SPI/MI100", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1397,9 +1924,14 @@ def test_analyze_ipblocks_SPI_MI300A_A1(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SPI/MI300A_A1"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SPI/MI300A_A1", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 @@ -1407,7 +1939,12 @@ def test_analyze_ipblocks_SPI_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SPI/MI200"], + [ + "rocprof-compute", + "analyze", + "--path", + "tests/workloads/ipblocks_SPI/MI200", + ], ): - omniperf.main() + rocprof_compute.main() assert e.value.code == 0 diff --git a/projects/rocprofiler-compute/tests/test_import_workloads.py b/projects/rocprofiler-compute/tests/test_import_workloads.py index 7b169f8a9d..32828071b7 100644 --- a/projects/rocprofiler-compute/tests/test_import_workloads.py +++ b/projects/rocprofiler-compute/tests/test_import_workloads.py @@ -2,7 +2,7 @@ import pytest from unittest.mock import patch from importlib.machinery import SourceFileLoader -omniperf = SourceFileLoader("omniperf", "src/omniperf").load_module() +rocprof_compute = SourceFileLoader("rocprof-compute", "src/rocprof-compute").load_module() ################################################## ## Generated tests ## @@ -13,7 +13,7 @@ def test_import_D_str_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -28,14 +28,14 @@ def test_import_D_str_inv1_mi100(): "tests/workloads/D_str_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_D_str_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -50,14 +50,14 @@ def test_D_str_inv1_mi100(): "tests/workloads/D_str_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_dev01p3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -72,14 +72,14 @@ def test_import_dev01p3_mi100(): "tests/workloads/dev01p3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_SQC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -94,14 +94,14 @@ def test_import_SQC_mi100(): "tests/workloads/SQC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_SQC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -116,14 +116,14 @@ def test_SQC_mi100(): "tests/workloads/SQC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_Axes2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -138,14 +138,14 @@ def test_import_Axes2_mi100(): "tests/workloads/Axes2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_Axes2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -160,14 +160,14 @@ def test_Axes2_mi100(): "tests/workloads/Axes2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_SQ_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -182,14 +182,14 @@ def test_import_no_roof_SQ_mi100(): "tests/workloads/no_roof_SQ/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_SQ_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -204,14 +204,14 @@ def test_no_roof_SQ_mi100(): "tests/workloads/no_roof_SQ/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_CPF_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -226,14 +226,14 @@ def test_import_CPF_mi100(): "tests/workloads/CPF/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_CPF_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -248,14 +248,14 @@ def test_CPF_mi100(): "tests/workloads/CPF/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_LDS_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -270,14 +270,14 @@ def test_import_no_roof_LDS_mi100(): "tests/workloads/no_roof_LDS/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_LDS_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -292,14 +292,14 @@ def test_no_roof_LDS_mi100(): "tests/workloads/no_roof_LDS/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_D_str_inv4_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -314,14 +314,14 @@ def test_import_D_str_inv4_mi100(): "tests/workloads/D_str_inv4/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_D_str_inv4_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -336,14 +336,14 @@ def test_D_str_inv4_mi100(): "tests/workloads/D_str_inv4/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_K_int_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -358,14 +358,14 @@ def test_roof_only_K_int_inv2_mi100(): "tests/workloads/roof_only_K_int_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_SPI_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -380,14 +380,14 @@ def test_import_no_roof_SPI_mi100(): "tests/workloads/no_roof_SPI/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_SPI_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -402,14 +402,14 @@ def test_no_roof_SPI_mi100(): "tests/workloads/no_roof_SPI/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_K_str_valid_2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -424,14 +424,14 @@ def test_import_no_roof_K_str_valid_2_mi100(): "tests/workloads/no_roof_K_str_valid_2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_K_str_valid_2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -446,14 +446,14 @@ def test_no_roof_K_str_valid_2_mi100(): "tests/workloads/no_roof_K_str_valid_2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_mixbench1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -468,14 +468,14 @@ def test_import_no_roof_mixbench1_mi100(): "tests/workloads/no_roof_mixbench1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_mixbench1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -490,14 +490,14 @@ def test_no_roof_mixbench1_mi100(): "tests/workloads/no_roof_mixbench1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_TA_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -512,14 +512,14 @@ def test_import_no_roof_TA_mi100(): "tests/workloads/no_roof_TA/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_TA_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -534,14 +534,14 @@ def test_no_roof_TA_mi100(): "tests/workloads/no_roof_TA/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_CPF_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -556,14 +556,14 @@ def test_import_no_roof_CPF_mi100(): "tests/workloads/no_roof_CPF/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_CPF_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -578,14 +578,14 @@ def test_no_roof_CPF_mi100(): "tests/workloads/no_roof_CPF/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_CPC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -600,14 +600,14 @@ def test_import_no_roof_CPC_mi100(): "tests/workloads/no_roof_CPC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_CPC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -622,14 +622,14 @@ def test_no_roof_CPC_mi100(): "tests/workloads/no_roof_CPC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_K_str_inv3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -644,14 +644,14 @@ def test_import_K_str_inv3_mi100(): "tests/workloads/K_str_inv3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_K_str_inv3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -666,14 +666,14 @@ def test_K_str_inv3_mi100(): "tests/workloads/K_str_inv3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_LDS_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -688,14 +688,14 @@ def test_import_LDS_mi100(): "tests/workloads/LDS/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_LDS_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -710,14 +710,14 @@ def test_LDS_mi100(): "tests/workloads/LDS/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_K_str_valid_3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -732,14 +732,14 @@ def test_import_no_roof_K_str_valid_3_mi100(): "tests/workloads/no_roof_K_str_valid_3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_D_int_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -754,14 +754,14 @@ def test_roof_only_D_int_inv2_mi100(): "tests/workloads/roof_only_D_int_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_K_str_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -776,14 +776,14 @@ def test_roof_only_K_str_inv1_mi100(): "tests/workloads/roof_only_K_str_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_SQC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -798,14 +798,14 @@ def test_roof_only_SQC_mi100(): "tests/workloads/roof_only_SQC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_Axes2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -820,14 +820,14 @@ def test_import_no_roof_Axes2_mi100(): "tests/workloads/no_roof_Axes2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_Axes2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -842,14 +842,14 @@ def test_no_roof_Axes2_mi100(): "tests/workloads/no_roof_Axes2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_HBM_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -864,14 +864,14 @@ def test_import_HBM_mi100(): "tests/workloads/HBM/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_HBM_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -886,14 +886,14 @@ def test_HBM_mi100(): "tests/workloads/HBM/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_TA_CPC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -908,14 +908,14 @@ def test_roof_only_TA_CPC_mi100(): "tests/workloads/roof_only_TA_CPC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_D_val_int_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -930,14 +930,14 @@ def test_roof_only_D_val_int_mi100(): "tests/workloads/roof_only_D_val_int/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_L2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -952,14 +952,14 @@ def test_import_no_roof_L2_mi100(): "tests/workloads/no_roof_L2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_L2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -974,14 +974,14 @@ def test_no_roof_L2_mi100(): "tests/workloads/no_roof_L2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_L2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -996,14 +996,14 @@ def test_import_L2_mi100(): "tests/workloads/L2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_L2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1018,14 +1018,14 @@ def test_L2_mi100(): "tests/workloads/L2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_dev1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1040,14 +1040,14 @@ def test_import_no_roof_dev1_mi100(): "tests/workloads/no_roof_dev1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_dev1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1062,14 +1062,14 @@ def test_no_roof_dev1_mi100(): "tests/workloads/no_roof_dev1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_K_str_inv3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1084,14 +1084,14 @@ def test_roof_only_K_str_inv3_mi100(): "tests/workloads/roof_only_K_str_inv3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_K_str_valid_1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1106,14 +1106,14 @@ def test_roof_only_K_str_valid_1_mi100(): "tests/workloads/roof_only_K_str_valid_1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_CPC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1128,14 +1128,14 @@ def test_roof_only_CPC_mi100(): "tests/workloads/roof_only_CPC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_Axes3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1150,14 +1150,14 @@ def test_import_no_roof_Axes3_mi100(): "tests/workloads/no_roof_Axes3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_Axes3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1172,14 +1172,14 @@ def test_no_roof_Axes3_mi100(): "tests/workloads/no_roof_Axes3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_D_str_inv3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1194,14 +1194,14 @@ def test_import_no_roof_D_str_inv3_mi100(): "tests/workloads/no_roof_D_str_inv3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_D_str_inv3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1216,14 +1216,14 @@ def test_no_roof_D_str_inv3_mi100(): "tests/workloads/no_roof_D_str_inv3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_D_int_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1238,14 +1238,14 @@ def test_import_no_roof_D_int_inv2_mi100(): "tests/workloads/no_roof_D_int_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_D_int_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1260,14 +1260,14 @@ def test_no_roof_D_int_inv2_mi100(): "tests/workloads/no_roof_D_int_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_TD_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1282,14 +1282,14 @@ def test_import_TD_mi100(): "tests/workloads/TD/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_TD_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1304,14 +1304,14 @@ def test_TD_mi100(): "tests/workloads/TD/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_D_int_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1326,14 +1326,14 @@ def test_roof_only_D_int_inv1_mi100(): "tests/workloads/roof_only_D_int_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_D_val_int2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1348,14 +1348,14 @@ def test_import_D_val_int2_mi100(): "tests/workloads/D_val_int2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_D_val_int2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1370,14 +1370,14 @@ def test_D_val_int2_mi100(): "tests/workloads/D_val_int2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_mixbench2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1392,14 +1392,14 @@ def test_import_no_roof_mixbench2_mi100(): "tests/workloads/no_roof_mixbench2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_mixbench2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1414,14 +1414,14 @@ def test_no_roof_mixbench2_mi100(): "tests/workloads/no_roof_mixbench2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_SPI_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1436,14 +1436,14 @@ def test_roof_only_SPI_mi100(): "tests/workloads/roof_only_SPI/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_D_val_int2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1458,14 +1458,14 @@ def test_import_no_roof_D_val_int2_mi100(): "tests/workloads/no_roof_D_val_int2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_D_val_int2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1480,14 +1480,14 @@ def test_no_roof_D_val_int2_mi100(): "tests/workloads/no_roof_D_val_int2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_K_str_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1502,14 +1502,14 @@ def test_import_K_str_inv1_mi100(): "tests/workloads/K_str_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_K_str_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1524,14 +1524,14 @@ def test_K_str_inv1_mi100(): "tests/workloads/K_str_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_TA_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1546,14 +1546,14 @@ def test_roof_only_TA_mi100(): "tests/workloads/roof_only_TA/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_K_str_valid_3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1568,14 +1568,14 @@ def test_import_K_str_valid_3_mi100(): "tests/workloads/K_str_valid_3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_SQ_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1590,14 +1590,14 @@ def test_import_SQ_mi100(): "tests/workloads/SQ/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_SQ_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1612,14 +1612,14 @@ def test_SQ_mi100(): "tests/workloads/SQ/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_D_str_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1634,14 +1634,14 @@ def test_import_no_roof_D_str_inv1_mi100(): "tests/workloads/no_roof_D_str_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_D_str_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1656,14 +1656,14 @@ def test_no_roof_D_str_inv1_mi100(): "tests/workloads/no_roof_D_str_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_dev01p3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1678,14 +1678,14 @@ def test_import_no_roof_dev01p3_mi100(): "tests/workloads/no_roof_dev01p3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_D_val_int2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1700,14 +1700,14 @@ def test_roof_only_D_val_int2_mi100(): "tests/workloads/roof_only_D_val_int2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_D_str_inv4_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1722,14 +1722,14 @@ def test_import_no_roof_D_str_inv4_mi100(): "tests/workloads/no_roof_D_str_inv4/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_D_str_inv4_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1744,14 +1744,14 @@ def test_no_roof_D_str_inv4_mi100(): "tests/workloads/no_roof_D_str_inv4/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_CPF_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1766,14 +1766,14 @@ def test_roof_only_CPF_mi100(): "tests/workloads/roof_only_CPF/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_mixbench_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1788,14 +1788,14 @@ def test_import_mixbench_mi100(): "tests/workloads/mixbench/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_mixbench_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1810,14 +1810,14 @@ def test_mixbench_mi100(): "tests/workloads/mixbench/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_D_str_inv4_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1832,14 +1832,14 @@ def test_roof_only_D_str_inv4_mi100(): "tests/workloads/roof_only_D_str_inv4/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_kernels_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1854,14 +1854,14 @@ def test_import_no_roof_kernels_mi100(): "tests/workloads/no_roof_kernels/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_kernels_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1876,14 +1876,14 @@ def test_no_roof_kernels_mi100(): "tests/workloads/no_roof_kernels/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_TCC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1898,14 +1898,14 @@ def test_roof_only_TCC_mi100(): "tests/workloads/roof_only_TCC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_TA_CPC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1920,14 +1920,14 @@ def test_import_TA_CPC_mi100(): "tests/workloads/TA_CPC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_TA_CPC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1942,14 +1942,14 @@ def test_TA_CPC_mi100(): "tests/workloads/TA_CPC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_SQ_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1964,14 +1964,14 @@ def test_roof_only_SQ_mi100(): "tests/workloads/roof_only_SQ/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_K_int_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -1986,14 +1986,14 @@ def test_import_K_int_inv2_mi100(): "tests/workloads/K_int_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_K_int_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2008,14 +2008,14 @@ def test_K_int_inv2_mi100(): "tests/workloads/K_int_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_TCP_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2030,14 +2030,14 @@ def test_roof_only_TCP_mi100(): "tests/workloads/roof_only_TCP/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_K_str_valid_2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2052,14 +2052,14 @@ def test_roof_only_K_str_valid_2_mi100(): "tests/workloads/roof_only_K_str_valid_2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_D_int_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2074,14 +2074,14 @@ def test_import_D_int_inv2_mi100(): "tests/workloads/D_int_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_D_int_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2096,14 +2096,14 @@ def test_D_int_inv2_mi100(): "tests/workloads/D_int_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_Axes3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2118,14 +2118,14 @@ def test_roof_only_Axes3_mi100(): "tests/workloads/roof_only_Axes3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_dev0_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2140,14 +2140,14 @@ def test_import_dev0_mi100(): "tests/workloads/dev0/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_dev0_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2162,14 +2162,14 @@ def test_dev0_mi100(): "tests/workloads/dev0/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_K_str_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2184,14 +2184,14 @@ def test_roof_only_K_str_inv2_mi100(): "tests/workloads/roof_only_K_str_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_Axes1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2206,14 +2206,14 @@ def test_import_Axes1_mi100(): "tests/workloads/Axes1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_Axes1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2228,14 +2228,14 @@ def test_Axes1_mi100(): "tests/workloads/Axes1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_HBM_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2250,14 +2250,14 @@ def test_roof_only_HBM_mi100(): "tests/workloads/roof_only_HBM/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_D_val_int_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2272,14 +2272,14 @@ def test_import_D_val_int_mi100(): "tests/workloads/D_val_int/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_D_val_int_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2294,14 +2294,14 @@ def test_D_val_int_mi100(): "tests/workloads/D_val_int/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_TCC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2316,14 +2316,14 @@ def test_import_no_roof_TCC_mi100(): "tests/workloads/no_roof_TCC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_TCC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2338,14 +2338,14 @@ def test_no_roof_TCC_mi100(): "tests/workloads/no_roof_TCC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_SQC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2360,14 +2360,14 @@ def test_import_no_roof_SQC_mi100(): "tests/workloads/no_roof_SQC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_SQC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2382,14 +2382,14 @@ def test_no_roof_SQC_mi100(): "tests/workloads/no_roof_SQC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_TD_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2404,14 +2404,14 @@ def test_roof_only_TD_mi100(): "tests/workloads/roof_only_TD/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_K_int_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2426,14 +2426,14 @@ def test_import_no_roof_K_int_inv1_mi100(): "tests/workloads/no_roof_K_int_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_K_int_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2448,14 +2448,14 @@ def test_no_roof_K_int_inv1_mi100(): "tests/workloads/no_roof_K_int_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_Axes1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2470,14 +2470,14 @@ def test_import_no_roof_Axes1_mi100(): "tests/workloads/no_roof_Axes1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_Axes1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2492,14 +2492,14 @@ def test_no_roof_Axes1_mi100(): "tests/workloads/no_roof_Axes1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_SPI_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2514,14 +2514,14 @@ def test_import_SPI_mi100(): "tests/workloads/SPI/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_SPI_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2536,14 +2536,14 @@ def test_SPI_mi100(): "tests/workloads/SPI/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_D_str_inv3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2558,14 +2558,14 @@ def test_roof_only_D_str_inv3_mi100(): "tests/workloads/roof_only_D_str_inv3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_D_val_int_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2580,14 +2580,14 @@ def test_import_no_roof_D_val_int_mi100(): "tests/workloads/no_roof_D_val_int/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_D_val_int_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2602,14 +2602,14 @@ def test_no_roof_D_val_int_mi100(): "tests/workloads/no_roof_D_val_int/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_K_str_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2624,14 +2624,14 @@ def test_import_K_str_inv2_mi100(): "tests/workloads/K_str_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_K_str_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2646,14 +2646,14 @@ def test_K_str_inv2_mi100(): "tests/workloads/K_str_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_CPC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2668,14 +2668,14 @@ def test_import_CPC_mi100(): "tests/workloads/CPC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_CPC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2690,14 +2690,14 @@ def test_CPC_mi100(): "tests/workloads/CPC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_dispatches_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2712,14 +2712,14 @@ def test_roof_only_dispatches_mi100(): "tests/workloads/roof_only_dispatches/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_mixbench2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2734,14 +2734,14 @@ def test_roof_only_mixbench2_mi100(): "tests/workloads/roof_only_mixbench2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_Axes4_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2756,14 +2756,14 @@ def test_import_Axes4_mi100(): "tests/workloads/Axes4/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_Axes4_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2778,14 +2778,14 @@ def test_Axes4_mi100(): "tests/workloads/Axes4/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_TCP_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2800,14 +2800,14 @@ def test_import_no_roof_TCP_mi100(): "tests/workloads/no_roof_TCP/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_TCP_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2822,14 +2822,14 @@ def test_no_roof_TCP_mi100(): "tests/workloads/no_roof_TCP/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_LDS_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2844,14 +2844,14 @@ def test_roof_only_LDS_mi100(): "tests/workloads/roof_only_LDS/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_invdev_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2866,14 +2866,14 @@ def test_import_invdev_mi100(): "tests/workloads/invdev/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_invdev_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2888,14 +2888,14 @@ def test_invdev_mi100(): "tests/workloads/invdev/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_dev0_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2910,14 +2910,14 @@ def test_import_no_roof_dev0_mi100(): "tests/workloads/no_roof_dev0/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_dev0_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2932,14 +2932,14 @@ def test_no_roof_dev0_mi100(): "tests/workloads/no_roof_dev0/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_Axes1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2954,14 +2954,14 @@ def test_roof_only_Axes1_mi100(): "tests/workloads/roof_only_Axes1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_invdev_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2976,14 +2976,14 @@ def test_roof_only_invdev_mi100(): "tests/workloads/roof_only_invdev/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_D_str_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -2998,14 +2998,14 @@ def test_roof_only_D_str_inv2_mi100(): "tests/workloads/roof_only_D_str_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_K_str_inv3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3020,14 +3020,14 @@ def test_import_no_roof_K_str_inv3_mi100(): "tests/workloads/no_roof_K_str_inv3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_K_str_inv3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3042,14 +3042,14 @@ def test_no_roof_K_str_inv3_mi100(): "tests/workloads/no_roof_K_str_inv3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_K_str_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3064,14 +3064,14 @@ def test_import_no_roof_K_str_inv2_mi100(): "tests/workloads/no_roof_K_str_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_K_str_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3086,14 +3086,14 @@ def test_no_roof_K_str_inv2_mi100(): "tests/workloads/no_roof_K_str_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_D_str_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3108,14 +3108,14 @@ def test_import_D_str_inv2_mi100(): "tests/workloads/D_str_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_D_str_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3130,14 +3130,14 @@ def test_D_str_inv2_mi100(): "tests/workloads/D_str_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_kernels_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3152,14 +3152,14 @@ def test_import_kernels_mi100(): "tests/workloads/kernels/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_kernels_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3174,14 +3174,14 @@ def test_kernels_mi100(): "tests/workloads/kernels/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_Axes4_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3196,14 +3196,14 @@ def test_import_no_roof_Axes4_mi100(): "tests/workloads/no_roof_Axes4/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_Axes4_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3218,14 +3218,14 @@ def test_no_roof_Axes4_mi100(): "tests/workloads/no_roof_Axes4/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_CMD_INV_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3240,14 +3240,14 @@ def test_import_CMD_INV_mi100(): "tests/workloads/CMD_INV/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_K_int_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3262,14 +3262,14 @@ def test_import_K_int_inv1_mi100(): "tests/workloads/K_int_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_K_int_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3284,14 +3284,14 @@ def test_K_int_inv1_mi100(): "tests/workloads/K_int_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_mixbench2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3306,14 +3306,14 @@ def test_import_mixbench2_mi100(): "tests/workloads/mixbench2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_mixbench2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3328,14 +3328,14 @@ def test_mixbench2_mi100(): "tests/workloads/mixbench2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_Double_N_flag_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3350,14 +3350,14 @@ def test_roof_only_Double_N_flag_mi100(): "tests/workloads/roof_only_Double_N_flag/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_TD_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3372,14 +3372,14 @@ def test_import_no_roof_TD_mi100(): "tests/workloads/no_roof_TD/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_TD_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3394,14 +3394,14 @@ def test_no_roof_TD_mi100(): "tests/workloads/no_roof_TD/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_TCC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3416,14 +3416,14 @@ def test_import_TCC_mi100(): "tests/workloads/TCC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_TCC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3438,14 +3438,14 @@ def test_TCC_mi100(): "tests/workloads/TCC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_dev0_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3460,14 +3460,14 @@ def test_roof_only_dev0_mi100(): "tests/workloads/roof_only_dev0/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_D_str_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3482,14 +3482,14 @@ def test_import_no_roof_D_str_inv2_mi100(): "tests/workloads/no_roof_D_str_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_D_str_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3504,14 +3504,14 @@ def test_no_roof_D_str_inv2_mi100(): "tests/workloads/no_roof_D_str_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_L2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3526,14 +3526,14 @@ def test_roof_only_L2_mi100(): "tests/workloads/roof_only_L2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_TA_CPC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3548,14 +3548,14 @@ def test_import_no_roof_TA_CPC_mi100(): "tests/workloads/no_roof_TA_CPC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_TA_CPC_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3570,14 +3570,14 @@ def test_no_roof_TA_CPC_mi100(): "tests/workloads/no_roof_TA_CPC/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_Double_N_flag_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3592,14 +3592,14 @@ def test_import_no_roof_Double_N_flag_mi100(): "tests/workloads/no_roof_Double_N_flag/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_Double_N_flag_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3614,14 +3614,14 @@ def test_no_roof_Double_N_flag_mi100(): "tests/workloads/no_roof_Double_N_flag/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_Double_N_flag_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3636,14 +3636,14 @@ def test_import_Double_N_flag_mi100(): "tests/workloads/Double_N_flag/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_Double_N_flag_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3658,14 +3658,14 @@ def test_Double_N_flag_mi100(): "tests/workloads/Double_N_flag/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_K_int_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3680,14 +3680,14 @@ def test_roof_only_K_int_inv1_mi100(): "tests/workloads/roof_only_K_int_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_K_str_valid_1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3702,14 +3702,14 @@ def test_import_no_roof_K_str_valid_1_mi100(): "tests/workloads/no_roof_K_str_valid_1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_K_str_valid_1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3724,14 +3724,14 @@ def test_no_roof_K_str_valid_1_mi100(): "tests/workloads/no_roof_K_str_valid_1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_mixbench1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3746,14 +3746,14 @@ def test_roof_only_mixbench1_mi100(): "tests/workloads/roof_only_mixbench1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_dev1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3768,14 +3768,14 @@ def test_import_dev1_mi100(): "tests/workloads/dev1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_dev1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3790,14 +3790,14 @@ def test_dev1_mi100(): "tests/workloads/dev1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_K_str_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3812,14 +3812,14 @@ def test_import_no_roof_K_str_inv1_mi100(): "tests/workloads/no_roof_K_str_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_K_str_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3834,14 +3834,14 @@ def test_no_roof_K_str_inv1_mi100(): "tests/workloads/no_roof_K_str_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_K_str_valid_1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3856,14 +3856,14 @@ def test_import_K_str_valid_1_mi100(): "tests/workloads/K_str_valid_1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_K_str_valid_1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3878,14 +3878,14 @@ def test_K_str_valid_1_mi100(): "tests/workloads/K_str_valid_1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_mixbench1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3900,14 +3900,14 @@ def test_import_mixbench1_mi100(): "tests/workloads/mixbench1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_mixbench1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3922,14 +3922,14 @@ def test_mixbench1_mi100(): "tests/workloads/mixbench1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_CMD_INV_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3944,14 +3944,14 @@ def test_import_no_roof_CMD_INV_mi100(): "tests/workloads/no_roof_CMD_INV/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_D_str_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3966,14 +3966,14 @@ def test_roof_only_D_str_inv1_mi100(): "tests/workloads/roof_only_D_str_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_HBM_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -3988,14 +3988,14 @@ def test_import_no_roof_HBM_mi100(): "tests/workloads/no_roof_HBM/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_HBM_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4010,14 +4010,14 @@ def test_no_roof_HBM_mi100(): "tests/workloads/no_roof_HBM/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_kernels_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4032,14 +4032,14 @@ def test_roof_only_kernels_mi100(): "tests/workloads/roof_only_kernels/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_D_int_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4054,14 +4054,14 @@ def test_import_D_int_inv1_mi100(): "tests/workloads/D_int_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_D_int_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4076,14 +4076,14 @@ def test_D_int_inv1_mi100(): "tests/workloads/D_int_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_K_str_valid_2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4098,14 +4098,14 @@ def test_import_K_str_valid_2_mi100(): "tests/workloads/K_str_valid_2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_K_str_valid_2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4120,14 +4120,14 @@ def test_K_str_valid_2_mi100(): "tests/workloads/K_str_valid_2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_TCP_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4142,14 +4142,14 @@ def test_import_TCP_mi100(): "tests/workloads/TCP/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_TCP_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4164,14 +4164,14 @@ def test_TCP_mi100(): "tests/workloads/TCP/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_Axes3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4186,14 +4186,14 @@ def test_import_Axes3_mi100(): "tests/workloads/Axes3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_Axes3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4208,14 +4208,14 @@ def test_Axes3_mi100(): "tests/workloads/Axes3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_invdev_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4230,14 +4230,14 @@ def test_import_no_roof_invdev_mi100(): "tests/workloads/no_roof_invdev/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_invdev_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4252,14 +4252,14 @@ def test_no_roof_invdev_mi100(): "tests/workloads/no_roof_invdev/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_dispatches_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4274,14 +4274,14 @@ def test_import_no_roof_dispatches_mi100(): "tests/workloads/no_roof_dispatches/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_dispatches_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4296,14 +4296,14 @@ def test_no_roof_dispatches_mi100(): "tests/workloads/no_roof_dispatches/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_D_str_inv3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4318,14 +4318,14 @@ def test_import_D_str_inv3_mi100(): "tests/workloads/D_str_inv3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_D_str_inv3_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4340,14 +4340,14 @@ def test_D_str_inv3_mi100(): "tests/workloads/D_str_inv3/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_TA_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4362,14 +4362,14 @@ def test_import_TA_mi100(): "tests/workloads/TA/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_TA_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4384,14 +4384,14 @@ def test_TA_mi100(): "tests/workloads/TA/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_D_int_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4406,14 +4406,14 @@ def test_import_no_roof_D_int_inv1_mi100(): "tests/workloads/no_roof_D_int_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_D_int_inv1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4428,14 +4428,14 @@ def test_no_roof_D_int_inv1_mi100(): "tests/workloads/no_roof_D_int_inv1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_dispatches_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4450,14 +4450,14 @@ def test_import_dispatches_mi100(): "tests/workloads/dispatches/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_dispatches_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4472,14 +4472,14 @@ def test_dispatches_mi100(): "tests/workloads/dispatches/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_roof_only_dev1_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4494,14 +4494,14 @@ def test_roof_only_dev1_mi100(): "tests/workloads/roof_only_dev1/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_import_no_roof_K_int_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4516,14 +4516,14 @@ def test_import_no_roof_K_int_inv2_mi100(): "tests/workloads/no_roof_K_int_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() def test_no_roof_K_int_inv2_mi100(): with patch( "sys.argv", [ - "omniperf", + "rocprof-compute", "database", "--import", "-H", @@ -4538,4 +4538,4 @@ def test_no_roof_K_int_inv2_mi100(): "tests/workloads/no_roof_K_int_inv2/mi100", ], ): - omniperf.main() + rocprof_compute.main() diff --git a/projects/rocprofiler-compute/tests/test_profile_general.py b/projects/rocprofiler-compute/tests/test_profile_general.py index 28b1e07b3c..d6da91c0c1 100644 --- a/projects/rocprofiler-compute/tests/test_profile_general.py +++ b/projects/rocprofiler-compute/tests/test_profile_general.py @@ -24,8 +24,8 @@ SUPPORTED_ARCHS = { def check_arch_override(): - if "OMNIPERF_ARCH_OVERRIDE" in os.environ.keys(): - return os.environ["OMNIPERF_ARCH_OVERRIDE"] + if "ROCPROFCOMPUTE_ARCH_OVERRIDE" in os.environ.keys(): + return os.environ["ROCPROFCOMPUTE_ARCH_OVERRIDE"] return "" @@ -34,7 +34,9 @@ def check_arch_override(): # -- config = {} -config["omniperf"] = SourceFileLoader("omniperf", "src/omniperf").load_module() +config["rocprofiler-compute"] = SourceFileLoader( + "rocprofiler-compute", "src/rocprof-compute" +).load_module() config["kernel_name_1"] = "vecCopy(double*, double*, double*, int, int) [clone .kd]" config["app_1"] = ["./tests/vcopy", "-n", "1048576", "-b", "256", "-i", "3"] config["cleanup"] = True @@ -42,7 +44,7 @@ config["COUNTER_LOGGING"] = False config["METRIC_COMPARE"] = False config["METRIC_LOGGING"] = False -baseline_opts = ["omniperf", "profile", "-n", "app_1", "-VVV"] +baseline_opts = ["rocprof-compute", "profile", "-n", "app_1", "-VVV"] num_kernels = 3 num_devices = 1 @@ -312,7 +314,7 @@ def gpu_soc(): else: print( "Cannot parse MI300 details from rocminfo. Please verify output or set the arch using (e.g.,) " - 'export OMNIPERF_ARCH_OVERRIDE="MI300A"' + 'export ROCPROFCOMPUTE_ARCH_OVERRIDE="MI300A"' ) assert 0 return gpu_model @@ -364,7 +366,7 @@ def baseline_compare_metric(test_name, workload_dir, args=[]): t = subprocess.Popen( [ sys.executable, - "src/omniperf", + "src/rocprof_compute", "analyze", "--path", Baseline_dir, @@ -503,7 +505,7 @@ def validate(test_name, workload_dir, file_dict, args=[]): def test_path(): options = baseline_opts workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) @@ -526,7 +528,7 @@ def test_path(): def test_no_roof(): options = baseline_opts + ["--no-roof"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) if soc == "MI100": @@ -554,7 +556,9 @@ def test_no_roof(): def test_kernel_names(): options = baseline_opts + ["--roof-only", "--kernel-names"] workload_dir = test_utils.get_output_dir() - e = test_utils.launch_omniperf(config, options, workload_dir, check_success=False) + e = test_utils.launch_rocprof_compute( + config, options, workload_dir, check_success=False + ) if soc == "MI100" or "MI300" in soc: # assert that it did not run @@ -589,7 +593,7 @@ def test_device_filter(): options = baseline_opts + ["--device", device_id] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, 1, num_kernels) if soc == "MI100": @@ -617,7 +621,7 @@ def test_device_filter(): def test_kernel(): options = baseline_opts + ["--kernel", config["kernel_name_1"]] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) if soc == "MI100": @@ -643,7 +647,7 @@ def test_kernel(): def test_block_SQ(): options = baseline_opts + ["--block", "SQ"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -719,7 +723,7 @@ def test_block_SQ(): def test_block_SQC(): options = baseline_opts + ["--block", "SQC"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -749,7 +753,7 @@ def test_block_SQC(): def test_block_TA(): options = baseline_opts + ["--block", "TA"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -783,7 +787,7 @@ def test_block_TA(): def test_block_TD(): options = baseline_opts + ["--block", "TD"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -831,7 +835,7 @@ def test_block_TD(): def test_block_TCP(): options = baseline_opts + ["--block", "TCP"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -867,7 +871,7 @@ def test_block_TCP(): def test_block_TCC(): options = baseline_opts + ["--block", "TCC"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -933,7 +937,7 @@ def test_block_TCC(): def test_block_SPI(): options = baseline_opts + ["--block", "SPI"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -968,7 +972,7 @@ def test_block_SPI(): def test_block_CPC(): options = baseline_opts + ["--block", "CPC"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -996,7 +1000,7 @@ def test_block_CPC(): def test_block_CPF(): options = baseline_opts + ["--block", "CPF"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -1026,7 +1030,7 @@ def test_block_CPF(): def test_block_SQ_CPC(): options = baseline_opts + ["--block", "SQ", "CPC"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -1102,7 +1106,7 @@ def test_block_SQ_CPC(): def test_block_SQ_TA(): options = baseline_opts + ["--block", "SQ", "TA"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -1174,7 +1178,7 @@ def test_block_SQ_TA(): def test_block_SQ_SPI(): options = baseline_opts + ["--block", "SQ", "SPI"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -1249,7 +1253,7 @@ def test_block_SQ_SPI(): def test_block_SQ_SQC_TCP_CPC(): options = baseline_opts + ["--block", "SQ", "SQC", "TCP", "CPC"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -1321,7 +1325,7 @@ def test_block_SQ_SQC_TCP_CPC(): def test_block_SQ_SPI_TA_TCC_CPF(): options = baseline_opts + ["--block", "SQ", "SPI", "TA", "TCC", "CPF"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) expected_csvs = [ @@ -1397,7 +1401,7 @@ def test_block_SQ_SPI_TA_TCC_CPF(): def test_dispatch_0(): options = baseline_opts + ["--dispatch", "0"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, 1) if soc == "MI100": @@ -1427,7 +1431,7 @@ def test_dispatch_0(): def test_dispatch_0_1(): options = baseline_opts + ["--dispatch", "0:2"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, 2) if soc == "MI100": @@ -1454,7 +1458,7 @@ def test_dispatch_0_1(): def test_dispatch_2(): options = baseline_opts + ["--dispatch", dispatch_id] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, 1) if soc == "MI100": @@ -1484,7 +1488,7 @@ def test_dispatch_2(): def test_join_type_grid(): options = baseline_opts + ["--join-type", "grid"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) if soc == "MI100": @@ -1510,7 +1514,7 @@ def test_join_type_grid(): def test_join_type_kernel(): options = baseline_opts + ["--join-type", "kernel"] workload_dir = test_utils.get_output_dir() - test_utils.launch_omniperf(config, options, workload_dir) + test_utils.launch_rocprof_compute(config, options, workload_dir) file_dict = test_utils.check_csv_files(workload_dir, num_devices, num_kernels) @@ -1537,7 +1541,9 @@ def test_join_type_kernel(): def test_sort_dispatches(): options = baseline_opts + ["--roof-only", "--sort", "dispatches"] workload_dir = test_utils.get_output_dir() - e = test_utils.launch_omniperf(config, options, workload_dir, check_success=False) + e = test_utils.launch_rocprof_compute( + config, options, workload_dir, check_success=False + ) if soc == "MI100" or "MI300" in soc: # assert that it did not run @@ -1568,7 +1574,9 @@ def test_sort_dispatches(): def test_sort_kernels(): options = baseline_opts + ["--roof-only", "--sort", "kernels"] workload_dir = test_utils.get_output_dir() - e = test_utils.launch_omniperf(config, options, workload_dir, check_success=False) + e = test_utils.launch_rocprof_compute( + config, options, workload_dir, check_success=False + ) if soc == "MI100" or "MI300" in soc: # assert that it did not run @@ -1598,7 +1606,9 @@ def test_sort_kernels(): def test_mem_levels_HBM(): options = baseline_opts + ["--roof-only", "--mem-level", "HBM"] workload_dir = test_utils.get_output_dir() - e = test_utils.launch_omniperf(config, options, workload_dir, check_success=False) + e = test_utils.launch_rocprof_compute( + config, options, workload_dir, check_success=False + ) if soc == "MI100" or "MI300" in soc: # assert that it did not run @@ -1628,7 +1638,9 @@ def test_mem_levels_HBM(): def test_mem_levels_L2(): options = baseline_opts + ["--roof-only", "--mem-level", "L2"] workload_dir = test_utils.get_output_dir() - e = test_utils.launch_omniperf(config, options, workload_dir, check_success=False) + e = test_utils.launch_rocprof_compute( + config, options, workload_dir, check_success=False + ) if soc == "MI100" or "MI300" in soc: # assert that it did not run @@ -1658,7 +1670,9 @@ def test_mem_levels_L2(): def test_mem_levels_vL1D(): options = baseline_opts + ["--roof-only", "--mem-level", "vL1D"] workload_dir = test_utils.get_output_dir() - e = test_utils.launch_omniperf(config, options, workload_dir, check_success=False) + e = test_utils.launch_rocprof_compute( + config, options, workload_dir, check_success=False + ) if soc == "MI100" or "MI300" in soc: # assert that it did not run @@ -1688,7 +1702,9 @@ def test_mem_levels_vL1D(): def test_mem_levels_LDS(): options = baseline_opts + ["--roof-only", "--mem-level", "LDS"] workload_dir = test_utils.get_output_dir() - e = test_utils.launch_omniperf(config, options, workload_dir, check_success=False) + e = test_utils.launch_rocprof_compute( + config, options, workload_dir, check_success=False + ) if soc == "MI100" or "MI300" in soc: # assert that it did not run @@ -1718,7 +1734,9 @@ def test_mem_levels_LDS(): def test_mem_levels_HBM_LDS(): options = baseline_opts + ["--roof-only", "--mem-level", "HBM", "LDS"] workload_dir = test_utils.get_output_dir() - e = test_utils.launch_omniperf(config, options, workload_dir, check_success=False) + e = test_utils.launch_rocprof_compute( + config, options, workload_dir, check_success=False + ) if soc == "MI100" or "MI300" in soc: # assert that it did not run @@ -1748,7 +1766,9 @@ def test_mem_levels_HBM_LDS(): def test_mem_levels_vL1D_LDS(): options = baseline_opts + ["--roof-only", "--mem-level", "vL1D", "LDS"] workload_dir = test_utils.get_output_dir() - e = test_utils.launch_omniperf(config, options, workload_dir, check_success=False) + e = test_utils.launch_rocprof_compute( + config, options, workload_dir, check_success=False + ) if soc == "MI100" or "MI300" in soc: # assert that it did not run @@ -1778,7 +1798,9 @@ def test_mem_levels_vL1D_LDS(): def test_mem_levels_L2_vL1D_LDS(): options = baseline_opts + ["--roof-only", "--mem-level", "L2", "vL1D", "LDS"] workload_dir = test_utils.get_output_dir() - e = test_utils.launch_omniperf(config, options, workload_dir, check_success=False) + e = test_utils.launch_rocprof_compute( + config, options, workload_dir, check_success=False + ) if soc == "MI100" or "MI300" in soc: # assert that it did not run diff --git a/projects/rocprofiler-compute/tests/test_utils.py b/projects/rocprofiler-compute/tests/test_utils.py index 6ee8bac42c..3d8ccc2474 100644 --- a/projects/rocprofiler-compute/tests/test_utils.py +++ b/projects/rocprofiler-compute/tests/test_utils.py @@ -142,7 +142,7 @@ def launch_omniperf(config, options, workload_dir, check_success=True): with patch( "sys.argv", options + ["--path", workload_dir, "--"] + config["app_1"] ): - config["omniperf"].main() + config["rocprofiler-compute"].main() # verify run status if check_success: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_IFETCH_LEVEL.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index cb500c7561..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,8 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TCC_CYCLE[0],TCC_RW_REQ[0],TCC_HIT[0],TCC_MISS[0],TCC_CYCLE[1],TCC_RW_REQ[1],TCC_HIT[1],TCC_MISS[1],TCC_CYCLE[2],TCC_RW_REQ[2],TCC_HIT[2],TCC_MISS[2],TCC_CYCLE[3],TCC_RW_REQ[3],TCC_HIT[3],TCC_MISS[3],TCC_CYCLE[4],TCC_RW_REQ[4],TCC_HIT[4],TCC_MISS[4],TCC_CYCLE[5],TCC_RW_REQ[5],TCC_HIT[5],TCC_MISS[5],TCC_CYCLE[6],TCC_RW_REQ[6],TCC_HIT[6],TCC_MISS[6],TCC_CYCLE[7],TCC_RW_REQ[7],TCC_HIT[7],TCC_MISS[7],TCC_CYCLE[8],TCC_RW_REQ[8],TCC_HIT[8],TCC_MISS[8],TCC_CYCLE[9],TCC_RW_REQ[9],TCC_HIT[9],TCC_MISS[9],TCC_CYCLE[10],TCC_RW_REQ[10],TCC_HIT[10],TCC_MISS[10],TCC_CYCLE[11],TCC_RW_REQ[11],TCC_HIT[11],TCC_MISS[11],TCC_CYCLE[12],TCC_RW_REQ[12],TCC_HIT[12],TCC_MISS[12],TCC_CYCLE[13],TCC_RW_REQ[13],TCC_HIT[13],TCC_MISS[13],TCC_CYCLE[14],TCC_RW_REQ[14],TCC_HIT[14],TCC_MISS[14],TCC_CYCLE[15],TCC_RW_REQ[15],TCC_HIT[15],TCC_MISS[15],TCC_CYCLE[16],TCC_RW_REQ[16],TCC_HIT[16],TCC_MISS[16],TCC_CYCLE[17],TCC_RW_REQ[17],TCC_HIT[17],TCC_MISS[17],TCC_CYCLE[18],TCC_RW_REQ[18],TCC_HIT[18],TCC_MISS[18],TCC_CYCLE[19],TCC_RW_REQ[19],TCC_HIT[19],TCC_MISS[19],TCC_CYCLE[20],TCC_RW_REQ[20],TCC_HIT[20],TCC_MISS[20],TCC_CYCLE[21],TCC_RW_REQ[21],TCC_HIT[21],TCC_MISS[21],TCC_CYCLE[22],TCC_RW_REQ[22],TCC_HIT[22],TCC_MISS[22],TCC_CYCLE[23],TCC_RW_REQ[23],TCC_HIT[23],TCC_MISS[23],TCC_CYCLE[24],TCC_RW_REQ[24],TCC_HIT[24],TCC_MISS[24],TCC_CYCLE[25],TCC_RW_REQ[25],TCC_HIT[25],TCC_MISS[25],TCC_CYCLE[26],TCC_RW_REQ[26],TCC_HIT[26],TCC_MISS[26],TCC_CYCLE[27],TCC_RW_REQ[27],TCC_HIT[27],TCC_MISS[27],TCC_CYCLE[28],TCC_RW_REQ[28],TCC_HIT[28],TCC_MISS[28],TCC_CYCLE[29],TCC_RW_REQ[29],TCC_HIT[29],TCC_MISS[29],TCC_CYCLE[30],TCC_RW_REQ[30],TCC_HIT[30],TCC_MISS[30],TCC_CYCLE[31],TCC_RW_REQ[31],TCC_HIT[31],TCC_MISS[31],CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,GRBM_COUNT,GRBM_GUI_ACTIVE,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789017,789017,256,256,0,0,12,4,32,64,0x0,0x7fc39b83d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,15492,15492,9586176074970,9595697581667,9595697588067,9586194080958 -1,"global_write(int*, int) [clone .kd]",2,0,1,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b805200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,14214,14214,9586194431757,9595697981345,9595697983585,9586195534149 -2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789017,789017,1,1,4096,0,4,4,48,64,0x0,0x7fc39b805240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16792,16792,9586194965600,9595697989025,9595697991265,9586196424752 -3,"global_read(int*, int) [clone .kd]",2,0,3,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b805280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,17066,17066,9586195545500,9595698033025,9595698035745,9586197503640 -4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b8052c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16835,16835,9586196089011,9595698039905,9595698042305,9586198594409 -5,"global_atomic(int*, int) [clone .kd]",2,0,5,789017,789017,1,1,0,0,4,4,16,64,0x0,0x7fc39b805300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16490,16490,9586196678469,9595698072385,9595698076225,9586199643230 -6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789017,789017,1,1,4096,0,4,4,48,64,0x0,0x7fc39b805340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,17235,17235,9586197190792,9595698076225,9595698080065,9586200731796 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_LDS.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index 1a975cb385..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,8 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TCC_REQ[0],TCC_READ[0],TCC_WRITE[0],TCC_ATOMIC[0],TCC_REQ[1],TCC_READ[1],TCC_WRITE[1],TCC_ATOMIC[1],TCC_REQ[2],TCC_READ[2],TCC_WRITE[2],TCC_ATOMIC[2],TCC_REQ[3],TCC_READ[3],TCC_WRITE[3],TCC_ATOMIC[3],TCC_REQ[4],TCC_READ[4],TCC_WRITE[4],TCC_ATOMIC[4],TCC_REQ[5],TCC_READ[5],TCC_WRITE[5],TCC_ATOMIC[5],TCC_REQ[6],TCC_READ[6],TCC_WRITE[6],TCC_ATOMIC[6],TCC_REQ[7],TCC_READ[7],TCC_WRITE[7],TCC_ATOMIC[7],TCC_REQ[8],TCC_READ[8],TCC_WRITE[8],TCC_ATOMIC[8],TCC_REQ[9],TCC_READ[9],TCC_WRITE[9],TCC_ATOMIC[9],TCC_REQ[10],TCC_READ[10],TCC_WRITE[10],TCC_ATOMIC[10],TCC_REQ[11],TCC_READ[11],TCC_WRITE[11],TCC_ATOMIC[11],TCC_REQ[12],TCC_READ[12],TCC_WRITE[12],TCC_ATOMIC[12],TCC_REQ[13],TCC_READ[13],TCC_WRITE[13],TCC_ATOMIC[13],TCC_REQ[14],TCC_READ[14],TCC_WRITE[14],TCC_ATOMIC[14],TCC_REQ[15],TCC_READ[15],TCC_WRITE[15],TCC_ATOMIC[15],TCC_REQ[16],TCC_READ[16],TCC_WRITE[16],TCC_ATOMIC[16],TCC_REQ[17],TCC_READ[17],TCC_WRITE[17],TCC_ATOMIC[17],TCC_REQ[18],TCC_READ[18],TCC_WRITE[18],TCC_ATOMIC[18],TCC_REQ[19],TCC_READ[19],TCC_WRITE[19],TCC_ATOMIC[19],TCC_REQ[20],TCC_READ[20],TCC_WRITE[20],TCC_ATOMIC[20],TCC_REQ[21],TCC_READ[21],TCC_WRITE[21],TCC_ATOMIC[21],TCC_REQ[22],TCC_READ[22],TCC_WRITE[22],TCC_ATOMIC[22],TCC_REQ[23],TCC_READ[23],TCC_WRITE[23],TCC_ATOMIC[23],TCC_REQ[24],TCC_READ[24],TCC_WRITE[24],TCC_ATOMIC[24],TCC_REQ[25],TCC_READ[25],TCC_WRITE[25],TCC_ATOMIC[25],TCC_REQ[26],TCC_READ[26],TCC_WRITE[26],TCC_ATOMIC[26],TCC_REQ[27],TCC_READ[27],TCC_WRITE[27],TCC_ATOMIC[27],TCC_REQ[28],TCC_READ[28],TCC_WRITE[28],TCC_ATOMIC[28],TCC_REQ[29],TCC_READ[29],TCC_WRITE[29],TCC_ATOMIC[29],TCC_REQ[30],TCC_READ[30],TCC_WRITE[30],TCC_ATOMIC[30],TCC_REQ[31],TCC_READ[31],TCC_WRITE[31],TCC_ATOMIC[31],CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,GRBM_SPI_BUSY,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789206,789206,256,256,0,0,12,4,32,64,0x0,0x7f092c135800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,7832,9586813518158,9595697581667,9595697588067,9586831878942 -1,"global_write(int*, int) [clone .kd]",2,0,1,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f9200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,4807,9586832277231,9595697981345,9595697983585,9586833234169 -2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789206,789206,1,1,4096,0,4,4,48,64,0x0,0x7f092c0f9240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6147,9586832819029,9595697989025,9595697991265,9586834206386 -3,"global_read(int*, int) [clone .kd]",2,0,3,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f9280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6439,9586833482506,9595698033025,9595698035745,9586835298047 -4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f92c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6821,9586834006330,9595698039905,9595698042305,9586836377766 -5,"global_atomic(int*, int) [clone .kd]",2,0,5,789206,789206,1,1,0,0,4,4,16,64,0x0,0x7f092c0f9300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6708,9586834769875,9595698072385,9595698076225,9586837446956 -6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789206,789206,1,1,4096,0,4,4,48,64,0x0,0x7f092c0f9340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,7838,9586835336510,9595698076225,9595698080065,9586838514602 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_SMEM.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index 8eae1c5875..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,8 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789393,789393,256,256,0,0,12,4,32,64,0x0,0x7f96ea49d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587521927328,9595697581667,9595697588067,9587540188696 -1,"global_write(int*, int) [clone .kd]",2,0,1,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea465200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587540565083,9595697981345,9595697983585,9587541639562 -2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789393,789393,1,1,4096,0,4,4,48,64,0x0,0x7f96ea465240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587541115507,9595697989025,9595697991265,9587542609585 -3,"global_read(int*, int) [clone .kd]",2,0,3,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea465280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587541696489,9595698033025,9595698035745,9587543620214 -4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea4652c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587542237877,9595698039905,9595698042305,9587544716895 -5,"global_atomic(int*, int) [clone .kd]",2,0,5,789393,789393,1,1,0,0,4,4,16,64,0x0,0x7f96ea465300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587542873531,9595698072385,9595698076225,9587545756779 -6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789393,789393,1,1,4096,0,4,4,48,64,0x0,0x7f96ea465340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,9587543404819,9595698076225,9595698080065,9587546843111 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_VMEM.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index c4c4af793c..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,8 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCC_EA_ATOMIC[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_ATOMIC_LEVEL[0],TCC_EA_ATOMIC[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_ATOMIC_LEVEL[1],TCC_EA_ATOMIC[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_ATOMIC_LEVEL[2],TCC_EA_ATOMIC[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_ATOMIC_LEVEL[3],TCC_EA_ATOMIC[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_ATOMIC_LEVEL[4],TCC_EA_ATOMIC[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_ATOMIC_LEVEL[5],TCC_EA_ATOMIC[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_ATOMIC_LEVEL[6],TCC_EA_ATOMIC[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_ATOMIC_LEVEL[7],TCC_EA_ATOMIC[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_ATOMIC_LEVEL[8],TCC_EA_ATOMIC[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_ATOMIC_LEVEL[9],TCC_EA_ATOMIC[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_ATOMIC_LEVEL[10],TCC_EA_ATOMIC[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_ATOMIC_LEVEL[11],TCC_EA_ATOMIC[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_ATOMIC_LEVEL[12],TCC_EA_ATOMIC[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_ATOMIC_LEVEL[13],TCC_EA_ATOMIC[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_ATOMIC_LEVEL[14],TCC_EA_ATOMIC[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_ATOMIC_LEVEL[15],TCC_EA_ATOMIC[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_ATOMIC_LEVEL[16],TCC_EA_ATOMIC[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_ATOMIC_LEVEL[17],TCC_EA_ATOMIC[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_ATOMIC_LEVEL[18],TCC_EA_ATOMIC[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_ATOMIC_LEVEL[19],TCC_EA_ATOMIC[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_ATOMIC_LEVEL[20],TCC_EA_ATOMIC[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_ATOMIC_LEVEL[21],TCC_EA_ATOMIC[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_ATOMIC_LEVEL[22],TCC_EA_ATOMIC[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_ATOMIC_LEVEL[23],TCC_EA_ATOMIC[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_ATOMIC_LEVEL[24],TCC_EA_ATOMIC[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_ATOMIC_LEVEL[25],TCC_EA_ATOMIC[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_ATOMIC_LEVEL[26],TCC_EA_ATOMIC[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_ATOMIC_LEVEL[27],TCC_EA_ATOMIC[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_ATOMIC_LEVEL[28],TCC_EA_ATOMIC[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_ATOMIC_LEVEL[29],TCC_EA_ATOMIC[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_ATOMIC_LEVEL[30],TCC_EA_ATOMIC[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ_LEVEL[31],TCC_EA_ATOMIC_LEVEL[31],CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789581,789581,256,256,0,0,12,4,32,64,0x0,0x7fa983c4d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588165999404,9595697581667,9595697588067,9588184873222 -1,"global_write(int*, int) [clone .kd]",2,0,1,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c15200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588185231295,9595697981345,9595697983585,9588186170961 -2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789581,789581,1,1,4096,0,4,4,48,64,0x0,0x7fa983c15240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588185747445,9595697989025,9595697991265,9588187051836 -3,"global_read(int*, int) [clone .kd]",2,0,3,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c15280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588186416192,9595698033025,9595698035745,9588187966405 -4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c152c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588186956707,9595698039905,9595698042305,9588188690015 -5,"global_atomic(int*, int) [clone .kd]",2,0,5,789581,789581,1,1,0,0,4,4,16,64,0x0,0x7fa983c15300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588187589306,9595698072385,9595698076225,9588189838613 -6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789581,789581,1,1,4096,0,4,4,48,64,0x0,0x7fa983c15340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9588188228397,9595698076225,9595698080065,9588190792135 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_LEVEL_WAVES.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_LEVEL_WAVES.csv deleted file mode 100644 index ba72ca8515..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,8 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],CPC_ME1_BUSY_FOR_PACKET_DECODE,CPC_CPC_UTCL2IU_STALL,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,GRBM_COUNT,GRBM_GUI_ACTIVE,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,__amd_rocclr_fillBufferAligned.kd,2,0,0,789767,789767,256,256,0,0,12,4,32,64,0x0,0x7f0b7a335800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,15256,15256,9588800635588,9595697581667,9595697588067,9588818795995 -1,"global_write(int*, int) [clone .kd]",2,0,1,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a319200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,14215,14215,9588819151083,9595697981345,9595697983585,9588820066433 -2,"generic_write(int*, int, int) [clone .kd]",2,0,2,789767,789767,1,1,4096,0,4,4,48,64,0x0,0x7f0b7a319240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,16303,16303,9588819631105,9595697989025,9595697991265,9588820711946 -3,"global_read(int*, int) [clone .kd]",2,0,3,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a319280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17633,17633,9588820290945,9595698033025,9595698035745,9588821548468 -4,"generic_read(int*, int, int) [clone .kd]",2,0,4,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a3192c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,16725,16725,9588820914807,9595698039905,9595698042305,9588822390240 -5,"global_atomic(int*, int) [clone .kd]",2,0,5,789767,789767,1,1,0,0,4,4,16,64,0x0,0x7f0b7a319300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17452,17452,9588821374712,9595698072385,9595698076225,9588823186356 -6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,789767,789767,1,1,4096,0,4,4,48,64,0x0,0x7f0b7a319340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17418,17418,9588822047877,9595698076225,9595698080065,9588824015775 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/log.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/log.txt deleted file mode 100644 index 2b99bd0b4e..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/log.txt +++ /dev/null @@ -1,270 +0,0 @@ -Omniperf version: 2.1.0 -Profiler choice: rocprofv1 -Path: /home/zichguan/omniperf_test/omniperf/tests/workloads/multikernel/MI210 -Target: MI200 -Command: ./sample/vmem -Kernel Selection: None -Dispatch Selection: None -Hardware Blocks: All - -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Collecting Performance Counters -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_IFETCH_LEVEL.txt - |-> [rocprof] RPL: on '241022_154555' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_IFETCH_LEVEL.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154555_788857' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154555_788857/input0_results_241022_154555' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154555_788857/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 152 metrics - |-> [rocprof] SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES, SQ_BUSY_CU_CYCLES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TCC_CYCLE[0], TCC_RW_REQ[0], TCC_HIT[0], TCC_MISS[0], TCC_CYCLE[1], TCC_RW_REQ[1], TCC_HIT[1], TCC_MISS[1], TCC_CYCLE[2], TCC_RW_REQ[2], TCC_HIT[2], TCC_MISS[2], TCC_CYCLE[3], TCC_RW_REQ[3], TCC_HIT[3], TCC_MISS[3], TCC_CYCLE[4], TCC_RW_REQ[4], TCC_HIT[4], TCC_MISS[4], TCC_CYCLE[5], TCC_RW_REQ[5], TCC_HIT[5], TCC_MISS[5], TCC_CYCLE[6], TCC_RW_REQ[6], TCC_HIT[6], TCC_MISS[6], TCC_CYCLE[7], TCC_RW_REQ[7], TCC_HIT[7], TCC_MISS[7], TCC_CYCLE[8], TCC_RW_REQ[8], TCC_HIT[8], TCC_MISS[8], TCC_CYCLE[9], TCC_RW_REQ[9], TCC_HIT[9], TCC_MISS[9], TCC_CYCLE[10], TCC_RW_REQ[10], TCC_HIT[10], TCC_MISS[10], TCC_CYCLE[11], TCC_RW_REQ[11], TCC_HIT[11], TCC_MISS[11], TCC_CYCLE[12], TCC_RW_REQ[12], TCC_HIT[12], TCC_MISS[12], TCC_CYCLE[13], TCC_RW_REQ[13], TCC_HIT[13], TCC_MISS[13], TCC_CYCLE[14], TCC_RW_REQ[14], TCC_HIT[14], TCC_MISS[14], TCC_CYCLE[15], TCC_RW_REQ[15], TCC_HIT[15], TCC_MISS[15], TCC_CYCLE[16], TCC_RW_REQ[16], TCC_HIT[16], TCC_MISS[16], TCC_CYCLE[17], TCC_RW_REQ[17], TCC_HIT[17], TCC_MISS[17], TCC_CYCLE[18], TCC_RW_REQ[18], TCC_HIT[18], TCC_MISS[18], TCC_CYCLE[19], TCC_RW_REQ[19], TCC_HIT[19], TCC_MISS[19], TCC_CYCLE[20], TCC_RW_REQ[20], TCC_HIT[20], TCC_MISS[20], TCC_CYCLE[21], TCC_RW_REQ[21], TCC_HIT[21], TCC_MISS[21], TCC_CYCLE[22], TCC_RW_REQ[22], TCC_HIT[22], TCC_MISS[22], TCC_CYCLE[23], TCC_RW_REQ[23], TCC_HIT[23], TCC_MISS[23], TCC_CYCLE[24], TCC_RW_REQ[24], TCC_HIT[24], TCC_MISS[24], TCC_CYCLE[25], TCC_RW_REQ[25], TCC_HIT[25], TCC_MISS[25], TCC_CYCLE[26], TCC_RW_REQ[26], TCC_HIT[26], TCC_MISS[26], TCC_CYCLE[27], TCC_RW_REQ[27], TCC_HIT[27], TCC_MISS[27], TCC_CYCLE[28], TCC_RW_REQ[28], TCC_HIT[28], TCC_MISS[28], TCC_CYCLE[29], TCC_RW_REQ[29], TCC_HIT[29], TCC_MISS[29], TCC_CYCLE[30], TCC_RW_REQ[30], TCC_HIT[30], TCC_MISS[30], TCC_CYCLE[31], TCC_RW_REQ[31], TCC_HIT[31], TCC_MISS[31], CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, GRBM_COUNT, GRBM_GUI_ACTIVE - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154555_788857/input0_results_241022_154555 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_IFETCH_LEVEL.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_LDS.txt - |-> [rocprof] RPL: on '241022_154556' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_LDS.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154556_789045' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154556_789045/input0_results_241022_154556' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154556_789045/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 151 metrics - |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TCC_REQ[0], TCC_READ[0], TCC_WRITE[0], TCC_ATOMIC[0], TCC_REQ[1], TCC_READ[1], TCC_WRITE[1], TCC_ATOMIC[1], TCC_REQ[2], TCC_READ[2], TCC_WRITE[2], TCC_ATOMIC[2], TCC_REQ[3], TCC_READ[3], TCC_WRITE[3], TCC_ATOMIC[3], TCC_REQ[4], TCC_READ[4], TCC_WRITE[4], TCC_ATOMIC[4], TCC_REQ[5], TCC_READ[5], TCC_WRITE[5], TCC_ATOMIC[5], TCC_REQ[6], TCC_READ[6], TCC_WRITE[6], TCC_ATOMIC[6], TCC_REQ[7], TCC_READ[7], TCC_WRITE[7], TCC_ATOMIC[7], TCC_REQ[8], TCC_READ[8], TCC_WRITE[8], TCC_ATOMIC[8], TCC_REQ[9], TCC_READ[9], TCC_WRITE[9], TCC_ATOMIC[9], TCC_REQ[10], TCC_READ[10], TCC_WRITE[10], TCC_ATOMIC[10], TCC_REQ[11], TCC_READ[11], TCC_WRITE[11], TCC_ATOMIC[11], TCC_REQ[12], TCC_READ[12], TCC_WRITE[12], TCC_ATOMIC[12], TCC_REQ[13], TCC_READ[13], TCC_WRITE[13], TCC_ATOMIC[13], TCC_REQ[14], TCC_READ[14], TCC_WRITE[14], TCC_ATOMIC[14], TCC_REQ[15], TCC_READ[15], TCC_WRITE[15], TCC_ATOMIC[15], TCC_REQ[16], TCC_READ[16], TCC_WRITE[16], TCC_ATOMIC[16], TCC_REQ[17], TCC_READ[17], TCC_WRITE[17], TCC_ATOMIC[17], TCC_REQ[18], TCC_READ[18], TCC_WRITE[18], TCC_ATOMIC[18], TCC_REQ[19], TCC_READ[19], TCC_WRITE[19], TCC_ATOMIC[19], TCC_REQ[20], TCC_READ[20], TCC_WRITE[20], TCC_ATOMIC[20], TCC_REQ[21], TCC_READ[21], TCC_WRITE[21], TCC_ATOMIC[21], TCC_REQ[22], TCC_READ[22], TCC_WRITE[22], TCC_ATOMIC[22], TCC_REQ[23], TCC_READ[23], TCC_WRITE[23], TCC_ATOMIC[23], TCC_REQ[24], TCC_READ[24], TCC_WRITE[24], TCC_ATOMIC[24], TCC_REQ[25], TCC_READ[25], TCC_WRITE[25], TCC_ATOMIC[25], TCC_REQ[26], TCC_READ[26], TCC_WRITE[26], TCC_ATOMIC[26], TCC_REQ[27], TCC_READ[27], TCC_WRITE[27], TCC_ATOMIC[27], TCC_REQ[28], TCC_READ[28], TCC_WRITE[28], TCC_ATOMIC[28], TCC_REQ[29], TCC_READ[29], TCC_WRITE[29], TCC_ATOMIC[29], TCC_REQ[30], TCC_READ[30], TCC_WRITE[30], TCC_ATOMIC[30], TCC_REQ[31], TCC_READ[31], TCC_WRITE[31], TCC_ATOMIC[31], CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, GRBM_SPI_BUSY - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154556_789045/input0_results_241022_154556 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_INST_LEVEL_LDS.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_SMEM.txt - |-> [rocprof] RPL: on '241022_154556' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_SMEM.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154556_789233' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154556_789233/input0_results_241022_154556' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154556_789233/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 150 metrics - |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31], CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154556_789233/input0_results_241022_154556 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_INST_LEVEL_SMEM.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_VMEM.txt - |-> [rocprof] RPL: on '241022_154557' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_INST_LEVEL_VMEM.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154557_789421' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154557_789421/input0_results_241022_154557' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154557_789421/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 148 metrics - |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCC_EA_ATOMIC[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_ATOMIC_LEVEL[0], TCC_EA_ATOMIC[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_ATOMIC_LEVEL[1], TCC_EA_ATOMIC[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_ATOMIC_LEVEL[2], TCC_EA_ATOMIC[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_ATOMIC_LEVEL[3], TCC_EA_ATOMIC[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_ATOMIC_LEVEL[4], TCC_EA_ATOMIC[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_ATOMIC_LEVEL[5], TCC_EA_ATOMIC[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_ATOMIC_LEVEL[6], TCC_EA_ATOMIC[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_ATOMIC_LEVEL[7], TCC_EA_ATOMIC[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_ATOMIC_LEVEL[8], TCC_EA_ATOMIC[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_ATOMIC_LEVEL[9], TCC_EA_ATOMIC[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_ATOMIC_LEVEL[10], TCC_EA_ATOMIC[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_ATOMIC_LEVEL[11], TCC_EA_ATOMIC[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_ATOMIC_LEVEL[12], TCC_EA_ATOMIC[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_ATOMIC_LEVEL[13], TCC_EA_ATOMIC[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_ATOMIC_LEVEL[14], TCC_EA_ATOMIC[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_ATOMIC_LEVEL[15], TCC_EA_ATOMIC[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_ATOMIC_LEVEL[16], TCC_EA_ATOMIC[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_ATOMIC_LEVEL[17], TCC_EA_ATOMIC[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_ATOMIC_LEVEL[18], TCC_EA_ATOMIC[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_ATOMIC_LEVEL[19], TCC_EA_ATOMIC[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_ATOMIC_LEVEL[20], TCC_EA_ATOMIC[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_ATOMIC_LEVEL[21], TCC_EA_ATOMIC[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_ATOMIC_LEVEL[22], TCC_EA_ATOMIC[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_ATOMIC_LEVEL[23], TCC_EA_ATOMIC[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_ATOMIC_LEVEL[24], TCC_EA_ATOMIC[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_ATOMIC_LEVEL[25], TCC_EA_ATOMIC[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_ATOMIC_LEVEL[26], TCC_EA_ATOMIC[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_ATOMIC_LEVEL[27], TCC_EA_ATOMIC[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_ATOMIC_LEVEL[28], TCC_EA_ATOMIC[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_ATOMIC_LEVEL[29], TCC_EA_ATOMIC[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_ATOMIC_LEVEL[30], TCC_EA_ATOMIC[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ_LEVEL[31], TCC_EA_ATOMIC_LEVEL[31], CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154557_789421/input0_results_241022_154557 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_INST_LEVEL_VMEM.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/SQ_LEVEL_WAVES.txt - |-> [rocprof] RPL: on '241022_154558' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/SQ_LEVEL_WAVES.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154558_789607' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154558_789607/input0_results_241022_154558' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154558_789607/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 148 metrics - |-> [rocprof] SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], CPC_ME1_BUSY_FOR_PACKET_DECODE, CPC_CPC_UTCL2IU_STALL, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, GRBM_COUNT, GRBM_GUI_ACTIVE - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154558_789607/input0_results_241022_154558 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/SQ_LEVEL_WAVES.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_0.txt - |-> [rocprof] RPL: on '241022_154558' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_0.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154558_789792' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154558_789792/input0_results_241022_154558' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154558_789792/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 114 metrics - |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_FLAT, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_CYCLE_sum, CPC_ME1_DC0_SPI_BUSY, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154558_789792/input0_results_241022_154558 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_0.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_1.txt - |-> [rocprof] RPL: on '241022_154559' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_1.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154559_789978' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154559_789978/input0_results_241022_154559' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154559_789978/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 20 metrics - |-> [rocprof] SQ_ACTIVE_INST_ANY, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum, TCC_NC_REQ_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154559_789978/input0_results_241022_154559 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_1.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_2.txt - |-> [rocprof] RPL: on '241022_154600' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_2.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154600_790176' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154600_790176/input0_results_241022_154600' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154600_790176/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 20 metrics - |-> [rocprof] SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum, TCC_REQ_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154600_790176/input0_results_241022_154600 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_2.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_3.txt - |-> [rocprof] RPL: on '241022_154600' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_3.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154600_790361' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154600_790361/input0_results_241022_154600' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154600_790361/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 18 metrics - |-> [rocprof] SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum, TCC_READ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154600_790361/input0_results_241022_154600 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_3.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_4.txt - |-> [rocprof] RPL: on '241022_154601' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_4.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154601_790548' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154601_790548/input0_results_241022_154601' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154601_790548/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 16 metrics - |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum, TCC_EA_WRREQ_sum - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154601_790548/input0_results_241022_154601 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_4.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_5.txt - |-> [rocprof] RPL: on '241022_154602' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_5.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154602_790732' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154602_790732/input0_results_241022_154602' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154602_790732/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 12 metrics - |-> [rocprof] SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum, TCC_EA_WRREQ_STALL_sum - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154602_790732/input0_results_241022_154602 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_5.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_6.txt - |-> [rocprof] RPL: on '241022_154602' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_6.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154602_790917' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154602_790917/input0_results_241022_154602' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154602_790917/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 12 metrics - |-> [rocprof] SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154602_790917/input0_results_241022_154602 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_6.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_7.txt - |-> [rocprof] RPL: on '241022_154603' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_7.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154603_791101' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154603_791101/input0_results_241022_154603' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154603_791101/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 12 metrics - |-> [rocprof] SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154603_791101/input0_results_241022_154603 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_7.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_8.txt - |-> [rocprof] RPL: on '241022_154603' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_8.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154603_791285' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154603_791285/input0_results_241022_154603' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154603_791285/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 10 metrics - |-> [rocprof] SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154603_791285/input0_results_241022_154603 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_8.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/pmc_perf_9.txt - |-> [rocprof] RPL: on '241022_154604' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/pmc_perf_9.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154604_791469' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154604_791469/input0_results_241022_154604' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154604_791469/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 2 metrics - |-> [rocprof] TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154604_791469/input0_results_241022_154604 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/pmc_perf_9.csv' is generating - |-> [rocprof] -[profiling] Current input file: tests/workloads/multikernel/MI210/perfmon/timestamps.txt - |-> [rocprof] RPL: on '241022_154605' from '/opt/rocm-6.2.1' in '/home/zichguan/omniperf_test/omniperf' - |-> [rocprof] RPL: profiling '""./sample/vmem""' - |-> [rocprof] RPL: input file 'tests/workloads/multikernel/MI210/perfmon/timestamps.txt' - |-> [rocprof] RPL: output dir '/tmp/rpl_data_241022_154605_791667' - |-> [rocprof] RPL: result dir '/tmp/rpl_data_241022_154605_791667/input0_results_241022_154605' - |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_241022_154605_791667/input0.xml" - |-> [rocprof] gpu_index = - |-> [rocprof] kernel = - |-> [rocprof] range = - |-> [rocprof] 0 metrics - |-> [rocprof] - |-> [rocprof] ROCPRofiler: 7 contexts collected, output directory /tmp/rpl_data_241022_154605_791667/input0_results_241022_154605 - |-> [rocprof] File 'tests/workloads/multikernel/MI210/timestamps.csv' is generating - |-> [rocprof] -[roofline] Checking for roofline.csv in tests/workloads/multikernel/MI210 -[roofline] No roofline data found. Generating... diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index bde9fa9462..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES SQ_BUSY_CU_CYCLES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TCC_CYCLE[0] TCC_RW_REQ[0] TCC_HIT[0] TCC_MISS[0] TCC_CYCLE[1] TCC_RW_REQ[1] TCC_HIT[1] TCC_MISS[1] TCC_CYCLE[2] TCC_RW_REQ[2] TCC_HIT[2] TCC_MISS[2] TCC_CYCLE[3] TCC_RW_REQ[3] TCC_HIT[3] TCC_MISS[3] TCC_CYCLE[4] TCC_RW_REQ[4] TCC_HIT[4] TCC_MISS[4] TCC_CYCLE[5] TCC_RW_REQ[5] TCC_HIT[5] TCC_MISS[5] TCC_CYCLE[6] TCC_RW_REQ[6] TCC_HIT[6] TCC_MISS[6] TCC_CYCLE[7] TCC_RW_REQ[7] TCC_HIT[7] TCC_MISS[7] TCC_CYCLE[8] TCC_RW_REQ[8] TCC_HIT[8] TCC_MISS[8] TCC_CYCLE[9] TCC_RW_REQ[9] TCC_HIT[9] TCC_MISS[9] TCC_CYCLE[10] TCC_RW_REQ[10] TCC_HIT[10] TCC_MISS[10] TCC_CYCLE[11] TCC_RW_REQ[11] TCC_HIT[11] TCC_MISS[11] TCC_CYCLE[12] TCC_RW_REQ[12] TCC_HIT[12] TCC_MISS[12] TCC_CYCLE[13] TCC_RW_REQ[13] TCC_HIT[13] TCC_MISS[13] TCC_CYCLE[14] TCC_RW_REQ[14] TCC_HIT[14] TCC_MISS[14] TCC_CYCLE[15] TCC_RW_REQ[15] TCC_HIT[15] TCC_MISS[15] TCC_CYCLE[16] TCC_RW_REQ[16] TCC_HIT[16] TCC_MISS[16] TCC_CYCLE[17] TCC_RW_REQ[17] TCC_HIT[17] TCC_MISS[17] TCC_CYCLE[18] TCC_RW_REQ[18] TCC_HIT[18] TCC_MISS[18] TCC_CYCLE[19] TCC_RW_REQ[19] TCC_HIT[19] TCC_MISS[19] TCC_CYCLE[20] TCC_RW_REQ[20] TCC_HIT[20] TCC_MISS[20] TCC_CYCLE[21] TCC_RW_REQ[21] TCC_HIT[21] TCC_MISS[21] TCC_CYCLE[22] TCC_RW_REQ[22] TCC_HIT[22] TCC_MISS[22] TCC_CYCLE[23] TCC_RW_REQ[23] TCC_HIT[23] TCC_MISS[23] TCC_CYCLE[24] TCC_RW_REQ[24] TCC_HIT[24] TCC_MISS[24] TCC_CYCLE[25] TCC_RW_REQ[25] TCC_HIT[25] TCC_MISS[25] TCC_CYCLE[26] TCC_RW_REQ[26] TCC_HIT[26] TCC_MISS[26] TCC_CYCLE[27] TCC_RW_REQ[27] TCC_HIT[27] TCC_MISS[27] TCC_CYCLE[28] TCC_RW_REQ[28] TCC_HIT[28] TCC_MISS[28] TCC_CYCLE[29] TCC_RW_REQ[29] TCC_HIT[29] TCC_MISS[29] TCC_CYCLE[30] TCC_RW_REQ[30] TCC_HIT[30] TCC_MISS[30] TCC_CYCLE[31] TCC_RW_REQ[31] TCC_HIT[31] TCC_MISS[31] CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL SPI_CSN_WINDOW_VALID SPI_CSN_BUSY GRBM_COUNT GRBM_GUI_ACTIVE - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 487719a26f..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TCC_REQ[0] TCC_READ[0] TCC_WRITE[0] TCC_ATOMIC[0] TCC_REQ[1] TCC_READ[1] TCC_WRITE[1] TCC_ATOMIC[1] TCC_REQ[2] TCC_READ[2] TCC_WRITE[2] TCC_ATOMIC[2] TCC_REQ[3] TCC_READ[3] TCC_WRITE[3] TCC_ATOMIC[3] TCC_REQ[4] TCC_READ[4] TCC_WRITE[4] TCC_ATOMIC[4] TCC_REQ[5] TCC_READ[5] TCC_WRITE[5] TCC_ATOMIC[5] TCC_REQ[6] TCC_READ[6] TCC_WRITE[6] TCC_ATOMIC[6] TCC_REQ[7] TCC_READ[7] TCC_WRITE[7] TCC_ATOMIC[7] TCC_REQ[8] TCC_READ[8] TCC_WRITE[8] TCC_ATOMIC[8] TCC_REQ[9] TCC_READ[9] TCC_WRITE[9] TCC_ATOMIC[9] TCC_REQ[10] TCC_READ[10] TCC_WRITE[10] TCC_ATOMIC[10] TCC_REQ[11] TCC_READ[11] TCC_WRITE[11] TCC_ATOMIC[11] TCC_REQ[12] TCC_READ[12] TCC_WRITE[12] TCC_ATOMIC[12] TCC_REQ[13] TCC_READ[13] TCC_WRITE[13] TCC_ATOMIC[13] TCC_REQ[14] TCC_READ[14] TCC_WRITE[14] TCC_ATOMIC[14] TCC_REQ[15] TCC_READ[15] TCC_WRITE[15] TCC_ATOMIC[15] TCC_REQ[16] TCC_READ[16] TCC_WRITE[16] TCC_ATOMIC[16] TCC_REQ[17] TCC_READ[17] TCC_WRITE[17] TCC_ATOMIC[17] TCC_REQ[18] TCC_READ[18] TCC_WRITE[18] TCC_ATOMIC[18] TCC_REQ[19] TCC_READ[19] TCC_WRITE[19] TCC_ATOMIC[19] TCC_REQ[20] TCC_READ[20] TCC_WRITE[20] TCC_ATOMIC[20] TCC_REQ[21] TCC_READ[21] TCC_WRITE[21] TCC_ATOMIC[21] TCC_REQ[22] TCC_READ[22] TCC_WRITE[22] TCC_ATOMIC[22] TCC_REQ[23] TCC_READ[23] TCC_WRITE[23] TCC_ATOMIC[23] TCC_REQ[24] TCC_READ[24] TCC_WRITE[24] TCC_ATOMIC[24] TCC_REQ[25] TCC_READ[25] TCC_WRITE[25] TCC_ATOMIC[25] TCC_REQ[26] TCC_READ[26] TCC_WRITE[26] TCC_ATOMIC[26] TCC_REQ[27] TCC_READ[27] TCC_WRITE[27] TCC_ATOMIC[27] TCC_REQ[28] TCC_READ[28] TCC_WRITE[28] TCC_ATOMIC[28] TCC_REQ[29] TCC_READ[29] TCC_WRITE[29] TCC_ATOMIC[29] TCC_REQ[30] TCC_READ[30] TCC_WRITE[30] TCC_ATOMIC[30] TCC_REQ[31] TCC_READ[31] TCC_WRITE[31] TCC_ATOMIC[31] CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE GRBM_SPI_BUSY - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index fff8e8f692..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index 9e8e854092..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TCC_EA_ATOMIC[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_ATOMIC_LEVEL[0] TCC_EA_ATOMIC[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_ATOMIC_LEVEL[1] TCC_EA_ATOMIC[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_ATOMIC_LEVEL[2] TCC_EA_ATOMIC[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_ATOMIC_LEVEL[3] TCC_EA_ATOMIC[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_ATOMIC_LEVEL[4] TCC_EA_ATOMIC[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_ATOMIC_LEVEL[5] TCC_EA_ATOMIC[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_ATOMIC_LEVEL[6] TCC_EA_ATOMIC[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_ATOMIC_LEVEL[7] TCC_EA_ATOMIC[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_ATOMIC_LEVEL[8] TCC_EA_ATOMIC[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_ATOMIC_LEVEL[9] TCC_EA_ATOMIC[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_ATOMIC_LEVEL[10] TCC_EA_ATOMIC[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_ATOMIC_LEVEL[11] TCC_EA_ATOMIC[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_ATOMIC_LEVEL[12] TCC_EA_ATOMIC[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_ATOMIC_LEVEL[13] TCC_EA_ATOMIC[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_ATOMIC_LEVEL[14] TCC_EA_ATOMIC[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_ATOMIC_LEVEL[15] TCC_EA_ATOMIC[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_ATOMIC_LEVEL[16] TCC_EA_ATOMIC[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_ATOMIC_LEVEL[17] TCC_EA_ATOMIC[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_ATOMIC_LEVEL[18] TCC_EA_ATOMIC[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_ATOMIC_LEVEL[19] TCC_EA_ATOMIC[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_ATOMIC_LEVEL[20] TCC_EA_ATOMIC[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_ATOMIC_LEVEL[21] TCC_EA_ATOMIC[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_ATOMIC_LEVEL[22] TCC_EA_ATOMIC[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_ATOMIC_LEVEL[23] TCC_EA_ATOMIC[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_ATOMIC_LEVEL[24] TCC_EA_ATOMIC[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_ATOMIC_LEVEL[25] TCC_EA_ATOMIC[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_ATOMIC_LEVEL[26] TCC_EA_ATOMIC[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_ATOMIC_LEVEL[27] TCC_EA_ATOMIC[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_ATOMIC_LEVEL[28] TCC_EA_ATOMIC[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_ATOMIC_LEVEL[29] TCC_EA_ATOMIC[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_ATOMIC_LEVEL[30] TCC_EA_ATOMIC[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ_LEVEL[31] TCC_EA_ATOMIC_LEVEL[31] CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_LEVEL_WAVES.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 91c1452d0b..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] CPC_ME1_BUSY_FOR_PACKET_DECODE CPC_CPC_UTCL2IU_STALL SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN GRBM_COUNT GRBM_GUI_ACTIVE - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_0.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_0.txt deleted file mode 100644 index 157b0fa30a..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_FLAT SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY SQ_WAIT_INST_ANY TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_CYCLE_sum CPC_ME1_DC0_SPI_BUSY SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_1.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_1.txt deleted file mode 100644 index b621588d2b..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum TCC_NC_REQ_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_2.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_2.txt deleted file mode 100644 index c385f7a070..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum TCC_REQ_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_3.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_3.txt deleted file mode 100644 index c201a09ec6..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum TCC_READ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_4.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_4.txt deleted file mode 100644 index dae1577474..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum TCC_EA_WRREQ_sum - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_5.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_5.txt deleted file mode 100644 index 6c5efd1c95..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum TCC_EA_WRREQ_STALL_sum - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_6.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_6.txt deleted file mode 100644 index 512ffbd896..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_7.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_7.txt deleted file mode 100644 index e7479b0f45..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_8.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_8.txt deleted file mode 100644 index 4afa81372a..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_9.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_9.txt deleted file mode 100644 index 5b7d3f8529..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/timestamps.txt b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_dispatch_info.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_dispatch_info.csv deleted file mode 100644 index 4c84144877..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_dispatch_info.csv +++ /dev/null @@ -1,8 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID -0,__amd_rocclr_fillBufferAligned.kd,2 -1,"global_write(int*, int) [clone .kd]",2 -2,"generic_write(int*, int, int) [clone .kd]",2 -3,"global_read(int*, int) [clone .kd]",2 -4,"generic_read(int*, int, int) [clone .kd]",2 -5,"global_atomic(int*, int) [clone .kd]",2 -6,"generic_atomic(int*, int, int) [clone .kd]",2 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_perf.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_perf.csv deleted file mode 100644 index b50d5c38f9..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/pmc_perf.csv +++ /dev/null @@ -1,8 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,TCC_EA_WRREQ_sum,wave_size_1,obj_1,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,SQ_ACTIVE_INST_ANY,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,TCC_NC_REQ_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_3,obj_3,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,TCC_REQ_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_4,obj_4,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,TCC_READ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_5,obj_5,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,wave_size_6,obj_6,SQ_INSTS_VALU_INT64,SQ_INSTS_FLAT,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_CYCLE_sum,CPC_ME1_DC0_SPI_BUSY,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_7,obj_7,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,wave_size_8,obj_8,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_9,obj_9,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,TCC_EA_WRREQ_STALL_sum,wave_size_10,obj_10,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_11,obj_11,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES_11,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TCC_CYCLE[0],TCC_RW_REQ[0],TCC_HIT[0],TCC_MISS[0],TCC_CYCLE[1],TCC_RW_REQ[1],TCC_HIT[1],TCC_MISS[1],TCC_CYCLE[2],TCC_RW_REQ[2],TCC_HIT[2],TCC_MISS[2],TCC_CYCLE[3],TCC_RW_REQ[3],TCC_HIT[3],TCC_MISS[3],TCC_CYCLE[4],TCC_RW_REQ[4],TCC_HIT[4],TCC_MISS[4],TCC_CYCLE[5],TCC_RW_REQ[5],TCC_HIT[5],TCC_MISS[5],TCC_CYCLE[6],TCC_RW_REQ[6],TCC_HIT[6],TCC_MISS[6],TCC_CYCLE[7],TCC_RW_REQ[7],TCC_HIT[7],TCC_MISS[7],TCC_CYCLE[8],TCC_RW_REQ[8],TCC_HIT[8],TCC_MISS[8],TCC_CYCLE[9],TCC_RW_REQ[9],TCC_HIT[9],TCC_MISS[9],TCC_CYCLE[10],TCC_RW_REQ[10],TCC_HIT[10],TCC_MISS[10],TCC_CYCLE[11],TCC_RW_REQ[11],TCC_HIT[11],TCC_MISS[11],TCC_CYCLE[12],TCC_RW_REQ[12],TCC_HIT[12],TCC_MISS[12],TCC_CYCLE[13],TCC_RW_REQ[13],TCC_HIT[13],TCC_MISS[13],TCC_CYCLE[14],TCC_RW_REQ[14],TCC_HIT[14],TCC_MISS[14],TCC_CYCLE[15],TCC_RW_REQ[15],TCC_HIT[15],TCC_MISS[15],TCC_CYCLE[16],TCC_RW_REQ[16],TCC_HIT[16],TCC_MISS[16],TCC_CYCLE[17],TCC_RW_REQ[17],TCC_HIT[17],TCC_MISS[17],TCC_CYCLE[18],TCC_RW_REQ[18],TCC_HIT[18],TCC_MISS[18],TCC_CYCLE[19],TCC_RW_REQ[19],TCC_HIT[19],TCC_MISS[19],TCC_CYCLE[20],TCC_RW_REQ[20],TCC_HIT[20],TCC_MISS[20],TCC_CYCLE[21],TCC_RW_REQ[21],TCC_HIT[21],TCC_MISS[21],TCC_CYCLE[22],TCC_RW_REQ[22],TCC_HIT[22],TCC_MISS[22],TCC_CYCLE[23],TCC_RW_REQ[23],TCC_HIT[23],TCC_MISS[23],TCC_CYCLE[24],TCC_RW_REQ[24],TCC_HIT[24],TCC_MISS[24],TCC_CYCLE[25],TCC_RW_REQ[25],TCC_HIT[25],TCC_MISS[25],TCC_CYCLE[26],TCC_RW_REQ[26],TCC_HIT[26],TCC_MISS[26],TCC_CYCLE[27],TCC_RW_REQ[27],TCC_HIT[27],TCC_MISS[27],TCC_CYCLE[28],TCC_RW_REQ[28],TCC_HIT[28],TCC_MISS[28],TCC_CYCLE[29],TCC_RW_REQ[29],TCC_HIT[29],TCC_MISS[29],TCC_CYCLE[30],TCC_RW_REQ[30],TCC_HIT[30],TCC_MISS[30],TCC_CYCLE[31],TCC_RW_REQ[31],TCC_HIT[31],TCC_MISS[31],CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_12,obj_12,SQ_CYCLES,SQ_WAVES_12,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES_12,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],CPC_ME1_BUSY_FOR_PACKET_DECODE,CPC_CPC_UTCL2IU_STALL,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,GRBM_COUNT_12,GRBM_GUI_ACTIVE_12,wave_size_13,obj_13,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES_13,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TCC_REQ[0],TCC_READ[0],TCC_WRITE[0],TCC_ATOMIC[0],TCC_REQ[1],TCC_READ[1],TCC_WRITE[1],TCC_ATOMIC[1],TCC_REQ[2],TCC_READ[2],TCC_WRITE[2],TCC_ATOMIC[2],TCC_REQ[3],TCC_READ[3],TCC_WRITE[3],TCC_ATOMIC[3],TCC_REQ[4],TCC_READ[4],TCC_WRITE[4],TCC_ATOMIC[4],TCC_REQ[5],TCC_READ[5],TCC_WRITE[5],TCC_ATOMIC[5],TCC_REQ[6],TCC_READ[6],TCC_WRITE[6],TCC_ATOMIC[6],TCC_REQ[7],TCC_READ[7],TCC_WRITE[7],TCC_ATOMIC[7],TCC_REQ[8],TCC_READ[8],TCC_WRITE[8],TCC_ATOMIC[8],TCC_REQ[9],TCC_READ[9],TCC_WRITE[9],TCC_ATOMIC[9],TCC_REQ[10],TCC_READ[10],TCC_WRITE[10],TCC_ATOMIC[10],TCC_REQ[11],TCC_READ[11],TCC_WRITE[11],TCC_ATOMIC[11],TCC_REQ[12],TCC_READ[12],TCC_WRITE[12],TCC_ATOMIC[12],TCC_REQ[13],TCC_READ[13],TCC_WRITE[13],TCC_ATOMIC[13],TCC_REQ[14],TCC_READ[14],TCC_WRITE[14],TCC_ATOMIC[14],TCC_REQ[15],TCC_READ[15],TCC_WRITE[15],TCC_ATOMIC[15],TCC_REQ[16],TCC_READ[16],TCC_WRITE[16],TCC_ATOMIC[16],TCC_REQ[17],TCC_READ[17],TCC_WRITE[17],TCC_ATOMIC[17],TCC_REQ[18],TCC_READ[18],TCC_WRITE[18],TCC_ATOMIC[18],TCC_REQ[19],TCC_READ[19],TCC_WRITE[19],TCC_ATOMIC[19],TCC_REQ[20],TCC_READ[20],TCC_WRITE[20],TCC_ATOMIC[20],TCC_REQ[21],TCC_READ[21],TCC_WRITE[21],TCC_ATOMIC[21],TCC_REQ[22],TCC_READ[22],TCC_WRITE[22],TCC_ATOMIC[22],TCC_REQ[23],TCC_READ[23],TCC_WRITE[23],TCC_ATOMIC[23],TCC_REQ[24],TCC_READ[24],TCC_WRITE[24],TCC_ATOMIC[24],TCC_REQ[25],TCC_READ[25],TCC_WRITE[25],TCC_ATOMIC[25],TCC_REQ[26],TCC_READ[26],TCC_WRITE[26],TCC_ATOMIC[26],TCC_REQ[27],TCC_READ[27],TCC_WRITE[27],TCC_ATOMIC[27],TCC_REQ[28],TCC_READ[28],TCC_WRITE[28],TCC_ATOMIC[28],TCC_REQ[29],TCC_READ[29],TCC_WRITE[29],TCC_ATOMIC[29],TCC_REQ[30],TCC_READ[30],TCC_WRITE[30],TCC_ATOMIC[30],TCC_REQ[31],TCC_READ[31],TCC_WRITE[31],TCC_ATOMIC[31],CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,GRBM_SPI_BUSY,wave_size_14,obj_14,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES_14,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCC_EA_ATOMIC[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_ATOMIC_LEVEL[0],TCC_EA_ATOMIC[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_ATOMIC_LEVEL[1],TCC_EA_ATOMIC[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_ATOMIC_LEVEL[2],TCC_EA_ATOMIC[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_ATOMIC_LEVEL[3],TCC_EA_ATOMIC[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_ATOMIC_LEVEL[4],TCC_EA_ATOMIC[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_ATOMIC_LEVEL[5],TCC_EA_ATOMIC[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_ATOMIC_LEVEL[6],TCC_EA_ATOMIC[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_ATOMIC_LEVEL[7],TCC_EA_ATOMIC[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_ATOMIC_LEVEL[8],TCC_EA_ATOMIC[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_ATOMIC_LEVEL[9],TCC_EA_ATOMIC[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_ATOMIC_LEVEL[10],TCC_EA_ATOMIC[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_ATOMIC_LEVEL[11],TCC_EA_ATOMIC[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_ATOMIC_LEVEL[12],TCC_EA_ATOMIC[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_ATOMIC_LEVEL[13],TCC_EA_ATOMIC[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_ATOMIC_LEVEL[14],TCC_EA_ATOMIC[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_ATOMIC_LEVEL[15],TCC_EA_ATOMIC[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_ATOMIC_LEVEL[16],TCC_EA_ATOMIC[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_ATOMIC_LEVEL[17],TCC_EA_ATOMIC[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_ATOMIC_LEVEL[18],TCC_EA_ATOMIC[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_ATOMIC_LEVEL[19],TCC_EA_ATOMIC[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_ATOMIC_LEVEL[20],TCC_EA_ATOMIC[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_ATOMIC_LEVEL[21],TCC_EA_ATOMIC[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_ATOMIC_LEVEL[22],TCC_EA_ATOMIC[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_ATOMIC_LEVEL[23],TCC_EA_ATOMIC[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_ATOMIC_LEVEL[24],TCC_EA_ATOMIC[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_ATOMIC_LEVEL[25],TCC_EA_ATOMIC[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_ATOMIC_LEVEL[26],TCC_EA_ATOMIC[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_ATOMIC_LEVEL[27],TCC_EA_ATOMIC[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_ATOMIC_LEVEL[28],TCC_EA_ATOMIC[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_ATOMIC_LEVEL[29],TCC_EA_ATOMIC[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_ATOMIC_LEVEL[30],TCC_EA_ATOMIC[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ_LEVEL[31],TCC_EA_ATOMIC_LEVEL[31],CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,Start_Timestamp,End_Timestamp -0,__amd_rocclr_fillBufferAligned.kd,2,256,256,0,0,12,4,32,64,0x7fb019e7d800,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c4bd800,0.0,0.0,64,0x7fe35344d800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93ecdd800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b64bd800,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501f115800,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc510b5800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b4a5800,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410dc0d800,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353b15800,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea49d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b83d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,15492,15492,64,0x7f0b7a335800,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,15256,15256,64,0x7f092c135800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,7832,64,0x7fa983c4d800,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595697581667,9595697588067 -1,"global_write(int*, int) [clone .kd]",2,1,1,0,0,4,4,16,64,0x7fb019e4d200,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d200,0.0,0.0,64,0x7fe353429200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca5200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d200,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe1200,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc51079200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d200,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e1200,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af1200,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea465200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b805200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,14214,14214,64,0x7f0b7a319200,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,14215,14215,64,0x7f092c0f9200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,4807,64,0x7fa983c15200,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595697981345,9595697983585 -2,"generic_write(int*, int, int) [clone .kd]",2,1,1,4096,0,4,4,48,64,0x7fb019e4d240,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d240,0.0,0.0,64,0x7fe353429240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca5240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d240,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe1240,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc51079240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d240,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e1240,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af1240,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea465240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b805240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16792,16792,64,0x7f0b7a319240,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,16303,16303,64,0x7f092c0f9240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6147,64,0x7fa983c15240,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595697989025,9595697991265 -3,"global_read(int*, int) [clone .kd]",2,1,1,0,0,4,4,16,64,0x7fb019e4d280,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d280,0.0,0.0,64,0x7fe353429280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca5280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d280,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe1280,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc51079280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d280,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e1280,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af1280,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea465280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b805280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,17066,17066,64,0x7f0b7a319280,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17633,17633,64,0x7f092c0f9280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6439,64,0x7fa983c15280,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595698033025,9595698035745 -4,"generic_read(int*, int, int) [clone .kd]",2,1,1,0,0,4,4,16,64,0x7fb019e4d2c0,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d2c0,0.0,0.0,64,0x7fe3534292c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca52c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d2c0,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe12c0,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc510792c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d2c0,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e12c0,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af12c0,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea4652c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b8052c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16835,16835,64,0x7f0b7a3192c0,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,16725,16725,64,0x7f092c0f92c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6821,64,0x7fa983c152c0,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595698039905,9595698042305 -5,"global_atomic(int*, int) [clone .kd]",2,1,1,0,0,4,4,16,64,0x7fb019e4d300,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d300,0.0,0.0,64,0x7fe353429300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca5300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d300,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe1300,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc51079300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d300,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e1300,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af1300,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea465300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b805300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,16490,16490,64,0x7f0b7a319300,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17452,17452,64,0x7f092c0f9300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,6708,64,0x7fa983c15300,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595698072385,9595698076225 -6,"generic_atomic(int*, int, int) [clone .kd]",2,1,1,4096,0,4,4,48,64,0x7fb019e4d340,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,64,0x7f099c49d340,0.0,0.0,64,0x7fe353429340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fa93eca5340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7fe7b648d340,0,0,0,0,0,0,0,0,131072.0,131072.0,0.0,971473.0,33551804.0,29353105.0,0.0,0.0,16384,0,64,0x7f501efe1340,46,26,5,15,2,0,4,16,930.0,0.0,0.0,0.0,64,0x7fbc51079340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,1213216,992963,0,0,0,0,1175854,1033860,0,1520989,1091404,0,1468827,1047492,0,0,0,0,1239120,1082184,0,1072038,981313,0,1024755,978955,0,1114067,1067349,0,1125538,973712,0,1092006,1136315,0,1488950,1046986,0,1420108,1188281,0,1087014,957831,0,1079591,979515,0,1200842,1084335,0,0,0,0,1085995,1022303,0,1295858,1104205,0,1049908,1014016,0,1533784,1320993,0,1166083,1076118,0,1122956,992991,0,998575,952668,0,1169185,1082850,0,1178114,999491,0,1062056,1000641,0,1153969,999775,0,1310176,1179285,0,0.0,14941,16384,0,64,0x7f817b47d340,46,26,5,15,2,0,0.0,0.0,0.0,5812.0,64,0x7f410c9e1340,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7ff353af1340,0,0,0,0,0,0,0,0,33551804.0,29353105.0,0.0,0.0,64,0x7f96ea465340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,64,0x7fc39b805340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,17235,17235,64,0x7f0b7a319340,0,0,0,0,0,0,0,0,16384.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,16384,0,17418,17418,64,0x7f092c0f9340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,16384.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,25626,16384,0,7838,64,0x7fa983c15340,0,0,0,0,0,0,0,0,16384.0,0.0,0.0,131072.0,131072.0,0.0,971473.0,1102230,965274,0,0,0,0,0,0,1213216,992963,0,0,0,0,0,0,1175854,1033860,0,0,1520989,1091404,0,0,1468827,1047492,0,0,0,0,0,0,1239120,1082184,0,0,1072038,981313,0,0,1024755,978955,0,0,1114067,1067349,0,0,1125538,973712,0,0,1092006,1136315,0,0,1488950,1046986,0,0,1420108,1188281,0,0,1087014,957831,0,0,1079591,979515,0,0,1200842,1084335,0,0,0,0,0,0,1085995,1022303,0,0,1295858,1104205,0,0,1049908,1014016,0,0,1533784,1320993,0,0,1166083,1076118,0,0,1122956,992991,0,0,998575,952668,0,0,1169185,1082850,0,0,1178114,999491,0,0,1062056,1000641,0,0,1153969,999775,0,0,1310176,1179285,0,0,14941,11278,0,16384,0,9595698076225,9595698080065 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/roofline.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/roofline.csv deleted file mode 100644 index 6ec250343a..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/roofline.csv +++ /dev/null @@ -1,4 +0,0 @@ -device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1392.4641,1391.8217,1393.1066,5012.8921,4999.646,5026.1382,9233.5303,9232.7051,9234.3555,21014.016,21012.709,21015.322,20999.16,20998.666,20999.654,20187.006,19967.416,20406.596,170734.45,170729.66,170739.25,165067.44,165061.97,165072.91,41480.547,41479.074,41482.02,41303.828,40844.742,41762.914,166839.7,166833.48,166845.92 -1,1391.9521,1391.3705,1392.5338,5005.9937,4997.5942,5014.3931,9197.5605,9196.7617,9198.3594,20984.785,20983.42,20986.15,20944.287,20943.701,20944.873,20222.557,20221.738,20223.375,170379.27,170372.45,170386.08,164480.19,164473.75,164486.62,41338.699,41336.965,41340.434,41397.539,41395.738,41399.34,166265.69,166259,166272.38 -2,1383.8199,1367.1714,1400.4685,5018.9521,5012.7114,5025.1929,9215.9326,9215.2646,9216.6006,21009.275,21007.996,21010.555,20973.949,20973.555,20974.344,20256.393,20255.896,20256.889,170535.72,170531.75,170539.69,164753.2,164748.77,164757.64,41403.738,41402.945,41404.531,41465.727,41464.988,41466.465,166533.73,166531.06,166536.41 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/sysinfo.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/sysinfo.csv deleted file mode 100644 index 5ac906c7d1..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,chip_id,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -multikernel,./sample/vmem,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Tue 22 Oct 2024 03:45:54 PM (CDT),2,dell-rack-10,AMD EPYC 7313 16-Core Processor,Dell Inc.2.2.5,Ubuntu 20.04.6 LTS,5.15.0-122-generic,,527949684,,6.2.1-99,113-D67301-064D,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,29711,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/timestamps.csv b/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/timestamps.csv deleted file mode 100644 index 23782c1d1b..0000000000 --- a/projects/rocprofiler-compute/tests/workloads/multikernel/MI200/timestamps.csv +++ /dev/null @@ -1,8 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,__amd_rocclr_fillBufferAligned.kd,2,0,0,791827,791827,256,256,0,0,12,4,32,64,0x0,0x7fd72f815800,9595697470571,9595697581667,9595697588067,9595697604693 -1,"global_write(int*, int) [clone .kd]",2,0,1,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d9200,9595697964779,9595697981345,9595697983585,9595697985168 -2,"generic_write(int*, int, int) [clone .kd]",2,0,2,791827,791827,1,1,4096,0,4,4,48,64,0x0,0x7fd72e4d9240,9595697979166,9595697989025,9595697991265,9595698006628 -3,"global_read(int*, int) [clone .kd]",2,0,3,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d9280,9595697986791,9595698033025,9595698035745,9595698036745 -4,"generic_read(int*, int, int) [clone .kd]",2,0,4,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d92c0,9595698029551,9595698039905,9595698042305,9595698049348 -5,"global_atomic(int*, int) [clone .kd]",2,0,5,791827,791827,1,1,0,0,4,4,16,64,0x0,0x7fd72e4d9300,9595698036745,9595698072385,9595698076225,9595698076890 -6,"generic_atomic(int*, int, int) [clone .kd]",2,0,6,791827,791827,1,1,4096,0,4,4,48,64,0x0,0x7fd72e4d9340,9595698067583,9595698076225,9595698080065,9595698086618 diff --git a/projects/rocprofiler-compute/utils/build.sh b/projects/rocprofiler-compute/utils/build.sh index 5aebc0f9b3..80711889d0 100755 --- a/projects/rocprofiler-compute/utils/build.sh +++ b/projects/rocprofiler-compute/utils/build.sh @@ -1,11 +1,11 @@ #!/usr/bin/env bash -pyinstaller src/omniperf.py \ - --name "omniperf" \ +pyinstaller src/rocprofiler-compute.py \ + --name "rocprofiler-compute" \ --add-data "src/perfmon_pub/*:perfmon_pub" \ --add-data "src/utils/*:utils" \ --add-data "src/soc_params/*.csv:soc_params" \ - --add-data "src/omniperf_analyze/*:omniperf_analyze" \ + --add-data "src/rocprof_compute_analyze/*:rocprof_compute_analyze" \ --hidden-import matplotlib.backends.backend_pdf \ ${@} @@ -53,14 +53,14 @@ echo "(build.sh) Loading dash_svg" # Take care of dash-svg module that isn't detected by PyInstaller dash_info=$(pip3 show dash_svg) dash_loc=$(sed -n '8p' <<<"$dash_info") -cp -r ${dash_loc:10}/dash_svg "$distpath"/omniperf/ +cp -r ${dash_loc:10}/dash_svg "$distpath"/rocprofiler-compute/ echo "(build.sh) Fixing flattened directories" #TODO: Copy orig file structure from over to flattened packaged version -rm -rf "$distpath"/omniperf/omniperf_analyze/ -cp -r src/omniperf_analyze/ "$distpath"/omniperf/ +rm -rf "$distpath"/rocprofiler-compute/rocprof_compute_analyze/ +cp -r src/rocprof_compute_analyze/ "$distpath"/rocprofiler-compute/ -rm -rf "$distpath"/omniperf/perfmon_pub/ -cp -r src/perfmon_pub/ "$distpath"/omniperf/ +rm -rf "$distpath"/rocprofiler-compute/perfmon_pub/ +cp -r src/perfmon_pub/ "$distpath"/rocprofiler-compute/ -rm -rf "$distpath"/omniperf/perfmon/ +rm -rf "$distpath"/rocprofiler-compute/perfmon/ From 14d90939da5188dd57bd4e10891cbd006caf8c65 Mon Sep 17 00:00:00 2001 From: Cole Ramos Date: Fri, 1 Nov 2024 13:16:49 -0500 Subject: [PATCH 25/29] Give executable permission to rocprof-compute (#456) Signed-off-by: coleramos425 [ROCm/rocprofiler-compute commit: 8a88e8bd90f4546ec48343e63f3b3758d6bcd9a5] --- projects/rocprofiler-compute/src/rocprof-compute | 0 1 file changed, 0 insertions(+), 0 deletions(-) mode change 100644 => 100755 projects/rocprofiler-compute/src/rocprof-compute diff --git a/projects/rocprofiler-compute/src/rocprof-compute b/projects/rocprofiler-compute/src/rocprof-compute old mode 100644 new mode 100755 From e43db734fa72a3fa1eefd955244b0ab44b42aa10 Mon Sep 17 00:00:00 2001 From: David Galiffi Date: Fri, 1 Nov 2024 15:26:34 -0400 Subject: [PATCH 26/29] Update VERSION to 3.0.0 (#457) * Update VERSION and README to 3.0.0 * Update version mismatch of profiling data to a warning. Signed-off-by: David Galiffi [ROCm/rocprofiler-compute commit: 152eff0df156d3984be722159501b73b7c3129e8] --- projects/rocprofiler-compute/README.md | 6 +++--- projects/rocprofiler-compute/VERSION | 2 +- projects/rocprofiler-compute/src/utils/specs.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/projects/rocprofiler-compute/README.md b/projects/rocprofiler-compute/README.md index 217f394edf..36d4d7f5d8 100644 --- a/projects/rocprofiler-compute/README.md +++ b/projects/rocprofiler-compute/README.md @@ -50,11 +50,11 @@ style reference is provided below for convenience: Keith Lowery and Nicholas Curtis and Cristian Di Pietrantonio}, - title = {ROCm/rocprofiler-compute: v2.1.0 (27 September 2024)}, - month = september, + title = {ROCm/rocprofiler-compute: v3.0.0 (01 November 2024)}, + month = November, year = 2024, publisher = {Zenodo}, - version = {v2.1.0}, + version = {v3.0.0}, doi = {10.5281/zenodo.7314631}, url = {https://doi.org/10.5281/zenodo.7314631} } diff --git a/projects/rocprofiler-compute/VERSION b/projects/rocprofiler-compute/VERSION index 7ec1d6db40..4a36342fca 100644 --- a/projects/rocprofiler-compute/VERSION +++ b/projects/rocprofiler-compute/VERSION @@ -1 +1 @@ -2.1.0 +3.0.0 diff --git a/projects/rocprofiler-compute/src/utils/specs.py b/projects/rocprofiler-compute/src/utils/specs.py index 4cbc55e5b3..2ea0b64bbc 100644 --- a/projects/rocprofiler-compute/src/utils/specs.py +++ b/projects/rocprofiler-compute/src/utils/specs.py @@ -93,7 +93,7 @@ def generate_machine_specs(args, sysinfo: dict = None): ) version = get_version(config.rocprof_compute_home)["version"] if sysinfo_ver != version[: version.find(".")]: - console_error( + console_warning( "Detected mismatch in sysinfo versioning. You need to reprofile to update data." ) return MachineSpecs(**sysinfo) From 4e78cf9b8c9578d12109ea899f97a9beff1b818d Mon Sep 17 00:00:00 2001 From: David Galiffi Date: Fri, 1 Nov 2024 17:51:00 -0400 Subject: [PATCH 27/29] Install LICENCE to ${CMAKE_INSTALL_DOCDIR} (#458) * Install LICENSE to ${CMAKE_INSTALL_DOCDIR} * Update tarball.yml to test for LICENSE file after the install --------- Signed-off-by: David Galiffi [ROCm/rocprofiler-compute commit: 50755de8673e5f53e4e9481f6d05ff8ec8c115f1] --- projects/rocprofiler-compute/.github/workflows/tarball.yml | 3 ++- projects/rocprofiler-compute/CMakeLists.txt | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/projects/rocprofiler-compute/.github/workflows/tarball.yml b/projects/rocprofiler-compute/.github/workflows/tarball.yml index 13cbfcc65b..fe32ded625 100644 --- a/projects/rocprofiler-compute/.github/workflows/tarball.yml +++ b/projects/rocprofiler-compute/.github/workflows/tarball.yml @@ -8,7 +8,7 @@ on: concurrency: group: ${{ github.workflow }}-${{ github.ref }} cancel-in-progress: true - + jobs: distbuild: runs-on: ubuntu-latest @@ -91,6 +91,7 @@ jobs: test -d $INSTALL_DIR/rocprofiler-compute/libexec/rocprofiler-compute/utils test -s $INSTALL_DIR/rocprofiler-compute/share/rocprofiler-compute/sample/vcopy.cpp test -d $INSTALL_DIR/rocprofiler-compute/share/rocprofiler-compute/modulefiles + test -s $INSTALL_DIR/rocprofiler-compute/share/doc/rocprofiler-compute/LICENSE - name: Query version (setting PYTHONPATH by hand) run: | export PYTHONPATH=${INSTALL_DIR}/python-libs:$PYTHONPATH diff --git a/projects/rocprofiler-compute/CMakeLists.txt b/projects/rocprofiler-compute/CMakeLists.txt index 8f35fbd6a1..b312b6db5f 100644 --- a/projects/rocprofiler-compute/CMakeLists.txt +++ b/projects/rocprofiler-compute/CMakeLists.txt @@ -372,6 +372,11 @@ add_custom_target( "src/${PACKAGE_NAME},cmake/Dockerfile,cmake/rocm_install.sh,docker/docker-entrypoint.sh,src/rocprof_compute_analyze/convertor/mongodb/convert" ) +install( + FILES ${PROJECT_SOURCE_DIR}/LICENSE + DESTINATION ${CMAKE_INSTALL_DOCDIR} + COMPONENT main) + # TEST collateral option(INSTALL_TESTS "Build test suite" OFF) if(INSTALL_TESTS) From f1c9c686ffcc7464d7a5c86e7ca76674142f6bcb Mon Sep 17 00:00:00 2001 From: "fei.zheng" Date: Mon, 4 Nov 2024 14:31:52 -0700 Subject: [PATCH 28/29] fix PoP of VALU Active Threads with wave_size Signed-off-by: fei.zheng [ROCm/rocprofiler-compute commit: 1b37572b4a180cce611e58fe636ec0ba6729be9a] --- .../analysis_configs/gfx906/0200_system-speed-of-light.yaml | 5 ++--- .../analysis_configs/gfx908/0200_system-speed-of-light.yaml | 5 ++--- .../analysis_configs/gfx940/0200_system-speed-of-light.yaml | 5 ++--- .../analysis_configs/gfx941/0200_system-speed-of-light.yaml | 5 ++--- .../analysis_configs/gfx942/0200_system-speed-of-light.yaml | 5 ++--- projects/rocprofiler-compute/src/utils/parser.py | 1 + 6 files changed, 11 insertions(+), 15 deletions(-) diff --git a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0200_system-speed-of-light.yaml index 1e7b7f2875..aafb938fa4 100644 --- a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0200_system-speed-of-light.yaml +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx906/0200_system-speed-of-light.yaml @@ -102,9 +102,8 @@ Panel Config: value: AVG(((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU) if (SQ_ACTIVE_INST_VALU != 0) else None)) unit: Threads - peak: 64 - pop: (AVG(((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU) if (SQ_ACTIVE_INST_VALU - != 0) else None)) * 1.5625) + peak: $wave_size + pop: (100 * AVG((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU / $wave_size) if (SQ_ACTIVE_INST_VALU != 0) else None)) tips: IPC: value: AVG((SQ_INSTS / SQ_BUSY_CU_CYCLES)) diff --git a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0200_system-speed-of-light.yaml index 1bd4979de9..00da40724d 100644 --- a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0200_system-speed-of-light.yaml +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx908/0200_system-speed-of-light.yaml @@ -102,9 +102,8 @@ Panel Config: value: AVG(((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU) if (SQ_ACTIVE_INST_VALU != 0) else None)) unit: Threads - peak: 64 - pop: (AVG(((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU) if (SQ_ACTIVE_INST_VALU - != 0) else None)) * 1.5625) + peak: $wave_size + pop: (100 * AVG((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU / $wave_size) if (SQ_ACTIVE_INST_VALU != 0) else None)) tips: IPC: value: AVG((SQ_INSTS / SQ_BUSY_CU_CYCLES)) diff --git a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0200_system-speed-of-light.yaml index 7752ee879e..eec30fe8fc 100644 --- a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0200_system-speed-of-light.yaml +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx940/0200_system-speed-of-light.yaml @@ -119,9 +119,8 @@ Panel Config: value: AVG(((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU) if (SQ_ACTIVE_INST_VALU != 0) else None)) unit: Threads - peak: 64 - pop: (AVG(((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU) if (SQ_ACTIVE_INST_VALU - != 0) else None)) * 1.5625) + peak: $wave_size + pop: (100 * AVG((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU / $wave_size) if (SQ_ACTIVE_INST_VALU != 0) else None)) tips: IPC: value: AVG((SQ_INSTS / SQ_BUSY_CU_CYCLES)) diff --git a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0200_system-speed-of-light.yaml index 7752ee879e..eec30fe8fc 100644 --- a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0200_system-speed-of-light.yaml +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx941/0200_system-speed-of-light.yaml @@ -119,9 +119,8 @@ Panel Config: value: AVG(((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU) if (SQ_ACTIVE_INST_VALU != 0) else None)) unit: Threads - peak: 64 - pop: (AVG(((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU) if (SQ_ACTIVE_INST_VALU - != 0) else None)) * 1.5625) + peak: $wave_size + pop: (100 * AVG((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU / $wave_size) if (SQ_ACTIVE_INST_VALU != 0) else None)) tips: IPC: value: AVG((SQ_INSTS / SQ_BUSY_CU_CYCLES)) diff --git a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0200_system-speed-of-light.yaml b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0200_system-speed-of-light.yaml index 9909e68a71..9e6cba483e 100644 --- a/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0200_system-speed-of-light.yaml +++ b/projects/rocprofiler-compute/src/rocprof_compute_soc/analysis_configs/gfx942/0200_system-speed-of-light.yaml @@ -119,9 +119,8 @@ Panel Config: value: AVG(((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU) if (SQ_ACTIVE_INST_VALU != 0) else None)) unit: Threads - peak: 64 - pop: (AVG(((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU) if (SQ_ACTIVE_INST_VALU - != 0) else None)) * 1.5625) + peak: $wave_size + pop: (100 * AVG((SQ_THREAD_CYCLES_VALU / SQ_ACTIVE_INST_VALU / $wave_size) if (SQ_ACTIVE_INST_VALU != 0) else None)) tips: IPC: value: AVG((SQ_INSTS / SQ_BUSY_CU_CYCLES)) diff --git a/projects/rocprofiler-compute/src/utils/parser.py b/projects/rocprofiler-compute/src/utils/parser.py index 654057b400..8e2f84319f 100644 --- a/projects/rocprofiler-compute/src/utils/parser.py +++ b/projects/rocprofiler-compute/src/utils/parser.py @@ -698,6 +698,7 @@ def eval_metric(dfs, dfs_type, sys_info, raw_pmc_df, debug): ammolite__hbm_bw = sys_info.hbm_bw ammolite__total_l2_chan = calc_builtin_var("$total_l2_chan", sys_info) ammolite__num_xcd = sys_info.num_xcd + ammolite__wave_size = sys_info.wave_size # TODO: fix all $normUnit in Unit column or title From 5a30a05800b7874fff9ec544318f9541523101f4 Mon Sep 17 00:00:00 2001 From: Peter Park Date: Mon, 4 Nov 2024 16:45:16 -0500 Subject: [PATCH 29/29] Fix changelog heading Signed-off-by: Peter Park [ROCm/rocprofiler-compute commit: 6a381d8966b51d56d420c0dafca26d9668fd4715] --- projects/rocprofiler-compute/CHANGELOG.md | 38 +++++++++++------------ 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/projects/rocprofiler-compute/CHANGELOG.md b/projects/rocprofiler-compute/CHANGELOG.md index 5c18aeb8c1..7200a39a1a 100644 --- a/projects/rocprofiler-compute/CHANGELOG.md +++ b/projects/rocprofiler-compute/CHANGELOG.md @@ -2,37 +2,37 @@ Full documentation for ROCm Compute Profiler is available at [https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/](https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/). -## Omniperf 2.1.0 for ROCm 6.2.2 +## Omniperf 2.0.1 for ROCm 6.2.1 -### Changes +### Changed - * enable rocprofv1 for MI300 hardware (#391) - * refactoring and updating documemtation (#362, #394, #398, #414, #420) - * branch renaming and workflow updates (#389, #404, #409) - * bug fix for analysis output - * add dependency checks on application launch (#393) - * patch for profiling multi-process/multi-GPU applications (#376, #396) - * packaging updates (#386) - * rename CHANGES to CHANGELOG.md (#410) - * rollback Grafana version in Dockerfile for Angular plugin compatibility (#416) - * enable CI triggers for Azure CI (#426) - * add GPU model distinction for MI300 systems (#423) - * new MAINTAINERS.md guide for omniperf publishing procedures (#402) +* enable rocprofv1 for MI300 hardware (#391) +* refactoring and updating documemtation (#362, #394, #398, #414, #420) +* branch renaming and workflow updates (#389, #404, #409) +* bug fix for analysis output +* add dependency checks on application launch (#393) +* patch for profiling multi-process/multi-GPU applications (#376, #396) +* packaging updates (#386) +* rename CHANGES to CHANGELOG.md (#410) +* rollback Grafana version in Dockerfile for Angular plugin compatibility (#416) +* enable CI triggers for Azure CI (#426) +* add GPU model distinction for MI300 systems (#423) +* new MAINTAINERS.md guide for omniperf publishing procedures (#402) -### Optimizations +### Optimized - * reduced running time of Omniperf when profiling (#384) - * console logging improvements +* reduced running time of Omniperf when profiling (#384) +* console logging improvements ## Omniperf 2.0.1 for ROCm 6.2.0 -### Changes +### Added * new option to force hardware target via `OMNIPERF_ARCH_OVERRIDE` global (#370) * CI/CD support for MI300 hardware (#373) * support for MI308X hardware (#375) -### Optimizations +### Optimized * cmake build improvements (#374)