Ammar ELWazir e4569c41fe SWDEV-295522: Fixing Performance Issue
Removing DEBUG_TRACES and the unnecessary use of roctracer_op_string, made the MS app reporting 78 to 81 stable samples per second, depending on the type of the trace, while the main app without rocprof reports 100 to 106. More detailed numbers will be posted in the ticket.

Change-Id: Ifbc529278cea54dd23e6086aa9b9ea2df952d5dd
2022-04-22 18:51:49 -04:00
2022-04-19 09:30:45 -07:00
2018-05-10 13:19:10 -05:00
2022-04-19 09:30:45 -07:00
2022-04-19 09:30:45 -07:00
2022-04-19 09:30:45 -07:00
2022-04-20 22:00:59 -07:00
2022-04-19 09:30:45 -07:00
2022-04-15 20:34:21 +00:00
2022-04-19 09:30:45 -07:00

ROC-tracer

  • ROC-tracer library: Runtimes Generic Callback/Activity APIs

    The goal of the implementation is to provide a generic independent from specific runtime profiler to trace API and asynchronous activity.

    The API provides functionality for registering the runtimes API callbacks and asynchronous activity records pool support.

  • ROC-TX library: Code Annotation Events API

    Includes API for:

    • roctxMark
    • roctxRangePush
    • roctxRangePop

Usage

rocTracer API

To use the rocTracer API you need the API header and to link your application with roctracer .so library:

  • /opt/rocm/roctracer/include/roctracer.h

    API header.

  • /opt/rocm/lib/libroctracer64.so

    .so library.

rocTX API

To use the rocTX API you need the API header and to link your application with roctx .so library:

  • /opt/rocm/roctracer/include/roctx.h

    API header.

  • /opt/rocm/lib/libroctx64.so

    .so library.

Library source tree

  • doc

    Documentation.

  • inc

    Include header files.

    • roctracer.h

      rocTacer library public API header.

    • roctx.h

      rocTX library public API header.

  • src

    Library sources.

    • core

      rocTracer library API sources.

    • roctx

      rocTX library API sources.

    • util

      Library utils sources.

  • test

    Test suit.

    • MatrixTranspose

      Test based on HIP MatrixTranspose sample.

Documentation

Build and run tests

  • ROCm is required

  • Python modules requirements: CppHeaderParser, argparse.

    To install:

    pip3 install CppHeaderParser argparse
    
  • Clone development branch of roctracer:

    git clone -b amd-master https://github.com/ROCm-Developer-Tools/roctracer
    
  • To build roctracer library:

    cd <your path>/roctracer
    mkdir build && cd build
    cmake -DCMAKE_PREFIX_PATH=/opt/rocm -DCMAKE_INSTALL_PREFIX=/opt/rocm ..
    make
    
  • To build and run test:

    make mytest
    run.sh
    

Installation

Install by:

make install

or:

make package && dpkg -i *.deb
S
Opis
No description provided
Readme 282 MiB
Languages
C++ 67.5%
C 20.6%
Python 6.6%
CMake 3.4%
Shell 0.6%
Pozostałe 1.1%