Ammar ELWazir 2905fb5e95 Update run-ci.py (#641)
* Temp: Fixing node id

* source formatting (clang-format v11) (#709)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Using logical node id

* Update agent.cpp

* Update agent.cpp

* Python formatting

* Update run-ci.py

* Update run-ci.py

* Update continuous_integration.yml

* Update continuous_integration.yml

running directly using the prepared runner container

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update run-ci.py

* Clean up

* Fixing install paths

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Update continuous_integration.yml

* Fixing GPU Agents Test Validation

* python formatting (black) (#712)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Fixing the issue with rocclr detected kernels __amd_rocclr_.*

* python formatting (black) (#713)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Fixing the issue with rocclr detected kernels __amd_rocclr_.*

* Fixing static number of async copies and using hsa_api instead for validation

* python formatting (black) (#714)

Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>

* Increasing the time limit for waiting on active signals

* Update continuous_integration.yml

* Update async_copy.cpp

* Update CMakeLists.txt

* changing node id to logical node id in rocprofv3

* Update tool.cpp

* testing async mem copy signal decrement

* Update logging.cpp

* Update validate.py

---------

Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler1.amd.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: ammarwa <3832908+ammarwa@users.noreply.github.com>
Co-authored-by: Ammar ELWazir <aelwazir@rocprofiler2.amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
2024-04-02 01:39:24 -05:00
2024-04-02 01:39:24 -05:00
2024-04-02 01:39:24 -05:00
2024-04-02 01:39:24 -05:00
2023-08-24 19:19:48 -05:00
2023-08-08 18:39:01 -05:00
2024-01-24 16:32:54 -06:00
2023-11-14 10:58:33 -06:00
2023-08-08 18:39:01 -05:00
2024-03-07 21:05:16 -06:00
2023-11-16 03:21:39 -06:00
2024-03-14 04:40:58 -05:00

ROCprofiler-SDK: Application Profiling, Tracing, and Performance Analysis


Note: rocprofiler-sdk is currently not supported as part of public ROCm software stack and only distributed as a beta
release to customers.


Overview

ROCProfiler-SDK is AMDs new and improved tooling infrastructure that provides a hardware specific low level performance analysis interface for the profiling and the tracing of GPU compute applications. To see whats 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 that is built using rocprofiler-sdk library and shipped with 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 automatically generate API documentation. 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 location if needed.

Build and Installation

git clone https://git@github.com:ROCm/rocprofiler-sdk-internal.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 detailed section on build and installation here: click

Support

Please report in the Github Issues.

Limitations

  • Individual xcc mode is not supported.
S
Описание
No description provided
Readme 282 MiB
Languages
C++ 67.5%
C 20.6%
Python 6.6%
CMake 3.4%
Shell 0.6%
Разное 1.1%