Compare commits

..

35 Commits

Author SHA1 Message Date
Matt Williams
b3211cc6fa Updating broken link (#5258) 2025-09-05 16:02:13 -04:00
Peter Park
5853468fca Update PyTorch training benchmark docker doc to 25.7 (#5255) (#5260)
* Update PyTorch training benchmark docker doc to 25.7

* update .wordlist.txt

* update conf.py

* update data sheet

* fix sphinx warnings
2025-09-05 12:14:09 -04:00
Matt Williams
245c95690f Merge pull request #5228 from ROCm/cherry-pick-link-fix
Fix hyperlink syntax
2025-08-26 11:42:57 -04:00
Dominic Widdows
39c1b926f6 Fix hyperlink syntax 2025-08-26 11:35:30 -04:00
Jeffrey Novotny
3c3847f9f7 Merge pull request #5224 from amd-jnovotny/dlf-matt-docs643
Deep learning frameworks edits for scale (#5189)
2025-08-22 11:56:27 -04:00
Matt Williams
249bd177ec Deep learning frameworks edits for scale (#5189)
* Deep learning frameworks edits for scale

Based on https://ontrack-internal.amd.com/browse/ROCDOC-1809

* update table

table

* leo comments

* formatting

* format

* update table based on feedback

* header

* Update machine learning page

* headers

* Apply suggestions from code review

Co-authored-by: anisha-amd <anisha.sankar@amd.com>

* Update .wordlist.txt

* formatting

* Update docs/how-to/deep-learning-rocm.rst

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>

---------

Co-authored-by: Matt Williams <Matt.Williams+amdeng@amd.com>
Co-authored-by: anisha-amd <anisha.sankar@amd.com>
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
(cherry picked from commit 1d42f7cc62)
2025-08-22 11:52:32 -04:00
Peter Park
b2ee8d4b2e docs: Add Primus (Megatron) training Docker documentation (#5218) (#5222)
(cherry picked from commit 98029db4ee)
2025-08-22 09:02:40 -04:00
Peter Park
3f834cf520 Fix documented VRAM for Radeon AI Pro R9700 (#5203) (#5204)
(cherry picked from commit c154b7e0a3)
2025-08-18 10:20:22 -04:00
Peter Park
70ba866c5b vLLM inference benchmark doc: add missing data field (#5199) (#5200)
(cherry picked from commit 55d0a88ec5)
2025-08-15 13:52:51 -04:00
Peter Park
320ec4669a [docs/6.4.3] Update vLLM benchmark doc for 20250812 Docker release (#5196) (#5198)
(cherry picked from commit 7ee22790ce)
2025-08-14 15:51:58 -04:00
anisha-amd
c9bd93b537 [Docs] 6.4.3: compatibility matrix frameworks support update (#5186) 2025-08-12 14:25:45 -04:00
Peter Park
a060550bcd Add Hunyuan Video to PyTorch inference benchmark models doc (#5094)
(cherry picked from commit 80f7dc79b9)
2025-08-12 11:59:51 -04:00
Parag Bhandari
c92cbaee66 Merge branch 'roc-6.4.x' into docs/6.4.3 2025-08-08 08:49:53 -04:00
Parag Bhandari
c84afacc8d Merge branch 'develop' into roc-6.4.x 2025-08-08 08:49:39 -04:00
Parag Bhandari
843fd1b3fb Merge branch 'roc-6.4.x' into docs/6.4.3 2025-08-08 07:21:31 -04:00
Parag Bhandari
82221c4e2d Merge branch 'develop' into roc-6.4.x 2025-08-08 07:18:53 -04:00
pbhandar-amd
d0ebe126e7 Sync develop into docs/6.4.3 2025-08-07 09:07:38 -04:00
pbhandar-amd
74610893a9 Merge pull request #5154 from ROCm/amd/pbhandar/merge_from_develop
Merge develop into docs/6.4.3
2025-08-06 11:25:50 -04:00
Parag Bhandari
afe3e21cad Merge branch 'develop' into docs/6.4.3 2025-08-05 16:24:07 -04:00
Alex Xu
ae2440772f upgrade rocm-docs-core to 1.22.0 2025-07-31 16:41:40 -04:00
anisha-amd
61f970a24d Cherry pick into 6.4.3 - Docs: Adding frameworks compatibility for Megablocks and Taichi (#5138) 2025-07-31 14:02:09 -04:00
Alex Xu
85a1682573 Merge branch 'develop' into roc-6.4.x 2025-07-21 17:22:49 -04:00
Alex Xu
87c6e320b4 Merge branch 'develop' into roc-6.4.x 2025-07-21 15:52:30 -04:00
ammallya
b50948fe6b Fix for rocrsamples and rocr_debug_agent (#4863)
* Fix for rocrsamples

* Fix for rocr_debug_agent
2025-05-30 16:27:29 -07:00
ammallya
91407405a9 Changed naming convention for hip (#4837)
* Changed naming convention for hip

* Changed naming convention for hip
2025-05-29 10:19:28 -07:00
ammallya
8f23f63a6b Fix for tests (#4818)
* Fix for RBT

* Fix for roctst and kfd test
2025-05-27 17:38:48 -07:00
Alex Xu
11747aaadc Merge branch 'develop' into roc-6.4.x 2025-05-21 15:04:02 -04:00
Alex Xu
1088beefe5 Merge branch 'develop' into roc-6.4.x 2025-05-21 12:27:13 -04:00
Alex Xu
b7988925a5 Merge branch 'develop' into roc-6.4.x 2025-05-21 12:25:30 -04:00
chiranjeevipattigidi
89dafa6232 Update packages - remove broken packages (#4758)
* Update envsetup.sh HIP_ON_ROCclr_ROOT path to hip and remove

aqlprofiletest

* Update packages - remove broken packages
2025-05-21 09:06:39 -07:00
chiranjeevipattigidi
8054852dad Update envsetup.sh HIP_ON_ROCclr_ROOT path to hip and remove (#4755)
aqlprofiletest
2025-05-20 07:59:07 -07:00
ammallya
542d7813ce Removing aqlprofiletest 2025-04-14 15:26:24 -07:00
ammallya
bc1ffe4fcb bypass tests 2025-04-14 13:41:34 -07:00
ammallya
09997c68bb Removing kfd test 2025-04-14 12:55:13 -07:00
ammallya
42bc3501ac Merge pull request #4623 from ammallya/roc-6.4.x
Rebasing branch 6.4.x
2025-04-14 11:42:06 -07:00
66 changed files with 788 additions and 2640 deletions

View File

@@ -1,29 +1,10 @@
parameters:
- name: componentName
type: string
default: hip_clr_combined
- name: checkoutRepo
type: string
default: 'self'
- name: checkoutRef
type: string
default: ''
# monorepo related parameters
- name: sparseCheckoutDir
type: string
default: ''
- name: triggerDownstreamJobs
type: boolean
default: false
- name: downstreamAggregateNames
type: string
default: ''
- name: buildDependsOn
type: object
default: null
- name: unifiedBuild
type: boolean
default: false
# set to true if doing full build of ROCm stack
# and dependencies are pulled from same pipeline
- name: aggregatePipeline
@@ -54,24 +35,93 @@ parameters:
type: object
default:
- llvm-project
- ROCR-Runtime
# hip and clr are tightly-coupled
# run this same template for both repos
# any changes for clr should just trigger HIP pipeline
# similarly for hipother repo, for Nvidia backend
- name: jobMatrix
type: object
default:
buildJobs:
- { os: ubuntu2204, packageManager: apt, platform: amd }
- { os: ubuntu2204, packageManager: apt, platform: nvidia }
- { os: almalinux8, packageManager: dnf, platform: amd }
- { os: almalinux8, packageManager: dnf, platform: nvidia }
- { os: ubuntu2204, packageManager: apt }
- { os: almalinux8, packageManager: dnf }
# HIP with AMD backend
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: ${{ parameters.componentName }}_${{ job.os }}_${{ job.platform }}
${{ if parameters.buildDependsOn }}:
dependsOn:
- ${{ each build in parameters.buildDependsOn }}:
- ${{ build }}_${{ job.os }}
- job: hip_clr_combined_${{ job.os }}_amd
pool:
vmImage: 'ubuntu-22.04'
${{ if eq(job.os, 'almalinux8') }}:
container:
image: rocmexternalcicd.azurecr.io/manylinux228:latest
endpoint: ContainerService3
variables:
- group: common
- template: /.azuredevops/variables-global.yml
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
packageManager: ${{ job.packageManager }}
# checkout triggering repo (either HIP or clr)
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# if this is triggered by HIP repo, matching repo is clr
# if this is triggered by clr repo, matching repo is HIP
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: matching_repo
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: hipother_repo
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmDependenciesAMD }}
aggregatePipeline: ${{ parameters.aggregatePipeline }}
os: ${{ job.os }}
# compile clr
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
componentName: clr
cmakeBuildDir: '$(Build.SourcesDirectory)/clr/build'
cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
os: ${{ job.os }}
useAmdclang: false
extraBuildFlags: >-
-DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
-DHIP_PLATFORM=amd
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DHIPCC_BIN_DIR=$(Agent.BuildDirectory)/rocm/bin
-DCLR_BUILD_HIP=ON
-DCLR_BUILD_OCL=ON
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
artifactName: amd
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
artifactName: amd
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
# - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
# parameters:
# aptPackages: ${{ parameters.aptPackages }}
# pipModules: ${{ parameters.pipModules }}
# environment: amd
# HIP with Nvidia backend
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: hip_clr_combined_${{ job.os }}_nvidia
pool:
vmImage: 'ubuntu-22.04'
${{ if eq(job.os, 'almalinux8') }}:
@@ -90,45 +140,49 @@ jobs:
pipModules: ${{ parameters.pipModules }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
# full checkout of rocm-systems superrepo, we need clr, hip, and hipother
# checkout triggering repo (either HIP or clr)
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
# if this is triggered by HIP repo, matching repo is clr
# if this is triggered by clr repo, matching repo is HIP
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: matching_repo
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: hipother_repo
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmDependenciesNvidia }}
aggregatePipeline: ${{ parameters.aggregatePipeline }}
os: ${{ job.os }}
${{ if eq(job.platform, 'amd') }}:
dependencyList: ${{ parameters.rocmDependenciesAMD }}
${{ elseif eq(job.platform, 'nvidia') }}:
dependencyList: ${{ parameters.rocmDependenciesNvidia }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- script: 'ls -1R $(Agent.BuildDirectory)/rocm'
displayName: 'Artifact listing'
# compile clr
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
componentName: clr
cmakeBuildDir: $(Agent.BuildDirectory)/s/projects/clr/build
cmakeSourceDir: $(Agent.BuildDirectory)/s/projects/clr
cmakeBuildDir: '$(Build.SourcesDirectory)/clr/build'
cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
os: ${{ job.os }}
useAmdclang: false
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
-DHIP_PLATFORM=nvidia
-DHIPCC_BIN_DIR=$(Agent.BuildDirectory)/rocm/bin
-DHIP_COMMON_DIR=$(Agent.BuildDirectory)/s/projects/hip
-DHIPNV_DIR=$(Agent.BuildDirectory)/s/projects/hipother/hipnv
-DHIP_PLATFORM=${{ job.platform }}
-DCLR_BUILD_HIP=ON
-DCLR_BUILD_OCL=ON
-DCLR_BUILD_OCL=OFF
-DHIPNV_DIR=$(Build.SourcesDirectory)/hipother/hipnv
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
artifactName: ${{ job.platform }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
artifactName: ${{ job.platform }}
artifactName: nvidia
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
# - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
# parameters:
# aptPackages: ${{ parameters.aptPackages }}
# pipModules: ${{ parameters.pipModules }}
# environment: nvidia

View File

@@ -123,7 +123,7 @@ jobs:
- template: /.azuredevops/variables-global.yml
- name: ROCM_PATH
value: $(Agent.BuildDirectory)/rocm
pool: ${{ variables.MEDIUM_BUILD_POOL }}
pool: ${{ variables.HIGH_BUILD_POOL }}
workspace:
clean: all
steps:
@@ -131,7 +131,6 @@ 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:
@@ -150,7 +149,6 @@ jobs:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- task: Bash@3
displayName: Build and install other dependencies
retryCountOnTaskFailure: 3
inputs:
targetType: inline
workingDirectory: $(Agent.BuildDirectory)/s
@@ -212,7 +210,6 @@ 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:
@@ -231,7 +228,6 @@ jobs:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- task: Bash@3
displayName: Build and install other dependencies
retryCountOnTaskFailure: 3
inputs:
targetType: inline
workingDirectory: $(Agent.BuildDirectory)/s

View File

@@ -171,7 +171,6 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- task: DownloadPipelineArtifact@2
displayName: 'Download Pipeline Wheel Files'
retryCountOnTaskFailure: 3
inputs:
itemPattern: '**/*${{ job.os }}*.whl'
targetPath: $(Agent.BuildDirectory)

View File

@@ -35,13 +35,9 @@ parameters:
- ccache
- gfortran
- git
- libboost-filesystem-dev
- libboost-program-options-dev
- libdrm-dev
- liblapack-dev
- libmsgpack-dev
- libnuma-dev
- libopenblas-dev
- ninja-build
- python3-pip
- python3-venv
@@ -50,12 +46,6 @@ parameters:
default:
- joblib
- "packaging>=22.0"
- pyyaml
- msgpack
- simplejson
- ujson
- orjson
- yappi
- --upgrade
- name: rocmDependencies
type: object
@@ -91,12 +81,12 @@ parameters:
- { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx90a }
- { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1201 }
- { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1100 }
#- { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1030 }
- { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1030 }
- { pool: rocm-ci_ultra_build_pool, os: almalinux8, packageManager: dnf, target: gfx942 }
- { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx90a }
- { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1201 }
- { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1100 }
#- { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1030 }
- { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1030 }
testJobs:
- { os: ubuntu2204, packageManager: apt, target: gfx942 }
- { os: ubuntu2204, packageManager: apt, target: gfx90a }
@@ -178,8 +168,8 @@ jobs:
mkdir -p $(Agent.BuildDirectory)/temp-deps
cd $(Agent.BuildDirectory)/temp-deps
# position-independent LAPACK is required for almalinux8 builds
cmake -DBUILD_GTEST=OFF -DBUILD_LAPACK=ON -DCMAKE_POSITION_INDEPENDENT_CODE=ON $(Agent.BuildDirectory)/sparse/projects/hipblaslt/deps
make -j
cmake -DBUILD_GTEST=OFF -DBUILD_LAPACK=ON -DCMAKE_POSITION_INDEPENDENT_CODE=ON $(Agent.BuildDirectory)/s/deps
make
sudo make install
- script: |
mkdir -p $(CCACHE_DIR)
@@ -197,8 +187,6 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
os: ${{ job.os }}
cmakeSourceDir: $(Agent.BuildDirectory)/sparse/projects/hipblaslt
cmakeBuildDir: $(Agent.BuildDirectory)/sparse/projects/hipblaslt/build
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
-DCMAKE_INCLUDE_PATH=$(Agent.BuildDirectory)/rocm/llvm/include
@@ -207,11 +195,7 @@ jobs:
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache
-DCMAKE_C_COMPILER_LAUNCHER=ccache
-DAMDGPU_TARGETS=${{ job.target }}
-DGPU_TARGETS=${{ job.target }}
-DBUILD_CLIENTS_TESTS=ON
-DHIPBLASLT_ENABLE_ROCROLLER=ON
-DHIPBLASLT_ENABLE_FETCH=ON
-DHIPBLASLT_ENABLE_BLIS=OFF
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:

View File

@@ -69,7 +69,7 @@ parameters:
- { os: ubuntu2204, packageManager: apt, target: gfx942 }
- { os: ubuntu2204, packageManager: apt, target: gfx90a }
- { os: ubuntu2204, packageManager: apt, target: gfx1201 }
#- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
- { os: ubuntu2204, packageManager: apt, target: gfx1100 }
testJobs:
- { os: ubuntu2204, packageManager: apt, target: gfx942 }

View File

@@ -113,8 +113,7 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# ignore sparse checkout for monorepo case, we want access to hipblaslt directory
# sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
@@ -131,10 +130,7 @@ jobs:
displayName: Create temp folder for external dependencies
# hipSPARSELt already has a CMake script for external deps, so we can just run that
# https://github.com/ROCm/hipSPARSELt/blob/develop/deps/CMakeLists.txt
- ${{ if ne(parameters.sparseCheckoutDir, '') }}:
script: cmake $(Pipeline.Workspace)/s/projects/hipsparselt/deps
${{ else }}:
script: cmake $(Pipeline.Workspace)/s/deps
- script: cmake $(Pipeline.Workspace)/s/deps
displayName: Configure hipSPARSELt external dependencies
workingDirectory: $(Pipeline.Workspace)/deps
- script: make
@@ -158,11 +154,7 @@ jobs:
-DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DBUILD_CLIENTS_TESTS=ON
-DBUILD_USE_LOCAL_TENSILE=OFF
-GNinja
${{ if ne(parameters.sparseCheckoutDir, '') }}:
cmakeSourceDir: $(Build.SourcesDirectory)/projects/hipsparselt
cmakeBuildDir: $(Build.SourcesDirectory)/projects/hipsparselt
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
componentName: ${{ parameters.componentName }}

View File

@@ -30,7 +30,7 @@ parameters:
default:
buildJobs:
- { os: ubuntu2204, packageManager: apt }
# - { os: ubuntu2404, packageManager: apt }
- { os: ubuntu2404, packageManager: apt }
- { os: almalinux8, packageManager: dnf }
jobs:

View File

@@ -1,236 +0,0 @@
parameters:
- name: componentName
type: string
default: origami
- name: checkoutRepo
type: string
default: 'self'
- name: checkoutRef
type: string
default: ''
# monorepo related parameters
- name: sparseCheckoutDir
type: string
default: ''
- name: triggerDownstreamJobs
type: boolean
default: false
- name: downstreamAggregateNames
type: string
default: ''
- name: buildDependsOn
type: object
default: null
- name: unifiedBuild
type: boolean
default: false
# set to true if doing full build of ROCm stack
# and dependencies are pulled from same pipeline
- name: aggregatePipeline
type: boolean
default: false
- name: aptPackages
type: object
default:
- cmake
- git
- ninja-build
- wget
- python3
- python3-dev
- python3-pip
- name: pipModules
type: object
default:
- nanobind>=2.0.0
- name: rocmDependencies
type: object
default:
- clr
- llvm-project
- rocm-cmake
- rocminfo
- ROCR-Runtime
- rocprofiler-register
- name: rocmTestDependencies
type: object
default:
- clr
- llvm-project
- rocm-cmake
- rocminfo
- ROCR-Runtime
- rocprofiler-register
- name: jobMatrix
type: object
default:
buildJobs:
- { os: ubuntu2204, packageManager: apt }
- { os: almalinux8, packageManager: dnf }
testJobs:
- { os: ubuntu2204, packageManager: apt, target: gfx942 }
- { os: ubuntu2204, packageManager: apt, target: gfx90a }
- name: downstreamComponentMatrix
type: object
default:
- hipBLASLt:
name: hipBLASLt
sparseCheckoutDir: projects/hipblaslt
skipUnifiedBuild: 'false'
buildDependsOn:
- origami_build
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: origami_build_${{ job.os }}
${{ if parameters.buildDependsOn }}:
dependsOn:
- ${{ each build in parameters.buildDependsOn }}:
- ${{ build }}_${{ job.os }}
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: ROCM_PATH
value: $(Agent.BuildDirectory)/rocm
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
${{ if eq(job.os, 'almalinux8') }}:
container:
image: rocmexternalcicd.azurecr.io/manylinux228:latest
endpoint: ContainerService3
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
packageManager: ${{ job.packageManager }}
- 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 }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmDependencies }}
os: ${{ job.os }}
aggregatePipeline: ${{ parameters.aggregatePipeline }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
os: ${{ job.os }}
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DORIGAMI_BUILD_SHARED_LIBS=ON
-DORIGAMI_ENABLE_PYTHON=ON
-DORIGAMI_BUILD_TESTING=ON
-GNinja
- ${{ if ne(job.os, 'almalinux8') }}:
- task: PublishPipelineArtifact@1
displayName: 'Publish Build Directory Artifact'
inputs:
targetPath: '$(Agent.BuildDirectory)/s/build'
artifact: '${{ parameters.componentName }}_${{ job.os }}_build_dir'
publishLocation: 'pipeline'
- task: PublishPipelineArtifact@1
displayName: 'Publish Python Source Artifact'
inputs:
targetPath: '$(Agent.BuildDirectory)/s/python'
artifact: '${{ parameters.componentName }}_${{ job.os }}_python_src'
publishLocation: 'pipeline'
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
componentName: ${{ parameters.componentName }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
os: ${{ job.os }}
componentName: ${{ parameters.componentName }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
- ${{ if eq(parameters.unifiedBuild, False) }}:
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: origami_test_${{ job.os }}_${{ job.target }}
timeoutInMinutes: 120
dependsOn: origami_build_${{ job.os }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
preTargetFilter: ${{ parameters.componentName }}
os: ${{ job.os }}
- task: DownloadPipelineArtifact@2
displayName: 'Download Build Directory Artifact'
inputs:
artifact: '${{ parameters.componentName }}_${{ job.os }}_build_dir'
path: '$(Agent.BuildDirectory)/s/build'
- task: DownloadPipelineArtifact@2
displayName: 'Download Python Source Artifact'
inputs:
artifact: '${{ parameters.componentName }}_${{ job.os }}_python_src'
path: '$(Agent.BuildDirectory)/s/python'
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmTestDependencies }}
os: ${{ job.os }}
gpuTarget: ${{ job.target }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
- script: |
export PYTHONPATH=$(Agent.BuildDirectory)/s/build/python:$PYTHONPATH
echo "--- Running origami_test.py ---"
python3 $(Agent.BuildDirectory)/s/python/origami_test.py
echo "--- Running origami_grid_test.py ---"
python3 $(Agent.BuildDirectory)/s/python/origami_grid_test.py
displayName: 'Run Python Binding Tests'
condition: succeeded()
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
environment: test
gpuTarget: ${{ job.target }}
- ${{ if parameters.triggerDownstreamJobs }}:
- ${{ each component in parameters.downstreamComponentMatrix }}:
- ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
- template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
buildDependsOn: ${{ component.buildDependsOn }}
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
triggerDownstreamJobs: true
unifiedBuild: ${{ parameters.unifiedBuild }}

View File

@@ -76,7 +76,7 @@ jobs:
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Build.BinariesDirectory)/rocm
pool: ${{ variables.MEDIUM_BUILD_POOL }}
pool: ${{ variables.HIGH_BUILD_POOL }}
workspace:
clean: all
steps:

View File

@@ -84,12 +84,12 @@ parameters:
- { os: ubuntu2204, packageManager: apt, target: gfx90a }
- { os: ubuntu2204, packageManager: apt, target: gfx1201 }
- { os: ubuntu2204, packageManager: apt, target: gfx1100 }
#- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
- { os: almalinux8, packageManager: dnf, target: gfx942 }
- { os: almalinux8, packageManager: dnf, target: gfx90a }
- { os: almalinux8, packageManager: dnf, target: gfx1201 }
- { os: almalinux8, packageManager: dnf, target: gfx1100 }
#- { os: almalinux8, packageManager: dnf, target: gfx1030 }
- { os: almalinux8, packageManager: dnf, target: gfx1030 }
testJobs:
- { os: ubuntu2204, packageManager: apt, target: gfx942 }
- { os: ubuntu2204, packageManager: apt, target: gfx90a }
@@ -115,13 +115,6 @@ parameters:
# buildDependsOn:
# - rocBLAS_build
# - rocPRIM_build
# temporary rocblas->hipblas downstream path while the SOLVERs are disabled
- hipBLAS:
name: hipBLAS
sparseCheckoutDir: projects/hipblas
skipUnifiedBuild: 'false'
buildDependsOn:
- rocBLAS_build
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:

View File

@@ -8,25 +8,6 @@ parameters:
- name: checkoutRef
type: string
default: ''
- name: rocPyDecodeRepo
type: string
default: rocpydecode_repo
# monorepo related parameters
- name: sparseCheckoutDir
type: string
default: ''
- name: triggerDownstreamJobs
type: boolean
default: false
- name: downstreamAggregateNames
type: string
default: ''
- name: buildDependsOn
type: object
default: null
- name: unifiedBuild
type: boolean
default: false
# set to true if doing full build of ROCm stack
# and dependencies are pulled from same pipeline
- name: aggregatePipeline
@@ -75,23 +56,10 @@ parameters:
testJobs:
- { os: ubuntu2204, packageManager: apt, target: gfx942 }
- { os: ubuntu2204, packageManager: apt, target: gfx90a }
- name: downstreamComponentMatrix
type: object
default:
- rocPyDecode:
name: rocPyDecode
sparseCheckoutDir: ''
skipUnifiedBuild: 'false'
buildDependsOn:
- rocDecode_build
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: ${{ parameters.componentName }}_build_${{ job.os }}
${{ if parameters.buildDependsOn }}:
dependsOn:
- ${{ each build in parameters.buildDependsOn }}:
- ${{ build }}_${{ job.os }}
variables:
- group: common
- template: /.azuredevops/variables-global.yml
@@ -115,15 +83,12 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmDependencies }}
os: ${{ job.os }}
aggregatePipeline: ${{ parameters.aggregatePipeline }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
os: ${{ job.os }}
@@ -204,15 +169,3 @@ jobs:
registerROCmPackages: true
environment: test
gpuTarget: ${{ job.target }}
- ${{ if parameters.triggerDownstreamJobs }}:
- ${{ each component in parameters.downstreamComponentMatrix }}:
- ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
- template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
parameters:
checkoutRepo: ${{ parameters.rocPyDecodeRepo }}
sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
buildDependsOn: ${{ component.buildDependsOn }}
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
triggerDownstreamJobs: true
unifiedBuild: ${{ parameters.unifiedBuild }}

View File

@@ -5,22 +5,6 @@ parameters:
- name: checkoutRef
type: string
default: ''
# monorepo related parameters
- name: sparseCheckoutDir
type: string
default: ''
- name: triggerDownstreamJobs
type: boolean
default: false
- name: downstreamAggregateNames
type: string
default: ''
- name: buildDependsOn
type: object
default: null
- name: unifiedBuild
type: boolean
default: false
# set to true if doing full build of ROCm stack
# and dependencies are pulled from same pipeline
- name: aggregatePipeline
@@ -63,19 +47,19 @@ parameters:
type: object
default:
buildJobs:
- { os: ubuntu2204, packageManager: apt, target: gfx942 }
- { os: ubuntu2204, packageManager: apt, target: gfx90a }
- gfx942:
target: gfx942
- gfx90a:
target: gfx90a
testJobs:
- { os: ubuntu2204, packageManager: apt, target: gfx942 }
- { os: ubuntu2204, packageManager: apt, target: gfx90a }
- gfx942:
target: gfx942
- gfx90a:
target: gfx90a
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: rocPyDecode_build_${{ job.target }}
${{ if parameters.buildDependsOn }}:
dependsOn:
- ${{ each build in parameters.buildDependsOn }}:
- ${{ build }}_${{ job.os }}
variables:
- group: common
- template: /.azuredevops/variables-global.yml
@@ -90,20 +74,16 @@ jobs:
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmDependencies }}
gpuTarget: ${{ job.target }}
aggregatePipeline: ${{ parameters.aggregatePipeline }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- task: Bash@3
displayName: 'Save Python Package Paths'
inputs:
@@ -210,7 +190,6 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- task: DownloadPipelineArtifact@2
displayName: 'Download Pipeline Wheel Files'
retryCountOnTaskFailure: 3
inputs:
itemPattern: '**/*.whl'
targetPath: $(Agent.BuildDirectory)

View File

@@ -74,12 +74,12 @@ parameters:
- { os: ubuntu2204, packageManager: apt, target: gfx90a }
- { os: ubuntu2204, packageManager: apt, target: gfx1201 }
- { os: ubuntu2204, packageManager: apt, target: gfx1100 }
#- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
- { os: almalinux8, packageManager: dnf, target: gfx942 }
- { os: almalinux8, packageManager: dnf, target: gfx90a }
- { os: almalinux8, packageManager: dnf, target: gfx1201 }
- { os: almalinux8, packageManager: dnf, target: gfx1100 }
#- { os: almalinux8, packageManager: dnf, target: gfx1030 }
- { os: almalinux8, packageManager: dnf, target: gfx1030 }
testJobs:
- { os: ubuntu2204, packageManager: apt, target: gfx942 }
- { os: ubuntu2204, packageManager: apt, target: gfx90a }

View File

@@ -73,7 +73,7 @@ parameters:
- { os: ubuntu2204, packageManager: apt, target: gfx90a }
- { os: ubuntu2204, packageManager: apt, target: gfx1201 }
- { os: ubuntu2204, packageManager: apt, target: gfx1100 }
#- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
- { os: ubuntu2204, packageManager: apt, target: gfx1030 }
testJobs:
- { os: ubuntu2204, packageManager: apt, target: gfx942 }
- { os: ubuntu2204, packageManager: apt, target: gfx90a }

View File

@@ -70,7 +70,7 @@ jobs:
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
pool: ${{ variables.HIGH_BUILD_POOL }}
workspace:
clean: all
steps:

View File

@@ -1,29 +1,10 @@
parameters:
- name: componentName
type: string
default: rocm-core
- name: checkoutRepo
type: string
default: 'self'
- name: checkoutRef
type: string
default: ''
# monorepo related parameters
- name: sparseCheckoutDir
type: string
default: ''
- name: triggerDownstreamJobs
type: boolean
default: false
- name: downstreamAggregateNames
type: string
default: ''
- name: buildDependsOn
type: object
default: null
- name: unifiedBuild
type: boolean
default: false
# set to true if doing full build of ROCm stack
# and dependencies are pulled from same pipeline
- name: aggregatePipeline
@@ -46,10 +27,6 @@ parameters:
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: rocm_core_${{ job.os }}
${{ if parameters.buildDependsOn }}:
dependsOn:
- ${{ each build in parameters.buildDependsOn }}:
- ${{ build }}_${{ job.os }}
pool:
${{ if eq(job.os, 'ubuntu2404') }}:
vmImage: 'ubuntu-24.04'
@@ -73,10 +50,8 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
componentName: ${{ parameters.componentName }}
os: ${{ job.os }}
useAmdclang: false
extraBuildFlags: >-
@@ -90,12 +65,9 @@ jobs:
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
componentName: ${{ parameters.componentName }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
componentName: ${{ parameters.componentName }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
# - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml

View File

@@ -36,10 +36,8 @@ parameters:
- gfortran
- git
- libdrm-dev
- liblapack-dev
- libmsgpack-dev
- libnuma-dev
- libopenblas-dev
- ninja-build
- python3-pip
- python3-venv
@@ -48,8 +46,6 @@ parameters:
default:
- joblib
- "packaging>=22.0"
- pytest
- pytest-cmake
- --upgrade
- name: rocmDependencies
type: object
@@ -102,12 +98,12 @@ jobs:
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
packageManager: ${{ job.packageManager }}
- 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:
@@ -138,26 +134,12 @@ jobs:
rocm-libraries | ${{ job.os }} | ${{ job.target }} | $(DAY_STRING)
rocm-libraries | ${{ job.os }} | ${{ job.target }}
rocm-libraries | ${{ job.os }}
- task: Bash@3
displayName: Add paths for CMake and Python site-packages binaries
inputs:
targetType: inline
script: |
USER_BASE=$(python3 -m site --user-base)
echo "##vso[task.prependpath]$USER_BASE/bin"
echo "##vso[task.setvariable variable=PytestCmakePath]$USER_BASE/share/Pytest/cmake"
displayName: Set cmake configure paths
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
os: ${{ job.os }}
extraBuildFlags: >-
-D CMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor;$(PytestCmakePath)
-D CMAKE_INCLUDE_PATH=$(Agent.BuildDirectory)/rocm/llvm/include
-D CMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-D CMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-D CMAKE_CXX_COMPILER_LAUNCHER=ccache
-D CMAKE_C_COMPILER_LAUNCHER=ccache
-G Ninja
-DROCM_LIBRARIES_SUPERBUILD=ON
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
componentName: ${{ parameters.componentName }}

View File

@@ -1,29 +1,10 @@
parameters:
- name: componentName
type: string
default: rocm-smi-lib
- name: checkoutRepo
type: string
default: 'self'
- name: checkoutRef
type: string
default: ''
# monorepo related parameters
- name: sparseCheckoutDir
type: string
default: ''
- name: triggerDownstreamJobs
type: boolean
default: false
- name: downstreamAggregateNames
type: string
default: ''
- name: buildDependsOn
type: object
default: null
- name: unifiedBuild
type: boolean
default: false
# set to true if doing full build of ROCm stack
# and dependencies are pulled from same pipeline
- name: aggregatePipeline
@@ -51,10 +32,6 @@ parameters:
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: rocm_smi_lib_build_${{ job.os }}
${{ if parameters.buildDependsOn }}:
dependsOn:
- ${{ each build in parameters.buildDependsOn }}:
- ${{ build }}_${{ job.os }}
pool:
${{ if eq(job.os, 'ubuntu2404') }}:
vmImage: 'ubuntu-24.04'
@@ -78,10 +55,8 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
componentName: ${{ parameters.componentName }}
os: ${{ job.os }}
useAmdclang: false
extraBuildFlags: >-
@@ -90,56 +65,51 @@ jobs:
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
componentName: ${{ parameters.componentName }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
componentName: ${{ parameters.componentName }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
# - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
# parameters:
# aptPackages: ${{ parameters.aptPackages }}
- ${{ if eq(parameters.unifiedBuild, False) }}:
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: rocm_smi_lib_test_${{ job.os }}_${{ job.target }}
dependsOn: rocm_smi_lib_build_${{ job.os }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- checkout: none
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
parameters:
runRocminfo: false
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: ${{ parameters.componentName }}
testDir: '$(Agent.BuildDirectory)'
testExecutable: 'sudo ./rocm/share/rocm_smi/rsmitst_tests/rsmitst'
testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
environment: test
gpuTarget: ${{ job.target }}
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: rocm_smi_lib_test_${{ job.os }}_${{ job.target }}
dependsOn: rocm_smi_lib_build_${{ job.os }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
parameters:
runRocminfo: false
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: rocm_smi_lib
testDir: '$(Agent.BuildDirectory)'
testExecutable: 'sudo ./rocm/share/rocm_smi/rsmitst_tests/rsmitst'
testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
environment: test
gpuTarget: ${{ job.target }}

View File

@@ -1,29 +1,10 @@
parameters:
- name: componentName
type: string
default: rocminfo
- name: checkoutRepo
type: string
default: 'self'
- name: checkoutRef
type: string
default: ''
# monorepo related parameters
- name: sparseCheckoutDir
type: string
default: ''
- name: triggerDownstreamJobs
type: boolean
default: false
- name: downstreamAggregateNames
type: string
default: ''
- name: buildDependsOn
type: object
default: null
- name: unifiedBuild
type: boolean
default: false
# set to true if doing full build of ROCm stack
# and dependencies are pulled from same pipeline
- name: aggregatePipeline
@@ -59,11 +40,7 @@ parameters:
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: ${{ parameters.componentName }}_build_${{ job.os }}
${{ if parameters.buildDependsOn }}:
dependsOn:
- ${{ each build in parameters.buildDependsOn }}:
- ${{ build }}_${{ job.os }}
- job: rocminfo_build_${{ job.os }}
pool:
vmImage: 'ubuntu-22.04'
${{ if eq(job.os, 'almalinux8') }}:
@@ -85,18 +62,14 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmDependencies }}
aggregatePipeline: ${{ parameters.aggregatePipeline }}
os: ${{ job.os }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
componentName: ${{ parameters.componentName }}
os: ${{ job.os }}
useAmdclang: false
extraBuildFlags: >-
@@ -105,71 +78,65 @@ jobs:
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
componentName: ${{ parameters.componentName }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
componentName: ${{ parameters.componentName }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
- ${{ if eq(parameters.unifiedBuild, False) }}:
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: rocminfo_test_${{ job.target }}
dependsOn: rocminfo_build_${{ job.os }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
packageManager: ${{ job.packageManager }}
registerROCmPackages: true
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmTestDependencies }}
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
parameters:
runRocminfo: false
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: ${{ parameters.componentName }}
testDir: '$(Agent.BuildDirectory)'
testExecutable: './rocm/bin/rocminfo'
testParameters: ''
testPublishResults: false
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: rocm_agent_enumerator
testDir: '$(Agent.BuildDirectory)'
testExecutable: './rocm/bin/rocm_agent_enumerator'
testParameters: ''
testPublishResults: false
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
registerROCmPackages: true
environment: test
gpuTarget: ${{ job.target }}
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: rocminfo_test_${{ job.target }}
dependsOn: rocminfo_build_${{ job.os }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
packageManager: ${{ job.packageManager }}
registerROCmPackages: true
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmTestDependencies }}
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
parameters:
runRocminfo: false
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: rocminfo
testDir: '$(Agent.BuildDirectory)'
testExecutable: './rocm/bin/rocminfo'
testParameters: ''
testPublishResults: false
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: rocm_agent_enumerator
testDir: '$(Agent.BuildDirectory)'
testExecutable: './rocm/bin/rocm_agent_enumerator'
testParameters: ''
testPublishResults: false
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
registerROCmPackages: true
environment: test
gpuTarget: ${{ job.target }}

View File

@@ -1,29 +1,10 @@
parameters:
- name: componentName
type: string
default: rocprofiler-compute
- name: checkoutRepo
type: string
default: 'self'
- name: checkoutRef
type: string
default: ''
# monorepo related parameters
- name: sparseCheckoutDir
type: string
default: ''
- name: triggerDownstreamJobs
type: boolean
default: false
- name: downstreamAggregateNames
type: string
default: ''
- name: buildDependsOn
type: object
default: null
- name: unifiedBuild
type: boolean
default: false
# set to true if doing full build of ROCm stack
# and dependencies are pulled from same pipeline
- name: aggregatePipeline
@@ -55,7 +36,6 @@ parameters:
- pymongo
- pyyaml
- setuptools
- sqlalchemy
- tabulate
- textual
- textual_plotext
@@ -98,10 +78,6 @@ parameters:
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: rocprofiler_compute_build_${{ job.target }}
${{ if parameters.buildDependsOn }}:
dependsOn:
- ${{ each build in parameters.buildDependsOn }}:
- ${{ build }}_${{ job.os }}_${{ job.target }}
variables:
- group: common
- template: /.azuredevops/variables-global.yml
@@ -118,19 +94,15 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
componentName: ${{ parameters.componentName }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
gpuTarget: ${{ job.target }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
componentName: ${{ parameters.componentName }}
gpuTarget: ${{ job.target }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
# - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -139,83 +111,78 @@ jobs:
# pipModules: ${{ parameters.pipModules }}
# gpuTarget: ${{ job.target }}
- ${{ if eq(parameters.unifiedBuild, False) }}:
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: rocprofiler_compute_test_${{ job.target }}
timeoutInMinutes: 120
dependsOn: rocprofiler_compute_build_${{ job.target }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: PYTHON_VERSION
value: 3.10
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
preTargetFilter: ${{ parameters.componentName }}
gpuTarget: ${{ job.target }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmTestDependencies }}
gpuTarget: ${{ job.target }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- task: Bash@3
displayName: Add en_US.UTF-8 locale
inputs:
targetType: inline
script: |
sudo locale-gen en_US.UTF-8
sudo update-locale
locale -a
- task: Bash@3
displayName: Add ROCm binaries to PATH
inputs:
targetType: inline
script: |
echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_HIP_ARCHITECTURES=${{ job.target }}
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_BUILD_TYPE=Release
-DENABLE_TESTS=ON
-DINSTALL_TESTS=ON
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: ${{ parameters.componentName }}
testDir: $(Build.BinariesDirectory)/libexec/rocprofiler-compute
testExecutable: ROCM_PATH=$(Agent.BuildDirectory)/rocm ctest
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
environment: test
gpuTarget: ${{ job.target }}
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: rocprofiler_compute_test_${{ job.target }}
timeoutInMinutes: 120
dependsOn: rocprofiler_compute_build_${{ job.target }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: PYTHON_VERSION
value: 3.10
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
gpuTarget: ${{ job.target }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmTestDependencies }}
gpuTarget: ${{ job.target }}
- task: Bash@3
displayName: Add en_US.UTF-8 locale
inputs:
targetType: inline
script: |
sudo locale-gen en_US.UTF-8
sudo update-locale
locale -a
- task: Bash@3
displayName: Add ROCm binaries to PATH
inputs:
targetType: inline
script: |
echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_HIP_ARCHITECTURES=${{ job.target }}
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_BUILD_TYPE=Release
-DENABLE_TESTS=ON
-DINSTALL_TESTS=ON
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: rocprofiler-compute
testDir: $(Build.BinariesDirectory)/libexec/rocprofiler-compute
testExecutable: ROCM_PATH=$(Agent.BuildDirectory)/rocm ctest
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
environment: test
gpuTarget: ${{ job.target }}

View File

@@ -8,22 +8,6 @@ parameters:
- name: checkoutRef
type: string
default: ''
# monorepo related parameters
- name: sparseCheckoutDir
type: string
default: ''
- name: triggerDownstreamJobs
type: boolean
default: false
- name: downstreamAggregateNames
type: string
default: ''
- name: buildDependsOn
type: object
default: null
- name: unifiedBuild
type: boolean
default: false
# set to true if doing full build of ROCm stack
# and dependencies are pulled from same pipeline
- name: aggregatePipeline
@@ -86,10 +70,6 @@ parameters:
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
${{ if parameters.buildDependsOn }}:
dependsOn:
- ${{ each build in parameters.buildDependsOn }}:
- ${{ build }}_${{ job.os }}_${{ job.target }}
variables:
- group: common
- template: /.azuredevops/variables-global.yml
@@ -114,7 +94,6 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
parameters:
dependencyList:
@@ -129,8 +108,6 @@ jobs:
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
aggregatePipeline: ${{ parameters.aggregatePipeline }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
os: ${{ job.os }}
@@ -138,7 +115,6 @@ jobs:
extraBuildFlags: >-
-DCMAKE_MODULE_PATH=$(Build.SourcesDirectory)/cmake_modules;$(Agent.BuildDirectory)/rocm/lib/cmake;$(Agent.BuildDirectory)/rocm/lib/cmake/hip;$(Agent.BuildDirectory)/rocm/lib64/cmake;$(Agent.BuildDirectory)/rocm/lib64/cmake/hip
-DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor"
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_POSITION_INDEPENDENT_CODE=ON
-DENABLE_LDCONFIG=OFF
-DUSE_PROF_API=1
@@ -146,13 +122,10 @@ jobs:
multithreadFlag: -- -j32
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
componentName: ${{ parameters.componentName }}
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
componentName: ${{ parameters.componentName }}
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
@@ -166,68 +139,63 @@ jobs:
- HIP_ROCCLR_HOME:::/home/user/workspace/rocm
- ROCM_PATH:::/home/user/workspace/rocm
- ${{ if eq(parameters.unifiedBuild, False) }}:
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: ROCM_PATH
value: $(Agent.BuildDirectory)/rocm
- name: LD_LIBRARY_PATH
value: $(Agent.BuildDirectory)/rocm/lib/rocprofiler:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1/test:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- checkout: none
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
preTargetFilter: ${{ parameters.componentName }}
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
parameters:
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmDependencies }}
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: rocprofilerV1
testDir: $(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1
testExecutable: ./run.sh
testParameters: ''
testPublishResults: false
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: rocprofilerV2
testDir: $(Agent.BuildDirectory)/rocm
testExecutable: share/rocprofiler/tests/runUnitTests
testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
environment: test
gpuTarget: ${{ job.target }}
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: ROCM_PATH
value: $(Agent.BuildDirectory)/rocm
- name: LD_LIBRARY_PATH
value: $(Agent.BuildDirectory)/rocm/lib/rocprofiler:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1/test:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
parameters:
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmDependencies }}
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: rocprofilerV1
testDir: $(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1
testExecutable: ./run.sh
testParameters: ''
testPublishResults: false
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: rocprofilerV2
testDir: $(Agent.BuildDirectory)/rocm
testExecutable: share/rocprofiler/tests/runUnitTests
testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
environment: test
gpuTarget: ${{ job.target }}

View File

@@ -8,22 +8,6 @@ parameters:
- name: checkoutRef
type: string
default: ''
# monorepo related parameters
- name: sparseCheckoutDir
type: string
default: ''
- name: triggerDownstreamJobs
type: boolean
default: false
- name: downstreamAggregateNames
type: string
default: ''
- name: buildDependsOn
type: object
default: null
- name: unifiedBuild
type: boolean
default: false
# set to true if doing full build of ROCm stack
# and dependencies are pulled from same pipeline
- name: aggregatePipeline
@@ -81,10 +65,6 @@ parameters:
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
${{ if parameters.buildDependsOn }}:
dependsOn:
- ${{ each build in parameters.buildDependsOn }}:
- ${{ build }}_${{ job.os }}_${{ job.target }}
variables:
- group: common
- template: /.azuredevops/variables-global.yml
@@ -107,7 +87,6 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
@@ -115,8 +94,6 @@ jobs:
gpuTarget: ${{ job.target }}
aggregatePipeline: ${{ parameters.aggregatePipeline }}
os: ${{ job.os }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
# the linker flags will not affect ubuntu2204 builds as the paths do not exist
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
@@ -132,13 +109,10 @@ jobs:
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
componentName: ${{ parameters.componentName }}
sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
os: ${{ job.os }}
gpuTarget: ${{ job.target }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
componentName: ${{ parameters.componentName }}
os: ${{ job.os }}
gpuTarget: ${{ job.target }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
@@ -149,57 +123,53 @@ jobs:
# gpuTarget: ${{ job.target }}
# registerROCmPackages: true
- ${{ if eq(parameters.unifiedBuild, False) }}:
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
packageManager: ${{ job.packageManager }}
registerROCmPackages: true
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
preTargetFilter: ${{ parameters.componentName }}
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmTestDependencies }}
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
${{ if parameters.triggerDownstreamJobs }}:
downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: ${{ parameters.componentName }}
testExecutable: $(Agent.BuildDirectory)/rocm/share/roctracer/run_tests.sh
testParameters: ''
testDir: $(Agent.BuildDirectory)
testPublishResults: false
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
environment: test
gpuTarget: ${{ job.target }}
registerROCmPackages: true
- ${{ each job in parameters.jobMatrix.testJobs }}:
- job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
condition:
and(succeeded(),
eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
eq(${{ parameters.aggregatePipeline }}, False)
)
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ job.target }}_test_pool
workspace:
clean: all
steps:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
packageManager: ${{ job.packageManager }}
registerROCmPackages: true
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
parameters:
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
checkoutRef: ${{ parameters.checkoutRef }}
dependencyList: ${{ parameters.rocmTestDependencies }}
gpuTarget: ${{ job.target }}
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: roctracer
testExecutable: $(Agent.BuildDirectory)/rocm/share/roctracer/run_tests.sh
testParameters: ''
testDir: $(Agent.BuildDirectory)
testPublishResults: false
os: ${{ job.os }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
environment: test
gpuTarget: ${{ job.target }}
registerROCmPackages: true

View File

@@ -1,63 +0,0 @@
parameters:
- name: checkoutRepo
type: string
default: 'self'
- name: checkoutRef
type: string
default: ''
- name: catch2Version
type: string
default: ''
- name: aptPackages
type: object
default:
- cmake
- git
- ninja-build
- name: jobMatrix
type: object
default:
buildJobs:
- { os: ubuntu2204, packageManager: apt}
- { os: almalinux8, packageManager: dnf}
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: catch2_${{ job.os }}
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool:
vmImage: 'ubuntu-22.04'
${{ if eq(job.os, 'almalinux8') }}:
container:
image: rocmexternalcicd.azurecr.io/manylinux228:latest
endpoint: ContainerService3
workspace:
clean: all
steps:
- checkout: none
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- task: Bash@3
displayName: Clone catch2 ${{ parameters.catch2Version }}
inputs:
targetType: inline
script: git clone https://github.com/catchorg/Catch2.git -b ${{ parameters.catch2Version }}
workingDirectory: $(Agent.BuildDirectory)
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
os: ${{ job.os }}
cmakeBuildDir: $(Agent.BuildDirectory)/Catch2/build
cmakeSourceDir: $(Agent.BuildDirectory)/Catch2
useAmdclang: false
extraBuildFlags: >-
-DCMAKE_BUILD_TYPE=Release
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
os: ${{ job.os }}

View File

@@ -1,67 +0,0 @@
parameters:
- name: checkoutRepo
type: string
default: 'self'
- name: checkoutRef
type: string
default: ''
- name: fmtlibVersion
type: string
default: ''
- name: aptPackages
type: object
default:
- cmake
- git
- ninja-build
- libfmt-dev
- name: jobMatrix
type: object
default:
buildJobs:
- { os: ubuntu2204, packageManager: apt}
- { os: almalinux8, packageManager: dnf}
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: fmtlib_${{ job.os }}
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool:
vmImage: 'ubuntu-22.04'
${{ if eq(job.os, 'almalinux8') }}:
container:
image: rocmexternalcicd.azurecr.io/manylinux228:latest
endpoint: ContainerService3
workspace:
clean: all
steps:
- checkout: none
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- task: Bash@3
displayName: Clone fmtlib ${{ parameters.fmtlibVersion }}
inputs:
targetType: inline
script: git clone https://github.com/fmtlib/fmt.git -b ${{ parameters.fmtlibVersion }}
workingDirectory: $(Agent.BuildDirectory)
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
os: ${{ job.os }}
cmakeBuildDir: $(Agent.BuildDirectory)/fmt/build
cmakeSourceDir: $(Agent.BuildDirectory)/fmt
useAmdclang: false
extraBuildFlags: >-
-DCMAKE_BUILD_TYPE=Release
-DFMT_SYSTEM_HEADERS=ON
-DFMT_INSTALL=ON
-DFMT_TEST=OFF
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
os: ${{ job.os }}

View File

@@ -1,64 +0,0 @@
parameters:
- name: checkoutRepo
type: string
default: 'self'
- name: checkoutRef
type: string
default: ''
- name: libdivideVersion
type: string
default: ''
- name: aptPackages
type: object
default:
- cmake
- git
- ninja-build
- name: jobMatrix
type: object
default:
buildJobs:
- { os: ubuntu2204, packageManager: apt}
- { os: almalinux8, packageManager: dnf}
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: libdivide_${{ job.os }}
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool:
vmImage: 'ubuntu-22.04'
${{ if eq(job.os, 'almalinux8') }}:
container:
image: rocmexternalcicd.azurecr.io/manylinux228:latest
endpoint: ContainerService3
workspace:
clean: all
steps:
- checkout: none
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- task: Bash@3
displayName: Clone libdivide ${{ parameters.libdivideVersion }}
inputs:
targetType: inline
script: git clone https://github.com/ridiculousfish/libdivide.git -b ${{ parameters.libdivideVersion }}
workingDirectory: $(Agent.BuildDirectory)
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
os: ${{ job.os }}
cmakeBuildDir: $(Agent.BuildDirectory)/libdivide/build
cmakeSourceDir: $(Agent.BuildDirectory)/libdivide
useAmdclang: false
extraBuildFlags: >-
-DCMAKE_BUILD_TYPE=Release
-DLIBDIVIDE_BUILD_TESTS=OFF
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
os: ${{ job.os }}

View File

@@ -1,71 +0,0 @@
parameters:
- name: checkoutRepo
type: string
default: 'self'
- name: checkoutRef
type: string
default: ''
- name: spdlogVersion
type: string
default: ''
- name: aptPackages
type: object
default:
- cmake
- git
- ninja-build
- name: jobMatrix
type: object
default:
buildJobs:
- { os: ubuntu2204, packageManager: apt}
- { os: almalinux8, packageManager: dnf}
jobs:
- ${{ each job in parameters.jobMatrix.buildJobs }}:
- job: spdlog_${{ job.os }}
variables:
- group: common
- template: /.azuredevops/variables-global.yml
pool:
vmImage: 'ubuntu-22.04'
${{ if eq(job.os, 'almalinux8') }}:
container:
image: rocmexternalcicd.azurecr.io/manylinux228:latest
endpoint: ContainerService3
workspace:
clean: all
steps:
- checkout: none
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
packageManager: ${{ job.packageManager }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
parameters:
dependencyList:
- fmtlib
- task: Bash@3
displayName: Clone spdlog ${{ parameters.spdlogVersion }}
inputs:
targetType: inline
script: git clone https://github.com/gabime/spdlog.git -b ${{ parameters.spdlogVersion }}
workingDirectory: $(Agent.BuildDirectory)
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
os: ${{ job.os }}
cmakeBuildDir: $(Agent.BuildDirectory)/spdlog/build
cmakeSourceDir: $(Agent.BuildDirectory)/spdlog
useAmdclang: false
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/vendor
-DCMAKE_BUILD_TYPE=Release
-DSPDLOG_USE_STD_FORMAT=OFF
-DSPDLOG_FMT_EXTERNAL_HO=ON
-DSPDLOG_INSTALL=ON
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
os: ${{ job.os }}

View File

@@ -397,7 +397,6 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- task: DownloadPipelineArtifact@2
displayName: 'Download Pipeline Wheel Files'
retryCountOnTaskFailure: 3
inputs:
itemPattern: '**/*.whl'
targetPath: $(Agent.BuildDirectory)

View File

@@ -93,7 +93,7 @@ schedules:
jobs:
- ${{ each job in parameters.jobList }}:
- job: nightly_${{ job.os }}_${{ job.target }}
timeoutInMinutes: 120
timeoutInMinutes: 90
variables:
- group: common
- template: /.azuredevops/variables-global.yml
@@ -226,7 +226,6 @@ jobs:
cat Dockerfile
- task: Docker@2
displayName: Build and upload Docker image
retryCountOnTaskFailure: 3
inputs:
containerRegistry: ContainerService3
repository: 'nightly-${{ job.os }}-${{ job.target }}'

View File

@@ -1,23 +0,0 @@
variables:
- group: common
- template: /.azuredevops/variables-global.yml
parameters:
- name: catch2Version
type: string
default: "v3.7.0"
resources:
repositories:
- repository: pipelines_repo
type: github
endpoint: ROCm
name: ROCm/ROCm
trigger: none
pr: none
jobs:
- template: ${{ variables.CI_DEPENDENCIES_PATH }}/catch2.yml
parameters:
catch2Version: ${{ parameters.catch2Version }}

View File

@@ -1,23 +0,0 @@
variables:
- group: common
- template: /.azuredevops/variables-global.yml
parameters:
- name: fmtlibVersion
type: string
default: "11.1.3"
resources:
repositories:
- repository: pipelines_repo
type: github
endpoint: ROCm
name: ROCm/ROCm
trigger: none
pr: none
jobs:
- template: ${{ variables.CI_DEPENDENCIES_PATH }}/fmtlib.yml
parameters:
fmtlibVersion: ${{ parameters.fmtlibVersion }}

View File

@@ -1,23 +0,0 @@
variables:
- group: common
- template: /.azuredevops/variables-global.yml
parameters:
- name: libdivideVersion
type: string
default: master
resources:
repositories:
- repository: pipelines_repo
type: github
endpoint: ROCm
name: ROCm/ROCm
trigger: none
pr: none
jobs:
- template: ${{ variables.CI_DEPENDENCIES_PATH }}/libdivide.yml
parameters:
libdivideVersion: ${{ parameters.libdivideVersion }}

View File

@@ -1,23 +0,0 @@
variables:
- group: common
- template: /.azuredevops/variables-global.yml
parameters:
- name: spdlogVersion
type: string
default: "v1.15.1"
resources:
repositories:
- repository: pipelines_repo
type: github
endpoint: ROCm
name: ROCm/ROCm
trigger: none
pr: none
jobs:
- template: ${{ variables.CI_DEPENDENCIES_PATH }}/spdlog.yml
parameters:
spdlogVersion: ${{ parameters.spdlogVersion }}

View File

@@ -24,12 +24,8 @@ parameters:
steps:
- task: DownloadPipelineArtifact@2
displayName: Download ${{ parameters.componentName }}
retryCountOnTaskFailure: 3
inputs:
${{ if eq(parameters.componentName, 'clr') }}:
itemPattern: '**/*${{ parameters.componentName }}*${{ parameters.fileFilter }}*amd*' # filter out nvidia clr artifacts
${{ else }}:
itemPattern: '**/*${{ parameters.componentName }}*${{ parameters.fileFilter }}*'
itemPattern: '**/*${{ parameters.componentName }}*${{ parameters.fileFilter }}*'
targetPath: '$(Pipeline.Workspace)/d'
allowPartiallySucceededBuilds: true
${{ if parameters.aggregatePipeline }}:

View File

@@ -20,7 +20,7 @@ steps:
retryCountOnTaskFailure: 3
fetchFilter: blob:none
${{ if ne(parameters.sparseCheckoutDir, '') }}:
sparseCheckoutDirectories: ${{ parameters.sparseCheckoutDir }} shared
sparseCheckoutDirectories: ${{ parameters.sparseCheckoutDir }}
path: sparse
- ${{ if ne(parameters.sparseCheckoutDir, '') }}:
- task: Bash@3

View File

@@ -10,7 +10,6 @@ steps:
- ${{ if eq(parameters.registerROCmPackages, true) }}:
- task: Bash@3
displayName: 'Register AMDGPU & ROCm repos (apt)'
retryCountOnTaskFailure: 3
inputs:
targetType: inline
script: |
@@ -21,8 +20,7 @@ steps:
echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
sudo apt update
- task: Bash@3
displayName: 'APT update and install packages'
retryCountOnTaskFailure: 3
displayName: 'sudo apt-get update'
inputs:
targetType: inline
script: |
@@ -30,6 +28,15 @@ steps:
echo "deb http://archive.ubuntu.com/ubuntu/ jammy-updates main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
echo "deb http://archive.ubuntu.com/ubuntu/ jammy-backports main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
echo "deb http://archive.ubuntu.com/ubuntu/ jammy-security main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update && \
sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-broken install && \
sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-missing install ${{ join(' ', parameters.aptPackages) }}
sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update
- task: Bash@3
displayName: 'sudo apt-get fix'
inputs:
targetType: inline
script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-broken install
- ${{ if gt(length(parameters.aptPackages), 0) }}:
- task: Bash@3
displayName: 'sudo apt-get install ...'
inputs:
targetType: inline
script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-missing install ${{ join(' ', parameters.aptPackages) }}

View File

@@ -5,28 +5,51 @@ parameters:
steps:
- task: Bash@3
displayName: Download and install aqlprofile
retryCountOnTaskFailure: 3
displayName: Get aqlprofile package name
inputs:
targetType: inline
${{ if eq(parameters.os, 'ubuntu2204') }}:
script: |
export packageName=$(curl -s https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb")
echo "##vso[task.setvariable variable=packageName;isreadonly=true]$packageName"
${{ if eq(parameters.os, 'almalinux8') }}:
script: |
export packageName=$(curl -s https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/ | grep -oP "hsa-amd-aqlprofile-[^\"]+\.rpm" | head -n1)
echo "##vso[task.setvariable variable=packageName;isreadonly=true]$packageName"
- task: Bash@3
displayName: 'Download aqlprofile'
inputs:
targetType: inline
workingDirectory: '$(Pipeline.Workspace)'
${{ if eq(parameters.os, 'ubuntu2204') }}:
script: wget -nv https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/$(packageName)
${{ if eq(parameters.os, 'almalinux8') }}:
script: wget -nv https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/$(packageName)
- task: Bash@3
displayName: 'Extract aqlprofile'
inputs:
targetType: inline
workingDirectory: '$(Pipeline.Workspace)'
${{ if eq(parameters.os, 'ubuntu2204') }}:
script: |
mkdir hsa-amd-aqlprofile
dpkg-deb -R $(packageName) hsa-amd-aqlprofile
${{ if eq(parameters.os, 'almalinux8') }}:
script: |
mkdir hsa-amd-aqlprofile
sudo dnf -y install rpm-build cpio
rpm2cpio $(packageName) | (cd hsa-amd-aqlprofile && cpio -idmv)
- task: Bash@3
displayName: 'Copy aqlprofile files'
inputs:
targetType: inline
workingDirectory: $(Agent.BuildDirectory)
script: |
set -e
if [ "${{ parameters.os }}" = "ubuntu2204" ]; then
packageName=$(curl -s https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb") && \
wget -nv https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/$packageName && \
mkdir -p hsa-amd-aqlprofile && \
dpkg-deb -R $packageName hsa-amd-aqlprofile
elif [ "${{ parameters.os }}" = "almalinux8" ]; then
sudo dnf -y install rpm-build cpio && \
packageName=$(curl -s https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/ | grep -oP "hsa-amd-aqlprofile-[^\"]+\.rpm" | head -n1) && \
wget -nv https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/$packageName && \
mkdir -p hsa-amd-aqlprofile && \
rpm2cpio $packageName | (cd hsa-amd-aqlprofile && cpio -idmv)
else
echo "Unsupported OS: ${{ parameters.os }}"
exit 1
fi && \
mkdir -p $(Agent.BuildDirectory)/rocm && \
cp -R hsa-amd-aqlprofile/opt/rocm-*/* $(Agent.BuildDirectory)/rocm && \
rm -rf hsa-amd-aqlprofile $packageName
mkdir -p $(Agent.BuildDirectory)/rocm
cp -R hsa-amd-aqlprofile/opt/rocm-*/* $(Agent.BuildDirectory)/rocm
workingDirectory: '$(Pipeline.Workspace)'
- task: Bash@3
displayName: 'Clean up aqlprofile'
inputs:
targetType: inline
script: rm -rf hsa-amd-aqlprofile $(packageName)
workingDirectory: '$(Pipeline.Workspace)'

View File

@@ -54,13 +54,11 @@ parameters:
libfftw3-dev: fftw-devel
libfmt-dev: fmt-devel
libgmp-dev: gmp-devel
liblapack-dev: lapack-devel
liblzma-dev: xz-devel
libmpfr-dev: mpfr-devel
libmsgpack-dev: msgpack-devel
libncurses5-dev: ncurses-devel
libnuma-dev: numactl-devel
libopenblas-dev: openblas-devel
libopenmpi-dev: openmpi-devel
libpci-dev: libpciaccess-devel
libssl-dev: openssl-devel
@@ -89,7 +87,6 @@ steps:
- ${{ if eq(parameters.registerROCmPackages, true) }}:
- task: Bash@3
displayName: 'Register AMDGPU & ROCm repos (dnf)'
retryCountOnTaskFailure: 3
inputs:
targetType: inline
script: |
@@ -110,13 +107,12 @@ steps:
sudo dnf makecache
- task: Bash@3
displayName: 'Install base dnf packages'
retryCountOnTaskFailure: 3
inputs:
targetType: inline
script: |
sudo dnf config-manager --set-enabled powertools
# rpm fusion free repo for some dependencies
sudo dnf config-manager --set-enabled powertools && \
sudo dnf -y install https://download1.rpmfusion.org/free/el/rpmfusion-free-release-8.noarch.rpm && \
sudo dnf -y install https://download1.rpmfusion.org/free/el/rpmfusion-free-release-8.noarch.rpm
sudo dnf -y install ${{ join(' ', parameters.basePackages) }}
- task: Bash@3
displayName: 'Check gcc environment'
@@ -130,7 +126,6 @@ steps:
g++ -print-file-name=libstdc++.so
- task: Bash@3
displayName: 'Set python 3.11 as default'
retryCountOnTaskFailure: 3
inputs:
targetType: inline
script: |
@@ -145,20 +140,18 @@ steps:
- ${{ if eq(pkg, 'ninja-build') }}:
- task: Bash@3
displayName: 'Install ninja 1.11.1'
retryCountOnTaskFailure: 3
inputs:
targetType: inline
script: |
sudo dnf -y install unzip && \
curl -LO https://github.com/ninja-build/ninja/releases/download/v1.11.1/ninja-linux.zip && \
unzip ninja-linux.zip && \
sudo mv ninja /usr/local/bin/ninja && \
sudo chmod +x /usr/local/bin/ninja && \
curl -LO https://github.com/ninja-build/ninja/releases/download/v1.11.1/ninja-linux.zip
sudo dnf -y install unzip
unzip ninja-linux.zip
sudo mv ninja /usr/local/bin/ninja
sudo chmod +x /usr/local/bin/ninja
echo "##vso[task.prependpath]/usr/local/bin"
- ${{ if ne(parameters.aptToDnfMap[pkg], '') }}:
- task: Bash@3
displayName: 'dnf install ${{ parameters.aptToDnfMap[pkg] }}'
retryCountOnTaskFailure: 3
inputs:
targetType: inline
script: |

View File

@@ -27,7 +27,6 @@ steps:
- ${{ if gt(length(parameters.pipModules), 0) }}:
- task: Bash@3
displayName: 'pip install ...'
retryCountOnTaskFailure: 3
inputs:
targetType: inline
script: python3 -m pip install -v --force-reinstall ${{ join(' ', parameters.pipModules) }}

View File

@@ -47,8 +47,8 @@ parameters:
developBranch: aomp-dev
hasGpuTarget: false
clr:
pipelineId: 335
developBranch: develop
pipelineId: 145
developBranch: amd-staging
hasGpuTarget: false
composable_kernel:
pipelineId: 86
@@ -59,8 +59,8 @@ parameters:
developBranch: rocm
hasGpuTarget: false
HIP:
pipelineId: 335
developBranch: develop
pipelineId: 93
developBranch: amd-staging
hasGpuTarget: false
hip-tests:
pipelineId: 233
@@ -171,16 +171,16 @@ parameters:
developBranch: develop
hasGpuTarget: false
rocm-core:
pipelineId: 349
developBranch: develop
pipelineId: 103
developBranch: master
hasGpuTarget: false
rocm-examples:
pipelineId: 216
developBranch: amd-staging
hasGpuTarget: true
rocminfo:
pipelineId: 356
developBranch: develop
pipelineId: 91
developBranch: amd-staging
hasGpuTarget: false
rocMLIR:
pipelineId: 229
@@ -203,8 +203,8 @@ parameters:
developBranch: develop
hasGpuTarget: true
rocprofiler:
pipelineId: 329
developBranch: develop
pipelineId: 143
developBranch: amd-staging
hasGpuTarget: true
rocprofiler-compute:
pipelineId: 257
@@ -251,8 +251,8 @@ parameters:
developBranch: develop
hasGpuTarget: true
roctracer:
pipelineId: 331
developBranch: develop
pipelineId: 141
developBranch: amd-staging
hasGpuTarget: true
rocWMMA:
pipelineId: 109

View File

@@ -8,20 +8,15 @@ parameters:
type: object
default:
boost: 250
catch2: 343
fmtlib: 341
grpc: 72
gtest: 73
half560: 68
lapack: 69
libdivide: 342
spdlog: 340
steps:
- ${{ each dependency in parameters.dependencyList }}:
- task: DownloadPipelineArtifact@2
displayName: Download ${{ dependency }}
retryCountOnTaskFailure: 3
inputs:
project: ROCm-CI
buildType: specific
@@ -33,7 +28,7 @@ steps:
inputs:
archiveFilePatterns: '$(Pipeline.Workspace)/d/**/*.tar.gz'
destinationFolder: $(Agent.BuildDirectory)/vendor
cleanDestinationFolder: false
cleanDestinationFolder: true
overwriteExistingFiles: true
- task: DeleteFiles@1
displayName: Clean up ${{ dependency }}

View File

@@ -33,7 +33,6 @@ parameters:
steps:
- task: DownloadPipelineArtifact@2
displayName: Download ${{ parameters.preTargetFilter}}*${{ parameters.os }}_${{ parameters.gpuTarget}}*${{ parameters.postTargetFilter}}
retryCountOnTaskFailure: 3
inputs:
${{ if eq(parameters.buildType, 'specific') }}:
buildType: specific

View File

@@ -7,7 +7,6 @@ steps:
- task: Bash@3
name: downloadCKBuild
displayName: Download specific CK build
retryCountOnTaskFailure: 3
env:
CXX: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
CC: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
@@ -70,29 +69,20 @@ steps:
RETRIES=0
MAX_RETRIES=5
SUCCESS=false
while [ $RETRIES -lt $MAX_RETRIES ]; do
wget -nv $ARTIFACT_URL -O $(System.ArtifactsDirectory)/ck.zip && \
unzip $(System.ArtifactsDirectory)/ck.zip -d $(System.ArtifactsDirectory) && \
mkdir -p $(Agent.BuildDirectory)/rocm && \
tar -zxvf $(System.ArtifactsDirectory)/composable_kernel*/*.tar.gz -C $(Agent.BuildDirectory)/rocm && \
rm -r $(System.ArtifactsDirectory)/ck.zip $(System.ArtifactsDirectory)/composable_kernel*
if [ $? -eq 0 ]; then
SUCCESS=true
echo "Successfully downloaded CK."
break
else
RETRIES=$((RETRIES + 1))
echo "Failed to download CK on attempt $RETRIES/$MAX_RETRIES, retrying..."
sleep 1
until wget -nv $ARTIFACT_URL -O $(System.ArtifactsDirectory)/ck.zip; do
RETRIES=$((RETRIES+1))
if [[ $RETRIES -ge $MAX_RETRIES ]]; then
echo "Failed to download CK artifact after $MAX_RETRIES attempts."
exit 1
fi
echo "Download failed, retrying ($RETRIES/$MAX_RETRIES)..."
sleep 5
done
if [ "$SUCCESS" = false ]; then
echo "ERROR: failed to download CK after $MAX_RETRIES attempts."
exit 1
fi
unzip $(System.ArtifactsDirectory)/ck.zip -d $(System.ArtifactsDirectory)
mkdir -p $(Agent.BuildDirectory)/rocm
tar -zxvf $(System.ArtifactsDirectory)/composable_kernel*/*.tar.gz -C $(Agent.BuildDirectory)/rocm
rm -r $(System.ArtifactsDirectory)/ck.zip $(System.ArtifactsDirectory)/composable_kernel*
if [[ $EXIT_CODE -ne 0 ]]; then
BUILD_COMMIT=$(curl -s $AZ_API/build/builds/$CK_BUILD_ID | jq '.sourceVersion' | tr -d '"')

View File

@@ -28,13 +28,13 @@ variables:
- name: GFX90A_TEST_POOL
value: gfx90a_test_pool
- name: LATEST_RELEASE_VERSION
value: 6.4.3
value: 6.4.2
- name: REPO_RADEON_VERSION
value: 6.4.3
value: 6.4.2
- name: NEXT_RELEASE_VERSION
value: 7.0.0
- name: LATEST_RELEASE_TAG
value: rocm-6.4.3
value: rocm-6.4.2
- name: DOCKER_SKIP_GFX
value: gfx90a
- name: COMPOSABLE_KERNEL_PIPELINE_ID

View File

@@ -156,7 +156,6 @@ GEMMs
GFLOPS
GFortran
GFXIP
GGUF
Gemma
GiB
GIM
@@ -294,7 +293,6 @@ Multicore
Multithreaded
MyEnvironment
MyST
NANOO
NBIO
NBIOs
NCCL
@@ -502,7 +500,6 @@ Unhandled
VALU
VBIOS
VCN
verl's
VGPR
VGPRs
VM
@@ -745,7 +742,6 @@ logits
lossy
macOS
matchers
maxtext
megatron
microarchitecture
migraphx

View File

@@ -57,8 +57,9 @@ ROCm documentation continues to be updated to provide clearer and more comprehen
For more information about the changes, see [Changelog for the AI Developer Hub](https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/changelog.html).
* ROCm provides a comprehensive ecosystem for deep learning development. For more details, see [Deep learning frameworks for ROCm](https://rocm.docs.amd.com/en/docs-6.4.3/how-to/deep-learning-rocm.html). AMD ROCm adds support for the following deep learning framework:
* ROCm provides a comprehensive ecosystem for deep learning development. For more details, see [Deep learning frameworks for ROCm](https://rocm.docs.amd.com/en/docs-6.4.3/how-to/deep-learning-rocm.html). AMD ROCm adds support for the following deep learning frameworks:
* Taichi is an open-source, imperative, and parallel programming language designed for high-performance numerical computation. Embedded in Python, it leverages just-in-time (JIT) compilation frameworks such as LLVM to accelerate compute-intensive Python code by compiling it to native GPU or CPU instructions. It is currently supported on ROCm 6.3.2. For more information, see [Taichi compatibility](https://rocm.docs.amd.com/en/docs-6.4.3/compatibility/ml-compatibility/taichi-compatibility.html).
* Megablocks is a light-weight library for mixture-of-experts (MoE) training. The core of the system is efficient "dropless-MoE" and standard MoE layers. Megablocks is integrated with Megatron-LM, where data and pipeline parallel training of MoEs is supported. It is currently supported on ROCm 6.3.0. For more information, see [Megablocks compatibility](https://rocm.docs.amd.com/en/docs-6.4.3/compatibility/ml-compatibility/megablocks-compatibility.html).
* The [Data types and precision support](https://rocm.docs.amd.com/en/latest/reference/precision-support.html) topic now includes new hardware and library support information.

View File

@@ -1,12 +1,12 @@
<?xml version="1.0" encoding="UTF-8"?>
<manifest>
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
<default revision="refs/tags/20250912-42"
<default revision="refs/tags/rocm-6.4.2"
remote="rocm-org"
sync-c="true"
sync-j="4" />
<!--list of projects for ROCm-->
<project name="aqlprofile" />
<project name="ROCK-Kernel-Driver" />
<project name="ROCR-Runtime" />
<project name="amdsmi" />
<project name="rdc" />
@@ -37,37 +37,36 @@
<project name="rocr_debug_agent" />
<!-- ROCm Libraries -->
<project groups="mathlibs" name="AMDMIGraphX" />
<project groups="mathlibs" name="MIOpen" />
<project groups="mathlibs" name="MIVisionX" />
<project groups="mathlibs" name="ROCmValidationSuite" />
<project groups="mathlibs" name="Tensile" />
<project groups="mathlibs" name="composable_kernel" />
<project groups="mathlibs" name="hipBLAS-common" />
<project groups="mathlibs" name="hipBLAS" />
<project groups="mathlibs" name="hipBLASLt" />
<project groups="mathlibs" name="hipCUB" />
<project groups="mathlibs" name="hipFFT" />
<project groups="mathlibs" name="hipRAND" />
<project groups="mathlibs" name="hipSOLVER" />
<project groups="mathlibs" name="hipSPARSE" />
<project groups="mathlibs" name="hipSPARSELt" />
<project groups="mathlibs" name="hipTensor" />
<project groups="mathlibs" name="hipfort" />
<project groups="mathlibs" name="rccl" />
<project groups="mathlibs" name="rocAL" />
<project groups="mathlibs" name="rocALUTION" />
<project groups="mathlibs" name="rocBLAS" />
<project groups="mathlibs" name="rocDecode" />
<project groups="mathlibs" name="rocJPEG" />
<project groups="mathlibs" name="rocm-libraries">
<linkfile src="projects/hipcub" dest="hipCUB"/>
<linkfile src="projects/rocprim" dest="rocPRIM"/>
<linkfile src="projects/hiprand" dest="hipRAND"/>
<linkfile src="projects/rocrand" dest="rocRAND"/>
<linkfile src="projects/rocthrust" dest="rocThrust"/>
<linkfile src="projects/hipblas-common" dest="hipBLAS-common"/>
<linkfile src="projects/hipblaslt" dest="hipBLASLt"/>
<linkfile src="projects/rocblas" dest="rocBLAS"/>
<linkfile src="projects/hipsparselt" dest="hipSPARSELt"/>
<linkfile src="projects/rocsparse" dest="rocSPARSE"/>
<linkfile src="projects/hipsparse" dest="hipSPARSE"/>
<linkfile src="projects/hipblas" dest="hipBLAS"/>
<linkfile src="projects/miopen" dest="MIOpen"/>
<linkfile src="projects/hipfft" dest="hipFFT"/>
<linkfile src="projects/rocfft" dest="rocFFT"/>
</project>
<project groups="mathlibs" name="rocPyDecode" />
<project groups="mathlibs" name="rocFFT" />
<project groups="mathlibs" name="rocPRIM" />
<project groups="mathlibs" name="rocRAND" />
<project groups="mathlibs" name="rocSHMEM" />
<project groups="mathlibs" name="rocSOLVER" />
<project groups="mathlibs" name="rocSPARSE" />
<project groups="mathlibs" name="rocThrust" />
<project groups="mathlibs" name="rocWMMA" />
<project groups="mathlibs" name="rocm-cmake" />
<project groups="mathlibs" name="rpp" />

View File

@@ -29,7 +29,6 @@ additional licenses. Please review individual repositories for more information.
| [AMD SMI](https://github.com/ROCm/amdsmi) | [MIT](https://github.com/ROCm/amdsmi/blob/amd-staging/LICENSE) |
| [aomp](https://github.com/ROCm/aomp/) | [Apache 2.0](https://github.com/ROCm/aomp/blob/aomp-dev/LICENSE) |
| [aomp-extras](https://github.com/ROCm/aomp-extras/) | [MIT](https://github.com/ROCm/aomp-extras/blob/aomp-dev/LICENSE) |
| [AQLprofile] | [MIT](https://github.com/ROCm/aqlprofile/blob/amd-staging/LICENSE) |
| [Code Object Manager (Comgr)](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/comgr) | [The University of Illinois/NCSA](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/comgr/LICENSE.txt) |
| [Composable Kernel](https://github.com/ROCm/composable_kernel) | [MIT](https://github.com/ROCm/composable_kernel/blob/develop/LICENSE) |
| [half](https://github.com/ROCm/half/) | [MIT](https://github.com/ROCm/half/blob/rocm/LICENSE.txt) |
@@ -47,6 +46,7 @@ additional licenses. Please review individual repositories for more information.
| [hipSPARSE](https://github.com/ROCm/hipSPARSE/) | [MIT](https://github.com/ROCm/hipSPARSE/blob/develop/LICENSE.md) |
| [hipSPARSELt](https://github.com/ROCm/hipSPARSELt/) | [MIT](https://github.com/ROCm/hipSPARSELt/blob/develop/LICENSE.md) |
| [hipTensor](https://github.com/ROCm/hipTensor) | [MIT](https://github.com/ROCm/hipTensor/blob/develop/LICENSE) |
| hsa-amd-aqlprofile | [AMD Software EULA](https://www.amd.com/en/legal/eula/amd-software-eula.html) |
| [llvm-project](https://github.com/ROCm/llvm-project/) | [Apache](https://github.com/ROCm/llvm-project/blob/amd-staging/LICENSE.TXT) |
| [llvm-project/flang](https://github.com/ROCm/llvm-project/tree/amd-staging/flang) | [Apache 2.0](https://github.com/ROCm/llvm-project/blob/amd-staging/flang/LICENSE.TXT) |
| [MIGraphX](https://github.com/ROCm/AMDMIGraphX/) | [MIT](https://github.com/ROCm/AMDMIGraphX/blob/develop/LICENSE) |
@@ -132,10 +132,12 @@ companies.
### Package licensing
:::{attention}
ROCprof Trace Decoder and AOCC CPU optimizations are provided in binary form, subject to the license agreement enclosed on [GitHub](https://github.com/ROCm/rocprof-trace-decoder/blob/amd-mainline/LICENSE) for ROCprof Trace Decoder, and [Developer Central](https://www.amd.com/en/developer/aocc.html) for AOCC. By using, installing,
copying or distributing ROCprof Trace Decoder or AOCC CPU Optimizations, you agree to
AQL Profiler and AOCC CPU optimization are both provided in binary form, each
subject to the license agreement enclosed in the directory for the binary available
in `/opt/rocm/share/doc/hsa-amd-aqlprofile/EULA`. By using, installing,
copying or distributing AQL Profiler and/or AOCC CPU Optimizations, you agree to
the terms and conditions of this license agreement. If you do not agree to the
terms of this agreement, do not install, copy or use ROCprof Trace Decoder or the
terms of this agreement, do not install, copy or use the AQL Profiler and/or the
AOCC CPU Optimizations.
:::

View File

@@ -35,8 +35,6 @@ ROCm Version,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6
:doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_,N/A,N/A,N/A,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,
:doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
:doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>` [#taichi_compat]_,N/A,N/A,N/A,N/A,N/A,1.8.0b1,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
:doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat]_,N/A,N/A,2.48.0.post0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
:doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat]_,N/A,N/A,N/A,b5997,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
`ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.2,1.2,1.2,1.2,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
,,,,,,,,,,,,,,,,,,
,,,,,,,,,,,,,,,,,,
1 ROCm Version 6.4.3 6.4.2 6.4.1 6.4.0 6.3.3 6.3.2 6.3.1 6.3.0 6.2.4 6.2.2 6.2.1 6.2.0 6.1.5 6.1.2 6.1.1 6.1.0 6.0.2 6.0.0
35 :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_ N/A N/A N/A 2.4.0 N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A
36 :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat]_ N/A N/A N/A N/A N/A N/A N/A 0.7.0 N/A N/A N/A N/A N/A N/A N/A N/A N/A
37 :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>` [#taichi_compat]_ N/A N/A N/A N/A N/A 1.8.0b1 N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A
:doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat]_ N/A N/A 2.48.0.post0 N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A
:doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat]_ N/A N/A N/A b5997 N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A N/A
38 `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_ 1.2 1.2 1.2 1.2 1.17.3 1.17.3 1.17.3 1.17.3 1.17.3 1.17.3 1.17.3 1.17.3 1.17.3 1.17.3 1.17.3 1.17.3 1.14.1 1.14.1
39
40

View File

@@ -246,8 +246,6 @@ Expand for full historical view of:
.. [#dgl_compat] DGL is only supported on ROCm 6.4.0.
.. [#megablocks_compat] Megablocks is only supported on ROCm 6.3.0.
.. [#taichi_compat] Taichi is only supported on ROCm 6.3.2.
.. [#ray_compat] Ray is only supported on ROCm 6.4.1.
.. [#llama-cpp_compat] llama.cpp is only supported on ROCm 6.4.0.
.. [#kfd_support-past-60] As of ROCm 6.4.0, forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The tested user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
.. [#ROCT-rocr-past-60] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.

View File

@@ -1,156 +0,0 @@
:orphan:
.. meta::
:description: llama.cpp deep learning framework compatibility
:keywords: GPU, GGML, llama.cpp compatibility
.. version-set:: rocm_version latest
********************************************************************************
llama.cpp compatibility
********************************************************************************
`llama.cpp <https://github.com/ggml-org/llama.cpp>`__ is an open-source framework
for Large Language Model (LLM) inference that runs on both central processing units
(CPUs) and graphics processing units (GPUs). It is written in plain C/C++, providing
a simple, dependency-free setup.
The framework supports multiple quantization options, from 1.5-bit to 8-bit integers,
to speed up inference and reduce memory usage. Originally built as a CPU-first library,
llama.cpp is easy to integrate with other programming environments and is widely
adopted across diverse platforms, including consumer devices.
ROCm support for llama.cpp is upstreamed, and you can build the official source code
with ROCm support:
- ROCm support for llama.cpp is hosted in the official `https://github.com/ROCm/llama.cpp
<https://github.com/ROCm/llama.cpp>`_ repository.
- Due to independent compatibility considerations, this location differs from the
`https://github.com/ggml-org/llama.cpp <https://github.com/ggml-org/llama.cpp>`_ upstream repository.
- To install llama.cpp, use the prebuilt :ref:`Docker image <llama-cpp-docker-compat>`,
which includes ROCm, llama.cpp, and all required dependencies.
- See the :doc:`ROCm llama.cpp installation guide <rocm-install-on-linux:install/3rd-party/llama-cpp-install>`
to install and get started.
- See the `Installation guide <https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#hip>`__
in the upstream llama.cpp documentation.
.. note::
llama.cpp is supported on ROCm 6.4.0.
Supported devices
================================================================================
**Officially Supported**: AMD Instinct™ MI300X, MI210
Use cases and recommendations
================================================================================
llama.cpp can be applied in a variety of scenarios, particularly when you need to meet one or more of the following requirements:
- Plain C/C++ implementation with no external dependencies
- Support for 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory usage
- Custom HIP (Heterogeneous-compute Interface for Portability) kernels for running large language models (LLMs) on AMD GPUs (graphics processing units)
- CPU (central processing unit) + GPU (graphics processing unit) hybrid inference for partially accelerating models larger than the total available VRAM (video random-access memory)
llama.cpp is also used in a range of real-world applications, including:
- Games such as `Lucy's Labyrinth <https://github.com/MorganRO8/Lucys_Labyrinth>`__:
A simple maze game where AI-controlled agents attempt to trick the player.
- Tools such as `Styled Lines <https://marketplace.unity.com/packages/tools/ai-ml-integration/style-text-webgl-ios-stand-alone-llm-llama-cpp-wrapper-292902>`__:
A proprietary, asynchronous inference wrapper for Unity3D game development, including pre-built mobile and web platform wrappers and a model example.
- Various other AI applications use llama.cpp as their inference engine;
for a detailed list, see the `user interfaces (UIs) section <https://github.com/ggml-org/llama.cpp?tab=readme-ov-file#description>`__.
For more use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__,
where you can search for llama.cpp examples and best practices to optimize your workloads on AMD GPUs.
- The `Llama.cpp Meets Instinct: A New Era of Open-Source AI Acceleration <https://rocm.blogs.amd.com/ecosystems-and-partners/llama-cpp/README.html>`__,
blog post outlines how the open-source llama.cpp framework enables efficient LLM inference—including interactive inference with ``llama-cli``,
server deployment with ``llama-server``, GGUF model preparation and quantization, performance benchmarking, and optimizations tailored for
AMD Instinct GPUs within the ROCm ecosystem.
.. _llama-cpp-docker-compat:
Docker image compatibility
================================================================================
.. |docker-icon| raw:: html
<i class="fab fa-docker"></i>
AMD validates and publishes `ROCm llama.cpp Docker images <https://hub.docker.com/r/rocm/llama.cpp>`__
with ROCm backends on Docker Hub. The following Docker image tags and associated
inventories were tested on `ROCm 6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__.
Click |docker-icon| to view the image on Docker Hub.
.. important::
Tag endings of ``_full``, ``_server``, and ``_light`` serve different purposes for entrypoints as follows:
- Full: This image includes both the main executable file and the tools to convert ``LLaMA`` models into ``ggml`` and convert into 4-bit quantization.
- Server: This image only includes the server executable file.
- Light: This image only includes the main executable file.
.. list-table::
:header-rows: 1
:class: docker-image-compatibility
* - Full Docker
- Server Docker
- Light Docker
- llama.cpp
- Ubuntu
* - .. raw:: html
<a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_full/images/sha256-f78f6c81ab2f8e957469415fe2370a1334fe969c381d1fe46050c85effaee9d5"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
- .. raw:: html
<a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_server/images/sha256-275ad9e18f292c26a00a2de840c37917e98737a88a3520bdc35fd3fc5c9a6a9b"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
- .. raw:: html
<a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_light/images/sha256-cc324e6faeedf0e400011f07b49d2dc41a16bae257b2b7befa0f4e2e97231320"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
- `b5997 <https://github.com/ROCm/llama.cpp/tree/release/b5997>`__
- 24.04
Key ROCm libraries for llama.cpp
================================================================================
llama.cpp functionality on ROCm is determined by its underlying library
dependencies. These ROCm components affect the capabilities, performance, and
feature set available to developers.
.. list-table::
:header-rows: 1
* - ROCm library
- Version
- Purpose
- Usage
* - `hipBLAS <https://github.com/ROCm/hipBLAS>`__
- :version-ref:`hipBLAS rocm_version`
- Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
matrix and vector operations.
- Supports operations such as matrix multiplication, matrix-vector
products, and tensor contractions. Utilized in both dense and batched
linear algebra operations.
* - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`__
- :version-ref:`hipBLASLt rocm_version`
- hipBLASLt is an extension of the hipBLAS library, providing additional
features like epilogues fused into the matrix multiplication kernel or
use of integer tensor cores.
- By setting the flag ``ROCBLAS_USE_HIPBLASLT``, you can dispatch hipblasLt
kernels where possible.
* - `rocWMMA <https://github.com/ROCm/rocWMMA>`__
- :version-ref:`rocWMMA rocm_version`
- Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
multiplication (GEMM) and accumulation operations with mixed precision
support.
- Can be used to enhance the flash attention performance on AMD compute, by enabling
the flag during compile time.

View File

@@ -1,111 +0,0 @@
:orphan:
.. meta::
:description: Ray deep learning framework compatibility
:keywords: GPU, Ray compatibility
.. version-set:: rocm_version latest
*******************************************************************************
Ray compatibility
*******************************************************************************
Ray is a unified framework for scaling AI and Python applications from your laptop
to a full cluster, without changing your code. Ray consists of `a core distributed
runtime <https://docs.ray.io/en/latest/ray-core/walkthrough.html>`_ and a set of
`AI libraries <https://docs.ray.io/en/latest/ray-air/getting-started.html>`_ for
simplifying machine learning computations.
Ray is a general-purpose framework that runs many types of workloads efficiently.
Any Python application can be scaled with Ray, without extra infrastructure.
ROCm support for Ray is upstreamed, and you can build the official source code
with ROCm support:
- ROCm support for Ray is hosted in the official `https://github.com/ROCm/ray
<https://github.com/ROCm/ray>`_ repository.
- Due to independent compatibility considerations, this location differs from the
`https://github.com/ray-project/ray <https://github.com/ray-project/ray>`_ upstream repository.
- To install Ray, use the prebuilt :ref:`Docker image <ray-docker-compat>`
which includes ROCm, Ray, and all required dependencies.
- See the :doc:`ROCm Ray installation guide <rocm-install-on-linux:install/3rd-party/ray-install>`
for instructions to get started.
- See the `Installation section <https://docs.ray.io/en/latest/ray-overview/installation.html>`_
in the upstream Ray documentation.
- The Docker image provided is based on the upstream Ray `Daily Release (Nightly) wheels <https://docs.ray.io/en/latest/ray-overview/installation.html#daily-releases-nightlies>`__
corresponding to commit `005c372 <https://github.com/ray-project/ray/commit/005c372262e050d5745f475e22e64305fa07f8b8>`__.
.. note::
Ray is supported on ROCm 6.4.1.
Supported devices
================================================================================
**Officially Supported**: AMD Instinct™ MI300X, MI210
Use cases and recommendations
================================================================================
* The `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm
Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`__
blog provides an overview of Volcano Engine Reinforcement Learning (verl)
for large language models (LLMs) and discusses its benefits in large-scale
reinforcement learning from human feedback (RLHF). It uses Ray as part of a
hybrid orchestration engine to schedule and coordinate training and inference
tasks in parallel, enabling optimized resource utilization and potential overlap
between these phases. This dynamic resource allocation strategy significantly
improves overall system efficiency. The blog presents verls performance results,
focusing on throughput and convergence accuracy achieved on AMD Instinct™ MI300X
GPUs. Follow this guide to get started with verl on AMD Instinct GPUs and
accelerate your RLHF training with ROCm-optimized performance.
* The `Exploring Use Cases for Scalable AI: Implementing Ray with ROCm Support for Efficient ML Workflows
<https://rocm.blogs.amd.com/artificial-intelligence/rocm-ray/README.html>`__
blog post describes key use cases such as training and inference for large language models (LLMs),
model serving, hyperparameter tuning, reinforcement learning, and the orchestration of large-scale
workloads using Ray in the ROCm environment.
For more use cases and recommendations, see the AMD GPU tabs in the `Accelerator Support
topic <https://docs.ray.io/en/latest/ray-core/scheduling/accelerators.html#accelerator-support>`__
of the Ray core documentation and refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__,
where you can search for Ray examples and best practices to optimize your workloads on AMD GPUs.
.. _ray-docker-compat:
Docker image compatibility
================================================================================
.. |docker-icon| raw:: html
<i class="fab fa-docker"></i>
AMD validates and publishes ready-made `ROCm Ray Docker images <https://hub.docker.com/r/rocm/ray/tags>`__
with ROCm backends on Docker Hub. The following Docker image tags and
associated inventories represent the latest Ray version from the official Docker Hub and are validated for
`ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`_. Click the |docker-icon|
icon to view the image on Docker Hub.
.. list-table::
:header-rows: 1
:class: docker-image-compatibility
* - Docker image
- Ray
- Pytorch
- Ubuntu
- Python
* - .. raw:: html
<a href="https://hub.docker.com/layers/rocm/ray/ray-2.48.0.post0_rocm6.4.1_ubuntu24.04_py3.12_pytorch2.6.0/images/sha256-0d166fe6bdced38338c78eedfb96eff92655fb797da3478a62dd636365133cc0"><i class="fab fa-docker fa-lg"></i> rocm/ray</a>
- `2.48.0.post0 <https://github.com/ROCm/ray/tree/release/2.48.0.post0>`_
- 2.6.0+git684f6f2
- 24.04
- `3.12.10 <https://www.python.org/downloads/release/python-31210/>`_

View File

@@ -9,21 +9,17 @@ import shutil
import sys
from pathlib import Path
gh_release_path = os.path.join("..", "RELEASE.md")
gh_changelog_path = os.path.join("..", "CHANGELOG.md")
sphinx_release_path = os.path.join("about", "release-notes.md")
sphinx_changelog_path = os.path.join("release", "changelog.md")
shutil.copy2(gh_release_path, sphinx_release_path)
shutil.copy2(gh_changelog_path, sphinx_changelog_path)
shutil.copy2("../RELEASE.md", "./about/release-notes.md")
shutil.copy2("../CHANGELOG.md", "./release/changelog.md")
# Mark the consolidated changelog as orphan to prevent Sphinx from warning about missing toctree entries
with open(sphinx_changelog_path, "r+", encoding="utf-8") as file:
with open("./release/changelog.md", "r+") as file:
content = file.read()
file.seek(0)
file.write(":orphan:\n" + content)
# Replace GitHub-style [!ADMONITION]s with Sphinx-compatible ```{admonition} blocks
with open(sphinx_changelog_path, "r", encoding="utf-8") as file:
with open("./release/changelog.md", "r") as file:
lines = file.readlines()
modified_lines = []
@@ -61,14 +57,11 @@ with open(sphinx_changelog_path, "r", encoding="utf-8") as file:
file.close()
with open(sphinx_changelog_path, "w", encoding="utf-8") as file:
with open("./release/changelog.md", 'w') as file:
file.writelines(modified_lines)
matrix_path = os.path.join("compatibility", "compatibility-matrix-historical-6.0.csv")
rtd_path = os.path.join("..", "_readthedocs", "html", "downloads")
if not os.path.exists(rtd_path):
os.makedirs(rtd_path)
shutil.copy2(matrix_path, rtd_path)
os.system("mkdir -p ../_readthedocs/html/downloads")
os.system("cp compatibility/compatibility-matrix-historical-6.0.csv ../_readthedocs/html/downloads/compatibility-matrix-historical-6.0.csv")
latex_engine = "xelatex"
latex_elements = {
@@ -108,8 +101,6 @@ article_pages = [
{"file": "compatibility/ml-compatibility/dgl-compatibility", "os": ["linux"]},
{"file": "compatibility/ml-compatibility/megablocks-compatibility", "os": ["linux"]},
{"file": "compatibility/ml-compatibility/taichi-compatibility", "os": ["linux"]},
{"file": "compatibility/ml-compatibility/ray-compatibility", "os": ["linux"]},
{"file": "compatibility/ml-compatibility/llama-cpp-compatibility", "os": ["linux"]},
{"file": "how-to/deep-learning-rocm", "os": ["linux"]},
{"file": "how-to/rocm-for-ai/index", "os": ["linux"]},

View File

@@ -28,31 +28,13 @@ See the [Python requirements file](https://github.com/ROCm/ROCm/blob/develop/doc
Use the Python Virtual Environment (`venv`) and run the following commands from the project root:
::::{tab-set}
:::{tab-item} Linux and WSL
:sync: linux
```sh
python3 -mvenv .venv
.venv/bin/python -m pip install -r docs/sphinx/requirements.txt
.venv/bin/python -m sphinx -T -E -b html -d _build/doctrees -D language=en docs _build/html
.venv/bin/python -m pip install -r docs/sphinx/requirements.txt
.venv/bin/python -m sphinx -T -E -b html -d _build/doctrees -D language=en docs _build/html
```
:::
:::{tab-item} Windows
:sync: windows
```powershell
python -mvenv .venv
.venv\Scripts\python.exe -m pip install -r docs/sphinx/requirements.txt
.venv\Scripts\python.exe -m sphinx -T -E -b html -d _build/doctrees -D language=en docs _build/html
```
:::
::::
Navigate to `_build/html/index.html` and open this file in a web browser.
## Visual Studio Code

View File

@@ -78,11 +78,7 @@ vllm_benchmark:
model_repo: Qwen/QwQ-32B
url: https://huggingface.co/Qwen/QwQ-32B
precision: float16
- model: Qwen3 30B A3B
mad_tag: pyt_vllm_qwen3-30b-a3b
model_repo: Qwen/Qwen3-30B-A3B
url: https://huggingface.co/Qwen/Qwen3-30B-A3B
precision: float16
tunableop: true
- group: Microsoft Phi
tag: phi
models:

View File

@@ -1,72 +0,0 @@
dockers:
- pull_tag: rocm/jax-training:maxtext-v25.7
docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
components:
ROCm: 6.4.1
JAX: 0.5.0
Python: 3.10.12
Transformer Engine: 2.1.0+90d703dd
hipBLASLt: 1.x.x
- pull_tag: rocm/jax-training:maxtext-v25.7-jax060
docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
components:
ROCm: 6.4.1
JAX: 0.6.0
Python: 3.10.12
Transformer Engine: 2.1.0+90d703dd
hipBLASLt: 1.1.0-499ece1c21
model_groups:
- group: Meta Llama
tag: llama
models:
- model: Llama 3.3 70B
mad_tag: jax_maxtext_train_llama-3.3-70b
model_repo: Llama-3.3-70B
precision: bf16
doc_options: ["single-node"]
- model: Llama 3.1 8B
mad_tag: jax_maxtext_train_llama-3.1-8b
model_repo: Llama-3.1-8B
precision: bf16
doc_options: ["single-node"]
- model: Llama 3.1 70B
mad_tag: jax_maxtext_train_llama-3.1-70b
model_repo: Llama-3.1-70B
precision: bf16
doc_options: ["single-node"]
- model: Llama 3 8B
mad_tag: jax_maxtext_train_llama-3-8b
multinode_training_script: llama3_8b_multinode.sh
doc_options: ["multi-node"]
- model: Llama 3 70B
mad_tag: jax_maxtext_train_llama-3-70b
multinode_training_script: llama3_70b_multinode.sh
doc_options: ["multi-node"]
- model: Llama 2 7B
mad_tag: jax_maxtext_train_llama-2-7b
model_repo: Llama-2-7B
precision: bf16
multinode_training_script: llama2_7b_multinode.sh
doc_options: ["single-node", "multi-node"]
- model: Llama 2 70B
mad_tag: jax_maxtext_train_llama-2-70b
model_repo: Llama-2-70B
precision: bf16
multinode_training_script: llama2_70b_multinode.sh
doc_options: ["single-node", "multi-node"]
- group: DeepSeek
tag: deepseek
models:
- model: DeepSeek-V2-Lite (16B)
mad_tag: jax_maxtext_train_deepseek-v2-lite-16b
model_repo: DeepSeek-V2-lite
precision: bf16
doc_options: ["single-node"]
- group: Mistral AI
tag: mistral
models:
- model: Mixtral 8x7B
mad_tag: jax_maxtext_train_mixtral-8x7b
model_repo: Mixtral-8x7B
precision: bf16
doc_options: ["single-node"]

View File

@@ -110,28 +110,6 @@ The table below summarizes information about ROCm-enabled deep learning framewor
<a href="https://github.com/ROCm/taichi"><i class="fab fa-github fa-lg"></i></a>
* - `Ray <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/ray-compatibility.html>`__
- .. raw:: html
<a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/ray-install.html"><i class="fas fa-link fa-lg"></i></a>
-
- `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/ray-install.html#using-a-prebuilt-docker-image-with-ray-pre-installed>`__
- `Wheels package <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/ray-install.html#install-ray-on-bare-metal-or-a-custom-container>`__
- `ROCm Base Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/ray-install.html#build-your-own-docker-image>`__
- .. raw:: html
<a href="https://github.com/ROCm/ray"><i class="fab fa-github fa-lg"></i></a>
* - `llama.cpp <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/llama-cpp-compatibility.html>`__
- .. raw:: html
<a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/llama-cpp-install.html"><i class="fas fa-link fa-lg"></i></a>
-
- `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/llama-cpp-install.html#use-a-prebuilt-docker-image-with-llama-cpp-pre-installed>`__
- .. raw:: html
<a href="https://github.com/ROCm/llama.cpp"><i class="fab fa-github fa-lg"></i></a>
Learn how to use your ROCm deep learning environment for training, fine-tuning, inference, and performance optimization
through the following guides.

View File

@@ -2,9 +2,9 @@
:description: How to train a model using JAX MaxText for ROCm.
:keywords: ROCm, AI, LLM, train, jax, torch, Llama, flux, tutorial, docker
******************************************
Training a model with JAX MaxText for ROCm
******************************************
**************************************
Training a model with MaxText for ROCm
**************************************
MaxText is a high-performance, open-source framework built on the Google JAX
machine learning library to train LLMs at scale. The MaxText framework for
@@ -12,108 +12,70 @@ ROCm is an optimized fork of the upstream
`<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
on AMD MI300X series accelerators.
The MaxText for ROCm training Docker image
The MaxText for ROCm training Docker (``rocm/jax-training:maxtext-v25.5``) image
provides a prebuilt environment for training on AMD Instinct MI300X and MI325X accelerators,
including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
It includes the following software components:
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+--------------------------+--------------------------------+
| Software component | Version |
+==========================+================================+
| ROCm | 6.3.4 |
+--------------------------+--------------------------------+
| JAX | 0.4.35 |
+--------------------------+--------------------------------+
| Python | 3.10.12 |
+--------------------------+--------------------------------+
| Transformer Engine | 1.12.0.dev0+b8b92dc |
+--------------------------+--------------------------------+
| hipBLASLt | 0.13.0-ae9c477a |
+--------------------------+--------------------------------+
{% set dockers = data.dockers %}
.. tab-set::
Supported features and models
=============================
{% for docker in dockers %}
{% set jax_version = docker.components["JAX"] %}
.. tab-item:: JAX {{ jax_version }}
:sync: {{ docker.pull_tag }}
.. list-table::
:header-rows: 1
* - Software component
- Version
{% for component_name, component_version in docker.components.items() %}
* - {{ component_name }}
- {{ component_version }}
{% endfor %}
{% if jax_version == "0.6.0" %}
.. note::
Shardy is a new config in JAX 0.6.0. You might get related errors if it's
not configured correctly. For now you can turn it off by setting
``shardy=False`` during the training run. You can also follow the `migration
guide <https://docs.jax.dev/en/latest/shardy_jax_migration.html>`__ to enable
it.
The provided multi-node training scripts in this documentation are
not currently supported with JAX 0.6.0. For multi-node training, use the JAX 0.5.0
Docker image.
{% endif %}
{% endfor %}
MaxText with on ROCm provides the following key features to train large language models efficiently:
MaxText provides the following key features to train large language models efficiently:
- Transformer Engine (TE)
- Flash Attention (FA) 3 -- with or without sequence input packing
- Flash Attention (FA) 3
- GEMM tuning
- Multi-node support
- NANOO FP8 quantization support
.. _amd-maxtext-model-support:
.. _amd-maxtext-model-support-v257:
The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
Supported models
================
* Llama 3.3 70B
The following models are pre-optimized for performance on AMD Instinct MI300
series accelerators. Some instructions, commands, and available training
configurations in this documentation might vary by model -- select one to get
started.
* Llama 3.1 8B
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
* Llama 3.1 70B
{% set model_groups = data.model_groups %}
.. raw:: html
* Llama 3 8B
<div id="vllm-benchmark-ud-params-picker" class="container-fluid">
<div class="row">
<div class="col-2 me-2 model-param-head">Model</div>
<div class="row col-10">
{% for model_group in model_groups %}
<div class="col-4 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
{% endfor %}
</div>
</div>
* Llama 3 70B
<div class="row mt-1">
<div class="col-2 me-2 model-param-head">Model variant</div>
<div class="row col-10">
{% for model_group in model_groups %}
{% set models = model_group.models %}
{% for model in models %}
{% if models|length % 3 == 0 %}
<div class="col-4 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
{% else %}
<div class="col-6 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
{% endif %}
{% endfor %}
{% endfor %}
</div>
</div>
</div>
* Llama 2 7B
* Llama 2 70B
* DeepSeek-V2-Lite
.. note::
Some models, such as Llama 3, require an external license agreement through
a third party (for example, Meta).
Unsupported features
--------------------
Currently, MaxText's default packed input format is not supported. Using this format
with the current Docker image results in incorrect attention calculations
across different input sequences. Support for packed input format is planned for a future release.
System validation
=================
@@ -136,14 +98,14 @@ This Docker image is optimized for specific model configurations outlined
as follows. Performance can vary for other training workloads, as AMD
doesnt validate configurations and run conditions outside those described.
.. _amd-maxtext-multi-node-setup-v257:
.. _amd-maxtext-multi-node-setup:
Multi-node setup
----------------
For multi-node environments, ensure you have all the necessary packages for
your network device, such as, RDMA. If you're not using a multi-node setup
with RDMA, skip ahead to :ref:`amd-maxtext-get-started-v257`.
with RDMA, skip ahead to :ref:`amd-maxtext-download-docker`.
1. Install the following packages to build and install the RDMA driver.
@@ -218,203 +180,196 @@ with RDMA, skip ahead to :ref:`amd-maxtext-get-started-v257`.
# If using Mellanox NIC
export NCCL_IB_HCA=mlx5_0,mlx5_1,mlx5_2,mlx5_3,mlx5_4,mlx5_5,mlx5_8,mlx5_9
.. _amd-maxtext-get-started-v257:
.. _amd-maxtext-download-docker:
Benchmarking
============
Pull the Docker image
---------------------
Once the setup is complete, choose between two options to reproduce the
benchmark results:
1. Use the following command to pull the Docker image from Docker Hub.
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
.. code-block:: shell
.. _vllm-benchmark-mad:
docker pull rocm/jax-training:maxtext-v25.5
{% set dockers = data.dockers %}
{% set model_groups = data.model_groups %}
{% for model_group in model_groups %}
{% for model in model_group.models %}
2. Use the following command to launch the Docker container. Note that the benchmarking scripts
used in the :ref:`following section <amd-maxtext-get-started>` automatically launch the Docker container
and execute the benchmark.
.. container:: model-doc {{model.mad_tag}}
.. code-block:: shell
.. tab-set::
docker run -it --device /dev/dri --device /dev/kfd --network host --ipc host --group-add video --cap-add SYS_PTRACE --security-opt seccomp=unconfined --privileged -v $HOME/.ssh:/root/.ssh --shm-size 128G --name maxtext_training rocm/jax-training:maxtext-v25.5
{% if model.mad_tag and "single-node" in model.doc_options %}
.. tab-item:: MAD-integrated benchmarking
.. _amd-maxtext-get-started:
1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
directory and install the required packages on the host machine.
.. code-block:: shell
git clone https://github.com/ROCm/MAD
cd MAD
pip install -r requirements.txt
2. Use this command to run the performance benchmark test on the {{ model.model }} model
using one GPU with the :literal:`{{model.precision}}` data type on the host machine.
.. code-block:: shell
export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
madengine run \
--tags {{model.mad_tag}} \
--keep-model-dir \
--live-output \
--timeout 28800
MAD launches a Docker container with the name
``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
model are collected in the following path: ``~/MAD/perf.csv/``.
{% endif %}
.. tab-item:: Standalone benchmarking
.. rubric:: Download the Docker image and required scripts
Run the JAX MaxText benchmark tool independently by starting the
Docker container as shown in the following snippet.
.. tab-set::
{% for docker in dockers %}
{% set jax_version = docker.components["JAX"] %}
.. tab-item:: JAX {{ jax_version }}
:sync: {{ docker.pull_tag }}
.. code-block:: shell
docker pull {{ docker.pull_tag }}
{% endfor %}
{% if model.model_repo and "single-node" in model.doc_options %}
.. rubric:: Single node training
1. Set up environment variables.
.. code-block:: shell
export MAD_SECRETS_HFTOKEN=<Your Hugging Face token>
export HF_HOME=<Location of saved/cached Hugging Face models>
``MAD_SECRETS_HFTOKEN`` is your Hugging Face access token to access models, tokenizers, and data.
See `User access tokens <https://huggingface.co/docs/hub/en/security-tokens>`__.
``HF_HOME`` is where ``huggingface_hub`` will store local data. See `huggingface_hub CLI <https://huggingface.co/docs/huggingface_hub/main/en/guides/cli#huggingface-cli-download>`__.
If you already have downloaded or cached Hugging Face artifacts, set this variable to that path.
Downloaded files typically get cached to ``~/.cache/huggingface``.
2. Launch the Docker container.
.. tab-set::
{% for docker in dockers %}
{% set jax_version = docker.components["JAX"] %}
.. tab-item:: JAX {{ jax_version }}
:sync: {{ docker.pull_tag }}
.. code-block:: shell
docker run -it \
--device=/dev/dri \
--device=/dev/kfd \
--network host \
--ipc host \
--group-add video \
--cap-add=SYS_PTRACE \
--security-opt seccomp=unconfined \
--privileged \
-v $HOME:$HOME \
-v $HOME/.ssh:/root/.ssh \
-v $HF_HOME:/hf_cache \
-e HF_HOME=/hf_cache \
-e MAD_SECRETS_HFTOKEN=$MAD_SECRETS_HFTOKEN
--shm-size 64G \
--name training_env \
{{ docker.pull_tag }}
{% endfor %}
3. In the Docker container, clone the ROCm MAD repository and navigate to the
benchmark scripts directory at ``MAD/scripts/jax-maxtext``.
.. code-block:: shell
git clone https://github.com/ROCm/MAD
cd MAD/scripts/jax-maxtext
4. Run the setup scripts to install libraries and datasets needed
for benchmarking.
.. code-block:: shell
./jax-maxtext_benchmark_setup.sh -m {{ model.model_repo }}
5. To run the training benchmark without quantization, use the following command:
.. code-block:: shell
./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }}
For quantized training, use the following command:
.. code-block:: shell
./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q nanoo_fp8
.. important::
Quantized training is not supported with the JAX 0.6.0 Docker image; support
will be added in a future release. For quantized training, use the JAX 0.5.0
Docker image: ``rocm/jax-training:maxtext-v25.7``.
{% endif %}
{% if model.multinode_training_script and "multi-node" in model.doc_options %}
.. rubric:: Multi-node training
The following examples use SLURM to run on multiple nodes.
.. note::
The following scripts will launch the Docker container and run the
benchmark. Run them outside of any Docker container.
1. Make sure ``$HF_HOME`` is set before running the test. See
`ROCm benchmarking <https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/readme.md>`__
for more details on downloading the Llama models before running the
benchmark.
2. To run multi-node training for {{ model.model }},
use the
`multi-node training script <https://github.com/ROCm/MAD/blob/develop/scripts/jax-maxtext/gpu-rocm/{{ model.multinode_training_script }}>`__
under the ``scripts/jax-maxtext/gpu-rocm/`` directory.
3. Run the multi-node training benchmark script.
.. code-block:: shell
sbatch -N <num_nodes> {{ model.multinode_training_script }}
{% else %}
.. rubric:: Multi-node training
For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v257`
with an available `multi-node training script <https://github.com/ROCm/MAD/tree/develop/scripts/jax-maxtext/gpu-rocm>`__.
{% endif %}
{% endfor %}
{% endfor %}
Further reading
Getting started
===============
- See the ROCm/maxtext benchmarking README at `<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/readme.md>`__.
The following examples demonstrate how to get started with single node
and multi-node training using the benchmarking scripts provided at
`<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__.
- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
.. important::
- To learn more about system settings and management practices to configure your system for
AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
The provided scripts launch a Docker container and execute a benchmark. Ensure you run these commands outside of any existing Docker container.
- For a list of other ready-made Docker images for AI with ROCm, see
`AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
Before running any benchmarks, ensure the ``$HF_HOME`` environment variable is
set correctly and points to your Hugging Face cache directory. Refer to the
README at `<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__
for more detailed instructions.
Single node training benchmarking examples
------------------------------------------
* Example 1: Single node training with Llama 2 7B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_7b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama2_7b.sh
* Example 2: Single node training with Llama 2 70B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_70b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama2_70b.sh
* Example 3: Single node training with Llama 3 8B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_8b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3_8b.sh
* Example 4: Single node training with Llama 3 70B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_70b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3_70b.sh
* Example 5: Single node training with Llama 3.3 70B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3.3_70b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3.3_70b.sh
* Example 6: Single node training with DeepSeek V2 16B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/deepseek_v2_16b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./deepseek_v2_16b.sh
.. note::
The reported TFLOP/s by MaxText for DeepSeek is not accurate. Use
the tokens/s as a performance indicator.
Multi-node training benchmarking examples
-----------------------------------------
The following examples use SLURM for running on multiple nodes -- the commands might need to be adjusted for your
own cluster setup.
* Example 1: Multi-node training with Llama 2 7B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_7b_multinode.sh
Run the multi-node training benchmark. For example:
.. code-block:: shell
sbatch -N <num_nodes> llama2_7b_multinode.sh
* Example 2: Multi-node training with Llama 2 70B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_70b_multinode.sh
Run the multi-node training benchmark. For example:
.. code-block:: shell
sbatch -N <num_nodes> llama2_70b_multinode.sh
* Example 3: Multi-node training with Llama 3 8B model
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_8b_multinode.sh
Run the multi-node training benchmark. For example:
.. code-block:: shell
sbatch -N <num_nodes> llama3_8b_multinode.sh
* Example 4: Multi-node training with Llama 3 70B model
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_70b_multinode.sh
Run the multi-node training benchmark. For example:
.. code-block:: shell
sbatch -N <num_nodes> llama3_70b_multinode.sh
Previous versions
=================

View File

@@ -17,21 +17,12 @@ previous releases of the ``ROCm/jax-training`` Docker image on `Docker Hub <http
- Components
- Resources
* - 25.7 (latest)
-
* ROCm 6.4.1
* JAX 0.6.0, 0.5.0
-
* :doc:`Documentation <../jax-maxtext>`
* `Docker Hub (JAX 0.6.0) <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7-jax060/images/sha256-7352212ae033a76dca2b9dceffc23c1b5f1a61a7a560082cf747a9bf1acfc9ce>`__
* `Docker Hub (JAX 0.5.0) <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025>`__
* - 25.5
* - 25.5 (latest)
-
* ROCm 6.3.4
* JAX 0.4.35
-
* :doc:`Documentation <jax-maxtext-v25.5>`
* :doc:`Documentation <../jax-maxtext>`
* `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.5/images/sha256-4e0516358a227cae8f552fb866ec07e2edcf244756f02e7b40212abfbab5217b>`__
* - 25.4

View File

@@ -51,7 +51,7 @@ MaxText provides the following key features to train large language models effic
- Multi-node support
.. _amd-maxtext-model-support-v254:
.. _amd-maxtext-model-support:
The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.

View File

@@ -1,385 +0,0 @@
:orphan:
.. meta::
:description: How to train a model using JAX MaxText for ROCm.
:keywords: ROCm, AI, LLM, train, jax, torch, Llama, flux, tutorial, docker
**************************************
Training a model with MaxText for ROCm
**************************************
.. caution::
This documentation does not reflect the latest version of ROCm JAX MaxText
training performance documentation. See :doc:`../jax-maxtext` for the latest version.
MaxText is a high-performance, open-source framework built on the Google JAX
machine learning library to train LLMs at scale. The MaxText framework for
ROCm is an optimized fork of the upstream
`<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
on AMD MI300X series accelerators.
The MaxText for ROCm training Docker (``rocm/jax-training:maxtext-v25.5``) image
provides a prebuilt environment for training on AMD Instinct MI300X and MI325X accelerators,
including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
It includes the following software components:
+--------------------------+--------------------------------+
| Software component | Version |
+==========================+================================+
| ROCm | 6.3.4 |
+--------------------------+--------------------------------+
| JAX | 0.4.35 |
+--------------------------+--------------------------------+
| Python | 3.10.12 |
+--------------------------+--------------------------------+
| Transformer Engine | 1.12.0.dev0+b8b92dc |
+--------------------------+--------------------------------+
| hipBLASLt | 0.13.0-ae9c477a |
+--------------------------+--------------------------------+
Supported features and models
=============================
MaxText provides the following key features to train large language models efficiently:
- Transformer Engine (TE)
- Flash Attention (FA) 3
- GEMM tuning
- Multi-node support
.. _amd-maxtext-model-support-v255:
The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
* Llama 3.3 70B
* Llama 3.1 8B
* Llama 3.1 70B
* Llama 3 8B
* Llama 3 70B
* Llama 2 7B
* Llama 2 70B
* DeepSeek-V2-Lite
.. note::
Some models, such as Llama 3, require an external license agreement through
a third party (for example, Meta).
Unsupported features
--------------------
Currently, MaxText's default packed input format is not supported. Using this format
with the current Docker image results in incorrect attention calculations
across different input sequences. Support for packed input format is planned for a future release.
System validation
=================
Before running AI workloads, it's important to validate that your AMD hardware is configured
correctly and performing optimally.
If you have already validated your system settings, including aspects like NUMA auto-balancing, you
can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
before starting training.
To test for optimal performance, consult the recommended :ref:`System health benchmarks
<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
system's configuration.
Environment setup
=================
This Docker image is optimized for specific model configurations outlined
as follows. Performance can vary for other training workloads, as AMD
doesnt validate configurations and run conditions outside those described.
.. _amd-maxtext-multi-node-setup-v255:
Multi-node setup
----------------
For multi-node environments, ensure you have all the necessary packages for
your network device, such as, RDMA. If you're not using a multi-node setup
with RDMA, skip ahead to :ref:`amd-maxtext-download-docker`.
1. Install the following packages to build and install the RDMA driver.
.. code-block:: shell
sudo apt install iproute2 -y
sudo apt install -y linux-headers-"$(uname-r)" libelf-dev
sudo apt install -y gcc make libtool autoconf librdmacm-dev rdmacm-utils infiniband-diags ibverbs-utils perftest ethtool libibverbs-dev rdma-core strace libibmad5 libibnetdisc5 ibverbs-providers libibumad-dev libibumad3 libibverbs1 libnl-3-dev libnl-route-3-dev
Refer to your NIC manufacturer's documentation for further steps on
compiling and installing the RoCE driver. For example, for Broadcom,
see `Compiling Broadcom NIC software from source <https://docs.broadcom.com/doc/957608-AN2XX#G3.484341>`_
in `Ethernet networking guide for AMD Instinct MI300X GPU clusters <https://docs.broadcom.com/doc/957608-AN2XX>`_.
2. Set the following environment variables.
a. Master address
Change ``localhost`` to the master node's resolvable hostname or IP address:
.. code-block:: bash
export MASTER_ADDR="${MASTER_ADDR:-localhost}"
b. Number of nodes
Set the number of nodes you want to train on (for example, ``2``, ``4``, or ``8``):
.. code-block:: bash
export NNODES="${NNODES:-1}"
c. Node ranks
Set the rank of each node (``0`` for master, ``1`` for the first worker node, and so on)
Node ranks should be unique across all nodes in the cluster.
.. code-block:: bash
export NODE_RANK="${NODE_RANK:-0}"
d. Network interface
Update the network interface in the script to match your system's network interface. To
find your network interface, run the following (outside of any Docker container):
.. code-block:: bash
ip a
Look for an active interface with an IP address in the same subnet as
your other nodes. Then, update the following variable in the script, for
example:
.. code-block:: bash
export NCCL_SOCKET_IFNAME=ens50f0np0
This variable specifies which network interface to use for inter-node communication.
Setting this variable to the incorrect interface can result in communication failures
or significantly reduced performance.
e. RDMA interface
Ensure the :ref:`required packages <amd-maxtext-multi-node-setup>` are installed on all nodes.
Then, set the RDMA interfaces to use for communication.
.. code-block:: bash
# If using Broadcom NIC
export NCCL_IB_HCA=rdma0,rdma1,rdma2,rdma3,rdma4,rdma5,rdma6,rdma7
# If using Mellanox NIC
export NCCL_IB_HCA=mlx5_0,mlx5_1,mlx5_2,mlx5_3,mlx5_4,mlx5_5,mlx5_8,mlx5_9
.. _amd-maxtext-download-docker-v255:
Pull the Docker image
---------------------
1. Use the following command to pull the Docker image from Docker Hub.
.. code-block:: shell
docker pull rocm/jax-training:maxtext-v25.5
2. Use the following command to launch the Docker container. Note that the benchmarking scripts
used in the :ref:`following section <amd-maxtext-get-started>` automatically launch the Docker container
and execute the benchmark.
.. code-block:: shell
docker run -it --device /dev/dri --device /dev/kfd --network host --ipc host --group-add video --cap-add SYS_PTRACE --security-opt seccomp=unconfined --privileged -v $HOME/.ssh:/root/.ssh --shm-size 128G --name maxtext_training rocm/jax-training:maxtext-v25.5
.. _amd-maxtext-get-started-v255:
Getting started
===============
The following examples demonstrate how to get started with single node
and multi-node training using the benchmarking scripts provided at
`<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__.
.. important::
The provided scripts launch a Docker container and execute a benchmark. Ensure you run these commands outside of any existing Docker container.
Before running any benchmarks, ensure the ``$HF_HOME`` environment variable is
set correctly and points to your Hugging Face cache directory. Refer to the
README at `<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__
for more detailed instructions.
Single node training benchmarking examples
------------------------------------------
* Example 1: Single node training with Llama 2 7B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_7b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama2_7b.sh
* Example 2: Single node training with Llama 2 70B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_70b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama2_70b.sh
* Example 3: Single node training with Llama 3 8B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_8b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3_8b.sh
* Example 4: Single node training with Llama 3 70B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_70b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3_70b.sh
* Example 5: Single node training with Llama 3.3 70B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3.3_70b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3.3_70b.sh
* Example 6: Single node training with DeepSeek V2 16B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/deepseek_v2_16b.sh
Run the single node training benchmark:
.. code-block:: shell
IMAGE="rocm/jax-training:maxtext-v25.5" bash ./deepseek_v2_16b.sh
.. note::
The reported TFLOP/s by MaxText for DeepSeek is not accurate. Use
the tokens/s as a performance indicator.
Multi-node training benchmarking examples
-----------------------------------------
The following examples use SLURM for running on multiple nodes -- the commands might need to be adjusted for your
own cluster setup.
* Example 1: Multi-node training with Llama 2 7B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_7b_multinode.sh
Run the multi-node training benchmark. For example:
.. code-block:: shell
sbatch -N <num_nodes> llama2_7b_multinode.sh
* Example 2: Multi-node training with Llama 2 70B
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_70b_multinode.sh
Run the multi-node training benchmark. For example:
.. code-block:: shell
sbatch -N <num_nodes> llama2_70b_multinode.sh
* Example 3: Multi-node training with Llama 3 8B model
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_8b_multinode.sh
Run the multi-node training benchmark. For example:
.. code-block:: shell
sbatch -N <num_nodes> llama3_8b_multinode.sh
* Example 4: Multi-node training with Llama 3 70B model
Download the benchmarking script:
.. code-block:: shell
wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_70b_multinode.sh
Run the multi-node training benchmark. For example:
.. code-block:: shell
sbatch -N <num_nodes> llama3_70b_multinode.sh
Previous versions
=================
See :doc:`jax-maxtext-history` to find documentation for previous releases
of the ``ROCm/jax-training`` Docker image.

View File

@@ -32,23 +32,19 @@ subtrees:
- file: compatibility/ml-compatibility/pytorch-compatibility.rst
title: PyTorch compatibility
- file: compatibility/ml-compatibility/tensorflow-compatibility.rst
title: TensorFlow compatibility
title: TensorFlow compatibility
- file: compatibility/ml-compatibility/jax-compatibility.rst
title: JAX compatibility
- file: compatibility/ml-compatibility/verl-compatibility.rst
title: verl compatibility
title: verl compatibility
- file: compatibility/ml-compatibility/stanford-megatron-lm-compatibility.rst
title: Stanford Megatron-LM compatibility
- file: compatibility/ml-compatibility/dgl-compatibility.rst
title: DGL compatibility
title: DGL compatibility
- file: compatibility/ml-compatibility/megablocks-compatibility.rst
title: Megablocks compatibility
- file: compatibility/ml-compatibility/taichi-compatibility.rst
title: Taichi compatibility
- file: compatibility/ml-compatibility/ray-compatibility.rst
title: Ray compatibility
- file: compatibility/ml-compatibility/llama-cpp-compatibility.rst
title: llama.cpp compatibility
title: Taichi compatibility
- file: how-to/build-rocm.rst
title: Build ROCm from source

View File

@@ -1,4 +1,4 @@
rocm-docs-core==1.20.1
rocm-docs-core==1.22.0
sphinx-reredirects
sphinx-sitemap
sphinxcontrib.datatemplates==0.11.0

View File

@@ -23,7 +23,7 @@ beautifulsoup4==4.13.4
# via pydata-sphinx-theme
breathe==4.36.0
# via rocm-docs-core
certifi==2025.4.26
certifi==2025.7.14
# via requests
cffi==1.17.1
# via
@@ -35,18 +35,16 @@ click==8.2.1
# via
# jupyter-cache
# sphinx-external-toc
comm==0.2.2
comm==0.2.3
# via ipykernel
cryptography==45.0.3
cryptography==45.0.5
# via pyjwt
debugpy==1.8.14
debugpy==1.8.15
# via ipykernel
decorator==5.2.1
# via ipython
defusedxml==0.7.1
# via sphinxcontrib-datatemplates
deprecated==1.2.18
# via pygithub
docutils==0.21.2
# via
# myst-parser
@@ -62,7 +60,7 @@ fastjsonschema==2.21.1
# rocm-docs-core
gitdb==4.0.12
# via gitpython
gitpython==3.1.44
gitpython==3.1.45
# via rocm-docs-core
greenlet==3.2.3
# via sqlalchemy
@@ -74,7 +72,7 @@ importlib-metadata==8.7.0
# via
# jupyter-cache
# myst-nb
ipykernel==6.29.5
ipykernel==6.30.0
# via myst-nb
ipython==8.37.0
# via
@@ -86,7 +84,7 @@ jinja2==3.1.6
# via
# myst-parser
# sphinx
jsonschema==4.24.0
jsonschema==4.25.0
# via nbformat
jsonschema-specifications==2025.4.1
# via jsonschema
@@ -116,7 +114,7 @@ mdit-py-plugins==0.4.2
# via myst-parser
mdurl==0.1.2
# via markdown-it-py
myst-nb==1.2.0
myst-nb==1.3.0
# via rocm-docs-core
myst-parser==4.0.1
# via myst-nb
@@ -134,7 +132,6 @@ nest-asyncio==1.6.0
packaging==25.0
# via
# ipykernel
# pydata-sphinx-theme
# sphinx
parso==0.8.4
# via jedi
@@ -152,13 +149,13 @@ pure-eval==0.2.3
# via stack-data
pycparser==2.22
# via cffi
pydata-sphinx-theme==0.15.4
pydata-sphinx-theme==0.16.1
# via
# rocm-docs-core
# sphinx-book-theme
pygithub==2.6.1
pygithub==2.7.0
# via rocm-docs-core
pygments==2.19.1
pygments==2.19.2
# via
# accessible-pygments
# ipython
@@ -178,7 +175,7 @@ pyyaml==6.0.2
# rocm-docs-core
# sphinx-external-toc
# sphinxcontrib-datatemplates
pyzmq==26.4.0
pyzmq==27.0.0
# via
# ipykernel
# jupyter-client
@@ -190,9 +187,9 @@ requests==2.32.4
# via
# pygithub
# sphinx
rocm-docs-core==1.20.1
rocm-docs-core==1.22.0
# via -r requirements.in
rpds-py==0.25.1
rpds-py==0.26.0
# via
# jsonschema
# referencing
@@ -220,7 +217,7 @@ sphinx==8.1.3
# sphinx-reredirects
# sphinxcontrib-datatemplates
# sphinxcontrib-runcmd
sphinx-book-theme==1.1.4
sphinx-book-theme==1.1.3
# via rocm-docs-core
sphinx-copybutton==0.5.2
# via rocm-docs-core
@@ -234,7 +231,7 @@ sphinx-notfound-page==1.1.0
# via rocm-docs-core
sphinx-reredirects==0.1.6
# via -r requirements.in
sphinx-sitemap==2.8.0
sphinx-sitemap==2.7.2
# via -r requirements.in
sphinxcontrib-applehelp==2.0.0
# via sphinx
@@ -252,7 +249,7 @@ sphinxcontrib-runcmd==0.2.0
# via sphinxcontrib-datatemplates
sphinxcontrib-serializinghtml==2.0.0
# via sphinx
sqlalchemy==2.0.41
sqlalchemy==2.0.42
# via jupyter-cache
stack-data==0.6.3
# via ipython
@@ -266,7 +263,6 @@ tornado==6.5.1
# jupyter-client
traitlets==5.14.3
# via
# comm
# ipykernel
# ipython
# jupyter-client
@@ -274,7 +270,7 @@ traitlets==5.14.3
# matplotlib-inline
# nbclient
# nbformat
typing-extensions==4.14.0
typing-extensions==4.14.1
# via
# beautifulsoup4
# exceptiongroup
@@ -290,7 +286,5 @@ urllib3==2.5.0
# requests
wcwidth==0.2.13
# via prompt-toolkit
wrapt==1.17.2
# via deprecated
zipp==3.23.0
# via importlib-metadata

View File

@@ -1,7 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<manifest>
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
<default revision="refs/tags/rocm-6.4.3"
<default revision="refs/tags/rocm-6.4.2"
remote="rocm-org"
sync-c="true"
sync-j="4" />

View File

@@ -1,79 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<manifest>
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
<default revision="refs/tags/20250912-42"
remote="rocm-org"
sync-c="true"
sync-j="4" />
<!--list of projects for ROCm-->
<project name="aqlprofile" />
<project name="ROCR-Runtime" />
<project name="amdsmi" />
<project name="rdc" />
<project name="rocm_bandwidth_test" />
<project name="rocm_smi_lib" />
<project name="rocm-core" />
<project name="rocm-examples" />
<project name="rocminfo" />
<project name="rocprofiler" />
<project name="rocprofiler-register" />
<project name="rocprofiler-sdk" />
<project name="rocprofiler-compute" />
<project name="rocprofiler-systems" />
<project name="roctracer" />
<!--HIP Projects-->
<project name="HIP" />
<project name="hip-tests" />
<project name="HIPIFY" />
<project name="clr" />
<project name="hipother" />
<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
<project name="half" />
<project name="llvm-project" />
<project name="spirv-llvm-translator" />
<!-- gdb projects -->
<project name="ROCdbgapi" />
<project name="ROCgdb" />
<project name="rocr_debug_agent" />
<!-- ROCm Libraries -->
<project groups="mathlibs" name="AMDMIGraphX" />
<project groups="mathlibs" name="MIVisionX" />
<project groups="mathlibs" name="ROCmValidationSuite" />
<project groups="mathlibs" name="composable_kernel" />
<project groups="mathlibs" name="hipSOLVER" />
<project groups="mathlibs" name="hipTensor" />
<project groups="mathlibs" name="hipfort" />
<project groups="mathlibs" name="rccl" />
<project groups="mathlibs" name="rocAL" />
<project groups="mathlibs" name="rocALUTION" />
<project groups="mathlibs" name="rocDecode" />
<project groups="mathlibs" name="rocJPEG" />
<project groups="mathlibs" name="rocm-libraries">
<linkfile src="projects/hipcub" dest="hipCUB"/>
<linkfile src="projects/rocprim" dest="rocPRIM"/>
<linkfile src="projects/hiprand" dest="hipRAND"/>
<linkfile src="projects/rocrand" dest="rocRAND"/>
<linkfile src="projects/rocthrust" dest="rocThrust"/>
<linkfile src="projects/hipblas-common" dest="hipBLAS-common"/>
<linkfile src="projects/hipblaslt" dest="hipBLASLt"/>
<linkfile src="projects/rocblas" dest="rocBLAS"/>
<linkfile src="projects/hipsparselt" dest="hipSPARSELt"/>
<linkfile src="projects/rocsparse" dest="rocSPARSE"/>
<linkfile src="projects/hipsparse" dest="hipSPARSE"/>
<linkfile src="projects/hipblas" dest="hipBLAS"/>
<linkfile src="projects/miopen" dest="MIOpen"/>
<linkfile src="projects/hipfft" dest="hipFFT"/>
<linkfile src="projects/rocfft" dest="rocFFT"/>
</project>
<project groups="mathlibs" name="rocPyDecode" />
<project groups="mathlibs" name="rocSHMEM" />
<project groups="mathlibs" name="rocSOLVER" />
<project groups="mathlibs" name="rocWMMA" />
<project groups="mathlibs" name="rocm-cmake" />
<project groups="mathlibs" name="rpp" />
<project groups="mathlibs" name="TransferBench" />
<!-- Projects for OpenMP-Extras -->
<project name="aomp" path="openmp-extras/aomp" />
<project name="aomp-extras" path="openmp-extras/aomp-extras" />
<project name="flang" path="openmp-extras/flang" />
</manifest>

View File

@@ -1,79 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<manifest>
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
<default revision="refs/tags/rocm-6.4.3"
remote="rocm-org"
sync-c="true"
sync-j="4" />
<!--list of projects for ROCm-->
<project name="ROCm" revision="roc-6.4.x" />
<project name="ROCK-Kernel-Driver" />
<project name="ROCR-Runtime" />
<project name="amdsmi" />
<project name="rdc" />
<project name="rocm_bandwidth_test" />
<project name="rocm_smi_lib" />
<project name="rocm-core" />
<project name="rocm-examples" />
<project name="rocminfo" />
<project name="rocprofiler" />
<project name="rocprofiler-register" />
<project name="rocprofiler-sdk" />
<project name="rocprofiler-compute" />
<project name="rocprofiler-systems" />
<project name="roctracer" />
<!--HIP Projects-->
<project name="hip" />
<project name="hip-tests" />
<project name="HIPIFY" />
<project name="clr" />
<project name="hipother" />
<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
<project name="half" />
<project name="llvm-project" />
<project name="spirv-llvm-translator" />
<!-- gdb projects -->
<project name="ROCdbgapi" />
<project name="ROCgdb" />
<project name="rocr_debug_agent" />
<!-- ROCm Libraries -->
<project groups="mathlibs" name="AMDMIGraphX" />
<project groups="mathlibs" name="MIOpen" />
<project groups="mathlibs" name="MIVisionX" />
<project groups="mathlibs" name="ROCmValidationSuite" />
<project groups="mathlibs" name="Tensile" />
<project groups="mathlibs" name="composable_kernel" />
<project groups="mathlibs" name="hipBLAS-common" />
<project groups="mathlibs" name="hipBLAS" />
<project groups="mathlibs" name="hipBLASLt" />
<project groups="mathlibs" name="hipCUB" />
<project groups="mathlibs" name="hipFFT" />
<project groups="mathlibs" name="hipRAND" />
<project groups="mathlibs" name="hipSOLVER" />
<project groups="mathlibs" name="hipSPARSE" />
<project groups="mathlibs" name="hipSPARSELt" />
<project groups="mathlibs" name="hipTensor" />
<project groups="mathlibs" name="hipfort" />
<project groups="mathlibs" name="rccl" />
<project groups="mathlibs" name="rocAL" />
<project groups="mathlibs" name="rocALUTION" />
<project groups="mathlibs" name="rocBLAS" />
<project groups="mathlibs" name="rocDecode" />
<project groups="mathlibs" name="rocJPEG" />
<project groups="mathlibs" name="rocPyDecode" />
<project groups="mathlibs" name="rocFFT" />
<project groups="mathlibs" name="rocPRIM" />
<project groups="mathlibs" name="rocRAND" />
<project groups="mathlibs" name="rocSHMEM" />
<project groups="mathlibs" name="rocSOLVER" />
<project groups="mathlibs" name="rocSPARSE" />
<project groups="mathlibs" name="rocThrust" />
<project groups="mathlibs" name="rocWMMA" />
<project groups="mathlibs" name="rocm-cmake" />
<project groups="mathlibs" name="rpp" />
<project groups="mathlibs" name="TransferBench" />
<!-- Projects for OpenMP-Extras -->
<project name="aomp" path="openmp-extras/aomp" />
<project name="aomp-extras" path="openmp-extras/aomp-extras" />
<project name="flang" path="openmp-extras/flang" />
</manifest>