Giovanni Lenzi Baraldi
099ac7c72d
* Enabling codeobj and thread trace samples * Updating aqlprofile_v2 header * Codeobj and thread trace samples with output log files * Fixing clang format * Cmake formatting * Adding coverage to codeobj * Comment trace sample * Adding ATT Parser API * Fixing forwarding to aqlprofile * Clang formatting * Clang tidy * Adding option to print memory kernels * Clang format * Remove default from switch case * Separating client/main on codeobj sample for ASAn * Formatting * Gbaraldi/att tool rebase (#801) * Enabling codeobj and thread trace samples * Updating aqlprofile_v2 header * Codeobj and thread trace samples with output log files * Fixing clang format * Cmake formatting * Adding coverage to codeobj * Comment trace sample * Removing python from workflow * Adding ATT Parser API * Fixing forwarding to aqlprofile * Clang formatting * Clang tidy * Adding option to print memory kernels * Clang format * Remove default from switch case * Separating client/main on codeobj sample for ASAn * Formatting * Enabling codeobj and thread trace samples * Updating aqlprofile_v2 header * Codeobj and thread trace samples with output log files * Fixing clang format * Cmake formatting * Adding coverage to codeobj * Comment trace sample * Adding ATT Parser API * Fixing forwarding to aqlprofile * Clang formatting * Clang tidy * Adding option to print memory kernels * Clang format * Remove default from switch case * Separating client/main on codeobj sample for ASAn * Formatting * Fix codeobj library * Allow thread trace in parallel with other service * Zeroing the HSA signals * Adding exception wrappers in ATT sample * Removed force configure * Remove force configure from ISA decode * Removing codecov flag * Gbaraldi/att tool tests (#828) * Adding tests for codeobj ISA decode * Adding ATT tests * Adding ATT integration tests * Formatting * Changing codeobj binary extension * Renaming codeobj library spaces * Fixing samples * Formatting * Formatting * Fixing int test * Fixing linker error * Fixing memory fault * Moving kernel ot inside namespace * ASAN linking fix * Removing unecessary headers * Formatting * Fixing target_cu * Remove codeobj binary * Revert "Remove codeobj binary" This reverts commit 7d286f89d8096bc36925cd79cd742a5e6d10d179. * Enable memory snapshot * adding comgr --------- Co-authored-by: Ammar ELWazir <ammar.elwazir@amd.com>
ROCprofiler-SDK: Application Profiling, Tracing, and Performance Analysis
Note: rocprofiler-sdk is currently not supported as part of the public ROCm software stack and is only distributed as a beta
release to customers.
Overview
ROCProfiler-SDK is AMD’s new and improved tooling infrastructure, providing a hardware-specific low-level performance analysis interface for profiling and tracing GPU compute applications. To see what's changed Click Here
GPU Metrics
- GPU hardware counters
- HIP API tracing
- HIP kernel tracing
- HSA API tracing
- HSA operation tracing
- Marker(ROCtx) tracing
Tool Support
rocprofv3 is the command line tool built using the rocprofiler-sdk library and shipped with the ROCm stack. To see details on the command line options of rocprofv3, please see rocprofv3 user guide Click Here
Documentation
We make use of doxygen to generate API documentation automatically. The generated document can be found in the following path:
<ROCM_PATH>/share/html/rocprofiler-sdk
ROCM_PATH by default is /opt/rocm It can be set by the user in different locations if needed.
Build and Installation
git clone https://git@github.com:ROCm/rocprofiler-sdk.git rocprofiler-sdk-source
cmake \
-B rocprofiler-sdk-build \
-D ROCPROFILER_BUILD_TESTS=ON \
-D ROCPROFILER_BUILD_SAMPLES=ON \
-D ROCPROFILER_BUILD_DOCS=ON \
-D CMAKE_INSTALL_PREFIX=/opt/rocm \
rocprofiler-sdk-source
cmake --build rocprofiler-sdk-build --target all --parallel 8
To install ROCprofiler, run:
cmake --build rocprofiler-sdk-build --target install
Please see the detailed section on build and installation here: Click Here
Support
Please report in the Github Issues.
Limitations
- Individual XCC mode is not supported.