mirror of
https://github.com/ROCm/ROCm.git
synced 2026-01-10 15:18:11 -05:00
Compare commits
41 Commits
docs/6.2.1
...
generatede
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
d4d308d981 | ||
|
|
96211cdce8 | ||
|
|
11d65cde71 | ||
|
|
7cd3868ec1 | ||
|
|
f83a474813 | ||
|
|
b352e231cc | ||
|
|
8b63092333 | ||
|
|
7843d46e47 | ||
|
|
b61c291302 | ||
|
|
28c5e16bf6 | ||
|
|
d7e3a38e2c | ||
|
|
f86f275cf1 | ||
|
|
956d62e621 | ||
|
|
4f04f2dc2e | ||
|
|
b1d47db155 | ||
|
|
2d86e0ffca | ||
|
|
0c4a7bb77e | ||
|
|
ccb8e6269c | ||
|
|
c595960b96 | ||
|
|
74c7d7d31b | ||
|
|
e691307d60 | ||
|
|
681a98a59d | ||
|
|
17ad66f3d4 | ||
|
|
5d1204ecdc | ||
|
|
c542ee1363 | ||
|
|
ed4ffafec5 | ||
|
|
3fe8e17e56 | ||
|
|
fa31ee35e3 | ||
|
|
4b737a1cda | ||
|
|
ff0d863a0d | ||
|
|
b203a7cb74 | ||
|
|
7d0e1aa06c | ||
|
|
920efcd0b1 | ||
|
|
ff26ae7c18 | ||
|
|
f9f92037cb | ||
|
|
3ab3782a7f | ||
|
|
516b6c8ebc | ||
|
|
c5d0fb8477 | ||
|
|
3dc6d89297 | ||
|
|
7c0c197c91 | ||
|
|
7963d27853 |
@@ -8,20 +8,21 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- git
|
||||
- cmake
|
||||
- ninja-build
|
||||
- git
|
||||
- libdnnl-dev
|
||||
- libdrm-dev
|
||||
- libnuma-dev
|
||||
- python3-pip
|
||||
- python3-venv
|
||||
- libtbb-dev
|
||||
- nlohmann-json3-dev
|
||||
- libmsgpack-dev
|
||||
- libsqlite3-dev
|
||||
- libnuma-dev
|
||||
- libprotobuf-dev
|
||||
- libsqlite3-dev
|
||||
- libtbb-dev
|
||||
- ninja-build
|
||||
- nlohmann-json3-dev
|
||||
- protobuf-compiler
|
||||
- python3-pip
|
||||
- python3-pybind11
|
||||
- python3-venv
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
@@ -50,6 +51,26 @@ parameters:
|
||||
- rocminfo
|
||||
- rocMLIR
|
||||
- rocprofiler-register
|
||||
- roctracer
|
||||
- name: rocmTestDependencies
|
||||
type: object
|
||||
default:
|
||||
- aomp
|
||||
- aomp-extras
|
||||
- clr
|
||||
- composable_kernel
|
||||
- hipBLAS
|
||||
- hipBLAS-common
|
||||
- hipBLASLt
|
||||
- llvm-project
|
||||
- MIOpen
|
||||
- rocm-cmake
|
||||
- ROCR-Runtime
|
||||
- rocBLAS
|
||||
- rocminfo
|
||||
- rocMLIR
|
||||
- rocprofiler-register
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: AMDMIGraphX
|
||||
@@ -95,17 +116,81 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DGPU_TARGETS=$(JOB_GPU_TARGET)
|
||||
-DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
|
||||
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
|
||||
-DHALF_INCLUDE_DIR=$(Agent.BuildDirectory)/rocm/include
|
||||
-DMIGRAPHX_USE_COMPOSABLEKERNEL=OFF
|
||||
-DBUILD_TESTING=ON
|
||||
-GNinja
|
||||
# REFERENCE: https://github.com/ROCm/composable_kernel/issues/782
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
parameters:
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
|
||||
- job: AMDMIGraphX_testing
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: MIGRAPHX_TRACE_BENCHMARKING
|
||||
value: 1
|
||||
pool: $(JOB_TEST_POOL)
|
||||
workspace:
|
||||
clean: all
|
||||
strategy:
|
||||
matrix:
|
||||
gfx942:
|
||||
JOB_GPU_TARGET: gfx942
|
||||
JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
|
||||
steps:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
|
||||
parameters:
|
||||
aptPackages: ${{ parameters.aptPackages }}
|
||||
pipModules: ${{ parameters.pipModules }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
|
||||
parameters:
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
# half version should be fixed to 5.6.0
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencySource: fixed
|
||||
fixedComponentName: half
|
||||
fixedPipelineIdentifier: ${{ variables.HALF560_PIPELINE_ID }}
|
||||
skipLibraryLinking: true
|
||||
skipLlvmSymlink: true
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmTestDependencies }}
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
# CI case: download latest default branch build
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
- task: CMake@1
|
||||
displayName: MIGraphXTest CMake Flags
|
||||
inputs:
|
||||
cmakeArgs: >-
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DGPU_TARGETS=$(JOB_GPU_TARGET)
|
||||
-DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
|
||||
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
|
||||
-DHALF_INCLUDE_DIR=$(Agent.BuildDirectory)/rocm/include
|
||||
-DBUILD_TESTING=ON
|
||||
-DMIGRAPHX_ENABLE_C_API_TEST=ON
|
||||
..
|
||||
- task: Bash@3
|
||||
displayName: Build and run MIGraphX tests
|
||||
inputs:
|
||||
targetType: inline
|
||||
workingDirectory: build
|
||||
script: make -j$(nproc) check
|
||||
|
||||
@@ -8,15 +8,23 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- software-properties-common
|
||||
- python3-pip
|
||||
- cmake
|
||||
- ninja-build
|
||||
- libsqlite3-dev
|
||||
- libbz2-dev
|
||||
- nlohmann-json3-dev
|
||||
- libgtest-dev
|
||||
- libdrm-dev
|
||||
- libeigen3-dev
|
||||
- libgmock-dev
|
||||
- libgtest-dev
|
||||
- libsqlite3-dev
|
||||
- libstdc++-12-dev
|
||||
- ninja-build
|
||||
- nlohmann-json3-dev
|
||||
- python3-pip
|
||||
- software-properties-common
|
||||
- zstd
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
- cget
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
@@ -35,6 +43,24 @@ parameters:
|
||||
- clr
|
||||
- rocminfo
|
||||
- roctracer
|
||||
- name: rocmTestDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- composable_kernel
|
||||
- half
|
||||
- hipBLAS
|
||||
- hipBLAS-common
|
||||
- hipBLASLt
|
||||
- llvm-project
|
||||
- rocBLAS
|
||||
- rocm-cmake
|
||||
- rocminfo
|
||||
- rocMLIR
|
||||
- ROCR-Runtime
|
||||
- rocprofiler-register
|
||||
- rocRAND
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: MIOpen
|
||||
@@ -54,18 +80,16 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
|
||||
parameters:
|
||||
aptPackages: ${{ parameters.aptPackages }}
|
||||
pipModules: ${{ parameters.pipModules }}
|
||||
# The default boost library from apt is 1.74, which does not satisfy MIOpen's build requirement (1.79+)
|
||||
# Upgrade boost from apt by following https://launchpad.net/~mhier/+archive/ubuntu/libboost-latest
|
||||
- task: Bash@3
|
||||
displayName: 'update boost version'
|
||||
displayName: 'Install Boost 1.83'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: sudo add-apt-repository ppa:mhier/libboost-latest -y
|
||||
- task: Bash@3
|
||||
displayName: 'install boost'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: sudo apt-get --yes install libboost1.83-dev libboost-system1.83-dev libboost-filesystem1.83-dev
|
||||
script: |
|
||||
sudo add-apt-repository ppa:mhier/libboost-latest -y
|
||||
sudo apt-get --yes install libboost1.83-dev libboost-system1.83-dev libboost-filesystem1.83-dev
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
@@ -94,3 +118,110 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
parameters:
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
|
||||
- job: MIOpen_testing
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: $(JOB_TEST_POOL)
|
||||
workspace:
|
||||
clean: all
|
||||
strategy:
|
||||
matrix:
|
||||
gfx942:
|
||||
JOB_GPU_TARGET: gfx942
|
||||
JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
|
||||
steps:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
|
||||
parameters:
|
||||
aptPackages: ${{ parameters.aptPackages }}
|
||||
pipModules: ${{ parameters.pipModules }}
|
||||
- task: Bash@3
|
||||
displayName: 'Install Boost 1.83'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
sudo add-apt-repository ppa:mhier/libboost-latest -y
|
||||
sudo apt-get --yes install libboost1.83-dev libboost-system1.83-dev libboost-filesystem1.83-dev
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
|
||||
parameters:
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmTestDependencies }}
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
# MIOpen depends on a specific version of frugally-deep which is forked here: https://github.com/ROCm/frugally-deep
|
||||
# https://github.com/ROCm/frugally-deep/blob/master/INSTALL.md
|
||||
- task: Bash@3
|
||||
displayName: Add Python site-packages binaries to path
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
USER_BASE=$(python3 -m site --user-base)
|
||||
echo "##vso[task.prependpath]$USER_BASE/bin"
|
||||
- task: Bash@3
|
||||
displayName: Install FunctionalPlus
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: cget install Dobiasd/FunctionalPlus
|
||||
- task: Bash@3
|
||||
displayName: Remove Python site-packages binaries from path
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
USER_BASE=$(python3 -m site --user-base)
|
||||
echo "##vso[task.setvariable variable=PATH]$(echo $PATH | sed -e 's;:$USER_BASE/bin;;' -e 's;^/;;' -e 's;/$;;')"
|
||||
- task: Bash@3
|
||||
displayName: git clone frugally-deep
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: git clone https://github.com/ROCm/frugally-deep --depth=1 --shallow-submodules
|
||||
workingDirectory: $(Build.SourcesDirectory)
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
componentName: frugally-deep
|
||||
cmakeBuildDir: $(Build.SourcesDirectory)/frugally-deep/build
|
||||
installDir: $(Build.SourcesDirectory)/bin
|
||||
extraBuildFlags: -DCMAKE_PREFIX_PATH=$(Build.SourcesDirectory)/cget/cget/pkg/Dobiasd__FunctionalPlus/install
|
||||
- task: CMake@1
|
||||
displayName: 'MIOpen Test CMake Flags'
|
||||
inputs:
|
||||
cmakeArgs: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Build.SourcesDirectory)/bin;$(Build.SourcesDirectory)/cget/cget/pkg/Dobiasd__FunctionalPlus/install
|
||||
-DCMAKE_INSTALL_PREFIX=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DMIOPEN_BACKEND=HIP
|
||||
-DMIOPEN_TEST_FLAGS=" --disable-verification-cache"
|
||||
-DCMAKE_BUILD_TYPE=release
|
||||
-DBUILD_DEV=OFF
|
||||
-DMIOPEN_USE_MLIR=ON
|
||||
-DMIOPEN_GPU_SYNC=OFF
|
||||
..
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
|
||||
parameters:
|
||||
componentName: MIOpen
|
||||
testExecutable: 'CTEST_PARALLEL_LEVEL=4 make -j$(nproc) check'
|
||||
testParameters: ''
|
||||
reloadAMDGPU: true
|
||||
testPublishResults: false
|
||||
- task: Bash@3
|
||||
condition: always()
|
||||
displayName: Clean up Boost 1.83
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
sudo apt -y autoremove libboost1.83-dev libboost-system1.83-dev libboost-filesystem1.83-dev
|
||||
sudo add-apt-repository --remove ppa:mhier/libboost-latest -y
|
||||
sudo apt update
|
||||
|
||||
@@ -8,15 +8,21 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- libelf-dev
|
||||
- g++
|
||||
- libdrm-dev
|
||||
- libelf-dev
|
||||
- libnuma-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- llvm-project
|
||||
- rocprofiler-register
|
||||
- name: rocmTestDependencies
|
||||
type: object
|
||||
default:
|
||||
- llvm-project
|
||||
- rocm_smi_lib
|
||||
- rocprofiler-register
|
||||
|
||||
jobs:
|
||||
- job: ROCR_Runtime
|
||||
@@ -50,3 +56,120 @@ jobs:
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DBUILD_SHARED_LIBS=ON
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
- job: ROCR_Runtime_testing
|
||||
dependsOn: ROCR_Runtime
|
||||
condition: succeeded()
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: $(JOB_TEST_POOL)
|
||||
workspace:
|
||||
clean: all
|
||||
strategy:
|
||||
matrix:
|
||||
gfx942:
|
||||
JOB_GPU_TARGET: gfx942
|
||||
JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
|
||||
steps:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
|
||||
parameters:
|
||||
aptPackages: ${{ parameters.aptPackages }}
|
||||
- task: Bash@3
|
||||
displayName: Install libhwloc5
|
||||
inputs:
|
||||
targetType: 'inline'
|
||||
script: |
|
||||
wget http://ftp.us.debian.org/debian/pool/main/h/hwloc/libhwloc5_1.11.12-3_amd64.deb
|
||||
wget http://ftp.us.debian.org/debian/pool/main/h/hwloc/libhwloc-dev_1.11.12-3_amd64.deb
|
||||
sudo apt install -y --allow-downgrades ./libhwloc5_1.11.12-3_amd64.deb ./libhwloc-dev_1.11.12-3_amd64.deb
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
|
||||
parameters:
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmTestDependencies }}
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
- task: Bash@3
|
||||
displayName: Build kfdtest
|
||||
inputs:
|
||||
targetType: 'inline'
|
||||
workingDirectory: $(Build.SourcesDirectory)/libhsakmt/tests/kfdtest
|
||||
script: |
|
||||
mkdir build && cd build
|
||||
cmake -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm ..
|
||||
make
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
|
||||
parameters:
|
||||
componentName: kfdtest
|
||||
testExecutable: BIN_DIR=$(Build.SourcesDirectory)/libhsakmt/tests/kfdtest/build ./run_kfdtest.sh
|
||||
testParameters: '-p core --gtest_output=xml:./test_output.xml --gtest_color=yes'
|
||||
testDir: $(Build.SourcesDirectory)/libhsakmt/tests/kfdtest/scripts
|
||||
- task: Bash@3
|
||||
displayName: Build rdmatest app
|
||||
inputs:
|
||||
targetType: 'inline'
|
||||
workingDirectory: $(Build.SourcesDirectory)/libhsakmt/tests/rdma/simple/app
|
||||
script: |
|
||||
cmake -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm -DLIBHSAKMT_PATH=$(Agent.BuildDirectory)/rocm -DDRM_AMDGPU_INCLUDE_DIRS=$(Agent.BuildDirectory)/rocm/include .
|
||||
cmake --build .
|
||||
- task: Bash@3
|
||||
displayName: Build rdmatest driver
|
||||
inputs:
|
||||
targetType: 'inline'
|
||||
workingDirectory: $(Build.SourcesDirectory)/libhsakmt/tests/rdma/simple/drv
|
||||
script: |
|
||||
sed -i 's/HSAKMT_PAGE_SHIFT/PAGE_SHIFT/g' amdp2ptest.c
|
||||
sed -i 's/"MIT"/"GPL"/' amdp2ptest.c
|
||||
RDMA_HEADER_DIR=/usr/src/amdgpu-*/include make all
|
||||
- task: Bash@3
|
||||
displayName: Install rdmatest driver
|
||||
inputs:
|
||||
targetType: 'inline'
|
||||
workingDirectory: $(Build.SourcesDirectory)/libhsakmt/tests/rdma/simple/drv
|
||||
script: |
|
||||
sudo rmmod amdp2ptest.ko
|
||||
sudo insmod amdp2ptest.ko
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
|
||||
parameters:
|
||||
componentName: rdmatest
|
||||
testExecutable: yes | ./rdma_test
|
||||
testParameters: ''
|
||||
testDir: $(Build.SourcesDirectory)/libhsakmt/tests/rdma/simple/app
|
||||
testPublishResults: false
|
||||
- task: Bash@3
|
||||
displayName: Build rocrtst
|
||||
inputs:
|
||||
targetType: 'inline'
|
||||
workingDirectory: $(Build.SourcesDirectory)/rocrtst/suites/test_common
|
||||
script: |
|
||||
sudo rm -rf $(Agent.BuildDirectory)/external/llvm-project
|
||||
mkdir -p $(Agent.BuildDirectory)/external/llvm-project/clang/lib
|
||||
sudo ln -s $(Agent.BuildDirectory)/rocm/llvm/lib/clang/20/include $(Agent.BuildDirectory)/external/llvm-project/clang/lib/Headers
|
||||
mkdir build && cd build
|
||||
cmake .. \
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm \
|
||||
-DTARGET_DEVICES=$(JOB_GPU_TARGET) \
|
||||
-DROCM_DIR=$(Agent.BuildDirectory)/rocm \
|
||||
-DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm/bin \
|
||||
-DOPENCL_DIR=$(Agent.BuildDirectory)/rocm/llvm/bin
|
||||
make
|
||||
make rocrtst_kernels
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
|
||||
parameters:
|
||||
componentName: rocrtst
|
||||
testExecutable: ./rocrtst64
|
||||
testParameters: '--gtest_filter="-rocrtstNeg.Memory_Negative_Tests" --gtest_output=xml:./test_output.xml --gtest_color=yes'
|
||||
testDir: $(Build.SourcesDirectory)/rocrtst/suites/test_common/build/$(JOB_GPU_TARGET)
|
||||
|
||||
@@ -43,6 +43,7 @@ parameters:
|
||||
- rocprofiler-register
|
||||
- ROCR-Runtime
|
||||
- rocRAND
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: ROCmValidationSuite
|
||||
|
||||
@@ -90,6 +90,8 @@ jobs:
|
||||
-DCMAKE_C_COMPILER_LAUNCHER=ccache
|
||||
-DCMAKE_HIP_FLAGS="-Wno-missing-include-dirs"
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCK_BUILD_JIT_LIB=ON
|
||||
-DCMAKE_POSITION_INDEPENDENT_CODE=ON
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DGPU_TARGETS=$(JOB_GPU_TARGET)
|
||||
-GNinja
|
||||
|
||||
@@ -89,7 +89,7 @@ jobs:
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
|
||||
- job: hip_tests_testing
|
||||
timeoutInMinutes: 180
|
||||
timeoutInMinutes: 240
|
||||
dependsOn: hip_tests
|
||||
condition: succeeded()
|
||||
variables:
|
||||
@@ -130,6 +130,7 @@ jobs:
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
sudo rm -rf /opt/rocm
|
||||
sudo mkdir -p /opt/rocm/bin
|
||||
sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rocm_agent_enumerator /opt/rocm/bin/rocm_agent_enumerator
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
|
||||
|
||||
@@ -42,6 +42,7 @@ parameters:
|
||||
- ROCR-Runtime
|
||||
- rocSOLVER
|
||||
- rocSPARSE
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: hipSOLVER
|
||||
|
||||
@@ -37,6 +37,7 @@ parameters:
|
||||
- rocprofiler-register
|
||||
- ROCR-Runtime
|
||||
- rocSPARSE
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: hipSPARSE
|
||||
|
||||
@@ -117,4 +117,4 @@ jobs:
|
||||
parameters:
|
||||
componentName: hipTensor
|
||||
testDir: '$(Agent.BuildDirectory)/rocm/bin/hiptensor'
|
||||
testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
|
||||
testParameters: '-E ".*-extended" -VV --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
|
||||
|
||||
141
.azuredevops/components/omnitrace.yml
Normal file
141
.azuredevops/components/omnitrace.yml
Normal file
@@ -0,0 +1,141 @@
|
||||
# largely referenced from: https://github.com/ROCm/omnitrace/blob/main/.github/workflows/ubuntu-jammy.yml
|
||||
parameters:
|
||||
- name: checkoutRepo
|
||||
type: string
|
||||
default: 'self'
|
||||
- name: checkoutRef
|
||||
type: string
|
||||
default: ''
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- autoconf
|
||||
- autotools-dev
|
||||
- bison
|
||||
- build-essential
|
||||
- bzip2
|
||||
- clang
|
||||
- cmake
|
||||
- environment-modules
|
||||
- g++-12
|
||||
- libdrm-dev
|
||||
- libfabric-dev
|
||||
- libiberty-dev
|
||||
- libpapi-dev
|
||||
- libpfm4-dev
|
||||
- libtool
|
||||
- libopenmpi-dev
|
||||
- m4
|
||||
- openmpi-bin
|
||||
- software-properties-common
|
||||
- python3-pip
|
||||
- texinfo
|
||||
- zlib1g-dev
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
- numpy
|
||||
- perfetto
|
||||
- dataclasses
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- llvm-project
|
||||
- rccl
|
||||
- rocm-core
|
||||
- rocm_smi_lib
|
||||
- rocminfo
|
||||
- ROCR-Runtime
|
||||
- rocprofiler
|
||||
- rocprofiler-register
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: omnitrace
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
workspace:
|
||||
clean: all
|
||||
strategy:
|
||||
matrix:
|
||||
gfx942:
|
||||
JOB_GPU_TARGET: gfx942
|
||||
gfx90a:
|
||||
JOB_GPU_TARGET: gfx90a
|
||||
steps:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
|
||||
parameters:
|
||||
aptPackages: ${{ parameters.aptPackages }}
|
||||
pipModules: ${{ parameters.pipModules }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
# CI case: download latest default branch build
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
- task: Bash@3
|
||||
displayName: ROCm symbolic link
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
sudo rm -rf /opt/rocm
|
||||
sudo ln -s $(Agent.BuildDirectory)/rocm /opt/rocm
|
||||
- task: Bash@3
|
||||
displayName: Add ROCm binaries to PATH
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
|
||||
- task: Bash@3
|
||||
displayName: Add ROCm compilers to PATH
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
# build flags reference: https://rocm.docs.amd.com/projects/omnitrace/en/latest/install/install.html
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DOMNITRACE_BUILD_TESTING=ON
|
||||
-DOMNITRACE_BUILD_DYNINST=ON
|
||||
-DOMNITRACE_BUILD_LIBUNWIND=ON
|
||||
-DDYNINST_BUILD_TBB=ON
|
||||
-DDYNINST_BUILD_ELFUTILS=ON
|
||||
-DDYNINST_BUILD_LIBIBERTY=ON
|
||||
-DDYNINST_BUILD_BOOST=ON
|
||||
-DOMNITRACE_USE_PAPI=ON
|
||||
-DOMNITRACE_USE_MPI=ON
|
||||
-DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
|
||||
multithreadFlag: -- -j32
|
||||
- task: Bash@3
|
||||
displayName: Set up omnitrace env
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: source share/omnitrace/setup-env.sh
|
||||
workingDirectory: build
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
|
||||
parameters:
|
||||
componentName: omnitrace
|
||||
- task: Bash@3
|
||||
displayName: Remove ROCm binaries from PATH
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: echo "##vso[task.setvariable variable=PATH]$(echo $PATH | sed -e 's;:$(Agent.BuildDirectory)/rocm/bin;;' -e 's;^/;;' -e 's;/$;;')"
|
||||
- task: Bash@3
|
||||
displayName: Remove ROCm compilers from PATH
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: echo "##vso[task.setvariable variable=PATH]$(echo $PATH | sed -e 's;:$(Agent.BuildDirectory)/rocm/llvm/bin;;' -e 's;^/;;' -e 's;/$;;')"
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
parameters:
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
@@ -43,6 +43,7 @@ parameters:
|
||||
- ROCR-Runtime
|
||||
- rocRAND
|
||||
- rocSPARSE
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: rocALUTION
|
||||
|
||||
@@ -52,6 +52,7 @@ parameters:
|
||||
- rocprofiler-register
|
||||
- rocm_smi_lib
|
||||
- ROCR-Runtime
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: rocBLAS
|
||||
|
||||
@@ -105,7 +105,9 @@ jobs:
|
||||
displayName: ROCm symbolic link
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: sudo ln -s $(Agent.BuildDirectory)/rocm /opt/rocm
|
||||
script: |
|
||||
sudo rm -rf /opt/rocm
|
||||
sudo ln -s $(Agent.BuildDirectory)/rocm /opt/rocm
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
installEnabled: false
|
||||
|
||||
@@ -73,6 +73,13 @@ jobs:
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
- task: Bash@3
|
||||
displayName: 'ROCm symbolic link'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
sudo rm -rf /opt/rocm
|
||||
sudo ln -s $(Agent.BuildDirectory)/rocm /opt/rocm
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
@@ -85,6 +92,27 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
parameters:
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
publish: false
|
||||
- task: Bash@3
|
||||
displayName: Create wheel file
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
export ROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
export HIP_INCLUDE_DIRS=$(Agent.BuildDirectory)/rocm/include/hip
|
||||
python3 setup.py bdist_wheel
|
||||
workingDirectory: $(Build.SourcesDirectory)
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
|
||||
parameters:
|
||||
sourceDir: $(Build.SourcesDirectory)/dist
|
||||
contentsString: '*.whl'
|
||||
targetDir: $(Build.ArtifactStagingDirectory)
|
||||
clean: false
|
||||
- task: PublishPipelineArtifact@1
|
||||
displayName: 'wheel file Publish'
|
||||
retryCountOnTaskFailure: 3
|
||||
inputs:
|
||||
targetPath: $(Build.ArtifactStagingDirectory)
|
||||
|
||||
- job: rocPyDecode_testing
|
||||
dependsOn: rocPyDecode
|
||||
|
||||
@@ -44,6 +44,7 @@ parameters:
|
||||
- rocprofiler-register
|
||||
- ROCR-Runtime
|
||||
- rocSPARSE
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: rocSOLVER
|
||||
|
||||
@@ -40,6 +40,7 @@ parameters:
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- ROCR-Runtime
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: rocSPARSE
|
||||
|
||||
95
.azuredevops/components/rocprofiler-sdk.yml
Normal file
95
.azuredevops/components/rocprofiler-sdk.yml
Normal file
@@ -0,0 +1,95 @@
|
||||
parameters:
|
||||
- name: checkoutRepo
|
||||
type: string
|
||||
default: 'self'
|
||||
- name: checkoutRef
|
||||
type: string
|
||||
default: ''
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- cmake
|
||||
- python3-pip
|
||||
- libdrm-dev
|
||||
- libdw-dev
|
||||
- libelf-dev
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
- black
|
||||
- clang-format
|
||||
- clang-tidy
|
||||
- cmake
|
||||
- cmake-format
|
||||
- dataclasses
|
||||
- numpy
|
||||
- otf2
|
||||
- pandas
|
||||
- perfetto
|
||||
- pycobertura
|
||||
- pytest
|
||||
- pyyaml
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- llvm-project
|
||||
- rccl
|
||||
- rocm-cmake
|
||||
- rocm-core
|
||||
- rocminfo
|
||||
- ROCR-Runtime
|
||||
- rocprofiler-register
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: rocprofilersdk
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
workspace:
|
||||
clean: all
|
||||
strategy:
|
||||
matrix:
|
||||
gfx942:
|
||||
JOB_GPU_TARGET: gfx942
|
||||
gfx90a:
|
||||
JOB_GPU_TARGET: gfx90a
|
||||
steps:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
|
||||
parameters:
|
||||
aptPackages: ${{ parameters.aptPackages }}
|
||||
pipModules: ${{ parameters.pipModules }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
|
||||
parameters:
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
# CI case: download latest default branch build
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DROCPROFILER_BUILD_TESTS=ON
|
||||
-DROCPROFILER_BUILD_SAMPLES=OFF
|
||||
-DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
|
||||
multithreadFlag: -- -j2
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
parameters:
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
@@ -9,8 +9,18 @@ parameters:
|
||||
type: object
|
||||
default:
|
||||
- cmake
|
||||
- libopencv-dev
|
||||
- libsndfile1-dev
|
||||
- libstdc++-12-dev
|
||||
- imagemagick
|
||||
- ninja-build
|
||||
- clang
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
- openpyxl
|
||||
- pandas
|
||||
- sphinx
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
@@ -20,6 +30,18 @@ parameters:
|
||||
- llvm-project
|
||||
- rocminfo
|
||||
- ROCR-Runtime
|
||||
- name: rocmTestDependencies
|
||||
type: object
|
||||
default:
|
||||
- aomp
|
||||
- clr
|
||||
- half
|
||||
- hipTensor
|
||||
- llvm-project
|
||||
- rocm-cmake
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- ROCR-Runtime
|
||||
|
||||
jobs:
|
||||
- job: rpp
|
||||
@@ -68,3 +90,92 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
parameters:
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
|
||||
- job: rpp_testing
|
||||
dependsOn: rpp
|
||||
condition: succeeded()
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: LD_LIBRARY_PATH
|
||||
value: $(Agent.BuildDirectory)/rocm/lib;$(Agent.BuildDirectory)/rocm/llvm/lib
|
||||
pool: $(JOB_TEST_POOL)
|
||||
workspace:
|
||||
clean: all
|
||||
strategy:
|
||||
matrix:
|
||||
gfx942:
|
||||
JOB_GPU_TARGET: gfx942
|
||||
JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
|
||||
steps:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
|
||||
parameters:
|
||||
aptPackages: ${{ parameters.aptPackages }}
|
||||
pipModules: ${{ parameters.pipModules }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
|
||||
parameters:
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
|
||||
parameters:
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmTestDependencies }}
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
${{ if eq(parameters.checkoutRef, '') }}:
|
||||
dependencySource: staging
|
||||
${{ elseif ne(parameters.checkoutRef, '') }}:
|
||||
dependencySource: tag-builds
|
||||
# Dependencies from: https://github.com/ROCm/rpp/blob/develop/utilities/test_suite/README.md
|
||||
- task: Bash@3
|
||||
displayName: Build and install Turbo JPEG
|
||||
inputs:
|
||||
targetType: 'inline'
|
||||
script: |
|
||||
sudo apt-get install nasm
|
||||
sudo apt-get install wget
|
||||
git clone -b 3.0.2 https://github.com/libjpeg-turbo/libjpeg-turbo.git
|
||||
cd libjpeg-turbo
|
||||
mkdir build
|
||||
cd build
|
||||
cmake -DCMAKE_INSTALL_PREFIX=/usr \
|
||||
-DCMAKE_BUILD_TYPE=RELEASE \
|
||||
-DENABLE_STATIC=FALSE \
|
||||
-DCMAKE_INSTALL_DEFAULT_LIBDIR=lib \
|
||||
-DWITH_JPEG8=TRUE \
|
||||
..
|
||||
make -j$nproc
|
||||
sudo make install
|
||||
- task: Bash@3
|
||||
displayName: Build and install Nifti
|
||||
inputs:
|
||||
targetType: 'inline'
|
||||
script: |
|
||||
git clone https://github.com/NIFTI-Imaging/nifti_clib.git
|
||||
cd nifti_clib
|
||||
mkdir build
|
||||
cd build
|
||||
cmake ..
|
||||
sudo make -j$nproc install
|
||||
- task: Bash@3
|
||||
displayName: Build rpp tests
|
||||
inputs:
|
||||
targetType: 'inline'
|
||||
script: |
|
||||
sudo rm -rf /opt/rocm
|
||||
sudo ln -s $(Agent.BuildDirectory)/rocm /opt/rocm
|
||||
mkdir rpp-tests
|
||||
cd rpp-tests
|
||||
cmake /opt/rocm/share/rpp/test \
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++ \
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
|
||||
parameters:
|
||||
componentName: rpp
|
||||
testExecutable: 'export PATH=$(Agent.BuildDirectory)/rocm/llvm/bin:$PATH; CC=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang CMAKE_VERBOSE_MAKEFILE=ON VERBOSE=1 ctest'
|
||||
testDir: 'rpp-tests'
|
||||
- script: sudo rm /opt/rocm
|
||||
|
||||
@@ -62,6 +62,8 @@ parameters:
|
||||
- ffmpeg
|
||||
- libopenblas-dev
|
||||
- liblapack-dev
|
||||
- libswscale-dev
|
||||
- libavformat-dev
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
@@ -87,6 +89,9 @@ parameters:
|
||||
# list for vision
|
||||
- auditwheel
|
||||
- future
|
||||
- pytest
|
||||
- pytest-azurepipelines
|
||||
- pillow
|
||||
# list from https://github.com/pytorch/builder/blob/main/manywheel/build_rocm.sh
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
@@ -117,6 +122,24 @@ parameters:
|
||||
- hipCUB
|
||||
- rocThrust
|
||||
- hipBLAS-common
|
||||
- name: rocmTestDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocminfo
|
||||
# Reference on what tests to run for torchvision found in private repo:
|
||||
# https://github.com/ROCm/rocAutomation/blob/jenkins-pipelines/pytorch/pytorch_ci/test_pytorch_test1.sh#L54
|
||||
# Will iterate through this list using pytest
|
||||
- name: torchTestList
|
||||
type: object
|
||||
default:
|
||||
- nn
|
||||
- torch
|
||||
# - cuda seg faults and might need cuda installed on test system
|
||||
# - ops takes too long
|
||||
- unary_ufuncs
|
||||
- binary_ufuncs
|
||||
- autograd
|
||||
# - inductor/torchinductor takes too long
|
||||
|
||||
trigger: none
|
||||
pr: none
|
||||
@@ -300,7 +323,10 @@ jobs:
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: >-
|
||||
BUILD_VERSION=$(ROCM_BRANCH).$(JOB_GPU_TARGET)-$(cat $(Build.SourcesDirectory)/pytorch/version.txt | cut -da -f1)$(date -u +%Y%m%d)
|
||||
TORCH_PACKAGE_NAME=torch.$(ROCM_BRANCH).$(JOB_GPU_TARGET)
|
||||
TORCHVISION_PACKAGE_NAME=torchvision.$(ROCM_BRANCH).$(JOB_GPU_TARGET)
|
||||
PYTORCH_VERSION=$(cat $(Build.SourcesDirectory)/pytorch/version.txt | cut -da -f1)post$(date -u +%Y%m%d)
|
||||
BUILD_VERSION=$(cat $(Build.SourcesDirectory)/vision/version.txt | cut -da -f1)post$(date -u +%Y%m%d)
|
||||
python3 setup.py bdist_wheel
|
||||
workingDirectory: $(Build.SourcesDirectory)/vision
|
||||
- task: Bash@3
|
||||
@@ -319,3 +345,192 @@ jobs:
|
||||
retryCountOnTaskFailure: 3
|
||||
inputs:
|
||||
targetPath: $(Build.BinariesDirectory)
|
||||
|
||||
- job: torchvision_testing
|
||||
dependsOn: pytorch
|
||||
condition: succeeded()
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: PYTORCH_TEST_WITH_ROCM
|
||||
value: 1
|
||||
pool: $(JOB_TEST_POOL)
|
||||
workspace:
|
||||
clean: all
|
||||
strategy:
|
||||
matrix:
|
||||
gfx942:
|
||||
JOB_GPU_TARGET: gfx942
|
||||
JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
|
||||
steps:
|
||||
- task: Bash@3
|
||||
displayName: 'Register libjpeg-turbo packages'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
sudo mkdir --parents --mode=0755 /etc/apt/keyrings
|
||||
wget -q -O- https://packagecloud.io/dcommander/libjpeg-turbo/gpgkey | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/libjpeg-turbo.gpg > /dev/null
|
||||
echo "deb [signed-by=/etc/apt/trusted.gpg.d/libjpeg-turbo.gpg] https://packagecloud.io/dcommander/libjpeg-turbo/any/ any main" | sudo tee /etc/apt/sources.list.d/libjpeg-turbo.list
|
||||
sudo apt update
|
||||
apt-cache show libjpeg-turbo-official | grep Version
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
|
||||
parameters:
|
||||
aptPackages: ${{ parameters.aptPackages }}
|
||||
pipModules: ${{ parameters.pipModules }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
|
||||
- task: DownloadPipelineArtifact@2
|
||||
displayName: 'Download Pipeline Wheel Files'
|
||||
inputs:
|
||||
itemPattern: '**/*$(JOB_GPU_TARGET)*.whl'
|
||||
targetPath: $(Agent.BuildDirectory)
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
|
||||
parameters:
|
||||
dependencySource: staging
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmTestDependencies }}
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
dependencySource: staging
|
||||
skipLlvmSymlink: true
|
||||
# get sources to run test scripts
|
||||
- task: Bash@3
|
||||
displayName: git clone upstream pytorch
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: git clone https://github.com/pytorch/pytorch.git --depth=1 --recurse-submodules
|
||||
workingDirectory: $(Build.SourcesDirectory)
|
||||
- task: Bash@3
|
||||
displayName: git clone pytorch vision
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: git clone https://github.com/pytorch/vision.git --depth=1 --recurse-submodules
|
||||
workingDirectory: $(Build.SourcesDirectory)
|
||||
- task: Bash@3
|
||||
displayName: Install Wheel Files
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: find . -name "*.whl" -exec pip install --no-index --find-links=. --no-dependencies -v {} \;
|
||||
workingDirectory: $(Agent.BuildDirectory)
|
||||
- task: Bash@3
|
||||
displayName: Show Updated pip List
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: pip list -v
|
||||
workingDirectory: $(Agent.BuildDirectory)
|
||||
- task: Bash@3
|
||||
displayName: Add ROCm binaries to PATH
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
|
||||
- task: Bash@3
|
||||
displayName: Add Python site-packages binaries to path
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
USER_BASE=$(python3 -m site --user-base)
|
||||
echo "##vso[task.prependpath]$USER_BASE/bin"
|
||||
- task: Bash@3
|
||||
displayName: Add torch libs to ldconfig
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
echo $(python3 -m site --user-site)/torch/lib | sudo tee /etc/ld.so.conf.d/torch.conf
|
||||
sudo ldconfig -v
|
||||
ldconfig -p
|
||||
# https://pytorch.org/get-started/locally/#linux-verification
|
||||
# https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/3rd-party/pytorch-install.html#testing-the-pytorch-installation
|
||||
- task: Bash@3
|
||||
displayName: Simple Import Torch Tests
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
python3 -c 'import torch' 2> /dev/null && echo 'Success' || echo 'Failure'
|
||||
python3 -c 'import torch; print(torch.cuda.is_available())'
|
||||
python3 -c 'import torch; x = torch.rand(5, 3); print(x)'
|
||||
# Test artifact build script has too many if statements for different environments
|
||||
# Based off the snippet of interest for this environment, with some adjustments
|
||||
# https://github.com/pytorch/pytorch/blob/main/.ci/pytorch/build.sh#L335-L375
|
||||
# Removing in-line comments since it does not fit with the yaml markup
|
||||
- task: Bash@3
|
||||
displayName: Build Pytorch Test Artifacts
|
||||
continueOnError: true
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
CUSTOM_TEST_ARTIFACT_BUILD_DIR="build/custom_test_artifacts"
|
||||
CUSTOM_TEST_USE_ROCM=ON
|
||||
CUSTOM_TEST_MODULE_PATH="${PWD}/cmake/public"
|
||||
mkdir -pv "${CUSTOM_TEST_ARTIFACT_BUILD_DIR}"
|
||||
|
||||
CUSTOM_OP_BUILD="${CUSTOM_TEST_ARTIFACT_BUILD_DIR}/custom-op-build"
|
||||
CUSTOM_OP_TEST="${PWD}/test/custom_operator"
|
||||
python --version
|
||||
SITE_PACKAGES="$(python -c 'import site; print(";".join([x for x in site.getsitepackages()] + [x + "/torch" for x in site.getsitepackages()]))')"
|
||||
|
||||
mkdir -p "$CUSTOM_OP_BUILD"
|
||||
pushd "$CUSTOM_OP_BUILD"
|
||||
cmake "$CUSTOM_OP_TEST" -DCMAKE_PREFIX_PATH="$SITE_PACKAGES" -DPython_EXECUTABLE="$(which python)" \
|
||||
-DCMAKE_MODULE_PATH="$CUSTOM_TEST_MODULE_PATH" -DUSE_ROCM="$CUSTOM_TEST_USE_ROCM"
|
||||
make VERBOSE=1
|
||||
popd
|
||||
|
||||
JIT_HOOK_BUILD="${CUSTOM_TEST_ARTIFACT_BUILD_DIR}/jit-hook-build"
|
||||
JIT_HOOK_TEST="$PWD/test/jit_hooks"
|
||||
python --version
|
||||
SITE_PACKAGES="$(python -c 'import site; print(";".join([x for x in site.getsitepackages()] + [x + "/torch" for x in site.getsitepackages()]))')"
|
||||
mkdir -p "$JIT_HOOK_BUILD"
|
||||
pushd "$JIT_HOOK_BUILD"
|
||||
cmake "$JIT_HOOK_TEST" -DCMAKE_PREFIX_PATH="$SITE_PACKAGES" -DPython_EXECUTABLE="$(which python)" \
|
||||
-DCMAKE_MODULE_PATH="$CUSTOM_TEST_MODULE_PATH" -DUSE_ROCM="$CUSTOM_TEST_USE_ROCM"
|
||||
make VERBOSE=1
|
||||
popd
|
||||
|
||||
CUSTOM_BACKEND_BUILD="${CUSTOM_TEST_ARTIFACT_BUILD_DIR}/custom-backend-build"
|
||||
CUSTOM_BACKEND_TEST="${PWD}/test/custom_backend"
|
||||
python --version
|
||||
mkdir -p "$CUSTOM_BACKEND_BUILD"
|
||||
pushd "$CUSTOM_BACKEND_BUILD"
|
||||
cmake "$CUSTOM_BACKEND_TEST" -DCMAKE_PREFIX_PATH="$SITE_PACKAGES" -DPython_EXECUTABLE="$(which python)" \
|
||||
-DCMAKE_MODULE_PATH="$CUSTOM_TEST_MODULE_PATH" -DUSE_ROCM="$CUSTOM_TEST_USE_ROCM"
|
||||
make VERBOSE=1
|
||||
popd
|
||||
workingDirectory: $(Build.SourcesDirectory)/pytorch
|
||||
- ${{ each torchTest in parameters.torchTestList }}:
|
||||
- task: Bash@3
|
||||
displayName: Test ${{ torchTest }}
|
||||
continueOnError: true
|
||||
inputs:
|
||||
targetType: inline
|
||||
workingDirectory: $(Build.SourcesDirectory)/pytorch
|
||||
${{ if contains(torchTest, '/') }}:
|
||||
script: pytest test/${{ split(torchTest, '/')[0] }}/test_${{ split(torchTest, '/')[1] }}.py
|
||||
${{ else }}:
|
||||
script: pytest test/test_${{ torchTest }}.py
|
||||
# Reference on what tests to run for torchvision found in private repo:
|
||||
# https://github.com/ROCm/rocAutomation/blob/jenkins-pipelines/pytorch/pytorch_ci/test_torchvision.sh#L51
|
||||
- task: Bash@3
|
||||
displayName: Test vision/transforms
|
||||
continueOnError: true
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: pytest test/test_transforms.py
|
||||
workingDirectory: $(Build.SourcesDirectory)/vision
|
||||
- task: Bash@3
|
||||
displayName: Uninstall Wheel Files
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: find . -name "*.whl" -exec pip uninstall -y {} \;
|
||||
workingDirectory: $(Agent.BuildDirectory)
|
||||
- task: Bash@3
|
||||
displayName: Remove Python site-packages binaries from path
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
USER_BASE=$(python3 -m site --user-base)
|
||||
echo "##vso[task.setvariable variable=PATH]$(echo $PATH | sed -e 's;:$USER_BASE/bin;;' -e 's;^/;;' -e 's;/$;;')"
|
||||
- task: Bash@3
|
||||
displayName: Remove ROCm binaries from PATH
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: echo "##vso[task.setvariable variable=PATH]$(echo $PATH | sed -e 's;:$(Agent.BuildDirectory)/rocm/bin;;' -e 's;^/;;' -e 's;/$;;')"
|
||||
|
||||
@@ -46,6 +46,7 @@ parameters:
|
||||
- rocm_smi_lib
|
||||
- rocPRIM
|
||||
- rocprofiler-register
|
||||
- rocprofiler-sdk
|
||||
- rocprofiler
|
||||
- rocPyDecode
|
||||
- ROCR-Runtime
|
||||
@@ -101,6 +102,7 @@ jobs:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
skipLibraryLinking: true
|
||||
skipLlvmSymlink: true
|
||||
gpuTarget: $(JOB_GPU_TARGET)
|
||||
- script: df -h
|
||||
displayName: System disk space after ROCm
|
||||
|
||||
46
.azuredevops/scripts/compareDot.py
Normal file
46
.azuredevops/scripts/compareDot.py
Normal file
@@ -0,0 +1,46 @@
|
||||
import os
|
||||
import requests
|
||||
import hashlib
|
||||
import sys
|
||||
|
||||
def download_dotfile(url, file_path):
|
||||
response = requests.get(url)
|
||||
if response.status_code == 200:
|
||||
with open(file_path, 'wb') as f:
|
||||
f.write(response.content)
|
||||
else:
|
||||
raise Exception(f"Failed to download file from {url}. Status code: {response.status_code}")
|
||||
|
||||
def hash_file(file_path):
|
||||
sha256_hash = hashlib.sha256()
|
||||
with open(file_path, 'rb') as f:
|
||||
for byte_block in iter(lambda: f.read(4096), b""):
|
||||
sha256_hash.update(byte_block)
|
||||
return sha256_hash.hexdigest()
|
||||
|
||||
def compare_files(local_file, downloaded_file):
|
||||
local_hash = hash_file(local_file)
|
||||
downloaded_hash = hash_file(downloaded_file)
|
||||
return local_hash == downloaded_hash
|
||||
|
||||
def main():
|
||||
script_directory = os.path.dirname(os.path.abspath(__file__))
|
||||
local_dotfile = os.path.join(script_directory, 'input.dot')
|
||||
downloaded_dotfile = os.path.join(script_directory, 'dependency_graph.dot')
|
||||
|
||||
url = 'https://raw.githubusercontent.com/ROCm/ROCm/refs/heads/generatedependencygraph/.azuredevops/scripts/dependency_graph.dot'
|
||||
|
||||
try:
|
||||
download_dotfile(url, downloaded_dotfile)
|
||||
if compare_files(local_dotfile, downloaded_dotfile):
|
||||
print("The local DOT file and the downloaded DOT file are the same.")
|
||||
else:
|
||||
print("The local DOT file and the downloaded DOT file are different.")
|
||||
# Exit with a non-zero status to signal failed/unstable build on Jenkins
|
||||
# to trigger post-build email
|
||||
sys.exit(1)
|
||||
except Exception as e:
|
||||
print(f"Error: {e}")
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
149
.azuredevops/scripts/dependencyGraph.py
Normal file
149
.azuredevops/scripts/dependencyGraph.py
Normal file
@@ -0,0 +1,149 @@
|
||||
import os
|
||||
import yaml
|
||||
from graphviz import Digraph
|
||||
|
||||
# Set DEBUG to False for normal output, True for debug output
|
||||
DEBUG = False
|
||||
|
||||
def debug_print(message):
|
||||
if DEBUG:
|
||||
print(message)
|
||||
|
||||
import os
|
||||
import yaml
|
||||
|
||||
def extract_dependencies(exclude_nodes=[]):
|
||||
dependencies = {}
|
||||
debug_print("Extracting dependencies from YAML files...")
|
||||
|
||||
# Define a mapping of specific filenames to component names
|
||||
component_name_mapping = {
|
||||
'HIP.yml': 'clr', # Remap HIP.yml to clr in graph
|
||||
}
|
||||
|
||||
script_directory = os.path.dirname(os.path.abspath(__file__))
|
||||
yaml_directory = os.path.join(script_directory, '..', 'components')
|
||||
|
||||
for filename in os.listdir(yaml_directory):
|
||||
if filename.endswith(".yaml") or filename.endswith(".yml"):
|
||||
debug_print(f"Processing file: {filename}")
|
||||
try:
|
||||
with open(os.path.join(yaml_directory, filename), 'r') as file:
|
||||
data = yaml.safe_load(file) or {}
|
||||
parameters = data.get('parameters', [])
|
||||
|
||||
# Check for both 'rocmDependencies' and 'rocmDependenciesAMD'
|
||||
rocm_dependencies = next((param['default'] for param in parameters if param['name'] == 'rocmDependencies' or param['name'] == 'rocmDependenciesAMD'), [])
|
||||
test_dependencies = next((param['default'] for param in parameters if param['name'] == 'rocmTestDependencies'), [])
|
||||
|
||||
unique_dependencies = list(set(rocm_dependencies + test_dependencies))
|
||||
unique_dependencies = [dep for dep in unique_dependencies if dep not in exclude_nodes]
|
||||
|
||||
# Use the mapped component name if it exists
|
||||
component_name = component_name_mapping.get(filename, os.path.splitext(filename)[0])
|
||||
dependencies[component_name] = {
|
||||
'dependencies': unique_dependencies
|
||||
}
|
||||
debug_print(f"Found unique dependencies for {component_name}: {unique_dependencies}")
|
||||
except Exception as e:
|
||||
print(f"Error processing {filename}: {e}")
|
||||
|
||||
return dependencies
|
||||
|
||||
def simplify_dependencies(graph):
|
||||
simplified_graph = {}
|
||||
|
||||
for component, deps in graph.items():
|
||||
if component not in simplified_graph:
|
||||
simplified_graph[component] = set(deps) # Use a set for uniqueness
|
||||
|
||||
for dep in deps:
|
||||
if dep in graph: # If the dependency has its own dependencies
|
||||
for sub_dep in graph[dep]:
|
||||
simplified_graph[component].discard(sub_dep) # Remove transitive dependencies
|
||||
|
||||
# Convert sets back to lists
|
||||
for component in simplified_graph:
|
||||
simplified_graph[component] = list(simplified_graph[component])
|
||||
|
||||
return simplified_graph
|
||||
|
||||
def build_dependency_graph(dependencies, exclude_nodes=None):
|
||||
if exclude_nodes is None:
|
||||
exclude_nodes = []
|
||||
|
||||
graph = {}
|
||||
debug_print("Building dependency graph...")
|
||||
|
||||
for component, deps in dependencies.items():
|
||||
if component in exclude_nodes:
|
||||
continue # Skip excluded components
|
||||
|
||||
# Ensure uniqueness and prevent self-dependency
|
||||
all_deps = [dep for dep in set(deps['dependencies']) if dep != component and dep not in exclude_nodes]
|
||||
graph[component] = all_deps
|
||||
debug_print(f"{component} -> {all_deps}")
|
||||
|
||||
# Simplify the dependencies to remove transitive dependencies
|
||||
simplified_graph = simplify_dependencies(graph)
|
||||
|
||||
return simplified_graph
|
||||
|
||||
def build_full_dependency_tree(graph):
|
||||
tree = {}
|
||||
debug_print("Building full dependency tree...")
|
||||
|
||||
def dfs(component, visited):
|
||||
if component in visited:
|
||||
return
|
||||
visited.add(component)
|
||||
for dep in graph.get(component, []):
|
||||
# Prevent self-dependency in the tree
|
||||
if dep != component:
|
||||
if dep not in tree:
|
||||
tree[dep] = []
|
||||
if component not in tree[dep]: # Prevent duplicates
|
||||
tree[dep].append(component)
|
||||
dfs(dep, visited)
|
||||
|
||||
for component in graph.keys():
|
||||
dfs(component, set())
|
||||
|
||||
return tree
|
||||
|
||||
def visualize_graph(graph):
|
||||
dot = Digraph()
|
||||
|
||||
# sort edges for consistent dot file hash
|
||||
for component in sorted(graph):
|
||||
for dep in sorted(graph[component]):
|
||||
dot.edge(component, dep)
|
||||
|
||||
script_directory = os.path.dirname(os.path.abspath(__file__))
|
||||
|
||||
# make an input dot file for comparisons
|
||||
dot_file_path = os.path.join(script_directory, 'input.dot')
|
||||
with open(dot_file_path, 'w') as f:
|
||||
f.write(dot.source)
|
||||
|
||||
dot.render(os.path.join(script_directory, 'dependency_graph'), format='png', cleanup=True) # Save as PNG
|
||||
|
||||
def main():
|
||||
exclude_deps = ['rocm-examples']
|
||||
dependencies = extract_dependencies(exclude_nodes=exclude_deps)
|
||||
|
||||
if not dependencies:
|
||||
debug_print("No dependencies found.")
|
||||
return
|
||||
|
||||
graph = build_dependency_graph(dependencies, exclude_nodes=exclude_deps)
|
||||
full_tree = build_full_dependency_tree(graph)
|
||||
|
||||
print("Dependency tree:")
|
||||
print(full_tree)
|
||||
|
||||
# Call this function after building the graph
|
||||
visualize_graph(full_tree)
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
94
.azuredevops/scripts/dependency_graph.dot
Normal file
94
.azuredevops/scripts/dependency_graph.dot
Normal file
@@ -0,0 +1,94 @@
|
||||
digraph {
|
||||
AMDMIGraphX -> MIVisionX
|
||||
HIPIFY -> rccl
|
||||
MIOpen -> AMDMIGraphX
|
||||
MIVisionX -> rocAL
|
||||
"ROCR-Runtime" -> clr
|
||||
"ROCR-Runtime" -> rocminfo
|
||||
ROCdbgapi -> ROCgdb
|
||||
ROCdbgapi -> rocprofiler
|
||||
ROCdbgapi -> rocr_debug_agent
|
||||
ROCgdb -> aomp
|
||||
ROCmValidationSuite -> rdc
|
||||
amdsmi -> aomp
|
||||
amdsmi -> rdc
|
||||
aomp -> hipBLASLt
|
||||
aomp -> rccl
|
||||
aomp -> rocFFT
|
||||
aomp -> rpp
|
||||
"aomp-extras" -> rccl
|
||||
"aomp-extras" -> rocBLAS
|
||||
clr -> ROCdbgapi
|
||||
clr -> composable_kernel
|
||||
clr -> half
|
||||
clr -> "hip-tests"
|
||||
clr -> "hipBLAS-common"
|
||||
clr -> rocDecode
|
||||
clr -> rocMLIR
|
||||
clr -> rocPRIM
|
||||
clr -> rocRAND
|
||||
clr -> rocm_bandwidth_test
|
||||
clr -> roctracer
|
||||
composable_kernel -> MIOpen
|
||||
composable_kernel -> hipTensor
|
||||
half -> MIOpen
|
||||
half -> rpp
|
||||
hipBLAS -> MIOpen
|
||||
hipBLAS -> hipfort
|
||||
"hipBLAS-common" -> hipBLASLt
|
||||
hipBLASLt -> rocBLAS
|
||||
hipFFT -> hipfort
|
||||
hipRAND -> ROCmValidationSuite
|
||||
hipRAND -> rocFFT
|
||||
hipRAND -> rocThrust
|
||||
hipSOLVER -> hipfort
|
||||
hipSPARSE -> hipSPARSELt
|
||||
hipSPARSE -> rocSOLVER
|
||||
hipTensor -> rpp
|
||||
"llvm-project" -> "ROCR-Runtime"
|
||||
"llvm-project" -> "aomp-extras"
|
||||
rccl -> omnitrace
|
||||
rccl -> "rocprofiler-sdk"
|
||||
rocBLAS -> ROCmValidationSuite
|
||||
rocBLAS -> rocSPARSE
|
||||
rocBLAS -> rocWMMA
|
||||
rocDecode -> MIVisionX
|
||||
rocDecode -> rocPyDecode
|
||||
rocFFT -> hipFFT
|
||||
rocMLIR -> MIOpen
|
||||
rocPRIM -> hipCUB
|
||||
rocPRIM -> rocSPARSE
|
||||
rocPRIM -> rocThrust
|
||||
rocRAND -> MIOpen
|
||||
rocRAND -> hipRAND
|
||||
rocRAND -> rocALUTION
|
||||
rocSOLVER -> hipBLAS
|
||||
rocSOLVER -> hipSOLVER
|
||||
rocSPARSE -> hipSPARSE
|
||||
rocSPARSE -> rocALUTION
|
||||
"rocm-cmake" -> "llvm-project"
|
||||
"rocm-core" -> aomp
|
||||
"rocm-core" -> rocDecode
|
||||
"rocm-core" -> rocprofiler
|
||||
rocm_smi_lib -> "ROCR-Runtime"
|
||||
rocminfo -> ROCdbgapi
|
||||
rocminfo -> composable_kernel
|
||||
rocminfo -> half
|
||||
rocminfo -> "hip-tests"
|
||||
rocminfo -> "hipBLAS-common"
|
||||
rocminfo -> rocDecode
|
||||
rocminfo -> rocMLIR
|
||||
rocminfo -> rocPRIM
|
||||
rocminfo -> rocRAND
|
||||
rocminfo -> rocm_bandwidth_test
|
||||
rocminfo -> roctracer
|
||||
rocprofiler -> hipfort
|
||||
rocprofiler -> omniperf
|
||||
rocprofiler -> omnitrace
|
||||
rocprofiler -> rdc
|
||||
"rocprofiler-register" -> "ROCR-Runtime"
|
||||
roctracer -> aomp
|
||||
roctracer -> rocprofiler
|
||||
roctracer -> "rocprofiler-sdk"
|
||||
rpp -> MIVisionX
|
||||
}
|
||||
BIN
.azuredevops/scripts/dependency_graph.png
Normal file
BIN
.azuredevops/scripts/dependency_graph.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 475 KiB |
29
.azuredevops/tag-builds/omnitrace.yml
Normal file
29
.azuredevops/tag-builds/omnitrace.yml
Normal file
@@ -0,0 +1,29 @@
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
|
||||
parameters:
|
||||
- name: checkoutRef
|
||||
type: string
|
||||
default: refs/tags/$(LATEST_RELEASE_TAG)
|
||||
|
||||
resources:
|
||||
repositories:
|
||||
- repository: pipelines_repo
|
||||
type: github
|
||||
endpoint: ROCm
|
||||
name: ROCm/ROCm
|
||||
- repository: release_repo
|
||||
type: github
|
||||
endpoint: ROCm
|
||||
name: ROCm/omnitrace
|
||||
ref: ${{ parameters.checkoutRef }}
|
||||
|
||||
trigger: none
|
||||
pr: none
|
||||
|
||||
jobs:
|
||||
- template: ${{ variables.CI_COMPONENT_PATH }}/omnitrace.yml
|
||||
parameters:
|
||||
checkoutRepo: release_repo
|
||||
checkoutRef: ${{ parameters.checkoutRef }}
|
||||
29
.azuredevops/tag-builds/rocprofiler-sdk.yml
Normal file
29
.azuredevops/tag-builds/rocprofiler-sdk.yml
Normal file
@@ -0,0 +1,29 @@
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
|
||||
parameters:
|
||||
- name: checkoutRef
|
||||
type: string
|
||||
default: refs/tags/$(LATEST_RELEASE_TAG)
|
||||
|
||||
resources:
|
||||
repositories:
|
||||
- repository: pipelines_repo
|
||||
type: github
|
||||
endpoint: ROCm
|
||||
name: ROCm/ROCm
|
||||
- repository: release_repo
|
||||
type: github
|
||||
endpoint: ROCm
|
||||
name: ROCm/rocprofiler-sdk
|
||||
ref: ${{ parameters.checkoutRef }}
|
||||
|
||||
trigger: none
|
||||
pr: none
|
||||
|
||||
jobs:
|
||||
- template: ${{ variables.CI_COMPONENT_PATH }}/rocprofiler-sdk.yml
|
||||
parameters:
|
||||
checkoutRepo: release_repo
|
||||
checkoutRef: ${{ parameters.checkoutRef }}
|
||||
@@ -29,6 +29,7 @@ parameters:
|
||||
composable_kernel: develop
|
||||
half: rocm
|
||||
HIP: amd-staging
|
||||
hip-tests: amd-staging
|
||||
hipBLAS: develop
|
||||
hipBLASLt: develop
|
||||
hipBLAS-common: develop
|
||||
@@ -44,6 +45,7 @@ parameters:
|
||||
llvm-project: amd-staging
|
||||
MIOpen: develop
|
||||
MIVisionX: develop
|
||||
omniperf: amd-staging
|
||||
rccl: develop
|
||||
rdc: develop
|
||||
rocAL: develop
|
||||
@@ -62,8 +64,10 @@ parameters:
|
||||
rocm_bandwidth_test: master
|
||||
rocm_smi_lib: develop
|
||||
rocPRIM: develop
|
||||
rocprofiler-register: amd-mainline
|
||||
rocprofiler-register: amd-staging
|
||||
rocprofiler-sdk: amd-staging
|
||||
rocprofiler: amd-staging
|
||||
rocPyDecode: develop
|
||||
ROCR-Runtime: amd-staging
|
||||
rocRAND: develop
|
||||
rocr_debug_agent: amd-staging
|
||||
@@ -79,12 +83,14 @@ parameters:
|
||||
- amdsmi
|
||||
- aomp
|
||||
- HIPIFY
|
||||
- MIVisionX
|
||||
- omniperf
|
||||
- rccl
|
||||
- rdc
|
||||
- rocm-cmake
|
||||
- rocm_smi_lib
|
||||
- rocFFT
|
||||
- MIVisionX
|
||||
- rpp
|
||||
# BELOW REQUIRED IF useDefaultBranch false
|
||||
- name: branchName
|
||||
type: string
|
||||
|
||||
@@ -37,6 +37,7 @@ parameters:
|
||||
composable_kernel: $(COMPOSABLE_KERNEL_PIPELINE_ID)
|
||||
half: $(HALF_PIPELINE_ID)
|
||||
HIP: $(HIP_PIPELINE_ID)
|
||||
hip-tests: $(HIP_TESTS_PIPELINE_ID)
|
||||
hipBLAS: $(HIPBLAS_PIPELINE_ID)
|
||||
hipBLAS-common: $(HIPBLAS_COMMON_PIPELINE_ID)
|
||||
hipBLASLt: $(HIPBLASLT_PIPELINE_ID)
|
||||
@@ -72,7 +73,9 @@ parameters:
|
||||
rocm_smi_lib: $(ROCM_SMI_LIB_PIPELINE_ID)
|
||||
rocPRIM: $(ROCPRIM_PIPELINE_ID)
|
||||
rocprofiler-register: $(ROCPROFILER_REGISTER_PIPELINE_ID)
|
||||
rocprofiler-sdk: $(ROCPROFILER_SDK_PIPELINE_ID)
|
||||
rocprofiler: $(ROCPROFILER_PIPELINE_ID)
|
||||
rocPyDecode: $(ROCPYDECODE_PIPELINE_ID)
|
||||
ROCR-Runtime: $(ROCR_RUNTIME_PIPELINE_ID)
|
||||
rocRAND: $(ROCRAND_PIPELINE_ID)
|
||||
rocr_debug_agent: $(ROCR_DEBUG_AGENT_PIPELINE_ID)
|
||||
@@ -94,6 +97,7 @@ parameters:
|
||||
composable_kernel: $(COMPOSABLE_KERNEL_TAGGED_PIPELINE_ID)
|
||||
half: $(HALF_TAGGED_PIPELINE_ID)
|
||||
HIP: $(HIP_TAGGED_PIPELINE_ID)
|
||||
hip-tests: $(HIP_TESTS_TAGGED_PIPELINE_ID)
|
||||
hipBLAS: $(HIPBLAS_TAGGED_PIPELINE_ID)
|
||||
hipBLAS-common: $(HIPBLAS_COMMON_TAGGED_PIPELINE_ID)
|
||||
hipBLASLt: $(HIPBLASLT_TAGGED_PIPELINE_ID)
|
||||
@@ -129,7 +133,9 @@ parameters:
|
||||
rocm_smi_lib: $(ROCM_SMI_LIB_TAGGED_PIPELINE_ID)
|
||||
rocPRIM: $(ROCPRIM_TAGGED_PIPELINE_ID)
|
||||
rocprofiler-register: $(ROCPROFILER_REGISTER_TAGGED_PIPELINE_ID)
|
||||
rocprofiler-sdk: $(ROCPROFILER_SDK_TAGGED_PIPELINE_ID)
|
||||
rocprofiler: $(ROCPROFILER_TAGGED_PIPELINE_ID)
|
||||
rocPyDecode: $(ROCPYDECODE_TAGGED_PIPELINE_ID)
|
||||
ROCR-Runtime: $(ROCR_RUNTIME_TAGGED_PIPELINE_ID)
|
||||
rocRAND: $(ROCRAND_TAGGED_PIPELINE_ID)
|
||||
rocr_debug_agent: $(ROCR_DEBUG_AGENT_TAGGED_PIPELINE_ID)
|
||||
@@ -174,7 +180,9 @@ parameters:
|
||||
- rocFFT
|
||||
- rocm-examples
|
||||
- rocPRIM
|
||||
- rocprofiler-sdk
|
||||
- rocprofiler
|
||||
- rocPyDecode
|
||||
- rocRAND
|
||||
- rocSOLVER
|
||||
- rocSPARSE
|
||||
|
||||
@@ -79,6 +79,10 @@ variables:
|
||||
value: 93
|
||||
- name: HIP_TAGGED_PIPELINE_ID
|
||||
value: 31
|
||||
- name: HIP_TESTS_PIPELINE_ID
|
||||
value: 233
|
||||
- name: HIP_TESTS_TAGGED_PIPELINE_ID
|
||||
value: 220
|
||||
- name: HIPBLAS_COMMON_PIPELINE_ID
|
||||
value: 223
|
||||
- name: HIPBLAS_COMMON_TAGGED_PIPELINE_ID
|
||||
@@ -223,6 +227,10 @@ variables:
|
||||
value: 22
|
||||
- name: ROCM_EXAMPLES_GFX942_TEST_PIPELINE_ID
|
||||
value: 204
|
||||
- name: ROCM_EXAMPLES_PIPELINE_ID
|
||||
value: 216
|
||||
- name: ROCM_EXAMPLES_TAGGED_PIPELINE_ID
|
||||
value: 245
|
||||
- name: ROCM_SMI_LIB_PIPELINE_ID
|
||||
value: 96
|
||||
- name: ROCM_SMI_LIB_TAGGED_PIPELINE_ID
|
||||
@@ -247,14 +255,22 @@ variables:
|
||||
value: 20
|
||||
- name: ROCPROFILER_GFX942_TEST_PIPELINE_ID
|
||||
value: 190
|
||||
- name: ROCPROFILER_PIPELINE_ID
|
||||
value: 143
|
||||
- name: ROCPROFILER_REGISTER_PIPELINE_ID
|
||||
value: 1
|
||||
- name: ROCPROFILER_REGISTER_TAGGED_PIPELINE_ID
|
||||
value: 25
|
||||
- name: ROCPROFILER_SDK_PIPELINE_ID
|
||||
value: 246
|
||||
- name: ROCPROFILER_SDK_TAGGED_PIPELINE_ID
|
||||
value: 234
|
||||
- name: ROCPROFILER_PIPELINE_ID
|
||||
value: 143
|
||||
- name: ROCPROFILER_TAGGED_PIPELINE_ID
|
||||
value: 28
|
||||
- name: ROCPYDECODE_PIPELINE_ID
|
||||
value: 239
|
||||
- name: ROCPYDECODE_TAGGED_PIPELINE_ID
|
||||
value: 232
|
||||
- name: ROCR_DEBUG_AGENT_PIPELINE_ID
|
||||
value: 136
|
||||
- name: ROCR_DEBUG_AGENT_TAGGED_PIPELINE_ID
|
||||
|
||||
@@ -36,7 +36,6 @@ Bluefield
|
||||
Bootloader
|
||||
CCD
|
||||
CDNA
|
||||
CHTML
|
||||
CIFAR
|
||||
CLI
|
||||
CLion
|
||||
@@ -71,7 +70,6 @@ Concretized
|
||||
Conda
|
||||
ConnectX
|
||||
CuPy
|
||||
Dashboarding
|
||||
DDR
|
||||
DF
|
||||
DGEMM
|
||||
@@ -229,7 +227,6 @@ Mellanox's
|
||||
Meta's
|
||||
Miniconda
|
||||
MirroredStrategy
|
||||
Mixtral
|
||||
Multicore
|
||||
Multithreaded
|
||||
MyEnvironment
|
||||
@@ -275,8 +272,6 @@ OpenMPI
|
||||
OpenSSL
|
||||
OpenVX
|
||||
OpenXLA
|
||||
Oversubscription
|
||||
PagedAttention
|
||||
PCC
|
||||
PCI
|
||||
PCIe
|
||||
@@ -298,7 +293,6 @@ PowerShell
|
||||
PyPi
|
||||
PyTorch
|
||||
Qcycles
|
||||
Qwen
|
||||
RAII
|
||||
RAS
|
||||
RCCL
|
||||
@@ -496,6 +490,7 @@ cuLIB
|
||||
cuRAND
|
||||
cuSOLVER
|
||||
cuSPARSE
|
||||
customizations
|
||||
cTDP
|
||||
dataset
|
||||
datasets
|
||||
@@ -567,7 +562,6 @@ hipfort
|
||||
hipify
|
||||
hipsolver
|
||||
hipsparse
|
||||
hlist
|
||||
hotspotting
|
||||
hpc
|
||||
hpp
|
||||
@@ -591,7 +585,6 @@ intra
|
||||
invariants
|
||||
invocating
|
||||
ipo
|
||||
jax
|
||||
kdb
|
||||
kfd
|
||||
latencies
|
||||
@@ -612,7 +605,6 @@ migraphx
|
||||
miopen
|
||||
miopengemm
|
||||
mivisionx
|
||||
mjx
|
||||
mkdir
|
||||
mlirmiopen
|
||||
mtypes
|
||||
@@ -707,6 +699,7 @@ rocsolver
|
||||
rocsparse
|
||||
rocthrust
|
||||
roctracer
|
||||
rst
|
||||
runtime
|
||||
runtimes
|
||||
sL
|
||||
|
||||
@@ -76,7 +76,7 @@ The Build time will reduce significantly if we limit the GPU Architecture/s agai
|
||||
|
||||
mkdir -p ~/WORKSPACE/ # Or any folder name other than WORKSPACE
|
||||
cd ~/WORKSPACE/
|
||||
export ROCM_VERSION=6.2.1
|
||||
export ROCM_VERSION=6.2.2 # Or 6.2.0 or 6.2.1
|
||||
~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.2.x -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
|
||||
~/bin/repo sync
|
||||
|
||||
@@ -199,4 +199,4 @@ cmake --build build --target=doc
|
||||
## Older ROCm releases
|
||||
|
||||
For release information for older ROCm releases, refer to the
|
||||
[CHANGELOG](./CHANGELOG.md).
|
||||
[ROCm release history](https://rocm.docs.amd.com/en/latest/release/versions.html).
|
||||
|
||||
166
RELEASE.md
166
RELEASE.md
@@ -1,6 +1,43 @@
|
||||
# ROCm 6.2.1 release notes
|
||||
# ROCm 6.2.2 release notes
|
||||
|
||||
The release notes provide a summary of notable changes since the previous ROCm release.
|
||||
These release notes provide a summary of notable changes since the previous ROCm release.
|
||||
|
||||
```{note}
|
||||
As ROCm 6.2.2 was released shortly after 6.2.1, the changes between these versions
|
||||
are minimal. For a comprehensive overview of recent updates, the ROCm 6.2.1 release
|
||||
notes are appended to the end of this document.
|
||||
|
||||
For detailed information about the changes in ROCm 6.2.1, refer to the appended
|
||||
section: [ROCm 6.2.1 release notes](rocm-6-2-1-release-notes).
|
||||
```
|
||||
|
||||
The [Compatibility matrix](https://rocm.docs.amd.com/en/docs-6.2.2/compatibility/compatibility-matrix.html)
|
||||
provides the full list of supported hardware, operating systems, ecosystems, third-party components, and ROCm components
|
||||
for each ROCm release.
|
||||
|
||||
Release notes for previous ROCm releases are available in earlier versions of the documentation.
|
||||
See the [ROCm documentation release history](https://rocm.docs.amd.com/en/latest/release/versions.html).
|
||||
|
||||
## Release highlights
|
||||
|
||||
The following is a significant fix introduced in ROCm 6.2.2.
|
||||
|
||||
### Fixed Instinct MI300X error recovery failure
|
||||
|
||||
Improved the reliability of AMD Instinct MI300X accelerators in scenarios involving
|
||||
uncorrectable errors. Previously, error recovery did not occur as expected,
|
||||
potentially leaving the system in an undefined state. This fix ensures that error
|
||||
recovery functions as expected, maintaining system stability.
|
||||
|
||||
See the [original issue](#instinct-mi300x-gpu-recovery-failure-on-uncorrectable-errors)
|
||||
noted in the ROCm 6.2.1 release notes.
|
||||
|
||||
---
|
||||
|
||||
## ROCm 6.2.1 release notes
|
||||
|
||||
The ROCm 6.2.1 release notes document newly added ecosystem support, ROCm Offline Installer Creator updates,
|
||||
and improvements to several ROCm libraries and tools.
|
||||
|
||||
- [Release highlights](release-highlights)
|
||||
|
||||
@@ -14,31 +51,25 @@ The release notes provide a summary of notable changes since the previous ROCm r
|
||||
|
||||
- [ROCm upcoming changes](rocm-upcoming-changes)
|
||||
|
||||
The [Compatibility matrix](https://rocm.docs.amd.com/en/docs-6.2.1/compatibility/compatibility-matrix.html)
|
||||
provides the full list of supported hardware, operating systems, ecosystems, third-party components, and ROCm components for each ROCm release.
|
||||
|
||||
Release notes for previous ROCm releases are available in earlier versions of the documentation.
|
||||
See the [ROCm documentation release history](https://rocm.docs.amd.com/en/latest/release/versions.html).
|
||||
|
||||
## Release highlights
|
||||
### Release highlights
|
||||
|
||||
The following are notable new features and improvements in ROCm 6.2.1. For changes to individual components, see [Detailed component changes](#detailed-component-changes).
|
||||
|
||||
### rocAL major version change
|
||||
#### rocAL major version change
|
||||
|
||||
The new version of rocAL introduces many new features, but does not modify any of the existing public API functions. However, the version number was incremented from 1.3 to 2.0.
|
||||
Applications linked to version 1.3 must be recompiled to link against version 2.0.
|
||||
|
||||
See [the rocAL detailed changes](#rocal-2-0-0) for more information.
|
||||
|
||||
### New support for FBGEMM (Facebook General Matrix Multiplication)
|
||||
#### New support for FBGEMM (Facebook General Matrix Multiplication)
|
||||
|
||||
As of ROCm 6.2.1, ROCm supports Facebook General Matrix Multiplication (FBGEMM) and the related FBGEMM_GPU library.
|
||||
|
||||
FBGEMM is a low-precision, high-performance CPU kernel library for convolution and matrix multiplication. It is used for server-side inference and as a back end for PyTorch quantized operators. FBGEMM_GPU includes a collection of PyTorch GPU operator libraries for training and inference. For more information, see the ROCm [Model acceleration libraries guide](https://rocm.docs.amd.com/en/docs-6.2.1/how-to/llm-fine-tuning-optimization/model-acceleration-libraries.html)
|
||||
and [PyTorch's FBGEMM GitHub repository](https://github.com/pytorch/FBGEMM).
|
||||
|
||||
### ROCm Offline Installer Creator changes
|
||||
#### ROCm Offline Installer Creator changes
|
||||
|
||||
The [ROCm Offline Installer Creator 6.2.1](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.2.1/install/rocm-offline-installer.html) introduces several new features and improvements including:
|
||||
|
||||
@@ -47,27 +78,25 @@ The [ROCm Offline Installer Creator 6.2.1](https://rocm.docs.amd.com/projects/in
|
||||
* Updated prerequisite repositories
|
||||
* Fixed CTest issues
|
||||
|
||||
### ROCm documentation changes
|
||||
#### ROCm documentation changes
|
||||
|
||||
The HIP documentation has been updated with several new topics aimed at improving usability
|
||||
and providing more detailed information.
|
||||
There have been no changes to supported hardware or operating systems from ROCm 6.2.0 to ROCm 6.2.1.
|
||||
|
||||
* The Programming Model Reference and Understanding the Programming Model topics in HIP have been consolidated into one topic,
|
||||
[HIP programming model (conceptual)](https://rocm.docs.amd.com/projects/HIP/en/docs-6.2.1/understand/programming_model.html).
|
||||
|
||||
* The [HIP virtual memory management](https://rocm.docs.amd.com/projects/HIP/en/docs-6.2.1/how-to/virtual_memory.html) and [HIP virtual memory management API](https://rocm.docs.amd.com/projects/HIP/en/docs-6.2.1/reference/virtual_memory_reference.html) topics have been added.
|
||||
|
||||
```{note}
|
||||
To contribute to ROCm documentation, see the [ROCm documentation contribution guidelines](https://rocm.docs.amd.com/en/latest/contribute/contributing.html).
|
||||
The ROCm documentation, like all ROCm projects, is open source and available on GitHub. To contribute to ROCm documentation, see the [ROCm documentation contribution guidelines](https://rocm.docs.amd.com/en/latest/contribute/contributing.html).
|
||||
```
|
||||
|
||||
## Operating system and hardware support changes
|
||||
### Operating system and hardware support changes
|
||||
|
||||
ROCm 6.2.1 adds support for Ubuntu 24.04.1 (kernel: 6.8 [GA]).
|
||||
|
||||
See the [Compatibility matrix](https://rocm.docs.amd.com/en/docs-6.2.1/compatibility/compatibility-matrix.html) for the full list of supported operating systems and hardware architectures.
|
||||
|
||||
## ROCm components
|
||||
### ROCm components
|
||||
|
||||
The following table lists the versions of ROCm components for ROCm 6.2.1, including any version changes from 6.2.0 to 6.2.1.
|
||||
|
||||
@@ -295,7 +324,7 @@ Click the component's updated version to go to a detailed list of its changes. C
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href="https://rocm.docs.amd.com/projects/rdc/en/docs-6.2.1">ROCm Data Center Tool</a></td>
|
||||
<td>0.3.0</td>
|
||||
<td>1.0.0</td>
|
||||
<td><a href="https://github.com/ROCm/rdc/releases/tag/rocm-6.2.1"><i
|
||||
class="fab fa-github fa-lg"></i></a></td>
|
||||
</tr>
|
||||
@@ -317,7 +346,7 @@ Click the component's updated version to go to a detailed list of its changes. C
|
||||
<th rowspan="6"></th>
|
||||
<th rowspan="6">Performance</th>
|
||||
<td><a href="https://rocm.docs.amd.com/projects/omniperf/en/docs-6.2.1">Omniperf</a></td>
|
||||
<td>2.0.1 ⇒ <a href="#omniperf-2-0-1">2.0.1</a></td>
|
||||
<td>2.0.1</td>
|
||||
<td><a href="https://github.com/ROCm/omniperf/releases/tag/rocm-6.2.1"><i
|
||||
class="fab fa-github fa-lg"></i></a></td>
|
||||
</tr>
|
||||
@@ -422,76 +451,55 @@ Click the component's updated version to go to a detailed list of its changes. C
|
||||
</table>
|
||||
</div>
|
||||
|
||||
## Detailed component changes
|
||||
### Detailed component changes
|
||||
|
||||
The following sections describe key changes to ROCm components.
|
||||
|
||||
### **AMD SMI** (24.6.3)
|
||||
#### **AMD SMI** (24.6.3)
|
||||
|
||||
#### Changes
|
||||
##### Changes
|
||||
|
||||
* Added `amd-smi static --ras` on Guest VMs. Guest VMs can view enabled/disabled RAS features on Host cards.
|
||||
|
||||
#### Removals
|
||||
##### Removals
|
||||
|
||||
* Removed `amd-smi metric --ecc` & `amd-smi metric --ecc-blocks` on Guest VMs. Guest VMs do not support getting current ECC counts from the Host cards.
|
||||
|
||||
#### Resolved issues
|
||||
##### Resolved issues
|
||||
|
||||
* Fixed TypeError in `amd-smi process -G`.
|
||||
* Updated CLI error strings to handle empty and invalid GPU/CPU inputs.
|
||||
* Fixed Guest VM showing passthrough options.
|
||||
* Fixed firmware formatting where leading 0s were missing.
|
||||
|
||||
### **HIP** (6.2.1)
|
||||
#### **HIP** (6.2.1)
|
||||
|
||||
#### Resolved issues
|
||||
##### Resolved issues
|
||||
|
||||
* Soft hang when using `AMD_SERIALIZE_KERNEL`
|
||||
* Memory leak in `hipIpcCloseMemHandle`
|
||||
|
||||
### **HIPIFY** (18.0.0)
|
||||
#### **HIPIFY** (18.0.0)
|
||||
|
||||
#### Changes
|
||||
##### Changes
|
||||
|
||||
* Added CUDA 12.5.1 support.
|
||||
* Added cuDNN 9.2.1 support.
|
||||
* Added LLVM 18.1.8 support.
|
||||
* Added `hipBLAS` 64-bit APIs support.
|
||||
* Added Support for math constants `math_constants.h`.
|
||||
* Added CUDA 12.5.1 support
|
||||
* Added cuDNN 9.2.1 support
|
||||
* Added LLVM 18.1.8 support
|
||||
* Added `hipBLAS` 64-bit APIs support
|
||||
* Added Support for math constants `math_constants.h`
|
||||
|
||||
### **Omniperf** (2.0.1)
|
||||
#### **Omnitrace** (1.11.2)
|
||||
|
||||
#### Changes
|
||||
|
||||
* Enabled rocprofv1 for MI300 hardware.
|
||||
* Added dependency checks on application launch.
|
||||
* Updated Omniperf packaging.
|
||||
* Rolled back Grafana version in Dockerfile for Angular plugin compatibility.
|
||||
* Added GPU model distinction for MI300 systems.
|
||||
* Refactored and updated documemtation.
|
||||
|
||||
#### Resolved issues
|
||||
|
||||
* Fixed an issue with analysis output.
|
||||
* Fixed issues with profiling multi-process and multi-GPU applications.
|
||||
|
||||
#### Optimizations
|
||||
|
||||
* Reduced running time of Omniperf when profiling.
|
||||
* Improved console logging.
|
||||
|
||||
### **Omnitrace** (1.11.2)
|
||||
|
||||
#### Known issues
|
||||
##### Known issues
|
||||
|
||||
Perfetto can no longer open Omnitrace proto files. Loading Perfetto trace output `.proto` files in the latest version of `ui.perfetto.dev` can result in a dialog with the message, "Oops, something went wrong! Please file a bug." The information in the dialog will refer to an "Unknown field type." The workaround is to open the files with the previous version of the Perfetto UI found at [https://ui.perfetto.dev/v46.0-35b3d9845/#!/](https://ui.perfetto.dev/v46.0-35b3d9845/#!/).
|
||||
|
||||
See [issue #3767](https://github.com/ROCm/ROCm/issues/3767) on GitHub.
|
||||
|
||||
### **RCCL** (2.20.5)
|
||||
#### **RCCL** (2.20.5)
|
||||
|
||||
#### Known issues
|
||||
##### Known issues
|
||||
|
||||
On systems running Linux kernel 6.8.0, such as Ubuntu 24.04, Direct Memory Access (DMA) transfers between the GPU and NIC are disabled and impacts multi-node RCCL performance.
|
||||
This issue was reproduced with RCCL 2.20.5 (ROCm 6.2.0 and 6.2.1) on systems with Broadcom Thor-2 NICs and affects other systems with RoCE networks using Linux 6.8.0 or newer.
|
||||
@@ -501,9 +509,9 @@ This issue will be addressed in a future ROCm release.
|
||||
|
||||
See [issue #3772](https://github.com/ROCm/ROCm/issues/3772) on GitHub.
|
||||
|
||||
### **rocAL** (2.0.0)
|
||||
#### **rocAL** (2.0.0)
|
||||
|
||||
#### Changes
|
||||
##### Changes
|
||||
|
||||
* The new version of rocAL introduces many new features, but does not modify any of the existing public API functions.However, the version number was incremented from 1.3 to 2.0.
|
||||
Applications linked to version 1.3 must be recompiled to link against version 2.0.
|
||||
@@ -524,37 +532,37 @@ See [issue #3772](https://github.com/ROCm/ROCm/issues/3772) on GitHub.
|
||||
* Image to tensor updates
|
||||
* ROCm install - use case graphics removed
|
||||
|
||||
#### Known issues
|
||||
##### Known issues
|
||||
|
||||
* Dependencies are not installed with the rocAL package installer. Dependencies must be installed with the prerequisite setup script provided. See the [rocAL README on GitHub](https://github.com/ROCm/rocAL/blob/docs/6.2.1/README.md#prerequisites-setup-script) for details.
|
||||
|
||||
### **rocBLAS** (4.2.1)
|
||||
#### **rocBLAS** (4.2.1)
|
||||
|
||||
#### Removals
|
||||
##### Removals
|
||||
|
||||
* Removed Device_Memory_Allocation.pdf link in documentation.
|
||||
|
||||
#### Resolved issues
|
||||
##### Resolved issues
|
||||
|
||||
* Fixed error/warning message during `rocblas_set_stream()` call.
|
||||
|
||||
### **rocFFT** (1.0.29)
|
||||
#### **rocFFT** (1.0.29)
|
||||
|
||||
#### Optimizations
|
||||
##### Optimizations
|
||||
|
||||
* Implemented 1D kernels for factorizable sizes less than 1024.
|
||||
|
||||
### **ROCm SMI** (7.3.0)
|
||||
#### **ROCm SMI** (7.3.0)
|
||||
|
||||
#### Optimizations
|
||||
##### Optimizations
|
||||
|
||||
* Improved handling of UnicodeEncodeErrors with non UTF-8 locales. Non UTF-8 locales were causing crashes on UTF-8 special characters.
|
||||
|
||||
#### Resolved issues
|
||||
##### Resolved issues
|
||||
|
||||
* Fixed an issue where the Compute Partition tests segfaulted when AMDGPU was loaded with optional parameters.
|
||||
|
||||
#### Known issues
|
||||
##### Known issues
|
||||
|
||||
* When setting CPX as a partition mode, there is a DRM node limit of 64. This is a known limitation when multiple drivers are using the DRM nodes. The `ls /sys/class/drm` command can be used to see the number of DRM nodes, and the following steps can be used to remove unnecessary drivers:
|
||||
|
||||
@@ -562,18 +570,18 @@ See [issue #3772](https://github.com/ROCm/ROCm/issues/3772) on GitHub.
|
||||
2. Remove any unnecessary drivers using `rmmod`. For example, to remove an AST driver, run `sudo rmmod ast`.
|
||||
3. Reload AMDGPU using `modprobe`: `sudo modprobe amdgpu`.
|
||||
|
||||
### **rocPRIM** (3.2.1)
|
||||
#### **rocPRIM** (3.2.1)
|
||||
|
||||
#### Optimizations
|
||||
##### Optimizations
|
||||
|
||||
* Improved performance of `block_reduce_warp_reduce` when warp size equals block size.
|
||||
|
||||
## ROCm known issues
|
||||
### ROCm known issues
|
||||
|
||||
ROCm known issues are tracked on [GitHub](https://github.com/ROCm/ROCm/labels/Verified%20Issue). Known issues related to
|
||||
individual components are listed in the [Detailed component changes](detailed-component-changes) section.
|
||||
|
||||
### Instinct MI300X GPU recovery failure on uncorrectable errors
|
||||
#### Instinct MI300X GPU recovery failure on uncorrectable errors
|
||||
|
||||
For the AMD Instinct MI300X accelerator, GPU recovery resets triggered by uncorrectable errors (UE) might not complete
|
||||
successfully, which can result in the system being left in an undefined state. A system reboot is needed to recover from
|
||||
@@ -583,14 +591,14 @@ This issue is under investigation and will be resolved in a future ROCm release.
|
||||
|
||||
See [issue #3766](https://github.com/ROCm/ROCm/issues/3766) on GitHub.
|
||||
|
||||
## ROCm upcoming changes
|
||||
### ROCm upcoming changes
|
||||
|
||||
The following changes to the ROCm software stack are anticipated for future releases.
|
||||
|
||||
### rocm-llvm-alt
|
||||
#### rocm-llvm-alt
|
||||
|
||||
The `rocm-llvm-alt` package will be removed in an upcoming release. Users relying on the functionality provided by the closed-source compiler should transition to the open-source compiler. Once the `rocm-llvm-alt` package is removed, any compilation requesting functionality provided by the closed-source compiler will result in a Clang warning: "*[AMD] proprietary optimization compiler has been removed*".
|
||||
|
||||
### rccl-rdma-sharp-plugins
|
||||
#### rccl-rdma-sharp-plugins
|
||||
|
||||
The RCCL plugin package, `rccl-rdma-sharp-plugins`, will be removed in an upcoming ROCm release.
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<manifest>
|
||||
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
|
||||
<default revision="refs/tags/rocm-6.2.1"
|
||||
<default revision="refs/tags/rocm-6.2.2"
|
||||
remote="rocm-org"
|
||||
sync-c="true"
|
||||
sync-j="4" />
|
||||
|
||||
@@ -91,8 +91,7 @@ additional licenses. Please review individual repositories for more information.
|
||||
|
||||
Open sourced ROCm components are released via public GitHub
|
||||
repositories, packages on [https://repo.radeon.com](https://repo.radeon.com) and other distribution channels.
|
||||
Proprietary products are only available on [https://repo.radeon.com](https://repo.radeon.com). Currently, only
|
||||
one component of ROCm, `rocm-llvm-alt` is governed by a proprietary license.
|
||||
Proprietary products are only available on [https://repo.radeon.com](https://repo.radeon.com).
|
||||
Proprietary components are organized in a proprietary subdirectory in the package
|
||||
repositories to distinguish from open sourced packages.
|
||||
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
ROCm Version,6.2.1,6.2.0, 6.1.5, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
|
||||
:ref:`Operating Systems & kernels <OS-kernel-versions>`,"Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,,
|
||||
,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4, 22.04.3","Ubuntu 22.04.5, 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3, 22.04.2","Ubuntu 22.04.4, 22.04.3, 22.04.2"
|
||||
,,,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
|
||||
,"RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
|
||||
,"RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
|
||||
,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
|
||||
ROCm Version,6.2.2,6.2.1,6.2.0, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
|
||||
:ref:`Operating systems & kernels <OS-kernel-versions>`,"Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,
|
||||
,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3, 22.04.2","Ubuntu 22.04.4, 22.04.3, 22.04.2"
|
||||
,,,,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
|
||||
,"RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
|
||||
,"RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
|
||||
,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
|
||||
,,,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
|
||||
,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,,,
|
||||
,.. _architecture-support-compatibility-matrix-past-60:,,,,,,,
|
||||
@@ -16,102 +16,102 @@ ROCm Version,6.2.1,6.2.0, 6.1.5, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
|
||||
,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,
|
||||
:doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
|
||||
,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
|
||||
,gfx942 [#mi300_621-past-60]_,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
|
||||
,gfx942 [#mi300_622-past-60]_,gfx942 [#mi300_621-past-60]_,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
|
||||
,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
|
||||
,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
|
||||
,,,,,,,,
|
||||
FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,
|
||||
:doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>`,"2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
|
||||
:doc:`TensorFlow <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
|
||||
:doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>`,"2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
|
||||
:doc:`TensorFlow <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
|
||||
:doc:`JAX <rocm-install-on-linux:install/3rd-party/jax-install>`,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
|
||||
`ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
|
||||
,,,,,,,,
|
||||
THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix-past-60:,,,,,,,
|
||||
`UCC <https://github.com/ROCm/ucc>`_,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.2.0,>=1.2.0
|
||||
`UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
|
||||
`UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.15.0,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
|
||||
,,,,,,,,
|
||||
THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix-past-60:,,,,,,,
|
||||
Thrust,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
|
||||
CUB,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
|
||||
Thrust,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
|
||||
CUB,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
|
||||
,,,,,,,,
|
||||
KFD & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,
|
||||
Tested user space versions,"6.1.x, 6.0.x","6.1.x, 6.0.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.0.x, 5.7.x, 5.6.x"
|
||||
Tested user space versions,"6.1.x, 6.0.x","6.1.x, 6.0.x","6.1.x, 6.0.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x","6.2.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.0.x, 5.7.x, 5.6.x"
|
||||
,,,,,,,,
|
||||
ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix-past-60:,,,,,,,
|
||||
:doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
|
||||
:doc:`MIGraphX <amdmigraphx:index>`,2.10.0,2.10.0,2.9.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
|
||||
:doc:`MIOpen <miopen:index>`,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
|
||||
:doc:`MIVisionX <mivisionx:index>`,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
|
||||
:doc:`rocAL <rocal:index>`,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
|
||||
:doc:`MIGraphX <amdmigraphx:index>`,2.10.0,2.10.0,2.10.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
|
||||
:doc:`MIOpen <miopen:index>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
|
||||
:doc:`MIVisionX <mivisionx:index>`,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
|
||||
:doc:`rocAL <rocal:index>`,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
|
||||
:doc:`rocDecode <rocdecode:index>`,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
|
||||
:doc:`rocPyDecode <rocpydecode:index>`,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A,N/A
|
||||
:doc:`RPP <rpp:index>`,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
|
||||
:doc:`rocPyDecode <rocpydecode:index>`,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A
|
||||
:doc:`RPP <rpp:index>`,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
|
||||
,,,,,,,,
|
||||
COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,
|
||||
:doc:`RCCL <rccl:index>`,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
|
||||
:doc:`RCCL <rccl:index>`,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
|
||||
,,,,,,,,
|
||||
MATH LIBS,.. _mathlibs-support-compatibility-matrix-past-60:,,,,,,,
|
||||
`half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0
|
||||
:doc:`hipBLAS <hipblas:index>`,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
|
||||
:doc:`hipBLASLt <hipblaslt:index>`,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
|
||||
:doc:`hipFFT <hipfft:index>`,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
|
||||
:doc:`hipBLAS <hipblas:index>`,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
|
||||
:doc:`hipBLASLt <hipblaslt:index>`,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
|
||||
:doc:`hipFFT <hipfft:index>`,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
|
||||
:doc:`hipFORT <hipfort:index>`,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
|
||||
:doc:`hipRAND <hiprand:index>`,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
|
||||
:doc:`hipSOLVER <hipsolver:index>`,2.2.0,2.2.0,2.1.1,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
|
||||
:doc:`hipSPARSE <hipsparse:index>`,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
|
||||
:doc:`hipSPARSELt <hipsparselt:index>`,0.2.1,0.2.1,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
|
||||
:doc:`rocALUTION <rocalution:index>`,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
|
||||
:doc:`rocBLAS <rocblas:index>`,4.2.1,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
|
||||
:doc:`rocFFT <rocfft:index>`,1.0.29,1.0.28,1.0.27,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
|
||||
:doc:`rocRAND <rocrand:index>`,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
|
||||
:doc:`rocSOLVER <rocsolver:index>`,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
|
||||
:doc:`rocSPARSE <rocsparse:index>`,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
|
||||
:doc:`rocWMMA <rocwmma:index>`,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
|
||||
:doc:`hipRAND <hiprand:index>`,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
|
||||
:doc:`hipSOLVER <hipsolver:index>`,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
|
||||
:doc:`hipSPARSE <hipsparse:index>`,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
|
||||
:doc:`hipSPARSELt <hipsparselt:index>`,0.2.1,0.2.1,0.2.1,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
|
||||
:doc:`rocALUTION <rocalution:index>`,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
|
||||
:doc:`rocBLAS <rocblas:index>`,4.2.1,4.2.1,4.2.0,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
|
||||
:doc:`rocFFT <rocfft:index>`,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
|
||||
:doc:`rocRAND <rocrand:index>`,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
|
||||
:doc:`rocSOLVER <rocsolver:index>`,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
|
||||
:doc:`rocSPARSE <rocsparse:index>`,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
|
||||
:doc:`rocWMMA <rocwmma:index>`,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
|
||||
`Tensile <https://github.com/ROCm/Tensile>`_,4.40.0,4.40.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
|
||||
,,,,,,,,
|
||||
PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,
|
||||
:doc:`hipCUB <hipcub:index>`,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
|
||||
:doc:`hipTensor <hiptensor:index>`,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
|
||||
:doc:`rocPRIM <rocprim:index>`,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
|
||||
:doc:`rocThrust <rocthrust:index>`,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
|
||||
:doc:`hipCUB <hipcub:index>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
|
||||
:doc:`hipTensor <hiptensor:index>`,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
|
||||
:doc:`rocPRIM <rocprim:index>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
|
||||
:doc:`rocThrust <rocthrust:index>`,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
|
||||
,,,,,,,,
|
||||
SUPPORT LIBS,,,,,,,,
|
||||
`hipother <https://github.com/ROCm/hipother>`_,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
|
||||
`rocm-core <https://github.com/ROCm/rocm-core>`_,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
|
||||
`ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
|
||||
`hipother <https://github.com/ROCm/hipother>`_,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
|
||||
`rocm-core <https://github.com/ROCm/rocm-core>`_,6.2.2,6.2.1,6.2.0,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
|
||||
`ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240607.4.05,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
|
||||
,,,,,,,,
|
||||
SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,,
|
||||
:doc:`AMD SMI <amdsmi:index>`,24.6.3,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
|
||||
:doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
|
||||
:doc:`AMD SMI <amdsmi:index>`,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
|
||||
:doc:`ROCm Data Center Tool <rdc:index>`,1.0.0,1.0.0,1.0.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
|
||||
:doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
|
||||
:doc:`ROCm SMI <rocm_smi_lib:index>`,7.3.0,7.3.0,7.2.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
|
||||
:doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.2.1,rocm-6.2.0,rocm-6.1.5,rocm-6.1.2,rocm-6.1.1,rocm-6.1.0,rocm-6.0.2,rocm-6.0.0
|
||||
:doc:`ROCm SMI <rocm_smi_lib:index>`,7.3.0,7.3.0,7.3.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
|
||||
:doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.2.2,rocm-6.2.1,rocm-6.2.0,rocm-6.1.2,rocm-6.1.1,rocm-6.1.0,rocm-6.0.2,rocm-6.0.0
|
||||
,,,,,,,,
|
||||
PERFORMANCE TOOLS,,,,,,,,
|
||||
:doc:`Omniperf <omniperf:index>`,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
|
||||
:doc:`Omnitrace <omnitrace:index>`,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A,N/A
|
||||
:doc:`Omniperf <omniperf:index>`,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A
|
||||
:doc:`Omnitrace <omnitrace:index>`,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A
|
||||
:doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
|
||||
:doc:`ROCProfiler <rocprofiler:index>`,2.0.60201,2.0.60200,2.0.60105,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
|
||||
:doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A,N/A
|
||||
:doc:`ROCTracer <roctracer:index>`,4.1.60201,4.1.60200,4.1.60105,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
|
||||
:doc:`ROCProfiler <rocprofiler:index>`,2.0.60202,2.0.60201,2.0.60200,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
|
||||
:doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A
|
||||
:doc:`ROCTracer <roctracer:index>`,4.1.60202,4.1.60201,4.1.60200,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
|
||||
,,,,,,,,
|
||||
DEVELOPMENT TOOLS,,,,,,,,
|
||||
:doc:`HIPIFY <hipify:index>`,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
|
||||
:doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
|
||||
:doc:`ROCdbgapi <rocdbgapi:index>`,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
|
||||
:doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
|
||||
`rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,0.3.0,N/A,N/A
|
||||
:doc:`HIPIFY <hipify:index>`,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
|
||||
:doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
|
||||
:doc:`ROCdbgapi <rocdbgapi:index>`,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
|
||||
:doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,14.2.0,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
|
||||
`rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,N/A,N/A
|
||||
:doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
|
||||
,,,,,,,,
|
||||
COMPILERS,.. _compilers-support-compatibility-matrix-past-60:,,,,,,,
|
||||
`clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
|
||||
:doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
|
||||
`Flang <https://github.com/ROCm/flang>`_,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
|
||||
:doc:`llvm-project <llvm-project:index>`,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
|
||||
`OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
|
||||
`clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
|
||||
:doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
|
||||
`Flang <https://github.com/ROCm/flang>`_,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
|
||||
:doc:`llvm-project <llvm-project:index>`,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
|
||||
`OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
|
||||
,,,,,,,,
|
||||
RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,
|
||||
:doc:`AMD CLR <hip:understand/amd_clr>`,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
|
||||
:doc:`HIP <hip:index>`,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
|
||||
:doc:`AMD CLR <hip:understand/amd_clr>`,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
|
||||
:doc:`HIP <hip:index>`,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
|
||||
`OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0
|
||||
:doc:`ROCR-Runtime <rocr-runtime:index>`,1.14.0,1.13.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0
|
||||
:doc:`ROCR-Runtime <rocr-runtime:index>`,1.14.0,1.14.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0
|
||||
|
||||
|
@@ -10,6 +10,11 @@ Use this matrix to view the ROCm compatibility and system requirements across su
|
||||
|
||||
You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-rocm-compatibility-matrix>`.
|
||||
|
||||
|
||||
.. note::
|
||||
|
||||
Like AMD Instinct accelerators, AMD Radeon and Radeon Pro GPUs can be used in environments for compute purposes (no display information or graphics). If using AMD Radeon or Radeon Pro GPUs with ROCm for graphics-related purposes (for example, display connected), review the `Compatibility matrices <https://rocm.docs.amd.com/projects/radeon/en/latest/docs/compatibility.html>`_ in the Use ROCm on Radeon GPU documentation to confirm system requirements.
|
||||
|
||||
.. |br| raw:: html
|
||||
|
||||
<br/>
|
||||
@@ -17,10 +22,10 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
|
||||
.. container:: format-big-table
|
||||
|
||||
.. csv-table::
|
||||
:header: "ROCm Version", "6.2.1", "6.2.0", "6.1.0"
|
||||
:header: "ROCm Version", "6.2.2", "6.2.1", "6.1.0"
|
||||
:stub-columns: 1
|
||||
|
||||
:ref:`Operating Systems & kernels <OS-kernel-versions>`,"Ubuntu 24.04.1, 24.04",Ubuntu 24.04,
|
||||
:ref:`Operating systems & kernels <OS-kernel-versions>`,"Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04
|
||||
,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.4, 22.04.3"
|
||||
,,,"Ubuntu 20.04.6, 20.04.5"
|
||||
,"RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4 [#red-hat94]_, 9.3, 9.2"
|
||||
@@ -37,7 +42,7 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
|
||||
,.. _gpu-support-compatibility-matrix:,,
|
||||
:doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100,gfx1100
|
||||
,gfx1030,gfx1030,gfx1030
|
||||
,gfx942 [#mi300_621]_,gfx942 [#mi300_620]_, gfx942 [#mi300_610]_
|
||||
,gfx942 [#mi300_622]_,gfx942 [#mi300_621]_, gfx942 [#mi300_610]_
|
||||
,gfx90a,gfx90a,gfx90a
|
||||
,gfx908,gfx908,gfx908
|
||||
,,,
|
||||
@@ -63,7 +68,7 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
|
||||
:doc:`MIGraphX <amdmigraphx:index>`,2.10.0,2.10.0,2.9.0
|
||||
:doc:`MIOpen <miopen:index>`,3.2.0,3.2.0,3.1.0
|
||||
:doc:`MIVisionX <mivisionx:index>`,3.0.0,3.0.0,2.5.0
|
||||
:doc:`rocAL <rocal:index>`,2.0.0,1.0.0,1.0.0
|
||||
:doc:`rocAL <rocal:index>`,2.0.0,2.0.0,1.0.0
|
||||
:doc:`rocDecode <rocdecode:index>`,0.6.0,0.6.0,0.5.0
|
||||
:doc:`rocPyDecode <rocpydecode:index>`,0.1.0,0.1.0,N/A
|
||||
:doc:`RPP <rpp:index>`,1.8.0,1.8.0,1.5.0
|
||||
@@ -75,15 +80,15 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
|
||||
`half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0
|
||||
:doc:`hipBLAS <hipblas:index>`,2.2.0,2.2.0,2.1.0
|
||||
:doc:`hipBLASLt <hipblaslt:index>`,0.8.0,0.8.0,0.7.0
|
||||
:doc:`hipFFT <hipfft:index>`,1.0.15,1.0.14,1.0.14
|
||||
:doc:`hipFFT <hipfft:index>`,1.0.15,1.0.15,1.0.14
|
||||
:doc:`hipFORT <hipfort:index>`,0.4.0,0.4.0,0.4.0
|
||||
:doc:`hipRAND <hiprand:index>`,2.11.0,2.11.0,2.10.16
|
||||
:doc:`hipSOLVER <hipsolver:index>`,2.2.0,2.2.0,2.1.0
|
||||
:doc:`hipSPARSE <hipsparse:index>`,3.1.1,3.1.1,3.0.1
|
||||
:doc:`hipSPARSELt <hipsparselt:index>`,0.2.1,0.2.1,0.1.0
|
||||
:doc:`rocALUTION <rocalution:index>`,3.2.0,3.2.0,3.1.1
|
||||
:doc:`rocBLAS <rocblas:index>`,4.2.1,4.2.0,4.1.0
|
||||
:doc:`rocFFT <rocfft:index>`,1.0.29,1.0.28,1.0.26
|
||||
:doc:`rocBLAS <rocblas:index>`,4.2.1,4.2.1,4.1.0
|
||||
:doc:`rocFFT <rocfft:index>`,1.0.29,1.0.29,1.0.26
|
||||
:doc:`rocRAND <rocrand:index>`,3.1.0,3.1.0,3.0.1
|
||||
:doc:`rocSOLVER <rocsolver:index>`,3.26.0,3.26.0,3.25.0
|
||||
:doc:`rocSPARSE <rocsparse:index>`,3.2.0,3.2.0,3.1.2
|
||||
@@ -94,30 +99,30 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
|
||||
:doc:`hipCUB <hipcub:index>`,3.2.0,3.2.0,3.1.0
|
||||
:doc:`hipTensor <hiptensor:index>`,1.3.0,1.3.0,1.2.0
|
||||
:doc:`rocPRIM <rocprim:index>`,3.2.0,3.2.0,3.1.0
|
||||
:doc:`rocThrust <rocthrust:index>`,3.1.0,3.0.1,3.0.1
|
||||
:doc:`rocThrust <rocthrust:index>`,3.1.0,3.1.0,3.0.1
|
||||
,,,
|
||||
SUPPORT LIBS,,,
|
||||
`hipother <https://github.com/ROCm/hipother>`_,6.2.41134,6.2.41133,6.1.40091
|
||||
`rocm-core <https://github.com/ROCm/rocm-core>`_,6.2.1,6.2.0,6.1.0
|
||||
`ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240607.4.05,20240607.1.4246,20240125.3.30
|
||||
`hipother <https://github.com/ROCm/hipother>`_,6.2.41134,6.2.41134,6.1.40091
|
||||
`rocm-core <https://github.com/ROCm/rocm-core>`_,6.2.2,6.2.1,6.1.0
|
||||
`ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240607.4.05,20240607.4.05,20240125.3.30
|
||||
,,,
|
||||
SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix:,,
|
||||
:doc:`AMD SMI <amdsmi:index>`,24.6.3,24.6.2,24.4.1
|
||||
:doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0,0.3.0
|
||||
:doc:`AMD SMI <amdsmi:index>`,24.6.3,24.6.3,24.4.1
|
||||
:doc:`ROCm Data Center Tool <rdc:index>`,1.0.0,1.0.0,0.3.0
|
||||
:doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0
|
||||
:doc:`ROCm SMI <rocm_smi_lib:index>`,7.3.0,7.3.0,7.0.0
|
||||
:doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.2.1,rocm-6.2.0,rocm-6.1.0
|
||||
:doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.2.2,rocm-6.2.1,rocm-6.1.0
|
||||
,,,
|
||||
PERFORMANCE TOOLS,,,
|
||||
:doc:`Omniperf <omniperf:index>`,2.0.1,2.0.1,N/A
|
||||
:doc:`Omnitrace <omnitrace:index>`,1.11.2,1.11.2,N/A
|
||||
:doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0
|
||||
:doc:`ROCProfiler <rocprofiler:index>`,2.0.60201,2.0.60200,2.0.60100
|
||||
:doc:`ROCProfiler <rocprofiler:index>`,2.0.60202,2.0.60201,2.0.60100
|
||||
:doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.4.0,0.4.0,N/A
|
||||
:doc:`ROCTracer <roctracer:index>`,4.1.60201,4.1.60200,4.1.60100
|
||||
:doc:`ROCTracer <roctracer:index>`,4.1.60202,4.1.60201,4.1.60100
|
||||
,,,
|
||||
DEVELOPMENT TOOLS,,,
|
||||
:doc:`HIPIFY <hipify:index>`,18.0.0.24355,18.0.0.24232,17.0.0.24103
|
||||
:doc:`HIPIFY <hipify:index>`,18.0.0.24355,18.0.0.24355,17.0.0.24103
|
||||
:doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.13.0,0.13.0,0.12.0
|
||||
:doc:`ROCdbgapi <rocdbgapi:index>`,0.76.0,0.76.0,0.71.0
|
||||
:doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,14.2.0,14.2.0,14.1.0
|
||||
@@ -127,25 +132,25 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
|
||||
COMPILERS,.. _compilers-support-compatibility-matrix:,,
|
||||
`clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,0.5.0
|
||||
:doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.0.0
|
||||
`Flang <https://github.com/ROCm/flang>`_,18.0.0.24355,18.0.0.24232,17.0.0.24103
|
||||
:doc:`llvm-project <llvm-project:index>`,18.0.0.24355,18.0.0.24232,17.0.0.24103
|
||||
`OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24355,18.0.0.24232,17.0.0.24103
|
||||
`Flang <https://github.com/ROCm/flang>`_,18.0.0.24355,18.0.0.24355,17.0.0.24103
|
||||
:doc:`llvm-project <llvm-project:index>`,18.0.0.24355,18.0.0.24355,17.0.0.24103
|
||||
`OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24355,18.0.0.24355,17.0.0.24103
|
||||
,,,
|
||||
RUNTIMES,.. _runtime-support-compatibility-matrix:,,
|
||||
:doc:`AMD CLR <hip:understand/amd_clr>`,6.2.41134,6.2.41133,6.1.40091
|
||||
:doc:`HIP <hip:index>`,6.2.41134,6.2.41133,6.1.40091
|
||||
:doc:`AMD CLR <hip:understand/amd_clr>`,6.2.41134,6.2.41134,6.1.40091
|
||||
:doc:`HIP <hip:index>`,6.2.41134,6.2.41134,6.1.40091
|
||||
`OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0
|
||||
:doc:`ROCR-Runtime <rocr-runtime:index>`,1.14.0,1.13.0,1.13.0
|
||||
:doc:`ROCR-Runtime <rocr-runtime:index>`,1.14.0,1.14.0,1.13.0
|
||||
|
||||
|
||||
.. rubric:: Footnotes
|
||||
|
||||
.. [#red-hat94] **For ROCm 6.1** - RHEL 9.4 is supported only on AMD Instinct MI300A.
|
||||
.. [#red-hat94] RHEL 9.4 is supported only on AMD Instinct MI300A.
|
||||
.. [#oracle89] Oracle Linux is supported only on AMD Instinct MI300X.
|
||||
.. [#mi300_622] **For ROCm 6.2.2** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
|
||||
.. [#mi300_621] **For ROCm 6.2.1** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
|
||||
.. [#mi300_620] **For ROCm 6.2.0** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
|
||||
.. [#mi300_610] **For ROCm 6.1.0** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4.
|
||||
.. [#kfd_support] ROCm provides forward and backward compatibility between the Kernel Fusion Driver (KFD) and its user space software for +/- 2 releases. The tested user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
|
||||
.. [#kfd_support] ROCm provides forward and backward compatibility between the Kernel Fusion Driver (KFD) and its user space software for +/- 2 releases. These are the compatibility combinations that are currently supported.
|
||||
|
||||
|
||||
.. _OS-kernel-versions:
|
||||
@@ -207,7 +212,6 @@ Expand for full historical view of:
|
||||
|
||||
.. csv-table::
|
||||
:file: compatibility-matrix-historical-6.0.csv
|
||||
:widths: 20,10,10,10,10,10,10,10,10
|
||||
:header-rows: 1
|
||||
:stub-columns: 1
|
||||
|
||||
@@ -215,6 +219,7 @@ Expand for full historical view of:
|
||||
|
||||
.. [#red-hat94-past-60] RHEL 9.4 is supported only on AMD Instinct MI300A.
|
||||
.. [#oracle89-past-60] Oracle Linux is supported only on AMD Instinct MI300X.
|
||||
.. [#mi300_622-past-60] **For ROCm 6.2.2** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
|
||||
.. [#mi300_621-past-60] **For ROCm 6.2.1** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
|
||||
.. [#mi300_620-past-60] **For ROCm 6.2.0** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
|
||||
.. [#mi300_612-past-60] **For ROCm 6.1.2** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4 and Oracle Linux.
|
||||
@@ -222,4 +227,4 @@ Expand for full historical view of:
|
||||
.. [#mi300_610-past-60] **For ROCm 6.1.0** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4.
|
||||
.. [#mi300_602-past-60] **For ROCm 6.0.2** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
|
||||
.. [#mi300_600-past-60] **For ROCm 6.0.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
|
||||
.. [#kfd_support-past-60] ROCm provides forward and backward compatibility between the Kernel Fusion Driver (KFD) and its user space software for +/- 2 releases. The tested user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
|
||||
.. [#kfd_support-past-60] ROCm provides forward and backward compatibility between the Kernel Fusion Driver (KFD) and its user space software for +/- 2 releases. These are the compatibility combinations that are currently supported.
|
||||
|
||||
@@ -30,16 +30,15 @@ if os.environ.get("READTHEDOCS", "") == "True":
|
||||
project = "ROCm Documentation"
|
||||
author = "Advanced Micro Devices, Inc."
|
||||
copyright = "Copyright (c) 2024 Advanced Micro Devices, Inc. All rights reserved."
|
||||
version = "6.2.1"
|
||||
release = "6.2.1"
|
||||
version = "6.2.2"
|
||||
release = "6.2.2"
|
||||
setting_all_article_info = True
|
||||
all_article_info_os = ["linux", "windows"]
|
||||
all_article_info_author = ""
|
||||
|
||||
# pages with specific settings
|
||||
article_pages = [
|
||||
{"file": "about/release-notes", "os": ["linux", "windows"], "date": "2024-09-20"},
|
||||
{"file": "about/changelog", "os": ["linux", "windows"], "date": "2024-09-20"},
|
||||
{"file": "about/release-notes", "os": ["linux", "windows"], "date": "2024-09-27"},
|
||||
{"file": "how-to/deep-learning-rocm", "os": ["linux"]},
|
||||
{"file": "how-to/rocm-for-ai/index", "os": ["linux"]},
|
||||
{"file": "how-to/rocm-for-ai/install", "os": ["linux"]},
|
||||
@@ -82,7 +81,6 @@ article_pages = [
|
||||
"file": "how-to/llm-fine-tuning-optimization/profiling-and-debugging",
|
||||
"os": ["linux"],
|
||||
},
|
||||
{"file": "how-to/performance-validation/mi300x/vllm-benchmark", "os": ["linux"]},
|
||||
{"file": "how-to/system-optimization/index", "os": ["linux"]},
|
||||
{"file": "how-to/system-optimization/mi300x", "os": ["linux"]},
|
||||
{"file": "how-to/system-optimization/mi200", "os": ["linux"]},
|
||||
|
||||
@@ -1,153 +0,0 @@
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="description" content="Building ROCm documentation">
|
||||
<meta name="keywords" content="documentation, Visual Studio Code, GitHub, command line,
|
||||
AMD, ROCm">
|
||||
</head>
|
||||
|
||||
# Building documentation
|
||||
|
||||
You can build our documentation via GitHub (in a pull request) or locally (using the command line or
|
||||
Visual Studio (VS) Code.
|
||||
|
||||
## GitHub
|
||||
|
||||
If you open a pull request on the `develop` branch of a ROCm repository and scroll to the bottom of
|
||||
the page, there is a summary panel. Next to the line
|
||||
`docs/readthedocs.com:advanced-micro-devices-demo`, there is a `Details` link. If you click this, it takes
|
||||
you to the Read the Docs build for your pull request.
|
||||
|
||||

|
||||
|
||||
If you don't see this line, click `Show all checks` to get an itemized view.
|
||||
|
||||
## Command line
|
||||
|
||||
You can build our documentation via the command line using Python.
|
||||
|
||||
See the `build.tools.python` setting in the [Read the Docs configuration file](https://github.com/ROCm/ROCm/blob/develop/.readthedocs.yaml) for the Python version used by Read the Docs to build documentation.
|
||||
|
||||
See the [Python requirements file](https://github.com/ROCm/ROCm/blob/develop/docs/sphinx/requirements.txt) for Python packages needed to build the documentation.
|
||||
|
||||
Use the Python Virtual Environment (`venv`) and run the following commands from the project root:
|
||||
|
||||
```sh
|
||||
python3 -mvenv .venv
|
||||
|
||||
.venv/bin/python -m pip install -r docs/sphinx/requirements.txt
|
||||
.venv/bin/python -m sphinx -T -E -b html -d _build/doctrees -D language=en docs _build/html
|
||||
```
|
||||
|
||||
Navigate to `_build/html/index.html` and open this file in a web browser.
|
||||
|
||||
## Visual Studio Code
|
||||
|
||||
With the help of a few extensions, you can create a productive environment to author and test
|
||||
documentation locally using Visual Studio (VS) Code. Follow these steps to configure VS Code:
|
||||
|
||||
1. Install the required extensions:
|
||||
|
||||
* Python: `(ms-python.python)`
|
||||
* Live Server: `(ritwickdey.LiveServer)`
|
||||
|
||||
2. Add the following entries to `.vscode/settings.json`.
|
||||
|
||||
```json
|
||||
{
|
||||
"liveServer.settings.root": "/.vscode/build/html",
|
||||
"liveServer.settings.wait": 1000,
|
||||
"python.terminal.activateEnvInCurrentTerminal": true
|
||||
}
|
||||
```
|
||||
|
||||
* `liveServer.settings.root`: Sets the root of the output website for live previews. Must be changed
|
||||
alongside the `tasks.json` command.
|
||||
* `liveServer.settings.wait`: Tells the live server to wait with the update in order to give Sphinx time to
|
||||
regenerate the site contents and not refresh before the build is complete.
|
||||
* `python.terminal.activateEnvInCurrentTerminal`: Activates the automatic virtual environment, so you
|
||||
can build the site from the integrated terminal.
|
||||
|
||||
3. Add the following tasks to `.vscode/tasks.json`.
|
||||
|
||||
```json
|
||||
{
|
||||
"version": "2.0.0",
|
||||
"tasks": [
|
||||
{
|
||||
"label": "Build Docs",
|
||||
"type": "process",
|
||||
"windows": {
|
||||
"command": "${workspaceFolder}/.venv/Scripts/python.exe"
|
||||
},
|
||||
"command": "${workspaceFolder}/.venv/bin/python3",
|
||||
"args": [
|
||||
"-m",
|
||||
"sphinx",
|
||||
"-j",
|
||||
"auto",
|
||||
"-T",
|
||||
"-b",
|
||||
"html",
|
||||
"-d",
|
||||
"${workspaceFolder}/.vscode/build/doctrees",
|
||||
"-D",
|
||||
"language=en",
|
||||
"${workspaceFolder}/docs",
|
||||
"${workspaceFolder}/.vscode/build/html"
|
||||
],
|
||||
"problemMatcher": [
|
||||
{
|
||||
"owner": "sphinx",
|
||||
"fileLocation": "absolute",
|
||||
"pattern": {
|
||||
"regexp": "^(?:.*\\.{3}\\s+)?(\\/[^:]*|[a-zA-Z]:\\\\[^:]*):(\\d+):\\s+(WARNING|ERROR):\\s+(.*)$",
|
||||
"file": 1,
|
||||
"line": 2,
|
||||
"severity": 3,
|
||||
"message": 4
|
||||
}
|
||||
},
|
||||
{
|
||||
"owner": "sphinx",
|
||||
"fileLocation": "absolute",
|
||||
"pattern": {
|
||||
"regexp": "^(?:.*\\.{3}\\s+)?(\\/[^:]*|[a-zA-Z]:\\\\[^:]*):{1,2}\\s+(WARNING|ERROR):\\s+(.*)$",
|
||||
"file": 1,
|
||||
"severity": 2,
|
||||
"message": 3
|
||||
}
|
||||
}
|
||||
],
|
||||
"group": {
|
||||
"kind": "build",
|
||||
"isDefault": true
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
> Implementation detail: two problem matchers were needed to be defined,
|
||||
> because VS Code doesn't tolerate some problem information being potentially
|
||||
> absent. While a single regex could match all types of errors, if a capture
|
||||
> group remains empty (the line number doesn't show up in all warning/error
|
||||
> messages) but the `pattern` references said empty capture group, VS Code
|
||||
> discards the message completely.
|
||||
|
||||
4. Configure the Python virtual environment (`venv`).
|
||||
|
||||
From the Command Palette, run `Python: Create Environment`. Select `venv` environment and
|
||||
`docs/sphinx/requirements.txt`.
|
||||
|
||||
5. Build the docs.
|
||||
|
||||
Launch the default build task using one of the following options:
|
||||
|
||||
* A hotkey (the default is `Ctrl+Shift+B`)
|
||||
* Issuing the `Tasks: Run Build Task` from the Command Palette
|
||||
|
||||
6. Open the live preview.
|
||||
|
||||
Navigate to the site output within VS Code: right-click on `.vscode/build/html/index.html` and
|
||||
select `Open with Live Server`. The contents should update on every rebuild without having to
|
||||
refresh the browser.
|
||||
@@ -4,113 +4,68 @@
|
||||
<meta name="keywords" content="ROCm, contributing, contribute, maintainer, contributor">
|
||||
</head>
|
||||
|
||||
# Contribute to ROCm documentation
|
||||
# Contributing to the ROCm documentation
|
||||
|
||||
All ROCm projects are GitHub-based, so if you want to contribute, you can do so by:
|
||||
The ROCm documentation, like all of ROCm, is open source and available on GitHub. You can contribute to the ROCm documentation by forking the appropriate repository, making your changes, and opening a pull request.
|
||||
|
||||
* [Submitting a pull request in the appropriate GitHub repository](#submit-a-pull-request)
|
||||
* [Creating an issue in the appropriate GitHub repository](#create-an-issue)
|
||||
* [Suggesting a new feature](#suggest-a-new-feature)
|
||||
To provide feedback on the ROCm documentation, including submitting an issue or suggesting a feature, see [Providing feedback about the ROCm documentation](./feedback.md).
|
||||
|
||||
```{important}
|
||||
By creating a pull request (PR), you agree to allow your contribution to be licensed under the terms of the
|
||||
LICENSE.txt file in the corresponding repository. Different repositories may use different licenses.
|
||||
```
|
||||
## The ROCm repositories
|
||||
|
||||
## Submit a pull request
|
||||
The repositories for ROCm and all ROCm components are available on GitHub.
|
||||
|
||||
To make edits to our documentation via PR, follow these steps:
|
||||
| Module | Documentation location |
|
||||
| --- | --- |
|
||||
| ROCm framework | [https://github.com/ROCm/ROCm/tree/develop/docs](https://github.com/ROCm/ROCm/tree/develop/docs) |
|
||||
| ROCm installation for Linux | [https://github.com/ROCm/rocm-install-on-linux/tree/develop/docs](https://github.com/ROCm/rocm-install-on-linux/tree/develop/docs) |
|
||||
| ROCm HIP SDK installation for Windows | [https://github.com/ROCm/rocm-install-on-windows/tree/develop/docs](https://github.com/ROCm/rocm-install-on-windows/tree/develop/docs) |
|
||||
|
||||
1. Identify the repository and the file you want to update. For example, to update this page, you would
|
||||
need to modify content located in this file:
|
||||
`https://github.com/ROCm/ROCm/blob/develop/docs/contribute/contributing.md`
|
||||
Individual components have their own repositories with their own documentation in their own `docs` folders.
|
||||
|
||||
2. (optional, but recommended) Fork the repository.
|
||||
The sub-folders within the `docs` folders across ROCm are typically structured as follows:
|
||||
|
||||
3. Clone the repository locally and (optionally) add your fork. Select the green 'Code' button and copy
|
||||
the URL (e.g., `git@github.com:ROCm/ROCm.git`).
|
||||
| Sub-folder name | Documentation type |
|
||||
|-------|----------|
|
||||
| `install` | Installation instructions, build instructions, and prerequisites |
|
||||
| `conceptual` | Important concepts |
|
||||
| `how-to` | How to implement specific use cases |
|
||||
| `tutorials` | Tutorials |
|
||||
| `reference` | API references and other reference resources |
|
||||
|
||||
* From your terminal, run:
|
||||
## Editing and adding to the documentation
|
||||
|
||||
```bash
|
||||
git clone git@github.com:ROCm/ROCm.git
|
||||
```
|
||||
The ROCm documentation is written in [reStructuredText (rst)](https://www.sphinx-doc.org/en/master/usage/restructuredtext/index.html) and [Github-flavoured Markdown](https://github.github.com/gfm/), and follows the [Google developer documentation style guide](https://developers.google.com/style/highlights). reStructuredText is preferred when adding content to the documentation.
|
||||
|
||||
* Optionally add your fork to this local copy of the repository by running:
|
||||
To edit or add to the documentation:
|
||||
|
||||
```bash
|
||||
git add remote <name-of-my-fork> <git@github.com:my-username/ROCm.git>
|
||||
```
|
||||
1. Fork the repository you want to add to or edit.
|
||||
2. Clone your fork locally.
|
||||
3. Create a new local branch cut from the `develop` branch of the repository.
|
||||
4. Make your changes to the documentation.
|
||||
|
||||
To get the URL of your fork, go to your GitHub profile, select the fork and click the green 'Code'
|
||||
button (the same process you followed to get the main GitHub repository URL).
|
||||
|
||||
4. Change directory into your local copy of the repository, and run ``git pull`` (or ``git pull origin develop``) to ensure your local copy has the most recent content.
|
||||
|
||||
5. Create and checkout a new branch using the following command:
|
||||
5. Optionally, build the documentation locally before creating a pull request by running the following commands from within the `docs` folder:
|
||||
|
||||
```bash
|
||||
git checkout -b <branch_name>
|
||||
```
|
||||
|
||||
6. Change directory into the `./docs` folder and make any documentation changes locally using your preferred code editor. Follow the guidelines listed on the
|
||||
[documentation structure](./doc-structure.md) page.
|
||||
|
||||
```{note}
|
||||
Spell checking is performed for pull requests by {doc}`ROCm Docs Core<rocm-docs-core:index>`. To ensure your PR passes spell checking you might need at add new words or acronyms to the `.wordlist.txt` file as described in {doc}`Spell Check<rocm-docs-core:user_guide/spellcheck>`.
|
||||
```
|
||||
|
||||
7. Optionally run a local test build of the documentation to ensure the content builds and looks as expected. In your terminal, run the following commands from within the `./docs` folder of your cloned repository:
|
||||
|
||||
```bash
|
||||
pip3 install -r sphinx/requirements.txt # You only need to run this command once
|
||||
python3 -m sphinx -T -E -b html -d _build/doctrees -D language=en . _build/html
|
||||
```
|
||||
|
||||
The build output files are located in the `docs/_build` folder. To preview your build, open the index file
|
||||
(`docs/_build/html/index.html`) file. For more information, see [Building documentation](building.md). To learn
|
||||
more about our build tools, see [Documentation toolchain](toolchain.md).
|
||||
The output files will be located in the `docs/_build` folder. Open `docs/_build/html/index.html` to view the documentation.
|
||||
|
||||
8. Commit your changes and push them to GitHub by running:
|
||||
For more information on ROCm build tools, see [Documentation toolchain](toolchain.md).
|
||||
6. Push your changes. A GitHub link will be returned in the output of the `git push` command. Open this link in a browser to create the pull request.
|
||||
|
||||
```bash
|
||||
git add <path-to-my-modified-file> # To add all modified files, you can use: git add .
|
||||
git commit -m "my-updates"
|
||||
git push <name-of-my-fork>
|
||||
```
|
||||
The documentation is built as part of the checks on pull request, along with spell checking and linting. Scroll to the bottom of your pull request to view all the checks.
|
||||
|
||||
After pushing, you will get a GitHub link in the terminal output. Copy this link and paste it into a
|
||||
browser to create your PR.
|
||||
Verify that the linking and spell checking have passed, and that the documentation was built successfully. New words or acronyms can be added to the [wordlist file](https://github.com/ROCm/rocm-docs-core/blob/develop/.wordlist.txt) as needed.
|
||||
|
||||
## Create an issue
|
||||
The Read The Docs build of your pull request can be accessed by clicking on the Details link next to the Read The Docs build check. Verify that your changes are in the build and look as expected.
|
||||
|
||||
1. To create a new GitHub issue, select the 'Issues' tab in the appropriate repository
|
||||
(e.g., https://github.com/ROCm/ROCm/issues).
|
||||
2. Use the search bar to make sure the issue doesn't already exist.
|
||||
3. If your issue is not already listed, select the green 'New issue' button to the right of the page. Select
|
||||
the type of issue and fill in the resulting template.
|
||||
Your pull request will be reviewed by a member of the ROCm documentation team.
|
||||
|
||||
### General issue guidelines
|
||||
See the [GitHub documentation](https://docs.github.com/en) for information on how to fork and clone a repository, and how to create and push a local branch.
|
||||
|
||||
* Use your best judgement for issue creation. If your issue is already listed, upvote the issue and
|
||||
comment or post to provide additional details, such as how you reproduced this issue.
|
||||
* If you're not sure if your issue is the same, err on the side of caution and file your issue.
|
||||
You can add a comment to include the issue number (and link) for the similar issue. If we evaluate
|
||||
your issue as being the same as the existing issue, we'll close the duplicate.
|
||||
* If your issue doesn't exist, use the issue template to file a new issue.
|
||||
* When filing an issue, be sure to provide as much information as possible, including script output so
|
||||
we can collect information about your configuration. This helps reduce the time required to
|
||||
reproduce your issue.
|
||||
* Check your issue regularly, as we may require additional information to successfully reproduce the
|
||||
issue.
|
||||
|
||||
## Suggest a new feature
|
||||
|
||||
Use the [GitHub Discussion forum](https://github.com/ROCm/ROCm/discussions)
|
||||
(Ideas category) to propose new features. Our maintainers are happy to provide direction and
|
||||
feedback on feature development.
|
||||
|
||||
## Future development workflow
|
||||
|
||||
The current ROCm development workflow is GitHub-based. If, in the future, we change this platform,
|
||||
the tools and links may change. In this instance, we will update contribution guidelines accordingly.
|
||||
```{important}
|
||||
By creating a pull request (PR), you agree to allow your contribution to be licensed under the terms of the
|
||||
LICENSE.txt file in the corresponding repository. Different repositories can use different licenses.
|
||||
```
|
||||
|
||||
@@ -1,219 +0,0 @@
|
||||
# Documentation structure
|
||||
|
||||
Our documentation follows the Pitchfork folder structure. Most documentation files are stored in the
|
||||
`/docs` folder. Some special files (such as release, contributing, and changelog) are stored in the root
|
||||
(`/`) folder.
|
||||
|
||||
All images are stored in the `/docs/data` folder. An image's file path mirrors that of the documentation
|
||||
file where it is used.
|
||||
|
||||
Our naming structure uses kebab case; for example, `my-file-name.rst`.
|
||||
|
||||
## Supported formats and syntax
|
||||
|
||||
Our documentation includes both Markdown and RST files. We are gradually transitioning existing
|
||||
Markdown to RST in order to more effectively meet our documentation needs. When contributing,
|
||||
RST is preferred; if you must use Markdown, use GitHub-flavored Markdown.
|
||||
|
||||
We use [Sphinx Design](https://sphinx-design.readthedocs.io/en/latest/index.html) syntax and compile
|
||||
our API references using [Doxygen](https://www.doxygen.nl/).
|
||||
|
||||
The following table shows some common documentation components and the syntax convention we
|
||||
use for each:
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<th>Component</th>
|
||||
<th>RST syntax</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Code blocks</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
.. code-block:: language-name
|
||||
|
||||
My code block.
|
||||
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Cross-referencing internal files</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
:doc:`Title <../path/to/file/filename>`
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>External links</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
`link name <URL>`_
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<tr>
|
||||
<td>Headings</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
******************
|
||||
Chapter title (H1)
|
||||
******************
|
||||
|
||||
Section title (H2)
|
||||
===============
|
||||
|
||||
Subsection title (H3)
|
||||
---------------------
|
||||
|
||||
Sub-subsection title (H4)
|
||||
^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Images</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
.. image:: image1.png
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Internal links</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
1. Add a tag to the section you want to reference:
|
||||
|
||||
.. _my-section-tag: section-1
|
||||
|
||||
Section 1
|
||||
==========
|
||||
|
||||
2. Link to your tag:
|
||||
|
||||
As shown in :ref:`section-1`.
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<tr>
|
||||
<td>Lists</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
# Ordered (numbered) list item
|
||||
|
||||
* Unordered (bulleted) list item
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<tr>
|
||||
<td>Math (block)</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
.. math::
|
||||
|
||||
A = \begin{pmatrix}
|
||||
0.0 & 1.0 & 1.0 & 3.0 \\
|
||||
4.0 & 5.0 & 6.0 & 7.0 \\
|
||||
\end{pmatrix}
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Math (inline)</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
:math:`2 \times 2 `
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Notes</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
.. note::
|
||||
|
||||
My note here.
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Tables</td>
|
||||
<td>
|
||||
|
||||
```rst
|
||||
|
||||
.. csv-table:: Optional title here
|
||||
:widths: 30, 70 #optional column widths
|
||||
:header: "entry1 header", "entry2 header"
|
||||
|
||||
"entry1", "entry2"
|
||||
|
||||
```
|
||||
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Language and style
|
||||
|
||||
We use the
|
||||
[Google developer documentation style guide](https://developers.google.com/style/highlights) to
|
||||
guide our content.
|
||||
|
||||
Font size and type, page layout, white space control, and other formatting
|
||||
details are controlled via
|
||||
[rocm-docs-core](https://github.com/ROCm/rocm-docs-core). If you want to notify us
|
||||
of any formatting issues, create a pull request in our
|
||||
[rocm-docs-core](https://github.com/ROCm/rocm-docs-core) GitHub repository.
|
||||
|
||||
## Building our documentation
|
||||
|
||||
<!-- % TODO: Fix the link to be able to work at every files -->
|
||||
To learn how to build our documentation, refer to
|
||||
[Building documentation](./building.md).
|
||||
@@ -4,12 +4,24 @@
|
||||
<meta name="keywords" content="documentation, pull request, GitHub, AMD, ROCm">
|
||||
</head>
|
||||
|
||||
# Providing feedback
|
||||
# Providing feedback about the ROCm documentation
|
||||
|
||||
Your feedback is welcome. You can provide feedback either through GitHub Discussions or GitHub Issues.
|
||||
Feedback about the ROCm documentation is welcome. You can provide feedback about the ROCm documentation either through GitHub Discussions or GitHub Issues.
|
||||
|
||||
Use [GitHub Discussions](https://github.com/ROCm/ROCm/discussions) to ask questions, view announcements, and communicate with other members of the community.
|
||||
## Participating in discussions through GitHub Discussions
|
||||
|
||||
Use [GitHub Issues](https://github.com/ROCm/ROCm/issues) to submit issues you find with ROCm or with the ROCm documentation.
|
||||
You can ask questions, view announcements, suggest new features, and communicate with other members of the community through [GitHub Discussions](https://github.com/ROCm/ROCm/discussions).
|
||||
|
||||
For information about contributing to the ROCm repository and creating a pull request (PR), see [Contributing](./contributing.md).
|
||||
## Submitting issues through GitHub Issues
|
||||
|
||||
You can submit issues through [GitHub Issues](https://github.com/ROCm/ROCm/issues).
|
||||
|
||||
When creating a new issue, follow the following guidelines:
|
||||
|
||||
1. Always do a search to see if the same issue already exists. If the issue already exists, upvote it, and comment or post to provide any additional details you might have.
|
||||
2. If you find an issue that is similar to your issue, log your issue, then add a comment that includes a link to the similar issue, as well as its issue number.
|
||||
3. Always provide as much information as possible. This helps reduce the time required to reproduce the issue.
|
||||
|
||||
After creating your issue, make sure to check it regularly for any requests for additional information.
|
||||
|
||||
For information about contributing content to the ROCm documentation, see [Contributing to the ROCm documentation](./contributing.md).
|
||||
|
||||
@@ -6,60 +6,47 @@
|
||||
|
||||
# ROCm documentation toolchain
|
||||
|
||||
Our documentation relies on several open source toolchains and sites.
|
||||
The ROCm documentation relies on several open source toolchains and sites.
|
||||
|
||||
## `rocm-docs-core`
|
||||
## rocm-docs-core
|
||||
|
||||
[rocm-docs-core](https://github.com/ROCm/rocm-docs-core) is an AMD-maintained
|
||||
project that applies customization for our documentation. This project is the tool most ROCm
|
||||
repositories use as part of the documentation build. It is also available as a
|
||||
[pip package on PyPI](https://pypi.org/project/rocm-docs-core/).
|
||||
project that applies customizations for the ROCm documentation. This project is the tool most ROCm repositories use as part of their documentation build pipeline. It is available as a [pip package on PyPI](https://pypi.org/project/rocm-docs-core/).
|
||||
|
||||
See the user and developer guides for rocm-docs-core at
|
||||
{doc}`rocm-docs-core documentation<rocm-docs-core:index>`.
|
||||
|
||||
## Sphinx
|
||||
|
||||
[Sphinx](https://www.sphinx-doc.org/en/master/) is a documentation generator originally used for
|
||||
Python. It is now widely used in the open source community.
|
||||
[Sphinx](https://www.sphinx-doc.org/en/master/) is a documentation generator originally used for Python. It is now widely used in the open source community.
|
||||
|
||||
### Sphinx External ToC
|
||||
|
||||
[Sphinx External ToC](https://sphinx-external-toc.readthedocs.io/en/latest/intro.html) is a Sphinx
|
||||
extension used for ROCm documentation navigation. This tool generates a navigation menu on the left
|
||||
[Sphinx External ToC](https://sphinx-external-toc.readthedocs.io/en/latest/intro.html) is a Sphinx extension used for ROCm documentation navigation. This tool generates a navigation menu on the left
|
||||
based on a YAML file (`_toc.yml.in`) that contains the table of contents.
|
||||
|
||||
### Sphinx-book-theme
|
||||
|
||||
[Sphinx-book-theme](https://sphinx-book-theme.readthedocs.io/en/latest/) is a Sphinx theme that
|
||||
defines the base appearance for ROCm documentation. ROCm documentation applies some
|
||||
customization, such as a custom header and footer on top of the Sphinx Book Theme.
|
||||
[Sphinx-book-theme](https://sphinx-book-theme.readthedocs.io/en/latest/) is a Sphinx theme that defines the base appearance for ROCm documentation. ROCm documentation applies some customization, such as a custom header and footer, on top of the Sphinx Book Theme.
|
||||
|
||||
### Sphinx Design
|
||||
|
||||
[Sphinx design](https://sphinx-design.readthedocs.io/en/latest/index.html) is a Sphinx extension that
|
||||
adds design functionality. ROCm documentation uses Sphinx Design for grids, cards, and synchronized
|
||||
tabs.
|
||||
[Sphinx design](https://sphinx-design.readthedocs.io/en/latest/index.html) is a Sphinx extension that adds design functionality. ROCm documentation uses Sphinx Design for grids, cards, and synchronized tabs.
|
||||
|
||||
## Doxygen
|
||||
|
||||
[Doxygen](https://www.doxygen.nl/) is a documentation generator that extracts information from inline
|
||||
code. ROCm projects typically use Doxygen for public API documentation (unless the upstream project
|
||||
uses a different tool).
|
||||
[Doxygen](https://www.doxygen.nl/) is a documentation generator that extracts information from in-code comments. It is used for API documentation.
|
||||
|
||||
## Breathe
|
||||
|
||||
[Breathe](https://www.breathe-doc.org/) is a Sphinx plugin to integrate Doxygen content.
|
||||
[Breathe](https://www.breathe-doc.org/) is a Sphinx plugin for integrating Doxygen content.
|
||||
|
||||
## MyST
|
||||
|
||||
[Markedly Structured Text (MyST)](https://myst-tools.org/docs/spec) is an extended flavor of
|
||||
Markdown ([CommonMark](https://commonmark.org/)) influenced by reStructuredText (RST) and
|
||||
Sphinx. It's integrated into ROCm documentation by the Sphinx extension
|
||||
[`myst-parser`](https://myst-parser.readthedocs.io/en/latest/).
|
||||
A MyST syntax cheat sheet is available on the [Jupyter reference](https://jupyterbook.org/en/stable/reference/cheatsheet.html) site.
|
||||
[Markedly Structured Text (MyST)](https://myst-tools.org/docs/spec) is an extended flavor of Markdown ([CommonMark](https://commonmark.org/)) influenced by reStructuredText (rst) and Sphinx. It is integrated into the ROCm documentation with the [`myst-parser`](https://myst-parser.readthedocs.io/en/latest/) Sphinx extension.
|
||||
|
||||
See the [MyST syntax cheat sheet](https://jupyterbook.org/en/stable/reference/cheatsheet.html) at the Jupyter Book site.
|
||||
|
||||
## Read the Docs
|
||||
|
||||
[Read the Docs](https://docs.readthedocs.io/en/stable/) is the service that builds and hosts the HTML
|
||||
documentation generated using Sphinx to our end users.
|
||||
[Read the Docs](https://docs.readthedocs.io/en/stable/) is the service that builds and hosts the HTML version of the ROCm documentation.
|
||||
|
||||
@@ -16,7 +16,7 @@ This section discusses how to implement `vLLM <https://docs.vllm.ai/en/latest>`_
|
||||
vLLM inference
|
||||
==============
|
||||
|
||||
vLLM is renowned for its PagedAttention algorithm that can reduce memory consumption and increase throughput thanks to
|
||||
vLLM is renowned for its paged attention algorithm that can reduce memory consumption and increase throughput thanks to
|
||||
its paging scheme. Instead of allocating GPU high-bandwidth memory (HBM) for the maximum output token lengths of the
|
||||
models, the paged attention of vLLM allocates GPU HBM dynamically for its actual decoding lengths. This paged attention
|
||||
is also effective when multiple requests share the same key and value contents for a large value of beam search or
|
||||
@@ -139,7 +139,9 @@ Refer to :ref:`mi300x-vllm-optimization` for performance optimization tips.
|
||||
|
||||
ROCm provides a prebuilt optimized Docker image for validating the performance of LLM inference with vLLM
|
||||
on the MI300X accelerator. The Docker image includes ROCm, vLLM, PyTorch, and tuning files in the CSV
|
||||
format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
|
||||
format. For more information, see the guide to
|
||||
`LLM inference performance validation with vLLM on the AMD Instinct™ MI300X accelerator <https://github.com/ROCm/MAD/blob/develop/benchmark/vllm/README.md>`_
|
||||
on the ROCm GitHub repository.
|
||||
|
||||
.. _fine-tuning-llms-tgi:
|
||||
|
||||
|
||||
@@ -1,407 +0,0 @@
|
||||
.. meta::
|
||||
:description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the unified
|
||||
ROCm Docker image.
|
||||
:keywords: model, MAD, automation, dashboarding, validate
|
||||
|
||||
***********************************************************
|
||||
LLM inference performance validation on AMD Instinct MI300X
|
||||
***********************************************************
|
||||
|
||||
.. _vllm-benchmark-unified-docker:
|
||||
|
||||
The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
|
||||
a prebuilt, optimized environment designed for validating large language model
|
||||
(LLM) inference performance on the AMD Instinct™ MI300X accelerator. This
|
||||
ROCm vLLM Docker image integrates vLLM and PyTorch tailored specifically for the
|
||||
MI300X accelerator and includes the following components:
|
||||
|
||||
* `ROCm 6.2.1 <https://github.com/ROCm/ROCm>`_
|
||||
|
||||
* `vLLM 0.6.4 <https://docs.vllm.ai/en/latest>`_
|
||||
|
||||
* `PyTorch 2.5.0 <https://github.com/pytorch/pytorch>`_
|
||||
|
||||
* Tuning files (in CSV format)
|
||||
|
||||
With this Docker image, you can quickly validate the expected inference
|
||||
performance numbers on the MI300X accelerator. This topic also provides tips on
|
||||
optimizing performance with popular AI models.
|
||||
|
||||
.. hlist::
|
||||
:columns: 6
|
||||
|
||||
* Llama 3.1 8B
|
||||
|
||||
* Llama 3.1 70B
|
||||
|
||||
* Llama 3.1 405B
|
||||
|
||||
* Llama 2 7B
|
||||
|
||||
* Llama 2 70B
|
||||
|
||||
* Mixtral 8x7B
|
||||
|
||||
* Mixtral 8x22B
|
||||
|
||||
* Mixtral 7B
|
||||
|
||||
* Qwen2 7B
|
||||
|
||||
* Qwen2 72B
|
||||
|
||||
* JAIS 13B
|
||||
|
||||
* JAIS 30B
|
||||
|
||||
.. _vllm-benchmark-vllm:
|
||||
|
||||
.. note::
|
||||
|
||||
vLLM is a toolkit and library for LLM inference and serving. AMD implements
|
||||
high-performance custom kernels and modules in vLLM to enhance performance.
|
||||
See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
|
||||
more information.
|
||||
|
||||
Getting started
|
||||
===============
|
||||
|
||||
Use the following procedures to reproduce the benchmark results on an
|
||||
MI300X accelerator with the prebuilt vLLM Docker image.
|
||||
|
||||
.. _vllm-benchmark-get-started:
|
||||
|
||||
1. Disable NUMA auto-balancing.
|
||||
|
||||
To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
|
||||
might hang until the periodic balancing is finalized. For more information,
|
||||
see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# disable automatic NUMA balancing
|
||||
sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
|
||||
# check if NUMA balancing is disabled (returns 0 if disabled)
|
||||
cat /proc/sys/kernel/numa_balancing
|
||||
0
|
||||
|
||||
2. Download the :ref:`ROCm vLLM Docker image <vllm-benchmark-unified-docker>`.
|
||||
|
||||
Use the following command to pull the Docker image from Docker Hub.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
|
||||
|
||||
Once setup is complete, you can choose between two options to reproduce the
|
||||
benchmark results:
|
||||
|
||||
- :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
|
||||
|
||||
- :ref:`Standalone benchmarking <vllm-benchmark-standalone>`
|
||||
|
||||
.. _vllm-benchmark-mad:
|
||||
|
||||
MAD-integrated benchmarking
|
||||
===========================
|
||||
|
||||
Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
|
||||
directory and install the required packages on the host machine.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
git clone https://github.com/ROCm/MAD
|
||||
cd MAD
|
||||
pip install -r requirements.txt
|
||||
|
||||
Use this command to run a performance benchmark test of the Llama 3.1 8B model
|
||||
on one GPU with ``float16`` data type in the host machine.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
|
||||
python3 tools/run_models.py --tags pyt_vllm_llama-3.1-8b --keep-model-dir --live-output --timeout 28800
|
||||
|
||||
ROCm MAD launches a Docker container with the name
|
||||
``container_ci-pyt_vllm_llama-3.1-8b``. The latency and throughput reports of the
|
||||
model are collected in the following path: ``~/MAD/reports_float16/``.
|
||||
|
||||
Although the following models are preconfigured to collect latency and
|
||||
throughput performance data, you can also change the benchmarking parameters.
|
||||
Refer to the :ref:`Standalone benchmarking <vllm-benchmark-standalone>` section.
|
||||
|
||||
Available models
|
||||
----------------
|
||||
|
||||
.. hlist::
|
||||
:columns: 3
|
||||
|
||||
* ``pyt_vllm_llama-3.1-8b``
|
||||
|
||||
* ``pyt_vllm_llama-3.1-70b``
|
||||
|
||||
* ``pyt_vllm_llama-3.1-405b``
|
||||
|
||||
* ``pyt_vllm_llama-2-7b``
|
||||
|
||||
* ``pyt_vllm_llama-2-70b``
|
||||
|
||||
* ``pyt_vllm_mixtral-8x7b``
|
||||
|
||||
* ``pyt_vllm_mixtral-8x22b``
|
||||
|
||||
* ``pyt_vllm_mistral-7b``
|
||||
|
||||
* ``pyt_vllm_qwen2-7b``
|
||||
|
||||
* ``pyt_vllm_qwen2-72b``
|
||||
|
||||
* ``pyt_vllm_jais-13b``
|
||||
|
||||
* ``pyt_vllm_jais-30b``
|
||||
|
||||
* ``pyt_vllm_llama-3.1-8b_fp8``
|
||||
|
||||
* ``pyt_vllm_llama-3.1-70b_fp8``
|
||||
|
||||
* ``pyt_vllm_llama-3.1-405b_fp8``
|
||||
|
||||
* ``pyt_vllm_mixtral-8x7b_fp8``
|
||||
|
||||
* ``pyt_vllm_mixtral-8x22b_fp8``
|
||||
|
||||
.. _vllm-benchmark-standalone:
|
||||
|
||||
Standalone benchmarking
|
||||
=======================
|
||||
|
||||
You can run the vLLM benchmark tool independently by starting the
|
||||
:ref:`Docker container <vllm-benchmark-get-started>` as shown in the following
|
||||
snippet.
|
||||
|
||||
.. code-block::
|
||||
|
||||
docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
|
||||
docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.4 rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
|
||||
|
||||
In the Docker container, clone the ROCm MAD repository and navigate to the
|
||||
benchmark scripts directory at ``~/MAD/scripts/vllm``.
|
||||
|
||||
.. code-block::
|
||||
|
||||
git clone https://github.com/ROCm/MAD
|
||||
cd MAD/scripts/vllm
|
||||
|
||||
Command
|
||||
-------
|
||||
|
||||
To start the benchmark, use the following command with the appropriate options.
|
||||
See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
|
||||
options and their descriptions.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
./vllm_benchmark_report.sh -s $test_option -m $model_repo -g $num_gpu -d $datatype
|
||||
|
||||
See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
|
||||
|
||||
.. note::
|
||||
|
||||
The input sequence length, output sequence length, and tensor parallel (TP) are
|
||||
already configured. You don't need to specify them with this script.
|
||||
|
||||
.. note::
|
||||
|
||||
If you encounter the following error, pass your access-authorized Hugging
|
||||
Face token to the gated models.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
OSError: You are trying to access a gated repo.
|
||||
|
||||
# pass your HF_TOKEN
|
||||
export HF_TOKEN=$your_personal_hf_token
|
||||
|
||||
.. _vllm-benchmark-standalone-options:
|
||||
|
||||
Options
|
||||
-------
|
||||
|
||||
.. list-table::
|
||||
:header-rows: 1
|
||||
:align: center
|
||||
|
||||
* - Name
|
||||
- Options
|
||||
- Description
|
||||
|
||||
* - ``$test_option``
|
||||
- latency
|
||||
- Measure decoding token latency
|
||||
|
||||
* -
|
||||
- throughput
|
||||
- Measure token generation throughput
|
||||
|
||||
* -
|
||||
- all
|
||||
- Measure both throughput and latency
|
||||
|
||||
* - ``$model_repo``
|
||||
- ``meta-llama/Meta-Llama-3.1-8B-Instruct``
|
||||
- Llama 3.1 8B
|
||||
|
||||
* - (``float16``)
|
||||
- ``meta-llama/Meta-Llama-3.1-70B-Instruct``
|
||||
- Llama 3.1 70B
|
||||
|
||||
* -
|
||||
- ``meta-llama/Meta-Llama-3.1-405B-Instruct``
|
||||
- Llama 3.1 405B
|
||||
|
||||
* -
|
||||
- ``meta-llama/Llama-2-7b-chat-hf``
|
||||
- Llama 2 7B
|
||||
|
||||
* -
|
||||
- ``meta-llama/Llama-2-70b-chat-hf``
|
||||
- Llama 2 70B
|
||||
|
||||
* -
|
||||
- ``mistralai/Mixtral-8x7B-Instruct-v0.1``
|
||||
- Mixtral 8x7B
|
||||
|
||||
* -
|
||||
- ``mistralai/Mixtral-8x22B-Instruct-v0.1``
|
||||
- Mixtral 8x22B
|
||||
|
||||
* -
|
||||
- ``mistralai/Mistral-7B-Instruct-v0.3``
|
||||
- Mixtral 7B
|
||||
|
||||
* -
|
||||
- ``Qwen/Qwen2-7B-Instruct``
|
||||
- Qwen2 7B
|
||||
|
||||
* -
|
||||
- ``Qwen/Qwen2-72B-Instruct``
|
||||
- Qwen2 72B
|
||||
|
||||
* -
|
||||
- ``core42/jais-13b-chat``
|
||||
- JAIS 13B
|
||||
|
||||
* -
|
||||
- ``core42/jais-30b-chat-v3``
|
||||
- JAIS 30B
|
||||
|
||||
* - ``$model_repo``
|
||||
- ``amd/Meta-Llama-3.1-8B-Instruct-FP8-KV``
|
||||
- Llama 3.1 8B
|
||||
|
||||
* - (``float8``)
|
||||
- ``amd/Meta-Llama-3.1-70B-Instruct-FP8-KV``
|
||||
- Llama 3.1 70B
|
||||
|
||||
* -
|
||||
- ``amd/Meta-Llama-3.1-405B-Instruct-FP8-KV``
|
||||
- Llama 3.1 405B
|
||||
|
||||
* -
|
||||
- ``amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV``
|
||||
- Mixtral 8x7B
|
||||
|
||||
* -
|
||||
- ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
|
||||
- Mixtral 8x22B
|
||||
|
||||
* - ``$num_gpu``
|
||||
- 1 or 8
|
||||
- Number of GPUs
|
||||
|
||||
* - ``$datatype``
|
||||
- ``float16`` or ``float8``
|
||||
- Data type
|
||||
|
||||
.. _vllm-benchmark-run-benchmark:
|
||||
|
||||
Running the benchmark on the MI300X accelerator
|
||||
-----------------------------------------------
|
||||
|
||||
Here are some examples of running the benchmark with various options.
|
||||
See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
|
||||
options and their descriptions.
|
||||
|
||||
Example 1: latency benchmark
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
Use this command to benchmark the latency of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
|
||||
|
||||
.. code-block::
|
||||
|
||||
./vllm_benchmark_report.sh -s latency -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
|
||||
./vllm_benchmark_report.sh -s latency -m amd/Meta-Llama-3.1-8B-Instruct-FP8-KV -g 1 -d float8
|
||||
|
||||
Find the latency reports at:
|
||||
|
||||
- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_latency_report.csv``
|
||||
|
||||
- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_latency_report.csv``
|
||||
|
||||
Example 2: throughput benchmark
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
Use this command to benchmark the throughput of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
./vllm_benchmark_report.sh -s throughput -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
|
||||
./vllm_benchmark_report.sh -s throughput -m amd/Meta-Llama-3.1-8B-Instruct-FP8-KV -g 1 -d float8
|
||||
|
||||
Find the throughput reports at:
|
||||
|
||||
- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_throughput_report.csv``
|
||||
|
||||
- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_throughput_report.csv``
|
||||
|
||||
.. raw:: html
|
||||
|
||||
<style>
|
||||
mjx-container[jax="CHTML"][display="true"] {
|
||||
text-align: left;
|
||||
margin: 0;
|
||||
}
|
||||
</style>
|
||||
|
||||
.. note::
|
||||
|
||||
Throughput is calculated as:
|
||||
|
||||
- .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
|
||||
|
||||
- .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
|
||||
|
||||
Further reading
|
||||
===============
|
||||
|
||||
- For application performance optimization strategies for HPC and AI workloads,
|
||||
including inference with vLLM, see :doc:`/how-to/tuning-guides/mi300x/workload`.
|
||||
|
||||
- To learn more about the options for latency and throughput benchmark scripts,
|
||||
see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
|
||||
|
||||
- To learn more about system settings and management practices to configure your system for
|
||||
MI300X accelerators, see :doc:`/how-to/system-optimization/mi300x`.
|
||||
|
||||
- To learn how to run LLM models from Hugging Face or your own model, see
|
||||
:doc:`Using ROCm for AI </how-to/rocm-for-ai/index>`.
|
||||
|
||||
- To learn how to optimize inference on LLMs, see
|
||||
:doc:`Fine-tuning LLMs and inference optimization </how-to/llm-fine-tuning-optimization/index>`.
|
||||
|
||||
- For a list of other ready-made Docker images for ROCm, see the
|
||||
:doc:`Docker image support matrix <rocm-install-on-linux:reference/docker-image-support-matrix>`.
|
||||
|
||||
- To compare with the previous version of the ROCm vLLM Docker image for performance validation, refer to
|
||||
`LLM inference performance validation on AMD Instinct MI300X (ROCm 6.2.0) <https://rocm.docs.amd.com/en/docs-6.2.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_.
|
||||
|
||||
@@ -46,7 +46,9 @@ Validating vLLM performance
|
||||
|
||||
ROCm provides a prebuilt optimized Docker image for validating the performance of LLM inference with vLLM
|
||||
on the MI300X accelerator. The Docker image includes ROCm, vLLM, PyTorch, and tuning files in the CSV
|
||||
format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
|
||||
format. For more information, see the guide to
|
||||
`LLM inference performance validation with vLLM on the AMD Instinct™ MI300X accelerator <https://github.com/ROCm/MAD/blob/develop/benchmark/vllm/README.md>`_
|
||||
on the ROCm GitHub repository.
|
||||
|
||||
.. _rocm-for-ai-serve-hugging-face-tgi:
|
||||
|
||||
|
||||
@@ -342,8 +342,8 @@ If SMT is enabled by setting "CCD/Core/Thread Enablement > SMT Control" to
|
||||
(logical) cores of the system:
|
||||
|
||||
* In the server BIOS, set IOMMU to "Enabled".
|
||||
* When configuring the Grub boot loader, add the following argument for the
|
||||
Linux kernel: `iommu=pt`
|
||||
* When configuring the Grub boot loader, add the following arguments for the
|
||||
Linux kernel: `amd_iommu=on iommu=pt`
|
||||
* Update Grub to use the modified configuration:
|
||||
|
||||
```shell
|
||||
@@ -355,7 +355,7 @@ If SMT is enabled by setting "CCD/Core/Thread Enablement > SMT Control" to
|
||||
|
||||
```none
|
||||
[...]
|
||||
[ 0.000000] Kernel command line: [...] iommu=pt
|
||||
[ 0.000000] Kernel command line: [...] amd_iommu=on iommu=pt
|
||||
[...]
|
||||
```
|
||||
|
||||
|
||||
@@ -327,8 +327,8 @@ If SMT is enabled by setting "CCD/Core/Thread Enablement > SMT Control" to
|
||||
(logical) cores of the system:
|
||||
|
||||
* In the server BIOS, set IOMMU to "Enabled".
|
||||
* When configuring the Grub boot loader, add the following argument for the
|
||||
Linux kernel: `iommu=pt`
|
||||
* When configuring the Grub boot loader, add the following arguments for the
|
||||
Linux kernel: `amd_iommu=on iommu=pt`
|
||||
* Update Grub to use the modified configuration:
|
||||
|
||||
```shell
|
||||
@@ -340,7 +340,7 @@ If SMT is enabled by setting "CCD/Core/Thread Enablement > SMT Control" to
|
||||
|
||||
```none
|
||||
[...]
|
||||
[ 0.000000] Kernel command line: [...] iommu=pt
|
||||
[ 0.000000] Kernel command line: [...] amd_iommu=on iommu=pt
|
||||
[...]
|
||||
```
|
||||
|
||||
|
||||
@@ -299,7 +299,7 @@ For a system that has AMD host CPUs add this to ``GRUB_CMDLINE_LINUX``:
|
||||
|
||||
.. code-block:: text
|
||||
|
||||
iommu=pt
|
||||
amd_iommu=on iommu=pt
|
||||
|
||||
Otherwise, if the system has Intel host CPUs add this instead to
|
||||
``GRUB_CMDLINE_LINUX``:
|
||||
@@ -500,7 +500,7 @@ If SMT is enabled by setting ``CCD/Core/Thread Enablement > SMT Control`` to
|
||||
|
||||
#. In the server BIOS, set IOMMU to ``Enabled``.
|
||||
|
||||
#. When configuring the GRUB boot loader, add the following argument for the Linux kernel: ``iommu=pt``.
|
||||
#. When configuring the GRUB boot loader, add the following arguments for the Linux kernel: ``amd_iommu=on iommu=pt``.
|
||||
|
||||
#. Update GRUB.
|
||||
|
||||
@@ -515,7 +515,7 @@ If SMT is enabled by setting ``CCD/Core/Thread Enablement > SMT Control`` to
|
||||
.. code-block:: shell
|
||||
|
||||
[...]
|
||||
[ 0.000000] Kernel command line: [...] iommu=pt
|
||||
[ 0.000000] Kernel command line: [...] amd_iommu=on iommu=pt
|
||||
[...]
|
||||
|
||||
Once the system is properly configured, ROCm software can be
|
||||
|
||||
@@ -111,7 +111,7 @@ sudo virsh net-start default /*to enable Virtual network by default
|
||||
Enable input-output memory management unit (IOMMU) in GRUB settings by adding the following line to `/etc/default/grub`:
|
||||
|
||||
```none
|
||||
GRUB_CMDLINE_LINUX_DEFAULT="quiet splash" for AMD CPU
|
||||
GRUB_CMDLINE_LINUX_DEFAULT="quiet splash amd_iommu=on" for AMD CPU
|
||||
```
|
||||
|
||||
Update grub and reboot
|
||||
|
||||
@@ -8,8 +8,6 @@ accelerators. They include detailed instructions on system settings and
|
||||
application tuning suggestions to help you fully leverage the capabilities of
|
||||
these accelerators, thereby achieving optimal performance.
|
||||
|
||||
* :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`
|
||||
|
||||
* :doc:`/how-to/tuning-guides/mi300x/system`
|
||||
|
||||
* :doc:`/how-to/tuning-guides/mi300x/workload`
|
||||
|
||||
@@ -152,7 +152,9 @@ address any new bottlenecks that may emerge.
|
||||
|
||||
ROCm provides a prebuilt optimized Docker image that has everything required to implement
|
||||
the tips in this section. It includes ROCm, vLLM, PyTorch, and tuning files in the CSV
|
||||
format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
|
||||
format. For more information, see the guide to
|
||||
`LLM inference performance validation with vLLM on the AMD Instinct™ MI300X accelerator <https://github.com/ROCm/MAD/blob/develop/benchmark/vllm/README.md>`_
|
||||
on the ROCm GitHub repository.
|
||||
|
||||
.. _mi300x-profiling-tools:
|
||||
|
||||
@@ -376,10 +378,11 @@ Refer to `vLLM documentation <https://docs.vllm.ai/en/latest/models/performance.
|
||||
for additional performance tips. :ref:`fine-tuning-llms-vllm` describes vLLM
|
||||
usage with ROCm.
|
||||
|
||||
ROCm provides a prebuilt optimized Docker image for validating the performance
|
||||
of LLM inference with vLLM on the MI300X accelerator. The Docker image includes
|
||||
ROCm, vLLM, PyTorch, and tuning files in the CSV format. For more information,
|
||||
see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
|
||||
ROCm provides a prebuilt optimized Docker image for validating the performance of LLM inference with vLLM
|
||||
on the MI300X accelerator. The Docker image includes ROCm, vLLM, PyTorch, and tuning files in the CSV
|
||||
format. For more information, see the guide to
|
||||
`LLM inference performance validation with vLLM on the AMD Instinct™ MI300X accelerator <https://github.com/ROCm/MAD/blob/develop/benchmark/vllm/README.md>`_
|
||||
on the ROCm GitHub repository.
|
||||
|
||||
Maximize throughput
|
||||
-------------------
|
||||
|
||||
@@ -45,8 +45,8 @@ ROCm documentation is organized into the following categories:
|
||||
* [Using ROCm for HPC](./how-to/rocm-for-hpc/index.rst)
|
||||
* [Fine-tuning LLMs and inference optimization](./how-to/llm-fine-tuning-optimization/index.rst)
|
||||
* [System optimization](./how-to/system-optimization/index.rst)
|
||||
* [AMD Instinct MI300X performance validation and tuning](./how-to/tuning-guides/mi300x/index.rst)
|
||||
* [GPU cluster networking](https://dcgpu.docs.amd.com/projects/gpu-cluster-networking/en/latest/index.html)
|
||||
* [AMD Instinct MI300X tuning guides](./how-to/tuning-guides/mi300x/index.rst)
|
||||
* [GPU cluster networking](https://rocm.docs.amd.com/projects/gpu-cluster-networking/en/latest/index.html)
|
||||
* [System debugging](./how-to/system-debugging.md)
|
||||
* [Using MPI](./how-to/gpu-enabled-mpi.rst)
|
||||
* [Using advanced compiler features](./conceptual/compiler-topics.md)
|
||||
|
||||
@@ -8,6 +8,7 @@
|
||||
|
||||
| Version | Release date |
|
||||
| ------- | ------------ |
|
||||
| [6.2.2](https://rocm.docs.amd.com/en/docs-6.2.2/) | September 27, 2024 |
|
||||
| [6.2.1](https://rocm.docs.amd.com/en/docs-6.2.1/) | September 20, 2024 |
|
||||
| [6.2.0](https://rocm.docs.amd.com/en/docs-6.2.0/) | August 2, 2024 |
|
||||
| [6.1.2](https://rocm.docs.amd.com/en/docs-6.1.2/) | June 4, 2024 |
|
||||
|
||||
@@ -70,18 +70,18 @@ subtrees:
|
||||
- file: how-to/system-optimization/w6000-v620.md
|
||||
title: AMD RDNA 2
|
||||
- file: how-to/tuning-guides/mi300x/index.rst
|
||||
title: AMD MI300X performance validation and tuning
|
||||
title: AMD MI300X tuning guides
|
||||
subtrees:
|
||||
- entries:
|
||||
- file: how-to/performance-validation/mi300x/vllm-benchmark.rst
|
||||
title: Performance validation
|
||||
- file: how-to/tuning-guides/mi300x/system.rst
|
||||
title: System tuning
|
||||
- file: how-to/tuning-guides/mi300x/workload.rst
|
||||
title: Workload tuning
|
||||
- file: how-to/system-debugging.md
|
||||
- url: https://rocm.docs.amd.com/projects/gpu-cluster-networking/en/${branch}/index.html
|
||||
title: GPU cluster networking
|
||||
- file: how-to/gpu-enabled-mpi.rst
|
||||
title: Using MPI
|
||||
- file: how-to/system-debugging.md
|
||||
- file: conceptual/compiler-topics.md
|
||||
title: Using advanced compiler features
|
||||
subtrees:
|
||||
@@ -175,16 +175,12 @@ subtrees:
|
||||
- caption: Contribute
|
||||
entries:
|
||||
- file: contribute/contributing.md
|
||||
title: Contribute to ROCm docs
|
||||
title: Contributing to the ROCm docmentation
|
||||
subtrees:
|
||||
- entries:
|
||||
- file: contribute/doc-structure.md
|
||||
title: Documentation structure
|
||||
- file: contribute/toolchain.md
|
||||
title: Documentation toolchain
|
||||
- file: contribute/building.md
|
||||
title: Build our documentation
|
||||
title: ROCm documentation toolchain
|
||||
- file: contribute/feedback.md
|
||||
title: Provide feedback
|
||||
title: Providing feedback about the ROCm documentation
|
||||
- file: about/license.md
|
||||
title: ROCm license
|
||||
title: ROCm licenses
|
||||
|
||||
@@ -1,2 +1,2 @@
|
||||
rocm-docs-core==1.8.1
|
||||
rocm-docs-core==1.8.2
|
||||
sphinx-reredirects
|
||||
|
||||
@@ -92,7 +92,7 @@ requests==2.32.3
|
||||
# via
|
||||
# pygithub
|
||||
# sphinx
|
||||
rocm-docs-core==1.8.1
|
||||
rocm-docs-core==1.8.2
|
||||
# via -r requirements.in
|
||||
smmap==5.0.1
|
||||
# via gitdb
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<manifest>
|
||||
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
|
||||
<default revision="refs/tags/rocm-6.1.1"
|
||||
<default revision="refs/tags/rocm-6.2.2"
|
||||
remote="rocm-org"
|
||||
sync-c="true"
|
||||
sync-j="4" />
|
||||
|
||||
@@ -184,5 +184,5 @@ clinfo, and HelloWord.cl and cause a system crash.
|
||||
* IRQ remapping does not support X2APIC mode
|
||||
* NMI error
|
||||
|
||||
Workaround: To avoid the system crash, add `iommu=pt` as the kernel bootparam, as
|
||||
Workaround: To avoid the system crash, add `amd_iommu=on iommu=pt` as the kernel bootparam, as
|
||||
indicated in the warning message.
|
||||
|
||||
@@ -1,3 +1,28 @@
|
||||
The release notes provide a comprehensive summary of changes since the previous ROCm release.
|
||||
|
||||
- [Release highlights](release-highlights)
|
||||
|
||||
- [Operating system and hardware support changes](operating-system-and-hardware-support-changes)
|
||||
|
||||
- [ROCm components versioning](rocm-components)
|
||||
|
||||
- [Detailed component changes](detailed-component-changes)
|
||||
|
||||
- [ROCm known issues](rocm-known-issues)
|
||||
|
||||
- [ROCm upcoming changes](rocm-upcoming-changes)
|
||||
|
||||
The [Compatibility matrix](https://rocm.docs.amd.com/en/docs-6.2.0/compatibility/compatibility-matrix.html)
|
||||
provides an overview of operating system, hardware, ecosystem, and ROCm component support across ROCm releases.
|
||||
|
||||
Release notes for previous ROCm releases are available in earlier versions of the documentation.
|
||||
See the [ROCm documentation release history](https://rocm.docs.amd.com/en/latest/release/versions.html).
|
||||
|
||||
## Release highlights
|
||||
|
||||
This section introduces notable new features and improvements in ROCm 6.2. See the
|
||||
[Detailed component changes](#detailed-component-changes) for individual component changes.
|
||||
|
||||
### New components
|
||||
|
||||
ROCm 6.2.0 introduces the following new components to the ROCm software stack.
|
||||
|
||||
@@ -1,6 +1,30 @@
|
||||
The release notes provide a summary of notable changes since the previous ROCm release.
|
||||
|
||||
- [Release highlights](release-highlights)
|
||||
|
||||
- [Operating system and hardware support changes](operating-system-and-hardware-support-changes)
|
||||
|
||||
- [ROCm components versioning](rocm-components)
|
||||
|
||||
- [Detailed component changes](detailed-component-changes)
|
||||
|
||||
- [ROCm known issues](rocm-known-issues)
|
||||
|
||||
- [ROCm upcoming changes](rocm-upcoming-changes)
|
||||
|
||||
The [Compatibility matrix](https://rocm.docs.amd.com/en/docs-6.2.1/compatibility/compatibility-matrix.html)
|
||||
provides the full list of supported hardware, operating systems, ecosystems, third-party components, and ROCm components for each ROCm release.
|
||||
|
||||
Release notes for previous ROCm releases are available in earlier versions of the documentation.
|
||||
See the [ROCm documentation release history](https://rocm.docs.amd.com/en/latest/release/versions.html).
|
||||
|
||||
## Release highlights
|
||||
|
||||
The following are notable new features and improvements in ROCm 6.2.1. For changes to individual components, see [Detailed component changes](#detailed-component-changes).
|
||||
|
||||
### rocAL major version change
|
||||
|
||||
The new version of rocAL introduces many new features, but does not modify any of the existing public API functions.However, the version number was incremented from 1.3 to 2.0.
|
||||
The new version of rocAL introduces many new features, but does not modify any of the existing public API functions. However, the version number was incremented from 1.3 to 2.0.
|
||||
Applications linked to version 1.3 must be recompiled to link against version 2.0.
|
||||
|
||||
See [the rocAL detailed changes](#rocal-2-0-0) for more information.
|
||||
@@ -9,12 +33,12 @@ See [the rocAL detailed changes](#rocal-2-0-0) for more information.
|
||||
|
||||
As of ROCm 6.2.1, ROCm supports Facebook General Matrix Multiplication (FBGEMM) and the related FBGEMM_GPU library.
|
||||
|
||||
FBGEMM is a low-precision, high-performance CPU kernel library for convolution and matrix multiplication. It is used for server-side inference and as a back end for PyTorch quantized operators. FBGEMM_GPU includes a collection of PyTorch GPU operator libraries for training and inference. For more information, see the ROCm [Model acceleration libraries guide](https://rocm.docs.amd.com/en/6.2.1/how-to/llm-fine-tuning-optimization/model-acceleration-libraries.html)
|
||||
FBGEMM is a low-precision, high-performance CPU kernel library for convolution and matrix multiplication. It is used for server-side inference and as a back end for PyTorch quantized operators. FBGEMM_GPU includes a collection of PyTorch GPU operator libraries for training and inference. For more information, see the ROCm [Model acceleration libraries guide](https://rocm.docs.amd.com/en/docs-6.2.1/how-to/llm-fine-tuning-optimization/model-acceleration-libraries.html)
|
||||
and [PyTorch's FBGEMM GitHub repository](https://github.com/pytorch/FBGEMM).
|
||||
|
||||
### ROCm Offline Installer Creator changes
|
||||
|
||||
The [ROCm Offline Installer Creator 6.2.1](https://rocm.docs.amd.com/projects/install-on-linux/en/6.2.1/install/rocm-offline-installer.html) introduces several new features and improvements including:
|
||||
The [ROCm Offline Installer Creator 6.2.1](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.2.1/install/rocm-offline-installer.html) introduces several new features and improvements including:
|
||||
|
||||
* Logging support for create and install logs
|
||||
* More stringent checks for Linux versions and distributions
|
||||
@@ -26,8 +50,8 @@ The [ROCm Offline Installer Creator 6.2.1](https://rocm.docs.amd.com/projects/in
|
||||
There have been no changes to supported hardware or operating systems from ROCm 6.2.0 to ROCm 6.2.1.
|
||||
|
||||
* The Programming Model Reference and Understanding the Programming Model topics in HIP have been consolidated into one topic,
|
||||
[HIP programming model (conceptual)](https://rocm.docs.amd.com/projects/HIP/en/6.2.1/understand/programming_model.html).
|
||||
* The [HIP virtual memory management](https://rocm.docs.amd.com/projects/HIP/en/6.2.1/how-to/virtual_memory.html) and [HIP virtual memory management API](https://rocm.docs.amd.com/projects/HIP/en/6.2.1/reference/virtual_memory_reference.html) topics have been added.
|
||||
[HIP programming model (conceptual)](https://rocm.docs.amd.com/projects/HIP/en/docs-6.2.1/understand/programming_model.html).
|
||||
* The [HIP virtual memory management](https://rocm.docs.amd.com/projects/HIP/en/docs-6.2.1/how-to/virtual_memory.html) and [HIP virtual memory management API](https://rocm.docs.amd.com/projects/HIP/en/docs-6.2.1/reference/virtual_memory_reference.html) topics have been added.
|
||||
|
||||
```{note}
|
||||
The ROCm documentation, like all ROCm projects, is open source and available on GitHub. To contribute to ROCm documentation, see the [ROCm documentation contribution guidelines](https://rocm.docs.amd.com/en/latest/contribute/contributing.html).
|
||||
|
||||
31
tools/autotag/templates/highlights/6.2.2.md
Normal file
31
tools/autotag/templates/highlights/6.2.2.md
Normal file
@@ -0,0 +1,31 @@
|
||||
These release notes provide a summary of notable changes since the previous ROCm release.
|
||||
|
||||
```{note}
|
||||
As ROCm 6.2.2 was released shortly after 6.2.1, the changes between these versions
|
||||
are minimal. For a comprehensive overview of recent updates, the ROCm 6.2.1 release
|
||||
notes are appended to the end of this document.
|
||||
|
||||
For detailed information about the changes in ROCm 6.2.1, refer to the appended
|
||||
section: [ROCm 6.2.1 release notes](rocm-6-2-1-release-notes).
|
||||
```
|
||||
|
||||
The [Compatibility matrix](https://rocm.docs.amd.com/en/docs-6.2.2/compatibility/compatibility-matrix.html)
|
||||
provides the full list of supported hardware, operating systems, ecosystems, third-party components, and ROCm components
|
||||
for each ROCm release.
|
||||
|
||||
Release notes for previous ROCm releases are available in earlier versions of the documentation.
|
||||
See the [ROCm documentation release history](https://rocm.docs.amd.com/en/latest/release/versions.html).
|
||||
|
||||
## Release highlights
|
||||
|
||||
The following is a significant fix introduced in ROCm 6.2.2.
|
||||
|
||||
### Fixed Instinct MI300X error recovery failure
|
||||
|
||||
Improved the reliability of AMD Instinct MI300X accelerators in scenarios involving
|
||||
uncorrectable errors. Previously, error recovery did not occur as expected,
|
||||
potentially leaving the system in an undefined state. This fix ensures that error
|
||||
recovery functions as expected, maintaining system stability.
|
||||
|
||||
See the [original issue](#instinct-mi300x-gpu-recovery-failure-on-uncorrectable-errors)
|
||||
noted in the ROCm 6.2.1 release notes.
|
||||
86
tools/autotag/templates/known_issues/6.2.0.md
Normal file
86
tools/autotag/templates/known_issues/6.2.0.md
Normal file
@@ -0,0 +1,86 @@
|
||||
## ROCm known issues
|
||||
|
||||
ROCm known issues are noted on {fab}`github` [GitHub](https://github.com/ROCm/ROCm/labels/Verified%20Issue). For known
|
||||
issues related to individual components, review the [Detailed component changes](detailed-component-changes).
|
||||
|
||||
### Default processor affinity behavior for helper threads
|
||||
|
||||
Processor affinity is a critical setting to ensure that ROCm helper threads run on the correct cores. By default, ROCm
|
||||
helper threads are spawned on all available cores, ignoring the parent thread’s processor affinity. This can lead to
|
||||
threads competing for available cores, which may result in suboptimal performance. This behavior occurs by default if
|
||||
the environment variable `HSA_OVERRIDE_CPU_AFFINITY_DEBUG` is not set or is set to `1`. If
|
||||
`HSA_OVERRIDE_CPU_AFFINITY_DEBUG` is set to `0`, the ROCr runtime uses the parent process's core affinity mask when
|
||||
creating helper threads. The parent’s affinity mask should then be set to account for the presence of additional threads
|
||||
by ensuring the affinity mask contains enough cores. Depending on the affinity settings of the software environment,
|
||||
batch system, launch commands like `numactl`/`taskset`, or explicit mask manipulation by the application itself, changing
|
||||
the setting may be advantageous to performance.
|
||||
|
||||
To ensure the parent's core affinity mask is honored by the ROCm helper threads, set the
|
||||
`HSA_OVERRIDE_CPU_AFFINITY_DEBUG` environment variable as follows:
|
||||
|
||||
```{code} shell
|
||||
export HSA_OVERRIDE_CPU_AFFINITY_DEBUG=0
|
||||
```
|
||||
|
||||
To ensure ROCm helper threads run on all available cores, set the `HSA_OVERRIDE_CPU_AFFINITY_DEBUG` environment variable
|
||||
as follows:
|
||||
|
||||
``` shell
|
||||
export HSA_OVERRIDE_CPU_AFFINITY_DEBUG=1
|
||||
```
|
||||
|
||||
Or the default:
|
||||
|
||||
``` shell
|
||||
|
||||
unset HSA_OVERRIDE_CPU_AFFINITY_DEBUG
|
||||
```
|
||||
|
||||
If unsure of the default processor affinity settings for your environment, run the following command from the shell:
|
||||
|
||||
``` shell
|
||||
|
||||
bash -c "echo taskset -p \$\$"
|
||||
```
|
||||
|
||||
See [issue #3493](https://github.com/ROCm/ROCm/issues/3493) on GitHub.
|
||||
|
||||
### Display issues on servers with Instinct MI300-series accelerators when loading AMDGPU driver
|
||||
|
||||
AMD Instinct MI300-series accelerators and third-party GPUs such as the Matrox G200 have an issue impacting video
|
||||
output. The issue was reproduced on a Dell server model PowerEdge XE9680. Servers from other vendors utilizing Matrox
|
||||
G200 cards may be impacted as well. This issue was found with ROCm 6.2.0 but is present in older ROCm versions.
|
||||
|
||||
The AMDGPU driver shipped with ROCm interferes with the operation of the display card video output. On Dell systems,
|
||||
this includes both the local video output and remote access via iDRAC. The display appears blank (black) after loading
|
||||
the `amdgpu` driver modules. Video output impacts both terminal access when running in `runlevel 3` and GUI access when
|
||||
running in `runlevel 5`. Server functionality can still be accessed via SSH or other remote connection methods.
|
||||
|
||||
See [issue #3494](https://github.com/ROCm/ROCm/issues/3494) on GitHub.
|
||||
|
||||
### KFDTest failure on Instinct MI300X with Oracle Linux 8.9
|
||||
|
||||
The `KFDEvictTest.QueueTest` is failing on the MI300X platform during KFD (Kernel Fusion Driver) tests, causing the full
|
||||
suite to not execute properly. This issue is suspected to be hardware-related.
|
||||
|
||||
See [issue #3495](https://github.com/ROCm/ROCm/issues/3495) on GitHub.
|
||||
|
||||
### Bandwidth limitation in gang and non-gang modes on Instinct MI300A
|
||||
|
||||
Expected target peak non-gang performance (~60GB/s) and target peak gang performance (~90GB/s) are not achieved. Both gang
|
||||
and non-gang performance are observed to be limited at 45GB/s.
|
||||
|
||||
This issue will be addressed in a future ROCm release.
|
||||
|
||||
See [issue #3496](https://github.com/ROCm/ROCm/issues/3496) on GitHub.
|
||||
|
||||
### rocm-llvm-alt
|
||||
|
||||
ROCm provides an optional package -- `rocm-llvm-alt` -- that provides a closed-source compiler for
|
||||
users interested in additional closed-source CPU optimizations. This feature is not functional in
|
||||
the ROCm 6.2.0 release. Users who attempt to invoke the closed-source compiler will experience an
|
||||
LLVM consumer-producer mismatch and the compilation will fail. There is no workaround that allows
|
||||
use of the closed-source compiler. It is recommended to compile using the default open-source
|
||||
compiler, which generates high-quality AMD CPU and AMD GPU code.
|
||||
|
||||
See [issue #3492](https://github.com/ROCm/ROCm/issues/3492) on GitHub.
|
||||
@@ -1,3 +1,8 @@
|
||||
## ROCm known issues
|
||||
|
||||
ROCm known issues are tracked on [GitHub](https://github.com/ROCm/ROCm/labels/Verified%20Issue). Known issues related to
|
||||
individual components are listed in the [Detailed component changes](detailed-component-changes) section.
|
||||
|
||||
### Instinct MI300X GPU recovery failure on uncorrectable errors
|
||||
|
||||
For the AMD Instinct MI300X accelerator, GPU recovery resets triggered by uncorrectable errors (UE) might not complete
|
||||
|
||||
@@ -1,85 +1,3 @@
|
||||
### Default processor affinity behavior for helper threads
|
||||
|
||||
Processor affinity is a critical setting to ensure that ROCm helper threads run on the correct cores. By default, ROCm
|
||||
helper threads are spawned on all available cores, ignoring the parent thread’s processor affinity. This can lead to
|
||||
threads competing for available cores, which may result in suboptimal performance. This behavior occurs by default if
|
||||
the environment variable `HSA_OVERRIDE_CPU_AFFINITY_DEBUG` is not set or is set to `1`. If
|
||||
`HSA_OVERRIDE_CPU_AFFINITY_DEBUG` is set to `0`, the ROCr runtime uses the parent process's core affinity mask when
|
||||
creating helper threads. The parent’s affinity mask should then be set to account for the presence of additional threads
|
||||
by ensuring the affinity mask contains enough cores. Depending on the affinity settings of the software environment,
|
||||
batch system, launch commands like `numactl`/`taskset`, or explicit mask manipulation by the application itself, changing
|
||||
the setting may be advantageous to performance.
|
||||
|
||||
To ensure the parent's core affinity mask is honored by the ROCm helper threads, set the
|
||||
`HSA_OVERRIDE_CPU_AFFINITY_DEBUG` environment variable as follows:
|
||||
|
||||
```{code} shell
|
||||
export HSA_OVERRIDE_CPU_AFFINITY_DEBUG=0
|
||||
```
|
||||
|
||||
To ensure ROCm helper threads run on all available cores, set the `HSA_OVERRIDE_CPU_AFFINITY_DEBUG` environment variable
|
||||
as follows:
|
||||
|
||||
``` shell
|
||||
export HSA_OVERRIDE_CPU_AFFINITY_DEBUG=1
|
||||
```
|
||||
|
||||
Or the default:
|
||||
|
||||
``` shell
|
||||
|
||||
unset HSA_OVERRIDE_CPU_AFFINITY_DEBUG
|
||||
```
|
||||
|
||||
If unsure of the default processor affinity settings for your environment, run the following command from the shell:
|
||||
|
||||
``` shell
|
||||
|
||||
bash -c "echo taskset -p \$\$"
|
||||
```
|
||||
|
||||
See [issue #3493](https://github.com/ROCm/ROCm/issues/3493) on GitHub.
|
||||
|
||||
### Display issues on servers with Instinct MI300-series accelerators when loading AMDGPU driver
|
||||
|
||||
AMD Instinct MI300-series accelerators and third-party GPUs such as the Matrox G200 have an issue impacting video
|
||||
output. The issue was reproduced on a Dell server model PowerEdge XE9680. Servers from other vendors utilizing Matrox
|
||||
G200 cards may be impacted as well. This issue was found with ROCm 6.2.0 but is present in older ROCm versions.
|
||||
|
||||
The AMDGPU driver shipped with ROCm interferes with the operation of the display card video output. On Dell systems,
|
||||
this includes both the local video output and remote access via iDRAC. The display appears blank (black) after loading
|
||||
the `amdgpu` driver modules. Video output impacts both terminal access when running in `runlevel 3` and GUI access when
|
||||
running in `runlevel 5`. Server functionality can still be accessed via SSH or other remote connection methods.
|
||||
|
||||
See [issue #3494](https://github.com/ROCm/ROCm/issues/3494) on GitHub.
|
||||
|
||||
### KFDTest failure on Instinct MI300X with Oracle Linux 8.9
|
||||
|
||||
The `KFDEvictTest.QueueTest` is failing on the MI300X platform during KFD (Kernel Fusion Driver) tests, causing the full
|
||||
suite to not execute properly. This issue is suspected to be hardware-related.
|
||||
|
||||
See [issue #3495](https://github.com/ROCm/ROCm/issues/3495) on GitHub.
|
||||
|
||||
### Bandwidth limitation in gang and non-gang modes on Instinct MI300A
|
||||
|
||||
Expected target peak non-gang performance (~60GB/s) and target peak gang performance (~90GB/s) are not achieved. Both gang
|
||||
and non-gang performance are observed to be limited at 45GB/s.
|
||||
|
||||
This issue will be addressed in a future ROCm release.
|
||||
|
||||
See [issue #3496](https://github.com/ROCm/ROCm/issues/3496) on GitHub.
|
||||
|
||||
### rocm-llvm-alt
|
||||
|
||||
ROCm provides an optional package -- `rocm-llvm-alt` -- that provides a closed-source compiler for
|
||||
users interested in additional closed-source CPU optimizations. This feature is not functional in
|
||||
the ROCm 6.2.0 release. Users who attempt to invoke the closed-source compiler will experience an
|
||||
LLVM consumer-producer mismatch and the compilation will fail. There is no workaround that allows
|
||||
use of the closed-source compiler. It is recommended to compile using the default open-source
|
||||
compiler, which generates high-quality AMD CPU and AMD GPU code.
|
||||
|
||||
See [issue #3492](https://github.com/ROCm/ROCm/issues/3492) on GitHub.
|
||||
|
||||
## ROCm upcoming changes
|
||||
|
||||
The section notes upcoming changes to the ROCm software stack. For upcoming changes related to individual components, review
|
||||
|
||||
@@ -1,3 +1,7 @@
|
||||
## ROCm upcoming changes
|
||||
|
||||
The following changes to the ROCm software stack are anticipated for future releases.
|
||||
|
||||
### rocm-llvm-alt
|
||||
|
||||
The `rocm-llvm-alt` package will be removed in an upcoming release. Users relying on the functionality provided by the closed-source compiler should transition to the open-source compiler. Once the `rocm-llvm-alt` package is removed, any compilation requesting functionality provided by the closed-source compiler will result in a Clang warning: "*[AMD] proprietary optimization compiler has been removed*".
|
||||
|
||||
@@ -67,18 +67,16 @@ endef
|
||||
|
||||
$(call adddep,amd_smi_lib,${ASAN_DEP})
|
||||
$(call adddep,aqlprofile,${ASAN_DEP} hsa)
|
||||
$(call adddep,clang-ocl,lightning rocm-cmake)
|
||||
$(call adddep,comgr,lightning devicelibs)
|
||||
$(call adddep,dbgapi,hsa comgr)
|
||||
$(call adddep,devicelibs,lightning)
|
||||
$(call adddep,hip_on_rocclr,${ASAN_DEP} hsa comgr hipcc rocprofiler-register)
|
||||
$(call adddep,hip_on_rocclr,${ASAN_DEP} rocclr rocprofiler-register)
|
||||
$(call adddep,hipcc,)
|
||||
$(call adddep,hipify_clang,hip_on_rocclr lightning)
|
||||
$(call adddep,hsa,${ASAN_DEP} thunk lightning devicelibs rocprofiler-register)
|
||||
$(call adddep,lightning,)
|
||||
$(call adddep,omniperf,${ASAN_DEP})
|
||||
$(call adddep,omnitrace,hipcc hsa hip_on_rocclr rocm_smi_lib rocprofiler roctracer)
|
||||
$(call adddep,opencl_icd_loader,)
|
||||
$(call adddep,opencl_on_rocclr,${ASAN_DEP} hsa comgr opencl_icd_loader)
|
||||
$(call adddep,opencl_on_rocclr,${ASAN_DEP} rocclr)
|
||||
$(call adddep,openmp_extras,thunk lightning devicelibs hsa)
|
||||
$(call adddep,rdc,${ASAN_DEP} rocm_smi_lib hsa rocprofiler)
|
||||
$(call adddep,rocclr,${ASAN_DEP} hsa comgr hipcc rocprofiler-register)
|
||||
@@ -89,15 +87,14 @@ $(call adddep,rocm-core,${ASAN_DEP})
|
||||
$(call adddep,rocm-gdb,dbgapi)
|
||||
$(call adddep,rocminfo,${ASAN_DEP} hsa)
|
||||
$(call adddep,rocprofiler-register,${ASAN_DEP})
|
||||
$(call adddep,rocprofiler-sdk,${ASAN_DEP} hsa aqlprofile opencl_on_rocclr hip_on_rocclr comgr)
|
||||
$(call adddep,rocprofiler,${ASAN_DEP} hsa roctracer aqlprofile opencl_on_rocclr hip_on_rocclr comgr)
|
||||
$(call adddep,rocprofiler,${ASAN_DEP} hsa roctracer aqlprofile opencl_on_rocclr hip_on_rocclr comgr dbgapi rocm_smi_lib)
|
||||
$(call adddep,rocr_debug_agent,${ASAN_DEP} hip_on_rocclr hsa dbgapi)
|
||||
$(call adddep,roctracer,${ASAN_DEP} hsa hip_on_rocclr)
|
||||
$(call adddep,thunk,${ASAN_DEP})
|
||||
|
||||
# rocm-dev points to all possible last finish components of Stage1 build.
|
||||
rocm-dev-components :=rdc hipify_clang openmp_extras \
|
||||
omniperf omnitrace rocm-core amd_smi_lib hipcc \
|
||||
rocm-core amd_smi_lib hipcc clang-ocl \
|
||||
rocm_bandwidth_test rocr_debug_agent rocm-gdb
|
||||
$(call adddep,rocm-dev,$(filter-out ${NOBUILD},${rocm-dev-components}))
|
||||
|
||||
@@ -120,7 +117,6 @@ $(call adddep,mivisionx,amdmigraphx miopen-hip rpp lightning hipcc)
|
||||
$(call adddep,rccl,hip_on_rocclr hsa lightning hipcc rocm_smi_lib hipify_clang)
|
||||
$(call adddep,rocalution,rocblas rocsparse rocrand lightning hipcc)
|
||||
$(call adddep,rocblas,hip_on_rocclr openmp_extras lightning hipcc)
|
||||
$(call adddep,rocal,mivisionx)
|
||||
$(call adddep,rocdecode,hip_on_rocclr lightning hipcc)
|
||||
$(call adddep,rocfft,hip_on_rocclr rocrand hiprand lightning hipcc openmp_extras)
|
||||
$(call adddep,rocmvalidationsuite,hip_on_rocclr hsa rocblas rocm-core lightning hipcc rocm_smi_lib)
|
||||
@@ -225,7 +221,7 @@ rocm-dev: T_rocm-dev
|
||||
|
||||
${OUT_DIR}/logs:
|
||||
sudo mkdir -p -m 775 "${ROCM_INSTALL_PATH}" && \
|
||||
sudo chown -R "$(shell id -u):$(shell id -g)" "/opt"
|
||||
sudo chown -R "$(shell id -u):$(shell id -g)" "${ROCM_INSTALL_PATH}"
|
||||
sudo chown -R "$(shell id -u):$(shell id -g)" "/home/$(shell id -un)"
|
||||
mkdir -p "${@}"
|
||||
mkdir -p ${HOME}/.ccache
|
||||
|
||||
@@ -22,13 +22,12 @@ build_amdmigraphx() {
|
||||
else
|
||||
GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
|
||||
fi
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
mkdir -p ${BUILD_DIR} && rm -rf ${BUILD_DIR}/* && mkdir -p ${HOME}/amdmigraphx && rm -rf ${HOME}/amdmigraphx/*
|
||||
rbuild package -d "${HOME}/amdmigraphx" -B "${BUILD_DIR}" \
|
||||
--cxx="${ROCM_PATH}/llvm/bin/clang++" \
|
||||
--cc="${ROCM_PATH}/llvm/bin/clang" \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DCMAKE_MODULE_LINKER_FLAGS="-Wl,--enable-new-dtags -Wl,--rpath,$ROCM_LIB_RPATH" \
|
||||
-DGPU_TARGETS="${GPU_TARGETS}" \
|
||||
-DCMAKE_INSTALL_RPATH=""
|
||||
|
||||
@@ -17,7 +17,9 @@ build_miopen_ck() {
|
||||
mkdir "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="-DAMDGPU_TARGETS=${GPU_ARCHS}"
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
else
|
||||
GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
|
||||
fi
|
||||
|
||||
if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
|
||||
@@ -41,7 +43,7 @@ build_miopen_ck() {
|
||||
${LAUNCHER_FLAGS} \
|
||||
-DINSTANCES_ONLY=ON \
|
||||
-DENABLE_ASAN_PACKAGING=true \
|
||||
"${GPU_TARGETS}" \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
"$COMPONENT_SRC"
|
||||
else
|
||||
cmake -DBUILD_DEV=OFF \
|
||||
@@ -61,11 +63,9 @@ build_miopen_ck() {
|
||||
-DROCM_DISABLE_LDCONFIG=ON \
|
||||
-DROCM_PATH=${ROCM_PATH} \
|
||||
-DCPACK_GENERATOR="${PKGTYPE^^}" \
|
||||
-DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
|
||||
-DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
|
||||
${LAUNCHER_FLAGS} \
|
||||
-DINSTANCES_ONLY=ON \
|
||||
"${GPU_TARGETS}" \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
"$COMPONENT_SRC"
|
||||
fi
|
||||
|
||||
@@ -106,6 +106,8 @@ build_miopen_ckProf() {
|
||||
architectures='gfx10 gfx11 gfx90 gfx94'
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
architectures=$(echo ${GPU_ARCHS} | awk -F';' '{for(i=1;i<=NF;i++) a[substr($i,1,5)]} END{for(i in a) printf i" "}')
|
||||
else
|
||||
architectures='gfx10 gfx11 gfx90 gfx94'
|
||||
fi
|
||||
|
||||
for arch in ${architectures}
|
||||
|
||||
@@ -28,10 +28,9 @@ build_hipblas() {
|
||||
rebuild_lapack
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
cmake \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DUSE_CUDA=OFF \
|
||||
-DBUILD_CLIENTS_TESTS=ON \
|
||||
-DBUILD_CLIENTS_BENCHMARKS=ON \
|
||||
|
||||
@@ -27,12 +27,11 @@ build_hipblaslt() {
|
||||
GPU_TARGETS=all
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
CXX=$(set_build_variables CXX)\
|
||||
cmake \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DTensile_LOGIC= \
|
||||
-DTensile_CODE_OBJECT_VERSION=default \
|
||||
-DTensile_CPU_THREADS= \
|
||||
|
||||
@@ -17,7 +17,6 @@ build_hipcub() {
|
||||
fi
|
||||
|
||||
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
@@ -28,7 +27,7 @@ build_hipcub() {
|
||||
CXX=$(set_build_variables CXX)\
|
||||
cmake \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip;${ROCM_PATH}/hip/cmake" \
|
||||
-Drocprim_DIR="${ROCM_PATH}/rocprim" \
|
||||
-DBUILD_TEST=ON \
|
||||
|
||||
@@ -16,7 +16,6 @@ build_hipfft() {
|
||||
|
||||
cd $COMPONENT_SRC
|
||||
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
@@ -27,7 +26,7 @@ build_hipfft() {
|
||||
cmake \
|
||||
-DCMAKE_CXX_COMPILER=$(set_build_variables CXX) \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
-DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip" \
|
||||
-DCMAKE_SKIP_BUILD_RPATH=TRUE \
|
||||
|
||||
@@ -61,6 +61,7 @@ build_hiprand() {
|
||||
rm -rf _CPack_Packages/ && find -name '*.o' -delete
|
||||
mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
|
||||
|
||||
$SCCACHE_BIN -s || echo "Unable to display sccache stats"
|
||||
}
|
||||
|
||||
clean_hiprand() {
|
||||
|
||||
@@ -27,11 +27,10 @@ build_hipsolver() {
|
||||
rebuild_lapack
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
cmake \
|
||||
-DUSE_CUDA=OFF \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DBUILD_CLIENTS_TESTS=ON \
|
||||
-DBUILD_CLIENTS_BENCHMARKS=ON \
|
||||
-DBUILD_CLIENTS_SAMPLES=ON \
|
||||
|
||||
@@ -22,12 +22,11 @@ build_hipsparse() {
|
||||
echo "CXX compiler: $CXX"
|
||||
|
||||
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
cmake \
|
||||
-DCPACK_SET_DESTDIR=OFF \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DUSE_CUDA=OFF \
|
||||
-DBUILD_CLIENTS_SAMPLES=ON \
|
||||
-DBUILD_CLIENTS_TESTS=ON \
|
||||
|
||||
@@ -28,7 +28,6 @@ build_hipsparselt() {
|
||||
|
||||
cd $COMPONENT_SRC
|
||||
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
@@ -42,7 +41,7 @@ build_hipsparselt() {
|
||||
cmake \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DTensile_LOGIC= \
|
||||
-DTensile_CODE_OBJECT_VERSION=default \
|
||||
-DTensile_CPU_THREADS= \
|
||||
|
||||
@@ -16,8 +16,6 @@ build_hiptensor() {
|
||||
|
||||
cd "$COMPONENT_SRC"
|
||||
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
@@ -27,7 +25,7 @@ build_hiptensor() {
|
||||
|
||||
cmake \
|
||||
-B "${BUILD_DIR}" \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
$(set_build_variables CMAKE_C_CXX) \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
${LAUNCHER_FLAGS} \
|
||||
|
||||
@@ -17,8 +17,7 @@ printUsage() {
|
||||
echo " -r, --release Build a release version of the package"
|
||||
echo " -a, --address_sanitizer Enable address sanitizer (enabled by default)"
|
||||
echo " -A --no_address_sanitizer Disable address sanitizer"
|
||||
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
|
||||
echo " -w, --wheel Creates python wheel package of rocm-llvm. It needs to be used along with -r option"
|
||||
echo " -s, --static Supports static CI by accepting this param & not bailing out. No effect of the param though"
|
||||
echo " -l, --build_llvm_static Build LLVM libraries statically linked. Default is to build dynamic linked libs"
|
||||
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
|
||||
type referred to by pkg_type"
|
||||
@@ -43,7 +42,6 @@ DEB_PATH="$(getDebPath lightning)"
|
||||
RPM_PATH="$(getRpmPath lightning)"
|
||||
INSTALL_PATH="${ROCM_INSTALL_PATH}/lib/llvm"
|
||||
LLVM_ROOT_LCL="${LLVM_ROOT}"
|
||||
ROCM_WHEEL_DIR="${BUILD_PATH}/_wheel"
|
||||
|
||||
TARGET="all"
|
||||
MAKEOPTS="$DASH_JAY"
|
||||
@@ -71,29 +69,14 @@ ASSERT_LLVM_VERSION_MINOR=""
|
||||
|
||||
SKIP_LIT_TESTS=0
|
||||
BUILD_MANPAGES="ON"
|
||||
STATIC_FLAG=
|
||||
|
||||
SANITIZER_AMDGPU=1
|
||||
HSA_INC_PATH="$WORK_ROOT/ROCR-Runtime/src/inc"
|
||||
COMGR_INC_PATH="$WORK_ROOT/llvm-project/amd/comgr/include"
|
||||
|
||||
VALID_STR=`getopt -o htcV:v:draAswlo:BPNM --long help,alt,clean,assert_llvm_ver_major:,assert_llvm_ver_minor:,debug,release,address_sanitizer,no_address_sanitizer,static,build_llvm_static,wheel,build,package,skip_lit_tests,skip_man_pages,outdir: -- "$@"`
|
||||
VALID_STR=`getopt -o htcV:v:draAslo:BPNM --long help,alt,clean,assert_llvm_ver_major:,assert_llvm_ver_minor:,debug,release,address_sanitizer,no_address_sanitizer,static,build_llvm_static,build,package,skip_lit_tests,skip_man_pages,outdir: -- "$@"`
|
||||
eval set -- "$VALID_STR"
|
||||
|
||||
set_dwarf_version(){
|
||||
case "$DISTRO_ID" in
|
||||
(sles*|rhel*)
|
||||
SET_DWARF_VERSION_4="-gdwarf-4"
|
||||
;;
|
||||
(*)
|
||||
SET_DWARF_VERSION_4=""
|
||||
;;
|
||||
esac
|
||||
export CFLAGS="$CFLAGS $SET_DWARF_VERSION_4 "
|
||||
export CXXFLAGS="$CXXFLAGS $SET_DWARF_VERSION_4 "
|
||||
export ASMFLAGS="$ASMFLAGS $SET_DWARF_VERSION_4 "
|
||||
}
|
||||
|
||||
while true ;
|
||||
do
|
||||
case "$1" in
|
||||
@@ -112,7 +95,6 @@ do
|
||||
(-r | --release)
|
||||
BUILD_TYPE="Release" ; shift ;;
|
||||
(-a | --address_sanitizer)
|
||||
set_dwarf_version
|
||||
SANITIZER_AMDGPU=1 ;
|
||||
HSA_INC_PATH="$WORK_ROOT/hsa/runtime/opensrc/hsa-runtime/inc" ;
|
||||
COMGR_INC_PATH="$WORK_ROOT/external/llvm-project/amd/comgr/include" ; shift ;;
|
||||
@@ -121,12 +103,9 @@ do
|
||||
unset HSA_INC_PATH ;
|
||||
unset COMGR_INC_PATH ; shift ;;
|
||||
(-s | --static)
|
||||
SHARED_LIBS="OFF" ;
|
||||
STATIC_FLAG="-DBUILD_SHARED_LIBS=$SHARED_LIBS" ; shift ;;
|
||||
SHARED_LIBS="OFF" ; shift ;;
|
||||
(-l | --build_llvm_static)
|
||||
BUILD_LLVM_DYLIB="OFF"; shift ;;
|
||||
(-w | --wheel)
|
||||
WHEEL_PACKAGE=true ; shift ;;
|
||||
(-o | --outdir)
|
||||
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
|
||||
(-B | --build)
|
||||
@@ -172,7 +151,6 @@ else
|
||||
fi
|
||||
|
||||
clean_lightning() {
|
||||
rm -rf "$ROCM_WHEEL_DIR"
|
||||
rm -rf "$BUILD_PATH"
|
||||
rm -rf "$DEB_PATH"
|
||||
rm -rf "$RPM_PATH"
|
||||
@@ -218,10 +196,7 @@ LLVM_VERSION_MINOR=""
|
||||
LLVM_VERSION_PATCH=""
|
||||
LLVM_VERSION_SUFFIX=""
|
||||
get_llvm_version() {
|
||||
local LLVM_VERSIONS=($(awk '/set\(LLVM_VERSION/ {print substr($2,1,length($2)-1)}' ${LLVM_ROOT_LCL}/../cmake/Modules/LLVMVersion.cmake))
|
||||
if [ ${#LLVM_VERSIONS[@]} -eq 0 ]; then
|
||||
LLVM_VERSIONS=($(awk '/set\(LLVM_VERSION/ {print substr($2,1,length($2)-1)}' ${LLVM_ROOT_LCL}/CMakeLists.txt))
|
||||
fi
|
||||
local LLVM_VERSIONS=($(awk '/set\(LLVM_VERSION/ {print substr($2,1,length($2)-1)}' ${LLVM_ROOT_LCL}/CMakeLists.txt))
|
||||
LLVM_VERSION_MAJOR=${LLVM_VERSIONS[0]}
|
||||
LLVM_VERSION_MINOR=${LLVM_VERSIONS[1]}
|
||||
LLVM_VERSION_PATCH=${LLVM_VERSIONS[2]}
|
||||
@@ -285,22 +260,15 @@ build_lightning() {
|
||||
|
||||
if [ ! -e Makefile ]; then
|
||||
echo "Building LLVM CMake environment"
|
||||
if [ -e "$LLVM_ROOT_LCL/../flang/AFARrelease" ]; then
|
||||
FLANG_NEW=1
|
||||
LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
|
||||
ENABLE_RUNTIMES="$ENABLE_RUNTIMES;openmp";
|
||||
else
|
||||
if [ -e "$LLVM_ROOT_LCL/../flang/docs/AssumedRank.md" ]; then
|
||||
FLANG_NEW=1
|
||||
LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
|
||||
else
|
||||
echo "NOT building project flang"
|
||||
fi
|
||||
|
||||
if [[ "${JOB_NAME}" != *afar* ]] && [ -e "$LLVM_ROOT_LCL/../flang/DoROCmRelease" ]; then
|
||||
FLANG_NEW=1
|
||||
LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
|
||||
else
|
||||
echo "NOT building project flang"
|
||||
fi
|
||||
fi
|
||||
set -x
|
||||
cmake $(rocm_cmake_params) ${GEN_NINJA} \
|
||||
${STATIC_FLAG} \
|
||||
-DCMAKE_INSTALL_PREFIX="$INSTALL_PATH" \
|
||||
-DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" \
|
||||
-DLLVM_ENABLE_PROJECTS="$LLVM_PROJECTS" \
|
||||
@@ -339,9 +307,9 @@ build_lightning() {
|
||||
-DCMAKE_SHARED_LINKER_FLAGS=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_LLVM_LIB_RPATH \
|
||||
-DROCM_LLVM_BACKWARD_COMPAT_LINK="$ROCM_INSTALL_PATH/llvm" \
|
||||
-DROCM_LLVM_BACKWARD_COMPAT_LINK_TARGET="./lib/llvm" \
|
||||
-DCLANG_LINK_FLANG_LEGACY=ON \
|
||||
-DCMAKE_CXX_STANDARD=17 \
|
||||
-DFLANG_INCLUDE_DOCS=OFF \
|
||||
-DCLANG_LINK_FLANG_LEGACY=ON \
|
||||
-DCMAKE_CXX_STANDARD=17 \
|
||||
-DFLANG_INCLUDE_DOCS=OFF \
|
||||
"$LLVM_ROOT_LCL"
|
||||
set +x
|
||||
echo "CMake complete"
|
||||
@@ -358,23 +326,8 @@ build_lightning() {
|
||||
echo "End Workaround for race condition"
|
||||
cmake --build . -- $MAKEOPTS
|
||||
|
||||
case "$DISTRO_ID" in
|
||||
(rhel*|centos*)
|
||||
RHEL_BUILD=1
|
||||
;;
|
||||
(*)
|
||||
RHEL_BUILD=0
|
||||
;;
|
||||
esac
|
||||
|
||||
if [ $SKIP_LIT_TESTS -eq 0 ]; then
|
||||
if [ $RHEL_BUILD -eq 1 ] && [ $BUILD_ALT != 1 ]; then
|
||||
if [ $FLANG_NEW -eq 1 ]; then
|
||||
cmake --build . -- $MAKEOPTS check-lld check-mlir
|
||||
else
|
||||
cmake --build . -- $MAKEOPTS check-lld
|
||||
fi
|
||||
elif [ "$DISTRO_NAME" != "sles" ] && [ $BUILD_ALT != 1 ]; then
|
||||
if [ "$DISTRO_NAME" != "sles" ] && [ $BUILD_ALT != 1 ]; then
|
||||
if [ $FLANG_NEW -eq 1 ]; then
|
||||
cmake --build . -- $MAKEOPTS check-llvm check-clang check-lld check-mlir
|
||||
else
|
||||
@@ -780,7 +733,7 @@ package_lightning_static() {
|
||||
local amd_compiler_commands=("amdclang" "amdclang++" "amdclang-cl" "amdclang-cpp" "amdflang" "amdlld" "offload-arch")
|
||||
local amd_man_pages=("amdclang.1.gz" "flang.1.gz" "amdflang.1.gz")
|
||||
local core_bin=("amdgpu-arch" "amdgpu-offload-arch" "amdlld" "amdllvm" "clang" "clang++" "clang-${LLVM_VERSION_MAJOR}" "clang-cl"
|
||||
"clang-cpp" "clang-build-select-link" "clang-offload-bundler" "clang-offload-packager" "clang-offload-wrapper" "clang-linker-wrapper" "clang-nvlink-wrapper" "flang" "flang-new"
|
||||
"clang-cpp" "clang-build-select-link" "clang-offload-bundler" "clang-offload-packager" "clang-offload-wrapper" "flang" "flang-new"
|
||||
"ld64.lld" "ld.lld" "llc" "lld" "lld-link" "llvm-ar" "llvm-bitcode-strip" "llvm-dwarfdump" "llvm-install-name-tool"
|
||||
"llvm-link" "llvm-mc" "llvm-objcopy" "llvm-objdump" "llvm-otool" "llvm-ranlib" "llvm-readelf" "llvm-readobj" "llvm-strip"
|
||||
"nvidia-arch" "nvptx-arch" "offload-arch" "opt" "wasm-ld" "amdclang" "amdclang++" "amdclang-${LLVM_VERSION_MAJOR}" "amdclang-cl"
|
||||
@@ -981,7 +934,7 @@ package_lightning_static() {
|
||||
|
||||
if [ $BUILD_ALT -eq 0 ]; then
|
||||
echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
|
||||
echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFile
|
||||
echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFile
|
||||
else
|
||||
echo "cp -R $LLVM_PROJECT_ALT_ROOT/EULA \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
|
||||
echo "cp -R $LLVM_PROJECT_ALT_ROOT/DISCLAIMER.txt \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
|
||||
@@ -995,6 +948,7 @@ package_lightning_static() {
|
||||
|
||||
echo "cp -d \"$distBin/flang\" \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFile
|
||||
|
||||
# Copy the config files
|
||||
if [ $BUILD_ALT -eq 0 ]; then
|
||||
echo "cp -d \"$distBin\"/*.cfg \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFile
|
||||
fi
|
||||
@@ -1016,12 +970,14 @@ package_lightning_static() {
|
||||
if [ "$BUILD_MANPAGES" == "ON" ]; then
|
||||
if [ $BUILD_ALT -eq 0 ]; then
|
||||
echo "mkdir -p \$RPM_BUILD_ROOT/$installPath/share/man/man1" >> $specFile
|
||||
|
||||
for i in "${core_man_pages[@]}"; do
|
||||
if [ -f "$distMan/man1/$i" ]; then
|
||||
echo "gzip -f $distMan/man1/$i" >> $specFile
|
||||
echo "cp -d $distMan/man1/${i}.gz \$RPM_BUILD_ROOT/$installPath/share/man/man1/" >> $specFile
|
||||
fi
|
||||
done
|
||||
|
||||
if [ -f "$distMan/man1/clang.1.gz" ]; then
|
||||
for i in "${amd_man_pages[@]}"; do
|
||||
echo "ln -sf clang.1.gz \"$distMan/man1/$i\"" >> $specFile
|
||||
@@ -1108,6 +1064,7 @@ package_lightning_static() {
|
||||
contains "$bin" "${core_bin[@]}" "${amd_compiler_commands[@]}" && continue
|
||||
echo "cp -d \"$i\" \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFileExtra
|
||||
done
|
||||
|
||||
for i in "$distLib"/*; do
|
||||
lib=$(basename "$i")
|
||||
contains "$lib" "${core_lib[@]}" && continue
|
||||
@@ -1115,15 +1072,18 @@ package_lightning_static() {
|
||||
done
|
||||
|
||||
echo "cp -R $distInc \$RPM_BUILD_ROOT/$installPath" >> $specFileExtra
|
||||
|
||||
echo "rm -rf \$RPM_BUILD_ROOT/$installPath/lib/clang" >> $specFileExtra
|
||||
|
||||
if [ $FLANG_NEW -eq 1 ]; then
|
||||
|
||||
echo "rm -rf \$RPM_BUILD_ROOT/$installPath/include/flang" >> $specFileExtra
|
||||
fi
|
||||
|
||||
if [ "$BUILD_MANPAGES" == "ON" ]; then
|
||||
if [ $BUILD_ALT -eq 0 ]; then
|
||||
echo "mkdir -p \$RPM_BUILD_ROOT/$installPath/share/man/man1" >> $specFileExtra
|
||||
|
||||
for i in "${extra_man_pages[@]}"; do
|
||||
if [ -f "$distMan/man1/$i" ]; then
|
||||
echo "gzip -f $distMan/man1/$i" >> $specFileExtra
|
||||
@@ -1165,34 +1125,34 @@ package_docs() {
|
||||
local packageName="rocm-llvm-docs"
|
||||
local packageSummary="ROCm LLVM compiler documentation"
|
||||
local packageSummaryLong="Documenation for LLVM $llvmParsedVersion"
|
||||
local installPath="$ROCM_INSTALL_PATH/lib/llvm/share"
|
||||
|
||||
local packageArch="amd64"
|
||||
local packageVersion="${llvmParsedVersion}.${LLVM_COMMIT_GITDATE}"
|
||||
local packageMaintainer="ROCm Compiler Support <rocm.compiler.support@amd.com>"
|
||||
local distDoc="$INSTALL_PATH/share/doc/LLVM"
|
||||
local distDoc="$INSTALL_PATH/share/doc"
|
||||
|
||||
local licenseDir="$ROCM_INSTALL_PATH/share/doc/$packageName"
|
||||
local packageDir="$BUILD_PATH/package"
|
||||
|
||||
local packageDeb="$packageDir/deb"
|
||||
local controlFile="$packageDeb/DEBIAN/control"
|
||||
local debDependencies="rocm-core"
|
||||
|
||||
local packageRpm="$packageDir/rpm"
|
||||
local specFile="$packageDir/$packageName.spec"
|
||||
local rpmRequires="rocm-core"
|
||||
|
||||
rm -rf "$packageDir"
|
||||
echo "rm -rf $packageDir"
|
||||
|
||||
if [ "$PACKAGEEXT" = "deb" ]; then
|
||||
|
||||
mkdir -p "$packageDeb/$licenseDir"
|
||||
mkdir -p "$packageDeb/$installPath"
|
||||
mkdir "${controlFile%/*}"
|
||||
mkdir -p "$packageDeb/$licenseDir"
|
||||
|
||||
cp -r "$LLVM_ROOT_LCL/LICENSE.TXT" "$packageDeb/$licenseDir"
|
||||
|
||||
cp -r "$distDoc" "$packageDeb/$licenseDir"
|
||||
cp -r "$distDoc" "$packageDeb/$installPath/doc"
|
||||
|
||||
{
|
||||
echo "Package: $packageName"
|
||||
@@ -1202,7 +1162,6 @@ package_docs() {
|
||||
echo "Maintainer: $packageMaintainer"
|
||||
echo "Version: ${packageVersion}.${ROCM_LIBPATCH_VERSION}-${JOB_DESIGNATOR}${BUILD_ID}~${DISTRO_RELEASE}"
|
||||
echo "Release: ${JOB_DESIGNATOR}${BUILD_ID}~${DISTRO_RELEASE}"
|
||||
echo "Depends: $debDependencies"
|
||||
echo "Recommends: $debRecommends"
|
||||
echo "Description: $packageSummary"
|
||||
echo " $packageSummaryLong"
|
||||
@@ -1223,7 +1182,6 @@ package_docs() {
|
||||
echo "Summary: $packageSummary" >> $specFile
|
||||
echo "Group: System Environment/Libraries" >> $specFile
|
||||
echo "License: ASL 2.0 with exceptions" >> $specFile
|
||||
echo "Requires: $rpmRequires" >> $specFile
|
||||
|
||||
echo "%description" >> $specFile
|
||||
echo "$packageSummaryLong" >> $specFile
|
||||
@@ -1232,13 +1190,16 @@ package_docs() {
|
||||
echo "%setup -T -D -c -n $packageName" >> $specFile
|
||||
|
||||
echo "%install" >> $specFile
|
||||
echo "rm -rf \$RPM_BUILD_ROOT/$installPath" >> $specFile
|
||||
echo "mkdir -p \$RPM_BUILD_ROOT/$installPath/doc" >> $specFile
|
||||
echo "mkdir -p \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
|
||||
|
||||
echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
|
||||
|
||||
echo "cp -R \"$distDoc\" \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
|
||||
echo "cp -R \"$distDoc\" \$RPM_BUILD_ROOT/$installPath" >> $specFile
|
||||
|
||||
echo "%clean" >> $specFile
|
||||
echo "rm -rf \$RPM_BUILD_ROOT/$installPath" >> $specFile
|
||||
echo "%files " >> $specFile
|
||||
echo "%defattr(-,root,root,-)" >> $specFile
|
||||
|
||||
@@ -1271,18 +1232,6 @@ build() {
|
||||
fi
|
||||
}
|
||||
|
||||
create_wheel_package() {
|
||||
echo "Creating rocm-llvm wheel package"
|
||||
mkdir -p "$ROCM_WHEEL_DIR"
|
||||
cp -f $SCRIPT_ROOT/generate_setup_py.py $ROCM_WHEEL_DIR
|
||||
cp -f $SCRIPT_ROOT/repackage_wheel.sh $ROCM_WHEEL_DIR
|
||||
cd $ROCM_WHEEL_DIR
|
||||
# Currently only supports python3.6
|
||||
./repackage_wheel.sh $RPM_PATH/rocm-llvm*.rpm python3.6
|
||||
# Copy the wheel created to RPM folder which will be uploaded to artifactory
|
||||
mv "$ROCM_WHEEL_DIR"/dist/*.whl "$RPM_PATH"
|
||||
}
|
||||
|
||||
case $TARGET in
|
||||
(clean) clean_lightning ;;
|
||||
(all)
|
||||
@@ -1301,9 +1250,4 @@ case $TARGET in
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
if [[ $WHEEL_PACKAGE == true ]]; then
|
||||
echo "Wheel Package build started !!!!"
|
||||
create_wheel_package
|
||||
fi
|
||||
|
||||
echo "Operation complete"
|
||||
|
||||
@@ -44,7 +44,7 @@ build_miopen_deps() {
|
||||
cd "$COMPONENT_SRC"
|
||||
|
||||
# Commenting the rocMLIR & composable_kernel from requirements.txt
|
||||
sed -i '/ROCm\/rocMLIR@\|ROCm\/composable_kernel@/s/^/#/' requirements.txt
|
||||
sed -i '/ROCmSoftwarePlatform\/rocMLIR@\|ROCmSoftwarePlatform\/composable_kernel@/s/^/#/' requirements.txt
|
||||
# Extract MLIR commit from requirements.txt
|
||||
MLIR_COMMIT="$(awk '/rocMLIR/ {split($1, s, "@"); print s[2]}' requirements.txt)"
|
||||
|
||||
|
||||
@@ -13,7 +13,7 @@ build_miopen_hip() {
|
||||
echo "Start build"
|
||||
|
||||
cd $COMPONENT_SRC
|
||||
git config --global --add safe.directory "$COMPONENT_SRC"
|
||||
|
||||
checkout_lfs
|
||||
|
||||
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
|
||||
@@ -22,9 +22,8 @@ build_miopen_hip() {
|
||||
fi
|
||||
|
||||
mkdir "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
init_rocm_common_cmake_params
|
||||
cmake \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DMIOPEN_BACKEND=HIP \
|
||||
-DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
|
||||
-DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
|
||||
|
||||
@@ -16,8 +16,6 @@ build_mivisionx() {
|
||||
BUILD_DEV=OFF
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
else
|
||||
@@ -25,7 +23,7 @@ build_mivisionx() {
|
||||
fi
|
||||
|
||||
cmake \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DROCM_PATH="$ROCM_PATH" \
|
||||
-DBUILD_DEV=$BUILD_DEV \
|
||||
-DCMAKE_INSTALL_LIBDIR=$(getInstallLibDir) \
|
||||
|
||||
@@ -1,171 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: ${BASH_SOURCE##*/} [options ...]"
|
||||
echo
|
||||
echo "Options:"
|
||||
echo " -c, --clean Clean output and delete all intermediate work"
|
||||
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
|
||||
echo " -p, --package <type> Specify packaging format"
|
||||
echo " -r, --release Make a release build instead of a debug build"
|
||||
echo " -a, --address_sanitizer Enable address sanitizer"
|
||||
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
|
||||
type referred to by pkg_type"
|
||||
echo " -w, --wheel Creates python wheel package of omniperf.
|
||||
It needs to be used along with -r option"
|
||||
echo " -h, --help Prints this help"
|
||||
echo
|
||||
echo "Possible values for <type>:"
|
||||
echo " deb -> Debian format (default)"
|
||||
echo " rpm -> RPM format"
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
API_NAME="omniperf"
|
||||
PROJ_NAME="$API_NAME"
|
||||
LIB_NAME="lib${API_NAME}"
|
||||
TARGET="build"
|
||||
MAKETARGET="deb"
|
||||
PACKAGE_ROOT="$(getPackageRoot)"
|
||||
PACKAGE_LIB="$(getLibPath)"
|
||||
BUILD_DIR="$(getBuildPath $API_NAME)"
|
||||
PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
|
||||
PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
|
||||
ROCM_WHEEL_DIR="${BUILD_DIR}/_wheel"
|
||||
BUILD_TYPE="Debug"
|
||||
MAKE_OPTS="$DASH_JAY -C $BUILD_DIR"
|
||||
SHARED_LIBS="ON"
|
||||
CLEAN_OR_OUT=0;
|
||||
MAKETARGET="deb"
|
||||
PKGTYPE="deb"
|
||||
WHEEL_PACKAGE=false
|
||||
|
||||
|
||||
#parse the arguments
|
||||
VALID_STR=$(getopt -o hcraso:p:w --long help,clean,release,static,address_sanitizer,outdir:,package:,wheel -- "$@")
|
||||
eval set -- "$VALID_STR"
|
||||
|
||||
while true ;
|
||||
do
|
||||
case "$1" in
|
||||
-h | --help)
|
||||
printUsage ; exit 0;;
|
||||
-c | --clean)
|
||||
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
|
||||
-r | --release)
|
||||
BUILD_TYPE="Release" ; shift ;;
|
||||
-a | --address_sanitizer)
|
||||
set_asan_env_vars
|
||||
set_address_sanitizer_on ; shift ;;
|
||||
-s | --static)
|
||||
SHARED_LIBS="OFF" ; shift ;;
|
||||
-o | --outdir)
|
||||
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
|
||||
-p | --package)
|
||||
MAKETARGET="$2" ; shift 2 ;;
|
||||
-w | --wheel)
|
||||
WHEEL_PACKAGE=true ; shift ;;
|
||||
--) shift; break;; # end delimiter
|
||||
*)
|
||||
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
|
||||
esac
|
||||
|
||||
done
|
||||
|
||||
RET_CONFLICT=1
|
||||
check_conflicting_options "$CLEAN_OR_OUT" "$PKGTYPE" "$MAKETARGET"
|
||||
if [ $RET_CONFLICT -ge 30 ]; then
|
||||
print_vars "$API_NAME" "$TARGET" "$BUILD_TYPE" "$SHARED_LIBS" "$CLEAN_OR_OUT" "$PKGTYPE" "$MAKETARGET"
|
||||
exit $RET_CONFLICT
|
||||
fi
|
||||
|
||||
clean() {
|
||||
echo "Cleaning $PROJ_NAME"
|
||||
rm -rf "$ROCM_WHEEL_DIR"
|
||||
rm -rf "$BUILD_DIR"
|
||||
rm -rf "$PACKAGE_DEB"
|
||||
rm -rf "$PACKAGE_RPM"
|
||||
rm -rf "$PACKAGE_ROOT/${PROJ_NAME:?}"
|
||||
rm -rf "$PACKAGE_LIB/${LIB_NAME:?}"*
|
||||
}
|
||||
|
||||
build() {
|
||||
echo "Building $PROJ_NAME"
|
||||
if [ "$DISTRO_ID" = centos-7 ]; then
|
||||
echo "Skip make and uploading packages for Omniperf on Centos7 distro, due to python dependency"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [ ! -d "$BUILD_DIR" ]; then
|
||||
mkdir -p "$BUILD_DIR"
|
||||
pushd "$BUILD_DIR" || exit
|
||||
|
||||
echo "ROCm CMake Params: $(rocm_cmake_params)"
|
||||
echo "ROCm Common CMake Params: $(rocm_common_cmake_params)"
|
||||
|
||||
print_lib_type $SHARED_LIBS
|
||||
cmake \
|
||||
$(rocm_cmake_params) \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DCHECK_PYTHON_DEPS=NO \
|
||||
-DPYTHON_DEPS=${BUILD_DIR}/python-libs \
|
||||
-DMOD_INSTALL_PATH=${BUILD_DIR}/modulefiles \
|
||||
"$OMNIPERF_ROOT"
|
||||
fi
|
||||
|
||||
make $MAKE_OPTS
|
||||
make $MAKE_OPTS install
|
||||
make $MAKE_OPTS package
|
||||
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
|
||||
}
|
||||
|
||||
create_wheel_package() {
|
||||
echo "Creating Omniperf wheel package"
|
||||
|
||||
# Copy the setup.py generator to build folder
|
||||
mkdir -p "$ROCM_WHEEL_DIR"
|
||||
cp -f "$SCRIPT_ROOT"/generate_setup_py.py "$ROCM_WHEEL_DIR"
|
||||
cp -f "$SCRIPT_ROOT"/repackage_wheel.sh "$ROCM_WHEEL_DIR"
|
||||
cd "$ROCM_WHEEL_DIR" || exit
|
||||
|
||||
# Currently only supports python3.6
|
||||
./repackage_wheel.sh "$BUILD_DIR"/*.rpm python3.6
|
||||
|
||||
# Copy the wheel created to RPM folder which will be uploaded to artifactory
|
||||
copy_if WHL "WHL" "$PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
|
||||
}
|
||||
|
||||
print_output_directory() {
|
||||
case ${PKGTYPE} in
|
||||
("deb")
|
||||
echo "${PACKAGE_DEB}";;
|
||||
("rpm")
|
||||
echo "${PACKAGE_RPM}";;
|
||||
(*)
|
||||
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
|
||||
esac
|
||||
exit
|
||||
}
|
||||
|
||||
verifyEnvSetup
|
||||
|
||||
case "$TARGET" in
|
||||
(clean) clean ;;
|
||||
(build) build ;;
|
||||
(outdir) print_output_directory ;;
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
if [[ $WHEEL_PACKAGE == true ]]; then
|
||||
echo "Wheel Package build started !!!!"
|
||||
create_wheel_package
|
||||
fi
|
||||
|
||||
echo "Operation complete"
|
||||
@@ -1,191 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: ${BASH_SOURCE##*/} [options ...]"
|
||||
echo
|
||||
echo "Options:"
|
||||
echo " -c, --clean Clean output and delete all intermediate work"
|
||||
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
|
||||
echo " -p, --package <type> Specify packaging format"
|
||||
echo " -r, --release Make a release build instead of a debug build"
|
||||
echo " -a, --address_sanitizer Enable address sanitizer"
|
||||
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
|
||||
type referred to by pkg_type"
|
||||
echo " -w, --wheel Creates python wheel package of omnitrace.
|
||||
It needs to be used along with -r option"
|
||||
echo " -h, --help Prints this help"
|
||||
echo
|
||||
echo "Possible values for <type>:"
|
||||
echo " deb -> Debian format (default)"
|
||||
echo " rpm -> RPM format"
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
API_NAME="omnitrace"
|
||||
PROJ_NAME="$API_NAME"
|
||||
LIB_NAME="lib${API_NAME}"
|
||||
TARGET="build"
|
||||
MAKETARGET="deb"
|
||||
PACKAGE_ROOT="$(getPackageRoot)"
|
||||
PACKAGE_LIB="$(getLibPath)"
|
||||
BUILD_DIR="$(getBuildPath $API_NAME)"
|
||||
PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
|
||||
PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
|
||||
BUILD_TYPE="Debug"
|
||||
MAKE_OPTS="-j 8"
|
||||
SHARED_LIBS="ON"
|
||||
CLEAN_OR_OUT=0
|
||||
MAKETARGET="deb"
|
||||
PKGTYPE="deb"
|
||||
ASAN=0
|
||||
|
||||
#parse the arguments
|
||||
VALID_STR=$(getopt -o hcraso:p:w --long help,clean,release,address_sanitizer,static,outdir:,package:,wheel -- "$@")
|
||||
eval set -- "$VALID_STR"
|
||||
|
||||
while true; do
|
||||
case "$1" in
|
||||
-h | --help)
|
||||
printUsage
|
||||
exit 0
|
||||
;;
|
||||
-c | --clean)
|
||||
TARGET="clean"
|
||||
((CLEAN_OR_OUT |= 1))
|
||||
shift
|
||||
;;
|
||||
-r | --release)
|
||||
BUILD_TYPE="RelWithDebInfo"
|
||||
shift
|
||||
;;
|
||||
-a | --address_sanitizer)
|
||||
ack_and_ignore_asan
|
||||
|
||||
ASAN=1
|
||||
shift
|
||||
;;
|
||||
-s | --static)
|
||||
SHARED_LIBS="OFF"
|
||||
shift
|
||||
;;
|
||||
-o | --outdir)
|
||||
TARGET="outdir"
|
||||
PKGTYPE=$2
|
||||
((CLEAN_OR_OUT |= 2))
|
||||
shift 2
|
||||
;;
|
||||
-p | --package)
|
||||
MAKETARGET="$2"
|
||||
shift 2
|
||||
;;
|
||||
-w | --wheel)
|
||||
echo "omnitrace: wheel build option accepted and ignored"
|
||||
shift
|
||||
;;
|
||||
--)
|
||||
shift
|
||||
break
|
||||
;;
|
||||
*)
|
||||
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] " >&2
|
||||
exit 20
|
||||
;;
|
||||
esac
|
||||
|
||||
done
|
||||
|
||||
RET_CONFLICT=1
|
||||
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
|
||||
if [ $RET_CONFLICT -ge 30 ]; then
|
||||
print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
|
||||
exit $RET_CONFLICT
|
||||
fi
|
||||
|
||||
clean() {
|
||||
echo "Cleaning $PROJ_NAME"
|
||||
rm -rf "$BUILD_DIR"
|
||||
rm -rf "$PACKAGE_DEB"
|
||||
rm -rf "$PACKAGE_RPM"
|
||||
rm -rf "$PACKAGE_ROOT/${PROJ_NAME:?}"
|
||||
rm -rf "$PACKAGE_LIB/${LIB_NAME:?}"*
|
||||
}
|
||||
|
||||
build_omnitrace() {
|
||||
echo "Building $PROJ_NAME"
|
||||
if [ "$DISTRO_ID" = "mariner-2.0" ] || [ "$DISTRO_ID" = "ubuntu-24.04" ] || [ "$DISTRO_ID" = "azurelinux-3.0" ]; then
|
||||
echo "Skip make and uploading packages for Omnitrace on \"${DISTRO_ID}\" distro"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [ $ASAN == 1 ]; then
|
||||
echo "Skip make and uploading packages for Omnitrace on ASAN build"
|
||||
exit 0
|
||||
fi
|
||||
if [ ! -d "$BUILD_DIR" ]; then
|
||||
mkdir -p "$BUILD_DIR"
|
||||
echo "Created build directory: $BUILD_DIR"
|
||||
fi
|
||||
|
||||
echo "Build directory: $BUILD_DIR"
|
||||
pushd "$BUILD_DIR" || exit
|
||||
print_lib_type $SHARED_LIBS
|
||||
|
||||
echo "ROCm CMake Params: $(rocm_cmake_params)"
|
||||
echo "ROCm Common CMake Params: $(rocm_common_cmake_params)"
|
||||
|
||||
|
||||
if [ $ASAN == 1 ]; then
|
||||
echo "Address Sanitizer path"
|
||||
|
||||
else
|
||||
cmake \
|
||||
$(rocm_cmake_params) \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DOMNITRACE_BUILD_{LIBUNWIND,DYNINST}=ON \
|
||||
-DDYNINST_BUILD_{TBB,BOOST,ELFUTILS,LIBIBERTY}=ON \
|
||||
"$OMNITRACE_ROOT"
|
||||
fi
|
||||
|
||||
|
||||
popd || exit
|
||||
|
||||
echo "Make Options: $MAKE_OPTS"
|
||||
cmake --build "$BUILD_DIR" --target all -- $MAKE_OPTS
|
||||
cmake --build "$BUILD_DIR" --target install -- $MAKE_OPTS
|
||||
cmake --build "$BUILD_DIR" --target package -- $MAKE_OPTS
|
||||
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
|
||||
}
|
||||
|
||||
print_output_directory() {
|
||||
case ${PKGTYPE} in
|
||||
"deb")
|
||||
echo "${PACKAGE_DEB}"
|
||||
;;
|
||||
"rpm")
|
||||
echo "${PACKAGE_RPM}"
|
||||
;;
|
||||
*)
|
||||
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
exit
|
||||
}
|
||||
|
||||
verifyEnvSetup
|
||||
|
||||
case "$TARGET" in
|
||||
clean) clean ;;
|
||||
build) build_omnitrace ;;
|
||||
outdir) print_output_directory ;;
|
||||
*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
echo "Operation complete"
|
||||
@@ -1,141 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
PROJ_NAME=OpenCL-ICD-Loader
|
||||
TARGET="build"
|
||||
MAKEOPTS="$DASH_JAY"
|
||||
BUILD_TYPE="Debug"
|
||||
PACKAGE_ROOT="$(getPackageRoot)"
|
||||
PACKAGE_DEB="$PACKAGE_ROOT/deb/${PROJ_NAME,,}"
|
||||
PACKAGE_RPM="$PACKAGE_ROOT/rpm/${PROJ_NAME,,}"
|
||||
CLEAN_OR_OUT=0;
|
||||
PKGTYPE="deb"
|
||||
MAKETARGET="deb"
|
||||
API_NAME="rocm-opencl-icd-loader"
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
|
||||
echo
|
||||
echo "Options:"
|
||||
echo " -c, --clean Clean output and delete all intermediate work"
|
||||
echo " -p, --package <type> Specify packaging format"
|
||||
echo " -r, --release Make a release build instead of a debug build"
|
||||
echo " -h, --help Prints this help"
|
||||
echo " -o, --outdir Print path of output directory containing packages"
|
||||
echo " -s, --static Component/Build does not support static builds just accepting this param & ignore. No effect of the param on this build"
|
||||
echo
|
||||
echo "Possible values for <type>:"
|
||||
echo " deb -> Debian format (default)"
|
||||
echo " rpm -> RPM format"
|
||||
echo
|
||||
return 0
|
||||
}
|
||||
|
||||
RET_CONFLICT=1
|
||||
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
|
||||
if [ $RET_CONFLICT -ge 30 ]; then
|
||||
print_vars $TARGET $BUILD_TYPE $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
|
||||
exit $RET_CONFLICT
|
||||
fi
|
||||
|
||||
clean_opencl_icd_loader() {
|
||||
echo "Cleaning $PROJ_NAME"
|
||||
rm -rf "$PACKAGE_DEB"
|
||||
rm -rf "$PACKAGE_RPM"
|
||||
rm -rf "$PACKAGE_ROOT/${PROJ_NAME,,}"
|
||||
}
|
||||
|
||||
copy_pkg_files_to_rocm() {
|
||||
local comp_folder=$1
|
||||
local comp_pkg_name=$2
|
||||
|
||||
cd "${OUT_DIR}/${PKGTYPE}/${comp_folder}"|| exit 2
|
||||
if [ "${PKGTYPE}" = 'deb' ]; then
|
||||
dpkg-deb -x ${comp_pkg_name}_*.deb pkg/
|
||||
else
|
||||
mkdir pkg && pushd pkg/ || exit 2
|
||||
if [[ "${comp_pkg_name}" != *-dev* ]]; then
|
||||
rpm2cpio ../${comp_pkg_name}-*.rpm | cpio -idmv
|
||||
else
|
||||
rpm2cpio ../${comp_pkg_name}el-*.rpm | cpio -idmv
|
||||
fi
|
||||
popd || exit 2
|
||||
fi
|
||||
ls ./pkg -alt
|
||||
cp -r ./pkg/*/rocm*/* "${ROCM_PATH}" || exit 2
|
||||
rm -rf pkg/
|
||||
}
|
||||
|
||||
build_opencl_icd_loader() {
|
||||
echo "Downloading $PROJ_NAME" package
|
||||
if [ "$DISTRO_NAME" = ubuntu ]; then
|
||||
mkdir -p "$PACKAGE_DEB"
|
||||
local rocm_ver=${ROCM_VERSION}
|
||||
if [ ${ROCM_VERSION##*.} = 0 ]; then
|
||||
rocm_ver=${ROCM_VERSION%.*}
|
||||
fi
|
||||
local url="https://repo.radeon.com/rocm/apt/${rocm_ver}/pool/main/r/${API_NAME}/"
|
||||
local package
|
||||
package=$(curl -s "$url" | grep -Po 'href="\K[^"]*' | grep "${DISTRO_RELEASE}" | head -n 1)
|
||||
|
||||
if [ -z "$package" ]; then
|
||||
echo "No package found for Ubuntu version $DISTRO_RELEASE"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
wget -t3 -P "$PACKAGE_DEB" "${url}${package}"
|
||||
copy_pkg_files_to_rocm ${PROJ_NAME,,} ${API_NAME}
|
||||
else
|
||||
echo "$DISTRO_ID is not supported..."
|
||||
exit 2
|
||||
fi
|
||||
|
||||
echo "Installing $PROJ_NAME" package
|
||||
}
|
||||
|
||||
print_output_directory() {
|
||||
case ${PKGTYPE} in
|
||||
("deb")
|
||||
echo ${PACKAGE_DEB};;
|
||||
("rpm")
|
||||
echo ${PACKAGE_RPM};;
|
||||
(*)
|
||||
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
|
||||
esac
|
||||
exit
|
||||
}
|
||||
|
||||
VALID_STR=`getopt -o hcraswlo:p: --long help,clean,release,outdir:,package: -- "$@"`
|
||||
eval set -- "$VALID_STR"
|
||||
while true ;
|
||||
do
|
||||
case "$1" in
|
||||
(-c | --clean )
|
||||
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
|
||||
(-r | --release )
|
||||
BUILD_TYPE="RelWithDebInfo" ; shift ;;
|
||||
(-h | --help )
|
||||
printUsage ; exit 0 ;;
|
||||
(-a | --address_sanitizer)
|
||||
ack_and_ignore_asan ; shift ;;
|
||||
(-o | --outdir)
|
||||
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
|
||||
(-p | --package)
|
||||
MAKETARGET="$2" ; shift 2;;
|
||||
(-s | --static)
|
||||
echo "-s parameter accepted but ignored" ; shift ;;
|
||||
--) shift; break;;
|
||||
(*)
|
||||
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
|
||||
esac
|
||||
done
|
||||
|
||||
case $TARGET in
|
||||
(clean) clean_opencl_icd_loader ;;
|
||||
(build) build_opencl_icd_loader ;;
|
||||
(outdir) print_output_directory ;;
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
echo "Operation complete"
|
||||
@@ -26,16 +26,14 @@ build_rccl() {
|
||||
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
CC=${ROCM_PATH}/bin/amdclang \
|
||||
CXX=$(set_build_variables CXX) \
|
||||
cmake \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
-DHIP_COMPILER=clang \
|
||||
-DCMAKE_PREFIX_PATH="${ROCM_PATH};${ROCM_PATH}/share/rocm/cmake/" \
|
||||
${LAUNCHER_FLAGS} \
|
||||
-DCPACK_GENERATOR="${PKGTYPE^^}" \
|
||||
-DROCM_PATCH_VERSION=$ROCM_LIBPATCH_VERSION \
|
||||
-DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \
|
||||
|
||||
@@ -1,53 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -ex
|
||||
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
|
||||
|
||||
set_component_src rocAL
|
||||
|
||||
build_rocal() {
|
||||
|
||||
if [ "$DISTRO_ID" = "mariner-2.0" ] ; then
|
||||
echo "Not building rocal for ${DISTRO_ID}. Exiting..."
|
||||
return 0
|
||||
fi
|
||||
|
||||
echo "Start build"
|
||||
|
||||
# Enable ASAN
|
||||
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
|
||||
set_asan_env_vars
|
||||
set_address_sanitizer_on
|
||||
fi
|
||||
|
||||
mkdir -p $BUILD_DIR && cd $BUILD_DIR
|
||||
|
||||
python3 ${COMPONENT_SRC}/rocAL-setup.py
|
||||
|
||||
cmake -DAMDRPP_PATH=$ROCM_PATH ${COMPONENT_SRC}
|
||||
make -j${PROC}
|
||||
cmake --build . --target PyPackageInstall
|
||||
sudo make install
|
||||
sudo make package
|
||||
sudo chown -R $(id -u):$(id -g) ${BUILD_DIR}
|
||||
|
||||
rm -rf _CPack_Packages/ && find -name '*.o' -delete
|
||||
mkdir -p $PACKAGE_DIR
|
||||
cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
|
||||
show_build_cache_stats
|
||||
}
|
||||
|
||||
clean_rocal() {
|
||||
echo "Cleaning rocAL build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
|
||||
rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
|
||||
echo "Done!"
|
||||
}
|
||||
|
||||
stage2_command_args "$@"
|
||||
|
||||
case $TARGET in
|
||||
build) build_rocal ;;
|
||||
outdir) print_output_directory ;;
|
||||
clean) clean_rocal ;;
|
||||
*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
@@ -22,7 +22,6 @@ build_rocalution() {
|
||||
echo "CXX compiler: $CXX"
|
||||
|
||||
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
@@ -33,7 +32,7 @@ build_rocalution() {
|
||||
cmake \
|
||||
-DSUPPORT_HIP=ON \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
-DCPACK_SET_DESTDIR=OFF \
|
||||
-DBUILD_CLIENTS_SAMPLES=ON \
|
||||
|
||||
@@ -28,12 +28,11 @@ build_rocblas() {
|
||||
else
|
||||
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack+;gfx90a:xnack-;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
|
||||
fi
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
cmake \
|
||||
-DCMAKE_TOOLCHAIN_FILE=toolchain-linux.cmake \
|
||||
-DBUILD_DIR="${BUILD_DIR}" \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DROCM_DIR="${ROCM_PATH}" \
|
||||
${LAUNCHER_FLAGS} \
|
||||
-DCMAKE_PREFIX_PATH="${DEPS_DIR};${ROCM_PATH}" \
|
||||
|
||||
@@ -4,16 +4,15 @@ source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
|
||||
set_component_src rocDecode
|
||||
BUILD_DEV=ON
|
||||
build_rocdecode() {
|
||||
if [ "$DISTRO_ID" = "centos-7" ] || [ "$DISTRO_ID" = "sles-15.4" ] ; then
|
||||
if [ "$DISTRO_ID" = "centos-7" ] ; then
|
||||
echo "Not building rocDecode for ${DISTRO_ID}. Exiting..."
|
||||
return 0
|
||||
fi
|
||||
|
||||
echo "Start build"
|
||||
mkdir -p $BUILD_DIR && cd $BUILD_DIR
|
||||
python3 ${COMPONENT_SRC}/rocDecode-setup.py --developer OFF
|
||||
|
||||
cmake -DROCM_DEP_ROCMCORE=ON ${COMPONENT_SRC}
|
||||
cmake ${COMPONENT_SRC}
|
||||
make -j8
|
||||
make install
|
||||
make package
|
||||
|
||||
@@ -16,7 +16,6 @@ build_rocfft() {
|
||||
set_address_sanitizer_on
|
||||
fi
|
||||
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
@@ -27,7 +26,7 @@ build_rocfft() {
|
||||
CXX="${ROCM_PATH}/bin/hipcc" \
|
||||
cmake \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
-DUSE_HIP_CLANG=ON \
|
||||
-DHIP_COMPILER=clang \
|
||||
|
||||
@@ -10,13 +10,11 @@ printUsage() {
|
||||
echo " -c, --clean Clean output and delete all intermediate work"
|
||||
echo " -r, --release Build a release version of the package"
|
||||
echo " -a, --address_sanitizer Enable address sanitizer"
|
||||
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
|
||||
echo " -w, --wheel Creates python wheel package of rocm-cmake.
|
||||
It needs to be used along with -r option"
|
||||
echo " -s, --static Supports static CI by accepting this param & not bailing out. No effect of the param though"
|
||||
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
|
||||
type referred to by pkg_type"
|
||||
echo " -p, --package <type> Specify packaging format"
|
||||
echo " -h, --help Prints this help"
|
||||
echo " -h, --help Prints this help"
|
||||
echo
|
||||
echo
|
||||
|
||||
@@ -32,7 +30,6 @@ ROCM_CMAKE_BUILD_DIR="$(getBuildPath rocm-cmake)"
|
||||
ROCM_CMAKE_BUILD_DIR="$(getBuildPath rocm-cmake)"
|
||||
ROCM_CMAKE_PACKAGE_DEB="$(getPackageRoot)/deb/rocm-cmake"
|
||||
ROCM_CMAKE_PACKAGE_RPM="$(getPackageRoot)/rpm/rocm-cmake"
|
||||
ROCM_WHEEL_DIR="${ROCM_CMAKE_BUILD_DIR}/_wheel"
|
||||
ROCM_CMAKE_BUILD_TYPE="debug"
|
||||
BUILD_TYPE="Debug"
|
||||
SHARED_LIBS="ON"
|
||||
@@ -40,7 +37,7 @@ CLEAN_OR_OUT=0;
|
||||
PKGTYPE="deb"
|
||||
MAKETARGET="deb"
|
||||
|
||||
VALID_STR=`getopt -o hcraswo:p: --long help,clean,release,static,wheel,address_sanitizer,outdir:,package: -- "$@"`
|
||||
VALID_STR=`getopt -o hcraso:p: --long help,clean,release,static,address_sanitizer,outdir:,package: -- "$@"`
|
||||
eval set -- "$VALID_STR"
|
||||
|
||||
while true ;
|
||||
@@ -56,8 +53,6 @@ do
|
||||
ack_and_ignore_asan ; shift ;;
|
||||
(-s | --static)
|
||||
SHARED_LIBS="OFF" ; shift ;;
|
||||
(-w | --wheel)
|
||||
WHEEL_PACKAGE=true ; shift ;;
|
||||
(-o | --outdir)
|
||||
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
|
||||
(-p | --package)
|
||||
@@ -78,7 +73,6 @@ fi
|
||||
|
||||
|
||||
clean_rocm_cmake() {
|
||||
rm -rf "$ROCM_WHEEL_DIR"
|
||||
rm -rf $ROCM_CMAKE_BUILD_DIR
|
||||
rm -rf $ROCM_CMAKE_PACKAGE_DEB
|
||||
rm -rf $ROCM_CMAKE_PACKAGE_RPM
|
||||
@@ -93,7 +87,6 @@ build_rocm_cmake() {
|
||||
|
||||
cmake \
|
||||
$(rocm_cmake_params) \
|
||||
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
|
||||
-DCPACK_SET_DESTDIR="OFF" \
|
||||
-DROCM_DISABLE_LDCONFIG=ON \
|
||||
$ROCM_CMAKE_ROOT
|
||||
@@ -106,19 +99,6 @@ build_rocm_cmake() {
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$ROCM_CMAKE_PACKAGE_RPM" $ROCM_CMAKE_BUILD_DIR/rocm-cmake*.rpm
|
||||
}
|
||||
|
||||
create_wheel_package() {
|
||||
echo "Creating rocm-cmake wheel package"
|
||||
# Copy the setup.py generator to build folder
|
||||
mkdir -p $ROCM_WHEEL_DIR
|
||||
cp -f $SCRIPT_ROOT/generate_setup_py.py $ROCM_WHEEL_DIR
|
||||
cp -f $SCRIPT_ROOT/repackage_wheel.sh $ROCM_WHEEL_DIR
|
||||
cd $ROCM_WHEEL_DIR
|
||||
# Currently only supports python3.6
|
||||
./repackage_wheel.sh $ROCM_CMAKE_BUILD_DIR/rocm-cmake*.rpm python3.6
|
||||
# Copy the wheel created to RPM folder which will be uploaded to artifactory
|
||||
copy_if WHL "WHL" "$ROCM_CMAKE_PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
|
||||
}
|
||||
|
||||
print_output_directory() {
|
||||
case ${PKGTYPE} in
|
||||
("deb")
|
||||
@@ -138,9 +118,4 @@ case $TARGET in
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
if [[ $WHEEL_PACKAGE == true ]]; then
|
||||
echo "Wheel Package build started !!!!"
|
||||
create_wheel_package
|
||||
fi
|
||||
|
||||
echo "Operation complete"
|
||||
|
||||
@@ -24,14 +24,13 @@ build_rocprim() {
|
||||
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
CXX="${ROCM_PATH}/bin/hipcc" \
|
||||
cmake \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
-DBUILD_BENCHMARK=OFF \
|
||||
-DBUILD_SHARED_LIBS=ON \
|
||||
-DBUILD_BENCHMARK=OFF \
|
||||
-DBUILD_TEST=ON \
|
||||
-DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip;${ROCM_PATH}/hip/cmake" \
|
||||
"$COMPONENT_SRC"
|
||||
|
||||
@@ -1,222 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: ${BASH_SOURCE##*/} [options ...]"
|
||||
echo
|
||||
echo "Options:"
|
||||
echo " -c, --clean Clean output and delete all intermediate work"
|
||||
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
|
||||
echo " -w, --wheel Creates python wheel package of rocprofiler-sdk.
|
||||
It needs to be used along with -r option"
|
||||
echo " -p, --package <type> Specify packaging format"
|
||||
echo " -r, --release Make a release build instead of a debug build"
|
||||
echo " -a, --address_sanitizer Enable address sanitizer"
|
||||
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
|
||||
type referred to by pkg_type"
|
||||
echo " -h, --help Prints this help"
|
||||
echo
|
||||
echo "Possible values for <type>:"
|
||||
echo " deb -> Debian format (default)"
|
||||
echo " rpm -> RPM format"
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
API_NAME="rocprofiler-sdk"
|
||||
PROJ_NAME="$API_NAME"
|
||||
LIB_NAME="lib${API_NAME}"
|
||||
TARGET="build"
|
||||
MAKETARGET="deb"
|
||||
PACKAGE_ROOT="$(getPackageRoot)"
|
||||
PACKAGE_LIB="$(getLibPath)"
|
||||
PACKAGE_INCLUDE="$(getIncludePath)"
|
||||
BUILD_DIR="$(getBuildPath $API_NAME)"
|
||||
PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
|
||||
PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
|
||||
ROCM_WHEEL_DIR="${BUILD_DIR}/_wheel"
|
||||
PACKAGE_PREFIX="$ROCM_INSTALL_PATH"
|
||||
BUILD_TYPE="Debug"
|
||||
MAKE_OPTS="$DASH_JAY"
|
||||
SHARED_LIBS="ON"
|
||||
CLEAN_OR_OUT=0
|
||||
MAKETARGET="deb"
|
||||
PKGTYPE="deb"
|
||||
|
||||
GPU_LIST="gfx900;gfx906;gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1031;gfx1100;gfx1101;gfx1102"
|
||||
ASAN=0
|
||||
|
||||
VALID_STR=$(getopt -o hcrawso:p: --long help,clean,release,static,address_sanitizer,wheel,outdir:,package: -- "$@")
|
||||
eval set -- "$VALID_STR"
|
||||
|
||||
while true; do
|
||||
case "$1" in
|
||||
-h | --help)
|
||||
printUsage
|
||||
exit 0
|
||||
;;
|
||||
-c | --clean)
|
||||
TARGET="clean"
|
||||
((CLEAN_OR_OUT |= 1))
|
||||
shift
|
||||
;;
|
||||
-r | --release)
|
||||
BUILD_TYPE="RelWithDebInfo"
|
||||
shift
|
||||
;;
|
||||
-a | --address_sanitizer)
|
||||
set_address_sanitizer_on
|
||||
set_asan_env_vars
|
||||
ASAN=1
|
||||
shift
|
||||
;;
|
||||
-s | --static)
|
||||
SHARED_LIBS="OFF"
|
||||
shift
|
||||
;;
|
||||
-w | --wheel)
|
||||
WHEEL_PACKAGE=true
|
||||
shift
|
||||
;;
|
||||
-o | --outdir)
|
||||
TARGET="outdir"
|
||||
PKGTYPE=$2
|
||||
OUT_DIR_SPECIFIED=1
|
||||
((CLEAN_OR_OUT |= 2))
|
||||
shift 2
|
||||
;;
|
||||
-p | --package)
|
||||
MAKETARGET="$2"
|
||||
shift 2
|
||||
;;
|
||||
--)
|
||||
shift
|
||||
break
|
||||
;; # end delimiter
|
||||
*)
|
||||
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] " >&2
|
||||
exit 20
|
||||
;;
|
||||
esac
|
||||
|
||||
done
|
||||
|
||||
RET_CONFLICT=1
|
||||
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
|
||||
if [ $RET_CONFLICT -ge 30 ]; then
|
||||
print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
|
||||
exit $RET_CONFLICT
|
||||
fi
|
||||
|
||||
clean() {
|
||||
echo "Cleaning $PROJ_NAME"
|
||||
rm -rf "$ROCM_WHEEL_DIR"
|
||||
rm -rf "$BUILD_DIR"
|
||||
rm -rf "$PACKAGE_DEB"
|
||||
rm -rf "$PACKAGE_RPM"
|
||||
rm -rf "$PACKAGE_ROOT/${PROJ_NAME}"
|
||||
rm -rf "$PACKAGE_ROOT/libexec/${PROJ_NAME}"
|
||||
rm -rf "$PACKAGE_INCLUDE/${PROJ_NAME}"
|
||||
rm -rf "$PACKAGE_LIB/${LIB_NAME}"*
|
||||
rm -rf "$PACKAGE_LIB/${PROJ_NAME}"
|
||||
}
|
||||
|
||||
build_rocprofiler-sdk() {
|
||||
if [ ! -f "${ROCPROFILER_SDK_ROOT}/CMakeLists.txt" ]; then
|
||||
echo "Warning: $ROCPROFILER_SDK_ROOT not found"
|
||||
else
|
||||
echo "Building $PROJ_NAME"
|
||||
PACKAGE_CMAKE="$(getCmakePath)"
|
||||
if [ ! -d "$BUILD_DIR" ]; then
|
||||
mkdir -p "$BUILD_DIR"
|
||||
pushd "$BUILD_DIR"
|
||||
print_lib_type $SHARED_LIBS
|
||||
|
||||
if [ $ASAN == 1 ]; then
|
||||
cmake \
|
||||
$(rocm_cmake_params) \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DAMDDeviceLibs_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/AMDDeviceLibs" \
|
||||
-Dhip_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hip" \
|
||||
-Dhip-lang_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hip-lang" \
|
||||
-Damd_comgr_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/amd_comgr" \
|
||||
-Dhsa-runtime64_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hsa-runtime64" \
|
||||
-Dhsakmt_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hsakmt" \
|
||||
-DCMAKE_HIP_COMPILER_ROCM_ROOT="${ROCM_INSTALL_PATH}" \
|
||||
-DCMAKE_PREFIX_PATH="${ROCM_INSTALL_PATH};${ROCM_INSTALL_PATH}/lib/asan" \
|
||||
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
|
||||
-DGPU_TARGETS="$GPU_LIST" \
|
||||
-DCPACK_DEBIAN_PACKAGE_SHLIBDEPS=OFF \
|
||||
-DPython3_EXECUTABLE=$(which python3) \
|
||||
"$ROCPROFILER_SDK_ROOT"
|
||||
else
|
||||
cmake \
|
||||
$(rocm_cmake_params) \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DCMAKE_PREFIX_PATH="${ROCM_INSTALL_PATH}" \
|
||||
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
|
||||
-DGPU_TARGETS="$GPU_LIST" \
|
||||
-DROCPROFILER_BUILD_SAMPLES=ON \
|
||||
-DROCPROFILER_BUILD_TESTS=ON \
|
||||
-DCPACK_DEBIAN_PACKAGE_SHLIBDEPS=OFF \
|
||||
-DPython3_EXECUTABLE=$(which python3) \
|
||||
"$ROCPROFILER_SDK_ROOT"
|
||||
fi
|
||||
|
||||
popd
|
||||
fi
|
||||
cmake --build "$BUILD_DIR" --target all -- $MAKE_OPTS
|
||||
cmake --build "$BUILD_DIR" --target install -- $MAKE_OPTS
|
||||
cmake --build "$BUILD_DIR" --target package -- $MAKE_OPTS
|
||||
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
|
||||
fi
|
||||
}
|
||||
|
||||
create_wheel_package() {
|
||||
echo "Creating rocprofiler sdk wheel package"
|
||||
mkdir -p "$ROCM_WHEEL_DIR"
|
||||
cp -f "$SCRIPT_ROOT"/generate_setup_py.py "$ROCM_WHEEL_DIR"
|
||||
cp -f "$SCRIPT_ROOT"/repackage_wheel.sh "$ROCM_WHEEL_DIR"
|
||||
cd "$ROCM_WHEEL_DIR"
|
||||
# Currently only supports python3.6
|
||||
./repackage_wheel.sh "$BUILD_DIR"/*.rpm python3.6
|
||||
# Copy the wheel created to RPM folder which will be uploaded to artifactory
|
||||
copy_if WHL "WHL" "$PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
|
||||
}
|
||||
|
||||
print_output_directory() {
|
||||
case ${PKGTYPE} in
|
||||
"deb")
|
||||
echo ${PACKAGE_DEB}
|
||||
;;
|
||||
"rpm")
|
||||
echo ${PACKAGE_RPM}
|
||||
;;
|
||||
*)
|
||||
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
exit
|
||||
}
|
||||
|
||||
verifyEnvSetup
|
||||
|
||||
case "$TARGET" in
|
||||
clean) clean ;;
|
||||
build) build_rocprofiler-sdk ;;
|
||||
outdir) print_output_directory ;;
|
||||
*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
if [[ $WHEEL_PACKAGE == true ]]; then
|
||||
echo "Wheel Package build started !!!!"
|
||||
create_wheel_package
|
||||
fi
|
||||
|
||||
echo "Operation complete"
|
||||
@@ -25,12 +25,10 @@ build_rocrand() {
|
||||
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
CXX=$(set_build_variables CXX)\
|
||||
cmake \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
-DBUILD_TEST=ON \
|
||||
-DBUILD_BENCHMARK=ON \
|
||||
|
||||
@@ -28,13 +28,11 @@ build_rocsolver() {
|
||||
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
CXX="${ROCM_PATH}/bin/hipcc" \
|
||||
cmake \
|
||||
-DCPACK_SET_DESTDIR=OFF \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-Drocblas_DIR="${ROCM_PATH}/rocblas/lib/cmake/rocblas" \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
-DBUILD_CLIENTS_TESTS=ON \
|
||||
|
||||
@@ -27,14 +27,12 @@ build_rocsparse() {
|
||||
fi
|
||||
|
||||
ROCSPARSE_TEST_MIRROR=$MIRROR \
|
||||
export CXX=$(set_build_variables CXX)\
|
||||
export CC=$(set_build_variables CC)\
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
CXX=$(set_build_variables CXX)\
|
||||
CC=$(set_build_variables CC)\
|
||||
cmake \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}"\
|
||||
$(rocm_common_cmake_params) \
|
||||
-DBUILD_CLIENTS_SAMPLES=ON \
|
||||
-DBUILD_CLIENTS_TESTS=ON \
|
||||
-DBUILD_CLIENTS_BENCHMARKS=ON \
|
||||
|
||||
@@ -27,12 +27,10 @@ build_rocthrust() {
|
||||
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
CXX=$(set_build_variables CXX)\
|
||||
cmake \
|
||||
${LAUNCHER_FLAGS} \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
-DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip;${ROCM_PATH}/hip/cmake" \
|
||||
-DROCPRIM_ROOT="${ROCM_PATH}/rocprim" \
|
||||
|
||||
@@ -27,11 +27,9 @@ build_rocwmma() {
|
||||
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1100;gfx1101"
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
CXX=$(set_build_variables CXX)\
|
||||
cmake \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
${LAUNCHER_FLAGS} \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
-DROCWMMA_BUILD_VALIDATION_TESTS=ON \
|
||||
|
||||
@@ -12,7 +12,7 @@ ROCM_LLVM_LIB_RPATH="\$ORIGIN/llvm/lib"
|
||||
rpp_specific_cmake_params() {
|
||||
local rpp_cmake_params
|
||||
if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
|
||||
rpp_cmake_params="-DCMAKE_EXE_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_ASAN_EXE_RPATH:$LLVM_LIBDIR"
|
||||
rpp_cmake_params="-DCMAKE_EXE_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_EXE_RPATH:$LLVM_LIBDIR"
|
||||
else
|
||||
rpp_cmake_params=""
|
||||
fi
|
||||
@@ -41,16 +41,14 @@ build_rpp() {
|
||||
GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100"
|
||||
fi
|
||||
|
||||
init_rocm_common_cmake_params
|
||||
|
||||
cmake \
|
||||
"${rocm_math_common_cmake_params[@]}" \
|
||||
$(rocm_common_cmake_params) \
|
||||
${LAUNCHER_FLAGS} \
|
||||
-DBACKEND=HIP \
|
||||
-DCMAKE_INSTALL_LIBDIR=$(getInstallLibDir) \
|
||||
$(rpp_specific_cmake_params) \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
-DCMAKE_SHARED_LINKER_FLAGS_INIT="-fno-openmp-implicit-rpath -Wl,--enable-new-dtags,--build-id=sha1,--rpath,${ROCM_LIB_RPATH}:${DEPS_DIR}/lib:${ROCM_LLVM_LIB_RPATH}" \
|
||||
-DCMAKE_SHARED_LINKER_FLAGS_INIT="-fno-openmp-implicit-rpath -Wl,--enable-new-dtags,--rpath,${ROCM_LIB_RPATH}:${DEPS_DIR}/lib:${ROCM_LLVM_LIB_RPATH}" \
|
||||
-DCMAKE_PREFIX_PATH="${DEPS_DIR};${ROCM_PATH}" \
|
||||
"$COMPONENT_SRC"
|
||||
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user