Commit Graph

12605 Commits

Author SHA1 Message Date
Giovanni Baraldi 2c7baf6c89 SWDEV-490031: Fixing activity metrics
Change-Id: Id4e74b0f3ff35d892de05e044faf399d98199354


[ROCm/rocprofiler commit: 59e9e3a0c3]
2024-12-17 10:32:01 -06:00
Longlong Yao 22ed708c39 Use /dev/dxg to detect wsl environment
Since wslinfo does not exist in docker running on wsl,
change the way to detect wsl environment.

Change-Id: I215eb985a227caeef47483cd51818c84bf1d8a4c
Signed-off-by: Longlong Yao <Longlong.Yao@amd.com>
2024-12-16 20:18:53 -08:00
dependabot[bot] 9be05fc673 Bump rocm-docs-core[api_reference] from 1.11.0 to 1.12.0 in /docs/sphinx
Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.11.0 to 1.12.0.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.11.0...v1.12.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core[api_reference]
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

[ROCm/rocprofiler-systems commit: fc6900c70e]
2024-12-16 22:46:06 -05:00
dependabot[bot] fc6900c70e Bump rocm-docs-core[api_reference] from 1.11.0 to 1.12.0 in /docs/sphinx
Bumps [rocm-docs-core[api_reference]](https://github.com/ROCm/rocm-docs-core) from 1.11.0 to 1.12.0.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.11.0...v1.12.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core[api_reference]
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2024-12-16 22:46:06 -05:00
Horatio Zhang b02b842368 rocrtst: fix build error for opencl-c.h
<built-in>:2:10: fatal error: '/opt/rocm/llvm/lib/clang/18/includeopencl-c.h' file not found
    2 | #include "/opt/rocm/llvm/lib/clang/18/includeopencl-c.h"
      |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1 error generated.

Change-Id: I56138aba15465b6dd47bb3aad810bdd10f2b2a74
Signed-off-by: Horatio Zhang <Hongkun.Zhang@amd.com>
2024-12-16 21:28:09 -05:00
Peter Park 01ba75c945 docs: Add section on building rocprofsys without ROCm (#57)
Adds brief information in install.rst regarding

Provided build scripts
What to do when building rocprofiler-systems w/o ROCm
Recent changes to the configuration settings as a result of rocprofiler-sdk support.
Fixes minor formatting issues in install.rst resulting in Sphinx build warnings

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 02ed6e187e]
2024-12-16 16:29:15 -05:00
Peter Park 02ed6e187e docs: Add section on building rocprofsys without ROCm (#57)
Adds brief information in install.rst regarding

Provided build scripts
What to do when building rocprofiler-systems w/o ROCm
Recent changes to the configuration settings as a result of rocprofiler-sdk support.
Fixes minor formatting issues in install.rst resulting in Sphinx build warnings

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2024-12-16 16:29:15 -05:00
darren-amd 5a6f6ed83d Allow disabling of openmp examples (#64)
Add flag to disable openmp examples

Co-authored-by: David Galiffi <David.Galiffi@amd.com>

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 888b9a43a0]
2024-12-16 14:31:56 -05:00
darren-amd 888b9a43a0 Allow disabling of openmp examples (#64)
Add flag to disable openmp examples

Co-authored-by: David Galiffi <David.Galiffi@amd.com>

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2024-12-16 14:31:56 -05:00
Xiaogang Chen ec457752dc kfdtest: update run_kfdtest.sh when HSA_TEST_GPUS_NUM is enable
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I68e4f4f8fd7397d3b39b3473638836e4531bef2b
2024-12-16 12:47:50 -05:00
Xiaogang Chen cbb38606e3 kfdtest: Convert KFDSVMRangeTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Ia4d55c38576c39b3768a847c60d70bda88f65740
2024-12-16 12:47:44 -05:00
Xiaogang Chen 641f1f797d kfdtest: Convert KFDLocalMemoryTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Iaf20ec15e85ed10998e9735881d3c029abedd3a4
2024-12-16 12:47:39 -05:00
Xiaogang Chen 10c9b98f6e kfdtest: Convert KFDMemoryTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I29d7fbb156a88b4df5be5f2fa0c20fbc47b108ed
2024-12-16 12:47:34 -05:00
Xiaogang Chen f229605b06 kfdtest: Convert KFDQMTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Ia3582ab5b802ead4df267eeb280b8e7d37eb0ac2
2024-12-16 12:47:28 -05:00
Xiaogang Chen dbccf11ef8 kfdtest: Convert KFDExceptionTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I545ac485d13a3a56a3b352926ec71daa5b074862
2024-12-16 12:47:21 -05:00
Xiaogang Chen 0357e2e139 kfdtest: Convert KFDEventTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Id1dc91f654686f159adb1bc70907e11558ee4be0
2024-12-16 12:47:14 -05:00
Xiaogang Chen fa31caddba kfdtest: Convert KFDCWSRTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I51646ebd95b2ef4820f7b503bd642deb05a86930
2024-12-16 12:47:08 -05:00
Xiaogang Chen 6c6daf66bf kfdtest: Convert KFDGWSTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I0901750b2ce55bd7f44425b01442d98f0faf12fd
2024-12-16 12:47:01 -05:00
Xiaogang Chen 759ca45f54 kfdtest: convert KFDGraphicsInterop into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I590be9ea063b0d115641aa5b40be4c376377c1dd
2024-12-16 12:46:55 -05:00
Xiaogang Chen dd1801df41 kfdtest: convert KFDPerfCountersTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I29124147394b69c7fb5533a0e54d375d06b1ec13
2024-12-16 12:46:49 -05:00
Xiaogang Chen c69e660e7a kfdtest: Update KFDMultiProcessTest class to support kfdtest run on multiple gpu
Update KFDMultiProcessTest class to fork process on gpu wise.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Ibb12d64b4cbc5f082d737fd8d8a74233b75be13e
2024-12-16 12:46:42 -05:00
Xiaogang Chen b4943d718b kfdtest: Implement an infracture to support kfdtest run on multi gpu
Update class KFDBaseComponentTest to have kfdtest run on multi gpu under google test framework.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: If139c4fc6cf062fb800ff171c69cbf9604f98278
2024-12-16 12:46:32 -05:00
Xiaogang Chen 665e6f80bf kfdtest: Add an env variable to control kfdtest on multi gpu
Add HSA_TEST_GPUS_NUM env variable that controls gpu number kfdtest uses.

This env variable will be used by following patches.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I800042f93d4e0955040f450e9b5cf09927971323
2024-12-16 12:46:25 -05:00
Xiaogang Chen 36a82593ed kfdtest: Extend gtest log functions
Extend Google test log functions to extend kfdtest running on multiple gpu.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I6d8de92fec606309756423b3a6fa2af3558c0517
2024-12-16 12:46:16 -05:00
Xiaogang Chen e1fdd6fb5f kfdtest: Separate LLVM initialization and instantiation
Assembler function from LLVM is not multi-thread safe and is ASIC dependent.
To extend kfdtest to test on multiple GPU separate LLVM initialization and
assembler instantiation. Each test uses its own assembler.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I94c996e807b81d8b19361b450be985b12042477c
2024-12-16 12:46:07 -05:00
Giovanni baraldi bcc709c174 SWDEV-495749: Adding SIMD_UTILIZATION metric
Change-Id: I38afd5db02de7a416d11274823bc4a0c326f1fbe
2024-12-16 10:22:57 -06:00
Giovanni baraldi 2baa5bd4ab SWDEV-495749: Adding SIMD_UTILIZATION metric
Change-Id: I38afd5db02de7a416d11274823bc4a0c326f1fbe


[ROCm/rocprofiler commit: bcc709c174]
2024-12-16 10:22:57 -06:00
David Yat Sin 5da1889fb7 rocr: Avoid deadlock due to queue signal not updated
Make sure waiting_ count for queue signal is always > 0 so that we
always call hsaKmtWaitOnEvent to force hsaKmtWaitOnEvent to return.

Remove incorrect warning print when running in debug mode.

Call internal Signal::WaitAny instead of AMD::hsa_amd_signal_wait_any
to avoid extra function calls.

Change-Id: I9e41b704643e4e8ee7402b1379b1c30ff4c544ef
2024-12-16 10:25:19 -05:00
David Galiffi 4297f75f83 Update VERSION to 0.2.0
[ROCm/rocprofiler-systems commit: 1f8b4bf67d]
2024-12-16 06:05:42 -05:00
David Galiffi 1f8b4bf67d Update VERSION to 0.2.0 2024-12-16 06:05:42 -05:00
Peter Park 92d23f72d2 docs: Fix docutils warnings (#59)
* fix typo

* fix `Lexing literal_block` docutils warning

* fix `Title underline too short` docutils warning

* use consistent file type

* fix `Malformed table` error

* improve index.rst and front-load TOC

[ROCm/rocprofiler-systems commit: a70034055e]
2024-12-16 06:05:42 -05:00
Peter Park a70034055e docs: Fix docutils warnings (#59)
* fix typo

* fix `Lexing literal_block` docutils warning

* fix `Title underline too short` docutils warning

* use consistent file type

* fix `Malformed table` error

* improve index.rst and front-load TOC
2024-12-16 06:05:42 -05:00
David Galiffi 78168bca8d Allow ElfUtils_CONFIG_OPTIONS to provide additional configuration options (#58)
Signed-off-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: dd96d78c7f]
2024-12-16 06:05:42 -05:00
David Galiffi dd96d78c7f Allow ElfUtils_CONFIG_OPTIONS to provide additional configuration options (#58)
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
2024-12-16 06:05:42 -05:00
David Galiffi 15c81fc2a3 Adding installer for Ubuntu 24.04 (#14)
* Add installers for ubuntu 24.04

* Formatting change to the ubuntu-focal and ubuntu-jammy workflows

* Initial Ubuntu 24.04 workflow - just build test

[ROCm/rocprofiler-systems commit: 42b795d2c5]
2024-12-16 06:05:42 -05:00
David Galiffi 42b795d2c5 Adding installer for Ubuntu 24.04 (#14)
* Add installers for ubuntu 24.04

* Formatting change to the ubuntu-focal and ubuntu-jammy workflows

* Initial Ubuntu 24.04 workflow - just build test
2024-12-16 06:05:42 -05:00
David Galiffi 890e50c95a Add installers for rocm-6.3 and rhel-9.5 and update installer script template (#50)
* Add installers for rocm-6.3 and rhel-9.5
* Updated the template "rocprof-sys-install.py.in".
Fixed the installer for the "rocm-x.y.z" style tags.

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: 2cb6a89a94]
2024-12-16 06:05:42 -05:00
David Galiffi 2cb6a89a94 Add installers for rocm-6.3 and rhel-9.5 and update installer script template (#50)
* Add installers for rocm-6.3 and rhel-9.5
* Updated the template "rocprof-sys-install.py.in".
Fixed the installer for the "rocm-x.y.z" style tags.

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
2024-12-16 06:05:42 -05:00
stali 8bcb5f7068 Enable RDC topology feature
1.Add topology APIs
2.Add topology example for topology API usage

Change-Id: Ib79c06d0bac85119672f194ba685ebf25029979c
2024-12-16 10:02:41 +08:00
Li Ma 30f9b2ac2f SWDEV-475244 - Memory Usage and Bandwidth: max mem and current mem
Implemented max memory bandwith and current memory bandwidth. Added two
new field ids: RDC_FI_GPU_MEMORY_MAX_BANDWIDTH, RDC_FI_GPU_MEMORY_CUR_BANDWIDTH

Signed-off-by: Li Ma <li.ma@amd.com>
Change-Id: I453e49937a84777146575f4f5bdd69fd4fe53bfc
2024-12-16 09:43:20 +08:00
Charis Poag 4de2168866 [SWDEV-496693] GPU metrics 1.7
Changes:
    - Added new GPU metrics:
      1) XGMI link status - Up/Down; 1 = up; 0 = down
      2) Graphics clocks below host limit (per XCP)
         accumulators -> used to help calculate a violation status
      3) VRAM max bandwidth at max memory clock
    - Updated rocm-smi --showmetrics to include new metrics.
    Units/values reflect as indicated by driver, may differ
    from AMD SMI or other ROCm SMI interfaces which
    use these fields.
    - N/A fields means the device does not support providing this
    data.

Change-Id: I17b313345f15070a76b3a30dd8d5645d212d601b
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2024-12-15 16:48:13 -05:00
David Galiffi b29cfac106 Update to use rocprofiler-sdk (#55)
- Renames the CMake option "ROCPROFSYS_USE_HIP" to "ROCPROFSYS_USE_ROCM"
- Remove the "ROCPROFSYS_USE_ROCM_SMI option. Controlled with the "ROCPROFSYS_USE_ROCM" option, instead.
   - Runtime configuration can still toggle ROCPROFSYS_USE_ROCM_SMI to disable the sampling.
- Rename ROCPROFSYS_HIP_VERSION macro to ROCPROFSYS_ROCM_VERSION and remove blocks for `ROCPROFSYS_ROCM_VERSION < 60000`
- Remove ROCPROFSYS_USE_ROCTRACER and ROCPROFSYS_USE_ROCPROFILER
- Update test cases
- Update docker files and workflows to install cmake 3.21, which is required for the rocprofiler-sdk findPackage script.
- Removed rocm-6.2 from workflows due to a rocprofiler-sdk API change. 

[ROCm/rocprofiler-systems commit: 88aa2d3cbe]
2024-12-13 18:48:39 -05:00
David Galiffi 88aa2d3cbe Update to use rocprofiler-sdk (#55)
- Renames the CMake option "ROCPROFSYS_USE_HIP" to "ROCPROFSYS_USE_ROCM"
- Remove the "ROCPROFSYS_USE_ROCM_SMI option. Controlled with the "ROCPROFSYS_USE_ROCM" option, instead.
   - Runtime configuration can still toggle ROCPROFSYS_USE_ROCM_SMI to disable the sampling.
- Rename ROCPROFSYS_HIP_VERSION macro to ROCPROFSYS_ROCM_VERSION and remove blocks for `ROCPROFSYS_ROCM_VERSION < 60000`
- Remove ROCPROFSYS_USE_ROCTRACER and ROCPROFSYS_USE_ROCPROFILER
- Update test cases
- Update docker files and workflows to install cmake 3.21, which is required for the rocprofiler-sdk findPackage script.
- Removed rocm-6.2 from workflows due to a rocprofiler-sdk API change.
2024-12-13 18:48:39 -05:00
David Galiffi 417d22ee3e Update VERSION to 0.2.0
[ROCm/rocprofiler-systems commit: d3725df816]
2024-12-13 17:35:22 -05:00
David Galiffi d3725df816 Update VERSION to 0.2.0 2024-12-13 17:35:22 -05:00
Peter Park 95b8f8fdd9 docs: Fix docutils warnings (#59)
* fix typo

* fix `Lexing literal_block` docutils warning

* fix `Title underline too short` docutils warning

* use consistent file type

* fix `Malformed table` error

* improve index.rst and front-load TOC

[ROCm/rocprofiler-systems commit: 39468e8867]
2024-12-13 15:59:07 -05:00
Peter Park 39468e8867 docs: Fix docutils warnings (#59)
* fix typo

* fix `Lexing literal_block` docutils warning

* fix `Title underline too short` docutils warning

* use consistent file type

* fix `Malformed table` error

* improve index.rst and front-load TOC
2024-12-13 15:59:07 -05:00
David Galiffi ab379457a1 Allow ElfUtils_CONFIG_OPTIONS to provide additional configuration options (#58)
Signed-off-by: David Galiffi <David.Galiffi@amd.com>

[ROCm/rocprofiler-systems commit: c76fb0cb81]
2024-12-13 14:52:10 -05:00
David Galiffi c76fb0cb81 Allow ElfUtils_CONFIG_OPTIONS to provide additional configuration options (#58)
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
2024-12-13 14:52:10 -05:00
Elwazir, Ammar 590f2a1cd0 Changing Mi300 Names (#69)
* Changing Mi300 Names

Making Mi300 names more specific:
Adding multiple type to differentiate between Mi300X, Mi300A, Mi325X

* Enable Mi300A PC Sampling testing
2024-12-13 12:19:23 -06:00