mirror of
https://github.com/ROCm/ROCm.git
synced 2026-01-10 23:28:03 -05:00
Compare commits
50 Commits
amd/dev/yh
...
docs/6.1.1
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
bdbd336d41 | ||
|
|
c4e752a7c6 | ||
|
|
3518cc3801 | ||
|
|
4419ad4535 | ||
|
|
86e6921cbf | ||
|
|
cf6b9f4847 | ||
|
|
83df73a564 | ||
|
|
b80f22f71a | ||
|
|
036cf71355 | ||
|
|
94e552315d | ||
|
|
a54a8a13a2 | ||
|
|
57ee1adcff | ||
|
|
0fd9f12687 | ||
|
|
1530837021 | ||
|
|
ea2f4abccd | ||
|
|
cb188e6bb8 | ||
|
|
80cbe0a744 | ||
|
|
10633f33eb | ||
|
|
c27cc438c6 | ||
|
|
0fc8670f94 | ||
|
|
f5fadd6aff | ||
|
|
d8d4d2eacd | ||
|
|
1ae6aee3b1 | ||
|
|
1d151c043c | ||
|
|
b058ed9448 | ||
|
|
27f94556f0 | ||
|
|
6bd4b84e30 | ||
|
|
bfc8f62ea2 | ||
|
|
e08c7d628b | ||
|
|
4a5a411a7b | ||
|
|
793207d5f4 | ||
|
|
de357d7c9d | ||
|
|
32f7a4856b | ||
|
|
40492d4039 | ||
|
|
9a1d8bd7ea | ||
|
|
4ce277d44a | ||
|
|
404017800b | ||
|
|
fd92cf9ba4 | ||
|
|
f08b2a88ec | ||
|
|
632f864466 | ||
|
|
7d35f4cf44 | ||
|
|
c95c7638b8 | ||
|
|
4792364033 | ||
|
|
dca8f0b896 | ||
|
|
54ba20ea7e | ||
|
|
06136b8c58 | ||
|
|
fd39cada5c | ||
|
|
1fafc06500 | ||
|
|
b039209968 | ||
|
|
365fec8a18 |
@@ -1,29 +0,0 @@
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
|
||||
resources:
|
||||
repositories:
|
||||
- repository: release_repo
|
||||
type: github
|
||||
endpoint: ROCm
|
||||
name: ROCm/aomp
|
||||
ref: aomp-dev
|
||||
- repository: llvm-project_repo
|
||||
type: github
|
||||
endpoint: ROCm
|
||||
name: ROCm/llvm-project
|
||||
ref: amd-staging
|
||||
pipelines:
|
||||
- pipeline: rocr-runtime_pipeline
|
||||
source: \ROCR-Runtime
|
||||
trigger: true
|
||||
# this job will only be triggered after successful build sequence of llvm-project and ROCR-Runtime
|
||||
|
||||
trigger: none
|
||||
pr: none
|
||||
|
||||
jobs:
|
||||
- template: ${{ variables.CI_COMPONENT_PATH }}/aomp.yml
|
||||
parameters:
|
||||
checkoutRepo: release_repo
|
||||
@@ -84,8 +84,8 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
|
||||
|
||||
@@ -9,29 +9,20 @@ parameters:
|
||||
type: object
|
||||
default:
|
||||
- software-properties-common
|
||||
- python3-pip
|
||||
- cmake
|
||||
- ninja-build
|
||||
- composablekernel-dev
|
||||
- half
|
||||
- rocrand
|
||||
- rocblas
|
||||
- libsqlite3-dev
|
||||
- libbz2-dev
|
||||
- nlohmann-json3-dev
|
||||
- libgtest-dev
|
||||
- libdrm-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocMLIR
|
||||
- rocRAND
|
||||
- rocBLAS
|
||||
- half
|
||||
- composable_kernel
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- rocprofiler-register
|
||||
- clr
|
||||
- rocminfo
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: MIOpen
|
||||
@@ -39,6 +30,8 @@ jobs:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -77,8 +70,9 @@ jobs:
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DMIOPEN_BACKEND=HIP
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
|
||||
-DMIOPEN_ENABLE_AI_KERNEL_TUNING=OFF
|
||||
-DMIOPEN_ENABLE_AI_IMMED_MODE_FALLBACK=OFF
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
|
||||
@@ -14,6 +14,10 @@ parameters:
|
||||
- wget
|
||||
- unzip
|
||||
- pkg-config
|
||||
- half
|
||||
- rocblas-dev
|
||||
- miopen-hip-dev
|
||||
- migraphx-dev
|
||||
- protobuf-compiler
|
||||
- libprotoc-dev
|
||||
- ffmpeg
|
||||
@@ -21,6 +25,10 @@ parameters:
|
||||
- libavformat-dev
|
||||
- libavutil-dev
|
||||
- libswscale-dev
|
||||
- rpp
|
||||
- rpp-dev
|
||||
- rocdecode
|
||||
- rocdecode-dev
|
||||
- build-essential
|
||||
- libgtk2.0-dev
|
||||
- libavcodec-dev
|
||||
@@ -33,7 +41,6 @@ parameters:
|
||||
- libtiff-dev
|
||||
- libdc1394-dev
|
||||
- libgmp-dev
|
||||
- libopencv-dev
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
@@ -43,21 +50,6 @@ parameters:
|
||||
- google==3.0.0
|
||||
- protobuf==3.12.4
|
||||
- onnx==1.12.0
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- half
|
||||
- rocBLAS
|
||||
- MIOpen
|
||||
- AMDMIGraphX
|
||||
- rpp
|
||||
- rocDecode
|
||||
|
||||
jobs:
|
||||
- job: MIVisionX
|
||||
@@ -66,6 +58,8 @@ jobs:
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -77,23 +71,11 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DROCM_PATH=/opt/rocm
|
||||
-DROCM_DEP_ROCMCORE=ON
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -10,13 +10,6 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- llvm-project
|
||||
- rocminfo
|
||||
- ROCR-Runtime
|
||||
|
||||
jobs:
|
||||
- job: ROCdbgapi
|
||||
@@ -25,6 +18,8 @@ jobs:
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -35,22 +30,9 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -10,33 +10,22 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- rocblas
|
||||
- libyaml-cpp-dev
|
||||
- libpci-dev
|
||||
- libpci3
|
||||
- googletest
|
||||
- git
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- llvm-project
|
||||
- rocBLAS
|
||||
- rocm-cmake
|
||||
- rocm_smi_lib
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- ROCR-Runtime
|
||||
- ROCT-Thunk-Interface
|
||||
|
||||
jobs:
|
||||
- job: ROCmValidationSuite
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: HIP_ROCCLR_HOME
|
||||
value: $(Build.BinariesDirectory)/rocm
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -47,23 +36,11 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCPACK_PACKAGING_INSTALL_PREFIX=$(Build.BinariesDirectory)
|
||||
-DROCM_PATH=/opt/rocm
|
||||
-DCMAKE_PREFIX_PATH=/opt/rocm
|
||||
-DCPACK_PACKAGING_INSTALL_PREFIX='$(Build.BinariesDirectory)'
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -5,9 +5,6 @@ parameters:
|
||||
- name: checkoutRef
|
||||
type: string
|
||||
default: ''
|
||||
- name: offloadEnabled
|
||||
type: boolean
|
||||
default: false
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
@@ -97,18 +94,18 @@ jobs:
|
||||
cmakeBuildDir: $(Build.SourcesDirectory)/llvm-project/openmp/build
|
||||
installDir: $(Build.BinariesDirectory)/llvm
|
||||
# offload does not exist for recent releases, so use CI conditional
|
||||
- ${{ if eq(parameters.offloadEnabled, true) }}:
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
componentName: llvm-offload
|
||||
extraBuildFlags: >-
|
||||
-DOPENMP_ENABLE_LIBOMPTARGET=1
|
||||
-DOPENMP_TEST_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
|
||||
-DOPENMP_TEST_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
|
||||
-DOPENMP_TEST_C_COMPILER==$(Agent.BuildDirectory)/rocm/llvm/bin/clang
|
||||
-DOPENMP_TEST_CXX_COMPILER==$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
|
||||
-DCMAKE_C_COMPILER==$(Agent.BuildDirectory)/rocm/llvm/bin/clang
|
||||
-DCMAKE_CXX_COMPILER==$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
|
||||
-DLIBOMPTARGET_AMDGCN_GFXLIST=gfx700;gfx701;gfx801;gfx803;gfx900;gfx902;gfx906;gfx908;gfx90a;gfx90c;gfx940;gfx941;gfx942;gfx1030;gfx1031;gfx1035;gfx1036;gfx1100;gfx1101;gfx1102;gfx1103
|
||||
-DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm
|
||||
-DLLVM_DIR==$(Agent.BuildDirectory)/rocm/llvm
|
||||
-DLLVM_MAIN_INCLUDE_DIR=$(Build.SourcesDirectory)/llvm-project/llvm/include
|
||||
-DLIBOMPTARGET_LLVM_INCLUDE_DIRS=$(Build.SourcesDirectory)/llvm-project/llvm/include
|
||||
-DCUDA_TOOLKIT_ROOT_DIR=OFF
|
||||
|
||||
@@ -11,16 +11,6 @@ parameters:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- git
|
||||
- python3-pip
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
|
||||
jobs:
|
||||
- job: composable_kernel
|
||||
@@ -28,6 +18,8 @@ jobs:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -38,24 +30,11 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DGPU_TARGETS=gfx1030;gfx1100
|
||||
-GNinja
|
||||
|
||||
@@ -8,17 +8,8 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- python3-pip
|
||||
- cmake
|
||||
- ninja-build
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
|
||||
jobs:
|
||||
- job: half
|
||||
@@ -27,6 +18,8 @@ jobs:
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -37,22 +30,9 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -10,33 +10,25 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- rocblas-dev
|
||||
- rocsparse
|
||||
- rocsolver-dev
|
||||
- gfortran
|
||||
- googletest
|
||||
- git
|
||||
- libgtest-dev
|
||||
- wget
|
||||
- python3-pip
|
||||
- libomp-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- rocBLAS
|
||||
- rocSPARSE
|
||||
- rocSOLVER
|
||||
- aomp
|
||||
|
||||
jobs:
|
||||
- job: hipBLAS
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: LD_LIBRARY_PATH
|
||||
value: '/lib:/usr/lib:/usr/local/lib'
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -59,24 +51,20 @@ jobs:
|
||||
targetType: inline
|
||||
script: sudo apt install --yes ./aocl-linux-aocc-4.1.0_1_amd64.deb
|
||||
workingDirectory: '$(Pipeline.Workspace)'
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- task: Bash@3
|
||||
displayName: 'ldconfig'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: sudo ldconfig
|
||||
workingDirectory: '/usr/local/lib'
|
||||
- script: 'ls -1R /usr/local'
|
||||
displayName: 'Artifact listing'
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_PREFIX_PATH=/opt/rocm
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DHIP_PLATFORM=amd
|
||||
-DBUILD_CLIENTS_TESTS=ON
|
||||
|
||||
@@ -8,44 +8,25 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- python3-venv
|
||||
- libmsgpack-dev
|
||||
- hipblas-dev
|
||||
- git
|
||||
- python3-pip
|
||||
- libdrm-dev
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
- joblib
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- hipBLAS
|
||||
|
||||
jobs:
|
||||
- job: hipBLASLt
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: HIP_ROCCLR_HOME
|
||||
value: $(Build.BinariesDirectory)/rocm
|
||||
- name: TENSILE_ROCM_ASSEMBLER_PATH
|
||||
value: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
- name: CMAKE_CXX_COMPILER
|
||||
value: $(Agent.BuildDirectory)/rocm/bin/hipcc
|
||||
- name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
|
||||
value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
|
||||
- name: TENSILE_ROCM_PATH
|
||||
value: $(Agent.BuildDirectory)/rocm/bin/hipcc
|
||||
- name: PATH
|
||||
value: $(Agent.BuildDirectory)/rocm/llvm/bin:$(Agent.BuildDirectory)/rocm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/snap/bin
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -53,36 +34,21 @@ jobs:
|
||||
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
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- script: sudo ln -s $(Agent.BuildDirectory)/rocm /opt/rocm
|
||||
displayName: ROCm symbolic link
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
|
||||
-DAMDGPU_TARGETS=gfx90a
|
||||
-DTensile_LOGIC=
|
||||
-DTensile_CPU_THREADS=
|
||||
-DTensile_CODE_OBJECT_VERSION=default
|
||||
-DTensile_LIBRARY_FORMAT=msgpack
|
||||
-DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
|
||||
-DCMAKE_PREFIX_PATH="/opt/rocm"
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -10,17 +10,9 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- rocprim
|
||||
- googletest
|
||||
- git
|
||||
- python3-pip
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- llvm-project
|
||||
- rocminfo
|
||||
- rocPRIM
|
||||
- ROCR-Runtime
|
||||
|
||||
jobs:
|
||||
- job: hipCUB
|
||||
@@ -28,6 +20,8 @@ jobs:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -38,24 +32,12 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
|
||||
-DCMAKE_PREFIX_PATH="/opt/rocm"
|
||||
-DBUILD_TEST=ON
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-GNinja
|
||||
|
||||
@@ -10,32 +10,22 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- rocrand
|
||||
- hiprand
|
||||
- rocfft
|
||||
- libboost-program-options-dev
|
||||
- libgtest-dev
|
||||
- googletest
|
||||
- libfftw3-dev
|
||||
- python3-pip
|
||||
- libomp-14-dev
|
||||
# rocm dependencies should match dependencies-rocm.yml
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocRAND
|
||||
- hipRAND
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocFFT
|
||||
- aomp
|
||||
|
||||
jobs:
|
||||
- job: hipFFT
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: HIP_ROCCLR_HOME
|
||||
value: $(Build.BinariesDirectory)/rocm
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -46,31 +36,16 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DUSE_HIP_CLANG=ON
|
||||
-DHIP_COMPILER=clang
|
||||
-DBUILD_CLIENTS_TESTS=ON
|
||||
-DBUILD_CLIENTS_BENCHMARKS=OFF
|
||||
-DBUILD_CLIENTS_BENCH=OFF
|
||||
-DBUILD_CLIENTS_SAMPLES=OFF
|
||||
-L
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -10,23 +10,15 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- rocblas
|
||||
- rocsparse
|
||||
- hipsparse
|
||||
- rocsolver
|
||||
- libsuitesparse-dev
|
||||
- gfortran
|
||||
- git
|
||||
- googletest
|
||||
- libgtest-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- hipSPARSE
|
||||
- llvm-project
|
||||
- rocBLAS
|
||||
- rocm-cmake
|
||||
- rocminfo
|
||||
- ROCR-Runtime
|
||||
- rocSPARSE
|
||||
- rocSOLVER
|
||||
|
||||
jobs:
|
||||
- job: hipSOLVER
|
||||
@@ -35,6 +27,8 @@ jobs:
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -45,18 +39,6 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
# build external gtest and lapack
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
@@ -70,10 +52,10 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Pipeline.Workspace)/deps-install
|
||||
-DCMAKE_PREFIX_PATH="/opt/rocm;$(Pipeline.Workspace)/deps-install"
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DBUILD_CLIENTS_TESTS=ON
|
||||
-DUSE_CUDA=OFF
|
||||
|
||||
@@ -13,18 +13,10 @@ parameters:
|
||||
- libboost-program-options-dev
|
||||
- googletest
|
||||
- libfftw3-dev
|
||||
- rocsparse
|
||||
- git
|
||||
- gfortran
|
||||
- libgtest-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- llvm-project
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- ROCR-Runtime
|
||||
- rocSPARSE
|
||||
|
||||
jobs:
|
||||
- job: hipSPARSE
|
||||
@@ -33,6 +25,8 @@ jobs:
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -43,35 +37,15 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake/
|
||||
-DCMAKE_PREFIX_PATH="/opt/rocm;/opt/rocm/share/rocm/cmake/"
|
||||
-DBUILD_CLIENTS_TESTS=ON
|
||||
-DBUILD_CLIENTS_SAMPLES=OFF
|
||||
-DBUILD_CLIENTS_BENCHMARKS=OFF
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
parameters:
|
||||
artifactName: hipSPARSE
|
||||
publish: false
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
|
||||
parameters:
|
||||
sourceDir: $(Build.SourcesDirectory)/build/clients
|
||||
contentsString: matrices/**
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
parameters:
|
||||
artifactName: testMatrices
|
||||
|
||||
@@ -8,43 +8,25 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- python3-venv
|
||||
- libmsgpack-dev
|
||||
- hipsparse-dev
|
||||
- git
|
||||
- python3-pip
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
- joblib
|
||||
# rocm dependencies should match dependencies-rocm.yml
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- hipSPARSE
|
||||
- rocBLAS
|
||||
|
||||
jobs:
|
||||
- job: hipSPARSELt
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: HIP_ROCCLR_HOME
|
||||
value: $(Build.BinariesDirectory)/rocm
|
||||
- name: TENSILE_ROCM_ASSEMBLER_PATH
|
||||
value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang
|
||||
- name: CMAKE_CXX_COMPILER
|
||||
value: $(Agent.BuildDirectory)/rocm/llvm/bin/hipcc
|
||||
- name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
|
||||
value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
|
||||
- name: PATH
|
||||
value: $(Agent.BuildDirectory)/rocm/llvm/bin:$(Agent.BuildDirectory)/rocm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/snap/bin
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -52,35 +34,21 @@ jobs:
|
||||
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
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
|
||||
-DAMDGPU_TARGETS=all
|
||||
-DTensile_LOGIC=
|
||||
-DTensile_CPU_THREADS=
|
||||
-DTensile_CODE_OBJECT_VERSION=default
|
||||
-DTensile_LIBRARY_FORMAT=msgpack
|
||||
-DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_PREFIX_PATH="/opt/rocm"
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -10,17 +10,12 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- python3-pip
|
||||
- composablekernel-dev
|
||||
- git
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- composable_kernel
|
||||
|
||||
jobs:
|
||||
- job: hipTensor
|
||||
@@ -28,6 +23,8 @@ jobs:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -53,11 +50,12 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/llvm
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
|
||||
-DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm/llvm"
|
||||
-DROCM_PATH="$(Agent.BuildDirectory)/rocm"
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DHIPTENSOR_BUILD_TESTS=ON
|
||||
-DAMDGPU_TARGETS=gfx90a
|
||||
multithreadFlag: -- -j32
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -14,7 +14,6 @@ parameters:
|
||||
- ninja-build
|
||||
- python-is-python3
|
||||
- zlib1g-dev
|
||||
- pkg-config
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
@@ -69,6 +68,8 @@ jobs:
|
||||
-DLIBCXXABI_INSTALL_STATIC_LIBRARY=OFF
|
||||
-DLLVM_BUILD_DOCS=OFF
|
||||
-DLLVM_ENABLE_SPHINX=OFF
|
||||
-DSPHINX_WARNINGS_AS_ERRORS=OFF
|
||||
-DSPHINX_OUTPUT_MAN=OFF
|
||||
-DLLVM_ENABLE_ASSERTIONS=OFF
|
||||
-DLLVM_ENABLE_Z3_SOLVER=OFF
|
||||
-DLLVM_ENABLE_ZLIB=ON
|
||||
@@ -79,6 +80,7 @@ jobs:
|
||||
-DPACKAGE_VENDOR=AMD
|
||||
-DCLANG_LINK_FLANG_LEGACY=ON
|
||||
-DCMAKE_CXX_STANDARD=17
|
||||
-DFLANG_INCLUDE_DOCS=OFF
|
||||
-DROCM_LLVM_BACKWARD_COMPAT_LINK=$(Build.BinariesDirectory)/llvm
|
||||
-DROCM_LLVM_BACKWARD_COMPAT_LINK_TARGET=./lib/llvm
|
||||
-GNinja
|
||||
|
||||
@@ -8,37 +8,21 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- python3-pip
|
||||
- cmake
|
||||
- libboost-program-options-dev
|
||||
- googletest
|
||||
- libfftw3-dev
|
||||
- git
|
||||
- ninja-build
|
||||
- libstdc++-12-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocm_smi_lib
|
||||
- rocprofiler-register
|
||||
- rocm-core
|
||||
- HIPIFY
|
||||
- aomp
|
||||
- aomp-extras
|
||||
|
||||
jobs:
|
||||
- job: rccl
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: HIP_ROCCLR_HOME
|
||||
value: $(Build.BinariesDirectory)/rocm
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -49,29 +33,14 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- script: chmod +x $(Agent.BuildDirectory)/rocm/bin/hipify-perl
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
|
||||
-DHALF_INCLUDE_DIR=$(Agent.BuildDirectory)/rocm/include
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DBUILD_TESTS=ON
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake/
|
||||
-DCMAKE_PREFIX_PATH="/opt/rocm;/opt/rocm/share/rocm/cmake/"
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -8,7 +8,6 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- python3-pip
|
||||
- cmake
|
||||
- ninja-build
|
||||
- git
|
||||
@@ -18,16 +17,6 @@ parameters:
|
||||
- autoconf
|
||||
- libtool
|
||||
- pkg-config
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocm_smi_lib
|
||||
- amdsmi
|
||||
|
||||
jobs:
|
||||
- job: rdc
|
||||
@@ -35,6 +24,8 @@ jobs:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -45,18 +36,6 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
# Build grpc
|
||||
- task: Bash@3
|
||||
displayName: 'git clone grpc'
|
||||
@@ -78,7 +57,6 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DGRPC_ROOT="$(Build.SourcesDirectory)/bin"
|
||||
-DBUILD_TESTS=ON
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -15,29 +15,16 @@ parameters:
|
||||
- git
|
||||
- mpich
|
||||
- ninja-build
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- aomp
|
||||
- clr
|
||||
- llvm-project
|
||||
- rocBLAS
|
||||
- rocminfo
|
||||
- rocPRIM
|
||||
- rocprofiler-register
|
||||
- ROCR-Runtime
|
||||
- rocRAND
|
||||
- rocSPARSE
|
||||
|
||||
jobs:
|
||||
- job: rocALUTION
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: HIP_ROCCLR_HOME
|
||||
value: $(Build.BinariesDirectory)/rocm
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -48,25 +35,13 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake/
|
||||
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/lib/cmake/hip
|
||||
-DCMAKE_PREFIX_PATH="/opt/rocm;/opt/rocm/share/rocm/cmake/"
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DBUILD_CLIENTS_TESTS=ON
|
||||
-DBUILD_CLIENTS_BENCHMARKS=OFF
|
||||
|
||||
@@ -18,40 +18,19 @@ parameters:
|
||||
- googletest
|
||||
- libgtest-dev
|
||||
- wget
|
||||
- python3-pip
|
||||
- libdrm-dev
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
- joblib
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- rocm_smi_lib
|
||||
- rocm-core
|
||||
- aomp
|
||||
- aomp-extras
|
||||
|
||||
jobs:
|
||||
- job: rocBLAS
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: HIP_ROCCLR_HOME
|
||||
value: $(Build.BinariesDirectory)/rocm
|
||||
- name: TENSILE_ROCM_ASSEMBLER_PATH
|
||||
value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang
|
||||
- name: CMAKE_CXX_COMPILER
|
||||
value: $(Agent.BuildDirectory)/rocm/bin/hipcc
|
||||
- name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
|
||||
value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -63,60 +42,23 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- task: Bash@3
|
||||
displayName: 'Download AOCL'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-2/aocl-linux-gcc-4.2.0_1_amd64.deb
|
||||
workingDirectory: '$(Pipeline.Workspace)'
|
||||
- task: Bash@3
|
||||
displayName: 'Install AOCL'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: sudo apt install --yes ./aocl-linux-gcc-4.2.0_1_amd64.deb
|
||||
workingDirectory: '$(Pipeline.Workspace)'
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- task: Bash@3
|
||||
displayName: 'Download AOCL'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-1/aocl-linux-aocc-4.1.0_1_amd64.deb
|
||||
workingDirectory: '$(Pipeline.Workspace)'
|
||||
- task: Bash@3
|
||||
displayName: 'Install AOCL'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: sudo apt install --yes ./aocl-linux-aocc-4.1.0_1_amd64.deb
|
||||
workingDirectory: '$(Pipeline.Workspace)'
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- script: echo $PATH
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_TOOLCHAIN_FILE=toolchain-linux.cmake
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm;$(Pipeline.Workspace)/deps-install
|
||||
-DCMAKE_PREFIX_PATH="/opt/rocm;$(Pipeline.Workspace)/deps-install"
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DTensile_CODE_OBJECT_VERSION=default
|
||||
-DTensile_LOGIC=asm_full
|
||||
-DTensile_SEPARATE_ARCHITECTURES=ON
|
||||
-DTensile_LAZY_LIBRARY_LOADING=ON
|
||||
-DTensile_LIBRARY_FORMAT=msgpack
|
||||
-DTENSILE_VENV_UPGRADE_PIP=ON
|
||||
-DBUILD_CLIENTS_TESTS=ON
|
||||
-DBUILD_CLIENTS_BENCHMARKS=OFF
|
||||
-DBUILD_CLIENTS_SAMPLES=OFF
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -8,7 +8,6 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- python3-pip
|
||||
- cmake
|
||||
- ninja-build
|
||||
- pkg-config
|
||||
@@ -19,16 +18,6 @@ parameters:
|
||||
- libstdc++-12-dev
|
||||
- libva-dev
|
||||
- mesa-amdgpu-va-drivers
|
||||
- libdrm-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocm-core
|
||||
|
||||
jobs:
|
||||
- job: rocDecode
|
||||
@@ -37,21 +26,11 @@ jobs:
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
# Since mesa-amdgpu-multimedia-devel is not directly available from apt, register it
|
||||
- task: Bash@3
|
||||
displayName: 'Register ROCm packages'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
sudo mkdir --parents --mode=0755 /etc/apt/keyrings
|
||||
wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/${{ variables.KEYRING_VERSION }}/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${{ variables.KEYRING_VERSION }} jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
|
||||
echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
|
||||
sudo apt update
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
|
||||
parameters:
|
||||
aptPackages: ${{ parameters.aptPackages }}
|
||||
@@ -59,24 +38,10 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-L
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -10,31 +10,20 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- rocrand
|
||||
- hiprand
|
||||
- libboost-program-options-dev
|
||||
- libgtest-dev
|
||||
- libfftw3-dev
|
||||
- python3-pip
|
||||
# rocm dependencies should match dependencies-rocm.yml
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- hipRAND
|
||||
- rocRAND
|
||||
- rocm-cmake
|
||||
- aomp
|
||||
|
||||
jobs:
|
||||
- job: rocFFT
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: HIP_ROCCLR_HOME
|
||||
value: $(Build.BinariesDirectory)/rocm
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -45,24 +34,12 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_PREFIX_PATH=/opt/rocm
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DUSE_HIP_CLANG=ON
|
||||
|
||||
@@ -10,13 +10,6 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- git
|
||||
- python3-pip
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- llvm-project
|
||||
- rocm-cmake
|
||||
|
||||
jobs:
|
||||
- job: rocMLIR
|
||||
@@ -24,6 +17,8 @@ jobs:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -34,25 +29,13 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_PREFIX_PATH=/opt/rocm
|
||||
-DBUILD_FAT_LIBROCKCOMPILER=1
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -12,15 +12,6 @@ parameters:
|
||||
- ninja-build
|
||||
- libgtest-dev
|
||||
- git
|
||||
- python3-pip
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
|
||||
jobs:
|
||||
- job: rocPRIM
|
||||
@@ -28,6 +19,8 @@ jobs:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -41,24 +34,12 @@ jobs:
|
||||
# ${{ }} are resolved during compile-time
|
||||
# so this next step is skipped completely until
|
||||
# we define explicit aptPackages needed to install
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DBUILD_BENCHMARK=ON
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DBUILD_TEST=ON
|
||||
-GNinja
|
||||
|
||||
@@ -10,25 +10,15 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- rocblas
|
||||
- rocsparse
|
||||
- hipsparse
|
||||
- libsuitesparse-dev
|
||||
- gfortran
|
||||
- libfmt-dev
|
||||
- git
|
||||
- googletest
|
||||
- libgtest-dev
|
||||
- python3-pip
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocBLAS
|
||||
- rocPRIM
|
||||
- rocSPARSE
|
||||
- hipSPARSE
|
||||
|
||||
jobs:
|
||||
- job: rocSOLVER
|
||||
@@ -36,6 +26,8 @@ jobs:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -52,18 +44,6 @@ jobs:
|
||||
targetType: inline
|
||||
script: git clone --depth 1 --branch v3.9.1 https://github.com/Reference-LAPACK/lapack
|
||||
workingDirectory: '$(Build.SourcesDirectory)'
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
componentName: lapack
|
||||
@@ -79,10 +59,11 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Pipeline.Workspace)/deps-install
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_PREFIX_PATH="/opt/rocm;$(Pipeline.Workspace)/deps-install"
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DUSE_CUDA=OFF
|
||||
-DBUILD_CLIENTS_TESTS=ON
|
||||
-DBUILD_CLIENTS_BENCHMARKS=OFF
|
||||
-DBUILD_CLIENTS_SAMPLES=OFF
|
||||
|
||||
@@ -8,7 +8,6 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- python3-pip
|
||||
- cmake
|
||||
- ninja-build
|
||||
- libboost-program-options-dev
|
||||
@@ -16,28 +15,17 @@ parameters:
|
||||
- libfftw3-dev
|
||||
- git
|
||||
- gfortran
|
||||
- rocprim-dev
|
||||
- libgtest-dev
|
||||
- libdrm-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocBLAS
|
||||
- rocminfo
|
||||
- rocPRIM
|
||||
- rocprofiler-register
|
||||
|
||||
jobs:
|
||||
- job: rocSPARSE
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: HIP_ROCCLR_HOME
|
||||
value: $(Build.BinariesDirectory)/rocm
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -48,40 +36,16 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/hipcc
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/bin/hipcc
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DBUILD_CLIENTS_SAMPLES=OFF
|
||||
-DBUILD_CLIENTS_TESTS=ON
|
||||
-DBUILD_CLIENTS_BENCHMARKS=OFF
|
||||
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip;$(Agent.BuildDirectory)/rocm/hip/cmake
|
||||
-DCMAKE_MODULE_PATH="/opt/rocm/lib/cmake/hip;/opt/rocm/hip/cmake"
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
parameters:
|
||||
artifactName: rocSPARSE
|
||||
publish: false
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
|
||||
parameters:
|
||||
sourceDir: $(Build.SourcesDirectory)/build/clients
|
||||
contentsString: matrices/**
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
parameters:
|
||||
artifactName: testMatrices
|
||||
|
||||
@@ -10,20 +10,12 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- hiprand
|
||||
- rocprim-dev
|
||||
- libboost-program-options-dev
|
||||
- googletest
|
||||
- libfftw3-dev
|
||||
- git
|
||||
- python3-pip
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- hipRAND
|
||||
- llvm-project
|
||||
- rocminfo
|
||||
- rocPRIM
|
||||
- ROCR-Runtime
|
||||
|
||||
jobs:
|
||||
- job: rocThrust
|
||||
@@ -31,6 +23,8 @@ jobs:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -41,25 +35,14 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-GNinja
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
|
||||
-DROCM_PATH=/opt/rocm
|
||||
-DCMAKE_PREFIX_PATH=/opt/rocm
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-DBUILD_TEST=ON
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -8,7 +8,6 @@ parameters:
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- python3-pip
|
||||
- cmake
|
||||
- ninja-build
|
||||
- libboost-program-options-dev
|
||||
@@ -16,18 +15,7 @@ parameters:
|
||||
- googletest
|
||||
- libfftw3-dev
|
||||
- git
|
||||
- libomp-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- llvm-project
|
||||
- ROCR-Runtime
|
||||
- clr
|
||||
- rocminfo
|
||||
- rocBLAS
|
||||
- aomp
|
||||
- rocm_smi_lib
|
||||
- rocblas
|
||||
|
||||
jobs:
|
||||
- job: rocWMMA
|
||||
@@ -35,6 +23,8 @@ jobs:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -45,23 +35,11 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DROCWMMA_BUILD_TESTS=ON
|
||||
-DROCWMMA_BUILD_SAMPLES=OFF
|
||||
|
||||
@@ -5,30 +5,6 @@ parameters:
|
||||
- name: checkoutRef
|
||||
type: string
|
||||
default: ''
|
||||
- name: aptPackages
|
||||
type: object
|
||||
default:
|
||||
- libglfw3-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- AMDMIGraphX
|
||||
- clr
|
||||
- hipBLAS
|
||||
- hipCUB
|
||||
- HIPIFY
|
||||
- hipRAND
|
||||
- hipSOLVER
|
||||
- hipSPARSE
|
||||
- llvm-project
|
||||
- rocBLAS
|
||||
- rocPRIM
|
||||
- rocprofiler-register
|
||||
- ROCR-Runtime
|
||||
- rocRAND
|
||||
- rocSOLVER
|
||||
- rocSPARSE
|
||||
- rocThrust
|
||||
|
||||
jobs:
|
||||
- job: rocm_examples
|
||||
@@ -44,28 +20,5 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
|
||||
parameters:
|
||||
aptPackages: ${{ parameters.aptPackages }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
# https://github.com/ROCm/HIP/issues/2203
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DROCM_ROOT=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_HIP_ARCHITECTURES=gfx1030;gfx1100
|
||||
-DCMAKE_EXE_LINKER_FLAGS=-fgpu-rdc
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -10,33 +10,21 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- ninja-build
|
||||
- python3-pip
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
- CppHeaderParser
|
||||
- argparse
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- llvm-project
|
||||
- rocminfo
|
||||
- rocprofiler-register
|
||||
- ROCR-Runtime
|
||||
- ROCT-Thunk-Interface
|
||||
|
||||
jobs:
|
||||
- job: rocm_bandwidth_test
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: ROCR_INC_DIR
|
||||
value: $(Agent.BuildDirectory)/rocm
|
||||
- name: ROCR_LIB_DIR
|
||||
value: $(Agent.BuildDirectory)/rocm
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -48,23 +36,11 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_BUILD_TYPE=release
|
||||
-DCMAKE_MODULE_PATH=$(Build.SourcesDirectory)/cmake_modules
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/include;$(Agent.BuildDirectory)/rocm/include/hsa
|
||||
-DCMAKE_MODULE_PATH="$(Build.SourcesDirectory)/cmake_modules"
|
||||
-DCMAKE_PREFIX_PATH=/opt/rocm
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -24,5 +24,4 @@ jobs:
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DBUILD_TESTS=ON
|
||||
-DROCM_DEP_ROCMCORE=ON
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -21,17 +21,4 @@ jobs:
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
componentName: rocprofiler-register
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
componentName: rocprofiler-register-tests
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_PREFIX_PATH=$(Build.BinariesDirectory)
|
||||
cmakeBuildDir: 'tests/build'
|
||||
installEnabled: false
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
|
||||
parameters:
|
||||
componentName: rocprofiler-register
|
||||
testDir: 'tests/build'
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -10,13 +10,12 @@ parameters:
|
||||
default:
|
||||
- cmake
|
||||
- libgtest-dev
|
||||
- libdrm-dev
|
||||
- libdw-dev
|
||||
- libsystemd-dev
|
||||
- libelf-dev
|
||||
- libnuma-dev
|
||||
- libpciaccess-dev
|
||||
- python3-pip
|
||||
- rocm-llvm-dev
|
||||
- name: pipModules
|
||||
type: object
|
||||
default:
|
||||
@@ -27,31 +26,15 @@ parameters:
|
||||
- lxml
|
||||
- barectf
|
||||
- pandas
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- clr
|
||||
- llvm-project
|
||||
- ROCdbgapi
|
||||
- rocm-cmake
|
||||
- rocm-core
|
||||
- rocm_smi_lib
|
||||
- rocminfo
|
||||
- ROCR-Runtime
|
||||
- rocprofiler-register
|
||||
- ROCT-Thunk-Interface
|
||||
- roctracer
|
||||
|
||||
jobs:
|
||||
- job: rocprofiler
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
- name: HIP_ROCCLR_HOME
|
||||
value: $(Agent.BuildDirectory)/rocm
|
||||
- name: ROCM_PATH
|
||||
value: $(Agent.BuildDirectory)/rocm
|
||||
pool: ${{ variables.MEDIUM_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -63,46 +46,11 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# Manually download aqlprofile, hard-coded 6.1.0 version
|
||||
- task: Bash@3
|
||||
displayName: 'Download aqlprofile'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: wget -nv https://repo.radeon.com/rocm/misc/aqlprofile/ubuntu-22.04/hsa-amd-aqlprofile_1.0.0.60200.60200-crdnnh.14213~22.04_amd64.deb
|
||||
workingDirectory: '$(Pipeline.Workspace)'
|
||||
- task: Bash@3
|
||||
displayName: 'Extract aqlprofile'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
mkdir hsa-amd-aqlprofile
|
||||
dpkg-deb -R hsa-amd-aqlprofile_1.0.0.60200.60200-crdnnh.14213~22.04_amd64.deb hsa-amd-aqlprofile
|
||||
workingDirectory: '$(Pipeline.Workspace)'
|
||||
- task: Bash@3
|
||||
displayName: 'Move aqlprofile'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
mkdir -p $(Agent.BuildDirectory)/rocm
|
||||
cp -R hsa-amd-aqlprofile/opt/rocm-6.2.0-14213/* $(Agent.BuildDirectory)/rocm
|
||||
workingDirectory: '$(Pipeline.Workspace)'
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_MODULE_PATH=$(Build.SourcesDirectory)/cmake_modules;$(Agent.BuildDirectory)/rocm/lib/cmake;$(Agent.BuildDirectory)/rocm/lib/cmake/hip
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_MODULE_PATH="$(Build.SourcesDirectory)/cmake_modules;/opt/rocm/lib/cmake"
|
||||
-DCMAKE_PREFIX_PATH="/opt/rocm"
|
||||
-DENABLE_LDCONFIG=OFF
|
||||
-DUSE_PROF_API=1
|
||||
-DGPU_TARGETS=gfx1030;gfx1100
|
||||
|
||||
@@ -12,16 +12,6 @@ parameters:
|
||||
- ninja-build
|
||||
- libelf-dev
|
||||
- libdw-dev
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- rocm-cmake
|
||||
- clr
|
||||
- llvm-project
|
||||
- ROCdbgapi
|
||||
- rocminfo
|
||||
- ROCR-Runtime
|
||||
- rocprofiler-register
|
||||
|
||||
jobs:
|
||||
- job: rocr_debug_agent
|
||||
@@ -30,6 +20,8 @@ jobs:
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -40,24 +32,11 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake;$(Agent.BuildDirectory)/rocm/lib/cmake/hip
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DROCM_PATH=/opt/rocm
|
||||
-DCMAKE_MODULE_PATH=/opt/rocm/lib/cmake
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -67,4 +67,10 @@ jobs:
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DGPU_TARGETS=gfx1030;gfx1100
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
# - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
# - task: Bash@3
|
||||
# displayName: 'Tests'
|
||||
# inputs:
|
||||
# targetType: inline
|
||||
# script: ./run.sh
|
||||
# workingDirectory: build
|
||||
|
||||
@@ -9,18 +9,10 @@ parameters:
|
||||
type: object
|
||||
default:
|
||||
- cmake
|
||||
- libomp-dev # needed to pass flag step
|
||||
- ninja-build
|
||||
- clang
|
||||
- name: rocmDependencies
|
||||
type: object
|
||||
default:
|
||||
- aomp # needed to pass build step
|
||||
- clr
|
||||
- half
|
||||
- llvm-project
|
||||
- rocminfo
|
||||
- ROCR-Runtime
|
||||
- libomp-dev
|
||||
|
||||
jobs:
|
||||
- job: rpp
|
||||
@@ -29,6 +21,8 @@ jobs:
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
pool:
|
||||
vmImage: ${{ variables.BASE_BUILD_POOL }}
|
||||
container:
|
||||
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
|
||||
workspace:
|
||||
clean: all
|
||||
steps:
|
||||
@@ -39,27 +33,13 @@ jobs:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
|
||||
parameters:
|
||||
checkoutRepo: ${{ parameters.checkoutRepo }}
|
||||
# CI case: download latest default branch build
|
||||
- ${{ if eq(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: staging
|
||||
# manual build case: triggered by ROCm/ROCm repo
|
||||
- ${{ if ne(parameters.checkoutRef, '') }}:
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
|
||||
parameters:
|
||||
dependencyList: ${{ parameters.rocmDependencies }}
|
||||
dependencySource: tag-builds
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
|
||||
parameters:
|
||||
extraBuildFlags: >-
|
||||
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
|
||||
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
|
||||
-DHALF_INCLUDE_DIRS=$(Agent.BuildDirectory)/rocm/include
|
||||
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
|
||||
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
|
||||
-DCMAKE_BUILD_TYPE=Release
|
||||
-DBUILD_CLIENTS=ON
|
||||
-DAMDGPU_TARGETS=gfx1030;gfx1100
|
||||
-GNinja
|
||||
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
|
||||
|
||||
@@ -23,7 +23,7 @@ trigger: none
|
||||
pr: none
|
||||
|
||||
jobs:
|
||||
- template: ${{ variables.CI_COMPONENT_PATH }}/ROCgdb.yml
|
||||
- template: ${{ variables.CI_COMPONENT_PATH }}/rocgdb.yml
|
||||
parameters:
|
||||
checkoutRepo: release_repo
|
||||
checkoutRef: ${{ parameters.checkoutRef }}
|
||||
@@ -1,29 +0,0 @@
|
||||
variables:
|
||||
- group: common
|
||||
- template: /.azuredevops/variables-global.yml
|
||||
|
||||
parameters:
|
||||
- name: checkoutRef
|
||||
type: string
|
||||
default: refs/tags/$(LATEST_RELEASE_TAG)
|
||||
|
||||
resources:
|
||||
repositories:
|
||||
- repository: pipelines_repo
|
||||
type: github
|
||||
endpoint: ROCm
|
||||
name: ROCm/ROCm
|
||||
- repository: release_repo
|
||||
type: github
|
||||
endpoint: ROCm
|
||||
name: ROCm/rocm-examples
|
||||
ref: ${{ parameters.checkoutRef }}
|
||||
|
||||
trigger: none
|
||||
pr: none
|
||||
|
||||
jobs:
|
||||
- template: ${{ variables.CI_COMPONENT_PATH }}/rocm-examples.yml
|
||||
parameters:
|
||||
checkoutRepo: release_repo
|
||||
checkoutRef: ${{ parameters.checkoutRef }}
|
||||
@@ -12,7 +12,6 @@ parameters:
|
||||
- name: defaultBranchList
|
||||
type: object
|
||||
default:
|
||||
amdsmi: develop
|
||||
aomp: aomp-dev
|
||||
aomp-extras: aomp-dev
|
||||
AMDMIGraphX: develop
|
||||
@@ -21,19 +20,13 @@ parameters:
|
||||
half: master
|
||||
HIP: develop
|
||||
hipBLAS: develop
|
||||
hipCUB: develop
|
||||
hipRAND: develop
|
||||
hipSOLVER: develop
|
||||
hipSPARSE: develop
|
||||
llvm-project: amd-staging
|
||||
MIOpen: develop
|
||||
rdc: develop
|
||||
rocBLAS: develop
|
||||
ROCdbgapi : amd-master
|
||||
rocDecode: develop
|
||||
rocFFT: develop
|
||||
rocm-cmake: develop
|
||||
rocm_smi_lib: develop
|
||||
rocminfo: master
|
||||
rocMLIR: develop
|
||||
rocPRIM: develop
|
||||
@@ -43,8 +36,6 @@ parameters:
|
||||
rocSOLVER: develop
|
||||
rocSPARSE: develop
|
||||
ROCT-Thunk-Interface: master
|
||||
rocThrust: develop
|
||||
roctracer: amd-master
|
||||
rpp: master
|
||||
- name: componentsFailureOkay
|
||||
type: object
|
||||
|
||||
@@ -5,9 +5,6 @@ parameters:
|
||||
- name: extraBuildFlags
|
||||
type: string
|
||||
default: ''
|
||||
- name: multithreadFlag
|
||||
type: string
|
||||
default: ''
|
||||
- name: cmakeBuildDir
|
||||
type: string
|
||||
default: 'build'
|
||||
@@ -20,9 +17,6 @@ parameters:
|
||||
- name: installDir
|
||||
type: string
|
||||
default: '$(Build.BinariesDirectory)'
|
||||
- name: installEnabled
|
||||
type: boolean
|
||||
default: true
|
||||
|
||||
steps:
|
||||
# create workingDirectory if it does not exist and change into it
|
||||
@@ -38,13 +32,12 @@ steps:
|
||||
displayName: '${{parameters.componentName }} Build'
|
||||
inputs:
|
||||
workingDirectory: ${{ parameters.cmakeBuildDir }}
|
||||
cmakeArgs: '--build ${{ parameters.cmakeTargetDir }} ${{ parameters.multithreadFlag }}'
|
||||
cmakeArgs: '--build ${{ parameters.cmakeTargetDir }}'
|
||||
retryCountOnTaskFailure: 10
|
||||
# equivalent to running make $cmakeTarget from $cmakeBuildDir
|
||||
# e.g., make install
|
||||
- ${{ if eq(parameters.installEnabled, true) }}:
|
||||
- task: CMake@1
|
||||
displayName: '${{parameters.componentName }} ${{ parameters.cmakeTarget }}'
|
||||
inputs:
|
||||
workingDirectory: ${{ parameters.cmakeBuildDir }}
|
||||
cmakeArgs: '--build ${{ parameters.cmakeTargetDir }} --target ${{ parameters.cmakeTarget }}'
|
||||
- task: CMake@1
|
||||
displayName: '${{parameters.componentName }} ${{ parameters.cmakeTarget }}'
|
||||
inputs:
|
||||
workingDirectory: ${{ parameters.cmakeBuildDir }}
|
||||
cmakeArgs: '--build ${{ parameters.cmakeTargetDir }} --target ${{ parameters.cmakeTarget }}'
|
||||
|
||||
@@ -1,10 +0,0 @@
|
||||
# replace cmake from apt install with newest version using snap install
|
||||
steps:
|
||||
- task: Bash@3
|
||||
displayName: update cmake
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: |
|
||||
sudo apt purge cmake
|
||||
sudo snap install cmake --classic
|
||||
hash -r
|
||||
@@ -12,31 +12,23 @@ steps:
|
||||
displayName: 'sudo apt-get update'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: sudo apt-get --yes update
|
||||
env:
|
||||
DEBIAN_FRONTEND: noninteractive
|
||||
script: sudo apt-get update
|
||||
- task: Bash@3
|
||||
displayName: 'sudo apt-get upgrade'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: sudo apt-get --yes upgrade
|
||||
env:
|
||||
DEBIAN_FRONTEND: noninteractive
|
||||
script: sudo apt-get update
|
||||
- task: Bash@3
|
||||
displayName: 'sudo apt-get fix'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: sudo apt --yes --fix-broken install
|
||||
env:
|
||||
DEBIAN_FRONTEND: noninteractive
|
||||
- ${{ if gt(length(parameters.aptPackages), 0) }}:
|
||||
- task: Bash@3
|
||||
displayName: 'sudo apt-get install ...'
|
||||
inputs:
|
||||
targetType: inline
|
||||
script: sudo apt-get --yes install ${{ join(' ', parameters.aptPackages) }}
|
||||
env:
|
||||
DEBIAN_FRONTEND: noninteractive
|
||||
- ${{ if gt(length(parameters.pipModules), 0) }}:
|
||||
- task: Bash@3
|
||||
displayName: 'pip install ...'
|
||||
|
||||
@@ -23,7 +23,6 @@ parameters:
|
||||
- name: stagingPipelineIdentifiers
|
||||
type: object
|
||||
default:
|
||||
amdsmi: $(amdsmi-pipeline-id)
|
||||
aomp: $(aomp-pipeline-id)
|
||||
aomp-extras: $(aomp-extras-pipeline-id)
|
||||
AMDMIGraphX: $(amdmigraphx-pipeline-id)
|
||||
@@ -31,21 +30,13 @@ parameters:
|
||||
composable_kernel: $(composable-kernel-pipeline-id)
|
||||
half: $(half-pipeline-id)
|
||||
hipBLAS: $(hipblas-pipeline-id)
|
||||
hipCUB: $(hipcub-pipeline-id)
|
||||
HIPIFY: $(hipify-pipeline-id)
|
||||
hipRAND: $(hiprand-pipeline-id)
|
||||
hipSOLVER: $(hipsolver-pipeline-id)
|
||||
hipSPARSE: $(hipsparse-pipeline-id)
|
||||
llvm-project: $(llvm-project-pipeline-id)
|
||||
MIOpen: $(miopen-pipeline-id)
|
||||
rdc: $(rdc-pipeline-id)
|
||||
rocBLAS: $(rocblas-pipeline-id)
|
||||
ROCdbgapi : $(rocdbgapi-pipeline-id)
|
||||
rocDecode: $(rocdecode-pipeline-id)
|
||||
rocFFT: $(rocfft-pipeline-id)
|
||||
rocFFT: $(rotfft-pipeline-id)
|
||||
rocm-cmake: $(rocm-cmake-pipeline-id)
|
||||
rocm-core: $(rocm-core-pipeline-id)
|
||||
rocm_smi_lib: $(rocm-smi-lib-pipeline-id)
|
||||
rocminfo: $(rocminfo-pipeline-id)
|
||||
rocMLIR: $(rocmlir-pipeline-id)
|
||||
rocPRIM: $(rocprim-pipeline-id)
|
||||
@@ -55,13 +46,10 @@ parameters:
|
||||
rocSOLVER: $(rocsolver-pipeline-id)
|
||||
rocSPARSE: $(rocsparse-pipeline-id)
|
||||
ROCT-Thunk-Interface: $(roct-thunk-interface-pipeline-id)
|
||||
rocThrust: $(rocthrust-pipeline-id)
|
||||
roctracer: $(roctracer-pipeline-id)
|
||||
rpp: $(rpp-pipeline-id)
|
||||
- name: taggedPipelineIdentifiers
|
||||
type: object
|
||||
default:
|
||||
amdsmi: $(amdsmi-tagged-pipeline-id)
|
||||
aomp: $(aomp-tagged-pipeline-id)
|
||||
aomp-extras: $(aomp-extras-tagged-pipeline-id)
|
||||
AMDMIGraphX: $(amdmigraphx-tagged-pipeline-id)
|
||||
@@ -69,21 +57,13 @@ parameters:
|
||||
composable_kernel: $(composable-kernel-tagged-pipeline-id)
|
||||
half: $(half-tagged-pipeline-id)
|
||||
hipBLAS: $(hipblas-tagged-pipeline-id)
|
||||
hipCUB: $(hipcub-tagged-pipeline-id)
|
||||
HIPIFY: $(hipify-tagged-pipeline-id)
|
||||
hipRAND: $(hiprand-tagged-pipeline-id)
|
||||
hipSOLVER: $(hipsolver-tagged-pipeline-id)
|
||||
hipSPARSE: $(hipsparse-tagged-pipeline-id)
|
||||
llvm-project: $(llvm-project-tagged-pipeline-id)
|
||||
MIOpen: $(miopen-tagged-pipeline-id)
|
||||
rdc: $(rdc-tagged-pipeline-id)
|
||||
rocBLAS: $(rocblas-tagged-pipeline-id)
|
||||
ROCdbgapi : $(rocdbgapi-tagged-pipeline-id)
|
||||
rocDecode: $(rocdecode-tagged-pipeline-id)
|
||||
rocFFT: $(rocfft-tagged-pipeline-id)
|
||||
rocFFT: $(rotfft-tagged-pipeline-id)
|
||||
rocm-cmake: $(rocm-cmake-tagged-pipeline-id)
|
||||
rocm-core: $(rocm-core-tagged-pipeline-id)
|
||||
rocm_smi_lib: $(rocm-smi-lib-tagged-pipeline-id)
|
||||
rocminfo: $(rocminfo-tagged-pipeline-id)
|
||||
rocMLIR: $(rocmlir-tagged-pipeline-id)
|
||||
rocPRIM: $(rocprim-tagged-pipeline-id)
|
||||
@@ -93,8 +73,6 @@ parameters:
|
||||
rocSOLVER: $(rocsolver-tagged-pipeline-id)
|
||||
rocSPARSE: $(rocsparse-tagged-pipeline-id)
|
||||
ROCT-Thunk-Interface: $(roct-thunk-interface-tagged-pipeline-id)
|
||||
rocThrust: $(rocthrust-tagged-pipeline-id)
|
||||
roctracer: $(roctracer-tagged-pipeline-id)
|
||||
rpp: $(rpp-tagged-pipeline-id)
|
||||
# set to true if you're calling this template file multiple files in same pipeline
|
||||
# only leave last call false to optimize sequence
|
||||
|
||||
@@ -27,5 +27,3 @@ variables:
|
||||
value: rocm/dev-ubuntu-22.04
|
||||
- name: LATEST_DOCKER_VERSION
|
||||
value: 6.1
|
||||
- name: KEYRING_VERSION
|
||||
value: 6.1
|
||||
|
||||
2
.gitignore
vendored
2
.gitignore
vendored
@@ -16,4 +16,4 @@ _readthedocs/
|
||||
docs/CHANGELOG.md
|
||||
docs/contribute/index.md
|
||||
docs/about/release-notes.md
|
||||
docs/about/changelog.md
|
||||
docs/about/CHANGELOG.md
|
||||
@@ -3,20 +3,19 @@
|
||||
|
||||
version: 2
|
||||
|
||||
sphinx:
|
||||
configuration: docs/conf.py
|
||||
|
||||
formats: [htmlzip]
|
||||
|
||||
python:
|
||||
install:
|
||||
- requirements: docs/sphinx/requirements.txt
|
||||
|
||||
build:
|
||||
os: ubuntu-22.04
|
||||
tools:
|
||||
python: "3.10"
|
||||
apt_packages:
|
||||
- "doxygen"
|
||||
- "gfortran" # For pre-processing fortran sources
|
||||
- "graphviz" # For dot graphs in doxygen
|
||||
|
||||
python:
|
||||
install:
|
||||
- requirements: docs/sphinx/requirements.txt
|
||||
|
||||
sphinx:
|
||||
configuration: docs/conf.py
|
||||
|
||||
formats: []
|
||||
|
||||
@@ -237,7 +237,6 @@ OpenCV
|
||||
OpenFabrics
|
||||
OpenGL
|
||||
OpenMP
|
||||
OpenMPI
|
||||
OpenSSL
|
||||
OpenVX
|
||||
PCI
|
||||
@@ -496,7 +495,6 @@ hipfort
|
||||
hipify
|
||||
hipsolver
|
||||
hipsparse
|
||||
hpc
|
||||
hpp
|
||||
hsa
|
||||
hsakmt
|
||||
@@ -633,7 +631,6 @@ subexpression
|
||||
subfolder
|
||||
subfolders
|
||||
supercomputing
|
||||
td
|
||||
tensorfloat
|
||||
th
|
||||
tokenization
|
||||
@@ -688,4 +685,4 @@ xargs
|
||||
xz
|
||||
yaml
|
||||
ysvmadyb
|
||||
zypper
|
||||
zypper
|
||||
1114
CHANGELOG.md
1114
CHANGELOG.md
File diff suppressed because it is too large
Load Diff
93
README.md
93
README.md
@@ -56,103 +56,12 @@ cd ~/ROCm/
|
||||
|
||||
**Note:** Using this sample code will cause the repo tool to download the open source code associated with the specified ROCm release. Ensure that you have ssh-keys configured on your machine for your GitHub ID prior to the download as explained at [Connecting to GitHub with SSH](https://docs.github.com/en/authentication/connecting-to-github-with-ssh).
|
||||
|
||||
## Building the ROCm source code
|
||||
### Building the ROCm source code
|
||||
|
||||
Each ROCm component repository contains directions for building that component, such as the rocSPARSE documentation [Installation and Building for Linux](https://rocm.docs.amd.com/projects/rocSPARSE/en/latest/install/Linux_Install_Guide.html). Refer to the specific component documentation for instructions on building the repository.
|
||||
|
||||
Each release of the ROCm software supports specific hardware and software configurations. Refer to [System requirements (Linux)](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html) for the current supported hardware and OS.
|
||||
|
||||
## Build ROCm from source
|
||||
|
||||
The Build will use as many processors as it can find to build in parallel. Some of the compiles can consume as much as 10GB of RAM, so make sure you have plenty of Swap Space !
|
||||
|
||||
By default the ROCm build will compile for all supported GPU architectures and will take approximately 500 CPU hours.
|
||||
The Build time will reduce significantly if we limit the GPU Architecture/s against which we need to build by using the environment variable GPU_ARCHS as mentioned below.
|
||||
|
||||
```bash
|
||||
# --------------------------------------
|
||||
# Step1: clone source code
|
||||
# --------------------------------------
|
||||
|
||||
mkdir -p ~/WORKSPACE/ # Or any folder name other than WORKSPACE
|
||||
cd ~/WORKSPACE/
|
||||
export ROCM_VERSION=6.1.0 # or 6.1.1 6.1.2
|
||||
~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.1.x -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
|
||||
~/bin/repo sync
|
||||
|
||||
# --------------------------------------
|
||||
# Step 2: Prepare build environment
|
||||
# --------------------------------------
|
||||
|
||||
# Option 1: Start a docker container
|
||||
# Pulling required base docker images:
|
||||
# Ubuntu20.04 built from ROCm/tools/rocm-build/docker/ubuntu20/Dockerfile
|
||||
docker pull rocm/rocm-build-ubuntu-20.04:6.1
|
||||
# Ubuntu22.04 built from ROCm/tools/rocm-build/docker/ubuntu22/Dockerfile
|
||||
docker pull rocm/rocm-build-ubuntu-22.04:6.1
|
||||
|
||||
# Start docker container and mount the source code folder:
|
||||
docker run -ti \
|
||||
-e ROCM_VERSION=${ROCM_VERSION} \
|
||||
-e CCACHE_DIR=$HOME/.ccache \
|
||||
-e CCACHE_ENABLED=true \
|
||||
-e DOCK_WORK_FOLD=/src \
|
||||
-w /src \
|
||||
-v $PWD:/src \
|
||||
-v /etc/passwd:/etc/passwd \
|
||||
-v /etc/shadow:/etc/shadow \
|
||||
-v ${HOME}/.ccache:${HOME}/.ccache \
|
||||
-u $(id -u):$(id -g) \
|
||||
<replace_with_required_ubuntu_base_docker_image> bash
|
||||
|
||||
# Option 2: Install required packages into the host machine
|
||||
# For ubuntu20.04 system
|
||||
cd ROCm/tools/rocm-build/docker/ubuntu20
|
||||
bash install-prerequisites.sh
|
||||
# For ubuntu22.04 system
|
||||
cd ROCm/tools/rocm-build/docker/ubuntu22
|
||||
bash install-prerequisities.sh
|
||||
|
||||
# --------------------------------------
|
||||
# Step 3: Run build command line
|
||||
# --------------------------------------
|
||||
|
||||
# Select GPU targets before building:
|
||||
# When GPU_ARCHS is not set, default GPU targets supported by ROCm6.1 will be used.
|
||||
# To build against a subset of GFX architectures you can use the below env variable.
|
||||
# Support MI300 (gfx940, gfx941, gfx942).
|
||||
export GPU_ARCHS="gfx942" # Example
|
||||
export GPU_ARCHS="gfx940;gfx941;gfx942" # Example
|
||||
|
||||
# Pick and run build commands in the docker container:
|
||||
# Build rocm-dev packages
|
||||
make -f ROCm/tools/rocm-build/ROCm.mk -j ${NPROC:-$(nproc)} rocm-dev
|
||||
# Build all ROCm packages
|
||||
make -f ROCm/tools/rocm-build/ROCm.mk -j ${NPROC:-$(nproc)} all
|
||||
# list all ROCm components to find required components
|
||||
make -f ROCm/tools/rocm-build/ROCm.mk list_components
|
||||
# Build a single ROCm packages
|
||||
make -f ROCm/tools/rocm-build/ROCm.mk T_rocblas
|
||||
|
||||
# Find built packages in ubuntu20.04:
|
||||
out/ubuntu-20.04/20.04/deb/
|
||||
# Find built packages in ubuntu22.04:
|
||||
out/ubuntu-22.04/22.04/deb/
|
||||
|
||||
# Find built logs in ubuntu20.04:
|
||||
out/ubuntu-20.04/20.04/logs/
|
||||
# Find built logs in ubuntu22.04:
|
||||
out/ubuntu-22.04/22.04/logs/
|
||||
# All logs pertaining to failed components, end with .errrors extension.
|
||||
out/ubuntu-22.04/22.04/logs/rocblas.errors # Example
|
||||
# All logs pertaining to building components, end with .inprogress extension.
|
||||
out/ubuntu-22.04/22.04/logs/rocblas.inprogress # Example
|
||||
# All logs pertaining to passed components, use the component names.
|
||||
out/ubuntu-22.04/22.04/logs/rocblas # Example
|
||||
```
|
||||
|
||||
Note: [Overview for ROCm.mk](tools/rocm-build/README.md)
|
||||
|
||||
## ROCm documentation
|
||||
|
||||
This repository contains the [manifest file](https://gerrit.googlesource.com/git-repo/+/HEAD/docs/manifest-format.md)
|
||||
|
||||
210
RELEASE.md
210
RELEASE.md
@@ -1,6 +1,4 @@
|
||||
# ROCm 6.1.2 release notes
|
||||
<!-- Do not edit this file! This file is autogenerated with -->
|
||||
<!-- tools/autotag/tag_script.py -->
|
||||
# ROCm 6.1.1 release notes
|
||||
|
||||
<!-- Disable lints since this is an auto-generated file. -->
|
||||
<!-- markdownlint-disable blanks-around-headers -->
|
||||
@@ -11,137 +9,155 @@
|
||||
|
||||
<!-- spellcheck-disable -->
|
||||
|
||||
ROCm 6.1.2 includes enhancements to SMI tools and improvements to some libraries.
|
||||
ROCm™ 6.1.1 introduces minor fixes and improvements to some tools and libraries.
|
||||
|
||||
### OS support
|
||||
## OS support
|
||||
|
||||
ROCm 6.1.2 has been tested against a pre-release version of Ubuntu 22.04.5 (kernel: 5.15 [GA], 6.8 [HWE]).
|
||||
* ROCm 6.1.1 now supports Oracle Linux. It has been tested against version 8.9 (kernel 5.15.0-205) with AMD Instinct MI300X accelerators.
|
||||
|
||||
### AMD SMI
|
||||
* ROCm 6.1.1 has been tested against a pre-release version of Ubuntu 22.04.5 (kernel: 5.15 [GA], 6.8 [HWE]).
|
||||
|
||||
AMD SMI for ROCm 6.1.2
|
||||
## AMD SMI
|
||||
|
||||
#### Additions
|
||||
AMD SMI for ROCm 6.1.1
|
||||
|
||||
* Added process isolation and clean shader APIs and CLI commands.
|
||||
* `amdsmi_get_gpu_process_isolation()`
|
||||
* `amdsmi_set_gpu_process_isolation()`
|
||||
* `amdsmi_set_gpu_clear_sram_data()`
|
||||
* Added the `MIN_POWER` metric to output provided by `amd-smi static --limit`.
|
||||
### Additions
|
||||
|
||||
#### Optimizations
|
||||
- Added deferred error correctable counts to `amd-smi metric -ecc -ecc-blocks`.
|
||||
|
||||
* Updated the `amd-smi monitor --pcie` output to prevent delays with the `monitor` command.
|
||||
### Changes
|
||||
|
||||
#### Changes
|
||||
- Updated the output of `amd-smi metric --ecc-blocks` to show counters available from blocks.
|
||||
- Updated the output of `amd-smi metric --clock` to reflect each engine.
|
||||
- Updated the output of `amd-smi topology --json` to align with output reported by host and guest systems.
|
||||
|
||||
* Updated `amismi_get_power_cap_info` to return values in uW instead of W.
|
||||
* Updated Python library return types for `amdsmi_get_gpu_memory_reserved_pages` and `amdsmi_get_gpu_bad_page_info`.
|
||||
* Updated the output of `amd-smi metric --ecc-blocks` to show counters available from blocks.
|
||||
### Fixes
|
||||
|
||||
#### Fixes
|
||||
- Fixed `amd-smi metric --clock`'s clock lock and deep sleep status.
|
||||
- Fixed an issue that would cause an error when resetting non-AMD GPUs.
|
||||
- Fixed `amd-smi metric --pcie` and `amdsmi_get_pcie_info()` when using RDNA3 (Navi 32 and Navi 31) hardware to prevent "UNKNOWN" reports.
|
||||
- Fixed the output results of `amd-smi process` when getting processes running on a device.
|
||||
|
||||
* `amdsmi_get_gpu_board_info()` no longer returns junk character strings.
|
||||
* `amd-smi metric --power` now correctly details power output for RDNA3, RDNA2, and MI1x devices.
|
||||
* Fixed the `amdsmitstReadWrite.TestPowerCapReadWrite` test for RDNA3, RDNA2, and MI100 devices.
|
||||
* Fixed an issue with the `amdsmi_get_gpu_memory_reserved_pages` and `amdsmi_get_gpu_bad_page_info` Python interface calls.
|
||||
### Removals
|
||||
|
||||
#### Removals
|
||||
- Removed the `amdsmi_get_gpu_process_info` API from the Python library. It was removed from the C library in an earlier release.
|
||||
|
||||
* Removed the `amdsmi_get_gpu_process_info` API from the Python library. It was removed from the C library in an earlier release.
|
||||
### Known issues
|
||||
|
||||
- `amd-smi bad-pages` can result in a `ValueError: Null pointer access` error when using some PMU firmware versions.
|
||||
|
||||
```{note}
|
||||
See the AMD SMI [detailed changelog](https://github.com/ROCm/amdsmi/blob/rocm-6.1.x/CHANGELOG.md) with code samples for more information.
|
||||
See the [detailed changelog](https://github.com/ROCm/amdsmi/blob/docs/6.1.1/CHANGELOG.md) with code samples for more information.
|
||||
```
|
||||
|
||||
### ROCm SMI
|
||||
## HIPCC
|
||||
|
||||
ROCm SMI for ROCm 6.1.2
|
||||
HIPCC for ROCm 6.1.1
|
||||
|
||||
### Changes
|
||||
|
||||
- **Upcoming:** a future release will enable use of compiled binaries `hipcc.bin` and `hipconfig.bin` by default. No action is needed by users. You can continue calling high-level Perl scripts `hipcc` and `hipconfig`. `hipcc.bin` and `hipconfig.bin` will be invoked by the high-level Perl scripts. To revert to the previous behavior and invoke `hipcc.pl` and `hipconfig.pl`, set the `HIP_USE_PERL_SCRIPTS` environment variable to `1`.
|
||||
- **Upcoming:** a subsequent release will remove high-level Perl scripts `hipcc` and `hipconfig`. This release will remove the `HIP_USE_PERL_SCRIPTS` environment variable. It will rename `hipcc.bin` and `hipconfig.bin` to `hipcc` and `hipconfig` respectively. No action is needed by the users. To revert to the previous behavior, invoke `hipcc.pl` and `hipconfig.pl` explicitly.
|
||||
- **Upcoming:** a subsequent release will remove `hipcc.pl` and `hipconfig.pl`.
|
||||
|
||||
## ROCm SMI
|
||||
|
||||
ROCm SMI for ROCm 6.1.1
|
||||
|
||||
### Additions
|
||||
|
||||
* Added the capability to unlock mutex when a process is dead. Added related debug output.
|
||||
* Added the `Partition ID` field to the `rocm-smi` CLI.
|
||||
* Added `NODE`, `GUID`, and `GFX Version` fields to the CLI.
|
||||
* Documentation now includes C++ and Python tutorials, API guides, and reference material.
|
||||
|
||||
### Changes
|
||||
|
||||
* Some `rocm-smi` fields now display `N/A` instead of `unknown/unsupported` for consistency.
|
||||
* Changed stacked ID formatting in the `rocm-smi` CLI to make it easier to spot identifiers.
|
||||
|
||||
### Fixes
|
||||
|
||||
* Fixed HIP and ROCm SMI mismatch on GPU bus assignments.
|
||||
* Fixed memory leaks caused by not closing directories and creating maps nodes instead of using `.at()`.
|
||||
* Fixed initializing calls which reuse `rocmsmi.initializeRsmi()` bindings in the `rocmsmi` Python API.
|
||||
* Fixed an issue causing `rsmi_dev_activity_metric_get` gfx/memory to not update with GPU activity.
|
||||
|
||||
### Known issues
|
||||
|
||||
- ROCm SMI reports GPU utilization incorrectly for RDNA3 GPUs in some situations. See the issue on [GitHub](https://github.com/ROCm/ROCm/issues/3112).
|
||||
|
||||
```{note}
|
||||
See the [detailed ROCm SMI changelog](https://github.com/ROCm/rocm_smi_lib/blob/docs/6.1.1/CHANGELOG.md) with code samples for more information.
|
||||
```
|
||||
|
||||
## Library changes in ROCm 6.1.1
|
||||
|
||||
| Library | Version |
|
||||
| ----------- | -------------------------------------------------------------------------- |
|
||||
| AMDMIGraphX | [2.9](https://github.com/ROCm/AMDMIGraphX/releases/tag/rocm-6.1.1) |
|
||||
| hipBLAS | [2.1.0](https://github.com/ROCm/hipBLAS/releases/tag/rocm-6.1.1) |
|
||||
| hipBLASLt | [0.7.0](https://github.com/ROCm/hipBLASLt/releases/tag/rocm-6.1.1) |
|
||||
| hipCUB | [3.1.0](https://github.com/ROCm/hipCUB/releases/tag/rocm-6.1.1) |
|
||||
| hipFFT | [1.0.14](https://github.com/ROCm/hipFFT/releases/tag/rocm-6.1.1) |
|
||||
| hipRAND | [2.10.17](https://github.com/ROCm/hipRAND/releases/tag/rocm-6.1.1) |
|
||||
| hipSOLVER | 2.1.0 ⇒ [2.1.1](https://github.com/ROCm/hipSOLVER/releases/tag/rocm-6.1.1) |
|
||||
| hipSPARSE | [3.0.1](https://github.com/ROCm/hipSPARSE/releases/tag/rocm-6.1.1) |
|
||||
| hipSPARSELt | [0.2.0](https://github.com/ROCm/hipSPARSELt/releases/tag/rocm-6.1.1) |
|
||||
| hipTensor | [1.2.0](https://github.com/ROCm/hipTensor/releases/tag/rocm-6.1.1) |
|
||||
| MIOpen | [3.1.0](https://github.com/ROCm/MIOpen/releases/tag/rocm-6.1.1) |
|
||||
| MIVisionX | [2.5.0](https://github.com/ROCm/MIVisionX/releases/tag/rocm-6.1.1) |
|
||||
| rccl | [2.18.6](https://github.com/ROCm/rccl/releases/tag/rocm-6.1.1) |
|
||||
| rocALUTION | [3.1.1](https://github.com/ROCm/rocALUTION/releases/tag/rocm-6.1.1) |
|
||||
| rocBLAS | [4.1.0](https://github.com/ROCm/rocBLAS/releases/tag/rocm-6.1.1) |
|
||||
| rocDecode | [0.5.0](https://github.com/ROCm/rocDecode/releases/tag/rocm-6.1.1) |
|
||||
| rocFFT | 1.0.26 ⇒ [1.0.27](https://github.com/ROCm/rocFFT/releases/tag/rocm-6.1.1) |
|
||||
| rocm-cmake | [0.12.0](https://github.com/ROCm/rocm-cmake/releases/tag/rocm-6.1.1) |
|
||||
| rocPRIM | [3.1.0](https://github.com/ROCm/rocPRIM/releases/tag/rocm-6.1.1) |
|
||||
| rocRAND | [3.0.1](https://github.com/ROCm/rocRAND/releases/tag/rocm-6.1.1) |
|
||||
| rocSOLVER | [3.25.0](https://github.com/ROCm/rocSOLVER/releases/tag/rocm-6.1.1) |
|
||||
| rocSPARSE | [3.1.2](https://github.com/ROCm/rocSPARSE/releases/tag/rocm-6.1.1) |
|
||||
| rocThrust | [3.0.1](https://github.com/ROCm/rocThrust/releases/tag/rocm-6.1.1) |
|
||||
| rocWMMA | [1.4.0](https://github.com/ROCm/rocWMMA/releases/tag/rocm-6.1.1) |
|
||||
| rpp | [1.5.0](https://github.com/ROCm/rpp/releases/tag/rocm-6.1.1) |
|
||||
| Tensile | [4.40.0](https://github.com/ROCm/Tensile/releases/tag/rocm-6.1.1) |
|
||||
|
||||
### hipBLASLt 0.7.0
|
||||
|
||||
hipBLASLt 0.7.0 for ROCm 6.1.1
|
||||
|
||||
#### Additions
|
||||
|
||||
* Added the ring hang event to the `amdsmi_evt_notification_type_t` enum.
|
||||
- Added `hipblasltExtSoftmax` extension API.
|
||||
- Added `hipblasltExtLayerNorm` extension API.
|
||||
- Added `hipblasltExtAMax` extension API.
|
||||
- Added `GemmTuning` extension parameter to set split-k by user.
|
||||
- Added support for mixed precision datatype: fp16/fp8 in with fp16 outk.
|
||||
|
||||
#### Fixes
|
||||
#### Deprecations
|
||||
|
||||
* Fixed an issue causing ROCm SMI to incorrectly report GPU utilization for RDNA3 GPUs. See the issue on [GitHub](https://github.com/ROCm/ROCm/issues/3112).
|
||||
* Fixed the parsing of `pp_od_clk_voltage` in `get_od_clk_volt_info` to work better with MI-series hardware.
|
||||
- **Upcoming**: `algoGetHeuristic()` ext API for GroupGemm will be deprecated in a future release of hipBLASLt.
|
||||
|
||||
## Library changes in ROCm 6.1.2
|
||||
### hipSOLVER 2.1.1
|
||||
|
||||
| Library | Version |
|
||||
|---------|---------|
|
||||
| AMDMIGraphX | [2.9](https://github.com/ROCm/AMDMIGraphX/releases/tag/rocm-6.1.2) |
|
||||
| composable_kernel | [0.2.0](https://github.com/ROCm/composable_kernel/releases/tag/rocm-6.1.2) |
|
||||
| hipBLAS | [2.1.0](https://github.com/ROCm/hipBLAS/releases/tag/rocm-6.1.2) |
|
||||
| hipBLASLt | [0.7.0](https://github.com/ROCm/hipBLASLt/releases/tag/rocm-6.1.2) |
|
||||
| hipCUB | [3.1.0](https://github.com/ROCm/hipCUB/releases/tag/rocm-6.1.2) |
|
||||
| hipFFT | [1.0.14](https://github.com/ROCm/hipFFT/releases/tag/rocm-6.1.2) |
|
||||
| hipRAND | [2.10.17](https://github.com/ROCm/hipRAND/releases/tag/rocm-6.1.2) |
|
||||
| hipSOLVER | [2.1.1](https://github.com/ROCm/hipSOLVER/releases/tag/rocm-6.1.2) |
|
||||
| hipSPARSE | [3.0.1](https://github.com/ROCm/hipSPARSE/releases/tag/rocm-6.1.2) |
|
||||
| hipSPARSELt | [0.2.0](https://github.com/ROCm/hipSPARSELt/releases/tag/rocm-6.1.2) |
|
||||
| hipTensor | [1.2.0](https://github.com/ROCm/hipTensor/releases/tag/rocm-6.1.2) |
|
||||
| MIOpen | [3.1.0](https://github.com/ROCm/MIOpen/releases/tag/rocm-6.1.2) |
|
||||
| MIVisionX | [2.5.0](https://github.com/ROCm/MIVisionX/releases/tag/rocm-6.1.2) |
|
||||
| rccl | [2.18.6](https://github.com/ROCm/rccl/releases/tag/rocm-6.1.2) |
|
||||
| rocALUTION | [3.1.1](https://github.com/ROCm/rocALUTION/releases/tag/rocm-6.1.2) |
|
||||
| rocBLAS | 4.1.0 ⇒ [4.1.2](https://github.com/ROCm/rocBLAS/releases/tag/rocm-6.1.2) |
|
||||
| rocDecode | 0.5.0 ⇒ [0.6.0](https://github.com/ROCm/rocDecode/releases/tag/rocm-6.1.2) |
|
||||
| rocFFT | [1.0.27](https://github.com/ROCm/rocFFT/releases/tag/rocm-6.1.2) |
|
||||
| rocm-cmake | [0.12.0](https://github.com/ROCm/rocm-cmake/releases/tag/rocm-6.1.2) |
|
||||
| rocPRIM | [3.1.0](https://github.com/ROCm/rocPRIM/releases/tag/rocm-6.1.2) |
|
||||
| rocRAND | [3.0.1](https://github.com/ROCm/rocRAND/releases/tag/rocm-6.1.2) |
|
||||
| rocSOLVER | [3.25.0](https://github.com/ROCm/rocSOLVER/releases/tag/rocm-6.1.2) |
|
||||
| rocSPARSE | [3.1.2](https://github.com/ROCm/rocSPARSE/releases/tag/rocm-6.1.2) |
|
||||
| rocThrust | [3.0.1](https://github.com/ROCm/rocThrust/releases/tag/rocm-6.1.2) |
|
||||
| rocWMMA | [1.4.0](https://github.com/ROCm/rocWMMA/releases/tag/rocm-6.1.2) |
|
||||
| rpp | [1.5.0](https://github.com/ROCm/rpp/releases/tag/rocm-6.1.2) |
|
||||
| Tensile | [4.40.0](https://github.com/ROCm/Tensile/releases/tag/rocm-6.1.2) |
|
||||
|
||||
### RCCL
|
||||
|
||||
RCCL 2.18.6 for ROCm 6.1.2
|
||||
hipSOLVER 2.1.1 for ROCm 6.1.1
|
||||
|
||||
#### Changes
|
||||
|
||||
* Reduced `NCCL_TOPO_MAX_NODES` to limit stack usage and avoid stack overflow.
|
||||
|
||||
### rocBLAS
|
||||
|
||||
rocBLAS 4.1.2 for ROCm 6.1.2
|
||||
|
||||
#### Optimizations
|
||||
|
||||
* Tuned BBS TN and TT operations on the CDNA3 architecture.
|
||||
- By default, `BUILD_WITH_SPARSE` is now set to OFF on Microsoft Windows.
|
||||
|
||||
#### Fixes
|
||||
|
||||
* Fixed an issue related to obtaining solutions for BF16 TT operations.
|
||||
- Fixed benchmark client build when `BUILD_WITH_SPARSE` is OFF.
|
||||
|
||||
### rocDecode
|
||||
### rocFFT 1.0.27
|
||||
|
||||
rocDecode 0.6.0 for ROCm 6.1.2
|
||||
rocFFT 1.0.27 for ROCm 6.1.1
|
||||
|
||||
#### Additions
|
||||
|
||||
* Added support for FFmpeg v5.x.
|
||||
|
||||
#### Optimizations
|
||||
|
||||
* Updated error checking in the `rocDecode-setup.py` script.
|
||||
|
||||
#### Changes
|
||||
|
||||
* Updated core dependencies.
|
||||
* Updated to support the use of public LibVA headers.
|
||||
- Enable multi-GPU testing on systems without direct GPU-interconnects.
|
||||
|
||||
#### Fixes
|
||||
|
||||
* Fixed some package dependencies.
|
||||
|
||||
## Upcoming changes
|
||||
|
||||
* A future release will enable the use of HIPCC compiled binaries `hipcc.bin` and `hipconfig.bin` by default. No action is needed by users; you may continue calling high-level Perl scripts `hipcc` and `hipconfig`. `hipcc.bin` and `hipconfig.bin` will be invoked by the high-level Perl scripts. To revert to the previous behavior and invoke `hipcc.pl` and `hipconfig.pl`, set the `HIP_USE_PERL_SCRIPTS` environment variable to `1`.
|
||||
* A subsequent release will remove high-level HIPCC Perl scripts from `hipcc` and `hipconfig`. This release will remove the `HIP_USE_PERL_SCRIPTS` environment variable. It will rename `hipcc.bin` and `hipconfig.bin` to `hipcc` and `hipconfig` respectively. No action is needed by the users. To revert to the previous behavior, invoke `hipcc.pl` and `hipconfig.pl` explicitly.
|
||||
* A subsequent release will remove `hipcc.pl` and `hipconfig.pl` for HIPCC.
|
||||
- Fixed kernel launch failure on execute of very large odd-length real-complex transforms.
|
||||
|
||||
@@ -1,11 +1,12 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<manifest>
|
||||
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
|
||||
<default revision="refs/tags/rocm-6.1.2"
|
||||
<default revision="refs/tags/rocm-6.1.1"
|
||||
remote="rocm-org"
|
||||
sync-c="true"
|
||||
sync-j="4" />
|
||||
<!--list of projects for ROCm-->
|
||||
<project path="ROCm-OpenCL-Runtime/api/opencl/khronos/icd" name="OpenCL-ICD-Loader" remote="KhronosGroup" />
|
||||
<project name="ROCK-Kernel-Driver" />
|
||||
<project name="ROCR-Runtime" />
|
||||
<project name="ROCT-Thunk-Interface" />
|
||||
|
||||
@@ -77,7 +77,8 @@ Obtain the value of `gpu-arch` by running the following command:
|
||||
|
||||
[//]: # (dated link below, needs updating)
|
||||
|
||||
See the complete list of [compiler command-line references](https://github.com/ROCm/llvm-project/blob/amd-staging/openmp/docs/CommandLineArgumentReference.rst).
|
||||
See the complete list of compiler command-line references
|
||||
[here](https://github.com/ROCm/llvm-project/blob/amd-stg-open/clang/docs/CommandGuide/clang.rst).
|
||||
|
||||
### Using `rocprof` with OpenMP
|
||||
|
||||
|
||||
@@ -12,119 +12,117 @@ Use this matrix to view the ROCm compatibility across successive major and minor
|
||||
.. container:: format-big-table
|
||||
|
||||
.. csv-table::
|
||||
:header: "ROCm Version", "6.1.2", "6.1.0", "6.0.0"
|
||||
:header: "ROCm Version", "6.1.0", "6.0.0"
|
||||
:stub-columns: 1
|
||||
|
||||
:doc:`Operating Systems <rocm-install-on-linux:reference/system-requirements>`, "Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3"
|
||||
,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
|
||||
,"RHEL 9.4 [#red-hat94_612]_, 9.3, 9.2","RHEL 9.4 [#red-hat94]_, 9.3, 9.2","RHEL 9.3, 9.2"
|
||||
,"RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
|
||||
,"SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
|
||||
,CentOS 7.9,CentOS 7.9,CentOS 7.9
|
||||
,"Oracle Linux 8.9 [#oracle89]_","Oracle Linux 8.9 [#oracle89]_"
|
||||
,,,
|
||||
:doc:`GFX Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3
|
||||
,CDNA2,CDNA2,CDNA2
|
||||
,CDNA,CDNA,CDNA
|
||||
,RDNA3,RDNA3,RDNA3
|
||||
,RDNA2,RDNA2,RDNA2
|
||||
,,,
|
||||
:doc:`GFX Card <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100,gfx1100
|
||||
,gfx1030,gfx1030,gfx1030
|
||||
,gfx942 [#mi300_612]_,gfx942 [#mi300_610]_, gfx942 [#mi300_600]_
|
||||
,gfx90a,gfx90a,gfx90a
|
||||
,gfx908,gfx908,gfx908
|
||||
,,,
|
||||
ECOSYSTEM SUPPORT:,,,
|
||||
:doc:`PyTorch <rocm-install-on-linux:how-to/3rd-party/pytorch-install>`,"2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
|
||||
:doc:`TensorFlow <rocm-install-on-linux:how-to/3rd-party/tensorflow-install>`,"2.15, 2.14, 2.13","2.15, 2.14, 2.13","2.14, 2.13, 2.12"
|
||||
:doc:`JAX <rocm-install-on-linux:how-to/3rd-party/jax-install>`,0.4.26,0.4.26,0.4.26
|
||||
`ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.17.3,1.14.1
|
||||
,,,
|
||||
3RD PARTY COMMUNICATION LIBS:,,,
|
||||
`UCC <https://github.com/ROCm/ucc>`_,>=1.2.0,>=1.2.0,>=1.2.0
|
||||
`UCX <https://github.com/ROCm/ucx>`_,>=1.14.1,>=1.14.1,>=1.14.1
|
||||
,,,
|
||||
3RD PARTY ALGORITHM LIBS:,,,
|
||||
Thrust,2.1.0,2.1.0,2.0.1
|
||||
CUB,2.1.0,2.1.0,2.0.1
|
||||
,,,
|
||||
ML & COMPUTER VISION LIBS:,,,
|
||||
:doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0
|
||||
:doc:`MIGraphX <amdmigraphx:index>`,2.9.0,2.9.0,2.8.0
|
||||
:doc:`MIOpen <miopen:index>`,3.1.0,3.1.0,3.0.0
|
||||
:doc:`MIVisionX <mivisionx:index>`,2.5.0,2.5.0,2.5.0
|
||||
:doc:`rocDecode <rocdecode:index>`,0.5.0,0.5.0,N/A
|
||||
:doc:`ROCm Performance Primitives (RPP) <rpp:index>`,1.5.0,1.5.0,1.4.0
|
||||
,,,
|
||||
COMMUNICATION:,,,
|
||||
:doc:`RCCL <rccl:index>`,2.18.6,2.18.6,2.18.3
|
||||
,,,
|
||||
MATH LIBS:,,,
|
||||
`half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0
|
||||
:doc:`hipBLAS <hipblas:index>`,2.1.0,2.1.0,2.0.0
|
||||
:doc:`hipBLASLt <hipblaslt:index>`,0.7.0,0.7.0,0.6.0
|
||||
:doc:`hipFFT <hipfft:index>`,1.0.14,1.0.14,1.0.13
|
||||
:doc:`hipFORT <hipfort:index>`,0.4.0,0.4.0,0.4.0
|
||||
:doc:`hipRAND <hiprand:index>`,2.10.16,2.10.16,2.10.16
|
||||
:doc:`hipSOLVER <hipsolver:index>`,2.1.0,2.1.0,2.0.0
|
||||
:doc:`hipSPARSE <hipsparse:index>`,3.0.1,3.0.1,3.0.0
|
||||
:doc:`hipSPARSELt <hipsparselt:index>`,0.1.0,0.1.0,0.1.0
|
||||
:doc:`rocALUTION <rocalution:index>`,3.1.1,3.1.1,3.0.3
|
||||
:doc:`rocBLAS <rocblas:index>`,4.1.0,4.1.0,4.0.0
|
||||
:doc:`rocFFT <rocfft:index>`,1.0.27,1.0.27,1.0.23
|
||||
:doc:`rocRAND <rocrand:index>`,3.0.1,3.0.1,2.10.17
|
||||
:doc:`rocSOLVER <rocsolver:index>`,3.25.0,3.25.0,3.24.0
|
||||
:doc:`rocSPARSE <rocsparse:index>`,3.1.2,3.1.2,3.0.2
|
||||
:doc:`rocWMMA <rocwmma:index>`,1.4.0,1.4.0,1.3.0
|
||||
`Tensile <https://github.com/ROCm/Tensile>`_,4.40.0,4.40.0,4.39.0
|
||||
,,,
|
||||
PRIMITIVES:,,,
|
||||
:doc:`hipCUB <hipcub:index>`,3.1.0,3.1.0,3.0.0
|
||||
:doc:`hipTensor <hiptensor:index>`,1.2.0,1.2.0,1.1.0
|
||||
:doc:`rocPRIM <rocprim:index>`,3.1.0,3.1.0,3.0.0
|
||||
:doc:`rocThrust <rocthrust:index>`,3.0.1,3.0.1,3.0.0
|
||||
,,,
|
||||
SUPPORT LIBS:,,,
|
||||
`hipother <https://github.com/ROCm/hipother>`_,6.1.40091,6.1.40091,6.0.32830
|
||||
:doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.12.0,0.12.0,0.11.0
|
||||
`rocm-core <https://github.com/ROCm/rocm-core>`_,6.1.0,6.1.0,6.0.0
|
||||
`ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240125.3.30,20240125.3.30,20231016.2.245
|
||||
,,,
|
||||
TOOLS:,,,
|
||||
:doc:`AMD SMI <amdsmi:index>`,24.4.1,24.4.1,23.4.2
|
||||
:doc:`HIPIFY <hipify:index>`,17.0.0,17.0.0,17.0.0
|
||||
:doc:`ROCdbgapi <rocdbgapi:index>`,0.71.0,0.71.0,0.71.0
|
||||
:doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0
|
||||
:doc:`ROCProfiler <rocprofiler:index>`,2.0.60100,2.0.60100,2.0.0
|
||||
`rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.3.0,0.3.0,N/A
|
||||
:doc:`ROCTracer <roctracer:index>`,4.1.60100,4.1.60100,4.1.0
|
||||
:doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0
|
||||
:doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0,0.3.0
|
||||
:doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,14.1.0,14.1.0,13.2.0
|
||||
:doc:`ROCm SMI <rocm_smi_lib:index>`,7.0.0,7.0.0,6.0.0
|
||||
:doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.1.0,rocm-6.1.0,rocm-6.0.0
|
||||
:doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3,2.0.3
|
||||
:doc:`TransferBench <transferbench:index>`,1.48,1.48,1.46
|
||||
,,,
|
||||
COMPILERS:,,,
|
||||
`clang-ocl <https://github.com/ROCm/clang-ocl>`_,0.5.0,0.5.0,0.5.0
|
||||
`Flang <https://github.com/ROCm/flang>`_,17.0.0.24103,17.0.0.24103,17.0.0.23483
|
||||
`llvm-project <https://github.com/ROCm/llvm-project>`_,17.0.0.24103,17.0.0.24103,17.0.0.23483
|
||||
`OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,17.0.0.24103,17.0.0.24103,17.0.0.23483
|
||||
,,,
|
||||
RUNTIMES:,,,
|
||||
:doc:`HIP <hip:index>`,6.1.40091,6.1.40091,6.0.32830
|
||||
`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>`,1.13.0,1.13.0,1.12.0
|
||||
:doc:`Operating Systems <rocm-install-on-linux:reference/system-requirements>`, "Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3"
|
||||
,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
|
||||
,"RHEL 9.4 [#red-hat94]_, 9.3, 9.2","RHEL 9.3, 9.2"
|
||||
,"RHEL 8.9, 8.8","RHEL 8.9, 8.8"
|
||||
,"SLES 15 SP5, SP4","SLES 15 SP5, SP4"
|
||||
,CentOS 7.9,CentOS 7.9
|
||||
,"Oracle Linux 8.9 [#oracle89]_"
|
||||
,,
|
||||
:doc:`GFX Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3
|
||||
,CDNA2,CDNA2
|
||||
,CDNA,CDNA
|
||||
,RDNA3,RDNA3
|
||||
,RDNA2,RDNA2
|
||||
,,
|
||||
:doc:`GFX Card <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100
|
||||
,gfx1030,gfx1030
|
||||
,gfx942 [#]_, gfx942 [#]_
|
||||
,gfx90a,gfx90a
|
||||
,gfx908,gfx908
|
||||
,,
|
||||
ECOSYSTEM SUPPORT:,,
|
||||
:doc:`PyTorch <rocm-install-on-linux:how-to/3rd-party/pytorch-install>`,"2.1, 2.0, 1.13","2.1, 2.0, 1.13"
|
||||
:doc:`TensorFlow <rocm-install-on-linux:how-to/3rd-party/tensorflow-install>`,"2.15, 2.14, 2.13","2.14, 2.13, 2.12"
|
||||
:doc:`JAX <rocm-install-on-linux:how-to/3rd-party/jax-install>`,0.4.26,0.4.26
|
||||
`ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.14.1
|
||||
,,
|
||||
3RD PARTY COMMUNICATION LIBS:,,
|
||||
`UCC <https://github.com/ROCm/ucc>`_,>=1.2.0,>=1.2.0
|
||||
`UCX <https://github.com/ROCm/ucx>`_,>=1.14.1,>=1.14.1
|
||||
,,
|
||||
3RD PARTY ALGORITHM LIBS:,,
|
||||
Thrust,2.1.0,2.0.1
|
||||
CUB,2.1.0,2.0.1
|
||||
,,
|
||||
ML & COMPUTER VISION LIBS:,,
|
||||
:doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0
|
||||
:doc:`MIGraphX <amdmigraphx:index>`,2.9.0,2.8.0
|
||||
:doc:`MIOpen <miopen:index>`,3.1.0,3.0.0
|
||||
:doc:`MIVisionX <mivisionx:index>`,2.5.0,2.5.0
|
||||
:doc:`rocDecode <rocdecode:index>`,0.5.0,N/A
|
||||
:doc:`ROCm Performance Primitives (RPP) <rpp:index>`,1.5.0,1.4.0
|
||||
,,
|
||||
COMMUNICATION:,,
|
||||
:doc:`RCCL <rccl:index>`,2.18.6,2.18.3
|
||||
,,
|
||||
MATH LIBS:,,
|
||||
`half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0
|
||||
:doc:`hipBLAS <hipblas:index>`,2.1.0,2.0.0
|
||||
:doc:`hipBLASLt <hipblaslt:index>`,0.7.0,0.6.0
|
||||
:doc:`hipFFT <hipfft:index>`,1.0.14,1.0.13
|
||||
:doc:`hipFORT <hipfort:index>`,0.4.0,0.4.0
|
||||
:doc:`hipRAND <hiprand:index>`,2.10.16,2.10.16
|
||||
:doc:`hipSOLVER <hipsolver:index>`,2.1.0,2.0.0
|
||||
:doc:`hipSPARSE <hipsparse:index>`,3.0.1,3.0.0
|
||||
:doc:`hipSPARSELt <hipsparselt:index>`,0.1.0,0.1.0
|
||||
:doc:`rocALUTION <rocalution:index>`,3.1.1,3.0.3
|
||||
:doc:`rocBLAS <rocblas:index>`,4.1.0,4.0.0
|
||||
:doc:`rocFFT <rocfft:index>`,1.0.27,1.0.23
|
||||
:doc:`rocRAND <rocrand:index>`,3.0.1,2.10.17
|
||||
:doc:`rocSOLVER <rocsolver:index>`,3.25.0,3.24.0
|
||||
:doc:`rocSPARSE <rocsparse:index>`,3.1.2,3.0.2
|
||||
:doc:`rocWMMA <rocwmma:index>`,1.4.0,1.3.0
|
||||
`Tensile <https://github.com/ROCm/Tensile>`_,4.40.0,4.39.0
|
||||
,,
|
||||
PRIMITIVES:,,
|
||||
:doc:`hipCUB <hipcub:index>`,3.1.0,3.0.0
|
||||
:doc:`hipTensor <hiptensor:index>`,1.2.0,1.1.0
|
||||
:doc:`rocPRIM <rocprim:index>`,3.1.0,3.0.0
|
||||
:doc:`rocThrust <rocthrust:index>`,3.0.1,3.0.0
|
||||
,,
|
||||
SUPPORT LIBS:,,
|
||||
`hipother <https://github.com/ROCm/hipother>`_,6.1.40091,6.0.32830
|
||||
:doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.12.0,0.11.0
|
||||
`rocm-core <https://github.com/ROCm/rocm-core>`_,6.1.0,6.0.0
|
||||
`ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240125.3.30,20231016.2.245
|
||||
,,
|
||||
TOOLS:,,
|
||||
:doc:`AMD SMI <amdsmi:index>`,24.4.1,23.4.2
|
||||
:doc:`HIPIFY <hipify:index>`,17.0.0,17.0.0
|
||||
:doc:`ROCdbgapi <rocdbgapi:index>`,0.71.0,0.71.0
|
||||
:doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0
|
||||
:doc:`ROCProfiler <rocprofiler:index>`,2.0.60100,2.0.0
|
||||
`rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.3.0,N/A
|
||||
:doc:`ROCTracer <roctracer:index>`,4.1.60100,4.1.0
|
||||
:doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0
|
||||
:doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0
|
||||
:doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,14.1.0,13.2.0
|
||||
:doc:`ROCm SMI <rocm_smi_lib:index>`,7.0.0,6.0.0
|
||||
:doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.1.0,rocm-6.0.0
|
||||
:doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3
|
||||
:doc:`TransferBench <transferbench:index>`,1.48,1.46
|
||||
,,
|
||||
COMPILERS:,,
|
||||
`clang-ocl <https://github.com/ROCm/clang-ocl>`_,0.5.0,0.5.0
|
||||
`Flang <https://github.com/ROCm/flang>`_,17.0.0.24103,17.0.0.23483
|
||||
`llvm-project <https://github.com/ROCm/llvm-project>`_,17.0.0.24103,17.0.0.23483
|
||||
`OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,17.0.0.24103,17.0.0.23483
|
||||
,,
|
||||
RUNTIMES:,,
|
||||
:doc:`HIP <hip:index>`,6.1.40091,6.0.32830
|
||||
`OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0
|
||||
:doc:`ROCR-Runtime <rocr-runtime:index>`,1.13.0,1.12.0
|
||||
|
||||
|
||||
.. rubric:: Footnotes
|
||||
|
||||
.. [#red-hat94_612] **For ROCm 6.1** - RHEL 9.4 is supported only on AMD Instinct MI300A.
|
||||
.. [#red-hat94] **For ROCm 6.1** - RHEL 9.4 is supported only on AMD Instinct MI300A.
|
||||
.. [#oracle89] **For ROCm 6.1.1** - Oracle Linux is supported only on AMD Instinct MI300X.
|
||||
.. [#mi300_612] **For ROCm 6.1** - 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_610] **For ROCm 6.1** - 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_600] **For ROCm 6.0** - 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.
|
||||
.. [#] **For ROCm 6.1** - 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.
|
||||
.. [#] **For ROCm 6.0** - 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.
|
||||
|
||||
|
||||
@@ -33,8 +33,8 @@ Units (CU). The MI250 GCD has 104 active CUs. Each compute unit is further
|
||||
subdivided into four SIMD units that process SIMD instructions of 16 data
|
||||
elements per instruction (for the FP64 data type). This enables the CU to
|
||||
process 64 work items (a so-called “wavefront”) at a peak clock frequency of 1.7
|
||||
GHz. Therefore, the theoretical maximum FP64 peak performance per GCD is 45.3
|
||||
TFLOPS for vector instructions. The MI250 compute units also provide specialized
|
||||
GHz. Therefore, the theoretical maximum FP64 peak performance per GCD is 22.6
|
||||
TFLOPS for vector instructions. This equates to 45.3 TFLOPS for vector instructions for both GCDs together. The MI250 compute units also provide specialized
|
||||
execution units (also called matrix cores), which are geared toward executing
|
||||
matrix operations like matrix-matrix multiplications. For FP64, the peak
|
||||
performance of these units amounts to 90.5 TFLOPS.
|
||||
|
||||
@@ -424,4 +424,8 @@ Shadow byte legend (one shadow byte represents 8 application bytes):
|
||||
|
||||
* Lack of detection on the GPU might also be due to the implementation not instrumenting accesses to all GPU specific address spaces. For example, in the current implementation accesses to "private" or "stack" variables on the GPU are not instrumented, and accesses to HIP shared variables (also known as "local data store" or "LDS") are also not instrumented.
|
||||
|
||||
* It can also be the case that a memory fault is hit for an invalid address even with the instrumentation. This is usually caused by the invalid address being so wild that its shadow address is outside any memory region, and the fault actually occurs on the access to the shadow address. It is also possible to hit a memory fault for the `NULL` pointer. While address 0 does have a shadow location, it is not poisoned by the runtime.
|
||||
* It can also be the case that a memory fault is reported for an invalid address even with the instrumentation. This is usually caused by the invalid address being so wild that its shadow address is outside any memory region, and the fault actually occurs on the access to the shadow address. It is also possible to hit a memory fault for the `NULL` pointer. While address 0 does have a shadow location, it is not poisoned by the runtime.
|
||||
|
||||
* There is currently a bug which can result in memory faults being reported when running instrumented device code which makes use of `malloc`, `free`, `new`, or `delete`.
|
||||
|
||||
* There is currently a bug which can result in undefined symbols being reported at compile time when instrumented device code makes use of `new` and `delete`.
|
||||
|
||||
32
docs/conf.py
32
docs/conf.py
@@ -23,7 +23,7 @@ for template in templates:
|
||||
|
||||
shutil.copy2('../RELEASE.md','./about/release-notes.md')
|
||||
# Keep capitalization due to similar linking on GitHub's markdown preview.
|
||||
shutil.copy2('../CHANGELOG.md','./about/changelog.md')
|
||||
shutil.copy2('../CHANGELOG.md','./about/CHANGELOG.md')
|
||||
|
||||
latex_engine = "xelatex"
|
||||
latex_elements = {
|
||||
@@ -38,8 +38,8 @@ latex_elements = {
|
||||
project = "ROCm Documentation"
|
||||
author = "Advanced Micro Devices, Inc."
|
||||
copyright = "Copyright (c) 2024 Advanced Micro Devices, Inc. All rights reserved."
|
||||
version = "6.1.2"
|
||||
release = "6.1.2"
|
||||
version = "6.1.1"
|
||||
release = "6.1.1"
|
||||
setting_all_article_info = True
|
||||
all_article_info_os = ["linux", "windows"]
|
||||
all_article_info_author = ""
|
||||
@@ -49,12 +49,12 @@ article_pages = [
|
||||
{
|
||||
"file":"about/release-notes",
|
||||
"os":["linux", "windows"],
|
||||
"date":"2024-06-04"
|
||||
"date":"2024-05-08"
|
||||
},
|
||||
{
|
||||
"file":"about/changelog",
|
||||
"file":"about/CHANGELOG",
|
||||
"os":["linux", "windows"],
|
||||
"date":"2024-06-04"
|
||||
"date":"2024-05-08"
|
||||
},
|
||||
|
||||
{"file":"install/windows/install-quick", "os":["windows"]},
|
||||
@@ -84,7 +84,25 @@ article_pages = [
|
||||
{"file":"how-to/system-debugging", "os":["linux"]},
|
||||
{"file":"how-to/tuning-guides", "os":["linux", "windows"]},
|
||||
|
||||
{"file":"rocm-a-z", "os":["linux", "windows"]},
|
||||
{"file":"how-to/rocm-for-ai/index", "os":["linux"]},
|
||||
{"file":"how-to/rocm-for-ai/install", "os":["linux"]},
|
||||
{"file":"how-to/rocm-for-ai/train-a-model", "os":["linux"]},
|
||||
{"file":"how-to/rocm-for-ai/deploy-your-model", "os":["linux"]},
|
||||
{"file":"how-to/rocm-for-ai/hugging-face-models", "os":["linux"]},
|
||||
|
||||
{"file":"how-to/rocm-for-hpc/index", "os":["linux"]},
|
||||
|
||||
{"file":"how-to/llm-fine-tuning-optimization/index", "os":["linux"]},
|
||||
{"file":"how-to/llm-fine-tuning-optimization/overview", "os":["linux"]},
|
||||
{"file":"how-to/llm-fine-tuning-optimization/fine-tuning-and-inference", "os":["linux"]},
|
||||
{"file":"how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference", "os":["linux"]},
|
||||
{"file":"how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference", "os":["linux"]},
|
||||
{"file":"how-to/llm-fine-tuning-optimization/llm-inference-frameworks", "os":["linux"]},
|
||||
{"file":"how-to/llm-fine-tuning-optimization/model-acceleration-libraries", "os":["linux"]},
|
||||
{"file":"how-to/llm-fine-tuning-optimization/model-quantization", "os":["linux"]},
|
||||
{"file":"how-to/llm-fine-tuning-optimization/optimizing-with-composable-kernel", "os":["linux"]},
|
||||
{"file":"how-to/llm-fine-tuning-optimization/optimizing-triton-kernel", "os":["linux"]},
|
||||
{"file":"how-to/llm-fine-tuning-optimization/profiling-and-debugging", "os":["linux"]},
|
||||
]
|
||||
|
||||
exclude_patterns = ['temp']
|
||||
|
||||
@@ -12,8 +12,7 @@ There are four standard ways to provide feedback on this repository.
|
||||
|
||||
All contributions to ROCm documentation should arrive via the
|
||||
[GitHub Flow](https://docs.github.com/en/get-started/quickstart/github-flow)
|
||||
targeting the develop branch of the repository. If you are unable to contribute
|
||||
via the GitHub Flow, feel free to email us at [rocm-feedback@amd.com](mailto:rocm-feedback@amd.com?subject=Documentation%20Feedback).
|
||||
targeting the develop branch of the repository.
|
||||
|
||||
For more in-depth information on creating a pull request (PR), see
|
||||
[Contributing](./contributing.md).
|
||||
@@ -30,7 +29,3 @@ and follow along on via public announcements.
|
||||
|
||||
Issues on existing or absent documentation can be filed in
|
||||
[GitHub Issues](https://github.com/ROCm/ROCm/issues).
|
||||
|
||||
## Email
|
||||
|
||||
Send other feedback or questions to [rocm-feedback@amd.com](mailto:rocm-feedback@amd.com?subject=Documentation%20Feedback).
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 187 KiB |
@@ -28,18 +28,9 @@ graphs, tensor parallel multi-GPU, GPTQ, AWQ, and token speculation.
|
||||
Installing vLLM
|
||||
---------------
|
||||
|
||||
1. To install vLLM, run the following commands.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Install from source
|
||||
git clone https://github.com/ROCm/vllm.git
|
||||
cd vllm
|
||||
PYTORCH_ROCM_ARCH=gfx942 python setup.py install #MI300 series
|
||||
|
||||
.. _fine-tuning-llms-vllm-rocm-docker-image:
|
||||
|
||||
2. Run the following commands to build a Docker image ``vllm-rocm``.
|
||||
1. Run the following commands to build a Docker image ``vllm-rocm``.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
@@ -52,7 +43,7 @@ Installing vLLM
|
||||
.. tab-item:: vLLM on a single-accelerator system
|
||||
:sync: single
|
||||
|
||||
3. To use vLLM as an API server to serve reference requests, first start a container using the :ref:`vllm-rocm
|
||||
2. To use vLLM as an API server to serve reference requests, first start a container using the :ref:`vllm-rocm
|
||||
Docker image <fine-tuning-llms-vllm-rocm-docker-image>`.
|
||||
|
||||
.. code-block:: shell
|
||||
@@ -69,7 +60,7 @@ Installing vLLM
|
||||
vllm-rocm \
|
||||
bash
|
||||
|
||||
4. Inside the container, start the API server to run on a single accelerator on port 8000 using the following command.
|
||||
3. Inside the container, start the API server to run on a single accelerator on port 8000 using the following command.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
@@ -81,7 +72,7 @@ Installing vLLM
|
||||
:alt: vLLM API server log message
|
||||
:align: center
|
||||
|
||||
5. To test, send it a curl request containing a prompt.
|
||||
4. To test, send it a curl request containing a prompt.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
@@ -92,11 +83,11 @@ Installing vLLM
|
||||
.. code-block:: text
|
||||
|
||||
{"text":["What is AMD Instinct?\nAmd Instinct is a brand new line of high-performance computing (HPC) processors from Advanced Micro Devices (AMD). These processors are designed to deliver unparalleled performance for HPC workloads, including scientific simulations, data analytics, and machine learning.\nThe Instinct lineup includes a range of processors, from the entry-level Inst"]}
|
||||
|
||||
|
||||
.. tab-item:: vLLM on a multi-accelerator system
|
||||
:sync: multi
|
||||
|
||||
3. To use vLLM as an API server to serve reference requests, first start a container using the :ref:`vllm-rocm
|
||||
2. To use vLLM as an API server to serve reference requests, first start a container using the :ref:`vllm-rocm
|
||||
Docker image <fine-tuning-llms-vllm-rocm-docker-image>`.
|
||||
|
||||
.. code-block:: shell
|
||||
@@ -114,14 +105,14 @@ Installing vLLM
|
||||
bash
|
||||
|
||||
|
||||
4. To run API server on multiple GPUs, use the ``-tp`` or ``--tensor-parallel-size`` parameter. For example, to use two
|
||||
3. To run API server on multiple GPUs, use the ``-tp`` or ``--tensor-parallel-size`` parameter. For example, to use two
|
||||
GPUs, start the API server using the following command.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
python -m vllm.entrypoints.api_server --model /app/model --dtype float16 -tp 2 --port 8000 &
|
||||
|
||||
5. To run multiple instances of API Servers, specify different ports for each server, and use ``ROCR_VISIBLE_DEVICES`` to
|
||||
4. To run multiple instances of API Servers, specify different ports for each server, and use ``ROCR_VISIBLE_DEVICES`` to
|
||||
isolate each instance to a different accelerator.
|
||||
|
||||
For example, to run two API servers, one on port 8000 using GPU 0 and 1, one on port 8001 using GPU 2 and 3, use a
|
||||
@@ -132,7 +123,7 @@ Installing vLLM
|
||||
ROCR_VISIBLE_DEVICES=0,1 python -m vllm.entrypoints.api_server --model /data/llama-2-7b-chat-hf --dtype float16 –tp 2 --port 8000 &
|
||||
ROCR_VISIBLE_DEVICES=2,3 python -m vllm.entrypoints.api_server --model /data/llama-2-7b-chat-hf --dtype float16 –tp 2--port 8001 &
|
||||
|
||||
6. To test, send it a curl request containing a prompt.
|
||||
5. To test, send it a curl request containing a prompt.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
@@ -163,27 +154,29 @@ speculation.
|
||||
Install TGI
|
||||
-----------
|
||||
|
||||
1. To install the TGI Docker image, run the following commands.
|
||||
1. Launch the TGI Docker container in the host machine.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Install from Dockerfile
|
||||
git clone https://github.com/huggingface/text-generation-inference.git -b mi300-compat
|
||||
cd text-generation-inference
|
||||
docker build . -f Dockerfile.rocm
|
||||
docker run --name tgi --rm -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined
|
||||
--device=/dev/kfd --device=/dev/dri --group-add video --ipc=host --shm-size 256g
|
||||
--net host -v $PWD:/data
|
||||
--entrypoint "/bin/bash"
|
||||
--env HUGGINGFACE_HUB_CACHE=/data
|
||||
ghcr.io/huggingface/text-generation-inference:latest-rocm
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: TGI on a single-accelerator system
|
||||
:sync: single
|
||||
|
||||
2. Launch a model using TGI server on a single accelerator.
|
||||
2. Inside the container, launch a model using TGI server on a single accelerator.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
export ROCM_USE_FLASH_ATTN_V2_TRITON=True
|
||||
text-generation-launcher --model-id NousResearch/Meta-Llama-3-70B --dtype float16 --port 8000 &
|
||||
|
||||
|
||||
3. To test, send it a curl request containing a prompt.
|
||||
|
||||
.. code-block:: shell
|
||||
@@ -191,26 +184,26 @@ Install TGI
|
||||
curl http://localhost:8000/generate_stream -X POST -d '{"inputs":"What is AMD Instinct?","parameters":{"max_new_tokens":20}}' -H 'Content-Type: application/json'
|
||||
|
||||
You should receive a response like the following.
|
||||
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
data:{"index":20,"token":{"id":304,"text":" in","logprob":-1.2822266,"special":false},"generated_text":" AMD Instinct is a new family of data center GPUs designed to accelerate the most demanding workloads in","details":null}
|
||||
|
||||
.. tab-item:: TGI on a multi-accelerator system
|
||||
|
||||
2. Launch a model using TGI server on multiple accelerators (4 in this case).
|
||||
2. Inside the container, launch a model using TGI server on multiple accelerators (4 in this case).
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
export ROCM_USE_FLASH_ATTN_V2_TRITON=True
|
||||
text-generation-launcher --model-id NousResearch/Meta-Llama-3-8B --dtype float16 --port 8000 --num-shard 4 &
|
||||
|
||||
|
||||
3. To test, send it a curl request containing a prompt.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
curl http://localhost:8000/generate_stream -X POST -d '{"inputs":"What is AMD Instinct?","parameters":{"max_new_tokens":20}}' -H 'Content-Type: application/json'
|
||||
|
||||
|
||||
You should receive a response like the following.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
@@ -154,13 +154,13 @@ kernels by configuring the ``exllama_config`` parameter as the following.
|
||||
.. code-block:: python
|
||||
|
||||
from transformers import AutoModelForCausalLM, GPTQConfig
|
||||
#pretrained_model_dir = "meta-llama/Llama-2-7b"
|
||||
base_model_name = "NousResearch/Llama-2-7b-hf"
|
||||
gptq_config = GPTQConfig(bits=4, dataset="c4", exllama_config={"version":2})
|
||||
pretrained_model_dir = "meta-llama/Llama-2-7b"
|
||||
gptq_config = GPTQConfig(bits=4, exllama_config={"version":2})
|
||||
quantized_model = AutoModelForCausalLM.from_pretrained(
|
||||
base_model_name,
|
||||
device_map="auto",
|
||||
base_model_name,
|
||||
device_map="auto",
|
||||
quantization_config=gptq_config)
|
||||
|
||||
bitsandbytes
|
||||
============
|
||||
|
||||
|
||||
@@ -343,11 +343,6 @@ or :doc:`rocBLAS <rocblas:index>` is faster for a specific operation.
|
||||
then required to strip out the kernel and create kernel
|
||||
compilation and launch via Triton.
|
||||
|
||||
* For advanced ``matmul`` or ``conv`` configuration tuning, the ``inductor-gemm-tuner`` can
|
||||
help. This implements the Triton ``conv``/``mm`` implementations used upstream
|
||||
and allows specification of inputs and configuration tuning search space if new
|
||||
tunings are found that can be added to the auto-tune list.
|
||||
|
||||
Other guidelines
|
||||
================
|
||||
|
||||
|
||||
0
docs/how-to/mi300x-workload-tuning.rst
Normal file
0
docs/how-to/mi300x-workload-tuning.rst
Normal file
@@ -21,6 +21,3 @@ In this guide, you'll learn about:
|
||||
- :doc:`Running models from Hugging Face <hugging-face-models>`
|
||||
|
||||
- :doc:`Deploying your model <deploy-your-model>`
|
||||
|
||||
To learn about ROCm for HPC applications and scientific computing, see
|
||||
:doc:`../rocm-for-hpc/index`.
|
||||
|
||||
@@ -137,4 +137,4 @@ The following developer blogs showcase examples of how to fine-tune a model on a
|
||||
* Recipes for fine-tuning Llama2 and 3 with ``llama-recipes``
|
||||
|
||||
* `meta-llama/llama-recipes: Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover
|
||||
single/multi-node GPUs <https://github.com/meta-llama/llama-recipes/tree/main/recipes/finetuning>`_
|
||||
single/multi-node GPUs <https://github.com/meta-llama/llama-recipes/tree/main/recipes/quickstart/finetuning>`_
|
||||
|
||||
@@ -1,231 +0,0 @@
|
||||
.. meta::
|
||||
:description: How to use ROCm for HPC
|
||||
:keywords: ROCm, AI, high performance computing, HPC
|
||||
|
||||
******************
|
||||
Using ROCm for HPC
|
||||
******************
|
||||
|
||||
The ROCm open-source software stack is optimized to extract high-performance
|
||||
computing (HPC) workload performance from AMD Instinct™ accelerators
|
||||
while maintaining compatibility with industry software frameworks.
|
||||
|
||||
ROCm enhances support and access for developers by providing streamlined and
|
||||
improved tools that significantly increase productivity. Being open-source, ROCm
|
||||
fosters innovation, differentiation, and collaboration within the developer
|
||||
community, making it a powerful and accessible solution for leveraging the full
|
||||
potential of AMD accelerators' capabilities in diverse computational
|
||||
applications.
|
||||
|
||||
* For more information, see :doc:`What is ROCm? <../../what-is-rocm>`.
|
||||
|
||||
* For guidance on installing ROCm, see :doc:`rocm-install-on-linux:index`. See
|
||||
the :doc:`../../compatibility/compatibility-matrix` for details on hardware
|
||||
and operating system support.
|
||||
|
||||
Some of the most popular HPC frameworks are part of the ROCm platform, including
|
||||
those to help parallelize operations across multiple accelerators and servers,
|
||||
handle memory hierarchies, and solve linear systems.
|
||||
|
||||
.. image:: ../../data/how-to/rocm-for-hpc/hpc-stack-2024_6_20.png
|
||||
:align: center
|
||||
:alt: Software and hardware ecosystem surrounding ROCm and AMD Instinct for HPC
|
||||
|
||||
The following catalog of GPU-accelerated solutions includes a vast set of
|
||||
platform-compatible HPC applications, including those for astrophysics, climate
|
||||
and weather, computational chemistry, computational fluid dynamics, earth
|
||||
science, genomics, geophysics, molecular dynamics, and physics computing.
|
||||
|
||||
Refer to the resources in the following table for instructions on building,
|
||||
running, and deploying these applications on ROCm-capable systems with AMD
|
||||
Instinct accelerators. Each build container provides parameters to specify
|
||||
different source code branches, release versions of ROCm, OpenMPI, UCX, and
|
||||
Ubuntu versions.
|
||||
|
||||
.. _hpc-apps:
|
||||
|
||||
..
|
||||
Reduce font size of HPC app descriptions slightly.
|
||||
|
||||
.. raw:: html
|
||||
|
||||
<style>
|
||||
#hpc-apps-table tr td:last-child {
|
||||
font-size: 0.9rem;
|
||||
}
|
||||
</style>
|
||||
|
||||
.. container::
|
||||
:name: hpc-apps-table
|
||||
|
||||
.. list-table::
|
||||
:header-rows: 1
|
||||
:stub-columns: 1
|
||||
:widths: 2 2 5
|
||||
|
||||
* - Application domain
|
||||
- HPC application
|
||||
- Description
|
||||
|
||||
* - Physics
|
||||
- `Chroma <https://github.com/amd/InfinityHub-CI/tree/main/chroma/>`_
|
||||
- The Chroma package supports data-parallel programming constructs for lattice
|
||||
field theory and in particular lattice QCD. It uses the SciDAC QDP++ data-parallel
|
||||
programming (in C++) that presents a single high-level code image to the user,
|
||||
but can generate highly optimized code for many architectural systems including
|
||||
single node workstations, multi and many-core nodes, clusters of nodes via
|
||||
QMP, and classic vector computers.
|
||||
|
||||
* -
|
||||
- `Grid <https://github.com/amd/InfinityHub-CI/tree/main/grid/>`_
|
||||
- Grid is a library for lattice QCD calculations that employs a high-level data parallel
|
||||
approach while using a number of techniques to target multiple types of parallelism.
|
||||
The library currently supports MPI, OpenMP and short vector parallelism. The SIMD
|
||||
instructions sets covered include SSE, AVX, AVX2, FMA4, IMCI and AVX512. Recent
|
||||
releases expanded this support to include GPU offloading.
|
||||
|
||||
* -
|
||||
- `MILC <https://github.com/amd/InfinityHub-CI/tree/main/milc/>`_
|
||||
- The MILC Code is a set of research codes developed by MIMD Lattice Computation
|
||||
(MILC) collaboration for doing simulations of four dimensional SU(3) lattice gauge
|
||||
theory on MIMD parallel machines scaling from single-processor workstations
|
||||
to HPC systems. The MILC Code is publicly available for research purposes.
|
||||
Publications of work done using this code or derivatives of this code should
|
||||
acknowledge this use.
|
||||
|
||||
* -
|
||||
- `PIConGPU <https://github.com/amd/InfinityHub-CI/tree/main/picongpu>`_
|
||||
- PIConGPU (Particle-in-cell on Graphics Processing Units) is an Open Source
|
||||
simulations framework for plasma and laser-plasma physics used to develop
|
||||
advanced particle accelerators for radiation therapy of cancer, high energy
|
||||
physics and photon science.
|
||||
|
||||
* - Astrophysics
|
||||
- `Cholla <https://github.com/amd/InfinityHub-CI/tree/main/cholla/>`_
|
||||
- An astrophysical simulation code developed for the extreme environments
|
||||
encountered in astrophysical systems.
|
||||
|
||||
* - Geophysics
|
||||
- `SPECFEM3D Cartesian <https://github.com/amd/InfinityHub-CI/tree/main/specfem3d>`_
|
||||
- SPECFEM3D Cartesian simulates acoustic (fluid), elastic (solid), coupled
|
||||
acoustic/elastic, poroelastic or seismic wave propagation in any type of
|
||||
conforming mesh of hexahedra (structured or not.) It can, for instance,
|
||||
model seismic waves propagating in sedimentary basins or any other
|
||||
regional geological model following earthquakes. It can also be used
|
||||
for non-destructive testing or for ocean acoustics.
|
||||
|
||||
* - Molecular dynamics
|
||||
- `GROMACS with HIP (AMD implementation) <https://github.com/amd/InfinityHub-CI/tree/main/gromacs>`_
|
||||
- GROMACS is a versatile package to perform molecular dynamics, i.e.
|
||||
simulate the Newtonian equations of motion for systems with hundreds
|
||||
to millions of particles. This AMD container is based on a released
|
||||
version of GROMACS modified by AMD. This container only supports up
|
||||
to a 8 GPU configuration
|
||||
|
||||
* -
|
||||
- `LAMMPS <https://github.com/amd/InfinityHub-CI/tree/main/lammps>`_
|
||||
- LAMMPS is a classical molecular dynamics code with a focus on materials
|
||||
modeling. It's an acronym for Large-scale Atomic/Molecular Massively
|
||||
Parallel Simulator.
|
||||
|
||||
* - Computational fluid dynamics
|
||||
- `NEKO <https://github.com/amd/InfinityHub-CI/tree/main/neko>`_
|
||||
- Neko is a portable framework for high-order spectral element flow simulations.
|
||||
Written in modern Fortran, Neko adopts an object-oriented approach, allowing
|
||||
multi-tier abstractions of the solver stack and facilitating various hardware
|
||||
backends ranging from general-purpose processors, CUDA and HIP enabled
|
||||
accelerators to SX-Aurora vector processors.
|
||||
|
||||
* -
|
||||
- `nekRS <https://github.com/amd/InfinityHub-CI/tree/main/nekrs>`_
|
||||
- nekRS is an open-source Navier Stokes solver based on the spectral element
|
||||
method targeting classical processors and accelerators like GPUs.
|
||||
|
||||
* - Computational chemistry
|
||||
- `QUDA <https://github.com/amd/InfinityHub-CI/tree/main/quda>`_
|
||||
- Library designed for efficient lattice QCD computations on
|
||||
accelerators. It includes optimized Dirac operators and a variety of
|
||||
fermion solvers and conjugate gradient (CG) implementations, enhancing
|
||||
performance and accuracy in lattice QCD simulations.
|
||||
|
||||
* - Electronic structure
|
||||
- `CP2K <https://github.com/amd/InfinityHub-CI/tree/main/cp2k>`_
|
||||
- CP2K is a quantum chemistry and solid state physics software package that can
|
||||
perform atomistic simulations of solid state, liquid, molecular, periodic, material,
|
||||
crystal, and biological systems. This AMD container, based on a released version
|
||||
of CP2K, is an AMD beta version with ongoing optimizations.
|
||||
|
||||
* - Quantum Monte Carlo Simulation
|
||||
- `QMCPACK <https://github.com/amd/InfinityHub-CI/tree/main/qmcpack>`_
|
||||
- QMCPACK is an open-source production-level many-body ab initio Quantum
|
||||
Monte Carlo code for computing the electronic structure of atoms, molecules, 2D
|
||||
nanomaterials and solids. The solid-state capabilities include metallic systems
|
||||
as well as insulators. QMCPACK is expected to run well on workstations through
|
||||
to the latest generation supercomputers. Besides high performance, particular
|
||||
emphasis is placed on code quality and reproducibility.
|
||||
|
||||
* - Climate and weather
|
||||
- `MPAS <https://github.com/amd/InfinityHub-CI/tree/main/mpas>`_
|
||||
- The Model for Prediction Across Scales (MPAS) is a collaborative project for
|
||||
developing atmosphere, ocean, and other earth-system simulation components
|
||||
for use in climate, regional climate, and weather studies.
|
||||
|
||||
* - Benchmark
|
||||
- `rocHPL <https://github.com/amd/InfinityHub-CI/tree/main/rochpl>`_
|
||||
- HPL, or High-Performance Linpack, is a benchmark which solves a uniformly
|
||||
random system of linear equations and reports floating-point execution rate.
|
||||
This documentation supports the implementation of the HPL benchmark on
|
||||
top of AMD's ROCm platform.
|
||||
|
||||
* -
|
||||
- `rocHPL-MxP <https://github.com/amd/InfinityHub-CI/tree/main/hpl-mxp>`_
|
||||
- Benchmark that highlights the convergence of HPC and AI workloads by
|
||||
solving a system of linear equations using novel, mixed-precision
|
||||
algorithms.
|
||||
|
||||
* -
|
||||
- `HPCG <https://github.com/amd/InfinityHub-CI/tree/main/hpcg>`_
|
||||
- HPCG, or the High Performance Conjugate Gradient Benchmark complements
|
||||
the High Performance LINPACK (HPL) benchmark. The computational and data
|
||||
access patterns of HPCG are designed to closely match a broad set of important
|
||||
applications not represented by HPL, and to incentivize computer system
|
||||
designers to invest in capabilities that will benefit the collective performance
|
||||
of these applications.
|
||||
|
||||
* - Tools and libraries
|
||||
- `ROCm with GPU-aware MPI container <https://github.com/amd/InfinityHub-CI/tree/main/base-gpu-mpi-rocm-docker>`_
|
||||
- Base container for GPU-aware MPI with ROCm for HPC applications. This
|
||||
project provides a boilerplate for building and running a Docker
|
||||
container with ROCm supporting GPU-aware MPI implementations using
|
||||
OpenMPI or UCX.
|
||||
|
||||
* -
|
||||
- `Kokkos <https://github.com/amd/InfinityHub-CI/tree/main/kokkos>`_
|
||||
- Kokkos is a programming model in C++ for writing performance portable
|
||||
applications for use across HPC platforms. It provides abstractions for both
|
||||
parallel execution of code and data management. Kokkos is designed to target
|
||||
complex node architectures with N-level memory hierarchies and multiple types
|
||||
of execution resources.
|
||||
|
||||
* -
|
||||
- `PyFR <https://github.com/amd/InfinityHub-CI/tree/main/pyfr>`_
|
||||
- PyFR is an open-source Python based framework for solving advection-diffusion
|
||||
type problems on streaming architectures using the Flux Reconstruction approach of
|
||||
Huynh. The framework is designed to solve a range of governing systems on mixed
|
||||
unstructured grids containing various element types. It is also designed to target a
|
||||
range of hardware platforms via use of an in-built domain specific language derived
|
||||
from the Mako templating engine.
|
||||
|
||||
* -
|
||||
- `RAJA <https://github.com/amd/InfinityHub-CI/tree/main/raja>`_
|
||||
- RAJA is a library of C++ software abstractions, primarily developed at Lawrence
|
||||
Livermore National Laboratory (LLNL), that enables architecture and programming
|
||||
model portability for HPC applications.
|
||||
|
||||
* -
|
||||
- `Trilinos <https://github.com/amd/InfinityHub-CI/tree/main/trilinos>`_
|
||||
- The Trilinos Project is an effort to develop algorithms and enabling technologies
|
||||
within an object-oriented software framework for the solution of large-scale,
|
||||
complex multi-physics engineering and scientific problems.
|
||||
|
||||
To learn about ROCm for AI applications, see :doc:`../rocm-for-ai/index`.
|
||||
@@ -5,7 +5,7 @@
|
||||
ROCm">
|
||||
</head>
|
||||
|
||||
# System debugging guide
|
||||
# System debugging
|
||||
|
||||
## ROCm language and system-level debug, flags, and environment variables
|
||||
|
||||
|
||||
@@ -1,108 +0,0 @@
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="description" content="AMD hardware optimization for specific workloads">
|
||||
<meta name="keywords" content="high-performance computing, HPC, Instinct accelerators,
|
||||
Radeon, tuning, tuning guide, AMD, ROCm">
|
||||
</head>
|
||||
|
||||
# System optimization
|
||||
|
||||
This guide outlines system setup and tuning suggestions for AMD hardware to optimize performance for specific types of
|
||||
workloads or use-cases.
|
||||
|
||||
## High-performance computing
|
||||
|
||||
High-performance computing (HPC) workloads have unique requirements. The default
|
||||
hardware and BIOS configurations for OEM platforms may not provide optimal
|
||||
performance for HPC workloads. To enable optimal HPC settings on a per-platform
|
||||
and per-workload level, this guide calls out:
|
||||
|
||||
* BIOS settings that can impact performance
|
||||
* Hardware configuration best practices
|
||||
* Supported versions of operating systems
|
||||
* Workload-specific recommendations for optimal BIOS and operating system
|
||||
settings
|
||||
|
||||
There is also a discussion on the AMD Instinct™ software development
|
||||
environment, including information on how to install and run the DGEMM, STREAM,
|
||||
HPCG, and HPL benchmarks. This guidance provides a good starting point but is
|
||||
not exhaustively tested across all compilers.
|
||||
|
||||
Prerequisites to understanding this document and to performing tuning of HPC
|
||||
applications include:
|
||||
|
||||
* Experience in configuring servers
|
||||
* Administrative access to the server's Management Interface (BMC)
|
||||
* Administrative access to the operating system
|
||||
* Familiarity with the OEM server's BMC (strongly recommended)
|
||||
* Familiarity with the OS specific tools for configuration, monitoring, and
|
||||
troubleshooting (strongly recommended)
|
||||
|
||||
This document provides guidance on tuning systems with various AMD Instinct™
|
||||
accelerators for HPC workloads. This document is not an all-inclusive guide, and
|
||||
some items referred to may have similar, but different, names in various OEM
|
||||
systems (for example, OEM-specific BIOS settings). This document also provides
|
||||
suggestions on items that should be the initial focus of additional,
|
||||
application-specific tuning.
|
||||
|
||||
This document is based on the AMD EPYC™ 7003-series processor family (former
|
||||
codename "Milan").
|
||||
|
||||
While this guide is a good starting point, developers are encouraged to perform
|
||||
their own performance testing for additional tuning.
|
||||
|
||||
:::::{grid} 1 1 2 2
|
||||
:gutter: 1
|
||||
|
||||
:::{grid-item-card}
|
||||
**[AMD Instinct™ MI200](./tuning-guides/mi200)**
|
||||
|
||||
This chapter goes through how to configure your AMD Instinct™ MI200 accelerated
|
||||
compute nodes to get the best performance out of them.
|
||||
|
||||
* [Instruction Set Architecture (ISA)](https://www.amd.com/system/files/TechDocs/instinct-mi200-cdna2-instruction-set-architecture.pdf)
|
||||
* [White paper](https://www.amd.com/system/files/documents/amd-cdna2-white-paper.pdf)
|
||||
|
||||
:::
|
||||
|
||||
:::{grid-item-card}
|
||||
**[AMD Instinct™ MI100](./tuning-guides/mi100)**
|
||||
|
||||
This chapter briefly reviews hardware aspects of the AMD Instinct™ MI100
|
||||
accelerators and the CDNA™ 1 architecture that is the foundation of these GPUs.
|
||||
|
||||
* [ISA](https://www.amd.com/system/files/TechDocs/instinct-mi100-cdna1-shader-instruction-set-architecture%C2%A0.pdf)
|
||||
* [White paper](https://www.amd.com/system/files/documents/amd-cdna-whitepaper.pdf)
|
||||
|
||||
:::
|
||||
|
||||
:::::
|
||||
|
||||
## Workstation
|
||||
|
||||
Workstation workloads, much like high-performance computing, have a unique set of
|
||||
requirements, a blend of both graphics and compute, certification, stability and
|
||||
the list continues.
|
||||
|
||||
The document covers specific software requirements and processes needed to use
|
||||
these GPUs for Single Root I/O Virtualization (SR-IOV) and machine learning
|
||||
(ML).
|
||||
|
||||
The main purpose of this document is to help users utilize the RDNA 2 GPUs to
|
||||
their full potential.
|
||||
|
||||
:::::{grid} 1 1 2 2
|
||||
:gutter: 1
|
||||
|
||||
:::{grid-item-card}
|
||||
**[AMD Radeon™ PRO W6000 and V620](./tuning-guides/w6000-v620)**
|
||||
|
||||
This chapter describes the AMD GPUs with RDNA™ 2 architecture, namely AMD Radeon
|
||||
PRO W6800 and AMD Radeon PRO V620
|
||||
|
||||
* [AMD RDNA2 ISA](https://www.amd.com/system/files/TechDocs/rdna2-shader-instruction-set-architecture.pdf)
|
||||
* [White paper](https://www.amd.com/system/files/documents/rdna2-explained-radeon-pro-W6000.pdf)
|
||||
|
||||
:::
|
||||
|
||||
:::::
|
||||
107
docs/how-to/tuning-guides.rst
Normal file
107
docs/how-to/tuning-guides.rst
Normal file
@@ -0,0 +1,107 @@
|
||||
.. meta::
|
||||
:description: AMD hardware optimization for specific workloads
|
||||
:keywords: high-performance computing, HPC, Instinct accelerators, Radeon,
|
||||
AMD, ROCm, system, EPYC, CPU, GPU, BIOS, OS
|
||||
|
||||
*******************
|
||||
System optimization
|
||||
*******************
|
||||
|
||||
System administrators can optimize the performance of their AMD hardware
|
||||
generally and based on specific workloads and use cases. This section outlines
|
||||
recommended system optimization options for AMD accelerators and GPUs, enabling
|
||||
administrators to maximize efficiency and performance.
|
||||
|
||||
High-performance computing workloads
|
||||
====================================
|
||||
|
||||
High-performance computing (HPC) workloads have unique requirements that may not
|
||||
be fully met by the default hardware and BIOS configurations of OEM platforms.
|
||||
To achieve optimal performance for HPC workloads, it is crucial to adjust
|
||||
settings at both the platform and workload levels.
|
||||
|
||||
The :ref:`AMD Instinct™ accelerator optimization guides <mi-optimization-guides>`
|
||||
in this section describe:
|
||||
|
||||
* BIOS settings that can impact performance
|
||||
* Hardware configuration best practices
|
||||
* Supported versions of operating systems
|
||||
* Workload-specific recommendations for optimal BIOS and operating system
|
||||
settings
|
||||
|
||||
The guides might also discuss the AMD Instinct software development
|
||||
environment, including information on how to install and run the DGEMM, STREAM,
|
||||
HPCG, and HPL benchmarks. The guides provide a good starting point but is
|
||||
not tested exhaustively across all compilers.
|
||||
|
||||
Knowledge prerequisites to better understand the following
|
||||
:ref:`Instinct system optimization guides <mi-optimization-guides>` and to
|
||||
perform tuning for HPC applications include:
|
||||
|
||||
* Experience in configuring servers
|
||||
* Administrative access to the server's Management Interface (BMC)
|
||||
* Administrative access to the operating system
|
||||
* Familiarity with the OEM server's BMC (strongly recommended)
|
||||
* Familiarity with the OS specific tools for configuration, monitoring, and
|
||||
troubleshooting (strongly recommended)
|
||||
|
||||
While the following guides are a good starting point, developers are encouraged
|
||||
to perform their own performance testing for additional tuning per device and
|
||||
per workload.
|
||||
|
||||
.. _mi-optimization-guides:
|
||||
|
||||
.. list-table::
|
||||
:header-rows: 1
|
||||
:stub-columns: 1
|
||||
|
||||
* - Optimization guide
|
||||
|
||||
- Architecture reference
|
||||
|
||||
- White papers
|
||||
|
||||
* - :doc:`AMD Instinct MI200 <tuning-guides/mi200>`
|
||||
|
||||
- `AMD Instinct MI200 instruction set architecture <https://www.amd.com/system/files/TechDocs/instinct-mi200-cdna2-instruction-set-architecture.pdf>`_
|
||||
|
||||
- `CDNA 2 architecture <https://www.amd.com/system/files/documents/amd-cdna2-white-paper.pdf>`_
|
||||
|
||||
* - :doc:`AMD Instinct MI100 <tuning-guides/mi100>`
|
||||
|
||||
- `AMD Instinct MI100 instruction set architecture <https://www.amd.com/system/files/TechDocs/instinct-mi100-cdna1-shader-instruction-set-architecture%C2%A0.pdf>`_
|
||||
|
||||
- `CDNA architecture <https://www.amd.com/system/files/documents/amd-cdna-whitepaper.pdf>`_
|
||||
|
||||
Workstation workloads
|
||||
=====================
|
||||
|
||||
Workstation workloads, much like those for HPC, have a unique set of
|
||||
requirements: a blend of both graphics and compute, certification, stability and
|
||||
others.
|
||||
|
||||
The document covers specific software requirements and processes needed to use
|
||||
these GPUs for Single Root I/O Virtualization (SR-IOV) and machine learning
|
||||
tasks.
|
||||
|
||||
The main purpose of this document is to help users utilize the RDNA™ 2 GPUs to
|
||||
their full potential.
|
||||
|
||||
.. _rdna-optimization-guides:
|
||||
|
||||
.. list-table::
|
||||
:header-rows: 1
|
||||
:stub-columns: 1
|
||||
|
||||
* - Optimization guide
|
||||
|
||||
- Architecture reference
|
||||
|
||||
- White papers
|
||||
|
||||
* - :doc:`AMD Radeon PRO W6000 and V620 <tuning-guides/w6000-v620>`
|
||||
|
||||
- `AMD RDNA 2 instruction set architecture <https://www.amd.com/system/files/TechDocs/rdna2-shader-instruction-set-architecture.pdf>`_
|
||||
|
||||
- `RDNA 2 architecture <https://www.amd.com/system/files/documents/rdna2-explained-radeon-pro-W6000.pdf>`_
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="description" content="MI100 high-performance computing and tuning guide">
|
||||
<meta name="keywords" content="MI100, high-performance computing, HPC, tuning, BIOS
|
||||
<meta name="keywords" content="MI100, high-performance computing, HPC, BIOS
|
||||
settings, NBIO, AMD, ROCm">
|
||||
</head>
|
||||
|
||||
# MI100 high-performance computing and tuning guide
|
||||
# AMD Instinct MI100 system optimization
|
||||
|
||||
## System settings
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="description" content="MI200 high-performance computing and tuning guide">
|
||||
<meta name="keywords" content="MI200, high-performance computing, HPC, tuning, BIOS
|
||||
<meta name="keywords" content="MI200, high-performance computing, HPC, BIOS
|
||||
settings, NBIO, AMD, ROCm">
|
||||
</head>
|
||||
|
||||
# MI200 high-performance computing and tuning guide
|
||||
# AMD Instinct MI200 system optimization
|
||||
|
||||
## System settings
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="description" content="RDNA2 workstation tuning guide">
|
||||
<meta name="keywords" content="RDNA2, workstation tuning, BIOS settings, installation, AMD,
|
||||
<meta name="keywords" content="RDNA2, workstation, BIOS settings, installation, AMD,
|
||||
ROCm">
|
||||
</head>
|
||||
|
||||
# RDNA2 workstation tuning guide
|
||||
# AMD RDNA2 system optimization
|
||||
|
||||
## System settings
|
||||
|
||||
|
||||
@@ -25,7 +25,6 @@ Our documentation is organized into the following categories:
|
||||
:class-container: rocm-doc-grid
|
||||
|
||||
:::{grid-item-card}
|
||||
:class-card: sd-text-black
|
||||
:img-top: ./data/banner-installation.jpg
|
||||
:img-alt: Install documentation
|
||||
:padding: 2
|
||||
@@ -47,7 +46,6 @@ Our documentation is organized into the following categories:
|
||||
:::
|
||||
|
||||
:::{grid-item-card}
|
||||
:class-card: sd-text-black
|
||||
:img-top: ./data/banner-compatibility.jpg
|
||||
:img-alt: Compatibility information
|
||||
:padding: 2
|
||||
@@ -65,7 +63,6 @@ Our documentation is organized into the following categories:
|
||||
|
||||
<!-- markdownlint-disable MD051 -->
|
||||
:::{grid-item-card}
|
||||
:class-card: sd-text-black
|
||||
:img-top: ./data/banner-reference.jpg
|
||||
:img-alt: Reference documentation
|
||||
:padding: 2
|
||||
@@ -86,30 +83,27 @@ Our documentation is organized into the following categories:
|
||||
<!-- markdownlint-enable MD051 -->
|
||||
|
||||
:::{grid-item-card}
|
||||
:class-card: sd-text-black
|
||||
:img-top: ./data/banner-howto.jpg
|
||||
:img-alt: How-to documentation
|
||||
:padding: 2
|
||||
|
||||
* [Using ROCm for AI](./how-to/rocm-for-ai/index.rst)
|
||||
* [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 tuning for various architectures](./how-to/tuning-guides.md)
|
||||
* [MI100](./how-to/tuning-guides/mi100.md)
|
||||
* [MI200](./how-to/tuning-guides/mi200.md)
|
||||
* [RDNA2](./how-to/tuning-guides/w6000-v620.md)
|
||||
* [System optimization](./how-to/tuning-guides.rst)
|
||||
* [AMD Instinct MI200](./how-to/tuning-guides/mi200.md)
|
||||
* [AMD Instinct MI100](./how-to/tuning-guides/mi100.md)
|
||||
* [AMD Instinct RDNA2](./how-to/tuning-guides/w6000-v620.md)
|
||||
* [System level debugging](./how-to/system-debugging.md)
|
||||
* [GPU-enabled MPI](./how-to/gpu-enabled-mpi.rst)
|
||||
* [Using compiler features](./conceptual/compiler-topics.md)
|
||||
* [Using AddressSanitizer](./conceptual/using-gpu-sanitizer.md)
|
||||
* [Compiler disambiguation](./conceptual/compiler-disambiguation.md)
|
||||
* [OpenMP support in ROCm](./about/compatibility/openmp.md)
|
||||
* [Setting the number of CUs](./how-to/setting-cus)
|
||||
* [System level debugging](./how-to/system-debugging.md)
|
||||
* [GitHub examples](https://github.com/amd/rocm-examples)
|
||||
:::
|
||||
|
||||
:::{grid-item-card}
|
||||
:class-card: sd-text-black
|
||||
:img-top: ./data/banner-conceptual.jpg
|
||||
:img-alt: Conceptual documentation
|
||||
:padding: 2
|
||||
|
||||
@@ -233,22 +233,6 @@ The following tables provide an overview of the hardware specifications for AMD
|
||||
- L0 Instruction Cache (KiB)
|
||||
- VGPR File (KiB)
|
||||
- SGPR File (KiB)
|
||||
*
|
||||
- Radeon PRO W7900 Dual Slot
|
||||
- RDNA3
|
||||
- gfx1100
|
||||
- 48
|
||||
- 96
|
||||
- 32
|
||||
- 128
|
||||
- 96
|
||||
- 6
|
||||
- 256
|
||||
- 32
|
||||
- 16
|
||||
- 32
|
||||
- 384
|
||||
- 20
|
||||
*
|
||||
- Radeon PRO W7900
|
||||
- RDNA3
|
||||
|
||||
@@ -53,7 +53,6 @@
|
||||
* {doc}`ROCm Data Center Tool <rdc:index>`
|
||||
* {doc}`ROCm SMI <rocm_smi_lib:index>`
|
||||
* {doc}`ROCm Validation Suite <rocmvalidationsuite:index>`
|
||||
* {doc}`TransferBench <transferbench:index>`
|
||||
:::
|
||||
|
||||
::::
|
||||
|
||||
@@ -8,7 +8,6 @@
|
||||
|
||||
| Version | Release date |
|
||||
| ------- | ------------ |
|
||||
| [6.1.2](https://rocm.docs.amd.com/en/docs-6.1.2/) | June 4, 2024 |
|
||||
| [6.1.1](https://rocm.docs.amd.com/en/docs-6.1.1/) | May 8, 2024 |
|
||||
| [6.1.0](https://rocm.docs.amd.com/en/docs-6.1.0/) | Apr 16, 2024 |
|
||||
| [6.0.2](https://rocm.docs.amd.com/en/docs-6.0.2/) | Jan 31, 2024 |
|
||||
|
||||
@@ -11,7 +11,7 @@ subtrees:
|
||||
title: Release notes
|
||||
subtrees:
|
||||
- entries:
|
||||
- file: about/changelog.md
|
||||
- file: about/CHANGELOG.md
|
||||
title: Changelog
|
||||
- url: https://github.com/ROCm/ROCm/labels/Verified%20Issue
|
||||
title: Known issues
|
||||
@@ -58,8 +58,6 @@ subtrees:
|
||||
- file: how-to/rocm-for-ai/train-a-model.rst
|
||||
- file: how-to/rocm-for-ai/hugging-face-models.rst
|
||||
- file: how-to/rocm-for-ai/deploy-your-model.rst
|
||||
- file: how-to/rocm-for-hpc/index.rst
|
||||
title: Using ROCm for HPC
|
||||
- file: how-to/llm-fine-tuning-optimization/index.rst
|
||||
title: Fine-tuning LLMs and inference optimization
|
||||
subtrees:
|
||||
@@ -81,16 +79,17 @@ subtrees:
|
||||
- file: how-to/llm-fine-tuning-optimization/optimizing-triton-kernel.rst
|
||||
title: Optimizing Triton kernels
|
||||
- file: how-to/llm-fine-tuning-optimization/profiling-and-debugging.rst
|
||||
- file: how-to/tuning-guides.md
|
||||
- file: how-to/tuning-guides.rst
|
||||
title: System optimization
|
||||
subtrees:
|
||||
- entries:
|
||||
- file: how-to/tuning-guides/mi100.md
|
||||
title: MI100
|
||||
- file: how-to/tuning-guides/mi200.md
|
||||
title: MI200
|
||||
title: AMD Instinct MI200
|
||||
- file: how-to/tuning-guides/mi100.md
|
||||
title: AMD Instinct MI100
|
||||
- file: how-to/tuning-guides/w6000-v620.md
|
||||
title: RDNA2
|
||||
title: AMD RDNA 2
|
||||
- file: how-to/system-debugging.md
|
||||
- file: how-to/gpu-enabled-mpi.rst
|
||||
title: Using MPI
|
||||
- file: conceptual/compiler-topics.md
|
||||
@@ -105,8 +104,6 @@ subtrees:
|
||||
title: OpenMP support
|
||||
- file: how-to/setting-cus
|
||||
title: Setting the number of CUs
|
||||
- file: how-to/system-debugging.md
|
||||
title: Debugging
|
||||
- url: https://github.com/amd/rocm-examples
|
||||
title: GitHub examples
|
||||
|
||||
|
||||
@@ -1,2 +1,2 @@
|
||||
rocm-docs-core==1.4.0
|
||||
sphinx-reredirects
|
||||
rocm-docs-core==1.8.0
|
||||
sphinx-reredirects
|
||||
|
||||
@@ -6,9 +6,9 @@
|
||||
#
|
||||
accessible-pygments==0.0.5
|
||||
# via pydata-sphinx-theme
|
||||
alabaster==0.7.16
|
||||
alabaster==1.0.0
|
||||
# via sphinx
|
||||
babel==2.15.0
|
||||
babel==2.16.0
|
||||
# via
|
||||
# pydata-sphinx-theme
|
||||
# sphinx
|
||||
@@ -16,9 +16,9 @@ beautifulsoup4==4.12.3
|
||||
# via pydata-sphinx-theme
|
||||
breathe==4.35.0
|
||||
# via rocm-docs-core
|
||||
certifi==2024.2.2
|
||||
certifi==2024.8.30
|
||||
# via requests
|
||||
cffi==1.16.0
|
||||
cffi==1.17.1
|
||||
# via
|
||||
# cryptography
|
||||
# pynacl
|
||||
@@ -26,7 +26,7 @@ charset-normalizer==3.3.2
|
||||
# via requests
|
||||
click==8.1.7
|
||||
# via sphinx-external-toc
|
||||
cryptography==42.0.7
|
||||
cryptography==43.0.1
|
||||
# via pyjwt
|
||||
deprecated==1.2.14
|
||||
# via pygithub
|
||||
@@ -36,13 +36,13 @@ docutils==0.21.2
|
||||
# myst-parser
|
||||
# pydata-sphinx-theme
|
||||
# sphinx
|
||||
fastjsonschema==2.19.1
|
||||
fastjsonschema==2.20.0
|
||||
# via rocm-docs-core
|
||||
gitdb==4.0.11
|
||||
# via gitpython
|
||||
gitpython==3.1.43
|
||||
# via rocm-docs-core
|
||||
idna==3.7
|
||||
idna==3.10
|
||||
# via requests
|
||||
imagesize==1.4.1
|
||||
# via sphinx
|
||||
@@ -56,34 +56,34 @@ markdown-it-py==3.0.0
|
||||
# myst-parser
|
||||
markupsafe==2.1.5
|
||||
# via jinja2
|
||||
mdit-py-plugins==0.4.1
|
||||
mdit-py-plugins==0.4.2
|
||||
# via myst-parser
|
||||
mdurl==0.1.2
|
||||
# via markdown-it-py
|
||||
myst-parser==3.0.1
|
||||
myst-parser==4.0.0
|
||||
# via rocm-docs-core
|
||||
packaging==24.0
|
||||
packaging==24.1
|
||||
# via
|
||||
# pydata-sphinx-theme
|
||||
# sphinx
|
||||
pycparser==2.22
|
||||
# via cffi
|
||||
pydata-sphinx-theme==0.15.3
|
||||
pydata-sphinx-theme==0.15.4
|
||||
# via
|
||||
# rocm-docs-core
|
||||
# sphinx-book-theme
|
||||
pygithub==2.3.0
|
||||
pygithub==2.4.0
|
||||
# via rocm-docs-core
|
||||
pygments==2.18.0
|
||||
# via
|
||||
# accessible-pygments
|
||||
# pydata-sphinx-theme
|
||||
# sphinx
|
||||
pyjwt[crypto]==2.8.0
|
||||
pyjwt[crypto]==2.9.0
|
||||
# via pygithub
|
||||
pynacl==1.5.0
|
||||
# via pygithub
|
||||
pyyaml==6.0.1
|
||||
pyyaml==6.0.2
|
||||
# via
|
||||
# myst-parser
|
||||
# rocm-docs-core
|
||||
@@ -92,15 +92,15 @@ requests==2.32.3
|
||||
# via
|
||||
# pygithub
|
||||
# sphinx
|
||||
rocm-docs-core==1.4.0
|
||||
rocm-docs-core==1.8.0
|
||||
# via -r requirements.in
|
||||
smmap==5.0.1
|
||||
# via gitdb
|
||||
snowballstemmer==2.2.0
|
||||
# via sphinx
|
||||
soupsieve==2.5
|
||||
soupsieve==2.6
|
||||
# via beautifulsoup4
|
||||
sphinx==7.3.7
|
||||
sphinx==8.0.2
|
||||
# via
|
||||
# breathe
|
||||
# myst-parser
|
||||
@@ -112,37 +112,37 @@ sphinx==7.3.7
|
||||
# sphinx-external-toc
|
||||
# sphinx-notfound-page
|
||||
# sphinx-reredirects
|
||||
sphinx-book-theme==1.1.2
|
||||
sphinx-book-theme==1.1.3
|
||||
# via rocm-docs-core
|
||||
sphinx-copybutton==0.5.2
|
||||
# via rocm-docs-core
|
||||
sphinx-design==0.6.0
|
||||
sphinx-design==0.6.1
|
||||
# via rocm-docs-core
|
||||
sphinx-external-toc==1.0.1
|
||||
# via rocm-docs-core
|
||||
sphinx-notfound-page==1.0.2
|
||||
sphinx-notfound-page==1.0.4
|
||||
# via rocm-docs-core
|
||||
sphinx-reredirects==0.1.4
|
||||
sphinx-reredirects==0.1.5
|
||||
# via -r requirements.in
|
||||
sphinxcontrib-applehelp==1.0.8
|
||||
sphinxcontrib-applehelp==2.0.0
|
||||
# via sphinx
|
||||
sphinxcontrib-devhelp==1.0.6
|
||||
sphinxcontrib-devhelp==2.0.0
|
||||
# via sphinx
|
||||
sphinxcontrib-htmlhelp==2.0.5
|
||||
sphinxcontrib-htmlhelp==2.1.0
|
||||
# via sphinx
|
||||
sphinxcontrib-jsmath==1.0.1
|
||||
# via sphinx
|
||||
sphinxcontrib-qthelp==1.0.7
|
||||
sphinxcontrib-qthelp==2.0.0
|
||||
# via sphinx
|
||||
sphinxcontrib-serializinghtml==1.1.10
|
||||
sphinxcontrib-serializinghtml==2.0.0
|
||||
# via sphinx
|
||||
tomli==2.0.1
|
||||
# via sphinx
|
||||
typing-extensions==4.12.0
|
||||
typing-extensions==4.12.2
|
||||
# via
|
||||
# pydata-sphinx-theme
|
||||
# pygithub
|
||||
urllib3==2.2.2
|
||||
urllib3==2.2.3
|
||||
# via
|
||||
# pygithub
|
||||
# requests
|
||||
|
||||
@@ -100,7 +100,7 @@ Tools
|
||||
":doc:`AMD SMI <amdsmi:index>`", "C library for Linux that provides a user space interface for applications to monitor and control AMD devices"
|
||||
":doc:`HIPIFY <hipify:index>`", "Translates CUDA source code into portable HIP C++"
|
||||
":doc:`ROCdbgapi <rocdbgapi:index>`", "ROCm debugger API library"
|
||||
":doc:`ROCmCC <./reference/rocmcc>`", "Clang/LLVM-based compiler"
|
||||
":doc:`ROCm compilers <./reference/rocmcc>`", "Clang/LLVM-based compiler"
|
||||
":doc:`rocminfo <rocminfo:index>`", "Reports system information"
|
||||
":doc:`ROCProfiler <rocprofiler:index>`", "Profiling tool for HIP applications"
|
||||
":doc:`ROCTracer <roctracer:index>`", "Intercepts runtime API calls and traces asynchronous activity"
|
||||
@@ -111,7 +111,6 @@ Tools
|
||||
":doc:`ROCm SMI <rocm_smi_lib:index>`", "C library for Linux that provides a user space interface for applications to monitor and control GPU applications"
|
||||
":doc:`ROCm Validation Suite <rocmvalidationsuite:index>`", "Detects and troubleshoots common problems affecting AMD GPUs running in a high-performance computing environment"
|
||||
":doc:`ROCr Debug Agent <rocr_debug_agent:index>`", "Prints the state of all AMD GPU wavefronts that caused a queue error by sending a SIGQUIT signal to the process while the program is running"
|
||||
":doc:`TransferBench <transferbench:index>`", "Utility to benchmark simultaneous transfers between user-specified devices (CPUs/GPUs)"
|
||||
|
||||
Compilers
|
||||
-----------------------------------------------
|
||||
@@ -120,7 +119,7 @@ Compilers
|
||||
:header: "Component", "Description"
|
||||
|
||||
"`FLANG <https://github.com/ROCm/flang/>`_", "An out-of-tree Fortran compiler targeting LLVM"
|
||||
":doc:`hipCC <hipcc:index>`", "Compiler driver utility that calls Clang or NVCC and passes the appropriate include and library options for the target compiler and HIP infrastructure"
|
||||
"`hipCC <https://github.com/ROCm/HIPCC>`_ ", "Compiler driver utility that calls Clang or NVCC and passes the appropriate include and library options for the target compiler and HIP infrastructure"
|
||||
"`LLVM (amdclang) <https://github.com/ROCm/llvm-project>`_ ", "Toolkit for the construction of highly optimized compilers, optimizers, and runtime environments"
|
||||
|
||||
Runtimes
|
||||
@@ -129,6 +128,6 @@ Runtimes
|
||||
.. csv-table::
|
||||
:header: "Component", "Description"
|
||||
|
||||
"`AMD Common Language Runtime (CLR) <https://github.com/ROCm/clr>`_", "Contains source code for AMD's common language runtimes: :doc:`HIP <hip:index>` and OpenCL"
|
||||
":doc:`AMD Common Language Runtime (CLR) <hip:understand/amd_clr>`", "Contains source code for AMD's common language runtimes: HIP and OpenCL"
|
||||
":doc:`HIP <hip:index>`", "AMD's GPU programming language extension and the GPU runtime"
|
||||
":doc:`ROCR-Runtime <rocr-runtime:index>`", "User-mode API interfaces and libraries necessary for host applications to launch compute kernels on available HSA ROCm kernel agents"
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
|
||||
<!-- spellcheck-disable -->
|
||||
|
||||
This page contains the release notes for AMD ROCm™ Software.
|
||||
This page contains the release notes for AMD ROCm Software.
|
||||
|
||||
{%- for version, release in releases %}
|
||||
|
||||
|
||||
@@ -17,6 +17,7 @@ AMD SMI for ROCm 6.1.1
|
||||
|
||||
#### Changes
|
||||
|
||||
* Updated the output of `amd-smi metric --ecc-blocks` to show counters available from blocks.
|
||||
* Updated the output of `amd-smi metric --clock` to reflect each engine.
|
||||
* Updated the output of `amd-smi topology --json` to align with output reported by host and guest systems.
|
||||
|
||||
@@ -27,6 +28,10 @@ AMD SMI for ROCm 6.1.1
|
||||
* Fixed `amd-smi metric --pcie` and `amdsmi_get_pcie_info()` when using RDNA3 (Navi 32 and Navi 31) hardware to prevent "UNKNOWN" reports.
|
||||
* Fixed the output results of `amd-smi process` when getting processes running on a device.
|
||||
|
||||
#### Removals
|
||||
|
||||
* Removed the `amdsmi_get_gpu_process_info` API from the Python library. It was removed from the C library in an earlier release.
|
||||
|
||||
#### Known issues
|
||||
|
||||
* `amd-smi bad-pages` can result in a `ValueError: Null pointer access` error when using certain PMU firmware versions.
|
||||
@@ -43,7 +48,7 @@ HIPCC for ROCm 6.1.1
|
||||
|
||||
* **Upcoming:** a future release will enable use of compiled binaries `hipcc.bin` and `hipconfig.bin` by default. No action is needed by users; you may continue calling high-level Perl scripts `hipcc` and `hipconfig`. `hipcc.bin` and `hipconfig.bin` will be invoked by the high-level Perl scripts. To revert to the previous behavior and invoke `hipcc.pl` and `hipconfig.pl`, set the `HIP_USE_PERL_SCRIPTS` environment variable to `1`.
|
||||
* **Upcoming:** a subsequent release will remove high-level Perl scripts `hipcc` and `hipconfig`. This release will remove the `HIP_USE_PERL_SCRIPTS` environment variable. It will rename `hipcc.bin` and `hipconfig.bin` to `hipcc` and `hipconfig` respectively. No action is needed by the users. To revert to the previous behavior, invoke `hipcc.pl` and `hipconfig.pl` explicitly.
|
||||
* **Upcoming:** a subsequent release will remove `hipcc.pl` and `hipconfig.pl`.
|
||||
* **Upcoming:** a subsequent will remove `hipcc.pl` and `hipconfig.pl`.
|
||||
|
||||
### ROCm SMI
|
||||
|
||||
|
||||
@@ -1,66 +0,0 @@
|
||||
|
||||
ROCm 6.1.2 includes enhancements to SMI tools and improvements to some libraries.
|
||||
|
||||
### OS support
|
||||
|
||||
ROCm 6.1.2 has been tested against a pre-release version of Ubuntu 22.04.5 (kernel: 5.15 [GA], 6.8 [HWE]).
|
||||
|
||||
### AMD SMI
|
||||
|
||||
AMD SMI for ROCm 6.1.2
|
||||
|
||||
#### Additions
|
||||
|
||||
* Added process isolation and clean shader APIs and CLI commands.
|
||||
* `amdsmi_get_gpu_process_isolation()`
|
||||
* `amdsmi_set_gpu_process_isolation()`
|
||||
* `amdsmi_set_gpu_clear_sram_data()`
|
||||
* Added the `MIN_POWER` metric to output provided by `amd-smi static --limit`.
|
||||
|
||||
#### Optimizations
|
||||
|
||||
* Updated the `amd-smi monitor --pcie` output to prevent delays with the `monitor` command.
|
||||
|
||||
#### Changes
|
||||
|
||||
* Updated `amismi_get_power_cap_info` to return values in uW instead of W.
|
||||
* Updated Python library return types for `amdsmi_get_gpu_memory_reserved_pages` and `amdsmi_get_gpu_bad_page_info`.
|
||||
* Updated the output of `amd-smi metric --ecc-blocks` to show counters available from blocks.
|
||||
|
||||
#### Fixes
|
||||
|
||||
* `amdsmi_get_gpu_board_info()` no longer returns junk character strings.
|
||||
* `amd-smi metric --power` now correctly details power output for RDNA3, RDNA2, and MI1x devices.
|
||||
* Fixed the `amdsmitstReadWrite.TestPowerCapReadWrite` test for RDNA3, RDNA2, and MI100 devices.
|
||||
* Fixed an issue with the `amdsmi_get_gpu_memory_reserved_pages` and `amdsmi_get_gpu_bad_page_info` Python interface calls.
|
||||
|
||||
#### Removals
|
||||
|
||||
* Removed the `amdsmi_get_gpu_process_info` API from the Python library. It was removed from the C library in an earlier release.
|
||||
|
||||
```{note}
|
||||
See the AMD SMI [detailed changelog](https://github.com/ROCm/amdsmi/blob/rocm-6.1.x/CHANGELOG.md) with code samples for more information.
|
||||
```
|
||||
|
||||
### HIPCC
|
||||
|
||||
HIPCC for ROCm 6.1.2
|
||||
|
||||
#### Changes
|
||||
|
||||
* **Upcoming:** a future release will enable use of compiled binaries `hipcc.bin` and `hipconfig.bin` by default. No action is needed by users; you may continue calling high-level Perl scripts `hipcc` and `hipconfig`. `hipcc.bin` and `hipconfig.bin` will be invoked by the high-level Perl scripts. To revert to the previous behavior and invoke `hipcc.pl` and `hipconfig.pl`, set the `HIP_USE_PERL_SCRIPTS` environment variable to `1`.
|
||||
* **Upcoming:** a subsequent release will remove high-level Perl scripts `hipcc` and `hipconfig`. This release will remove the `HIP_USE_PERL_SCRIPTS` environment variable. It will rename `hipcc.bin` and `hipconfig.bin` to `hipcc` and `hipconfig` respectively. No action is needed by the users. To revert to the previous behavior, invoke `hipcc.pl` and `hipconfig.pl` explicitly.
|
||||
* **Upcoming:** a subsequent release will remove `hipcc.pl` and `hipconfig.pl`.
|
||||
|
||||
### ROCm SMI
|
||||
|
||||
ROCm SMI for ROCm 6.1.2
|
||||
|
||||
#### Additions
|
||||
|
||||
* Added the ring hang event to the `amdsmi_evt_notification_type_t` enum.
|
||||
|
||||
#### Fixes
|
||||
|
||||
* Fixed an issue causing ROCm SMI to incorrectly report GPU utilization for RDNA3 GPUs. See the issue on [GitHub](https://github.com/ROCm/ROCm/issues/3112).
|
||||
* Fixed the parsing of `pp_od_clk_voltage` in `get_od_clk_volt_info` to work better with MI-series hardware.
|
||||
@@ -1,37 +0,0 @@
|
||||
# Overview for ROCm.mk
|
||||
|
||||
This Makefile builds the various projects that makes up ROCm in the correct order.
|
||||
It is expected to be run in an environment with the tooling set up. An easy way
|
||||
to do this is to use Docker.
|
||||
|
||||
## Targets
|
||||
|
||||
* all (default)
|
||||
* rocm-dev (a subset of all)
|
||||
* clean
|
||||
* list_components
|
||||
* help
|
||||
* T_foo
|
||||
* C_foo
|
||||
|
||||
## Makefile Variables
|
||||
|
||||
* PEVAL set to 1 to enable some Makefile debugging code.
|
||||
* RELEASE\_FLAG set to "" to avoid passing "-r" to builds, effect is package defined.
|
||||
* NOBUILD="foo bar" to avoid adding foo and bar into the dependencies of top level targets. They still may be
|
||||
built if they are needed as dependencies of other top level targets.
|
||||
* toplevel
|
||||
|
||||
## Makefile assumptions
|
||||
|
||||
### Requirements for package "foo"
|
||||
|
||||
#### program build\_foo.sh
|
||||
|
||||
* Should take option "-c" to clean
|
||||
* Should take option "-r" to do a normal "RelWithDeb" build
|
||||
|
||||
### For package "foo" we define some targets
|
||||
|
||||
* T\_foo - The main build target, calls "build\_foo.sh -r"
|
||||
* C\_foo - Clean target, calls "build_foo.sh -c"
|
||||
@@ -1,248 +0,0 @@
|
||||
# Traditional first make target
|
||||
all:
|
||||
|
||||
# Use bash as a shell
|
||||
# On Ubuntu sh is 'dash'
|
||||
SHELL:=bash
|
||||
|
||||
# Allow RELEASE_FLAG to be overwritten
|
||||
RELEASE_FLAG?=-r
|
||||
|
||||
# Set SANITIZER_FLAG for sanitizer
|
||||
ASAN_DEP:=
|
||||
ifeq (${ENABLE_ADDRESS_SANITIZER},true)
|
||||
ASAN_DEP=lightning
|
||||
SANITIZER_FLAG=-a
|
||||
endif
|
||||
|
||||
export INFRA_REPO:=ROCm/tools/rocm-build
|
||||
|
||||
OUT_DIR:=$(shell . ${INFRA_REPO}/envsetup.sh >/dev/null 2>&1 ; echo $${OUT_DIR})
|
||||
ROCM_INSTALL_PATH:=$(shell . ${INFRA_REPO}/envsetup.sh >/dev/null 2>&1 ; echo $${ROCM_INSTALL_PATH})
|
||||
|
||||
$(info OUT_DIR=${OUT_DIR})
|
||||
$(info ROCM_INSTALL_PATH=${ROCM_INSTALL_PATH})
|
||||
|
||||
# -------------------------------------------------------------------------
|
||||
# Internal stuff. Could be put in a different file to hide it.
|
||||
# Internal macros, they need to be defined before being used.
|
||||
|
||||
# The internal "eval" allows parts of the Makefile to be generated.
|
||||
# Whilst it is possible to dump the effective Makefile, it can be
|
||||
# hard to see where parts come from. Set up the "peval" macro which
|
||||
# optionally prints out the generated makefile snippet and evaluate it.
|
||||
# Use "make PEVAL=1 all" to see the things being evaluated.
|
||||
ifeq (,${PEVAL})
|
||||
define peval =
|
||||
$(eval $1)
|
||||
endef
|
||||
else
|
||||
define peval =
|
||||
$(eval $(info $1)$1)
|
||||
endef
|
||||
endif
|
||||
|
||||
# macro to add dependencies. Saves having to put all the OUT_DIR/logs in
|
||||
# The outer strip is to work around a gnu make 4.1 and earlier bug
|
||||
# It should not be needed.
|
||||
define adddep =
|
||||
$(strip $(call peval,components+= $(1) $(2))
|
||||
$(foreach comp,$(strip $2),$(call peval,${OUT_DIR}/logs/${1}: ${OUT_DIR}/logs/${comp}))
|
||||
)
|
||||
endef
|
||||
# End of internal stuff that is needed at the start of the file
|
||||
# -------------------------------------------------------------------------
|
||||
|
||||
# Dependencies. These can be updated. Anything that is mentioned in
|
||||
# either the args to the adddep macro will be added to components. as
|
||||
# an example there is no need for the adddep of lightning, as it
|
||||
# depends on nothing and at least one other component includes it.
|
||||
|
||||
# Syntax. Up to the first comma everything is fixed. The "call" is a
|
||||
# keyword to gnu make. The "adddep" is the name of the variable containing
|
||||
# the macro.
|
||||
# The second comma delimited argument is the target.
|
||||
# The third comma delimited arg is the thing that the target depends on.
|
||||
# It is a space seperated list with zero or more elements.
|
||||
|
||||
$(call adddep,amd_smi_lib,${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} 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,)
|
||||
$(call adddep,opencl_on_rocclr,${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)
|
||||
$(call adddep,rocm_bandwidth_test,${ASAN_DEP} hsa)
|
||||
$(call adddep,rocm_smi_lib,${ASAN_DEP})
|
||||
$(call adddep,rocm-cmake,${ASAN_DEP})
|
||||
$(call adddep,rocm-core,${ASAN_DEP})
|
||||
$(call adddep,rocm-gdb,dbgapi)
|
||||
$(call adddep,rocminfo,${ASAN_DEP} hsa)
|
||||
$(call adddep,rocprofiler-register,${ASAN_DEP})
|
||||
$(call adddep,rocprofiler,${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 \
|
||||
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}))
|
||||
|
||||
$(call adddep,amdmigraphx,hip_on_rocclr half rocblas miopen-hip lightning hipcc)
|
||||
$(call adddep,composable_kernel,lightning hipcc hip_on_rocclr rocm-cmake)
|
||||
$(call adddep,half,rocm-cmake)
|
||||
$(call adddep,hipblas,hip_on_rocclr rocblas rocsolver lightning hipcc)
|
||||
$(call adddep,hipblaslt,hip_on_rocclr openmp_extras hipblas lightning hipcc)
|
||||
$(call adddep,hipcub,hip_on_rocclr rocprim lightning hipcc)
|
||||
$(call adddep,hipfft,hip_on_rocclr openmp_extras rocfft rocrand hiprand lightning hipcc)
|
||||
$(call adddep,hipfort,rocblas hipblas rocsparse hipsparse rocfft hipfft rocrand hiprand rocsolver hipsolver lightning hipcc)
|
||||
$(call adddep,hiprand,hip_on_rocclr rocrand lightning hipcc)
|
||||
$(call adddep,hipsolver,hip_on_rocclr rocblas rocsolver rocsparse lightning hipcc hipsparse)
|
||||
$(call adddep,hipsparse,hip_on_rocclr rocsparse lightning hipcc)
|
||||
$(call adddep,hipsparselt,hip_on_rocclr hipsparse lightning hipcc openmp_extras)
|
||||
$(call adddep,hiptensor,hip_on_rocclr composable_kernel lightning hipcc)
|
||||
$(call adddep,miopen-deps,lightning hipcc)
|
||||
$(call adddep,miopen-hip,composable_kernel half hip_on_rocclr miopen-deps rocblas roctracer lightning hipcc)
|
||||
$(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,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)
|
||||
$(call adddep,rocprim,hip_on_rocclr lightning hipcc)
|
||||
$(call adddep,rocrand,hip_on_rocclr lightning hipcc)
|
||||
$(call adddep,rocsolver,hip_on_rocclr rocblas rocsparse lightning hipcc)
|
||||
$(call adddep,rocsparse,hip_on_rocclr rocprim lightning hipcc)
|
||||
$(call adddep,rocthrust,hip_on_rocclr rocprim lightning hipcc)
|
||||
$(call adddep,rocwmma,hip_on_rocclr rocblas lightning hipcc rocm-cmake rocm_smi_lib)
|
||||
$(call adddep,rpp,half lightning hipcc openmp_extras)
|
||||
|
||||
|
||||
# -------------------------------------------------------------------------
|
||||
# The rest of the file is internal
|
||||
# Do not pass jobserver params if -n build
|
||||
ifneq (,$(findstring n,${MAKEFLAGS}))
|
||||
RMAKE:=
|
||||
else
|
||||
RMAKE := +
|
||||
endif
|
||||
|
||||
|
||||
# disable the builtin rules
|
||||
.SUFFIXES:
|
||||
|
||||
# Linear
|
||||
# include moredeps
|
||||
|
||||
# A macro to define a toplevel target, add it to the 'all' target
|
||||
# Make it depend on the generated log. Generate the log of the build.
|
||||
|
||||
# See if the macro is already defined, if so don't touch it.
|
||||
# As GNU make allows more than one makefile to be specified with "-f"
|
||||
# one could put an alternative definition of "toplevel" in a different
|
||||
# file or even the environment, and use the data in this file for other
|
||||
# purposes. Uses might include generating output in "dot" format for
|
||||
# showing the dependency graph, or having a wrapper script to run programs
|
||||
# to generate code quality tools.
|
||||
ifeq (${toplevel},)
|
||||
# { Start of test to see if toplevel is defined
|
||||
define toplevel =
|
||||
|
||||
# The "target" make, this builds the package if it is out of date
|
||||
T_$1: ${OUT_DIR}/logs/$1 FRC
|
||||
: $1 built
|
||||
|
||||
# The "upload" for $1, it uploads the packages for $1 to the central storage
|
||||
U_$1: T_$1 FRC
|
||||
source $${INFRA_REPO}/envsetup.sh && $${INFRA_REPO}/upload_packages.sh "$1"
|
||||
: $1 uploaded
|
||||
|
||||
# The "clean" for $1, it just marks the target as not existing so it will be built
|
||||
# in the future.
|
||||
C_$1: FRC
|
||||
rm -f ${OUT_DIR}/logs/$1 ${OUT_DIR}/logs/$1.repackaged
|
||||
|
||||
# parallel build {
|
||||
${OUT_DIR}/logs/$1: | ${OUT_DIR}/logs
|
||||
ifneq ($(wildcard ${OUT_DIR}/logs/$1.repackaged),)
|
||||
@echo Skipping build of $1 as it has already been repackaged
|
||||
cat $$@.repackaged > $$@
|
||||
rm -f $$@.repackaged
|
||||
else # } {
|
||||
@echo $1 started due to $$? | sed "s:${OUT_DIR}/logs/::g"
|
||||
# Build in a subshell so we get the time output
|
||||
# Pass in jobserver info using the RMAKE variable
|
||||
${RMAKE}@( if set -x && source $${INFRA_REPO}/envsetup.sh && \
|
||||
rm -f $$@.errors $$@ $$@.repackaged && \
|
||||
$${INFRA_REPO}/build_$1.sh -c && source $${INFRA_REPO}/ccache-env-mathlib.sh && \
|
||||
time bash -x $${INFRA_REPO}/build_$1.sh $${RELEASE_FLAG} $${SANITIZER_FLAG} && $${INFRA_REPO}/post_inst_pkg.sh "$1" ; \
|
||||
then mv $$@.inprogress $$@ ; \
|
||||
else mv $$@.inprogress $$@.errors ; echo Error in $1 >&2 ; exit 1 ;\
|
||||
fi ) > $$@.inprogress 2>&1
|
||||
endif # }
|
||||
|
||||
# end of toplevel macro
|
||||
endef
|
||||
# } End of test to see if toplevel is defined
|
||||
endif
|
||||
|
||||
components:=$(sort $(components))
|
||||
|
||||
# Create all the T_xxxx and C_xxxx targets
|
||||
$(call peval,$(foreach dep,$(strip ${components}),$(call toplevel,${dep})))
|
||||
|
||||
# Add all the T_xxxx targets to "all" except those listed in NOBUILD
|
||||
# Note this does not prohibit them from being built, it just means that
|
||||
# a build of "all" will not force them to be built directly
|
||||
# example command
|
||||
# make -f jenkins-utils/scripts/Stage1.mk -j60
|
||||
|
||||
##help all: Build everything
|
||||
all: $(addprefix T_,$(filter-out ${NOBUILD},${components}))
|
||||
@echo All ROCm components built
|
||||
# Do not document this target
|
||||
upload: $(addprefix U_,${components})
|
||||
@echo All ROCm components built and uploaded
|
||||
|
||||
##help rocm-dev: Build a subset of ROCm
|
||||
rocm-dev: T_rocm-dev
|
||||
@echo rocm-dev built
|
||||
|
||||
${OUT_DIR}/logs:
|
||||
sudo mkdir -p -m 775 "${ROCM_INSTALL_PATH}" && \
|
||||
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 ${HOME}/.ccache
|
||||
|
||||
##help clean: remove the output directory and recreate it
|
||||
clean:
|
||||
[ -n "${OUT_DIR}" ] && rm -rf "${OUT_DIR}"
|
||||
mkdir -p ${OUT_DIR}/logs
|
||||
|
||||
.SECONDARY: ${components:%=${OUT_DIR}/logs/%}
|
||||
|
||||
.PHONY: all clean repack help list_components
|
||||
|
||||
##help list_components: output the list of components
|
||||
##help : Hint make list_components | paste - - - | column -t
|
||||
list_components:
|
||||
@echo "${components}" | sed 'y/ /\n/'
|
||||
|
||||
##help help: show this text
|
||||
help:
|
||||
@sed -n 's/^##help //p' ${MAKEFILE_LIST} | \
|
||||
if type -t column > /dev/null ; then column -s: -t ; else cat ; fi
|
||||
|
||||
FRC:
|
||||
@@ -1,145 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: $(basename "${BASH_SOURCE}") [-c|-r|-h] [makeopts]"
|
||||
echo
|
||||
echo "Options:"
|
||||
echo " -c, --clean Removes all amd_smi build artifacts"
|
||||
echo " -r, --release Build non-debug version amd_smi (default is debug)"
|
||||
echo " -a, --address_sanitizer Enable address sanitizer"
|
||||
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
|
||||
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 "Possible values for <type>:"
|
||||
echo " deb -> Debian format (default)"
|
||||
echo " rpm -> RPM format"
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
PACKAGE_ROOT="$(getPackageRoot)"
|
||||
TARGET="build"
|
||||
|
||||
PACKAGE_LIB=$(getLibPath)
|
||||
PACKAGE_INCLUDE="$(getIncludePath)"
|
||||
|
||||
AMDSMI_BUILD_DIR=$(getBuildPath amdsmi)
|
||||
AMDSMI_PACKAGE_DEB_DIR="$(getPackageRoot)/deb/amdsmi"
|
||||
AMDSMI_PACKAGE_RPM_DIR="$(getPackageRoot)/rpm/amdsmi"
|
||||
AMDSMI_BUILD_TYPE="debug"
|
||||
BUILD_TYPE="Debug"
|
||||
|
||||
MAKETARGET="deb"
|
||||
MAKEARG="$DASH_JAY O=$AMDSMI_BUILD_DIR"
|
||||
AMDSMI_MAKE_OPTS="$DASH_JAY O=$AMDSMI_BUILD_DIR -C $AMDSMI_BUILD_DIR"
|
||||
AMDSMI_PKG_NAME="amd-smi-lib"
|
||||
SHARED_LIBS="ON"
|
||||
CLEAN_OR_OUT=0;
|
||||
PKGTYPE="deb"
|
||||
|
||||
VALID_STR=`getopt -o hcraso:p: --long help,clean,release,static,address_sanitizer,outdir:,package: -- "$@"`
|
||||
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_asan_env_vars
|
||||
set_address_sanitizer_on
|
||||
# TODO - support standard option of passing cmake environment vars - CFLAGS,CXXFLAGS etc., to enable address sanitizer
|
||||
ADDRESS_SANITIZER=true ; 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;;
|
||||
--) 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 $RET_CONFLICT
|
||||
fi
|
||||
|
||||
clean_amdsmi() {
|
||||
rm -rf "$AMDSMI_BUILD_DIR"
|
||||
rm -rf "$AMDSMI_PACKAGE_DEB_DIR"
|
||||
rm -rf "$AMDSMI_PACKAGE_RPM_DIR"
|
||||
rm -rf "$PACKAGE_ROOT/amd_smi"
|
||||
rm -rf "$PACKAGE_INCLUDE/amd_smi"
|
||||
rm -f $PACKAGE_LIB/libamd_smi.*
|
||||
return 0
|
||||
}
|
||||
|
||||
build_amdsmi() {
|
||||
echo "Building AMDSMI"
|
||||
echo "AMDSMI_BUILD_DIR: ${AMDSMI_BUILD_DIR}"
|
||||
if [ ! -d "$AMDSMI_BUILD_DIR" ]; then
|
||||
mkdir -p $AMDSMI_BUILD_DIR
|
||||
pushd $AMDSMI_BUILD_DIR
|
||||
print_lib_type $SHARED_LIBS
|
||||
cmake \
|
||||
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
|
||||
$(rocm_common_cmake_params) \
|
||||
$(rocm_cmake_params) \
|
||||
-DENABLE_LDCONFIG=OFF \
|
||||
-DAMD_SMI_PACKAGE="${AMDSMI_PKG_NAME}" \
|
||||
-DCPACK_PACKAGE_VERSION_MAJOR="1" \
|
||||
-DCPACK_PACKAGE_VERSION_MINOR="$ROCM_LIBPATCH_VERSION" \
|
||||
-DCPACK_PACKAGE_VERSION_PATCH="0" \
|
||||
-DADDRESS_SANITIZER="$ADDRESS_SANITIZER" \
|
||||
-DBUILD_TESTS=ON \
|
||||
"$AMD_SMI_LIB_ROOT"
|
||||
popd
|
||||
fi
|
||||
|
||||
echo "Making amd_smi package:"
|
||||
cmake --build "$AMDSMI_BUILD_DIR" -- $AMDSMI_MAKE_OPTS
|
||||
cmake --build "$AMDSMI_BUILD_DIR" -- $AMDSMI_MAKE_OPTS install
|
||||
cmake --build "$AMDSMI_BUILD_DIR" -- $AMDSMI_MAKE_OPTS package
|
||||
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$AMDSMI_PACKAGE_DEB_DIR" $AMDSMI_BUILD_DIR/*.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$AMDSMI_PACKAGE_RPM_DIR" $AMDSMI_BUILD_DIR/*.rpm
|
||||
}
|
||||
|
||||
print_output_directory() {
|
||||
case ${PKGTYPE} in
|
||||
("deb")
|
||||
echo ${AMDSMI_PACKAGE_DEB_DIR};;
|
||||
("rpm")
|
||||
echo ${AMDSMI_PACKAGE_RPM_DIR};;
|
||||
(*)
|
||||
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
|
||||
esac
|
||||
exit
|
||||
}
|
||||
|
||||
verifyEnvSetup
|
||||
|
||||
case $TARGET in
|
||||
(clean) clean_amdsmi ;;
|
||||
(build) build_amdsmi ;;
|
||||
(outdir) print_output_directory ;;
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
echo "Operation complete"
|
||||
exit 0
|
||||
@@ -1,54 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -ex
|
||||
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
|
||||
|
||||
set_component_src AMDMIGraphX
|
||||
|
||||
build_amdmigraphx() {
|
||||
echo "Start build"
|
||||
|
||||
cd $COMPONENT_SRC
|
||||
|
||||
pip3 install https://github.com/RadeonOpenCompute/rbuild/archive/master.tar.gz
|
||||
|
||||
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
|
||||
set_asan_env_vars
|
||||
set_address_sanitizer_on
|
||||
fi
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
else
|
||||
GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
|
||||
fi
|
||||
|
||||
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" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DCMAKE_MODULE_LINKER_FLAGS="-Wl,--enable-new-dtags -Wl,--rpath,$ROCM_LIB_RPATH" \
|
||||
-DGPU_TARGETS="${GPU_TARGETS}" \
|
||||
-DCMAKE_INSTALL_RPATH=""
|
||||
|
||||
mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
|
||||
cd $BUILD_DIR && cmake --build . -- install -j${PROC}
|
||||
|
||||
show_build_cache_stats
|
||||
}
|
||||
|
||||
clean_amdmigraphx() {
|
||||
echo "Cleaning AMDMIGraphX build directory: ${BUILD_DIR} ${DEPS_DIR} ${PACKAGE_DIR}"
|
||||
rm -rf "$BUILD_DIR" "$DEPS_DIR" "$PACKAGE_DIR"
|
||||
echo "Done!"
|
||||
}
|
||||
|
||||
stage2_command_args "$@"
|
||||
|
||||
case $TARGET in
|
||||
build) build_amdmigraphx ;;
|
||||
outdir) print_output_directory ;;
|
||||
clean) clean_amdmigraphx ;;
|
||||
*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
@@ -1,150 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: ${BASH_SOURCE##*/} [options ...]"
|
||||
echo
|
||||
echo "Options:"
|
||||
echo " -c, --clean Clean output and delete all intermediate work"
|
||||
echo " -p, --package <type> Specify packaging format"
|
||||
echo " -r, --release Make a release build instead of a debug build"
|
||||
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
|
||||
type referred to by pkg_type"
|
||||
echo " -h, --help Prints this help"
|
||||
echo
|
||||
echo "Possible values for <type>:"
|
||||
echo " deb -> Debian format (default)"
|
||||
echo " rpm -> RPM format"
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
API_NAME="hsa-amd-aqlprofile"
|
||||
PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
|
||||
PROJ_NAME="$API_NAME"
|
||||
TARGET="build"
|
||||
BUILD_TYPE="Debug"
|
||||
MAKETARGET="deb"
|
||||
MAKE_OPTS="$DASH_JAY -C $BUILD_DIR"
|
||||
SHARED_LIBS="ON"
|
||||
CLEAN_OR_OUT=0
|
||||
MAKETARGET="deb"
|
||||
PKGTYPE="deb"
|
||||
|
||||
VALID_STR=$(getopt -o hcro:p: --long help,clean,release,clean,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="Release"
|
||||
shift
|
||||
;;
|
||||
-o | --outdir)
|
||||
TARGET="outdir"
|
||||
PKGTYPE=$2
|
||||
OUT_DIR_SPECIFIED=1
|
||||
((CLEAN_OR_OUT |= 2))
|
||||
shift 2
|
||||
;;
|
||||
--)
|
||||
shift
|
||||
break
|
||||
;;
|
||||
*)
|
||||
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] " >&2
|
||||
exit 20
|
||||
;;
|
||||
esac
|
||||
|
||||
done
|
||||
|
||||
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
|
||||
sudo cp -r ./pkg/*/rocm*/* "${ROCM_PATH}" || exit 2
|
||||
rm -rf pkg/
|
||||
}
|
||||
|
||||
clean() {
|
||||
echo "Cleaning $PROJ_NAME package"
|
||||
rm -rf "$PACKAGE_DEB"
|
||||
}
|
||||
|
||||
build() {
|
||||
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/${rocm_ver}/pool/main/h/${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 ${API_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
|
||||
}
|
||||
|
||||
case "$TARGET" in
|
||||
clean) clean ;;
|
||||
build) build ;;
|
||||
outdir) print_output_directory ;;
|
||||
*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
echo "Operation complete"
|
||||
@@ -1,136 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: $(basename "${BASH_SOURCE}") [-c|-r|-h] [makeopts]"
|
||||
echo
|
||||
echo "Options:"
|
||||
echo " -c, --clean Removes all clang-ocl build artifacts"
|
||||
echo " -r, --release Build non-debug version clang-ocl (default is debug)"
|
||||
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 " -s, --static Supports static CI by accepting this param & not bailing out. No effect of the param though"
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
|
||||
TARGET="build"
|
||||
CLANG_OCL_DEST="$(getBinPath)"
|
||||
CLANG_OCL_SRC_ROOT="$CLANG_OCL_ROOT"
|
||||
CLANG_OCL_BUILD_DIR="$(getBuildPath clang-ocl)"
|
||||
|
||||
MAKEARG="$DASH_JAY"
|
||||
PACKAGE_ROOT="$(getPackageRoot)"
|
||||
PACKAGE_UTILS="$(getUtilsPath)"
|
||||
CLANG_OCL_PACKAGE_DEB="$PACKAGE_ROOT/deb/clang-ocl"
|
||||
CLANG_OCL_PACKAGE_RPM="$PACKAGE_ROOT/rpm/clang-ocl"
|
||||
BUILD_TYPE="Debug"
|
||||
SHARED_LIBS="ON"
|
||||
CLEAN_OR_OUT=0;
|
||||
MAKETARGET="deb"
|
||||
PKGTYPE="deb"
|
||||
|
||||
|
||||
VALID_STR=`getopt -o hcraso:g: --long help,clean,release,clean,static,address_sanitizer,outdir:,gpu_list: -- "$@"`
|
||||
eval set -- "$VALID_STR"
|
||||
|
||||
while true ;
|
||||
do
|
||||
case "$1" in
|
||||
(-h | --help)
|
||||
printUsage ; exit 0;;
|
||||
(-c | --clean)
|
||||
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
|
||||
(-r | --release)
|
||||
MAKEARG="$MAKEARG BUILD_TYPE=rel" ; 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 ;;
|
||||
(-g | --gpu_list )
|
||||
GPU_LIST=$2; shift 2 ;;
|
||||
--) 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_clang-ocl() {
|
||||
echo "Removing clang-ocl"
|
||||
rm -rf $CLANG_OCL_DEST/clang-ocl
|
||||
rm -rf $CLANG_OCL_BUILD_DIR
|
||||
rm -rf $CLANG_OCL_PACKAGE_DEB
|
||||
rm -rf $CLANG_OCL_PACKAGE_RPM
|
||||
}
|
||||
|
||||
build_clang-ocl() {
|
||||
if [ ! -d "$CLANG_OCL_BUILD_DIR" ]; then
|
||||
mkdir -p $CLANG_OCL_BUILD_DIR
|
||||
pushd $CLANG_OCL_BUILD_DIR
|
||||
|
||||
if [ -e $PACKAGE_ROOT/lib/bitcode/opencl.amdgcn.bc ]; then
|
||||
BC_DIR="$ROCM_INSTALL_PATH/lib"
|
||||
else
|
||||
BC_DIR="$ROCM_INSTALL_PATH/amdgcn/bitcode"
|
||||
fi
|
||||
|
||||
cmake \
|
||||
$(rocm_cmake_params) \
|
||||
-DDISABLE_CHECKS="ON" \
|
||||
-DCLANG_BIN="$ROCM_INSTALL_PATH/llvm/bin" \
|
||||
-DBITCODE_DIR="$BC_DIR" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DCPACK_SET_DESTDIR="OFF" \
|
||||
$CLANG_OCL_SRC_ROOT
|
||||
|
||||
echo "Making clang-ocl:"
|
||||
cmake --build . -- $MAKEARG
|
||||
cmake --build . -- $MAKEARG install
|
||||
cmake --build . -- $MAKEARG package
|
||||
popd
|
||||
fi
|
||||
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$CLANG_OCL_PACKAGE_DEB" $CLANG_OCL_BUILD_DIR/rocm-clang-ocl*.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$CLANG_OCL_PACKAGE_RPM" $CLANG_OCL_BUILD_DIR/rocm-clang-ocl*.rpm
|
||||
}
|
||||
|
||||
|
||||
print_output_directory() {
|
||||
case ${PKGTYPE} in
|
||||
("deb")
|
||||
echo ${CLANG_OCL_PACKAGE_DEB};;
|
||||
("rpm")
|
||||
echo ${CLANG_OCL_PACKAGE_RPM};;
|
||||
(*)
|
||||
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
|
||||
esac
|
||||
exit
|
||||
}
|
||||
|
||||
case $TARGET in
|
||||
(clean) clean_clang-ocl ;;
|
||||
(build) build_clang-ocl ;;
|
||||
(outdir) print_output_directory ;;
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
echo "Operation complete"
|
||||
exit 0
|
||||
|
||||
@@ -1,151 +0,0 @@
|
||||
#!/bin/bash
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
|
||||
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 " -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 " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
|
||||
echo " -l, --link_llvm_static Link to LLVM statically. Default is to dynamically link to LLVM; requires that LLVM dylibs are created."
|
||||
echo
|
||||
echo "Possible values for <type>:"
|
||||
echo " deb -> Debian format (default)"
|
||||
echo " rpm -> RPM format"
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
API_NAME=amd_comgr
|
||||
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/$API_NAME
|
||||
PACKAGE_PREFIX=$ROCM_INSTALL_PATH
|
||||
BUILD_TYPE=Debug
|
||||
MAKE_OPTS="$DASH_JAY CTEST_OUTPUT_ON_FAILURE=1 -C $BUILD_DIR"
|
||||
VERBOSE_OPTS="AMD_COMGR_EMIT_VERBOSE_LOGS=1 AMD_COMGR_REDIRECT_LOGS=stdout"
|
||||
SHARED_LIBS="ON"
|
||||
CLEAN_OR_OUT=0;
|
||||
PKGTYPE="deb"
|
||||
MAKETARGET="deb"
|
||||
|
||||
LINK_LLVM_DYLIB="OFF"
|
||||
|
||||
VALID_STR=`getopt -o hcraslo:p: --long help,clean,release,address_sanitizer,static,link_llvm_static,outdir:,package: -- "$@"`
|
||||
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_asan_env_vars
|
||||
set_address_sanitizer_on ; shift ;;
|
||||
(-s | --static)
|
||||
SHARED_LIBS="OFF" ; shift ;;
|
||||
(-l | --link_llvm_static)
|
||||
LINK_LLVM_DYLIB="OFF"; 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 $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 $PROJ_NAME"
|
||||
|
||||
mkdir -p "$BUILD_DIR"
|
||||
pushd "$BUILD_DIR"
|
||||
if [ "$SHARED_LIBS" == "OFF" ]
|
||||
then
|
||||
echo " Building Archive "
|
||||
else
|
||||
echo " Building Shared Object "
|
||||
fi
|
||||
|
||||
cmake \
|
||||
$(rocm_cmake_params) \
|
||||
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DCMAKE_DISABLE_FIND_PACKAGE_hip=TRUE \
|
||||
-DCMAKE_CTEST_ARGUMENTS="--exclude-regex;multithread_test" \
|
||||
-DLLVM_LINK_LLVM_DYLIB=$LINK_LLVM_DYLIB \
|
||||
-DLLVM_ENABLE_LIBCXX=$LINK_LLVM_DYLIB \
|
||||
$COMGR_ROOT
|
||||
|
||||
popd
|
||||
cmake --build "$BUILD_DIR" -- $MAKE_OPTS
|
||||
cmake --build "$BUILD_DIR" -- $MAKE_OPTS $VERBOSE_OPTS test
|
||||
cmake --build "$BUILD_DIR" -- $MAKE_OPTS install
|
||||
cmake --build "$BUILD_DIR" -- $MAKE_OPTS package
|
||||
|
||||
mkdir -p $PACKAGE_LIB
|
||||
cp -R $BUILD_DIR/${LIB_NAME}* $PACKAGE_LIB
|
||||
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" $BUILD_DIR/comgr*.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" $BUILD_DIR/comgr*.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 ;;
|
||||
(outdir) print_output_directory ;;
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
echo "Operation complete"
|
||||
@@ -1,185 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -ex
|
||||
|
||||
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
|
||||
|
||||
set_component_src composable_kernel
|
||||
|
||||
build_miopen_ck() {
|
||||
echo "Start Building Composable Kernel"
|
||||
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
|
||||
set_asan_env_vars
|
||||
set_address_sanitizer_on
|
||||
fi
|
||||
|
||||
cd $COMPONENT_SRC
|
||||
mkdir "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
else
|
||||
GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
|
||||
fi
|
||||
|
||||
if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
|
||||
cmake -DBUILD_DEV=OFF \
|
||||
-DCMAKE_BUILD_TYPE=${BUILD_TYPE:-'RelWithDebInfo'} \
|
||||
-DCMAKE_CXX_COMPILER=${ROCM_PATH}/llvm/bin/clang++ \
|
||||
-DCMAKE_CXX_FLAGS=" -O3 " \
|
||||
-DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}/lib/cmake;${ROCM_PATH%-*}/$ASAN_LIBDIR;${ROCM_PATH%-*}/llvm;${ROCM_PATH%-*}" \
|
||||
-DCMAKE_SHARED_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_LIB_RPATH" \
|
||||
-DCMAKE_EXE_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_EXE_RPATH" \
|
||||
-DCMAKE_VERBOSE_MAKEFILE=1 \
|
||||
-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
|
||||
-DCMAKE_INSTALL_PREFIX=${ROCM_PATH} \
|
||||
-DCMAKE_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
|
||||
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
|
||||
-DROCM_SYMLINK_LIBS=OFF \
|
||||
-DCPACK_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
|
||||
-DROCM_DISABLE_LDCONFIG=ON \
|
||||
-DROCM_PATH=${ROCM_PATH} \
|
||||
-DCPACK_GENERATOR="${PKGTYPE^^}" \
|
||||
${LAUNCHER_FLAGS} \
|
||||
-DINSTANCES_ONLY=ON \
|
||||
-DENABLE_ASAN_PACKAGING=true \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
"$COMPONENT_SRC"
|
||||
else
|
||||
cmake -DBUILD_DEV=OFF \
|
||||
-DCMAKE_BUILD_TYPE=Release \
|
||||
-DCMAKE_CXX_COMPILER=${ROCM_PATH}/llvm/bin/clang++ \
|
||||
-DCMAKE_CXX_FLAGS=" -O3 " \
|
||||
-DCMAKE_PREFIX_PATH=${ROCM_PATH%-*} \
|
||||
-DCMAKE_SHARED_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN' \
|
||||
-DCMAKE_EXE_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN/../lib' \
|
||||
-DCMAKE_VERBOSE_MAKEFILE=1 \
|
||||
-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
|
||||
-DCMAKE_INSTALL_PREFIX=${ROCM_PATH} \
|
||||
-DCMAKE_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
|
||||
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
|
||||
-DROCM_SYMLINK_LIBS=OFF \
|
||||
-DCPACK_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
|
||||
-DROCM_DISABLE_LDCONFIG=ON \
|
||||
-DROCM_PATH=${ROCM_PATH} \
|
||||
-DCPACK_GENERATOR="${PKGTYPE^^}" \
|
||||
${LAUNCHER_FLAGS} \
|
||||
-DINSTANCES_ONLY=ON \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
"$COMPONENT_SRC"
|
||||
fi
|
||||
|
||||
cmake --build . -- -j${PROC} package
|
||||
cmake --build "$BUILD_DIR" -- install
|
||||
mkdir -p $PACKAGE_DIR && cp ./*.${PKGTYPE} $PACKAGE_DIR
|
||||
rm -rf *
|
||||
}
|
||||
|
||||
unset_asan_env_vars() {
|
||||
ASAN_CMAKE_PARAMS="false"
|
||||
export ADDRESS_SANITIZER="OFF"
|
||||
export LD_LIBRARY_PATH=""
|
||||
export ASAN_OPTIONS=""
|
||||
}
|
||||
|
||||
set_address_sanitizer_off() {
|
||||
export CFLAGS=""
|
||||
export CXXFLAGS=""
|
||||
export LDFLAGS=""
|
||||
}
|
||||
|
||||
build_miopen_ckProf() {
|
||||
ENABLE_ADDRESS_SANITIZER=false
|
||||
echo "Start Building Composable Kernel Profiler"
|
||||
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
|
||||
set_asan_env_vars
|
||||
set_address_sanitizer_on
|
||||
else
|
||||
unset_asan_env_vars
|
||||
set_address_sanitizer_off
|
||||
fi
|
||||
|
||||
cd $COMPONENT_SRC
|
||||
cd "$BUILD_DIR"
|
||||
rm -rf *
|
||||
|
||||
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 ${architectures}
|
||||
do
|
||||
if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
|
||||
cmake -DBUILD_DEV=OFF \
|
||||
-DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}/lib/cmake;${ROCM_PATH%-*}/$ASAN_LIBDIR;${ROCM_PATH%-*}/llvm;${ROCM_PATH%-*}" \
|
||||
-DCMAKE_BUILD_TYPE=${BUILD_TYPE:-'RelWithDebInfo'} \
|
||||
-DCMAKE_SHARED_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_LIB_RPATH" \
|
||||
-DCMAKE_EXE_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_EXE_RPATH" \
|
||||
-DCMAKE_VERBOSE_MAKEFILE=1 \
|
||||
-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
|
||||
-DCMAKE_INSTALL_PREFIX="${ROCM_PATH}" \
|
||||
-DCMAKE_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
|
||||
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
|
||||
-DROCM_SYMLINK_LIBS=OFF \
|
||||
-DCPACK_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
|
||||
-DROCM_DISABLE_LDCONFIG=ON \
|
||||
-DROCM_PATH="${ROCM_PATH}" \
|
||||
-DCPACK_GENERATOR="${PKGTYPE^^}" \
|
||||
-DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
|
||||
-DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
|
||||
${LAUNCHER_FLAGS} \
|
||||
-DPROFILER_ONLY=ON \
|
||||
-DENABLE_ASAN_PACKAGING=true \
|
||||
-DGPU_ARCH="${arch}" \
|
||||
"$COMPONENT_SRC"
|
||||
else
|
||||
cmake -DBUILD_DEV=OFF \
|
||||
-DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}" \
|
||||
-DCMAKE_BUILD_TYPE=Release \
|
||||
-DCMAKE_SHARED_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN' \
|
||||
-DCMAKE_EXE_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN/../lib' \
|
||||
-DCMAKE_VERBOSE_MAKEFILE=1 \
|
||||
-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
|
||||
-DCMAKE_INSTALL_PREFIX="${ROCM_PATH}" \
|
||||
-DCMAKE_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
|
||||
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
|
||||
-DROCM_SYMLINK_LIBS=OFF \
|
||||
-DCPACK_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
|
||||
-DROCM_DISABLE_LDCONFIG=ON \
|
||||
-DROCM_PATH="${ROCM_PATH}" \
|
||||
-DCPACK_GENERATOR="${PKGTYPE^^}" \
|
||||
-DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
|
||||
-DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
|
||||
${LAUNCHER_FLAGS} \
|
||||
-DPROFILER_ONLY=ON \
|
||||
-DGPU_ARCH="${arch}" \
|
||||
"$COMPONENT_SRC"
|
||||
fi
|
||||
|
||||
cmake --build . -- -j${PROC} package
|
||||
cp ./*ckprofiler*.${PKGTYPE} $PACKAGE_DIR
|
||||
rm -rf *
|
||||
done
|
||||
rm -rf _CPack_Packages/ && find -name '*.o' -delete
|
||||
|
||||
echo "Finished building Composable Kernel"
|
||||
show_build_cache_stats
|
||||
}
|
||||
|
||||
clean_miopen_ck() {
|
||||
echo "Cleaning MIOpen-CK build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
|
||||
rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
|
||||
echo "Done!"
|
||||
}
|
||||
|
||||
stage2_command_args "$@"
|
||||
|
||||
case $TARGET in
|
||||
build) build_miopen_ck; build_miopen_ckProf;;
|
||||
outdir) print_output_directory ;;
|
||||
clean) clean_miopen_ck ;;
|
||||
*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
@@ -1,159 +0,0 @@
|
||||
#!/bin/bash
|
||||
source "${BASH_SOURCE%/*}/compute_utils.sh"
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: $(basename "${BASH_SOURCE[0]}") [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 " --enable-assertions Enable assertions"
|
||||
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 " -M, --skip_man_pages Do not build the 'docs' target"
|
||||
echo " -s, --static Supports static CI by accepting this param & not bailing out. No effect of the param though"
|
||||
echo
|
||||
echo "Possible values for <type>:"
|
||||
echo " deb -> Debian format (default)"
|
||||
echo " rpm -> RPM format"
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
API_NAME=rocm-dbgapi
|
||||
AMD_DBGAPI_NAME=amd-dbgapi
|
||||
MAKEINSTALL_MANIFEST=makeinstall_manifest.txt
|
||||
PROJ_NAME=$API_NAME
|
||||
LIB_NAME=lib${API_NAME}.so
|
||||
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/$API_NAME
|
||||
BUILD_TYPE=Debug
|
||||
MAKE_OPTS=($DASH_JAY -C "$BUILD_DIR")
|
||||
SHARED_LIBS="ON"
|
||||
CLEAN_OR_OUT=0;
|
||||
MAKETARGET="deb"
|
||||
PKGTYPE="deb"
|
||||
DODOCSBUILD=true
|
||||
|
||||
VALID_STR=$(getopt -o hcraso:p:M --long help,clean,release,enable-assertions,static,address_sanitizer,outdir:,package:skip_man_pages -- "$@")
|
||||
eval set -- "$VALID_STR"
|
||||
|
||||
while true ;
|
||||
do
|
||||
case "$1" in
|
||||
(-h | --help)
|
||||
printUsage ; exit 0;;
|
||||
(-c | --clean)
|
||||
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ;;
|
||||
(-r | --release)
|
||||
ENABLE_ASSERTIONS=${ENABLE_ASSERTIONS:-"Off"} ;
|
||||
BUILD_TYPE="RelWithDebInfo" ;;
|
||||
( --enable-assertions)
|
||||
ENABLE_ASSERTIONS="On" ;;
|
||||
(-a | --address_sanitizer)
|
||||
set_asan_env_vars
|
||||
set_address_sanitizer_on ;;
|
||||
(-s | --static)
|
||||
SHARED_LIBS="OFF" ;;
|
||||
(-o | --outdir)
|
||||
TARGET="outdir"; PKGTYPE=$2 ; ((CLEAN_OR_OUT|=2)) ; shift 1 ;;
|
||||
(-M | --skip_man_pages) DODOCSBUILD=false;;
|
||||
(-p | --package)
|
||||
MAKETARGET="$2" ; shift 1;;
|
||||
--) shift; break;;
|
||||
(*)
|
||||
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
|
||||
esac
|
||||
shift
|
||||
|
||||
done
|
||||
|
||||
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 $PROJ_NAME"
|
||||
if [ -e "$BUILD_DIR/$MAKEINSTALL_MANIFEST" ] ; then
|
||||
xargs rm -f < "$BUILD_DIR/$MAKEINSTALL_MANIFEST"
|
||||
fi
|
||||
rm -rf "$BUILD_DIR"
|
||||
rm -rf "$PACKAGE_DEB"
|
||||
rm -rf "$PACKAGE_RPM"
|
||||
rm -rf "${PACKAGE_ROOT:?}/${PROJ_NAME}"
|
||||
rm -rf "${PACKAGE_LIB:?}/${LIB_NAME}"*
|
||||
rm -rf "${PACKAGE_LIB:?}/cmake/${AMD_DBGAPI_NAME}"
|
||||
rm -rf "${PACKAGE_INCLUDE:?}/${AMD_DBGAPI_NAME}"
|
||||
}
|
||||
|
||||
build() {
|
||||
if [ ! -e "$ROCM_DBGAPI_ROOT/CMakeLists.txt" ]
|
||||
then
|
||||
echo " No $ROCM_DBGAPI_ROOT/CMakeLists.txt file, skipping rocm-dbgapi" >&2
|
||||
echo " No $ROCM_DBGAPI_ROOT/CMakeLists.txt file, skipping rocm-dbgapi"
|
||||
exit 0
|
||||
fi
|
||||
echo "Building $PROJ_NAME"
|
||||
|
||||
mkdir -p "$BUILD_DIR"
|
||||
pushd "$BUILD_DIR" || exit 99
|
||||
|
||||
cmake \
|
||||
$(rocm_cmake_params) \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DENABLE_ASSERTIONS=${ENABLE_ASSERTIONS:-"On"} \
|
||||
"$ROCM_DBGAPI_ROOT"
|
||||
|
||||
popd || exit 99
|
||||
cmake --build "$BUILD_DIR" -- "${MAKE_OPTS[@]}"
|
||||
"$DODOCSBUILD" && cmake --build "$BUILD_DIR" -- "${MAKE_OPTS[@]}" doc
|
||||
cmake --build "$BUILD_DIR" -- "${MAKE_OPTS[@]}" install
|
||||
|
||||
mv "$BUILD_DIR/install_manifest.txt" "$BUILD_DIR/$MAKEINSTALL_MANIFEST"
|
||||
cmake --build "$BUILD_DIR" -- "${MAKE_OPTS[@]}" package
|
||||
|
||||
mkdir -p "$PACKAGE_LIB"
|
||||
(
|
||||
shopt -s nullglob
|
||||
cp -R "$BUILD_DIR/lib/${LIB_NAME}"* "$BUILD_DIR/${LIB_NAME}"* "$PACKAGE_LIB"
|
||||
)
|
||||
|
||||
copy_if DEB "${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 ;;
|
||||
(outdir) print_output_directory ;;
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
echo "Operation complete"
|
||||
@@ -1,140 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
|
||||
echo
|
||||
echo "Options:"
|
||||
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 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 " -h, --help Prints this help"
|
||||
echo
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
PACKAGE_ROOT="$(getPackageRoot)"
|
||||
PACKAGE_BIN="$(getBinPath)"
|
||||
PACKAGE_LIB="$(getLibPath)"
|
||||
BUILD_PATH="$(getBuildPath devicelibs)"
|
||||
INSTALL_PATH="$(getPackageRoot)"
|
||||
LIGHTNING_BUILD_PATH="$(getBuildPath lightning)"
|
||||
DEB_PATH="$(getDebPath devicelibs)"
|
||||
RPM_PATH="$(getRpmPath devicelibs)"
|
||||
AMDGCN_LIB_PATH="$PACKAGE_ROOT/amdgcn/bitcode/"
|
||||
|
||||
TARGET="build"
|
||||
MAKEOPTS="$DASH_JAY"
|
||||
SHARED_LIBS="ON"
|
||||
CLEAN_OR_OUT=0;
|
||||
PKGTYPE="deb"
|
||||
MAKETARGET="deb"
|
||||
|
||||
VALID_STR=`getopt -o hcraso: --long help,clean,release,static,address_sanitizer,outdir: -- "$@"`
|
||||
eval set -- "$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)
|
||||
ASAN_CMAKE_PARAMS="true"
|
||||
ack_and_ignore_asan ; shift ;;
|
||||
(-s | --static)
|
||||
SHARED_LIBS="OFF" ; shift ;;
|
||||
(-o | --outdir)
|
||||
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=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 $RET_CONFLICT
|
||||
fi
|
||||
|
||||
|
||||
clean_devicelibs() {
|
||||
rm -rf "$BUILD_PATH"
|
||||
rm -f $PACKAGE_LIB/hc*.bc
|
||||
rm -f $PACKAGE_LIB/irif*.bc
|
||||
rm -f $PACKAGE_LIB/ockl*.bc
|
||||
rm -f $PACKAGE_LIB/oclc*.bc
|
||||
rm -f $PACKAGE_LIB/ocml*.bc
|
||||
rm -f $PACKAGE_LIB/opencl*.bc
|
||||
rm -f $PACKAGE_LIB/openmp*.bc
|
||||
rm -rf $PACKAGE_ROOT/amdgcn
|
||||
rm -rf "$DEB_PATH"
|
||||
rm -rf "$RPM_PATH"
|
||||
}
|
||||
|
||||
build_devicelibs() {
|
||||
mkdir -p "$BUILD_PATH"
|
||||
pushd "$BUILD_PATH"
|
||||
|
||||
local clangResourceDir="$($LIGHTNING_BUILD_PATH/bin/clang -print-resource-dir)"
|
||||
local clangResourceVer=${clangResourceDir#*lib/clang/}
|
||||
local bitcodeInstallLoc="lib/llvm/lib/clang/${clangResourceVer}/lib"
|
||||
|
||||
export LLVM_BUILD="$LIGHTNING_BUILD_PATH"
|
||||
if [ ! -e Makefile ]; then
|
||||
cmake $(rocm_cmake_params) \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DROCM_DEVICE_LIBS_BITCODE_INSTALL_LOC_NEW="$bitcodeInstallLoc/amdgcn" \
|
||||
-DROCM_DEVICE_LIBS_BITCODE_INSTALL_LOC_OLD="amdgcn" \
|
||||
"$DEVICELIBS_ROOT"
|
||||
|
||||
echo "CMake complete"
|
||||
fi
|
||||
|
||||
echo "Building device-libs"
|
||||
cmake --build . -- $MAKEOPTS
|
||||
cmake --build . -- $MAKEOPTS install
|
||||
popd
|
||||
}
|
||||
|
||||
package_devicelibs() {
|
||||
mkdir -p "$DEB_PATH"
|
||||
mkdir -p "$RPM_PATH"
|
||||
pushd "$BUILD_PATH"
|
||||
cpack
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$DEB_PATH" *.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$RPM_PATH" *.rpm
|
||||
popd
|
||||
}
|
||||
|
||||
print_output_directory() {
|
||||
case ${PKGTYPE} in
|
||||
("deb")
|
||||
echo ${DEB_PATH};;
|
||||
("rpm")
|
||||
echo ${RPM_PATH};;
|
||||
(*)
|
||||
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
|
||||
esac
|
||||
exit
|
||||
}
|
||||
case $TARGET in
|
||||
(clean) clean_devicelibs ;;
|
||||
(build) build_devicelibs; package_devicelibs ;;
|
||||
(outdir) print_output_directory ;;
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
echo "Operation complete"
|
||||
@@ -1,46 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -ex
|
||||
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
|
||||
|
||||
set_component_src half
|
||||
|
||||
build_half() {
|
||||
echo "Start build"
|
||||
|
||||
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
|
||||
set_asan_env_vars
|
||||
set_address_sanitizer_on
|
||||
ASAN_CMAKE_PARAMS="false"
|
||||
fi
|
||||
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
|
||||
cmake \
|
||||
-DCMAKE_INSTALL_PREFIX="$ROCM_PATH" \
|
||||
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
|
||||
"$COMPONENT_SRC"
|
||||
|
||||
cmake --build "$BUILD_DIR" -- -j${PROC}
|
||||
cmake --build "$BUILD_DIR" -- package
|
||||
cmake --build "$BUILD_DIR" -- install
|
||||
|
||||
rm -rf _CPack_Packages/ && find -name '*.o' -delete
|
||||
mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
|
||||
|
||||
show_build_cache_stats
|
||||
}
|
||||
|
||||
clean_half() {
|
||||
echo "Cleaning half build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
|
||||
rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
|
||||
echo "Done!"
|
||||
}
|
||||
|
||||
stage2_command_args "$@"
|
||||
|
||||
case $TARGET in
|
||||
build) build_half ;;
|
||||
outdir) print_output_directory ;;
|
||||
clean) clean_half ;;
|
||||
*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
@@ -1,295 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
|
||||
echo
|
||||
echo "Options:"
|
||||
echo " -h, --help Prints this help"
|
||||
echo " -c, --clean Clean output and delete all intermediate work"
|
||||
echo " -r, --release Make a release build instead of a debug build"
|
||||
echo " -a, --address_sanitizer Enable address sanitizer"
|
||||
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
|
||||
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of type referred to by pkg_type"
|
||||
echo " -t, --offload-arch=<arch> Specify arch for catch tests ex: --offload-arch=gfx1030 --offload-arch=gfx1100"
|
||||
echo " -p, --package <type> Specify packaging format"
|
||||
echo
|
||||
echo "Possible values for <type>:"
|
||||
echo " deb -> Debian format (default)"
|
||||
echo " rpm -> RPM format"
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
MAKEOPTS="$DASH_JAY"
|
||||
|
||||
BUILD_PATH="$(getBuildPath hip-on-rocclr)"
|
||||
|
||||
TARGET="build"
|
||||
PACKAGE_ROOT="$(getPackageRoot)"
|
||||
PACKAGE_SRC="$(getSrcPath)"
|
||||
PACKAGE_DEB="$PACKAGE_ROOT/deb/hip-on-rocclr"
|
||||
PACKAGE_RPM="$PACKAGE_ROOT/rpm/hip-on-rocclr"
|
||||
PREFIX_PATH="$PACKAGE_ROOT"
|
||||
CORE_BUILD_DIR="$(getBuildPath hsa-core)"
|
||||
ROCclr_BUILD_DIR="$(getBuildPath rocclr)"
|
||||
HIPCC_BUILD_DIR="$(getBuildPath hipcc)"
|
||||
CATCH_BUILD_DIR="$(getBuildPath catch)"
|
||||
CATCH_SRC="$HIP_CATCH_TESTS_ROOT/catch"
|
||||
SAMPLES_SRC="$HIP_CATCH_TESTS_ROOT/samples"
|
||||
SAMPLES_BUILD_DIR="$(getBuildPath samples)"
|
||||
if [ ! -e "$CATCH_SRC/CMakeLists.txt" ]; then
|
||||
echo "Using catch source from hip project" >&2
|
||||
CATCH_SRC="$HIP_ON_ROCclr_ROOT/tests/catch"
|
||||
fi
|
||||
|
||||
BUILD_TYPE="Debug"
|
||||
SHARED_LIBS="ON"
|
||||
CLEAN_OR_OUT=0;
|
||||
MAKETARGET="deb"
|
||||
PKGTYPE="deb"
|
||||
OFFLOAD_ARCH=()
|
||||
|
||||
DEFAULT_OFFLOAD_ARCH=(gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942 gfx1030 gfx1031 gfx1033 gfx1034 gfx1035 gfx1100 gfx1101 gfx1102 gfx1103)
|
||||
|
||||
VALID_STR=`getopt -o hcrast:o: --long help,clean,release,address_sanitizer,static,offload-arch=:,outdir: -- "$@"`
|
||||
eval set -- "$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_asan_env_vars
|
||||
set_address_sanitizer_on ; shift ;;
|
||||
(-s | --static)
|
||||
SHARED_LIBS="OFF" ; shift ;;
|
||||
(-t | --offload-arch=)
|
||||
OFFLOAD_ARCH+=( "$2" ); ((CLEAN_OR_OUT|=2)); shift 2 ;;
|
||||
(-o | --outdir)
|
||||
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
|
||||
--) shift; break;;
|
||||
|
||||
(*)
|
||||
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
|
||||
esac
|
||||
|
||||
done
|
||||
|
||||
if [ ${#OFFLOAD_ARCH[@]} = 0 ] ; then
|
||||
OFFLOAD_ARCH=( "${DEFAULT_OFFLOAD_ARCH[@]}" )
|
||||
else
|
||||
echo "Using user defined offload archs ${OFFLOAD_ARCH[@]} for catch tests";
|
||||
fi
|
||||
printf -v OFFLOAD_ARCH_STR -- '--offload-arch=%q ' "${OFFLOAD_ARCH[@]}"
|
||||
|
||||
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 $RET_CONFLICT
|
||||
fi
|
||||
|
||||
clean_hip_on_rocclr() {
|
||||
rm -rf "$BUILD_PATH"
|
||||
rm -rf "$PACKAGE_DEB"
|
||||
rm -rf "$PACKAGE_RPM"
|
||||
rm -rf "$OUT_DIR/hip"
|
||||
}
|
||||
|
||||
build_hip_on_rocclr() {
|
||||
if [ -e "$CLR_ROOT/CMakeLists.txt" ]; then
|
||||
_HIP_CMAKELIST_DIR="$CLR_ROOT"
|
||||
_HIP_CMAKELIST_OPT="-DCLR_BUILD_HIP=ON -DCLR_BUILD_OCL=OFF"
|
||||
if [ -e "$HIPOTHER_ROOT/hipnv" ]; then
|
||||
_HIP_CMAKELIST_OPT="$_HIP_CMAKELIST_OPT -DHIPNV_DIR=$HIPOTHER_ROOT/hipnv"
|
||||
fi
|
||||
elif [ ! -e "$HIPAMD_ROOT/CMakeLists.txt" ]; then
|
||||
echo "No $HIPAMD_ROOT/CMakeLists.txt file, skipping hip on rocclr" >&2
|
||||
echo "No $HIPAMD_ROOT/CMakeLists.txt file, skipping hip on rocclr"
|
||||
exit 0
|
||||
else
|
||||
_HIP_CMAKELIST_DIR="$HIPAMD_ROOT"
|
||||
_HIP_CMAKELIST_OPT=""
|
||||
fi
|
||||
|
||||
echo "$_HIP_CMAKELIST_DIR"
|
||||
mkdir -p "$BUILD_PATH"
|
||||
pushd "$BUILD_PATH"
|
||||
|
||||
if [ ! -e Makefile ]; then
|
||||
echo "Building HIP-On-ROCclr CMake environment"
|
||||
print_lib_type $SHARED_LIBS
|
||||
|
||||
cmake $(rocm_cmake_params) \
|
||||
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
|
||||
-DHIP_COMPILER=clang \
|
||||
-DHIP_PLATFORM=amd \
|
||||
-DHIP_COMMON_DIR="$HIP_ON_ROCclr_ROOT" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DCMAKE_HIP_ARCHITECTURES=OFF \
|
||||
-DHSA_PATH="$ROCM_INSTALL_PATH" \
|
||||
-DCMAKE_SKIP_BUILD_RPATH=TRUE \
|
||||
-DCPACK_INSTALL_PREFIX="$ROCM_INSTALL_PATH" \
|
||||
-DROCM_PATH="$ROCM_INSTALL_PATH" \
|
||||
-DHIPCC_BIN_DIR="$HIPCC_BUILD_DIR" \
|
||||
-DHIP_CATCH_TEST=1 \
|
||||
$_HIP_CMAKELIST_OPT \
|
||||
"$_HIP_CMAKELIST_DIR"
|
||||
|
||||
echo "CMake complete"
|
||||
fi
|
||||
|
||||
echo "Build and Install HIP"
|
||||
cmake --build . -- $MAKEOPTS install "VERBOSE=1"
|
||||
|
||||
popd
|
||||
}
|
||||
|
||||
build_catch_tests() {
|
||||
WORKSPACE=`pwd`
|
||||
echo "Build catch2 tests independently"
|
||||
if [ ! -e "$CATCH_SRC/CMakeLists.txt" ]; then
|
||||
echo "catch source not found: $CATCH_SRC" >&2
|
||||
exit
|
||||
fi
|
||||
# build catch
|
||||
rm -rf "$CATCH_BUILD_DIR"
|
||||
mkdir -p "$CATCH_BUILD_DIR"
|
||||
pushd "$CATCH_BUILD_DIR"
|
||||
export HIP_PATH="$ROCM_INSTALL_PATH"
|
||||
export ROCM_PATH="$ROCM_INSTALL_PATH"
|
||||
cmake \
|
||||
-DCMAKE_BUILD_TYPE="${BUILD_TYPE}" \
|
||||
-DHIP_PLATFORM=amd \
|
||||
-DROCM_PATH="$ROCM_INSTALL_PATH" \
|
||||
-DOFFLOAD_ARCH_STR="$OFFLOAD_ARCH_STR" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DCPACK_RPM_DEBUGINFO_PACKAGE=FALSE \
|
||||
-DCPACK_DEBIAN_DEBUGINFO_PACKAGE=FALSE \
|
||||
-DCPACK_INSTALL_PREFIX="$ROCM_INSTALL_PATH" \
|
||||
"$CATCH_SRC"
|
||||
|
||||
|
||||
make $MAKEOPTS build_tests
|
||||
echo "Packaging catch tests"
|
||||
make $MAKEOPTS package_test
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" *.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" *.rpm
|
||||
popd
|
||||
}
|
||||
|
||||
package_samples() {
|
||||
if [ "$ASAN_CMAKE_PARAMS" == "true" ] ; then
|
||||
echo "Disable the packaging of HIP samples" >&2
|
||||
return
|
||||
fi
|
||||
WORKSPACE=`pwd`
|
||||
if [ ! -e "$SAMPLES_SRC/CMakeLists.txt" ]; then
|
||||
echo "HIP samples source not found at: $SAMPLES_SRC" >&2
|
||||
echo "Using samples package from hip project: $BUILD_PATH" >&2
|
||||
return
|
||||
fi
|
||||
|
||||
rm -rf "$SAMPLES_BUILD_DIR"
|
||||
mkdir -p "$SAMPLES_BUILD_DIR"
|
||||
pushd "$SAMPLES_BUILD_DIR"
|
||||
local CMAKE_PATH="$(getCmakePath)"
|
||||
export HIP_PATH="$ROCM_INSTALL_PATH"
|
||||
export ROCM_PATH="$ROCM_INSTALL_PATH"
|
||||
cmake \
|
||||
-DROCM_PATH="$ROCM_INSTALL_PATH" \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DCMAKE_MODULE_PATH="$CMAKE_PATH/hip" \
|
||||
-DCPACK_INSTALL_PREFIX="$ROCM_INSTALL_PATH" \
|
||||
"$SAMPLES_SRC"
|
||||
echo "Packaging hip samples from hip-tests project"
|
||||
make $MAKEOPTS package_samples
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" *.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" *.rpm
|
||||
popd
|
||||
}
|
||||
|
||||
clean_hip_tests(){
|
||||
rm -rf "$CATCH_BUILD_DIR"
|
||||
rm -rf "$PACKAGE_SRC/hip-on-rocclr"
|
||||
rm -rf "$PACKAGE_SRC/hipamd"
|
||||
rm -rf "$PACKAGE_SRC/rocclr"
|
||||
rm -rf "$PACKAGE_SRC/opencl-on-rocclr"
|
||||
rm -rf "$PACKAGE_SRC/clr"
|
||||
rm -rf "$PACKAGE_SRC/hip-tests"
|
||||
rm -rf "$PACKAGE_SRC/hipother"
|
||||
}
|
||||
copy_hip_tests() {
|
||||
clean_hip_tests
|
||||
|
||||
echo "Copy HIP & ROCclr Source and tests"
|
||||
|
||||
mkdir -p "$PACKAGE_SRC/hip-on-rocclr"
|
||||
echo "Copying hip-on-rocclr"
|
||||
progressCopy "$HIP_ON_ROCclr_ROOT" "$PACKAGE_SRC/hip-on-rocclr"
|
||||
|
||||
if [ -e "$CLR_ROOT/CMakeLists.txt" ]; then
|
||||
mkdir -p "$PACKAGE_SRC/clr"
|
||||
echo "Copying clr"
|
||||
progressCopy "$CLR_ROOT" "$PACKAGE_SRC/clr"
|
||||
else
|
||||
mkdir -p "$PACKAGE_SRC/hipamd"
|
||||
mkdir -p "$PACKAGE_SRC/rocclr"
|
||||
mkdir -p "$PACKAGE_SRC/opencl-on-rocclr"
|
||||
echo "Copying hipamd"
|
||||
progressCopy "$HIPAMD_ROOT" "$PACKAGE_SRC/hipamd"
|
||||
echo "Copying rocclr"
|
||||
progressCopy "$ROCclr_ROOT" "$PACKAGE_SRC/rocclr"
|
||||
echo "Copying opencl-on-rocclr"
|
||||
progressCopy "$OPENCL_ON_ROCclr_ROOT" "$PACKAGE_SRC/opencl-on-rocclr"
|
||||
fi
|
||||
|
||||
if [ -e "$HIPOTHER_ROOT/hipnv" ]; then
|
||||
mkdir -p "$PACKAGE_SRC/hipother"
|
||||
echo "Copying hipother"
|
||||
progressCopy "$HIPOTHER_ROOT" "$PACKAGE_SRC/hipother"
|
||||
fi
|
||||
|
||||
mkdir -p "$PACKAGE_SRC/hip-tests"
|
||||
echo "Copying hip-tests"
|
||||
progressCopy "$HIP_CATCH_TESTS_ROOT" "$PACKAGE_SRC/hip-tests"
|
||||
}
|
||||
|
||||
package_hip_on_rocclr()
|
||||
{
|
||||
echo "Packagin HIP-on-ROCclr"
|
||||
pushd "$BUILD_PATH"
|
||||
cmake --build . -- $MAKEOPTS package
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" *.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" *.rpm
|
||||
popd
|
||||
}
|
||||
|
||||
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
|
||||
}
|
||||
|
||||
case $TARGET in
|
||||
(clean) clean_hip_on_rocclr; clean_hip_tests ;;
|
||||
(build) build_hip_on_rocclr; build_catch_tests; package_hip_on_rocclr; package_samples; copy_hip_tests;;
|
||||
(outdir) print_output_directory ;;
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
echo "Operation complete"
|
||||
@@ -1,65 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -ex
|
||||
|
||||
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
|
||||
|
||||
set_component_src hipBLAS
|
||||
|
||||
build_hipblas() {
|
||||
echo "Start build"
|
||||
|
||||
CXX="g++"
|
||||
CLIENTS_SAMPLES="ON"
|
||||
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
|
||||
set_asan_env_vars
|
||||
set_address_sanitizer_on
|
||||
CLIENTS_SAMPLES="OFF"
|
||||
fi
|
||||
|
||||
echo "C compiler: $CC"
|
||||
echo "CXX compiler: $CXX"
|
||||
echo "FC compiler: $FC"
|
||||
|
||||
cd $COMPONENT_SRC
|
||||
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
|
||||
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
|
||||
rebuild_lapack
|
||||
fi
|
||||
|
||||
cmake \
|
||||
${LAUNCHER_FLAGS} \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DUSE_CUDA=OFF \
|
||||
-DBUILD_CLIENTS_TESTS=ON \
|
||||
-DBUILD_CLIENTS_BENCHMARKS=ON \
|
||||
-DBUILD_CLIENTS_SAMPLES="${CLIENTS_SAMPLES}" \
|
||||
-DCPACK_SET_DESTDIR=OFF \
|
||||
-DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \
|
||||
"$COMPONENT_SRC"
|
||||
|
||||
cmake --build "$BUILD_DIR" -- -j${PROC}
|
||||
cmake --build "$BUILD_DIR" -- install
|
||||
cmake --build "$BUILD_DIR" -- package
|
||||
|
||||
rm -rf _CPack_Packages/ && find -name '*.o' -delete
|
||||
mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
|
||||
|
||||
show_build_cache_stats
|
||||
}
|
||||
|
||||
clean_hipblas() {
|
||||
echo "Cleaning hipBLAS build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
|
||||
rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
|
||||
echo "Done!"
|
||||
}
|
||||
|
||||
stage2_command_args "$@"
|
||||
|
||||
case $TARGET in
|
||||
build) build_hipblas ;;
|
||||
outdir) print_output_directory ;;
|
||||
clean) clean_hipblas ;;
|
||||
*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
@@ -1,69 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -ex
|
||||
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
|
||||
|
||||
set_component_src hipBLASLt
|
||||
|
||||
build_hipblaslt() {
|
||||
echo "Start build"
|
||||
|
||||
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
|
||||
set_asan_env_vars
|
||||
set_address_sanitizer_on
|
||||
fi
|
||||
|
||||
cd $COMPONENT_SRC
|
||||
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
|
||||
|
||||
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
|
||||
rebuild_lapack
|
||||
fi
|
||||
|
||||
if [ -n "$GPU_ARCHS" ]; then
|
||||
GPU_TARGETS="$GPU_ARCHS"
|
||||
else
|
||||
# gfx90a:xnack+;gfx90a:xnack-;gfx940;gfx941;gfx942
|
||||
GPU_TARGETS=all
|
||||
fi
|
||||
|
||||
CXX=$(set_build_variables CXX)\
|
||||
cmake \
|
||||
-DAMDGPU_TARGETS=${GPU_TARGETS} \
|
||||
${LAUNCHER_FLAGS} \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DTensile_LOGIC= \
|
||||
-DTensile_CODE_OBJECT_VERSION=default \
|
||||
-DTensile_CPU_THREADS= \
|
||||
-DTensile_LIBRARY_FORMAT=msgpack \
|
||||
-DBUILD_CLIENTS_SAMPLES=ON \
|
||||
-DBUILD_CLIENTS_TESTS=ON \
|
||||
-DBUILD_CLIENTS_BENCHMARKS=ON \
|
||||
-DCPACK_SET_DESTDIR=OFF \
|
||||
-DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \
|
||||
"$COMPONENT_SRC"
|
||||
|
||||
cmake --build "$BUILD_DIR" -- -j${PROC}
|
||||
cmake --build "$BUILD_DIR" -- install
|
||||
cmake --build "$BUILD_DIR" -- package
|
||||
|
||||
rm -rf _CPack_Packages/ && find -name '*.o' -delete
|
||||
mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
|
||||
|
||||
show_build_cache_stats
|
||||
}
|
||||
|
||||
clean_hipblaslt() {
|
||||
echo "Cleaning hipBLASLt build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
|
||||
rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
|
||||
echo "Done!"
|
||||
}
|
||||
|
||||
stage2_command_args "$@"
|
||||
|
||||
case $TARGET in
|
||||
build) build_hipblaslt ;;
|
||||
outdir) print_output_directory ;;
|
||||
clean) clean_hipblaslt ;;
|
||||
*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
@@ -1,118 +0,0 @@
|
||||
#!/bin/bash
|
||||
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
|
||||
|
||||
|
||||
printUsage() {
|
||||
echo
|
||||
echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
|
||||
echo
|
||||
echo "Options:"
|
||||
echo " -a, --address_sanitizer Enable address sanitizer"
|
||||
echo " -c, --clean Clean output and delete all intermediate work"
|
||||
echo " -h, --help Prints this help"
|
||||
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
|
||||
type referred to by pkg_type"
|
||||
echo " -r, --release Makes a release build"
|
||||
echo
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
|
||||
API_NAME=hipcc
|
||||
PROJ_NAME=$API_NAME
|
||||
|
||||
TARGET="build"
|
||||
MAKEOPTS="$DASH_JAY"
|
||||
BUILD_TYPE="Debug"
|
||||
|
||||
BUILD_DIR=$(getBuildPath $API_NAME)
|
||||
PACKAGE_DEB=$(getPackageRoot)/deb/$API_NAME
|
||||
PACKAGE_RPM=$(getPackageRoot)/rpm/$API_NAME
|
||||
PACKAGE_SRC="$(getSrcPath)"
|
||||
|
||||
while [ "$1" != "" ];
|
||||
do
|
||||
case $1 in
|
||||
(-a | --address_sanitizer)
|
||||
ack_and_ignore_asan ;;
|
||||
(-c | --clean)
|
||||
TARGET="clean" ;;
|
||||
(-o | --outdir)
|
||||
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 1 ;;
|
||||
(-r | --release)
|
||||
BUILD_TYPE="RelWithDebInfo" ;;
|
||||
(-h | --help)
|
||||
printUsage ; exit 0 ;;
|
||||
(*)
|
||||
echo "Invalid option [$1]" >&2; printUsage; exit 1 ;;
|
||||
esac
|
||||
shift 1
|
||||
done
|
||||
|
||||
clean() {
|
||||
echo "Cleaning hipcc"
|
||||
rm -rf $BUILD_DIR
|
||||
|
||||
echo "Cleaning up hipcc DEB and RPM packages"
|
||||
rm -rf $PACKAGE_DEB
|
||||
rm -rf $PACKAGE_RPM
|
||||
}
|
||||
|
||||
copy_hipcc_sources() {
|
||||
echo "Clean up hipcc build folder"
|
||||
rm -rf "$PACKAGE_SRC/hipcc"
|
||||
echo "Copy hipcc sources"
|
||||
mkdir -p "$PACKAGE_SRC/hipcc"
|
||||
progressCopy "$HIPCC_ROOT" "$PACKAGE_SRC/hipcc"
|
||||
}
|
||||
|
||||
build() {
|
||||
echo "Build hipcc binary"
|
||||
mkdir -p "$BUILD_DIR"
|
||||
|
||||
pushd "$BUILD_DIR"
|
||||
if ! [ -e "$HIPCC_ROOT/CMakeLists.txt" ] ; then
|
||||
|
||||
echo "No source for hipcc, exiting. this is not an error" >&2
|
||||
exit 0
|
||||
fi
|
||||
|
||||
cmake \
|
||||
$(rocm_cmake_params) \
|
||||
$(rocm_common_cmake_params) \
|
||||
-DHIPCC_BACKWARD_COMPATIBILITY=OFF \
|
||||
-DCMAKE_INSTALL_PREFIX="$OUT_DIR" \
|
||||
$HIPCC_ROOT
|
||||
popd
|
||||
|
||||
cmake --build "$BUILD_DIR" -- $MAKEOPTS
|
||||
|
||||
echo "Installing and Packaging hipcc"
|
||||
cmake --build "$BUILD_DIR" -- $MAKEOPTS install
|
||||
cmake --build "$BUILD_DIR" -- $MAKEOPTS package
|
||||
|
||||
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" $BUILD_DIR/hipcc*.deb
|
||||
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" $BUILD_DIR/hipcc*.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
|
||||
}
|
||||
|
||||
case $TARGET in
|
||||
(clean) clean ;;
|
||||
(build) build ; copy_hipcc_sources ;;
|
||||
(outdir) print_output_directory ;;
|
||||
(*) die "Invalid target $TARGET" ;;
|
||||
esac
|
||||
|
||||
echo "Operation complete"
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user