rocm-systems

Files

T

Laurent Morichetti 26bb13ade0 SWDEV-318682: Using roctx to rename long kernel names to shorter ones.

To enable this feature use the --roctx-rename rocprof option. This
implementation records all messages received in roctxPush calls and
use them to replace corresponding kernel names.

Tested with the following HIP program:

\#include <hip/hip_runtime.h>
\#include <roctracer/roctx.h>

__global__ void
ThisIsALongKernelName ()
{
}

int
main (int argc, char* argv[])
{
  hipSetDevice (0);

  // Not in a roctx range.
  ThisIsALongKernelName<<<1, 1>>> ();

  roctxRangePush ("A");
  // In a simple first level roctx range.
  ThisIsALongKernelName<<<1, 1>>> ();
  roctxRangePop ();

  roctxRangePush ("B");
  roctxRangePush ("C");
  // In a nested roctx range.
  ThisIsALongKernelName<<<1, 1>>> ();
  roctxRangePop ();
  roctxRangePop ();

  roctxRangePush ("D");
  roctxRangePush ("E");
  roctxRangePop ();
  // In a first level roctx range, but after a nested range.
  ThisIsALongKernelName<<<1, 1>>> ();
  roctxRangePop ();

  hipDeviceSynchronize ();
  return 0;
}

Change-Id: I629312234468daff8b017caa5cb0773707d98cce


[ROCm/rocprofiler commit: 1078a088e9]

2022-04-07 18:03:03 -07:00

bin

SWDEV-318682: Using roctx to rename long kernel names to shorter ones.

2022-04-07 18:03:03 -07:00

cmake_modules

replace the set of CMAKE_SHARED_LINKER_FLAGS with add_link_options.

2022-02-03 12:31:45 -05:00

DEBIAN

rocprofiler: Consider apt upgrade operation check in package scripts.

2022-03-21 23:38:14 -04:00

doc

latest documentation revision

2018-06-15 10:53:06 -05:00

inc

kernel objects dumping

2020-09-11 10:01:54 -05:00

RPM

File Reorganization with backward compatibility

2022-03-05 14:49:41 -08:00

src

SWDEV-283957 : Emit correct group name for rocprof split metrics

2022-03-01 11:16:00 -06:00

test

SWDEV-324379 : Expose FP64 and FP32 performance counters on on AMD profilers for MI200

2022-03-17 14:06:24 -07:00

_clang-format

ROC profiler prototype sources importing

2017-11-09 17:26:19 -06:00

build.sh

optimization mechanism fix: correct tracker handler; kernel name query on completion;

2020-08-03 23:34:49 -05:00

CMakeLists.txt

File Reorganization with backward compatibility

2022-03-05 14:49:41 -08:00

LICENSE

SWDEV-318551: Adding License file for profiler

2022-01-26 13:38:42 -05:00

Readme.txt

cleanup after separating for staging and npi branches

2021-04-08 20:37:47 +00:00

rocprofiler-backward-compat.cmake

File Reorganization with backward compatibility

2022-03-05 14:49:41 -08:00

Readme.txt

ROC Profiler library.
Profiling with metrics and traces based on perfcounters (PMC) and traces (SPM).
Implementation is based on AqlProfile HSA extension.
Library supports GFX8/GFX9.

The library source tree:
 - doc  - Documentation
 - inc/rocprofiler.h - Library public API
 - src  - Library sources
   - core - Library API sources
   - util - Library utils sources
   - xml - XML parser
 - test - Library test suite
   - ctrl - Test controll
   - util - Test utils
   - simple_convolution - Simple convolution test kernel

Build environment:

$ export CMAKE_PREFIX_PATH=<path to hsa-runtime includes>:<path to hsa-runtime library>
$ export CMAKE_BUILD_TYPE=<debug|release> # release by default
$ export CMAKE_DEBUG_TRACE=1 # 1 to enable debug tracing

To build with the current installed ROCM:

$ cd .../rocprofiler
$ export CMAKE_PREFIX_PATH=/opt/rocm/include/hsa:/opt/rocm
$ mkdir build
$ cd build
$ cmake ..
$ make

To run the test:

$ cd .../rocprofiler/build
$ export LD_LIBRARY_PATH=.:<other paths> # paths to ROC profiler and oher libraries
$ export HSA_TOOLS_LIB=librocprofiler64.so # ROC profiler library loaded by HSA runtime
$ export ROCP_TOOL_LIB=test/libtool.so # tool library loaded by ROC profiler
$ export ROCP_METRICS=metrics.xml # ROC profiler metrics config file
$ export ROCP_INPUT=input.xml # input file for the tool library
$ export ROCP_OUTPUT_DIR=./ # output directory for the tool library, for metrics results file 'results.txt' and trace files
$ <your test>

Internal 'simple_convolution' test run script:
$ cd .../rocprofiler/build
$ run.sh

To enabled error messages logging to '/tmp/rocprofiler_log.txt':

$ export ROCPROFILER_LOG=1

To enable verbose tracing:

$ export ROCPROFILER_TRACE=1