Compare commits

..

50 Commits

Author SHA1 Message Date
Sam Wu
bdbd336d41 Update documentation requirements 2024-09-16 10:13:14 -08:00
Jeffrey Novotny
c4e752a7c6 Merge pull request #3567 from amd-jnovotny/peak-tflops-typo-docs611
Fix typo for TFLOPs metric in MI250 architecture page: cherry-pick to docs/6.1.1
2024-08-12 13:17:59 -04:00
Jeffrey Novotny
3518cc3801 Fix typo for TFLOPs metric in MI250 architecture page 2024-08-12 10:22:11 -04:00
Jeffrey Novotny
4419ad4535 Merge pull request #3531 from amd-jnovotny/update-llama-link-611
Fix link to meta-llama finetuning recipes
2024-08-07 12:42:37 -04:00
Jeffrey Novotny
86e6921cbf Fix link to meta-llama finetuning recipes 2024-08-06 15:50:35 -04:00
spolifroni-amd
cf6b9f4847 Cherry picking removal of email feedback into 6.1.1 (#3490)
* removed all references to the feedback email

* making the linter happy
2024-08-02 11:58:45 -06:00
randyh62
83df73a564 Update using-gpu-sanitizer.md with new known issues (#3423) (#3439)
Co-authored-by: b-sumner <brian.sumner@amd.com>
2024-07-18 20:42:06 -07:00
spolifroni-amd
b80f22f71a Merge pull request #3425 from spolifroni-amd/sp-cherry-pick-611
Cherry picking into 6.1.1
2024-07-16 16:45:41 -04:00
Peter Park
036cf71355 Update system optimization guides headings (#3422)
* update headings to system optimization

* update index

* conv tuning-guides.md to rst

* shorten system optimization landing page

* update conf.py

update toc order

add space

* Update docs/how-to/tuning-guides.rst

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

* update keywords

* update intro

---------

Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
2024-07-16 16:25:02 -04:00
spolifroni-amd
94e552315d Removed TransferBench from the tools list (#3421) 2024-07-16 16:20:07 -04:00
Peter Park
a54a8a13a2 Merge pull request #3392 from peterjunpark/docs/6.1.1
docs/6.1.1: update CLR docs reference (#3389)
2024-07-03 17:43:05 -04:00
randyh62
57ee1adcff update CLR docs reference (#3389)
* update CLR docs reference

* Apply suggestions from code review

Co-authored-by: Peter Park <peter.park@amd.com>

---------

Co-authored-by: amitkumar-amd <Amit.Kumar6@amd.com>
Co-authored-by: Peter Park <peter.park@amd.com>
2024-07-03 17:01:51 -04:00
Peter Park
0fd9f12687 Merge pull request #3377 from peterjunpark/docs/6.1.1
docs/6.1.1: remove card text styling
2024-07-01 22:03:28 -04:00
Peter Jun Park
1530837021 remove card text styling 2024-06-28 18:57:10 -04:00
Peter Park
ea2f4abccd Merge pull request #3367 from peterjunpark/docs/6.1.1
docs/6.1.1: Add fixes to vLLM install and triton kernel optimization (#3366)
2024-06-27 11:45:57 -07:00
Peter Park
cb188e6bb8 Add fixes to vLLM install and triton kernel optimization (#3366)
* Add fixes to vLLM install and triton kernel optimization

* Update TGI how-to

remove extra step in TGI
2024-06-27 14:30:00 -04:00
randyh62
80cbe0a744 added ROCm Core and AMD SMI (#3348) (#3350)
* added ROCm Core and AMD SMI

* fix URLs
2024-06-21 17:10:52 -07:00
randyh62
10633f33eb license information updated (#3339) (#3341)
* license information updated

* Young's comments

* Sam's comment
2024-06-21 09:44:54 -07:00
Peter Park
c27cc438c6 Merge pull request #3335 from peterjunpark/docs/6.1.1
docs/6.1.1: Add RHEL 9.4 to compat matrix (#3332)
2024-06-19 12:40:57 -07:00
Peter Park
0fc8670f94 Add RHEL 9.4 to compat matrix (#3332)
* Add RHEL 9.4 to compat matrix

* add rhel 9.4 footnote in compat matrix
2024-06-19 15:08:52 -04:00
Peter Park
f5fadd6aff Merge pull request #3328 from peterjunpark/docs/6.1.1
Add Oracle Linux support notes to 6.1.1
2024-06-18 19:18:10 -07:00
randyh62
d8d4d2eacd remove nvcc (#3313) (#3321)
* remove nvcc

* Update CHANGELOG to match 6.0.0 template

---------

Co-authored-by: Sam Wu <22262939+samjwu@users.noreply.github.com>
2024-06-18 17:26:19 -07:00
Peter Park
1ae6aee3b1 Add OL support note to compat matrix (#3325)
Fix footnote

Footnote order

Satisfy spellcheck
2024-06-18 18:41:28 -04:00
Peter Jun Park
1d151c043c Update RELEASE.md with CHANGELOG update 2024-06-18 18:38:38 -04:00
Peter Park
b058ed9448 Add Oracle Linux 8.9 to 6.1.1 changelog (#3327) 2024-06-18 18:37:14 -04:00
Peter Park
27f94556f0 Merge pull request #3315 from peterjunpark/docs/6.1.1
Update GA date in 6.1.1 release notes
2024-06-18 12:22:05 -07:00
Peter Jun Park
6bd4b84e30 Update GA date in release notes 2024-06-18 10:03:52 -04:00
Peter Park
bfc8f62ea2 Merge pull request #3309 from peterjunpark/docs/6.1.1
docs/6.1.1: Cherry-pick "What is ROCm?" clean-up (#3303) (#3282)
2024-06-17 10:34:40 -07:00
Peter Park
e08c7d628b Remove aomp from What is ROCm? page (#3282) 2024-06-17 11:50:01 -04:00
Peter Park
4a5a411a7b Update link to ROCr Debug Agent to docs portal (#3303)
* Fix link to debug agent in what-is-rocm

* ROCm --> ROCR

add index

* ROCR --> ROCr

* Change ROCm Debug Agent to ROCr Debug Agent in docs
2024-06-17 11:49:52 -04:00
Peter Park
793207d5f4 Fix first link in compatibility matrix table (#3239) (#3299)
* Fix first link in compatibility matrix table

* Revert "Fix first link in compatibility matrix table"

This reverts commit 069c5c116a.

* Remove sticky header and unused css

* Remove container from hardware specs matrix

---------

Co-authored-by: Sam Wu <22262939+samjwu@users.noreply.github.com>
2024-06-13 16:45:42 -04:00
randyh62
de357d7c9d update quarantine (#3284) (#3290) 2024-06-13 11:19:52 -07:00
Jeffrey Novotny
32f7a4856b Merge pull request #3297 from amd-jnovotny/port-aomp-fix-611
Remove AOMP from compatibility matrix (#3289)
2024-06-13 11:42:41 -04:00
Jeffrey Novotny
40492d4039 Remove AOMP from compatibility matrix (#3289) 2024-06-13 11:33:38 -04:00
Istvan Kiss
9a1d8bd7ea Update docs/conceptual/setting-cus.rst
Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>
2024-06-11 13:36:21 +02:00
Bence Parajdi
4ce277d44a Merge pull request #3062 from StreamHPC/cu
add cu setting page
2024-06-11 13:36:21 +02:00
Sam Wu
404017800b Update documentation requirements 2024-06-06 16:58:59 -06:00
Peter Park
fd92cf9ba4 Merge pull request #3256 from peterjunpark/docs/6.1.1
docs/6.1.1: Update links in compat matrix and what-is-rocm (#3253)
2024-06-06 10:52:36 -07:00
Peter Park
f08b2a88ec Update links in compat matrix and what-is-rocm (#3253)
* Update links in compat matrix and what-is-rocm

* Tensorflow -> TensorFlow

* Remove extra lines

* Revert "Remove extra lines"

This reverts commit 607c4323ac.

ROCm Debug Agent
2024-06-06 13:29:24 -04:00
Young Hui - AMD
632f864466 fix links for MIVisionX (#3240) (#3249) 2024-06-05 16:05:16 -04:00
Peter Park
7d35f4cf44 Merge pull request #3244 from peterjunpark/docs/6.1.1
docs/6.1.1: Rename fine-tuning and optimization guide directory and fix index.md …
2024-06-05 08:44:34 -07:00
Peter Park
c95c7638b8 Rename fine-tuning and optimization guide directory and fix index.md (#3242)
* Mv fine-tuning and optimization files

* Reorder index.md

* Rename images directory

* Fix internal links
2024-06-05 11:13:02 -04:00
Peter Park
4792364033 Merge pull request #3228 from peterjunpark/docs/6.1.1
docs/6.1.1: Update the links for rocminfo and rocm-bandwidth-test (#3213)
2024-06-04 08:12:05 -07:00
amitkumar-amd
dca8f0b896 Update the links for rocminfo and rocm-bandwidth-test (#3213)
* Update the links for rocminfo and rocm-bandwidth-test

* Update the links for rocminfo and rocm-bandwidth-test

* Update the links for rocminfo and rocm-bandwidth-test

* Update links to intersphinx links

---------

Co-authored-by: Peter Jun Park <peter.park@amd.com>
2024-06-04 11:01:29 -04:00
Peter Park
54ba20ea7e Merge pull request #3225 from peterjunpark/docs/6.1.1
docs/6.1.1: Update fine-tuning guide: title, improve readibility in code blocks, …
2024-06-04 07:02:41 -07:00
Peter Park
06136b8c58 Update fine-tuning guide: title, improve readibility in code blocks, fix typos (#3222)
* Fix typo

* Add torchtune link

* Add newlines before comments in code blocks for readability

* Update title
2024-06-03 22:12:31 -04:00
Peter Park
fd39cada5c Merge pull request #3219 from peterjunpark/docs/6.1.1
Disable epub in 6.1.1
2024-06-03 13:11:39 -07:00
Sam Wu
1fafc06500 Disable epub (#2557) 2024-06-03 15:41:30 -04:00
Peter Park
b039209968 Merge pull request #3217 from peterjunpark/docs/6.1.1
docs/6.1.1: Add "Fine Tuning LLMs" how to guide (#3124)
2024-06-03 11:16:03 -07:00
Peter Park
365fec8a18 Add "Fine Tuning LLMs" how to guide (#3124)
* Add Fine Tuning LLMs how to guide

* Reorg and refactor Fine-tuning LLMs with ROCm

Update index and headings

Fix formatting and update toc

Split out content from index to overview.rst

Add metadata

Clean up overview

Add inference sections, fix rst errors, clean up single-gpu-fine-tuning

Combine fine-tuning and inference guides

Fix some links and formatting

Update toc and add formatting fixes

Add ck kernel fusion content

Update toc

Clean up model quantization and acceleration

Add CK images

Clean up profiling

Update triton kernel performance optimization

Update llm inference frameworks guide

Disable automatic number of figures and tables in Sphinx conf

Change tabs to spaces

Change heading to end with -ing

Add link fixes and heading updates

Add rocprof/Omniperf/Omnitrace section

Update profiling and debugging guide

Add formatting fixes

Satisfy spellcheck

Fix words

Delete unused file

Finish overview

Clean up first 4 sections

Multi-gpu fine-tuning guide: slight fixes

Update toc

Remove tabs

Formatting fixes

* Minor wording updates

* Add some clean-up

* Update profiling and debugging gudie

* Fix Omnitrace link

* Update ck kernel fusion with latest

* Update CK formatting

* Fix perfetto link syntax

* Fix typos and add blurbs

* Add fixes to Triton optimization doc

* Tabify saving adapters / models section

* Fix linting errors - spellcheck

Fix spelling and grammar

Satisfy linter

Update wording in profiling guide

Add fixes to satisfy linter

More fixes for linting in Triton guide

More linting fixes

Spellcheck in CK guide

* Improve triton guide

Fix linting errors and optics

* Add occupancy / vgpr table

Change some wording

* Re-add tunableop

* Add missing indent in _toc.yml

* Remove ckProfiler references

* Add links to resources

* Add refs in CK optimization guide

* Rename files and fix internal links

* Organize tuning guides

Reorg triton

* Add compute unit diagram

* Remove AutoAWQ

* Add higher res image for Perfetto trace example

* Update link text

* Update fig nums

* Update some formatting

* Update "Inductor"

* Change "Inductor" to TorchInductor

* Add link to official TorchInductor docs
2024-06-03 14:06:37 -04:00
161 changed files with 1182 additions and 12833 deletions

View File

@@ -1,29 +0,0 @@
variables:
- group: common
- template: /.azuredevops/variables-global.yml
resources:
repositories:
- repository: release_repo
type: github
endpoint: ROCm
name: ROCm/aomp
ref: aomp-dev
- repository: llvm-project_repo
type: github
endpoint: ROCm
name: ROCm/llvm-project
ref: amd-staging
pipelines:
- pipeline: rocr-runtime_pipeline
source: \ROCR-Runtime
trigger: true
# this job will only be triggered after successful build sequence of llvm-project and ROCR-Runtime
trigger: none
pr: none
jobs:
- template: ${{ variables.CI_COMPONENT_PATH }}/aomp.yml
parameters:
checkoutRepo: release_repo

View File

@@ -84,8 +84,8 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_BUILD_TYPE=Release
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm

View File

@@ -9,29 +9,20 @@ parameters:
type: object
default:
- software-properties-common
- python3-pip
- cmake
- ninja-build
- composablekernel-dev
- half
- rocrand
- rocblas
- libsqlite3-dev
- libbz2-dev
- nlohmann-json3-dev
- libgtest-dev
- libdrm-dev
- name: rocmDependencies
type: object
default:
- rocMLIR
- rocRAND
- rocBLAS
- half
- composable_kernel
- rocm-cmake
- llvm-project
- ROCR-Runtime
- rocprofiler-register
- clr
- rocminfo
- roctracer
jobs:
- job: MIOpen
@@ -39,6 +30,8 @@ jobs:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -77,8 +70,9 @@ jobs:
parameters:
extraBuildFlags: >-
-DMIOPEN_BACKEND=HIP
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
-DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
-DMIOPEN_ENABLE_AI_KERNEL_TUNING=OFF
-DMIOPEN_ENABLE_AI_IMMED_MODE_FALLBACK=OFF
-DCMAKE_BUILD_TYPE=Release

View File

@@ -14,6 +14,10 @@ parameters:
- wget
- unzip
- pkg-config
- half
- rocblas-dev
- miopen-hip-dev
- migraphx-dev
- protobuf-compiler
- libprotoc-dev
- ffmpeg
@@ -21,6 +25,10 @@ parameters:
- libavformat-dev
- libavutil-dev
- libswscale-dev
- rpp
- rpp-dev
- rocdecode
- rocdecode-dev
- build-essential
- libgtk2.0-dev
- libavcodec-dev
@@ -33,7 +41,6 @@ parameters:
- libtiff-dev
- libdc1394-dev
- libgmp-dev
- libopencv-dev
- name: pipModules
type: object
default:
@@ -43,21 +50,6 @@ parameters:
- google==3.0.0
- protobuf==3.12.4
- onnx==1.12.0
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocprofiler-register
- half
- rocBLAS
- MIOpen
- AMDMIGraphX
- rpp
- rocDecode
jobs:
- job: MIVisionX
@@ -66,6 +58,8 @@ jobs:
- template: /.azuredevops/variables-global.yml
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -77,23 +71,11 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_BUILD_TYPE=Release
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DROCM_PATH=/opt/rocm
-DROCM_DEP_ROCMCORE=ON
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -10,13 +10,6 @@ parameters:
default:
- cmake
- ninja-build
- name: rocmDependencies
type: object
default:
- clr
- llvm-project
- rocminfo
- ROCR-Runtime
jobs:
- job: ROCdbgapi
@@ -25,6 +18,8 @@ jobs:
- template: /.azuredevops/variables-global.yml
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -35,22 +30,9 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_BUILD_TYPE=Release
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -10,33 +10,22 @@ parameters:
default:
- cmake
- ninja-build
- rocblas
- libyaml-cpp-dev
- libpci-dev
- libpci3
- googletest
- git
- name: rocmDependencies
type: object
default:
- clr
- llvm-project
- rocBLAS
- rocm-cmake
- rocm_smi_lib
- rocminfo
- rocprofiler-register
- ROCR-Runtime
- ROCT-Thunk-Interface
jobs:
- job: ROCmValidationSuite
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Build.BinariesDirectory)/rocm
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -47,23 +36,11 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCPACK_PACKAGING_INSTALL_PREFIX=$(Build.BinariesDirectory)
-DROCM_PATH=/opt/rocm
-DCMAKE_PREFIX_PATH=/opt/rocm
-DCPACK_PACKAGING_INSTALL_PREFIX='$(Build.BinariesDirectory)'
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -5,9 +5,6 @@ parameters:
- name: checkoutRef
type: string
default: ''
- name: offloadEnabled
type: boolean
default: false
- name: aptPackages
type: object
default:
@@ -97,18 +94,18 @@ jobs:
cmakeBuildDir: $(Build.SourcesDirectory)/llvm-project/openmp/build
installDir: $(Build.BinariesDirectory)/llvm
# offload does not exist for recent releases, so use CI conditional
- ${{ if eq(parameters.offloadEnabled, true) }}:
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
componentName: llvm-offload
extraBuildFlags: >-
-DOPENMP_ENABLE_LIBOMPTARGET=1
-DOPENMP_TEST_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
-DOPENMP_TEST_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
-DOPENMP_TEST_C_COMPILER==$(Agent.BuildDirectory)/rocm/llvm/bin/clang
-DOPENMP_TEST_CXX_COMPILER==$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
-DCMAKE_C_COMPILER==$(Agent.BuildDirectory)/rocm/llvm/bin/clang
-DCMAKE_CXX_COMPILER==$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
-DLIBOMPTARGET_AMDGCN_GFXLIST=gfx700;gfx701;gfx801;gfx803;gfx900;gfx902;gfx906;gfx908;gfx90a;gfx90c;gfx940;gfx941;gfx942;gfx1030;gfx1031;gfx1035;gfx1036;gfx1100;gfx1101;gfx1102;gfx1103
-DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm
-DLLVM_DIR==$(Agent.BuildDirectory)/rocm/llvm
-DLLVM_MAIN_INCLUDE_DIR=$(Build.SourcesDirectory)/llvm-project/llvm/include
-DLIBOMPTARGET_LLVM_INCLUDE_DIRS=$(Build.SourcesDirectory)/llvm-project/llvm/include
-DCUDA_TOOLKIT_ROOT_DIR=OFF

View File

@@ -11,16 +11,6 @@ parameters:
- cmake
- ninja-build
- git
- python3-pip
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocprofiler-register
jobs:
- job: composable_kernel
@@ -28,6 +18,8 @@ jobs:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -38,24 +30,11 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
-DCMAKE_BUILD_TYPE=Release
-DGPU_TARGETS=gfx1030;gfx1100
-GNinja

View File

@@ -8,17 +8,8 @@ parameters:
- name: aptPackages
type: object
default:
- python3-pip
- cmake
- ninja-build
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
jobs:
- job: half
@@ -27,6 +18,8 @@ jobs:
- template: /.azuredevops/variables-global.yml
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -37,22 +30,9 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -10,33 +10,25 @@ parameters:
default:
- cmake
- ninja-build
- rocblas-dev
- rocsparse
- rocsolver-dev
- gfortran
- googletest
- git
- libgtest-dev
- wget
- python3-pip
- libomp-dev
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocprofiler-register
- rocBLAS
- rocSPARSE
- rocSOLVER
- aomp
jobs:
- job: hipBLAS
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: LD_LIBRARY_PATH
value: '/lib:/usr/lib:/usr/local/lib'
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -59,24 +51,20 @@ jobs:
targetType: inline
script: sudo apt install --yes ./aocl-linux-aocc-4.1.0_1_amd64.deb
workingDirectory: '$(Pipeline.Workspace)'
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- task: Bash@3
displayName: 'ldconfig'
inputs:
targetType: inline
script: sudo ldconfig
workingDirectory: '/usr/local/lib'
- script: 'ls -1R /usr/local'
displayName: 'Artifact listing'
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_PREFIX_PATH=/opt/rocm
-DCMAKE_BUILD_TYPE=Release
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DHIP_PLATFORM=amd
-DBUILD_CLIENTS_TESTS=ON

View File

@@ -8,44 +8,25 @@ parameters:
- name: aptPackages
type: object
default:
- cmake
- ninja-build
- python3-venv
- libmsgpack-dev
- hipblas-dev
- git
- python3-pip
- libdrm-dev
- name: pipModules
type: object
default:
- joblib
- name: rocmDependencies
type: object
default:
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocprofiler-register
- hipBLAS
jobs:
- job: hipBLASLt
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Build.BinariesDirectory)/rocm
- name: TENSILE_ROCM_ASSEMBLER_PATH
value: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
- name: CMAKE_CXX_COMPILER
value: $(Agent.BuildDirectory)/rocm/bin/hipcc
- name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
- name: TENSILE_ROCM_PATH
value: $(Agent.BuildDirectory)/rocm/bin/hipcc
- name: PATH
value: $(Agent.BuildDirectory)/rocm/llvm/bin:$(Agent.BuildDirectory)/rocm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/snap/bin
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -53,36 +34,21 @@ jobs:
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- script: sudo ln -s $(Agent.BuildDirectory)/rocm /opt/rocm
displayName: ROCm symbolic link
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_BUILD_TYPE=Release
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
-DAMDGPU_TARGETS=gfx90a
-DTensile_LOGIC=
-DTensile_CPU_THREADS=
-DTensile_CODE_OBJECT_VERSION=default
-DTensile_LIBRARY_FORMAT=msgpack
-DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
-DCMAKE_PREFIX_PATH="/opt/rocm"
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -10,17 +10,9 @@ parameters:
default:
- cmake
- ninja-build
- rocprim
- googletest
- git
- python3-pip
- name: rocmDependencies
type: object
default:
- clr
- llvm-project
- rocminfo
- rocPRIM
- ROCR-Runtime
jobs:
- job: hipCUB
@@ -28,6 +20,8 @@ jobs:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -38,24 +32,12 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
-DCMAKE_PREFIX_PATH="/opt/rocm"
-DBUILD_TEST=ON
-DAMDGPU_TARGETS=gfx1030;gfx1100
-GNinja

View File

@@ -10,32 +10,22 @@ parameters:
default:
- cmake
- ninja-build
- rocrand
- hiprand
- rocfft
- libboost-program-options-dev
- libgtest-dev
- googletest
- libfftw3-dev
- python3-pip
- libomp-14-dev
# rocm dependencies should match dependencies-rocm.yml
- name: rocmDependencies
type: object
default:
- rocRAND
- hipRAND
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocFFT
- aomp
jobs:
- job: hipFFT
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Build.BinariesDirectory)/rocm
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -46,31 +36,16 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
-DCMAKE_BUILD_TYPE=Release
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DUSE_HIP_CLANG=ON
-DHIP_COMPILER=clang
-DBUILD_CLIENTS_TESTS=ON
-DBUILD_CLIENTS_BENCHMARKS=OFF
-DBUILD_CLIENTS_BENCH=OFF
-DBUILD_CLIENTS_SAMPLES=OFF
-L
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -10,23 +10,15 @@ parameters:
default:
- cmake
- ninja-build
- rocblas
- rocsparse
- hipsparse
- rocsolver
- libsuitesparse-dev
- gfortran
- git
- googletest
- libgtest-dev
- name: rocmDependencies
type: object
default:
- clr
- hipSPARSE
- llvm-project
- rocBLAS
- rocm-cmake
- rocminfo
- ROCR-Runtime
- rocSPARSE
- rocSOLVER
jobs:
- job: hipSOLVER
@@ -35,6 +27,8 @@ jobs:
- template: /.azuredevops/variables-global.yml
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -45,18 +39,6 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
# build external gtest and lapack
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
@@ -70,10 +52,10 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Pipeline.Workspace)/deps-install
-DCMAKE_PREFIX_PATH="/opt/rocm;$(Pipeline.Workspace)/deps-install"
-DCMAKE_BUILD_TYPE=Release
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DBUILD_CLIENTS_TESTS=ON
-DUSE_CUDA=OFF

View File

@@ -13,18 +13,10 @@ parameters:
- libboost-program-options-dev
- googletest
- libfftw3-dev
- rocsparse
- git
- gfortran
- libgtest-dev
- name: rocmDependencies
type: object
default:
- clr
- llvm-project
- rocminfo
- rocprofiler-register
- ROCR-Runtime
- rocSPARSE
jobs:
- job: hipSPARSE
@@ -33,6 +25,8 @@ jobs:
- template: /.azuredevops/variables-global.yml
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -43,35 +37,15 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
-DCMAKE_BUILD_TYPE=Release
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake/
-DCMAKE_PREFIX_PATH="/opt/rocm;/opt/rocm/share/rocm/cmake/"
-DBUILD_CLIENTS_TESTS=ON
-DBUILD_CLIENTS_SAMPLES=OFF
-DBUILD_CLIENTS_BENCHMARKS=OFF
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
artifactName: hipSPARSE
publish: false
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
parameters:
sourceDir: $(Build.SourcesDirectory)/build/clients
contentsString: matrices/**
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
artifactName: testMatrices

View File

@@ -8,43 +8,25 @@ parameters:
- name: aptPackages
type: object
default:
- cmake
- ninja-build
- python3-venv
- libmsgpack-dev
- hipsparse-dev
- git
- python3-pip
- name: pipModules
type: object
default:
- joblib
# rocm dependencies should match dependencies-rocm.yml
- name: rocmDependencies
type: object
default:
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocprofiler-register
- hipSPARSE
- rocBLAS
jobs:
- job: hipSPARSELt
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Build.BinariesDirectory)/rocm
- name: TENSILE_ROCM_ASSEMBLER_PATH
value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang
- name: CMAKE_CXX_COMPILER
value: $(Agent.BuildDirectory)/rocm/llvm/bin/hipcc
- name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
- name: PATH
value: $(Agent.BuildDirectory)/rocm/llvm/bin:$(Agent.BuildDirectory)/rocm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/snap/bin
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -52,35 +34,21 @@ jobs:
parameters:
aptPackages: ${{ parameters.aptPackages }}
pipModules: ${{ parameters.pipModules }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_BUILD_TYPE=Release
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
-DAMDGPU_TARGETS=all
-DTensile_LOGIC=
-DTensile_CPU_THREADS=
-DTensile_CODE_OBJECT_VERSION=default
-DTensile_LIBRARY_FORMAT=msgpack
-DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_PREFIX_PATH="/opt/rocm"
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -10,17 +10,12 @@ parameters:
default:
- cmake
- ninja-build
- python3-pip
- composablekernel-dev
- git
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- composable_kernel
jobs:
- job: hipTensor
@@ -28,6 +23,8 @@ jobs:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -53,11 +50,12 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/llvm
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
-DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm/llvm"
-DROCM_PATH="$(Agent.BuildDirectory)/rocm"
-DCMAKE_BUILD_TYPE=Release
-DHIPTENSOR_BUILD_TESTS=ON
-DAMDGPU_TARGETS=gfx90a
multithreadFlag: -- -j32
-DAMDGPU_TARGETS=gfx1030;gfx1100
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -14,7 +14,6 @@ parameters:
- ninja-build
- python-is-python3
- zlib1g-dev
- pkg-config
- name: rocmDependencies
type: object
default:
@@ -69,6 +68,8 @@ jobs:
-DLIBCXXABI_INSTALL_STATIC_LIBRARY=OFF
-DLLVM_BUILD_DOCS=OFF
-DLLVM_ENABLE_SPHINX=OFF
-DSPHINX_WARNINGS_AS_ERRORS=OFF
-DSPHINX_OUTPUT_MAN=OFF
-DLLVM_ENABLE_ASSERTIONS=OFF
-DLLVM_ENABLE_Z3_SOLVER=OFF
-DLLVM_ENABLE_ZLIB=ON
@@ -79,6 +80,7 @@ jobs:
-DPACKAGE_VENDOR=AMD
-DCLANG_LINK_FLANG_LEGACY=ON
-DCMAKE_CXX_STANDARD=17
-DFLANG_INCLUDE_DOCS=OFF
-DROCM_LLVM_BACKWARD_COMPAT_LINK=$(Build.BinariesDirectory)/llvm
-DROCM_LLVM_BACKWARD_COMPAT_LINK_TARGET=./lib/llvm
-GNinja

View File

@@ -8,37 +8,21 @@ parameters:
- name: aptPackages
type: object
default:
- python3-pip
- cmake
- libboost-program-options-dev
- googletest
- libfftw3-dev
- git
- ninja-build
- libstdc++-12-dev
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocm_smi_lib
- rocprofiler-register
- rocm-core
- HIPIFY
- aomp
- aomp-extras
jobs:
- job: rccl
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Build.BinariesDirectory)/rocm
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -49,29 +33,14 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- script: chmod +x $(Agent.BuildDirectory)/rocm/bin/hipify-perl
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
-DHALF_INCLUDE_DIR=$(Agent.BuildDirectory)/rocm/include
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
-DCMAKE_BUILD_TYPE=Release
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DBUILD_TESTS=ON
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake/
-DCMAKE_PREFIX_PATH="/opt/rocm;/opt/rocm/share/rocm/cmake/"
-DAMDGPU_TARGETS=gfx1030;gfx1100
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -8,7 +8,6 @@ parameters:
- name: aptPackages
type: object
default:
- python3-pip
- cmake
- ninja-build
- git
@@ -18,16 +17,6 @@ parameters:
- autoconf
- libtool
- pkg-config
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocm_smi_lib
- amdsmi
jobs:
- job: rdc
@@ -35,6 +24,8 @@ jobs:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -45,18 +36,6 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
# Build grpc
- task: Bash@3
displayName: 'git clone grpc'
@@ -78,7 +57,6 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DGRPC_ROOT="$(Build.SourcesDirectory)/bin"
-DBUILD_TESTS=ON
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -15,29 +15,16 @@ parameters:
- git
- mpich
- ninja-build
- name: rocmDependencies
type: object
default:
- aomp
- clr
- llvm-project
- rocBLAS
- rocminfo
- rocPRIM
- rocprofiler-register
- ROCR-Runtime
- rocRAND
- rocSPARSE
jobs:
- job: rocALUTION
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Build.BinariesDirectory)/rocm
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -48,25 +35,13 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
-DCMAKE_BUILD_TYPE=Release
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake/
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-DCMAKE_PREFIX_PATH="/opt/rocm;/opt/rocm/share/rocm/cmake/"
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DBUILD_CLIENTS_TESTS=ON
-DBUILD_CLIENTS_BENCHMARKS=OFF

View File

@@ -18,40 +18,19 @@ parameters:
- googletest
- libgtest-dev
- wget
- python3-pip
- libdrm-dev
- name: pipModules
type: object
default:
- joblib
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocprofiler-register
- rocm_smi_lib
- rocm-core
- aomp
- aomp-extras
jobs:
- job: rocBLAS
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Build.BinariesDirectory)/rocm
- name: TENSILE_ROCM_ASSEMBLER_PATH
value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang
- name: CMAKE_CXX_COMPILER
value: $(Agent.BuildDirectory)/rocm/bin/hipcc
- name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -63,60 +42,23 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- task: Bash@3
displayName: 'Download AOCL'
inputs:
targetType: inline
script: wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-2/aocl-linux-gcc-4.2.0_1_amd64.deb
workingDirectory: '$(Pipeline.Workspace)'
- task: Bash@3
displayName: 'Install AOCL'
inputs:
targetType: inline
script: sudo apt install --yes ./aocl-linux-gcc-4.2.0_1_amd64.deb
workingDirectory: '$(Pipeline.Workspace)'
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- task: Bash@3
displayName: 'Download AOCL'
inputs:
targetType: inline
script: wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-1/aocl-linux-aocc-4.1.0_1_amd64.deb
workingDirectory: '$(Pipeline.Workspace)'
- task: Bash@3
displayName: 'Install AOCL'
inputs:
targetType: inline
script: sudo apt install --yes ./aocl-linux-aocc-4.1.0_1_amd64.deb
workingDirectory: '$(Pipeline.Workspace)'
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- script: echo $PATH
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_TOOLCHAIN_FILE=toolchain-linux.cmake
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm;$(Pipeline.Workspace)/deps-install
-DCMAKE_PREFIX_PATH="/opt/rocm;$(Pipeline.Workspace)/deps-install"
-DCMAKE_BUILD_TYPE=Release
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DTensile_CODE_OBJECT_VERSION=default
-DTensile_LOGIC=asm_full
-DTensile_SEPARATE_ARCHITECTURES=ON
-DTensile_LAZY_LIBRARY_LOADING=ON
-DTensile_LIBRARY_FORMAT=msgpack
-DTENSILE_VENV_UPGRADE_PIP=ON
-DBUILD_CLIENTS_TESTS=ON
-DBUILD_CLIENTS_BENCHMARKS=OFF
-DBUILD_CLIENTS_SAMPLES=OFF
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -8,7 +8,6 @@ parameters:
- name: aptPackages
type: object
default:
- python3-pip
- cmake
- ninja-build
- pkg-config
@@ -19,16 +18,6 @@ parameters:
- libstdc++-12-dev
- libva-dev
- mesa-amdgpu-va-drivers
- libdrm-dev
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocm-core
jobs:
- job: rocDecode
@@ -37,21 +26,11 @@ jobs:
- template: /.azuredevops/variables-global.yml
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
# Since mesa-amdgpu-multimedia-devel is not directly available from apt, register it
- task: Bash@3
displayName: 'Register ROCm packages'
inputs:
targetType: inline
script: |
sudo mkdir --parents --mode=0755 /etc/apt/keyrings
wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/${{ variables.KEYRING_VERSION }}/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${{ variables.KEYRING_VERSION }} jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
sudo apt update
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
@@ -59,24 +38,10 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_BUILD_TYPE=Release
-L
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -10,31 +10,20 @@ parameters:
default:
- cmake
- ninja-build
- rocrand
- hiprand
- libboost-program-options-dev
- libgtest-dev
- libfftw3-dev
- python3-pip
# rocm dependencies should match dependencies-rocm.yml
- name: rocmDependencies
type: object
default:
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocprofiler-register
- hipRAND
- rocRAND
- rocm-cmake
- aomp
jobs:
- job: rocFFT
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Build.BinariesDirectory)/rocm
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -45,24 +34,12 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
-DCMAKE_PREFIX_PATH=/opt/rocm
-DCMAKE_BUILD_TYPE=Release
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DUSE_HIP_CLANG=ON

View File

@@ -10,13 +10,6 @@ parameters:
default:
- cmake
- ninja-build
- git
- python3-pip
- name: rocmDependencies
type: object
default:
- llvm-project
- rocm-cmake
jobs:
- job: rocMLIR
@@ -24,6 +17,8 @@ jobs:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -34,25 +29,13 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_BUILD_TYPE=Release
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
-DCMAKE_PREFIX_PATH=/opt/rocm
-DBUILD_FAT_LIBROCKCOMPILER=1
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -12,15 +12,6 @@ parameters:
- ninja-build
- libgtest-dev
- git
- python3-pip
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
jobs:
- job: rocPRIM
@@ -28,6 +19,8 @@ jobs:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -41,24 +34,12 @@ jobs:
# ${{ }} are resolved during compile-time
# so this next step is skipped completely until
# we define explicit aptPackages needed to install
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DBUILD_BENCHMARK=ON
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DBUILD_TEST=ON
-GNinja

View File

@@ -10,25 +10,15 @@ parameters:
default:
- cmake
- ninja-build
- rocblas
- rocsparse
- hipsparse
- libsuitesparse-dev
- gfortran
- libfmt-dev
- git
- googletest
- libgtest-dev
- python3-pip
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocBLAS
- rocPRIM
- rocSPARSE
- hipSPARSE
jobs:
- job: rocSOLVER
@@ -36,6 +26,8 @@ jobs:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -52,18 +44,6 @@ jobs:
targetType: inline
script: git clone --depth 1 --branch v3.9.1 https://github.com/Reference-LAPACK/lapack
workingDirectory: '$(Build.SourcesDirectory)'
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
componentName: lapack
@@ -79,10 +59,11 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Pipeline.Workspace)/deps-install
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DCMAKE_PREFIX_PATH="/opt/rocm;$(Pipeline.Workspace)/deps-install"
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DUSE_CUDA=OFF
-DBUILD_CLIENTS_TESTS=ON
-DBUILD_CLIENTS_BENCHMARKS=OFF
-DBUILD_CLIENTS_SAMPLES=OFF

View File

@@ -8,7 +8,6 @@ parameters:
- name: aptPackages
type: object
default:
- python3-pip
- cmake
- ninja-build
- libboost-program-options-dev
@@ -16,28 +15,17 @@ parameters:
- libfftw3-dev
- git
- gfortran
- rocprim-dev
- libgtest-dev
- libdrm-dev
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocBLAS
- rocminfo
- rocPRIM
- rocprofiler-register
jobs:
- job: rocSPARSE
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Build.BinariesDirectory)/rocm
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -48,40 +36,16 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/hipcc
-DCMAKE_C_COMPILER=/opt/rocm/bin/hipcc
-DCMAKE_BUILD_TYPE=Release
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DBUILD_CLIENTS_SAMPLES=OFF
-DBUILD_CLIENTS_TESTS=ON
-DBUILD_CLIENTS_BENCHMARKS=OFF
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip;$(Agent.BuildDirectory)/rocm/hip/cmake
-DCMAKE_MODULE_PATH="/opt/rocm/lib/cmake/hip;/opt/rocm/hip/cmake"
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
artifactName: rocSPARSE
publish: false
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
parameters:
sourceDir: $(Build.SourcesDirectory)/build/clients
contentsString: matrices/**
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
parameters:
artifactName: testMatrices

View File

@@ -10,20 +10,12 @@ parameters:
default:
- cmake
- ninja-build
- hiprand
- rocprim-dev
- libboost-program-options-dev
- googletest
- libfftw3-dev
- git
- python3-pip
- name: rocmDependencies
type: object
default:
- clr
- hipRAND
- llvm-project
- rocminfo
- rocPRIM
- ROCR-Runtime
jobs:
- job: rocThrust
@@ -31,6 +23,8 @@ jobs:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -41,25 +35,14 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-GNinja
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
-DROCM_PATH=/opt/rocm
-DCMAKE_PREFIX_PATH=/opt/rocm
-DAMDGPU_TARGETS=gfx1030;gfx1100
-DBUILD_TEST=ON
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -8,7 +8,6 @@ parameters:
- name: aptPackages
type: object
default:
- python3-pip
- cmake
- ninja-build
- libboost-program-options-dev
@@ -16,18 +15,7 @@ parameters:
- googletest
- libfftw3-dev
- git
- libomp-dev
- name: rocmDependencies
type: object
default:
- rocm-cmake
- llvm-project
- ROCR-Runtime
- clr
- rocminfo
- rocBLAS
- aomp
- rocm_smi_lib
- rocblas
jobs:
- job: rocWMMA
@@ -35,6 +23,8 @@ jobs:
- group: common
- template: /.azuredevops/variables-global.yml
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -45,23 +35,11 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_CXX_COMPILER=/opt/rocm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/bin/amdclang
-DCMAKE_BUILD_TYPE=Release
-DROCWMMA_BUILD_TESTS=ON
-DROCWMMA_BUILD_SAMPLES=OFF

View File

@@ -5,30 +5,6 @@ parameters:
- name: checkoutRef
type: string
default: ''
- name: aptPackages
type: object
default:
- libglfw3-dev
- name: rocmDependencies
type: object
default:
- AMDMIGraphX
- clr
- hipBLAS
- hipCUB
- HIPIFY
- hipRAND
- hipSOLVER
- hipSPARSE
- llvm-project
- rocBLAS
- rocPRIM
- rocprofiler-register
- ROCR-Runtime
- rocRAND
- rocSOLVER
- rocSPARSE
- rocThrust
jobs:
- job: rocm_examples
@@ -44,28 +20,5 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
parameters:
aptPackages: ${{ parameters.aptPackages }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
# https://github.com/ROCm/HIP/issues/2203
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DROCM_ROOT=$(Agent.BuildDirectory)/rocm
-DCMAKE_HIP_ARCHITECTURES=gfx1030;gfx1100
-DCMAKE_EXE_LINKER_FLAGS=-fgpu-rdc
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -10,33 +10,21 @@ parameters:
default:
- cmake
- ninja-build
- python3-pip
- name: pipModules
type: object
default:
- CppHeaderParser
- argparse
- name: rocmDependencies
type: object
default:
- clr
- llvm-project
- rocminfo
- rocprofiler-register
- ROCR-Runtime
- ROCT-Thunk-Interface
jobs:
- job: rocm_bandwidth_test
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: ROCR_INC_DIR
value: $(Agent.BuildDirectory)/rocm
- name: ROCR_LIB_DIR
value: $(Agent.BuildDirectory)/rocm
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -48,23 +36,11 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_BUILD_TYPE=release
-DCMAKE_MODULE_PATH=$(Build.SourcesDirectory)/cmake_modules
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/include;$(Agent.BuildDirectory)/rocm/include/hsa
-DCMAKE_MODULE_PATH="$(Build.SourcesDirectory)/cmake_modules"
-DCMAKE_PREFIX_PATH=/opt/rocm
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -24,5 +24,4 @@ jobs:
parameters:
extraBuildFlags: >-
-DBUILD_TESTS=ON
-DROCM_DEP_ROCMCORE=ON
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -21,17 +21,4 @@ jobs:
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
componentName: rocprofiler-register
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
componentName: rocprofiler-register-tests
extraBuildFlags: >-
-DCMAKE_PREFIX_PATH=$(Build.BinariesDirectory)
cmakeBuildDir: 'tests/build'
installEnabled: false
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
parameters:
componentName: rocprofiler-register
testDir: 'tests/build'
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -10,13 +10,12 @@ parameters:
default:
- cmake
- libgtest-dev
- libdrm-dev
- libdw-dev
- libsystemd-dev
- libelf-dev
- libnuma-dev
- libpciaccess-dev
- python3-pip
- rocm-llvm-dev
- name: pipModules
type: object
default:
@@ -27,31 +26,15 @@ parameters:
- lxml
- barectf
- pandas
- name: rocmDependencies
type: object
default:
- clr
- llvm-project
- ROCdbgapi
- rocm-cmake
- rocm-core
- rocm_smi_lib
- rocminfo
- ROCR-Runtime
- rocprofiler-register
- ROCT-Thunk-Interface
- roctracer
jobs:
- job: rocprofiler
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: HIP_ROCCLR_HOME
value: $(Agent.BuildDirectory)/rocm
- name: ROCM_PATH
value: $(Agent.BuildDirectory)/rocm
pool: ${{ variables.MEDIUM_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -63,46 +46,11 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# Manually download aqlprofile, hard-coded 6.1.0 version
- task: Bash@3
displayName: 'Download aqlprofile'
inputs:
targetType: inline
script: wget -nv https://repo.radeon.com/rocm/misc/aqlprofile/ubuntu-22.04/hsa-amd-aqlprofile_1.0.0.60200.60200-crdnnh.14213~22.04_amd64.deb
workingDirectory: '$(Pipeline.Workspace)'
- task: Bash@3
displayName: 'Extract aqlprofile'
inputs:
targetType: inline
script: |
mkdir hsa-amd-aqlprofile
dpkg-deb -R hsa-amd-aqlprofile_1.0.0.60200.60200-crdnnh.14213~22.04_amd64.deb hsa-amd-aqlprofile
workingDirectory: '$(Pipeline.Workspace)'
- task: Bash@3
displayName: 'Move aqlprofile'
inputs:
targetType: inline
script: |
mkdir -p $(Agent.BuildDirectory)/rocm
cp -R hsa-amd-aqlprofile/opt/rocm-6.2.0-14213/* $(Agent.BuildDirectory)/rocm
workingDirectory: '$(Pipeline.Workspace)'
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_MODULE_PATH=$(Build.SourcesDirectory)/cmake_modules;$(Agent.BuildDirectory)/rocm/lib/cmake;$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_MODULE_PATH="$(Build.SourcesDirectory)/cmake_modules;/opt/rocm/lib/cmake"
-DCMAKE_PREFIX_PATH="/opt/rocm"
-DENABLE_LDCONFIG=OFF
-DUSE_PROF_API=1
-DGPU_TARGETS=gfx1030;gfx1100

View File

@@ -12,16 +12,6 @@ parameters:
- ninja-build
- libelf-dev
- libdw-dev
- name: rocmDependencies
type: object
default:
- rocm-cmake
- clr
- llvm-project
- ROCdbgapi
- rocminfo
- ROCR-Runtime
- rocprofiler-register
jobs:
- job: rocr_debug_agent
@@ -30,6 +20,8 @@ jobs:
- template: /.azuredevops/variables-global.yml
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -40,24 +32,11 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_BUILD_TYPE=Release
-DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake;$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DROCM_PATH=/opt/rocm
-DCMAKE_MODULE_PATH=/opt/rocm/lib/cmake
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -67,4 +67,10 @@ jobs:
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DGPU_TARGETS=gfx1030;gfx1100
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
# - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
# - task: Bash@3
# displayName: 'Tests'
# inputs:
# targetType: inline
# script: ./run.sh
# workingDirectory: build

View File

@@ -9,18 +9,10 @@ parameters:
type: object
default:
- cmake
- libomp-dev # needed to pass flag step
- ninja-build
- clang
- name: rocmDependencies
type: object
default:
- aomp # needed to pass build step
- clr
- half
- llvm-project
- rocminfo
- ROCR-Runtime
- libomp-dev
jobs:
- job: rpp
@@ -29,6 +21,8 @@ jobs:
- template: /.azuredevops/variables-global.yml
pool:
vmImage: ${{ variables.BASE_BUILD_POOL }}
container:
image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
workspace:
clean: all
steps:
@@ -39,27 +33,13 @@ jobs:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
parameters:
checkoutRepo: ${{ parameters.checkoutRepo }}
# CI case: download latest default branch build
- ${{ if eq(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: staging
# manual build case: triggered by ROCm/ROCm repo
- ${{ if ne(parameters.checkoutRef, '') }}:
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
parameters:
dependencyList: ${{ parameters.rocmDependencies }}
dependencySource: tag-builds
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
extraBuildFlags: >-
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-DHALF_INCLUDE_DIRS=$(Agent.BuildDirectory)/rocm/include
-DCMAKE_CXX_COMPILER=/opt/rocm/llvm/bin/amdclang++
-DCMAKE_C_COMPILER=/opt/rocm/llvm/bin/amdclang
-DCMAKE_BUILD_TYPE=Release
-DBUILD_CLIENTS=ON
-DAMDGPU_TARGETS=gfx1030;gfx1100
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml

View File

@@ -23,7 +23,7 @@ trigger: none
pr: none
jobs:
- template: ${{ variables.CI_COMPONENT_PATH }}/ROCgdb.yml
- template: ${{ variables.CI_COMPONENT_PATH }}/rocgdb.yml
parameters:
checkoutRepo: release_repo
checkoutRef: ${{ parameters.checkoutRef }}

View File

@@ -1,29 +0,0 @@
variables:
- group: common
- template: /.azuredevops/variables-global.yml
parameters:
- name: checkoutRef
type: string
default: refs/tags/$(LATEST_RELEASE_TAG)
resources:
repositories:
- repository: pipelines_repo
type: github
endpoint: ROCm
name: ROCm/ROCm
- repository: release_repo
type: github
endpoint: ROCm
name: ROCm/rocm-examples
ref: ${{ parameters.checkoutRef }}
trigger: none
pr: none
jobs:
- template: ${{ variables.CI_COMPONENT_PATH }}/rocm-examples.yml
parameters:
checkoutRepo: release_repo
checkoutRef: ${{ parameters.checkoutRef }}

View File

@@ -12,7 +12,6 @@ parameters:
- name: defaultBranchList
type: object
default:
amdsmi: develop
aomp: aomp-dev
aomp-extras: aomp-dev
AMDMIGraphX: develop
@@ -21,19 +20,13 @@ parameters:
half: master
HIP: develop
hipBLAS: develop
hipCUB: develop
hipRAND: develop
hipSOLVER: develop
hipSPARSE: develop
llvm-project: amd-staging
MIOpen: develop
rdc: develop
rocBLAS: develop
ROCdbgapi : amd-master
rocDecode: develop
rocFFT: develop
rocm-cmake: develop
rocm_smi_lib: develop
rocminfo: master
rocMLIR: develop
rocPRIM: develop
@@ -43,8 +36,6 @@ parameters:
rocSOLVER: develop
rocSPARSE: develop
ROCT-Thunk-Interface: master
rocThrust: develop
roctracer: amd-master
rpp: master
- name: componentsFailureOkay
type: object

View File

@@ -5,9 +5,6 @@ parameters:
- name: extraBuildFlags
type: string
default: ''
- name: multithreadFlag
type: string
default: ''
- name: cmakeBuildDir
type: string
default: 'build'
@@ -20,9 +17,6 @@ parameters:
- name: installDir
type: string
default: '$(Build.BinariesDirectory)'
- name: installEnabled
type: boolean
default: true
steps:
# create workingDirectory if it does not exist and change into it
@@ -38,13 +32,12 @@ steps:
displayName: '${{parameters.componentName }} Build'
inputs:
workingDirectory: ${{ parameters.cmakeBuildDir }}
cmakeArgs: '--build ${{ parameters.cmakeTargetDir }} ${{ parameters.multithreadFlag }}'
cmakeArgs: '--build ${{ parameters.cmakeTargetDir }}'
retryCountOnTaskFailure: 10
# equivalent to running make $cmakeTarget from $cmakeBuildDir
# e.g., make install
- ${{ if eq(parameters.installEnabled, true) }}:
- task: CMake@1
displayName: '${{parameters.componentName }} ${{ parameters.cmakeTarget }}'
inputs:
workingDirectory: ${{ parameters.cmakeBuildDir }}
cmakeArgs: '--build ${{ parameters.cmakeTargetDir }} --target ${{ parameters.cmakeTarget }}'
- task: CMake@1
displayName: '${{parameters.componentName }} ${{ parameters.cmakeTarget }}'
inputs:
workingDirectory: ${{ parameters.cmakeBuildDir }}
cmakeArgs: '--build ${{ parameters.cmakeTargetDir }} --target ${{ parameters.cmakeTarget }}'

View File

@@ -1,10 +0,0 @@
# replace cmake from apt install with newest version using snap install
steps:
- task: Bash@3
displayName: update cmake
inputs:
targetType: inline
script: |
sudo apt purge cmake
sudo snap install cmake --classic
hash -r

View File

@@ -12,31 +12,23 @@ steps:
displayName: 'sudo apt-get update'
inputs:
targetType: inline
script: sudo apt-get --yes update
env:
DEBIAN_FRONTEND: noninteractive
script: sudo apt-get update
- task: Bash@3
displayName: 'sudo apt-get upgrade'
inputs:
targetType: inline
script: sudo apt-get --yes upgrade
env:
DEBIAN_FRONTEND: noninteractive
script: sudo apt-get update
- task: Bash@3
displayName: 'sudo apt-get fix'
inputs:
targetType: inline
script: sudo apt --yes --fix-broken install
env:
DEBIAN_FRONTEND: noninteractive
- ${{ if gt(length(parameters.aptPackages), 0) }}:
- task: Bash@3
displayName: 'sudo apt-get install ...'
inputs:
targetType: inline
script: sudo apt-get --yes install ${{ join(' ', parameters.aptPackages) }}
env:
DEBIAN_FRONTEND: noninteractive
- ${{ if gt(length(parameters.pipModules), 0) }}:
- task: Bash@3
displayName: 'pip install ...'

View File

@@ -23,7 +23,6 @@ parameters:
- name: stagingPipelineIdentifiers
type: object
default:
amdsmi: $(amdsmi-pipeline-id)
aomp: $(aomp-pipeline-id)
aomp-extras: $(aomp-extras-pipeline-id)
AMDMIGraphX: $(amdmigraphx-pipeline-id)
@@ -31,21 +30,13 @@ parameters:
composable_kernel: $(composable-kernel-pipeline-id)
half: $(half-pipeline-id)
hipBLAS: $(hipblas-pipeline-id)
hipCUB: $(hipcub-pipeline-id)
HIPIFY: $(hipify-pipeline-id)
hipRAND: $(hiprand-pipeline-id)
hipSOLVER: $(hipsolver-pipeline-id)
hipSPARSE: $(hipsparse-pipeline-id)
llvm-project: $(llvm-project-pipeline-id)
MIOpen: $(miopen-pipeline-id)
rdc: $(rdc-pipeline-id)
rocBLAS: $(rocblas-pipeline-id)
ROCdbgapi : $(rocdbgapi-pipeline-id)
rocDecode: $(rocdecode-pipeline-id)
rocFFT: $(rocfft-pipeline-id)
rocFFT: $(rotfft-pipeline-id)
rocm-cmake: $(rocm-cmake-pipeline-id)
rocm-core: $(rocm-core-pipeline-id)
rocm_smi_lib: $(rocm-smi-lib-pipeline-id)
rocminfo: $(rocminfo-pipeline-id)
rocMLIR: $(rocmlir-pipeline-id)
rocPRIM: $(rocprim-pipeline-id)
@@ -55,13 +46,10 @@ parameters:
rocSOLVER: $(rocsolver-pipeline-id)
rocSPARSE: $(rocsparse-pipeline-id)
ROCT-Thunk-Interface: $(roct-thunk-interface-pipeline-id)
rocThrust: $(rocthrust-pipeline-id)
roctracer: $(roctracer-pipeline-id)
rpp: $(rpp-pipeline-id)
- name: taggedPipelineIdentifiers
type: object
default:
amdsmi: $(amdsmi-tagged-pipeline-id)
aomp: $(aomp-tagged-pipeline-id)
aomp-extras: $(aomp-extras-tagged-pipeline-id)
AMDMIGraphX: $(amdmigraphx-tagged-pipeline-id)
@@ -69,21 +57,13 @@ parameters:
composable_kernel: $(composable-kernel-tagged-pipeline-id)
half: $(half-tagged-pipeline-id)
hipBLAS: $(hipblas-tagged-pipeline-id)
hipCUB: $(hipcub-tagged-pipeline-id)
HIPIFY: $(hipify-tagged-pipeline-id)
hipRAND: $(hiprand-tagged-pipeline-id)
hipSOLVER: $(hipsolver-tagged-pipeline-id)
hipSPARSE: $(hipsparse-tagged-pipeline-id)
llvm-project: $(llvm-project-tagged-pipeline-id)
MIOpen: $(miopen-tagged-pipeline-id)
rdc: $(rdc-tagged-pipeline-id)
rocBLAS: $(rocblas-tagged-pipeline-id)
ROCdbgapi : $(rocdbgapi-tagged-pipeline-id)
rocDecode: $(rocdecode-tagged-pipeline-id)
rocFFT: $(rocfft-tagged-pipeline-id)
rocFFT: $(rotfft-tagged-pipeline-id)
rocm-cmake: $(rocm-cmake-tagged-pipeline-id)
rocm-core: $(rocm-core-tagged-pipeline-id)
rocm_smi_lib: $(rocm-smi-lib-tagged-pipeline-id)
rocminfo: $(rocminfo-tagged-pipeline-id)
rocMLIR: $(rocmlir-tagged-pipeline-id)
rocPRIM: $(rocprim-tagged-pipeline-id)
@@ -93,8 +73,6 @@ parameters:
rocSOLVER: $(rocsolver-tagged-pipeline-id)
rocSPARSE: $(rocsparse-tagged-pipeline-id)
ROCT-Thunk-Interface: $(roct-thunk-interface-tagged-pipeline-id)
rocThrust: $(rocthrust-tagged-pipeline-id)
roctracer: $(roctracer-tagged-pipeline-id)
rpp: $(rpp-tagged-pipeline-id)
# set to true if you're calling this template file multiple files in same pipeline
# only leave last call false to optimize sequence

View File

@@ -27,5 +27,3 @@ variables:
value: rocm/dev-ubuntu-22.04
- name: LATEST_DOCKER_VERSION
value: 6.1
- name: KEYRING_VERSION
value: 6.1

2
.gitignore vendored
View File

@@ -16,4 +16,4 @@ _readthedocs/
docs/CHANGELOG.md
docs/contribute/index.md
docs/about/release-notes.md
docs/about/changelog.md
docs/about/CHANGELOG.md

View File

@@ -3,20 +3,19 @@
version: 2
sphinx:
configuration: docs/conf.py
formats: [htmlzip]
python:
install:
- requirements: docs/sphinx/requirements.txt
build:
os: ubuntu-22.04
tools:
python: "3.10"
apt_packages:
- "doxygen"
- "gfortran" # For pre-processing fortran sources
- "graphviz" # For dot graphs in doxygen
python:
install:
- requirements: docs/sphinx/requirements.txt
sphinx:
configuration: docs/conf.py
formats: []

View File

@@ -237,7 +237,6 @@ OpenCV
OpenFabrics
OpenGL
OpenMP
OpenMPI
OpenSSL
OpenVX
PCI
@@ -496,7 +495,6 @@ hipfort
hipify
hipsolver
hipsparse
hpc
hpp
hsa
hsakmt
@@ -633,7 +631,6 @@ subexpression
subfolder
subfolders
supercomputing
td
tensorfloat
th
tokenization
@@ -688,4 +685,4 @@ xargs
xz
yaml
ysvmadyb
zypper
zypper

File diff suppressed because it is too large Load Diff

View File

@@ -56,103 +56,12 @@ cd ~/ROCm/
**Note:** Using this sample code will cause the repo tool to download the open source code associated with the specified ROCm release. Ensure that you have ssh-keys configured on your machine for your GitHub ID prior to the download as explained at [Connecting to GitHub with SSH](https://docs.github.com/en/authentication/connecting-to-github-with-ssh).
## Building the ROCm source code
### Building the ROCm source code
Each ROCm component repository contains directions for building that component, such as the rocSPARSE documentation [Installation and Building for Linux](https://rocm.docs.amd.com/projects/rocSPARSE/en/latest/install/Linux_Install_Guide.html). Refer to the specific component documentation for instructions on building the repository.
Each release of the ROCm software supports specific hardware and software configurations. Refer to [System requirements (Linux)](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html) for the current supported hardware and OS.
## Build ROCm from source
The Build will use as many processors as it can find to build in parallel. Some of the compiles can consume as much as 10GB of RAM, so make sure you have plenty of Swap Space !
By default the ROCm build will compile for all supported GPU architectures and will take approximately 500 CPU hours.
The Build time will reduce significantly if we limit the GPU Architecture/s against which we need to build by using the environment variable GPU_ARCHS as mentioned below.
```bash
# --------------------------------------
# Step1: clone source code
# --------------------------------------
mkdir -p ~/WORKSPACE/ # Or any folder name other than WORKSPACE
cd ~/WORKSPACE/
export ROCM_VERSION=6.1.0 # or 6.1.1 6.1.2
~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.1.x -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
~/bin/repo sync
# --------------------------------------
# Step 2: Prepare build environment
# --------------------------------------
# Option 1: Start a docker container
# Pulling required base docker images:
# Ubuntu20.04 built from ROCm/tools/rocm-build/docker/ubuntu20/Dockerfile
docker pull rocm/rocm-build-ubuntu-20.04:6.1
# Ubuntu22.04 built from ROCm/tools/rocm-build/docker/ubuntu22/Dockerfile
docker pull rocm/rocm-build-ubuntu-22.04:6.1
# Start docker container and mount the source code folder:
docker run -ti \
-e ROCM_VERSION=${ROCM_VERSION} \
-e CCACHE_DIR=$HOME/.ccache \
-e CCACHE_ENABLED=true \
-e DOCK_WORK_FOLD=/src \
-w /src \
-v $PWD:/src \
-v /etc/passwd:/etc/passwd \
-v /etc/shadow:/etc/shadow \
-v ${HOME}/.ccache:${HOME}/.ccache \
-u $(id -u):$(id -g) \
<replace_with_required_ubuntu_base_docker_image> bash
# Option 2: Install required packages into the host machine
# For ubuntu20.04 system
cd ROCm/tools/rocm-build/docker/ubuntu20
bash install-prerequisites.sh
# For ubuntu22.04 system
cd ROCm/tools/rocm-build/docker/ubuntu22
bash install-prerequisities.sh
# --------------------------------------
# Step 3: Run build command line
# --------------------------------------
# Select GPU targets before building:
# When GPU_ARCHS is not set, default GPU targets supported by ROCm6.1 will be used.
# To build against a subset of GFX architectures you can use the below env variable.
# Support MI300 (gfx940, gfx941, gfx942).
export GPU_ARCHS="gfx942" # Example
export GPU_ARCHS="gfx940;gfx941;gfx942" # Example
# Pick and run build commands in the docker container:
# Build rocm-dev packages
make -f ROCm/tools/rocm-build/ROCm.mk -j ${NPROC:-$(nproc)} rocm-dev
# Build all ROCm packages
make -f ROCm/tools/rocm-build/ROCm.mk -j ${NPROC:-$(nproc)} all
# list all ROCm components to find required components
make -f ROCm/tools/rocm-build/ROCm.mk list_components
# Build a single ROCm packages
make -f ROCm/tools/rocm-build/ROCm.mk T_rocblas
# Find built packages in ubuntu20.04:
out/ubuntu-20.04/20.04/deb/
# Find built packages in ubuntu22.04:
out/ubuntu-22.04/22.04/deb/
# Find built logs in ubuntu20.04:
out/ubuntu-20.04/20.04/logs/
# Find built logs in ubuntu22.04:
out/ubuntu-22.04/22.04/logs/
# All logs pertaining to failed components, end with .errrors extension.
out/ubuntu-22.04/22.04/logs/rocblas.errors # Example
# All logs pertaining to building components, end with .inprogress extension.
out/ubuntu-22.04/22.04/logs/rocblas.inprogress # Example
# All logs pertaining to passed components, use the component names.
out/ubuntu-22.04/22.04/logs/rocblas # Example
```
Note: [Overview for ROCm.mk](tools/rocm-build/README.md)
## ROCm documentation
This repository contains the [manifest file](https://gerrit.googlesource.com/git-repo/+/HEAD/docs/manifest-format.md)

View File

@@ -1,6 +1,4 @@
# ROCm 6.1.2 release notes
<!-- Do not edit this file! This file is autogenerated with -->
<!-- tools/autotag/tag_script.py -->
# ROCm 6.1.1 release notes
<!-- Disable lints since this is an auto-generated file. -->
<!-- markdownlint-disable blanks-around-headers -->
@@ -11,137 +9,155 @@
<!-- spellcheck-disable -->
ROCm 6.1.2 includes enhancements to SMI tools and improvements to some libraries.
ROCm 6.1.1 introduces minor fixes and improvements to some tools and libraries.
### OS support
## OS support
ROCm 6.1.2 has been tested against a pre-release version of Ubuntu 22.04.5 (kernel: 5.15 [GA], 6.8 [HWE]).
* ROCm 6.1.1 now supports Oracle Linux. It has been tested against version 8.9 (kernel 5.15.0-205) with AMD Instinct MI300X accelerators.
### AMD SMI
* ROCm 6.1.1 has been tested against a pre-release version of Ubuntu 22.04.5 (kernel: 5.15 [GA], 6.8 [HWE]).
AMD SMI for ROCm 6.1.2
## AMD SMI
#### Additions
AMD SMI for ROCm 6.1.1
* Added process isolation and clean shader APIs and CLI commands.
* `amdsmi_get_gpu_process_isolation()`
* `amdsmi_set_gpu_process_isolation()`
* `amdsmi_set_gpu_clear_sram_data()`
* Added the `MIN_POWER` metric to output provided by `amd-smi static --limit`.
### Additions
#### Optimizations
- Added deferred error correctable counts to `amd-smi metric -ecc -ecc-blocks`.
* Updated the `amd-smi monitor --pcie` output to prevent delays with the `monitor` command.
### Changes
#### Changes
- Updated the output of `amd-smi metric --ecc-blocks` to show counters available from blocks.
- Updated the output of `amd-smi metric --clock` to reflect each engine.
- Updated the output of `amd-smi topology --json` to align with output reported by host and guest systems.
* Updated `amismi_get_power_cap_info` to return values in uW instead of W.
* Updated Python library return types for `amdsmi_get_gpu_memory_reserved_pages` and `amdsmi_get_gpu_bad_page_info`.
* Updated the output of `amd-smi metric --ecc-blocks` to show counters available from blocks.
### Fixes
#### Fixes
- Fixed `amd-smi metric --clock`'s clock lock and deep sleep status.
- Fixed an issue that would cause an error when resetting non-AMD GPUs.
- Fixed `amd-smi metric --pcie` and `amdsmi_get_pcie_info()` when using RDNA3 (Navi 32 and Navi 31) hardware to prevent "UNKNOWN" reports.
- Fixed the output results of `amd-smi process` when getting processes running on a device.
* `amdsmi_get_gpu_board_info()` no longer returns junk character strings.
* `amd-smi metric --power` now correctly details power output for RDNA3, RDNA2, and MI1x devices.
* Fixed the `amdsmitstReadWrite.TestPowerCapReadWrite` test for RDNA3, RDNA2, and MI100 devices.
* Fixed an issue with the `amdsmi_get_gpu_memory_reserved_pages` and `amdsmi_get_gpu_bad_page_info` Python interface calls.
### Removals
#### Removals
- Removed the `amdsmi_get_gpu_process_info` API from the Python library. It was removed from the C library in an earlier release.
* Removed the `amdsmi_get_gpu_process_info` API from the Python library. It was removed from the C library in an earlier release.
### Known issues
- `amd-smi bad-pages` can result in a `ValueError: Null pointer access` error when using some PMU firmware versions.
```{note}
See the AMD SMI [detailed changelog](https://github.com/ROCm/amdsmi/blob/rocm-6.1.x/CHANGELOG.md) with code samples for more information.
See the [detailed changelog](https://github.com/ROCm/amdsmi/blob/docs/6.1.1/CHANGELOG.md) with code samples for more information.
```
### ROCm SMI
## HIPCC
ROCm SMI for ROCm 6.1.2
HIPCC for ROCm 6.1.1
### Changes
- **Upcoming:** a future release will enable use of compiled binaries `hipcc.bin` and `hipconfig.bin` by default. No action is needed by users. You can continue calling high-level Perl scripts `hipcc` and `hipconfig`. `hipcc.bin` and `hipconfig.bin` will be invoked by the high-level Perl scripts. To revert to the previous behavior and invoke `hipcc.pl` and `hipconfig.pl`, set the `HIP_USE_PERL_SCRIPTS` environment variable to `1`.
- **Upcoming:** a subsequent release will remove high-level Perl scripts `hipcc` and `hipconfig`. This release will remove the `HIP_USE_PERL_SCRIPTS` environment variable. It will rename `hipcc.bin` and `hipconfig.bin` to `hipcc` and `hipconfig` respectively. No action is needed by the users. To revert to the previous behavior, invoke `hipcc.pl` and `hipconfig.pl` explicitly.
- **Upcoming:** a subsequent release will remove `hipcc.pl` and `hipconfig.pl`.
## ROCm SMI
ROCm SMI for ROCm 6.1.1
### Additions
* Added the capability to unlock mutex when a process is dead. Added related debug output.
* Added the `Partition ID` field to the `rocm-smi` CLI.
* Added `NODE`, `GUID`, and `GFX Version` fields to the CLI.
* Documentation now includes C++ and Python tutorials, API guides, and reference material.
### Changes
* Some `rocm-smi` fields now display `N/A` instead of `unknown/unsupported` for consistency.
* Changed stacked ID formatting in the `rocm-smi` CLI to make it easier to spot identifiers.
### Fixes
* Fixed HIP and ROCm SMI mismatch on GPU bus assignments.
* Fixed memory leaks caused by not closing directories and creating maps nodes instead of using `.at()`.
* Fixed initializing calls which reuse `rocmsmi.initializeRsmi()` bindings in the `rocmsmi` Python API.
* Fixed an issue causing `rsmi_dev_activity_metric_get` gfx/memory to not update with GPU activity.
### Known issues
- ROCm SMI reports GPU utilization incorrectly for RDNA3 GPUs in some situations. See the issue on [GitHub](https://github.com/ROCm/ROCm/issues/3112).
```{note}
See the [detailed ROCm SMI changelog](https://github.com/ROCm/rocm_smi_lib/blob/docs/6.1.1/CHANGELOG.md) with code samples for more information.
```
## Library changes in ROCm 6.1.1
| Library | Version |
| ----------- | -------------------------------------------------------------------------- |
| AMDMIGraphX | [2.9](https://github.com/ROCm/AMDMIGraphX/releases/tag/rocm-6.1.1) |
| hipBLAS | [2.1.0](https://github.com/ROCm/hipBLAS/releases/tag/rocm-6.1.1) |
| hipBLASLt | [0.7.0](https://github.com/ROCm/hipBLASLt/releases/tag/rocm-6.1.1) |
| hipCUB | [3.1.0](https://github.com/ROCm/hipCUB/releases/tag/rocm-6.1.1) |
| hipFFT | [1.0.14](https://github.com/ROCm/hipFFT/releases/tag/rocm-6.1.1) |
| hipRAND | [2.10.17](https://github.com/ROCm/hipRAND/releases/tag/rocm-6.1.1) |
| hipSOLVER | 2.1.0 ⇒ [2.1.1](https://github.com/ROCm/hipSOLVER/releases/tag/rocm-6.1.1) |
| hipSPARSE | [3.0.1](https://github.com/ROCm/hipSPARSE/releases/tag/rocm-6.1.1) |
| hipSPARSELt | [0.2.0](https://github.com/ROCm/hipSPARSELt/releases/tag/rocm-6.1.1) |
| hipTensor | [1.2.0](https://github.com/ROCm/hipTensor/releases/tag/rocm-6.1.1) |
| MIOpen | [3.1.0](https://github.com/ROCm/MIOpen/releases/tag/rocm-6.1.1) |
| MIVisionX | [2.5.0](https://github.com/ROCm/MIVisionX/releases/tag/rocm-6.1.1) |
| rccl | [2.18.6](https://github.com/ROCm/rccl/releases/tag/rocm-6.1.1) |
| rocALUTION | [3.1.1](https://github.com/ROCm/rocALUTION/releases/tag/rocm-6.1.1) |
| rocBLAS | [4.1.0](https://github.com/ROCm/rocBLAS/releases/tag/rocm-6.1.1) |
| rocDecode | [0.5.0](https://github.com/ROCm/rocDecode/releases/tag/rocm-6.1.1) |
| rocFFT | 1.0.26 ⇒ [1.0.27](https://github.com/ROCm/rocFFT/releases/tag/rocm-6.1.1) |
| rocm-cmake | [0.12.0](https://github.com/ROCm/rocm-cmake/releases/tag/rocm-6.1.1) |
| rocPRIM | [3.1.0](https://github.com/ROCm/rocPRIM/releases/tag/rocm-6.1.1) |
| rocRAND | [3.0.1](https://github.com/ROCm/rocRAND/releases/tag/rocm-6.1.1) |
| rocSOLVER | [3.25.0](https://github.com/ROCm/rocSOLVER/releases/tag/rocm-6.1.1) |
| rocSPARSE | [3.1.2](https://github.com/ROCm/rocSPARSE/releases/tag/rocm-6.1.1) |
| rocThrust | [3.0.1](https://github.com/ROCm/rocThrust/releases/tag/rocm-6.1.1) |
| rocWMMA | [1.4.0](https://github.com/ROCm/rocWMMA/releases/tag/rocm-6.1.1) |
| rpp | [1.5.0](https://github.com/ROCm/rpp/releases/tag/rocm-6.1.1) |
| Tensile | [4.40.0](https://github.com/ROCm/Tensile/releases/tag/rocm-6.1.1) |
### hipBLASLt 0.7.0
hipBLASLt 0.7.0 for ROCm 6.1.1
#### Additions
* Added the ring hang event to the `amdsmi_evt_notification_type_t` enum.
- Added `hipblasltExtSoftmax` extension API.
- Added `hipblasltExtLayerNorm` extension API.
- Added `hipblasltExtAMax` extension API.
- Added `GemmTuning` extension parameter to set split-k by user.
- Added support for mixed precision datatype: fp16/fp8 in with fp16 outk.
#### Fixes
#### Deprecations
* Fixed an issue causing ROCm SMI to incorrectly report GPU utilization for RDNA3 GPUs. See the issue on [GitHub](https://github.com/ROCm/ROCm/issues/3112).
* Fixed the parsing of `pp_od_clk_voltage` in `get_od_clk_volt_info` to work better with MI-series hardware.
- **Upcoming**: `algoGetHeuristic()` ext API for GroupGemm will be deprecated in a future release of hipBLASLt.
## Library changes in ROCm 6.1.2
### hipSOLVER 2.1.1
| Library | Version |
|---------|---------|
| AMDMIGraphX | [2.9](https://github.com/ROCm/AMDMIGraphX/releases/tag/rocm-6.1.2) |
| composable_kernel | [0.2.0](https://github.com/ROCm/composable_kernel/releases/tag/rocm-6.1.2) |
| hipBLAS | [2.1.0](https://github.com/ROCm/hipBLAS/releases/tag/rocm-6.1.2) |
| hipBLASLt | [0.7.0](https://github.com/ROCm/hipBLASLt/releases/tag/rocm-6.1.2) |
| hipCUB | [3.1.0](https://github.com/ROCm/hipCUB/releases/tag/rocm-6.1.2) |
| hipFFT | [1.0.14](https://github.com/ROCm/hipFFT/releases/tag/rocm-6.1.2) |
| hipRAND | [2.10.17](https://github.com/ROCm/hipRAND/releases/tag/rocm-6.1.2) |
| hipSOLVER | [2.1.1](https://github.com/ROCm/hipSOLVER/releases/tag/rocm-6.1.2) |
| hipSPARSE | [3.0.1](https://github.com/ROCm/hipSPARSE/releases/tag/rocm-6.1.2) |
| hipSPARSELt | [0.2.0](https://github.com/ROCm/hipSPARSELt/releases/tag/rocm-6.1.2) |
| hipTensor | [1.2.0](https://github.com/ROCm/hipTensor/releases/tag/rocm-6.1.2) |
| MIOpen | [3.1.0](https://github.com/ROCm/MIOpen/releases/tag/rocm-6.1.2) |
| MIVisionX | [2.5.0](https://github.com/ROCm/MIVisionX/releases/tag/rocm-6.1.2) |
| rccl | [2.18.6](https://github.com/ROCm/rccl/releases/tag/rocm-6.1.2) |
| rocALUTION | [3.1.1](https://github.com/ROCm/rocALUTION/releases/tag/rocm-6.1.2) |
| rocBLAS | 4.1.0 ⇒ [4.1.2](https://github.com/ROCm/rocBLAS/releases/tag/rocm-6.1.2) |
| rocDecode | 0.5.0 ⇒ [0.6.0](https://github.com/ROCm/rocDecode/releases/tag/rocm-6.1.2) |
| rocFFT | [1.0.27](https://github.com/ROCm/rocFFT/releases/tag/rocm-6.1.2) |
| rocm-cmake | [0.12.0](https://github.com/ROCm/rocm-cmake/releases/tag/rocm-6.1.2) |
| rocPRIM | [3.1.0](https://github.com/ROCm/rocPRIM/releases/tag/rocm-6.1.2) |
| rocRAND | [3.0.1](https://github.com/ROCm/rocRAND/releases/tag/rocm-6.1.2) |
| rocSOLVER | [3.25.0](https://github.com/ROCm/rocSOLVER/releases/tag/rocm-6.1.2) |
| rocSPARSE | [3.1.2](https://github.com/ROCm/rocSPARSE/releases/tag/rocm-6.1.2) |
| rocThrust | [3.0.1](https://github.com/ROCm/rocThrust/releases/tag/rocm-6.1.2) |
| rocWMMA | [1.4.0](https://github.com/ROCm/rocWMMA/releases/tag/rocm-6.1.2) |
| rpp | [1.5.0](https://github.com/ROCm/rpp/releases/tag/rocm-6.1.2) |
| Tensile | [4.40.0](https://github.com/ROCm/Tensile/releases/tag/rocm-6.1.2) |
### RCCL
RCCL 2.18.6 for ROCm 6.1.2
hipSOLVER 2.1.1 for ROCm 6.1.1
#### Changes
* Reduced `NCCL_TOPO_MAX_NODES` to limit stack usage and avoid stack overflow.
### rocBLAS
rocBLAS 4.1.2 for ROCm 6.1.2
#### Optimizations
* Tuned BBS TN and TT operations on the CDNA3 architecture.
- By default, `BUILD_WITH_SPARSE` is now set to OFF on Microsoft Windows.
#### Fixes
* Fixed an issue related to obtaining solutions for BF16 TT operations.
- Fixed benchmark client build when `BUILD_WITH_SPARSE` is OFF.
### rocDecode
### rocFFT 1.0.27
rocDecode 0.6.0 for ROCm 6.1.2
rocFFT 1.0.27 for ROCm 6.1.1
#### Additions
* Added support for FFmpeg v5.x.
#### Optimizations
* Updated error checking in the `rocDecode-setup.py` script.
#### Changes
* Updated core dependencies.
* Updated to support the use of public LibVA headers.
- Enable multi-GPU testing on systems without direct GPU-interconnects.
#### Fixes
* Fixed some package dependencies.
## Upcoming changes
* A future release will enable the use of HIPCC compiled binaries `hipcc.bin` and `hipconfig.bin` by default. No action is needed by users; you may continue calling high-level Perl scripts `hipcc` and `hipconfig`. `hipcc.bin` and `hipconfig.bin` will be invoked by the high-level Perl scripts. To revert to the previous behavior and invoke `hipcc.pl` and `hipconfig.pl`, set the `HIP_USE_PERL_SCRIPTS` environment variable to `1`.
* A subsequent release will remove high-level HIPCC Perl scripts from `hipcc` and `hipconfig`. This release will remove the `HIP_USE_PERL_SCRIPTS` environment variable. It will rename `hipcc.bin` and `hipconfig.bin` to `hipcc` and `hipconfig` respectively. No action is needed by the users. To revert to the previous behavior, invoke `hipcc.pl` and `hipconfig.pl` explicitly.
* A subsequent release will remove `hipcc.pl` and `hipconfig.pl` for HIPCC.
- Fixed kernel launch failure on execute of very large odd-length real-complex transforms.

View File

@@ -1,11 +1,12 @@
<?xml version="1.0" encoding="UTF-8"?>
<manifest>
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
<default revision="refs/tags/rocm-6.1.2"
<default revision="refs/tags/rocm-6.1.1"
remote="rocm-org"
sync-c="true"
sync-j="4" />
<!--list of projects for ROCm-->
<project path="ROCm-OpenCL-Runtime/api/opencl/khronos/icd" name="OpenCL-ICD-Loader" remote="KhronosGroup" />
<project name="ROCK-Kernel-Driver" />
<project name="ROCR-Runtime" />
<project name="ROCT-Thunk-Interface" />

View File

@@ -77,7 +77,8 @@ Obtain the value of `gpu-arch` by running the following command:
[//]: # (dated link below, needs updating)
See the complete list of [compiler command-line references](https://github.com/ROCm/llvm-project/blob/amd-staging/openmp/docs/CommandLineArgumentReference.rst).
See the complete list of compiler command-line references
[here](https://github.com/ROCm/llvm-project/blob/amd-stg-open/clang/docs/CommandGuide/clang.rst).
### Using `rocprof` with OpenMP

View File

@@ -12,119 +12,117 @@ Use this matrix to view the ROCm compatibility across successive major and minor
.. container:: format-big-table
.. csv-table::
:header: "ROCm Version", "6.1.2", "6.1.0", "6.0.0"
:header: "ROCm Version", "6.1.0", "6.0.0"
:stub-columns: 1
:doc:`Operating Systems <rocm-install-on-linux:reference/system-requirements>`, "Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3"
,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
,"RHEL 9.4 [#red-hat94_612]_, 9.3, 9.2","RHEL 9.4 [#red-hat94]_, 9.3, 9.2","RHEL 9.3, 9.2"
,"RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
,"SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
,CentOS 7.9,CentOS 7.9,CentOS 7.9
,"Oracle Linux 8.9 [#oracle89]_","Oracle Linux 8.9 [#oracle89]_"
,,,
:doc:`GFX Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3
,CDNA2,CDNA2,CDNA2
,CDNA,CDNA,CDNA
,RDNA3,RDNA3,RDNA3
,RDNA2,RDNA2,RDNA2
,,,
:doc:`GFX Card <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100,gfx1100
,gfx1030,gfx1030,gfx1030
,gfx942 [#mi300_612]_,gfx942 [#mi300_610]_, gfx942 [#mi300_600]_
,gfx90a,gfx90a,gfx90a
,gfx908,gfx908,gfx908
,,,
ECOSYSTEM SUPPORT:,,,
:doc:`PyTorch <rocm-install-on-linux:how-to/3rd-party/pytorch-install>`,"2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
:doc:`TensorFlow <rocm-install-on-linux:how-to/3rd-party/tensorflow-install>`,"2.15, 2.14, 2.13","2.15, 2.14, 2.13","2.14, 2.13, 2.12"
:doc:`JAX <rocm-install-on-linux:how-to/3rd-party/jax-install>`,0.4.26,0.4.26,0.4.26
`ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.17.3,1.14.1
,,,
3RD PARTY COMMUNICATION LIBS:,,,
`UCC <https://github.com/ROCm/ucc>`_,>=1.2.0,>=1.2.0,>=1.2.0
`UCX <https://github.com/ROCm/ucx>`_,>=1.14.1,>=1.14.1,>=1.14.1
,,,
3RD PARTY ALGORITHM LIBS:,,,
Thrust,2.1.0,2.1.0,2.0.1
CUB,2.1.0,2.1.0,2.0.1
,,,
ML & COMPUTER VISION LIBS:,,,
:doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0
:doc:`MIGraphX <amdmigraphx:index>`,2.9.0,2.9.0,2.8.0
:doc:`MIOpen <miopen:index>`,3.1.0,3.1.0,3.0.0
:doc:`MIVisionX <mivisionx:index>`,2.5.0,2.5.0,2.5.0
:doc:`rocDecode <rocdecode:index>`,0.5.0,0.5.0,N/A
:doc:`ROCm Performance Primitives (RPP) <rpp:index>`,1.5.0,1.5.0,1.4.0
,,,
COMMUNICATION:,,,
:doc:`RCCL <rccl:index>`,2.18.6,2.18.6,2.18.3
,,,
MATH LIBS:,,,
`half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0
:doc:`hipBLAS <hipblas:index>`,2.1.0,2.1.0,2.0.0
:doc:`hipBLASLt <hipblaslt:index>`,0.7.0,0.7.0,0.6.0
:doc:`hipFFT <hipfft:index>`,1.0.14,1.0.14,1.0.13
:doc:`hipFORT <hipfort:index>`,0.4.0,0.4.0,0.4.0
:doc:`hipRAND <hiprand:index>`,2.10.16,2.10.16,2.10.16
:doc:`hipSOLVER <hipsolver:index>`,2.1.0,2.1.0,2.0.0
:doc:`hipSPARSE <hipsparse:index>`,3.0.1,3.0.1,3.0.0
:doc:`hipSPARSELt <hipsparselt:index>`,0.1.0,0.1.0,0.1.0
:doc:`rocALUTION <rocalution:index>`,3.1.1,3.1.1,3.0.3
:doc:`rocBLAS <rocblas:index>`,4.1.0,4.1.0,4.0.0
:doc:`rocFFT <rocfft:index>`,1.0.27,1.0.27,1.0.23
:doc:`rocRAND <rocrand:index>`,3.0.1,3.0.1,2.10.17
:doc:`rocSOLVER <rocsolver:index>`,3.25.0,3.25.0,3.24.0
:doc:`rocSPARSE <rocsparse:index>`,3.1.2,3.1.2,3.0.2
:doc:`rocWMMA <rocwmma:index>`,1.4.0,1.4.0,1.3.0
`Tensile <https://github.com/ROCm/Tensile>`_,4.40.0,4.40.0,4.39.0
,,,
PRIMITIVES:,,,
:doc:`hipCUB <hipcub:index>`,3.1.0,3.1.0,3.0.0
:doc:`hipTensor <hiptensor:index>`,1.2.0,1.2.0,1.1.0
:doc:`rocPRIM <rocprim:index>`,3.1.0,3.1.0,3.0.0
:doc:`rocThrust <rocthrust:index>`,3.0.1,3.0.1,3.0.0
,,,
SUPPORT LIBS:,,,
`hipother <https://github.com/ROCm/hipother>`_,6.1.40091,6.1.40091,6.0.32830
:doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.12.0,0.12.0,0.11.0
`rocm-core <https://github.com/ROCm/rocm-core>`_,6.1.0,6.1.0,6.0.0
`ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240125.3.30,20240125.3.30,20231016.2.245
,,,
TOOLS:,,,
:doc:`AMD SMI <amdsmi:index>`,24.4.1,24.4.1,23.4.2
:doc:`HIPIFY <hipify:index>`,17.0.0,17.0.0,17.0.0
:doc:`ROCdbgapi <rocdbgapi:index>`,0.71.0,0.71.0,0.71.0
:doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0
:doc:`ROCProfiler <rocprofiler:index>`,2.0.60100,2.0.60100,2.0.0
`rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.3.0,0.3.0,N/A
:doc:`ROCTracer <roctracer:index>`,4.1.60100,4.1.60100,4.1.0
:doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0
:doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0,0.3.0
:doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,14.1.0,14.1.0,13.2.0
:doc:`ROCm SMI <rocm_smi_lib:index>`,7.0.0,7.0.0,6.0.0
:doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.1.0,rocm-6.1.0,rocm-6.0.0
:doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3,2.0.3
:doc:`TransferBench <transferbench:index>`,1.48,1.48,1.46
,,,
COMPILERS:,,,
`clang-ocl <https://github.com/ROCm/clang-ocl>`_,0.5.0,0.5.0,0.5.0
`Flang <https://github.com/ROCm/flang>`_,17.0.0.24103,17.0.0.24103,17.0.0.23483
`llvm-project <https://github.com/ROCm/llvm-project>`_,17.0.0.24103,17.0.0.24103,17.0.0.23483
`OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,17.0.0.24103,17.0.0.24103,17.0.0.23483
,,,
RUNTIMES:,,,
:doc:`HIP <hip:index>`,6.1.40091,6.1.40091,6.0.32830
`OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0
:doc:`ROCR-Runtime <rocr-runtime:index>`,1.13.0,1.13.0,1.12.0
:doc:`Operating Systems <rocm-install-on-linux:reference/system-requirements>`, "Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3"
,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
,"RHEL 9.4 [#red-hat94]_, 9.3, 9.2","RHEL 9.3, 9.2"
,"RHEL 8.9, 8.8","RHEL 8.9, 8.8"
,"SLES 15 SP5, SP4","SLES 15 SP5, SP4"
,CentOS 7.9,CentOS 7.9
,"Oracle Linux 8.9 [#oracle89]_"
,,
:doc:`GFX Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3
,CDNA2,CDNA2
,CDNA,CDNA
,RDNA3,RDNA3
,RDNA2,RDNA2
,,
:doc:`GFX Card <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100
,gfx1030,gfx1030
,gfx942 [#]_, gfx942 [#]_
,gfx90a,gfx90a
,gfx908,gfx908
,,
ECOSYSTEM SUPPORT:,,
:doc:`PyTorch <rocm-install-on-linux:how-to/3rd-party/pytorch-install>`,"2.1, 2.0, 1.13","2.1, 2.0, 1.13"
:doc:`TensorFlow <rocm-install-on-linux:how-to/3rd-party/tensorflow-install>`,"2.15, 2.14, 2.13","2.14, 2.13, 2.12"
:doc:`JAX <rocm-install-on-linux:how-to/3rd-party/jax-install>`,0.4.26,0.4.26
`ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.14.1
,,
3RD PARTY COMMUNICATION LIBS:,,
`UCC <https://github.com/ROCm/ucc>`_,>=1.2.0,>=1.2.0
`UCX <https://github.com/ROCm/ucx>`_,>=1.14.1,>=1.14.1
,,
3RD PARTY ALGORITHM LIBS:,,
Thrust,2.1.0,2.0.1
CUB,2.1.0,2.0.1
,,
ML & COMPUTER VISION LIBS:,,
:doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0
:doc:`MIGraphX <amdmigraphx:index>`,2.9.0,2.8.0
:doc:`MIOpen <miopen:index>`,3.1.0,3.0.0
:doc:`MIVisionX <mivisionx:index>`,2.5.0,2.5.0
:doc:`rocDecode <rocdecode:index>`,0.5.0,N/A
:doc:`ROCm Performance Primitives (RPP) <rpp:index>`,1.5.0,1.4.0
,,
COMMUNICATION:,,
:doc:`RCCL <rccl:index>`,2.18.6,2.18.3
,,
MATH LIBS:,,
`half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0
:doc:`hipBLAS <hipblas:index>`,2.1.0,2.0.0
:doc:`hipBLASLt <hipblaslt:index>`,0.7.0,0.6.0
:doc:`hipFFT <hipfft:index>`,1.0.14,1.0.13
:doc:`hipFORT <hipfort:index>`,0.4.0,0.4.0
:doc:`hipRAND <hiprand:index>`,2.10.16,2.10.16
:doc:`hipSOLVER <hipsolver:index>`,2.1.0,2.0.0
:doc:`hipSPARSE <hipsparse:index>`,3.0.1,3.0.0
:doc:`hipSPARSELt <hipsparselt:index>`,0.1.0,0.1.0
:doc:`rocALUTION <rocalution:index>`,3.1.1,3.0.3
:doc:`rocBLAS <rocblas:index>`,4.1.0,4.0.0
:doc:`rocFFT <rocfft:index>`,1.0.27,1.0.23
:doc:`rocRAND <rocrand:index>`,3.0.1,2.10.17
:doc:`rocSOLVER <rocsolver:index>`,3.25.0,3.24.0
:doc:`rocSPARSE <rocsparse:index>`,3.1.2,3.0.2
:doc:`rocWMMA <rocwmma:index>`,1.4.0,1.3.0
`Tensile <https://github.com/ROCm/Tensile>`_,4.40.0,4.39.0
,,
PRIMITIVES:,,
:doc:`hipCUB <hipcub:index>`,3.1.0,3.0.0
:doc:`hipTensor <hiptensor:index>`,1.2.0,1.1.0
:doc:`rocPRIM <rocprim:index>`,3.1.0,3.0.0
:doc:`rocThrust <rocthrust:index>`,3.0.1,3.0.0
,,
SUPPORT LIBS:,,
`hipother <https://github.com/ROCm/hipother>`_,6.1.40091,6.0.32830
:doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.12.0,0.11.0
`rocm-core <https://github.com/ROCm/rocm-core>`_,6.1.0,6.0.0
`ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240125.3.30,20231016.2.245
,,
TOOLS:,,
:doc:`AMD SMI <amdsmi:index>`,24.4.1,23.4.2
:doc:`HIPIFY <hipify:index>`,17.0.0,17.0.0
:doc:`ROCdbgapi <rocdbgapi:index>`,0.71.0,0.71.0
:doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0
:doc:`ROCProfiler <rocprofiler:index>`,2.0.60100,2.0.0
`rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.3.0,N/A
:doc:`ROCTracer <roctracer:index>`,4.1.60100,4.1.0
:doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0
:doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0
:doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,14.1.0,13.2.0
:doc:`ROCm SMI <rocm_smi_lib:index>`,7.0.0,6.0.0
:doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.1.0,rocm-6.0.0
:doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3
:doc:`TransferBench <transferbench:index>`,1.48,1.46
,,
COMPILERS:,,
`clang-ocl <https://github.com/ROCm/clang-ocl>`_,0.5.0,0.5.0
`Flang <https://github.com/ROCm/flang>`_,17.0.0.24103,17.0.0.23483
`llvm-project <https://github.com/ROCm/llvm-project>`_,17.0.0.24103,17.0.0.23483
`OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,17.0.0.24103,17.0.0.23483
,,
RUNTIMES:,,
:doc:`HIP <hip:index>`,6.1.40091,6.0.32830
`OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0
:doc:`ROCR-Runtime <rocr-runtime:index>`,1.13.0,1.12.0
.. rubric:: Footnotes
.. [#red-hat94_612] **For ROCm 6.1** - RHEL 9.4 is supported only on AMD Instinct MI300A.
.. [#red-hat94] **For ROCm 6.1** - RHEL 9.4 is supported only on AMD Instinct MI300A.
.. [#oracle89] **For ROCm 6.1.1** - Oracle Linux is supported only on AMD Instinct MI300X.
.. [#mi300_612] **For ROCm 6.1** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4.
.. [#mi300_610] **For ROCm 6.1** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4.
.. [#mi300_600] **For ROCm 6.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9 and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
.. [#] **For ROCm 6.1** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4.
.. [#] **For ROCm 6.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9 and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.

View File

@@ -33,8 +33,8 @@ Units (CU). The MI250 GCD has 104 active CUs. Each compute unit is further
subdivided into four SIMD units that process SIMD instructions of 16 data
elements per instruction (for the FP64 data type). This enables the CU to
process 64 work items (a so-called “wavefront”) at a peak clock frequency of 1.7
GHz. Therefore, the theoretical maximum FP64 peak performance per GCD is 45.3
TFLOPS for vector instructions. The MI250 compute units also provide specialized
GHz. Therefore, the theoretical maximum FP64 peak performance per GCD is 22.6
TFLOPS for vector instructions. This equates to 45.3 TFLOPS for vector instructions for both GCDs together. The MI250 compute units also provide specialized
execution units (also called matrix cores), which are geared toward executing
matrix operations like matrix-matrix multiplications. For FP64, the peak
performance of these units amounts to 90.5 TFLOPS.

View File

@@ -424,4 +424,8 @@ Shadow byte legend (one shadow byte represents 8 application bytes):
* Lack of detection on the GPU might also be due to the implementation not instrumenting accesses to all GPU specific address spaces. For example, in the current implementation accesses to "private" or "stack" variables on the GPU are not instrumented, and accesses to HIP shared variables (also known as "local data store" or "LDS") are also not instrumented.
* It can also be the case that a memory fault is hit for an invalid address even with the instrumentation. This is usually caused by the invalid address being so wild that its shadow address is outside any memory region, and the fault actually occurs on the access to the shadow address. It is also possible to hit a memory fault for the `NULL` pointer. While address 0 does have a shadow location, it is not poisoned by the runtime.
* It can also be the case that a memory fault is reported for an invalid address even with the instrumentation. This is usually caused by the invalid address being so wild that its shadow address is outside any memory region, and the fault actually occurs on the access to the shadow address. It is also possible to hit a memory fault for the `NULL` pointer. While address 0 does have a shadow location, it is not poisoned by the runtime.
* There is currently a bug which can result in memory faults being reported when running instrumented device code which makes use of `malloc`, `free`, `new`, or `delete`.
* There is currently a bug which can result in undefined symbols being reported at compile time when instrumented device code makes use of `new` and `delete`.

View File

@@ -23,7 +23,7 @@ for template in templates:
shutil.copy2('../RELEASE.md','./about/release-notes.md')
# Keep capitalization due to similar linking on GitHub's markdown preview.
shutil.copy2('../CHANGELOG.md','./about/changelog.md')
shutil.copy2('../CHANGELOG.md','./about/CHANGELOG.md')
latex_engine = "xelatex"
latex_elements = {
@@ -38,8 +38,8 @@ latex_elements = {
project = "ROCm Documentation"
author = "Advanced Micro Devices, Inc."
copyright = "Copyright (c) 2024 Advanced Micro Devices, Inc. All rights reserved."
version = "6.1.2"
release = "6.1.2"
version = "6.1.1"
release = "6.1.1"
setting_all_article_info = True
all_article_info_os = ["linux", "windows"]
all_article_info_author = ""
@@ -49,12 +49,12 @@ article_pages = [
{
"file":"about/release-notes",
"os":["linux", "windows"],
"date":"2024-06-04"
"date":"2024-05-08"
},
{
"file":"about/changelog",
"file":"about/CHANGELOG",
"os":["linux", "windows"],
"date":"2024-06-04"
"date":"2024-05-08"
},
{"file":"install/windows/install-quick", "os":["windows"]},
@@ -84,7 +84,25 @@ article_pages = [
{"file":"how-to/system-debugging", "os":["linux"]},
{"file":"how-to/tuning-guides", "os":["linux", "windows"]},
{"file":"rocm-a-z", "os":["linux", "windows"]},
{"file":"how-to/rocm-for-ai/index", "os":["linux"]},
{"file":"how-to/rocm-for-ai/install", "os":["linux"]},
{"file":"how-to/rocm-for-ai/train-a-model", "os":["linux"]},
{"file":"how-to/rocm-for-ai/deploy-your-model", "os":["linux"]},
{"file":"how-to/rocm-for-ai/hugging-face-models", "os":["linux"]},
{"file":"how-to/rocm-for-hpc/index", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/index", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/overview", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/fine-tuning-and-inference", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/llm-inference-frameworks", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/model-acceleration-libraries", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/model-quantization", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/optimizing-with-composable-kernel", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/optimizing-triton-kernel", "os":["linux"]},
{"file":"how-to/llm-fine-tuning-optimization/profiling-and-debugging", "os":["linux"]},
]
exclude_patterns = ['temp']

View File

@@ -12,8 +12,7 @@ There are four standard ways to provide feedback on this repository.
All contributions to ROCm documentation should arrive via the
[GitHub Flow](https://docs.github.com/en/get-started/quickstart/github-flow)
targeting the develop branch of the repository. If you are unable to contribute
via the GitHub Flow, feel free to email us at [rocm-feedback@amd.com](mailto:rocm-feedback@amd.com?subject=Documentation%20Feedback).
targeting the develop branch of the repository.
For more in-depth information on creating a pull request (PR), see
[Contributing](./contributing.md).
@@ -30,7 +29,3 @@ and follow along on via public announcements.
Issues on existing or absent documentation can be filed in
[GitHub Issues](https://github.com/ROCm/ROCm/issues).
## Email
Send other feedback or questions to [rocm-feedback@amd.com](mailto:rocm-feedback@amd.com?subject=Documentation%20Feedback).

Binary file not shown.

Before

Width:  |  Height:  |  Size: 187 KiB

View File

@@ -28,18 +28,9 @@ graphs, tensor parallel multi-GPU, GPTQ, AWQ, and token speculation.
Installing vLLM
---------------
1. To install vLLM, run the following commands.
.. code-block:: shell
# Install from source
git clone https://github.com/ROCm/vllm.git
cd vllm
PYTORCH_ROCM_ARCH=gfx942 python setup.py install #MI300 series
.. _fine-tuning-llms-vllm-rocm-docker-image:
2. Run the following commands to build a Docker image ``vllm-rocm``.
1. Run the following commands to build a Docker image ``vllm-rocm``.
.. code-block:: shell
@@ -52,7 +43,7 @@ Installing vLLM
.. tab-item:: vLLM on a single-accelerator system
:sync: single
3. To use vLLM as an API server to serve reference requests, first start a container using the :ref:`vllm-rocm
2. To use vLLM as an API server to serve reference requests, first start a container using the :ref:`vllm-rocm
Docker image <fine-tuning-llms-vllm-rocm-docker-image>`.
.. code-block:: shell
@@ -69,7 +60,7 @@ Installing vLLM
vllm-rocm \
bash
4. Inside the container, start the API server to run on a single accelerator on port 8000 using the following command.
3. Inside the container, start the API server to run on a single accelerator on port 8000 using the following command.
.. code-block:: shell
@@ -81,7 +72,7 @@ Installing vLLM
:alt: vLLM API server log message
:align: center
5. To test, send it a curl request containing a prompt.
4. To test, send it a curl request containing a prompt.
.. code-block:: shell
@@ -92,11 +83,11 @@ Installing vLLM
.. code-block:: text
{"text":["What is AMD Instinct?\nAmd Instinct is a brand new line of high-performance computing (HPC) processors from Advanced Micro Devices (AMD). These processors are designed to deliver unparalleled performance for HPC workloads, including scientific simulations, data analytics, and machine learning.\nThe Instinct lineup includes a range of processors, from the entry-level Inst"]}
.. tab-item:: vLLM on a multi-accelerator system
:sync: multi
3. To use vLLM as an API server to serve reference requests, first start a container using the :ref:`vllm-rocm
2. To use vLLM as an API server to serve reference requests, first start a container using the :ref:`vllm-rocm
Docker image <fine-tuning-llms-vllm-rocm-docker-image>`.
.. code-block:: shell
@@ -114,14 +105,14 @@ Installing vLLM
bash
4. To run API server on multiple GPUs, use the ``-tp`` or ``--tensor-parallel-size`` parameter. For example, to use two
3. To run API server on multiple GPUs, use the ``-tp`` or ``--tensor-parallel-size`` parameter. For example, to use two
GPUs, start the API server using the following command.
.. code-block:: shell
python -m vllm.entrypoints.api_server --model /app/model --dtype float16 -tp 2 --port 8000 &
5. To run multiple instances of API Servers, specify different ports for each server, and use ``ROCR_VISIBLE_DEVICES`` to
4. To run multiple instances of API Servers, specify different ports for each server, and use ``ROCR_VISIBLE_DEVICES`` to
isolate each instance to a different accelerator.
For example, to run two API servers, one on port 8000 using GPU 0 and 1, one on port 8001 using GPU 2 and 3, use a
@@ -132,7 +123,7 @@ Installing vLLM
ROCR_VISIBLE_DEVICES=0,1 python -m vllm.entrypoints.api_server --model /data/llama-2-7b-chat-hf --dtype float16 tp 2 --port 8000 &
ROCR_VISIBLE_DEVICES=2,3 python -m vllm.entrypoints.api_server --model /data/llama-2-7b-chat-hf --dtype float16 tp 2--port 8001 &
6. To test, send it a curl request containing a prompt.
5. To test, send it a curl request containing a prompt.
.. code-block:: shell
@@ -163,27 +154,29 @@ speculation.
Install TGI
-----------
1. To install the TGI Docker image, run the following commands.
1. Launch the TGI Docker container in the host machine.
.. code-block:: shell
# Install from Dockerfile
git clone https://github.com/huggingface/text-generation-inference.git -b mi300-compat
cd text-generation-inference
docker build . -f Dockerfile.rocm
docker run --name tgi --rm -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined
--device=/dev/kfd --device=/dev/dri --group-add video --ipc=host --shm-size 256g
--net host -v $PWD:/data
--entrypoint "/bin/bash"
--env HUGGINGFACE_HUB_CACHE=/data
ghcr.io/huggingface/text-generation-inference:latest-rocm
.. tab-set::
.. tab-item:: TGI on a single-accelerator system
:sync: single
2. Launch a model using TGI server on a single accelerator.
2. Inside the container, launch a model using TGI server on a single accelerator.
.. code-block:: shell
export ROCM_USE_FLASH_ATTN_V2_TRITON=True
text-generation-launcher --model-id NousResearch/Meta-Llama-3-70B --dtype float16 --port 8000 &
3. To test, send it a curl request containing a prompt.
.. code-block:: shell
@@ -191,26 +184,26 @@ Install TGI
curl http://localhost:8000/generate_stream -X POST -d '{"inputs":"What is AMD Instinct?","parameters":{"max_new_tokens":20}}' -H 'Content-Type: application/json'
You should receive a response like the following.
.. code-block:: shell
data:{"index":20,"token":{"id":304,"text":" in","logprob":-1.2822266,"special":false},"generated_text":" AMD Instinct is a new family of data center GPUs designed to accelerate the most demanding workloads in","details":null}
.. tab-item:: TGI on a multi-accelerator system
2. Launch a model using TGI server on multiple accelerators (4 in this case).
2. Inside the container, launch a model using TGI server on multiple accelerators (4 in this case).
.. code-block:: shell
export ROCM_USE_FLASH_ATTN_V2_TRITON=True
text-generation-launcher --model-id NousResearch/Meta-Llama-3-8B --dtype float16 --port 8000 --num-shard 4 &
3. To test, send it a curl request containing a prompt.
.. code-block:: shell
curl http://localhost:8000/generate_stream -X POST -d '{"inputs":"What is AMD Instinct?","parameters":{"max_new_tokens":20}}' -H 'Content-Type: application/json'
You should receive a response like the following.
.. code-block:: shell

View File

@@ -154,13 +154,13 @@ kernels by configuring the ``exllama_config`` parameter as the following.
.. code-block:: python
from transformers import AutoModelForCausalLM, GPTQConfig
#pretrained_model_dir = "meta-llama/Llama-2-7b"
base_model_name = "NousResearch/Llama-2-7b-hf"
gptq_config = GPTQConfig(bits=4, dataset="c4", exllama_config={"version":2})
pretrained_model_dir = "meta-llama/Llama-2-7b"
gptq_config = GPTQConfig(bits=4, exllama_config={"version":2})
quantized_model = AutoModelForCausalLM.from_pretrained(
base_model_name,
device_map="auto",
base_model_name,
device_map="auto",
quantization_config=gptq_config)
bitsandbytes
============

View File

@@ -343,11 +343,6 @@ or :doc:`rocBLAS <rocblas:index>` is faster for a specific operation.
then required to strip out the kernel and create kernel
compilation and launch via Triton.
* For advanced ``matmul`` or ``conv`` configuration tuning, the ``inductor-gemm-tuner`` can
help. This implements the Triton ``conv``/``mm`` implementations used upstream
and allows specification of inputs and configuration tuning search space if new
tunings are found that can be added to the auto-tune list.
Other guidelines
================

View File

View File

@@ -21,6 +21,3 @@ In this guide, you'll learn about:
- :doc:`Running models from Hugging Face <hugging-face-models>`
- :doc:`Deploying your model <deploy-your-model>`
To learn about ROCm for HPC applications and scientific computing, see
:doc:`../rocm-for-hpc/index`.

View File

@@ -137,4 +137,4 @@ The following developer blogs showcase examples of how to fine-tune a model on a
* Recipes for fine-tuning Llama2 and 3 with ``llama-recipes``
* `meta-llama/llama-recipes: Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover
single/multi-node GPUs <https://github.com/meta-llama/llama-recipes/tree/main/recipes/finetuning>`_
single/multi-node GPUs <https://github.com/meta-llama/llama-recipes/tree/main/recipes/quickstart/finetuning>`_

View File

@@ -1,231 +0,0 @@
.. meta::
:description: How to use ROCm for HPC
:keywords: ROCm, AI, high performance computing, HPC
******************
Using ROCm for HPC
******************
The ROCm open-source software stack is optimized to extract high-performance
computing (HPC) workload performance from AMD Instinct™ accelerators
while maintaining compatibility with industry software frameworks.
ROCm enhances support and access for developers by providing streamlined and
improved tools that significantly increase productivity. Being open-source, ROCm
fosters innovation, differentiation, and collaboration within the developer
community, making it a powerful and accessible solution for leveraging the full
potential of AMD accelerators' capabilities in diverse computational
applications.
* For more information, see :doc:`What is ROCm? <../../what-is-rocm>`.
* For guidance on installing ROCm, see :doc:`rocm-install-on-linux:index`. See
the :doc:`../../compatibility/compatibility-matrix` for details on hardware
and operating system support.
Some of the most popular HPC frameworks are part of the ROCm platform, including
those to help parallelize operations across multiple accelerators and servers,
handle memory hierarchies, and solve linear systems.
.. image:: ../../data/how-to/rocm-for-hpc/hpc-stack-2024_6_20.png
:align: center
:alt: Software and hardware ecosystem surrounding ROCm and AMD Instinct for HPC
The following catalog of GPU-accelerated solutions includes a vast set of
platform-compatible HPC applications, including those for astrophysics, climate
and weather, computational chemistry, computational fluid dynamics, earth
science, genomics, geophysics, molecular dynamics, and physics computing.
Refer to the resources in the following table for instructions on building,
running, and deploying these applications on ROCm-capable systems with AMD
Instinct accelerators. Each build container provides parameters to specify
different source code branches, release versions of ROCm, OpenMPI, UCX, and
Ubuntu versions.
.. _hpc-apps:
..
Reduce font size of HPC app descriptions slightly.
.. raw:: html
<style>
#hpc-apps-table tr td:last-child {
font-size: 0.9rem;
}
</style>
.. container::
:name: hpc-apps-table
.. list-table::
:header-rows: 1
:stub-columns: 1
:widths: 2 2 5
* - Application domain
- HPC application
- Description
* - Physics
- `Chroma <https://github.com/amd/InfinityHub-CI/tree/main/chroma/>`_
- The Chroma package supports data-parallel programming constructs for lattice
field theory and in particular lattice QCD. It uses the SciDAC QDP++ data-parallel
programming (in C++) that presents a single high-level code image to the user,
but can generate highly optimized code for many architectural systems including
single node workstations, multi and many-core nodes, clusters of nodes via
QMP, and classic vector computers.
* -
- `Grid <https://github.com/amd/InfinityHub-CI/tree/main/grid/>`_
- Grid is a library for lattice QCD calculations that employs a high-level data parallel
approach while using a number of techniques to target multiple types of parallelism.
The library currently supports MPI, OpenMP and short vector parallelism. The SIMD
instructions sets covered include SSE, AVX, AVX2, FMA4, IMCI and AVX512. Recent
releases expanded this support to include GPU offloading.
* -
- `MILC <https://github.com/amd/InfinityHub-CI/tree/main/milc/>`_
- The MILC Code is a set of research codes developed by MIMD Lattice Computation
(MILC) collaboration for doing simulations of four dimensional SU(3) lattice gauge
theory on MIMD parallel machines scaling from single-processor workstations
to HPC systems. The MILC Code is publicly available for research purposes.
Publications of work done using this code or derivatives of this code should
acknowledge this use.
* -
- `PIConGPU <https://github.com/amd/InfinityHub-CI/tree/main/picongpu>`_
- PIConGPU (Particle-in-cell on Graphics Processing Units) is an Open Source
simulations framework for plasma and laser-plasma physics used to develop
advanced particle accelerators for radiation therapy of cancer, high energy
physics and photon science.
* - Astrophysics
- `Cholla <https://github.com/amd/InfinityHub-CI/tree/main/cholla/>`_
- An astrophysical simulation code developed for the extreme environments
encountered in astrophysical systems.
* - Geophysics
- `SPECFEM3D Cartesian <https://github.com/amd/InfinityHub-CI/tree/main/specfem3d>`_
- SPECFEM3D Cartesian simulates acoustic (fluid), elastic (solid), coupled
acoustic/elastic, poroelastic or seismic wave propagation in any type of
conforming mesh of hexahedra (structured or not.) It can, for instance,
model seismic waves propagating in sedimentary basins or any other
regional geological model following earthquakes. It can also be used
for non-destructive testing or for ocean acoustics.
* - Molecular dynamics
- `GROMACS with HIP (AMD implementation) <https://github.com/amd/InfinityHub-CI/tree/main/gromacs>`_
- GROMACS is a versatile package to perform molecular dynamics, i.e.
simulate the Newtonian equations of motion for systems with hundreds
to millions of particles. This AMD container is based on a released
version of GROMACS modified by AMD. This container only supports up
to a 8 GPU configuration
* -
- `LAMMPS <https://github.com/amd/InfinityHub-CI/tree/main/lammps>`_
- LAMMPS is a classical molecular dynamics code with a focus on materials
modeling. It's an acronym for Large-scale Atomic/Molecular Massively
Parallel Simulator.
* - Computational fluid dynamics
- `NEKO <https://github.com/amd/InfinityHub-CI/tree/main/neko>`_
- Neko is a portable framework for high-order spectral element flow simulations.
Written in modern Fortran, Neko adopts an object-oriented approach, allowing
multi-tier abstractions of the solver stack and facilitating various hardware
backends ranging from general-purpose processors, CUDA and HIP enabled
accelerators to SX-Aurora vector processors.
* -
- `nekRS <https://github.com/amd/InfinityHub-CI/tree/main/nekrs>`_
- nekRS is an open-source Navier Stokes solver based on the spectral element
method targeting classical processors and accelerators like GPUs.
* - Computational chemistry
- `QUDA <https://github.com/amd/InfinityHub-CI/tree/main/quda>`_
- Library designed for efficient lattice QCD computations on
accelerators. It includes optimized Dirac operators and a variety of
fermion solvers and conjugate gradient (CG) implementations, enhancing
performance and accuracy in lattice QCD simulations.
* - Electronic structure
- `CP2K <https://github.com/amd/InfinityHub-CI/tree/main/cp2k>`_
- CP2K is a quantum chemistry and solid state physics software package that can
perform atomistic simulations of solid state, liquid, molecular, periodic, material,
crystal, and biological systems. This AMD container, based on a released version
of CP2K, is an AMD beta version with ongoing optimizations.
* - Quantum Monte Carlo Simulation
- `QMCPACK <https://github.com/amd/InfinityHub-CI/tree/main/qmcpack>`_
- QMCPACK is an open-source production-level many-body ab initio Quantum
Monte Carlo code for computing the electronic structure of atoms, molecules, 2D
nanomaterials and solids. The solid-state capabilities include metallic systems
as well as insulators. QMCPACK is expected to run well on workstations through
to the latest generation supercomputers. Besides high performance, particular
emphasis is placed on code quality and reproducibility.
* - Climate and weather
- `MPAS <https://github.com/amd/InfinityHub-CI/tree/main/mpas>`_
- The Model for Prediction Across Scales (MPAS) is a collaborative project for
developing atmosphere, ocean, and other earth-system simulation components
for use in climate, regional climate, and weather studies.
* - Benchmark
- `rocHPL <https://github.com/amd/InfinityHub-CI/tree/main/rochpl>`_
- HPL, or High-Performance Linpack, is a benchmark which solves a uniformly
random system of linear equations and reports floating-point execution rate.
This documentation supports the implementation of the HPL benchmark on
top of AMD's ROCm platform.
* -
- `rocHPL-MxP <https://github.com/amd/InfinityHub-CI/tree/main/hpl-mxp>`_
- Benchmark that highlights the convergence of HPC and AI workloads by
solving a system of linear equations using novel, mixed-precision
algorithms.
* -
- `HPCG <https://github.com/amd/InfinityHub-CI/tree/main/hpcg>`_
- HPCG, or the High Performance Conjugate Gradient Benchmark complements
the High Performance LINPACK (HPL) benchmark. The computational and data
access patterns of HPCG are designed to closely match a broad set of important
applications not represented by HPL, and to incentivize computer system
designers to invest in capabilities that will benefit the collective performance
of these applications.
* - Tools and libraries
- `ROCm with GPU-aware MPI container <https://github.com/amd/InfinityHub-CI/tree/main/base-gpu-mpi-rocm-docker>`_
- Base container for GPU-aware MPI with ROCm for HPC applications. This
project provides a boilerplate for building and running a Docker
container with ROCm supporting GPU-aware MPI implementations using
OpenMPI or UCX.
* -
- `Kokkos <https://github.com/amd/InfinityHub-CI/tree/main/kokkos>`_
- Kokkos is a programming model in C++ for writing performance portable
applications for use across HPC platforms. It provides abstractions for both
parallel execution of code and data management. Kokkos is designed to target
complex node architectures with N-level memory hierarchies and multiple types
of execution resources.
* -
- `PyFR <https://github.com/amd/InfinityHub-CI/tree/main/pyfr>`_
- PyFR is an open-source Python based framework for solving advection-diffusion
type problems on streaming architectures using the Flux Reconstruction approach of
Huynh. The framework is designed to solve a range of governing systems on mixed
unstructured grids containing various element types. It is also designed to target a
range of hardware platforms via use of an in-built domain specific language derived
from the Mako templating engine.
* -
- `RAJA <https://github.com/amd/InfinityHub-CI/tree/main/raja>`_
- RAJA is a library of C++ software abstractions, primarily developed at Lawrence
Livermore National Laboratory (LLNL), that enables architecture and programming
model portability for HPC applications.
* -
- `Trilinos <https://github.com/amd/InfinityHub-CI/tree/main/trilinos>`_
- The Trilinos Project is an effort to develop algorithms and enabling technologies
within an object-oriented software framework for the solution of large-scale,
complex multi-physics engineering and scientific problems.
To learn about ROCm for AI applications, see :doc:`../rocm-for-ai/index`.

View File

@@ -5,7 +5,7 @@
ROCm">
</head>
# System debugging guide
# System debugging
## ROCm language and system-level debug, flags, and environment variables

View File

@@ -1,108 +0,0 @@
<head>
<meta charset="UTF-8">
<meta name="description" content="AMD hardware optimization for specific workloads">
<meta name="keywords" content="high-performance computing, HPC, Instinct accelerators,
Radeon, tuning, tuning guide, AMD, ROCm">
</head>
# System optimization
This guide outlines system setup and tuning suggestions for AMD hardware to optimize performance for specific types of
workloads or use-cases.
## High-performance computing
High-performance computing (HPC) workloads have unique requirements. The default
hardware and BIOS configurations for OEM platforms may not provide optimal
performance for HPC workloads. To enable optimal HPC settings on a per-platform
and per-workload level, this guide calls out:
* BIOS settings that can impact performance
* Hardware configuration best practices
* Supported versions of operating systems
* Workload-specific recommendations for optimal BIOS and operating system
settings
There is also a discussion on the AMD Instinct™ software development
environment, including information on how to install and run the DGEMM, STREAM,
HPCG, and HPL benchmarks. This guidance provides a good starting point but is
not exhaustively tested across all compilers.
Prerequisites to understanding this document and to performing tuning of HPC
applications include:
* Experience in configuring servers
* Administrative access to the server's Management Interface (BMC)
* Administrative access to the operating system
* Familiarity with the OEM server's BMC (strongly recommended)
* Familiarity with the OS specific tools for configuration, monitoring, and
troubleshooting (strongly recommended)
This document provides guidance on tuning systems with various AMD Instinct™
accelerators for HPC workloads. This document is not an all-inclusive guide, and
some items referred to may have similar, but different, names in various OEM
systems (for example, OEM-specific BIOS settings). This document also provides
suggestions on items that should be the initial focus of additional,
application-specific tuning.
This document is based on the AMD EPYC™ 7003-series processor family (former
codename "Milan").
While this guide is a good starting point, developers are encouraged to perform
their own performance testing for additional tuning.
:::::{grid} 1 1 2 2
:gutter: 1
:::{grid-item-card}
**[AMD Instinct™ MI200](./tuning-guides/mi200)**
This chapter goes through how to configure your AMD Instinct™ MI200 accelerated
compute nodes to get the best performance out of them.
* [Instruction Set Architecture (ISA)](https://www.amd.com/system/files/TechDocs/instinct-mi200-cdna2-instruction-set-architecture.pdf)
* [White paper](https://www.amd.com/system/files/documents/amd-cdna2-white-paper.pdf)
:::
:::{grid-item-card}
**[AMD Instinct™ MI100](./tuning-guides/mi100)**
This chapter briefly reviews hardware aspects of the AMD Instinct™ MI100
accelerators and the CDNA™ 1 architecture that is the foundation of these GPUs.
* [ISA](https://www.amd.com/system/files/TechDocs/instinct-mi100-cdna1-shader-instruction-set-architecture%C2%A0.pdf)
* [White paper](https://www.amd.com/system/files/documents/amd-cdna-whitepaper.pdf)
:::
:::::
## Workstation
Workstation workloads, much like high-performance computing, have a unique set of
requirements, a blend of both graphics and compute, certification, stability and
the list continues.
The document covers specific software requirements and processes needed to use
these GPUs for Single Root I/O Virtualization (SR-IOV) and machine learning
(ML).
The main purpose of this document is to help users utilize the RDNA 2 GPUs to
their full potential.
:::::{grid} 1 1 2 2
:gutter: 1
:::{grid-item-card}
**[AMD Radeon™ PRO W6000 and V620](./tuning-guides/w6000-v620)**
This chapter describes the AMD GPUs with RDNA™ 2 architecture, namely AMD Radeon
PRO W6800 and AMD Radeon PRO V620
* [AMD RDNA2 ISA](https://www.amd.com/system/files/TechDocs/rdna2-shader-instruction-set-architecture.pdf)
* [White paper](https://www.amd.com/system/files/documents/rdna2-explained-radeon-pro-W6000.pdf)
:::
:::::

View File

@@ -0,0 +1,107 @@
.. meta::
:description: AMD hardware optimization for specific workloads
:keywords: high-performance computing, HPC, Instinct accelerators, Radeon,
AMD, ROCm, system, EPYC, CPU, GPU, BIOS, OS
*******************
System optimization
*******************
System administrators can optimize the performance of their AMD hardware
generally and based on specific workloads and use cases. This section outlines
recommended system optimization options for AMD accelerators and GPUs, enabling
administrators to maximize efficiency and performance.
High-performance computing workloads
====================================
High-performance computing (HPC) workloads have unique requirements that may not
be fully met by the default hardware and BIOS configurations of OEM platforms.
To achieve optimal performance for HPC workloads, it is crucial to adjust
settings at both the platform and workload levels.
The :ref:`AMD Instinct™ accelerator optimization guides <mi-optimization-guides>`
in this section describe:
* BIOS settings that can impact performance
* Hardware configuration best practices
* Supported versions of operating systems
* Workload-specific recommendations for optimal BIOS and operating system
settings
The guides might also discuss the AMD Instinct software development
environment, including information on how to install and run the DGEMM, STREAM,
HPCG, and HPL benchmarks. The guides provide a good starting point but is
not tested exhaustively across all compilers.
Knowledge prerequisites to better understand the following
:ref:`Instinct system optimization guides <mi-optimization-guides>` and to
perform tuning for HPC applications include:
* Experience in configuring servers
* Administrative access to the server's Management Interface (BMC)
* Administrative access to the operating system
* Familiarity with the OEM server's BMC (strongly recommended)
* Familiarity with the OS specific tools for configuration, monitoring, and
troubleshooting (strongly recommended)
While the following guides are a good starting point, developers are encouraged
to perform their own performance testing for additional tuning per device and
per workload.
.. _mi-optimization-guides:
.. list-table::
:header-rows: 1
:stub-columns: 1
* - Optimization guide
- Architecture reference
- White papers
* - :doc:`AMD Instinct MI200 <tuning-guides/mi200>`
- `AMD Instinct MI200 instruction set architecture <https://www.amd.com/system/files/TechDocs/instinct-mi200-cdna2-instruction-set-architecture.pdf>`_
- `CDNA 2 architecture <https://www.amd.com/system/files/documents/amd-cdna2-white-paper.pdf>`_
* - :doc:`AMD Instinct MI100 <tuning-guides/mi100>`
- `AMD Instinct MI100 instruction set architecture <https://www.amd.com/system/files/TechDocs/instinct-mi100-cdna1-shader-instruction-set-architecture%C2%A0.pdf>`_
- `CDNA architecture <https://www.amd.com/system/files/documents/amd-cdna-whitepaper.pdf>`_
Workstation workloads
=====================
Workstation workloads, much like those for HPC, have a unique set of
requirements: a blend of both graphics and compute, certification, stability and
others.
The document covers specific software requirements and processes needed to use
these GPUs for Single Root I/O Virtualization (SR-IOV) and machine learning
tasks.
The main purpose of this document is to help users utilize the RDNA™ 2 GPUs to
their full potential.
.. _rdna-optimization-guides:
.. list-table::
:header-rows: 1
:stub-columns: 1
* - Optimization guide
- Architecture reference
- White papers
* - :doc:`AMD Radeon PRO W6000 and V620 <tuning-guides/w6000-v620>`
- `AMD RDNA 2 instruction set architecture <https://www.amd.com/system/files/TechDocs/rdna2-shader-instruction-set-architecture.pdf>`_
- `RDNA 2 architecture <https://www.amd.com/system/files/documents/rdna2-explained-radeon-pro-W6000.pdf>`_

View File

@@ -1,11 +1,11 @@
<head>
<meta charset="UTF-8">
<meta name="description" content="MI100 high-performance computing and tuning guide">
<meta name="keywords" content="MI100, high-performance computing, HPC, tuning, BIOS
<meta name="keywords" content="MI100, high-performance computing, HPC, BIOS
settings, NBIO, AMD, ROCm">
</head>
# MI100 high-performance computing and tuning guide
# AMD Instinct MI100 system optimization
## System settings

View File

@@ -1,11 +1,11 @@
<head>
<meta charset="UTF-8">
<meta name="description" content="MI200 high-performance computing and tuning guide">
<meta name="keywords" content="MI200, high-performance computing, HPC, tuning, BIOS
<meta name="keywords" content="MI200, high-performance computing, HPC, BIOS
settings, NBIO, AMD, ROCm">
</head>
# MI200 high-performance computing and tuning guide
# AMD Instinct MI200 system optimization
## System settings

View File

@@ -1,11 +1,11 @@
<head>
<meta charset="UTF-8">
<meta name="description" content="RDNA2 workstation tuning guide">
<meta name="keywords" content="RDNA2, workstation tuning, BIOS settings, installation, AMD,
<meta name="keywords" content="RDNA2, workstation, BIOS settings, installation, AMD,
ROCm">
</head>
# RDNA2 workstation tuning guide
# AMD RDNA2 system optimization
## System settings

View File

@@ -25,7 +25,6 @@ Our documentation is organized into the following categories:
:class-container: rocm-doc-grid
:::{grid-item-card}
:class-card: sd-text-black
:img-top: ./data/banner-installation.jpg
:img-alt: Install documentation
:padding: 2
@@ -47,7 +46,6 @@ Our documentation is organized into the following categories:
:::
:::{grid-item-card}
:class-card: sd-text-black
:img-top: ./data/banner-compatibility.jpg
:img-alt: Compatibility information
:padding: 2
@@ -65,7 +63,6 @@ Our documentation is organized into the following categories:
<!-- markdownlint-disable MD051 -->
:::{grid-item-card}
:class-card: sd-text-black
:img-top: ./data/banner-reference.jpg
:img-alt: Reference documentation
:padding: 2
@@ -86,30 +83,27 @@ Our documentation is organized into the following categories:
<!-- markdownlint-enable MD051 -->
:::{grid-item-card}
:class-card: sd-text-black
:img-top: ./data/banner-howto.jpg
:img-alt: How-to documentation
:padding: 2
* [Using ROCm for AI](./how-to/rocm-for-ai/index.rst)
* [Using ROCm for HPC](./how-to/rocm-for-hpc/index.rst)
* [Fine-tuning LLMs and inference optimization](./how-to/llm-fine-tuning-optimization/index.rst)
* [System tuning for various architectures](./how-to/tuning-guides.md)
* [MI100](./how-to/tuning-guides/mi100.md)
* [MI200](./how-to/tuning-guides/mi200.md)
* [RDNA2](./how-to/tuning-guides/w6000-v620.md)
* [System optimization](./how-to/tuning-guides.rst)
* [AMD Instinct MI200](./how-to/tuning-guides/mi200.md)
* [AMD Instinct MI100](./how-to/tuning-guides/mi100.md)
* [AMD Instinct RDNA2](./how-to/tuning-guides/w6000-v620.md)
* [System level debugging](./how-to/system-debugging.md)
* [GPU-enabled MPI](./how-to/gpu-enabled-mpi.rst)
* [Using compiler features](./conceptual/compiler-topics.md)
* [Using AddressSanitizer](./conceptual/using-gpu-sanitizer.md)
* [Compiler disambiguation](./conceptual/compiler-disambiguation.md)
* [OpenMP support in ROCm](./about/compatibility/openmp.md)
* [Setting the number of CUs](./how-to/setting-cus)
* [System level debugging](./how-to/system-debugging.md)
* [GitHub examples](https://github.com/amd/rocm-examples)
:::
:::{grid-item-card}
:class-card: sd-text-black
:img-top: ./data/banner-conceptual.jpg
:img-alt: Conceptual documentation
:padding: 2

View File

@@ -233,22 +233,6 @@ The following tables provide an overview of the hardware specifications for AMD
- L0 Instruction Cache (KiB)
- VGPR File (KiB)
- SGPR File (KiB)
*
- Radeon PRO W7900 Dual Slot
- RDNA3
- gfx1100
- 48
- 96
- 32
- 128
- 96
- 6
- 256
- 32
- 16
- 32
- 384
- 20
*
- Radeon PRO W7900
- RDNA3

View File

@@ -53,7 +53,6 @@
* {doc}`ROCm Data Center Tool <rdc:index>`
* {doc}`ROCm SMI <rocm_smi_lib:index>`
* {doc}`ROCm Validation Suite <rocmvalidationsuite:index>`
* {doc}`TransferBench <transferbench:index>`
:::
::::

View File

@@ -8,7 +8,6 @@
| Version | Release date |
| ------- | ------------ |
| [6.1.2](https://rocm.docs.amd.com/en/docs-6.1.2/) | June 4, 2024 |
| [6.1.1](https://rocm.docs.amd.com/en/docs-6.1.1/) | May 8, 2024 |
| [6.1.0](https://rocm.docs.amd.com/en/docs-6.1.0/) | Apr 16, 2024 |
| [6.0.2](https://rocm.docs.amd.com/en/docs-6.0.2/) | Jan 31, 2024 |

View File

@@ -11,7 +11,7 @@ subtrees:
title: Release notes
subtrees:
- entries:
- file: about/changelog.md
- file: about/CHANGELOG.md
title: Changelog
- url: https://github.com/ROCm/ROCm/labels/Verified%20Issue
title: Known issues
@@ -58,8 +58,6 @@ subtrees:
- file: how-to/rocm-for-ai/train-a-model.rst
- file: how-to/rocm-for-ai/hugging-face-models.rst
- file: how-to/rocm-for-ai/deploy-your-model.rst
- file: how-to/rocm-for-hpc/index.rst
title: Using ROCm for HPC
- file: how-to/llm-fine-tuning-optimization/index.rst
title: Fine-tuning LLMs and inference optimization
subtrees:
@@ -81,16 +79,17 @@ subtrees:
- file: how-to/llm-fine-tuning-optimization/optimizing-triton-kernel.rst
title: Optimizing Triton kernels
- file: how-to/llm-fine-tuning-optimization/profiling-and-debugging.rst
- file: how-to/tuning-guides.md
- file: how-to/tuning-guides.rst
title: System optimization
subtrees:
- entries:
- file: how-to/tuning-guides/mi100.md
title: MI100
- file: how-to/tuning-guides/mi200.md
title: MI200
title: AMD Instinct MI200
- file: how-to/tuning-guides/mi100.md
title: AMD Instinct MI100
- file: how-to/tuning-guides/w6000-v620.md
title: RDNA2
title: AMD RDNA 2
- file: how-to/system-debugging.md
- file: how-to/gpu-enabled-mpi.rst
title: Using MPI
- file: conceptual/compiler-topics.md
@@ -105,8 +104,6 @@ subtrees:
title: OpenMP support
- file: how-to/setting-cus
title: Setting the number of CUs
- file: how-to/system-debugging.md
title: Debugging
- url: https://github.com/amd/rocm-examples
title: GitHub examples

View File

@@ -1,2 +1,2 @@
rocm-docs-core==1.4.0
sphinx-reredirects
rocm-docs-core==1.8.0
sphinx-reredirects

View File

@@ -6,9 +6,9 @@
#
accessible-pygments==0.0.5
# via pydata-sphinx-theme
alabaster==0.7.16
alabaster==1.0.0
# via sphinx
babel==2.15.0
babel==2.16.0
# via
# pydata-sphinx-theme
# sphinx
@@ -16,9 +16,9 @@ beautifulsoup4==4.12.3
# via pydata-sphinx-theme
breathe==4.35.0
# via rocm-docs-core
certifi==2024.2.2
certifi==2024.8.30
# via requests
cffi==1.16.0
cffi==1.17.1
# via
# cryptography
# pynacl
@@ -26,7 +26,7 @@ charset-normalizer==3.3.2
# via requests
click==8.1.7
# via sphinx-external-toc
cryptography==42.0.7
cryptography==43.0.1
# via pyjwt
deprecated==1.2.14
# via pygithub
@@ -36,13 +36,13 @@ docutils==0.21.2
# myst-parser
# pydata-sphinx-theme
# sphinx
fastjsonschema==2.19.1
fastjsonschema==2.20.0
# via rocm-docs-core
gitdb==4.0.11
# via gitpython
gitpython==3.1.43
# via rocm-docs-core
idna==3.7
idna==3.10
# via requests
imagesize==1.4.1
# via sphinx
@@ -56,34 +56,34 @@ markdown-it-py==3.0.0
# myst-parser
markupsafe==2.1.5
# via jinja2
mdit-py-plugins==0.4.1
mdit-py-plugins==0.4.2
# via myst-parser
mdurl==0.1.2
# via markdown-it-py
myst-parser==3.0.1
myst-parser==4.0.0
# via rocm-docs-core
packaging==24.0
packaging==24.1
# via
# pydata-sphinx-theme
# sphinx
pycparser==2.22
# via cffi
pydata-sphinx-theme==0.15.3
pydata-sphinx-theme==0.15.4
# via
# rocm-docs-core
# sphinx-book-theme
pygithub==2.3.0
pygithub==2.4.0
# via rocm-docs-core
pygments==2.18.0
# via
# accessible-pygments
# pydata-sphinx-theme
# sphinx
pyjwt[crypto]==2.8.0
pyjwt[crypto]==2.9.0
# via pygithub
pynacl==1.5.0
# via pygithub
pyyaml==6.0.1
pyyaml==6.0.2
# via
# myst-parser
# rocm-docs-core
@@ -92,15 +92,15 @@ requests==2.32.3
# via
# pygithub
# sphinx
rocm-docs-core==1.4.0
rocm-docs-core==1.8.0
# via -r requirements.in
smmap==5.0.1
# via gitdb
snowballstemmer==2.2.0
# via sphinx
soupsieve==2.5
soupsieve==2.6
# via beautifulsoup4
sphinx==7.3.7
sphinx==8.0.2
# via
# breathe
# myst-parser
@@ -112,37 +112,37 @@ sphinx==7.3.7
# sphinx-external-toc
# sphinx-notfound-page
# sphinx-reredirects
sphinx-book-theme==1.1.2
sphinx-book-theme==1.1.3
# via rocm-docs-core
sphinx-copybutton==0.5.2
# via rocm-docs-core
sphinx-design==0.6.0
sphinx-design==0.6.1
# via rocm-docs-core
sphinx-external-toc==1.0.1
# via rocm-docs-core
sphinx-notfound-page==1.0.2
sphinx-notfound-page==1.0.4
# via rocm-docs-core
sphinx-reredirects==0.1.4
sphinx-reredirects==0.1.5
# via -r requirements.in
sphinxcontrib-applehelp==1.0.8
sphinxcontrib-applehelp==2.0.0
# via sphinx
sphinxcontrib-devhelp==1.0.6
sphinxcontrib-devhelp==2.0.0
# via sphinx
sphinxcontrib-htmlhelp==2.0.5
sphinxcontrib-htmlhelp==2.1.0
# via sphinx
sphinxcontrib-jsmath==1.0.1
# via sphinx
sphinxcontrib-qthelp==1.0.7
sphinxcontrib-qthelp==2.0.0
# via sphinx
sphinxcontrib-serializinghtml==1.1.10
sphinxcontrib-serializinghtml==2.0.0
# via sphinx
tomli==2.0.1
# via sphinx
typing-extensions==4.12.0
typing-extensions==4.12.2
# via
# pydata-sphinx-theme
# pygithub
urllib3==2.2.2
urllib3==2.2.3
# via
# pygithub
# requests

View File

@@ -100,7 +100,7 @@ Tools
":doc:`AMD SMI <amdsmi:index>`", "C library for Linux that provides a user space interface for applications to monitor and control AMD devices"
":doc:`HIPIFY <hipify:index>`", "Translates CUDA source code into portable HIP C++"
":doc:`ROCdbgapi <rocdbgapi:index>`", "ROCm debugger API library"
":doc:`ROCmCC <./reference/rocmcc>`", "Clang/LLVM-based compiler"
":doc:`ROCm compilers <./reference/rocmcc>`", "Clang/LLVM-based compiler"
":doc:`rocminfo <rocminfo:index>`", "Reports system information"
":doc:`ROCProfiler <rocprofiler:index>`", "Profiling tool for HIP applications"
":doc:`ROCTracer <roctracer:index>`", "Intercepts runtime API calls and traces asynchronous activity"
@@ -111,7 +111,6 @@ Tools
":doc:`ROCm SMI <rocm_smi_lib:index>`", "C library for Linux that provides a user space interface for applications to monitor and control GPU applications"
":doc:`ROCm Validation Suite <rocmvalidationsuite:index>`", "Detects and troubleshoots common problems affecting AMD GPUs running in a high-performance computing environment"
":doc:`ROCr Debug Agent <rocr_debug_agent:index>`", "Prints the state of all AMD GPU wavefronts that caused a queue error by sending a SIGQUIT signal to the process while the program is running"
":doc:`TransferBench <transferbench:index>`", "Utility to benchmark simultaneous transfers between user-specified devices (CPUs/GPUs)"
Compilers
-----------------------------------------------
@@ -120,7 +119,7 @@ Compilers
:header: "Component", "Description"
"`FLANG <https://github.com/ROCm/flang/>`_", "An out-of-tree Fortran compiler targeting LLVM"
":doc:`hipCC <hipcc:index>`", "Compiler driver utility that calls Clang or NVCC and passes the appropriate include and library options for the target compiler and HIP infrastructure"
"`hipCC <https://github.com/ROCm/HIPCC>`_ ", "Compiler driver utility that calls Clang or NVCC and passes the appropriate include and library options for the target compiler and HIP infrastructure"
"`LLVM (amdclang) <https://github.com/ROCm/llvm-project>`_ ", "Toolkit for the construction of highly optimized compilers, optimizers, and runtime environments"
Runtimes
@@ -129,6 +128,6 @@ Runtimes
.. csv-table::
:header: "Component", "Description"
"`AMD Common Language Runtime (CLR) <https://github.com/ROCm/clr>`_", "Contains source code for AMD's common language runtimes: :doc:`HIP <hip:index>` and OpenCL"
":doc:`AMD Common Language Runtime (CLR) <hip:understand/amd_clr>`", "Contains source code for AMD's common language runtimes: HIP and OpenCL"
":doc:`HIP <hip:index>`", "AMD's GPU programming language extension and the GPU runtime"
":doc:`ROCR-Runtime <rocr-runtime:index>`", "User-mode API interfaces and libraries necessary for host applications to launch compute kernels on available HSA ROCm kernel agents"

View File

@@ -16,7 +16,7 @@
<!-- spellcheck-disable -->
This page contains the release notes for AMD ROCm Software.
This page contains the release notes for AMD ROCm Software.
{%- for version, release in releases %}

View File

@@ -17,6 +17,7 @@ AMD SMI for ROCm 6.1.1
#### Changes
* Updated the output of `amd-smi metric --ecc-blocks` to show counters available from blocks.
* Updated the output of `amd-smi metric --clock` to reflect each engine.
* Updated the output of `amd-smi topology --json` to align with output reported by host and guest systems.
@@ -27,6 +28,10 @@ AMD SMI for ROCm 6.1.1
* Fixed `amd-smi metric --pcie` and `amdsmi_get_pcie_info()` when using RDNA3 (Navi 32 and Navi 31) hardware to prevent "UNKNOWN" reports.
* Fixed the output results of `amd-smi process` when getting processes running on a device.
#### Removals
* Removed the `amdsmi_get_gpu_process_info` API from the Python library. It was removed from the C library in an earlier release.
#### Known issues
* `amd-smi bad-pages` can result in a `ValueError: Null pointer access` error when using certain PMU firmware versions.
@@ -43,7 +48,7 @@ HIPCC for ROCm 6.1.1
* **Upcoming:** a future release will enable use of compiled binaries `hipcc.bin` and `hipconfig.bin` by default. No action is needed by users; you may continue calling high-level Perl scripts `hipcc` and `hipconfig`. `hipcc.bin` and `hipconfig.bin` will be invoked by the high-level Perl scripts. To revert to the previous behavior and invoke `hipcc.pl` and `hipconfig.pl`, set the `HIP_USE_PERL_SCRIPTS` environment variable to `1`.
* **Upcoming:** a subsequent release will remove high-level Perl scripts `hipcc` and `hipconfig`. This release will remove the `HIP_USE_PERL_SCRIPTS` environment variable. It will rename `hipcc.bin` and `hipconfig.bin` to `hipcc` and `hipconfig` respectively. No action is needed by the users. To revert to the previous behavior, invoke `hipcc.pl` and `hipconfig.pl` explicitly.
* **Upcoming:** a subsequent release will remove `hipcc.pl` and `hipconfig.pl`.
* **Upcoming:** a subsequent will remove `hipcc.pl` and `hipconfig.pl`.
### ROCm SMI

View File

@@ -1,66 +0,0 @@
ROCm 6.1.2 includes enhancements to SMI tools and improvements to some libraries.
### OS support
ROCm 6.1.2 has been tested against a pre-release version of Ubuntu 22.04.5 (kernel: 5.15 [GA], 6.8 [HWE]).
### AMD SMI
AMD SMI for ROCm 6.1.2
#### Additions
* Added process isolation and clean shader APIs and CLI commands.
* `amdsmi_get_gpu_process_isolation()`
* `amdsmi_set_gpu_process_isolation()`
* `amdsmi_set_gpu_clear_sram_data()`
* Added the `MIN_POWER` metric to output provided by `amd-smi static --limit`.
#### Optimizations
* Updated the `amd-smi monitor --pcie` output to prevent delays with the `monitor` command.
#### Changes
* Updated `amismi_get_power_cap_info` to return values in uW instead of W.
* Updated Python library return types for `amdsmi_get_gpu_memory_reserved_pages` and `amdsmi_get_gpu_bad_page_info`.
* Updated the output of `amd-smi metric --ecc-blocks` to show counters available from blocks.
#### Fixes
* `amdsmi_get_gpu_board_info()` no longer returns junk character strings.
* `amd-smi metric --power` now correctly details power output for RDNA3, RDNA2, and MI1x devices.
* Fixed the `amdsmitstReadWrite.TestPowerCapReadWrite` test for RDNA3, RDNA2, and MI100 devices.
* Fixed an issue with the `amdsmi_get_gpu_memory_reserved_pages` and `amdsmi_get_gpu_bad_page_info` Python interface calls.
#### Removals
* Removed the `amdsmi_get_gpu_process_info` API from the Python library. It was removed from the C library in an earlier release.
```{note}
See the AMD SMI [detailed changelog](https://github.com/ROCm/amdsmi/blob/rocm-6.1.x/CHANGELOG.md) with code samples for more information.
```
### HIPCC
HIPCC for ROCm 6.1.2
#### Changes
* **Upcoming:** a future release will enable use of compiled binaries `hipcc.bin` and `hipconfig.bin` by default. No action is needed by users; you may continue calling high-level Perl scripts `hipcc` and `hipconfig`. `hipcc.bin` and `hipconfig.bin` will be invoked by the high-level Perl scripts. To revert to the previous behavior and invoke `hipcc.pl` and `hipconfig.pl`, set the `HIP_USE_PERL_SCRIPTS` environment variable to `1`.
* **Upcoming:** a subsequent release will remove high-level Perl scripts `hipcc` and `hipconfig`. This release will remove the `HIP_USE_PERL_SCRIPTS` environment variable. It will rename `hipcc.bin` and `hipconfig.bin` to `hipcc` and `hipconfig` respectively. No action is needed by the users. To revert to the previous behavior, invoke `hipcc.pl` and `hipconfig.pl` explicitly.
* **Upcoming:** a subsequent release will remove `hipcc.pl` and `hipconfig.pl`.
### ROCm SMI
ROCm SMI for ROCm 6.1.2
#### Additions
* Added the ring hang event to the `amdsmi_evt_notification_type_t` enum.
#### Fixes
* Fixed an issue causing ROCm SMI to incorrectly report GPU utilization for RDNA3 GPUs. See the issue on [GitHub](https://github.com/ROCm/ROCm/issues/3112).
* Fixed the parsing of `pp_od_clk_voltage` in `get_od_clk_volt_info` to work better with MI-series hardware.

View File

@@ -1,37 +0,0 @@
# Overview for ROCm.mk
This Makefile builds the various projects that makes up ROCm in the correct order.
It is expected to be run in an environment with the tooling set up. An easy way
to do this is to use Docker.
## Targets
* all (default)
* rocm-dev (a subset of all)
* clean
* list_components
* help
* T_foo
* C_foo
## Makefile Variables
* PEVAL set to 1 to enable some Makefile debugging code.
* RELEASE\_FLAG set to "" to avoid passing "-r" to builds, effect is package defined.
* NOBUILD="foo bar" to avoid adding foo and bar into the dependencies of top level targets. They still may be
built if they are needed as dependencies of other top level targets.
* toplevel
## Makefile assumptions
### Requirements for package "foo"
#### program build\_foo.sh
* Should take option "-c" to clean
* Should take option "-r" to do a normal "RelWithDeb" build
### For package "foo" we define some targets
* T\_foo - The main build target, calls "build\_foo.sh -r"
* C\_foo - Clean target, calls "build_foo.sh -c"

View File

@@ -1,248 +0,0 @@
# Traditional first make target
all:
# Use bash as a shell
# On Ubuntu sh is 'dash'
SHELL:=bash
# Allow RELEASE_FLAG to be overwritten
RELEASE_FLAG?=-r
# Set SANITIZER_FLAG for sanitizer
ASAN_DEP:=
ifeq (${ENABLE_ADDRESS_SANITIZER},true)
ASAN_DEP=lightning
SANITIZER_FLAG=-a
endif
export INFRA_REPO:=ROCm/tools/rocm-build
OUT_DIR:=$(shell . ${INFRA_REPO}/envsetup.sh >/dev/null 2>&1 ; echo $${OUT_DIR})
ROCM_INSTALL_PATH:=$(shell . ${INFRA_REPO}/envsetup.sh >/dev/null 2>&1 ; echo $${ROCM_INSTALL_PATH})
$(info OUT_DIR=${OUT_DIR})
$(info ROCM_INSTALL_PATH=${ROCM_INSTALL_PATH})
# -------------------------------------------------------------------------
# Internal stuff. Could be put in a different file to hide it.
# Internal macros, they need to be defined before being used.
# The internal "eval" allows parts of the Makefile to be generated.
# Whilst it is possible to dump the effective Makefile, it can be
# hard to see where parts come from. Set up the "peval" macro which
# optionally prints out the generated makefile snippet and evaluate it.
# Use "make PEVAL=1 all" to see the things being evaluated.
ifeq (,${PEVAL})
define peval =
$(eval $1)
endef
else
define peval =
$(eval $(info $1)$1)
endef
endif
# macro to add dependencies. Saves having to put all the OUT_DIR/logs in
# The outer strip is to work around a gnu make 4.1 and earlier bug
# It should not be needed.
define adddep =
$(strip $(call peval,components+= $(1) $(2))
$(foreach comp,$(strip $2),$(call peval,${OUT_DIR}/logs/${1}: ${OUT_DIR}/logs/${comp}))
)
endef
# End of internal stuff that is needed at the start of the file
# -------------------------------------------------------------------------
# Dependencies. These can be updated. Anything that is mentioned in
# either the args to the adddep macro will be added to components. as
# an example there is no need for the adddep of lightning, as it
# depends on nothing and at least one other component includes it.
# Syntax. Up to the first comma everything is fixed. The "call" is a
# keyword to gnu make. The "adddep" is the name of the variable containing
# the macro.
# The second comma delimited argument is the target.
# The third comma delimited arg is the thing that the target depends on.
# It is a space seperated list with zero or more elements.
$(call adddep,amd_smi_lib,${ASAN_DEP})
$(call adddep,aqlprofile,${ASAN_DEP} hsa)
$(call adddep,clang-ocl,lightning rocm-cmake)
$(call adddep,comgr,lightning devicelibs)
$(call adddep,dbgapi,hsa comgr)
$(call adddep,devicelibs,lightning)
$(call adddep,hip_on_rocclr,${ASAN_DEP} rocclr rocprofiler-register)
$(call adddep,hipcc,)
$(call adddep,hipify_clang,hip_on_rocclr lightning)
$(call adddep,hsa,${ASAN_DEP} thunk lightning devicelibs rocprofiler-register)
$(call adddep,lightning,)
$(call adddep,opencl_on_rocclr,${ASAN_DEP} rocclr)
$(call adddep,openmp_extras,thunk lightning devicelibs hsa)
$(call adddep,rdc,${ASAN_DEP} rocm_smi_lib hsa rocprofiler)
$(call adddep,rocclr,${ASAN_DEP} hsa comgr hipcc rocprofiler-register)
$(call adddep,rocm_bandwidth_test,${ASAN_DEP} hsa)
$(call adddep,rocm_smi_lib,${ASAN_DEP})
$(call adddep,rocm-cmake,${ASAN_DEP})
$(call adddep,rocm-core,${ASAN_DEP})
$(call adddep,rocm-gdb,dbgapi)
$(call adddep,rocminfo,${ASAN_DEP} hsa)
$(call adddep,rocprofiler-register,${ASAN_DEP})
$(call adddep,rocprofiler,${ASAN_DEP} hsa roctracer aqlprofile opencl_on_rocclr hip_on_rocclr comgr dbgapi rocm_smi_lib)
$(call adddep,rocr_debug_agent,${ASAN_DEP} hip_on_rocclr hsa dbgapi)
$(call adddep,roctracer,${ASAN_DEP} hsa hip_on_rocclr)
$(call adddep,thunk,${ASAN_DEP})
# rocm-dev points to all possible last finish components of Stage1 build.
rocm-dev-components :=rdc hipify_clang openmp_extras \
rocm-core amd_smi_lib hipcc clang-ocl \
rocm_bandwidth_test rocr_debug_agent rocm-gdb
$(call adddep,rocm-dev,$(filter-out ${NOBUILD},${rocm-dev-components}))
$(call adddep,amdmigraphx,hip_on_rocclr half rocblas miopen-hip lightning hipcc)
$(call adddep,composable_kernel,lightning hipcc hip_on_rocclr rocm-cmake)
$(call adddep,half,rocm-cmake)
$(call adddep,hipblas,hip_on_rocclr rocblas rocsolver lightning hipcc)
$(call adddep,hipblaslt,hip_on_rocclr openmp_extras hipblas lightning hipcc)
$(call adddep,hipcub,hip_on_rocclr rocprim lightning hipcc)
$(call adddep,hipfft,hip_on_rocclr openmp_extras rocfft rocrand hiprand lightning hipcc)
$(call adddep,hipfort,rocblas hipblas rocsparse hipsparse rocfft hipfft rocrand hiprand rocsolver hipsolver lightning hipcc)
$(call adddep,hiprand,hip_on_rocclr rocrand lightning hipcc)
$(call adddep,hipsolver,hip_on_rocclr rocblas rocsolver rocsparse lightning hipcc hipsparse)
$(call adddep,hipsparse,hip_on_rocclr rocsparse lightning hipcc)
$(call adddep,hipsparselt,hip_on_rocclr hipsparse lightning hipcc openmp_extras)
$(call adddep,hiptensor,hip_on_rocclr composable_kernel lightning hipcc)
$(call adddep,miopen-deps,lightning hipcc)
$(call adddep,miopen-hip,composable_kernel half hip_on_rocclr miopen-deps rocblas roctracer lightning hipcc)
$(call adddep,mivisionx,amdmigraphx miopen-hip rpp lightning hipcc)
$(call adddep,rccl,hip_on_rocclr hsa lightning hipcc rocm_smi_lib hipify_clang)
$(call adddep,rocalution,rocblas rocsparse rocrand lightning hipcc)
$(call adddep,rocblas,hip_on_rocclr openmp_extras lightning hipcc)
$(call adddep,rocdecode,hip_on_rocclr lightning hipcc)
$(call adddep,rocfft,hip_on_rocclr rocrand hiprand lightning hipcc openmp_extras)
$(call adddep,rocmvalidationsuite,hip_on_rocclr hsa rocblas rocm-core lightning hipcc rocm_smi_lib)
$(call adddep,rocprim,hip_on_rocclr lightning hipcc)
$(call adddep,rocrand,hip_on_rocclr lightning hipcc)
$(call adddep,rocsolver,hip_on_rocclr rocblas rocsparse lightning hipcc)
$(call adddep,rocsparse,hip_on_rocclr rocprim lightning hipcc)
$(call adddep,rocthrust,hip_on_rocclr rocprim lightning hipcc)
$(call adddep,rocwmma,hip_on_rocclr rocblas lightning hipcc rocm-cmake rocm_smi_lib)
$(call adddep,rpp,half lightning hipcc openmp_extras)
# -------------------------------------------------------------------------
# The rest of the file is internal
# Do not pass jobserver params if -n build
ifneq (,$(findstring n,${MAKEFLAGS}))
RMAKE:=
else
RMAKE := +
endif
# disable the builtin rules
.SUFFIXES:
# Linear
# include moredeps
# A macro to define a toplevel target, add it to the 'all' target
# Make it depend on the generated log. Generate the log of the build.
# See if the macro is already defined, if so don't touch it.
# As GNU make allows more than one makefile to be specified with "-f"
# one could put an alternative definition of "toplevel" in a different
# file or even the environment, and use the data in this file for other
# purposes. Uses might include generating output in "dot" format for
# showing the dependency graph, or having a wrapper script to run programs
# to generate code quality tools.
ifeq (${toplevel},)
# { Start of test to see if toplevel is defined
define toplevel =
# The "target" make, this builds the package if it is out of date
T_$1: ${OUT_DIR}/logs/$1 FRC
: $1 built
# The "upload" for $1, it uploads the packages for $1 to the central storage
U_$1: T_$1 FRC
source $${INFRA_REPO}/envsetup.sh && $${INFRA_REPO}/upload_packages.sh "$1"
: $1 uploaded
# The "clean" for $1, it just marks the target as not existing so it will be built
# in the future.
C_$1: FRC
rm -f ${OUT_DIR}/logs/$1 ${OUT_DIR}/logs/$1.repackaged
# parallel build {
${OUT_DIR}/logs/$1: | ${OUT_DIR}/logs
ifneq ($(wildcard ${OUT_DIR}/logs/$1.repackaged),)
@echo Skipping build of $1 as it has already been repackaged
cat $$@.repackaged > $$@
rm -f $$@.repackaged
else # } {
@echo $1 started due to $$? | sed "s:${OUT_DIR}/logs/::g"
# Build in a subshell so we get the time output
# Pass in jobserver info using the RMAKE variable
${RMAKE}@( if set -x && source $${INFRA_REPO}/envsetup.sh && \
rm -f $$@.errors $$@ $$@.repackaged && \
$${INFRA_REPO}/build_$1.sh -c && source $${INFRA_REPO}/ccache-env-mathlib.sh && \
time bash -x $${INFRA_REPO}/build_$1.sh $${RELEASE_FLAG} $${SANITIZER_FLAG} && $${INFRA_REPO}/post_inst_pkg.sh "$1" ; \
then mv $$@.inprogress $$@ ; \
else mv $$@.inprogress $$@.errors ; echo Error in $1 >&2 ; exit 1 ;\
fi ) > $$@.inprogress 2>&1
endif # }
# end of toplevel macro
endef
# } End of test to see if toplevel is defined
endif
components:=$(sort $(components))
# Create all the T_xxxx and C_xxxx targets
$(call peval,$(foreach dep,$(strip ${components}),$(call toplevel,${dep})))
# Add all the T_xxxx targets to "all" except those listed in NOBUILD
# Note this does not prohibit them from being built, it just means that
# a build of "all" will not force them to be built directly
# example command
# make -f jenkins-utils/scripts/Stage1.mk -j60
##help all: Build everything
all: $(addprefix T_,$(filter-out ${NOBUILD},${components}))
@echo All ROCm components built
# Do not document this target
upload: $(addprefix U_,${components})
@echo All ROCm components built and uploaded
##help rocm-dev: Build a subset of ROCm
rocm-dev: T_rocm-dev
@echo rocm-dev built
${OUT_DIR}/logs:
sudo mkdir -p -m 775 "${ROCM_INSTALL_PATH}" && \
sudo chown -R "$(shell id -u):$(shell id -g)" "${ROCM_INSTALL_PATH}"
sudo chown -R "$(shell id -u):$(shell id -g)" "/home/$(shell id -un)"
mkdir -p "${@}"
mkdir -p ${HOME}/.ccache
##help clean: remove the output directory and recreate it
clean:
[ -n "${OUT_DIR}" ] && rm -rf "${OUT_DIR}"
mkdir -p ${OUT_DIR}/logs
.SECONDARY: ${components:%=${OUT_DIR}/logs/%}
.PHONY: all clean repack help list_components
##help list_components: output the list of components
##help : Hint make list_components | paste - - - | column -t
list_components:
@echo "${components}" | sed 'y/ /\n/'
##help help: show this text
help:
@sed -n 's/^##help //p' ${MAKEFILE_LIST} | \
if type -t column > /dev/null ; then column -s: -t ; else cat ; fi
FRC:

View File

@@ -1,145 +0,0 @@
#!/bin/bash
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
printUsage() {
echo
echo "Usage: $(basename "${BASH_SOURCE}") [-c|-r|-h] [makeopts]"
echo
echo "Options:"
echo " -c, --clean Removes all amd_smi build artifacts"
echo " -r, --release Build non-debug version amd_smi (default is debug)"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of type referred to by pkg_type"
echo " -p, --package <type> Specify packaging format"
echo " -h, --help Prints this help"
echo "Possible values for <type>:"
echo " deb -> Debian format (default)"
echo " rpm -> RPM format"
echo
return 0
}
PACKAGE_ROOT="$(getPackageRoot)"
TARGET="build"
PACKAGE_LIB=$(getLibPath)
PACKAGE_INCLUDE="$(getIncludePath)"
AMDSMI_BUILD_DIR=$(getBuildPath amdsmi)
AMDSMI_PACKAGE_DEB_DIR="$(getPackageRoot)/deb/amdsmi"
AMDSMI_PACKAGE_RPM_DIR="$(getPackageRoot)/rpm/amdsmi"
AMDSMI_BUILD_TYPE="debug"
BUILD_TYPE="Debug"
MAKETARGET="deb"
MAKEARG="$DASH_JAY O=$AMDSMI_BUILD_DIR"
AMDSMI_MAKE_OPTS="$DASH_JAY O=$AMDSMI_BUILD_DIR -C $AMDSMI_BUILD_DIR"
AMDSMI_PKG_NAME="amd-smi-lib"
SHARED_LIBS="ON"
CLEAN_OR_OUT=0;
PKGTYPE="deb"
VALID_STR=`getopt -o hcraso:p: --long help,clean,release,static,address_sanitizer,outdir:,package: -- "$@"`
eval set -- "$VALID_STR"
while true ;
do
case "$1" in
(-h | --help)
printUsage ; exit 0;;
(-c | --clean)
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
(-r | --release)
BUILD_TYPE="RelWithDebInfo" ; shift ;;
(-a | --address_sanitizer)
set_asan_env_vars
set_address_sanitizer_on
# TODO - support standard option of passing cmake environment vars - CFLAGS,CXXFLAGS etc., to enable address sanitizer
ADDRESS_SANITIZER=true ; shift ;;
(-s | --static)
SHARED_LIBS="OFF" ; shift ;;
(-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
(-p | --package)
MAKETARGET="$2" ; shift 2;;
--) shift; break;; # end delimiter
(*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
esac
done
RET_CONFLICT=1
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
if [ $RET_CONFLICT -ge 30 ]; then
print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
exit $RET_CONFLICT
fi
clean_amdsmi() {
rm -rf "$AMDSMI_BUILD_DIR"
rm -rf "$AMDSMI_PACKAGE_DEB_DIR"
rm -rf "$AMDSMI_PACKAGE_RPM_DIR"
rm -rf "$PACKAGE_ROOT/amd_smi"
rm -rf "$PACKAGE_INCLUDE/amd_smi"
rm -f $PACKAGE_LIB/libamd_smi.*
return 0
}
build_amdsmi() {
echo "Building AMDSMI"
echo "AMDSMI_BUILD_DIR: ${AMDSMI_BUILD_DIR}"
if [ ! -d "$AMDSMI_BUILD_DIR" ]; then
mkdir -p $AMDSMI_BUILD_DIR
pushd $AMDSMI_BUILD_DIR
print_lib_type $SHARED_LIBS
cmake \
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
$(rocm_common_cmake_params) \
$(rocm_cmake_params) \
-DENABLE_LDCONFIG=OFF \
-DAMD_SMI_PACKAGE="${AMDSMI_PKG_NAME}" \
-DCPACK_PACKAGE_VERSION_MAJOR="1" \
-DCPACK_PACKAGE_VERSION_MINOR="$ROCM_LIBPATCH_VERSION" \
-DCPACK_PACKAGE_VERSION_PATCH="0" \
-DADDRESS_SANITIZER="$ADDRESS_SANITIZER" \
-DBUILD_TESTS=ON \
"$AMD_SMI_LIB_ROOT"
popd
fi
echo "Making amd_smi package:"
cmake --build "$AMDSMI_BUILD_DIR" -- $AMDSMI_MAKE_OPTS
cmake --build "$AMDSMI_BUILD_DIR" -- $AMDSMI_MAKE_OPTS install
cmake --build "$AMDSMI_BUILD_DIR" -- $AMDSMI_MAKE_OPTS package
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$AMDSMI_PACKAGE_DEB_DIR" $AMDSMI_BUILD_DIR/*.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$AMDSMI_PACKAGE_RPM_DIR" $AMDSMI_BUILD_DIR/*.rpm
}
print_output_directory() {
case ${PKGTYPE} in
("deb")
echo ${AMDSMI_PACKAGE_DEB_DIR};;
("rpm")
echo ${AMDSMI_PACKAGE_RPM_DIR};;
(*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
esac
exit
}
verifyEnvSetup
case $TARGET in
(clean) clean_amdsmi ;;
(build) build_amdsmi ;;
(outdir) print_output_directory ;;
(*) die "Invalid target $TARGET" ;;
esac
echo "Operation complete"
exit 0

View File

@@ -1,54 +0,0 @@
#!/bin/bash
set -ex
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
set_component_src AMDMIGraphX
build_amdmigraphx() {
echo "Start build"
cd $COMPONENT_SRC
pip3 install https://github.com/RadeonOpenCompute/rbuild/archive/master.tar.gz
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
set_asan_env_vars
set_address_sanitizer_on
fi
if [ -n "$GPU_ARCHS" ]; then
GPU_TARGETS="$GPU_ARCHS"
else
GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
fi
mkdir -p ${BUILD_DIR} && rm -rf ${BUILD_DIR}/* && mkdir -p ${HOME}/amdmigraphx && rm -rf ${HOME}/amdmigraphx/*
rbuild package -d "${HOME}/amdmigraphx" -B "${BUILD_DIR}" \
--cxx="${ROCM_PATH}/llvm/bin/clang++" \
--cc="${ROCM_PATH}/llvm/bin/clang" \
$(rocm_common_cmake_params) \
-DCMAKE_MODULE_LINKER_FLAGS="-Wl,--enable-new-dtags -Wl,--rpath,$ROCM_LIB_RPATH" \
-DGPU_TARGETS="${GPU_TARGETS}" \
-DCMAKE_INSTALL_RPATH=""
mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
cd $BUILD_DIR && cmake --build . -- install -j${PROC}
show_build_cache_stats
}
clean_amdmigraphx() {
echo "Cleaning AMDMIGraphX build directory: ${BUILD_DIR} ${DEPS_DIR} ${PACKAGE_DIR}"
rm -rf "$BUILD_DIR" "$DEPS_DIR" "$PACKAGE_DIR"
echo "Done!"
}
stage2_command_args "$@"
case $TARGET in
build) build_amdmigraphx ;;
outdir) print_output_directory ;;
clean) clean_amdmigraphx ;;
*) die "Invalid target $TARGET" ;;
esac

View File

@@ -1,150 +0,0 @@
#!/bin/bash
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
printUsage() {
echo
echo "Usage: ${BASH_SOURCE##*/} [options ...]"
echo
echo "Options:"
echo " -c, --clean Clean output and delete all intermediate work"
echo " -p, --package <type> Specify packaging format"
echo " -r, --release Make a release build instead of a debug build"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
echo " -h, --help Prints this help"
echo
echo "Possible values for <type>:"
echo " deb -> Debian format (default)"
echo " rpm -> RPM format"
echo
return 0
}
API_NAME="hsa-amd-aqlprofile"
PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
PROJ_NAME="$API_NAME"
TARGET="build"
BUILD_TYPE="Debug"
MAKETARGET="deb"
MAKE_OPTS="$DASH_JAY -C $BUILD_DIR"
SHARED_LIBS="ON"
CLEAN_OR_OUT=0
MAKETARGET="deb"
PKGTYPE="deb"
VALID_STR=$(getopt -o hcro:p: --long help,clean,release,clean,outdir:,package: -- "$@")
eval set -- "$VALID_STR"
while true; do
case "$1" in
-h | --help)
printUsage
exit 0
;;
-c | --clean)
TARGET="clean"
((CLEAN_OR_OUT |= 1))
shift
;;
-r | --release)
BUILD_TYPE="Release"
shift
;;
-o | --outdir)
TARGET="outdir"
PKGTYPE=$2
OUT_DIR_SPECIFIED=1
((CLEAN_OR_OUT |= 2))
shift 2
;;
--)
shift
break
;;
*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] " >&2
exit 20
;;
esac
done
copy_pkg_files_to_rocm() {
local comp_folder=$1
local comp_pkg_name=$2
cd "${OUT_DIR}/${PKGTYPE}/${comp_folder}"|| exit 2
if [ "${PKGTYPE}" = 'deb' ]; then
dpkg-deb -x ${comp_pkg_name}_*.deb pkg/
else
mkdir pkg && pushd pkg/ || exit 2
if [[ "${comp_pkg_name}" != *-dev* ]]; then
rpm2cpio ../${comp_pkg_name}-*.rpm | cpio -idmv
else
rpm2cpio ../${comp_pkg_name}el-*.rpm | cpio -idmv
fi
popd || exit 2
fi
ls ./pkg -alt
sudo cp -r ./pkg/*/rocm*/* "${ROCM_PATH}" || exit 2
rm -rf pkg/
}
clean() {
echo "Cleaning $PROJ_NAME package"
rm -rf "$PACKAGE_DEB"
}
build() {
echo "Downloading $PROJ_NAME" package
if [ "$DISTRO_NAME" = ubuntu ]; then
mkdir -p "$PACKAGE_DEB"
local rocm_ver=${ROCM_VERSION}
if [ ${ROCM_VERSION##*.} = 0 ]; then
rocm_ver=${ROCM_VERSION%.*}
fi
local url="https://repo.radeon.com/rocm/apt/${rocm_ver}/pool/main/h/${API_NAME}/"
local package
package=$(curl -s "$url" | grep -Po 'href="\K[^"]*' | grep "${DISTRO_RELEASE}" | head -n 1)
if [ -z "$package" ]; then
echo "No package found for Ubuntu version $DISTRO_RELEASE"
exit 1
fi
wget -t3 -P "$PACKAGE_DEB" "${url}${package}"
copy_pkg_files_to_rocm ${API_NAME} ${API_NAME}
else
echo "$DISTRO_ID is not supported..."
exit 2
fi
echo "Installing $PROJ_NAME" package
}
print_output_directory() {
case ${PKGTYPE} in
"deb")
echo ${PACKAGE_DEB}
;;
"rpm")
echo ${PACKAGE_RPM}
;;
*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2
exit 1
;;
esac
exit
}
case "$TARGET" in
clean) clean ;;
build) build ;;
outdir) print_output_directory ;;
*) die "Invalid target $TARGET" ;;
esac
echo "Operation complete"

View File

@@ -1,136 +0,0 @@
#!/bin/bash
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
printUsage() {
echo
echo "Usage: $(basename "${BASH_SOURCE}") [-c|-r|-h] [makeopts]"
echo
echo "Options:"
echo " -c, --clean Removes all clang-ocl build artifacts"
echo " -r, --release Build non-debug version clang-ocl (default is debug)"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
echo " -h, --help Prints this help"
echo " -s, --static Supports static CI by accepting this param & not bailing out. No effect of the param though"
echo
return 0
}
TARGET="build"
CLANG_OCL_DEST="$(getBinPath)"
CLANG_OCL_SRC_ROOT="$CLANG_OCL_ROOT"
CLANG_OCL_BUILD_DIR="$(getBuildPath clang-ocl)"
MAKEARG="$DASH_JAY"
PACKAGE_ROOT="$(getPackageRoot)"
PACKAGE_UTILS="$(getUtilsPath)"
CLANG_OCL_PACKAGE_DEB="$PACKAGE_ROOT/deb/clang-ocl"
CLANG_OCL_PACKAGE_RPM="$PACKAGE_ROOT/rpm/clang-ocl"
BUILD_TYPE="Debug"
SHARED_LIBS="ON"
CLEAN_OR_OUT=0;
MAKETARGET="deb"
PKGTYPE="deb"
VALID_STR=`getopt -o hcraso:g: --long help,clean,release,clean,static,address_sanitizer,outdir:,gpu_list: -- "$@"`
eval set -- "$VALID_STR"
while true ;
do
case "$1" in
(-h | --help)
printUsage ; exit 0;;
(-c | --clean)
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
(-r | --release)
MAKEARG="$MAKEARG BUILD_TYPE=rel" ; BUILD_TYPE="Release" ; shift ;;
(-a | --address_sanitizer)
set_asan_env_vars
set_address_sanitizer_on ; shift ;;
(-s | --static)
SHARED_LIBS="OFF" ; shift ;;
(-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
(-g | --gpu_list )
GPU_LIST=$2; shift 2 ;;
--) shift; break;;
(*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
esac
done
RET_CONFLICT=1
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
if [ $RET_CONFLICT -ge 30 ]; then
print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
exit $RET_CONFLICT
fi
clean_clang-ocl() {
echo "Removing clang-ocl"
rm -rf $CLANG_OCL_DEST/clang-ocl
rm -rf $CLANG_OCL_BUILD_DIR
rm -rf $CLANG_OCL_PACKAGE_DEB
rm -rf $CLANG_OCL_PACKAGE_RPM
}
build_clang-ocl() {
if [ ! -d "$CLANG_OCL_BUILD_DIR" ]; then
mkdir -p $CLANG_OCL_BUILD_DIR
pushd $CLANG_OCL_BUILD_DIR
if [ -e $PACKAGE_ROOT/lib/bitcode/opencl.amdgcn.bc ]; then
BC_DIR="$ROCM_INSTALL_PATH/lib"
else
BC_DIR="$ROCM_INSTALL_PATH/amdgcn/bitcode"
fi
cmake \
$(rocm_cmake_params) \
-DDISABLE_CHECKS="ON" \
-DCLANG_BIN="$ROCM_INSTALL_PATH/llvm/bin" \
-DBITCODE_DIR="$BC_DIR" \
$(rocm_common_cmake_params) \
-DCPACK_SET_DESTDIR="OFF" \
$CLANG_OCL_SRC_ROOT
echo "Making clang-ocl:"
cmake --build . -- $MAKEARG
cmake --build . -- $MAKEARG install
cmake --build . -- $MAKEARG package
popd
fi
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$CLANG_OCL_PACKAGE_DEB" $CLANG_OCL_BUILD_DIR/rocm-clang-ocl*.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$CLANG_OCL_PACKAGE_RPM" $CLANG_OCL_BUILD_DIR/rocm-clang-ocl*.rpm
}
print_output_directory() {
case ${PKGTYPE} in
("deb")
echo ${CLANG_OCL_PACKAGE_DEB};;
("rpm")
echo ${CLANG_OCL_PACKAGE_RPM};;
(*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
esac
exit
}
case $TARGET in
(clean) clean_clang-ocl ;;
(build) build_clang-ocl ;;
(outdir) print_output_directory ;;
(*) die "Invalid target $TARGET" ;;
esac
echo "Operation complete"
exit 0

View File

@@ -1,151 +0,0 @@
#!/bin/bash
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
printUsage() {
echo
echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
echo
echo "Options:"
echo " -c, --clean Clean output and delete all intermediate work"
echo " -p, --package <type> Specify packaging format"
echo " -r, --release Make a release build instead of a debug build"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
echo " -h, --help Prints this help"
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
echo " -l, --link_llvm_static Link to LLVM statically. Default is to dynamically link to LLVM; requires that LLVM dylibs are created."
echo
echo "Possible values for <type>:"
echo " deb -> Debian format (default)"
echo " rpm -> RPM format"
echo
return 0
}
API_NAME=amd_comgr
PROJ_NAME=$API_NAME
LIB_NAME=lib${API_NAME}
TARGET=build
MAKETARGET=deb
PACKAGE_ROOT=$(getPackageRoot)
PACKAGE_LIB=$(getLibPath)
PACKAGE_INCLUDE=$(getIncludePath)
BUILD_DIR=$(getBuildPath $API_NAME)
PACKAGE_DEB=$(getPackageRoot)/deb/$API_NAME
PACKAGE_RPM=$(getPackageRoot)/rpm/$API_NAME
PACKAGE_PREFIX=$ROCM_INSTALL_PATH
BUILD_TYPE=Debug
MAKE_OPTS="$DASH_JAY CTEST_OUTPUT_ON_FAILURE=1 -C $BUILD_DIR"
VERBOSE_OPTS="AMD_COMGR_EMIT_VERBOSE_LOGS=1 AMD_COMGR_REDIRECT_LOGS=stdout"
SHARED_LIBS="ON"
CLEAN_OR_OUT=0;
PKGTYPE="deb"
MAKETARGET="deb"
LINK_LLVM_DYLIB="OFF"
VALID_STR=`getopt -o hcraslo:p: --long help,clean,release,address_sanitizer,static,link_llvm_static,outdir:,package: -- "$@"`
eval set -- "$VALID_STR"
while true ;
do
case "$1" in
(-h | --help)
printUsage ; exit 0;;
(-c | --clean)
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
(-r | --release)
BUILD_TYPE="RelWithDebInfo" ; shift ;;
(-a | --address_sanitizer)
set_asan_env_vars
set_address_sanitizer_on ; shift ;;
(-s | --static)
SHARED_LIBS="OFF" ; shift ;;
(-l | --link_llvm_static)
LINK_LLVM_DYLIB="OFF"; shift ;;
(-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
(-p | --package)
MAKETARGET="$2" ; shift 2;;
--) shift; break;; # end delimiter
(*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
esac
done
RET_CONFLICT=1
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
if [ $RET_CONFLICT -ge 30 ]; then
print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
exit $RET_CONFLICT
fi
clean() {
echo "Cleaning $PROJ_NAME"
rm -rf $BUILD_DIR
rm -rf $PACKAGE_DEB
rm -rf $PACKAGE_RPM
rm -rf $PACKAGE_ROOT/${PROJ_NAME}
rm -rf $PACKAGE_LIB/${LIB_NAME}*
}
build() {
echo "Building $PROJ_NAME"
mkdir -p "$BUILD_DIR"
pushd "$BUILD_DIR"
if [ "$SHARED_LIBS" == "OFF" ]
then
echo " Building Archive "
else
echo " Building Shared Object "
fi
cmake \
$(rocm_cmake_params) \
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
$(rocm_common_cmake_params) \
-DCMAKE_DISABLE_FIND_PACKAGE_hip=TRUE \
-DCMAKE_CTEST_ARGUMENTS="--exclude-regex;multithread_test" \
-DLLVM_LINK_LLVM_DYLIB=$LINK_LLVM_DYLIB \
-DLLVM_ENABLE_LIBCXX=$LINK_LLVM_DYLIB \
$COMGR_ROOT
popd
cmake --build "$BUILD_DIR" -- $MAKE_OPTS
cmake --build "$BUILD_DIR" -- $MAKE_OPTS $VERBOSE_OPTS test
cmake --build "$BUILD_DIR" -- $MAKE_OPTS install
cmake --build "$BUILD_DIR" -- $MAKE_OPTS package
mkdir -p $PACKAGE_LIB
cp -R $BUILD_DIR/${LIB_NAME}* $PACKAGE_LIB
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" $BUILD_DIR/comgr*.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" $BUILD_DIR/comgr*.rpm
}
print_output_directory() {
case ${PKGTYPE} in
("deb")
echo ${PACKAGE_DEB};;
("rpm")
echo ${PACKAGE_RPM};;
(*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
esac
exit
}
verifyEnvSetup
case $TARGET in
(clean) clean ;;
(build) build ;;
(outdir) print_output_directory ;;
(*) die "Invalid target $TARGET" ;;
esac
echo "Operation complete"

View File

@@ -1,185 +0,0 @@
#!/bin/bash
set -ex
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
set_component_src composable_kernel
build_miopen_ck() {
echo "Start Building Composable Kernel"
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
set_asan_env_vars
set_address_sanitizer_on
fi
cd $COMPONENT_SRC
mkdir "$BUILD_DIR" && cd "$BUILD_DIR"
if [ -n "$GPU_ARCHS" ]; then
GPU_TARGETS="$GPU_ARCHS"
else
GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
fi
if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
cmake -DBUILD_DEV=OFF \
-DCMAKE_BUILD_TYPE=${BUILD_TYPE:-'RelWithDebInfo'} \
-DCMAKE_CXX_COMPILER=${ROCM_PATH}/llvm/bin/clang++ \
-DCMAKE_CXX_FLAGS=" -O3 " \
-DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}/lib/cmake;${ROCM_PATH%-*}/$ASAN_LIBDIR;${ROCM_PATH%-*}/llvm;${ROCM_PATH%-*}" \
-DCMAKE_SHARED_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_LIB_RPATH" \
-DCMAKE_EXE_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_EXE_RPATH" \
-DCMAKE_VERBOSE_MAKEFILE=1 \
-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
-DCMAKE_INSTALL_PREFIX=${ROCM_PATH} \
-DCMAKE_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
-DROCM_SYMLINK_LIBS=OFF \
-DCPACK_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
-DROCM_DISABLE_LDCONFIG=ON \
-DROCM_PATH=${ROCM_PATH} \
-DCPACK_GENERATOR="${PKGTYPE^^}" \
${LAUNCHER_FLAGS} \
-DINSTANCES_ONLY=ON \
-DENABLE_ASAN_PACKAGING=true \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
"$COMPONENT_SRC"
else
cmake -DBUILD_DEV=OFF \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_CXX_COMPILER=${ROCM_PATH}/llvm/bin/clang++ \
-DCMAKE_CXX_FLAGS=" -O3 " \
-DCMAKE_PREFIX_PATH=${ROCM_PATH%-*} \
-DCMAKE_SHARED_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN' \
-DCMAKE_EXE_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN/../lib' \
-DCMAKE_VERBOSE_MAKEFILE=1 \
-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
-DCMAKE_INSTALL_PREFIX=${ROCM_PATH} \
-DCMAKE_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
-DROCM_SYMLINK_LIBS=OFF \
-DCPACK_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
-DROCM_DISABLE_LDCONFIG=ON \
-DROCM_PATH=${ROCM_PATH} \
-DCPACK_GENERATOR="${PKGTYPE^^}" \
${LAUNCHER_FLAGS} \
-DINSTANCES_ONLY=ON \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
"$COMPONENT_SRC"
fi
cmake --build . -- -j${PROC} package
cmake --build "$BUILD_DIR" -- install
mkdir -p $PACKAGE_DIR && cp ./*.${PKGTYPE} $PACKAGE_DIR
rm -rf *
}
unset_asan_env_vars() {
ASAN_CMAKE_PARAMS="false"
export ADDRESS_SANITIZER="OFF"
export LD_LIBRARY_PATH=""
export ASAN_OPTIONS=""
}
set_address_sanitizer_off() {
export CFLAGS=""
export CXXFLAGS=""
export LDFLAGS=""
}
build_miopen_ckProf() {
ENABLE_ADDRESS_SANITIZER=false
echo "Start Building Composable Kernel Profiler"
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
set_asan_env_vars
set_address_sanitizer_on
else
unset_asan_env_vars
set_address_sanitizer_off
fi
cd $COMPONENT_SRC
cd "$BUILD_DIR"
rm -rf *
architectures='gfx10 gfx11 gfx90 gfx94'
if [ -n "$GPU_ARCHS" ]; then
architectures=$(echo ${GPU_ARCHS} | awk -F';' '{for(i=1;i<=NF;i++) a[substr($i,1,5)]} END{for(i in a) printf i" "}')
else
architectures='gfx10 gfx11 gfx90 gfx94'
fi
for arch in ${architectures}
do
if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
cmake -DBUILD_DEV=OFF \
-DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}/lib/cmake;${ROCM_PATH%-*}/$ASAN_LIBDIR;${ROCM_PATH%-*}/llvm;${ROCM_PATH%-*}" \
-DCMAKE_BUILD_TYPE=${BUILD_TYPE:-'RelWithDebInfo'} \
-DCMAKE_SHARED_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_LIB_RPATH" \
-DCMAKE_EXE_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_EXE_RPATH" \
-DCMAKE_VERBOSE_MAKEFILE=1 \
-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
-DCMAKE_INSTALL_PREFIX="${ROCM_PATH}" \
-DCMAKE_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
-DROCM_SYMLINK_LIBS=OFF \
-DCPACK_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
-DROCM_DISABLE_LDCONFIG=ON \
-DROCM_PATH="${ROCM_PATH}" \
-DCPACK_GENERATOR="${PKGTYPE^^}" \
-DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
-DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
${LAUNCHER_FLAGS} \
-DPROFILER_ONLY=ON \
-DENABLE_ASAN_PACKAGING=true \
-DGPU_ARCH="${arch}" \
"$COMPONENT_SRC"
else
cmake -DBUILD_DEV=OFF \
-DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}" \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_SHARED_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN' \
-DCMAKE_EXE_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN/../lib' \
-DCMAKE_VERBOSE_MAKEFILE=1 \
-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
-DCMAKE_INSTALL_PREFIX="${ROCM_PATH}" \
-DCMAKE_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
-DROCM_SYMLINK_LIBS=OFF \
-DCPACK_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
-DROCM_DISABLE_LDCONFIG=ON \
-DROCM_PATH="${ROCM_PATH}" \
-DCPACK_GENERATOR="${PKGTYPE^^}" \
-DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
-DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
${LAUNCHER_FLAGS} \
-DPROFILER_ONLY=ON \
-DGPU_ARCH="${arch}" \
"$COMPONENT_SRC"
fi
cmake --build . -- -j${PROC} package
cp ./*ckprofiler*.${PKGTYPE} $PACKAGE_DIR
rm -rf *
done
rm -rf _CPack_Packages/ && find -name '*.o' -delete
echo "Finished building Composable Kernel"
show_build_cache_stats
}
clean_miopen_ck() {
echo "Cleaning MIOpen-CK build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
echo "Done!"
}
stage2_command_args "$@"
case $TARGET in
build) build_miopen_ck; build_miopen_ckProf;;
outdir) print_output_directory ;;
clean) clean_miopen_ck ;;
*) die "Invalid target $TARGET" ;;
esac

View File

@@ -1,159 +0,0 @@
#!/bin/bash
source "${BASH_SOURCE%/*}/compute_utils.sh"
printUsage() {
echo
echo "Usage: $(basename "${BASH_SOURCE[0]}") [options ...]"
echo
echo "Options:"
echo " -c, --clean Clean output and delete all intermediate work"
echo " -p, --package <type> Specify packaging format"
echo " -r, --release Make a release build instead of a debug build"
echo " --enable-assertions Enable assertions"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
echo " -h, --help Prints this help"
echo " -M, --skip_man_pages Do not build the 'docs' target"
echo " -s, --static Supports static CI by accepting this param & not bailing out. No effect of the param though"
echo
echo "Possible values for <type>:"
echo " deb -> Debian format (default)"
echo " rpm -> RPM format"
echo
return 0
}
API_NAME=rocm-dbgapi
AMD_DBGAPI_NAME=amd-dbgapi
MAKEINSTALL_MANIFEST=makeinstall_manifest.txt
PROJ_NAME=$API_NAME
LIB_NAME=lib${API_NAME}.so
TARGET=build
MAKETARGET=deb
PACKAGE_ROOT=$(getPackageRoot)
PACKAGE_LIB=$(getLibPath)
PACKAGE_INCLUDE=$(getIncludePath)
BUILD_DIR=$(getBuildPath $API_NAME)
PACKAGE_DEB=$(getPackageRoot)/deb/$API_NAME
PACKAGE_RPM=$(getPackageRoot)/rpm/$API_NAME
BUILD_TYPE=Debug
MAKE_OPTS=($DASH_JAY -C "$BUILD_DIR")
SHARED_LIBS="ON"
CLEAN_OR_OUT=0;
MAKETARGET="deb"
PKGTYPE="deb"
DODOCSBUILD=true
VALID_STR=$(getopt -o hcraso:p:M --long help,clean,release,enable-assertions,static,address_sanitizer,outdir:,package:skip_man_pages -- "$@")
eval set -- "$VALID_STR"
while true ;
do
case "$1" in
(-h | --help)
printUsage ; exit 0;;
(-c | --clean)
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ;;
(-r | --release)
ENABLE_ASSERTIONS=${ENABLE_ASSERTIONS:-"Off"} ;
BUILD_TYPE="RelWithDebInfo" ;;
( --enable-assertions)
ENABLE_ASSERTIONS="On" ;;
(-a | --address_sanitizer)
set_asan_env_vars
set_address_sanitizer_on ;;
(-s | --static)
SHARED_LIBS="OFF" ;;
(-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; ((CLEAN_OR_OUT|=2)) ; shift 1 ;;
(-M | --skip_man_pages) DODOCSBUILD=false;;
(-p | --package)
MAKETARGET="$2" ; shift 1;;
--) shift; break;;
(*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
esac
shift
done
check_conflicting_options $CLEAN_OR_OUT "$PKGTYPE" "$MAKETARGET"
if [ "$RET_CONFLICT" -ge 30 ]; then
print_vars "$API_NAME" "$TARGET" "$BUILD_TYPE" "$SHARED_LIBS" "$CLEAN_OR_OUT" "$PKGTYPE" "$MAKETARGET"
exit "$RET_CONFLICT"
fi
clean() {
echo "Cleaning $PROJ_NAME"
if [ -e "$BUILD_DIR/$MAKEINSTALL_MANIFEST" ] ; then
xargs rm -f < "$BUILD_DIR/$MAKEINSTALL_MANIFEST"
fi
rm -rf "$BUILD_DIR"
rm -rf "$PACKAGE_DEB"
rm -rf "$PACKAGE_RPM"
rm -rf "${PACKAGE_ROOT:?}/${PROJ_NAME}"
rm -rf "${PACKAGE_LIB:?}/${LIB_NAME}"*
rm -rf "${PACKAGE_LIB:?}/cmake/${AMD_DBGAPI_NAME}"
rm -rf "${PACKAGE_INCLUDE:?}/${AMD_DBGAPI_NAME}"
}
build() {
if [ ! -e "$ROCM_DBGAPI_ROOT/CMakeLists.txt" ]
then
echo " No $ROCM_DBGAPI_ROOT/CMakeLists.txt file, skipping rocm-dbgapi" >&2
echo " No $ROCM_DBGAPI_ROOT/CMakeLists.txt file, skipping rocm-dbgapi"
exit 0
fi
echo "Building $PROJ_NAME"
mkdir -p "$BUILD_DIR"
pushd "$BUILD_DIR" || exit 99
cmake \
$(rocm_cmake_params) \
$(rocm_common_cmake_params) \
-DENABLE_ASSERTIONS=${ENABLE_ASSERTIONS:-"On"} \
"$ROCM_DBGAPI_ROOT"
popd || exit 99
cmake --build "$BUILD_DIR" -- "${MAKE_OPTS[@]}"
"$DODOCSBUILD" && cmake --build "$BUILD_DIR" -- "${MAKE_OPTS[@]}" doc
cmake --build "$BUILD_DIR" -- "${MAKE_OPTS[@]}" install
mv "$BUILD_DIR/install_manifest.txt" "$BUILD_DIR/$MAKEINSTALL_MANIFEST"
cmake --build "$BUILD_DIR" -- "${MAKE_OPTS[@]}" package
mkdir -p "$PACKAGE_LIB"
(
shopt -s nullglob
cp -R "$BUILD_DIR/lib/${LIB_NAME}"* "$BUILD_DIR/${LIB_NAME}"* "$PACKAGE_LIB"
)
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
}
print_output_directory() {
case ${PKGTYPE} in
("deb")
echo ${PACKAGE_DEB};;
("rpm")
echo ${PACKAGE_RPM};;
(*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
esac
exit
}
verifyEnvSetup
case $TARGET in
(clean) clean ;;
(build) build ;;
(outdir) print_output_directory ;;
(*) die "Invalid target $TARGET" ;;
esac
echo "Operation complete"

View File

@@ -1,140 +0,0 @@
#!/bin/bash
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
printUsage() {
echo
echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
echo
echo "Options:"
echo " -c, --clean Clean output and delete all intermediate work"
echo " -r, --release Build a release version of the package"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -s, --static Supports static CI by accepting this param & not bailing out. No effect of the param though"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
echo " -h, --help Prints this help"
echo
echo
return 0
}
PACKAGE_ROOT="$(getPackageRoot)"
PACKAGE_BIN="$(getBinPath)"
PACKAGE_LIB="$(getLibPath)"
BUILD_PATH="$(getBuildPath devicelibs)"
INSTALL_PATH="$(getPackageRoot)"
LIGHTNING_BUILD_PATH="$(getBuildPath lightning)"
DEB_PATH="$(getDebPath devicelibs)"
RPM_PATH="$(getRpmPath devicelibs)"
AMDGCN_LIB_PATH="$PACKAGE_ROOT/amdgcn/bitcode/"
TARGET="build"
MAKEOPTS="$DASH_JAY"
SHARED_LIBS="ON"
CLEAN_OR_OUT=0;
PKGTYPE="deb"
MAKETARGET="deb"
VALID_STR=`getopt -o hcraso: --long help,clean,release,static,address_sanitizer,outdir: -- "$@"`
eval set -- "$VALID_STR"
while true ;
do
case "$1" in
(-h | --help)
printUsage ; exit 0;;
(-c | --clean)
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
(-r | --release)
BUILD_TYPE="Release" ; shift ;;
(-a | --address_sanitizer)
ASAN_CMAKE_PARAMS="true"
ack_and_ignore_asan ; shift ;;
(-s | --static)
SHARED_LIBS="OFF" ; shift ;;
(-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
--) shift; break;; # end delimiter
(*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
esac
done
RET_CONFLICT=1
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
if [ $RET_CONFLICT -ge 30 ]; then
print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
exit $RET_CONFLICT
fi
clean_devicelibs() {
rm -rf "$BUILD_PATH"
rm -f $PACKAGE_LIB/hc*.bc
rm -f $PACKAGE_LIB/irif*.bc
rm -f $PACKAGE_LIB/ockl*.bc
rm -f $PACKAGE_LIB/oclc*.bc
rm -f $PACKAGE_LIB/ocml*.bc
rm -f $PACKAGE_LIB/opencl*.bc
rm -f $PACKAGE_LIB/openmp*.bc
rm -rf $PACKAGE_ROOT/amdgcn
rm -rf "$DEB_PATH"
rm -rf "$RPM_PATH"
}
build_devicelibs() {
mkdir -p "$BUILD_PATH"
pushd "$BUILD_PATH"
local clangResourceDir="$($LIGHTNING_BUILD_PATH/bin/clang -print-resource-dir)"
local clangResourceVer=${clangResourceDir#*lib/clang/}
local bitcodeInstallLoc="lib/llvm/lib/clang/${clangResourceVer}/lib"
export LLVM_BUILD="$LIGHTNING_BUILD_PATH"
if [ ! -e Makefile ]; then
cmake $(rocm_cmake_params) \
$(rocm_common_cmake_params) \
-DROCM_DEVICE_LIBS_BITCODE_INSTALL_LOC_NEW="$bitcodeInstallLoc/amdgcn" \
-DROCM_DEVICE_LIBS_BITCODE_INSTALL_LOC_OLD="amdgcn" \
"$DEVICELIBS_ROOT"
echo "CMake complete"
fi
echo "Building device-libs"
cmake --build . -- $MAKEOPTS
cmake --build . -- $MAKEOPTS install
popd
}
package_devicelibs() {
mkdir -p "$DEB_PATH"
mkdir -p "$RPM_PATH"
pushd "$BUILD_PATH"
cpack
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$DEB_PATH" *.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$RPM_PATH" *.rpm
popd
}
print_output_directory() {
case ${PKGTYPE} in
("deb")
echo ${DEB_PATH};;
("rpm")
echo ${RPM_PATH};;
(*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
esac
exit
}
case $TARGET in
(clean) clean_devicelibs ;;
(build) build_devicelibs; package_devicelibs ;;
(outdir) print_output_directory ;;
(*) die "Invalid target $TARGET" ;;
esac
echo "Operation complete"

View File

@@ -1,46 +0,0 @@
#!/bin/bash
set -ex
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
set_component_src half
build_half() {
echo "Start build"
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
set_asan_env_vars
set_address_sanitizer_on
ASAN_CMAKE_PARAMS="false"
fi
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
cmake \
-DCMAKE_INSTALL_PREFIX="$ROCM_PATH" \
-DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
"$COMPONENT_SRC"
cmake --build "$BUILD_DIR" -- -j${PROC}
cmake --build "$BUILD_DIR" -- package
cmake --build "$BUILD_DIR" -- install
rm -rf _CPack_Packages/ && find -name '*.o' -delete
mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
show_build_cache_stats
}
clean_half() {
echo "Cleaning half build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
echo "Done!"
}
stage2_command_args "$@"
case $TARGET in
build) build_half ;;
outdir) print_output_directory ;;
clean) clean_half ;;
*) die "Invalid target $TARGET" ;;
esac

View File

@@ -1,295 +0,0 @@
#!/bin/bash
printUsage() {
echo
echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
echo
echo "Options:"
echo " -h, --help Prints this help"
echo " -c, --clean Clean output and delete all intermediate work"
echo " -r, --release Make a release build instead of a debug build"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of type referred to by pkg_type"
echo " -t, --offload-arch=<arch> Specify arch for catch tests ex: --offload-arch=gfx1030 --offload-arch=gfx1100"
echo " -p, --package <type> Specify packaging format"
echo
echo "Possible values for <type>:"
echo " deb -> Debian format (default)"
echo " rpm -> RPM format"
echo
return 0
}
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
MAKEOPTS="$DASH_JAY"
BUILD_PATH="$(getBuildPath hip-on-rocclr)"
TARGET="build"
PACKAGE_ROOT="$(getPackageRoot)"
PACKAGE_SRC="$(getSrcPath)"
PACKAGE_DEB="$PACKAGE_ROOT/deb/hip-on-rocclr"
PACKAGE_RPM="$PACKAGE_ROOT/rpm/hip-on-rocclr"
PREFIX_PATH="$PACKAGE_ROOT"
CORE_BUILD_DIR="$(getBuildPath hsa-core)"
ROCclr_BUILD_DIR="$(getBuildPath rocclr)"
HIPCC_BUILD_DIR="$(getBuildPath hipcc)"
CATCH_BUILD_DIR="$(getBuildPath catch)"
CATCH_SRC="$HIP_CATCH_TESTS_ROOT/catch"
SAMPLES_SRC="$HIP_CATCH_TESTS_ROOT/samples"
SAMPLES_BUILD_DIR="$(getBuildPath samples)"
if [ ! -e "$CATCH_SRC/CMakeLists.txt" ]; then
echo "Using catch source from hip project" >&2
CATCH_SRC="$HIP_ON_ROCclr_ROOT/tests/catch"
fi
BUILD_TYPE="Debug"
SHARED_LIBS="ON"
CLEAN_OR_OUT=0;
MAKETARGET="deb"
PKGTYPE="deb"
OFFLOAD_ARCH=()
DEFAULT_OFFLOAD_ARCH=(gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942 gfx1030 gfx1031 gfx1033 gfx1034 gfx1035 gfx1100 gfx1101 gfx1102 gfx1103)
VALID_STR=`getopt -o hcrast:o: --long help,clean,release,address_sanitizer,static,offload-arch=:,outdir: -- "$@"`
eval set -- "$VALID_STR"
while true ;
do
case "$1" in
(-h | --help)
printUsage ; exit 0;;
(-c | --clean)
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
(-r | --release)
BUILD_TYPE="RelWithDebInfo" ; shift ;;
(-a | --address_sanitizer)
set_asan_env_vars
set_address_sanitizer_on ; shift ;;
(-s | --static)
SHARED_LIBS="OFF" ; shift ;;
(-t | --offload-arch=)
OFFLOAD_ARCH+=( "$2" ); ((CLEAN_OR_OUT|=2)); shift 2 ;;
(-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
--) shift; break;;
(*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
esac
done
if [ ${#OFFLOAD_ARCH[@]} = 0 ] ; then
OFFLOAD_ARCH=( "${DEFAULT_OFFLOAD_ARCH[@]}" )
else
echo "Using user defined offload archs ${OFFLOAD_ARCH[@]} for catch tests";
fi
printf -v OFFLOAD_ARCH_STR -- '--offload-arch=%q ' "${OFFLOAD_ARCH[@]}"
RET_CONFLICT=1
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
if [ $RET_CONFLICT -ge 30 ]; then
print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
exit $RET_CONFLICT
fi
clean_hip_on_rocclr() {
rm -rf "$BUILD_PATH"
rm -rf "$PACKAGE_DEB"
rm -rf "$PACKAGE_RPM"
rm -rf "$OUT_DIR/hip"
}
build_hip_on_rocclr() {
if [ -e "$CLR_ROOT/CMakeLists.txt" ]; then
_HIP_CMAKELIST_DIR="$CLR_ROOT"
_HIP_CMAKELIST_OPT="-DCLR_BUILD_HIP=ON -DCLR_BUILD_OCL=OFF"
if [ -e "$HIPOTHER_ROOT/hipnv" ]; then
_HIP_CMAKELIST_OPT="$_HIP_CMAKELIST_OPT -DHIPNV_DIR=$HIPOTHER_ROOT/hipnv"
fi
elif [ ! -e "$HIPAMD_ROOT/CMakeLists.txt" ]; then
echo "No $HIPAMD_ROOT/CMakeLists.txt file, skipping hip on rocclr" >&2
echo "No $HIPAMD_ROOT/CMakeLists.txt file, skipping hip on rocclr"
exit 0
else
_HIP_CMAKELIST_DIR="$HIPAMD_ROOT"
_HIP_CMAKELIST_OPT=""
fi
echo "$_HIP_CMAKELIST_DIR"
mkdir -p "$BUILD_PATH"
pushd "$BUILD_PATH"
if [ ! -e Makefile ]; then
echo "Building HIP-On-ROCclr CMake environment"
print_lib_type $SHARED_LIBS
cmake $(rocm_cmake_params) \
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
-DHIP_COMPILER=clang \
-DHIP_PLATFORM=amd \
-DHIP_COMMON_DIR="$HIP_ON_ROCclr_ROOT" \
$(rocm_common_cmake_params) \
-DCMAKE_HIP_ARCHITECTURES=OFF \
-DHSA_PATH="$ROCM_INSTALL_PATH" \
-DCMAKE_SKIP_BUILD_RPATH=TRUE \
-DCPACK_INSTALL_PREFIX="$ROCM_INSTALL_PATH" \
-DROCM_PATH="$ROCM_INSTALL_PATH" \
-DHIPCC_BIN_DIR="$HIPCC_BUILD_DIR" \
-DHIP_CATCH_TEST=1 \
$_HIP_CMAKELIST_OPT \
"$_HIP_CMAKELIST_DIR"
echo "CMake complete"
fi
echo "Build and Install HIP"
cmake --build . -- $MAKEOPTS install "VERBOSE=1"
popd
}
build_catch_tests() {
WORKSPACE=`pwd`
echo "Build catch2 tests independently"
if [ ! -e "$CATCH_SRC/CMakeLists.txt" ]; then
echo "catch source not found: $CATCH_SRC" >&2
exit
fi
# build catch
rm -rf "$CATCH_BUILD_DIR"
mkdir -p "$CATCH_BUILD_DIR"
pushd "$CATCH_BUILD_DIR"
export HIP_PATH="$ROCM_INSTALL_PATH"
export ROCM_PATH="$ROCM_INSTALL_PATH"
cmake \
-DCMAKE_BUILD_TYPE="${BUILD_TYPE}" \
-DHIP_PLATFORM=amd \
-DROCM_PATH="$ROCM_INSTALL_PATH" \
-DOFFLOAD_ARCH_STR="$OFFLOAD_ARCH_STR" \
$(rocm_common_cmake_params) \
-DCPACK_RPM_DEBUGINFO_PACKAGE=FALSE \
-DCPACK_DEBIAN_DEBUGINFO_PACKAGE=FALSE \
-DCPACK_INSTALL_PREFIX="$ROCM_INSTALL_PATH" \
"$CATCH_SRC"
make $MAKEOPTS build_tests
echo "Packaging catch tests"
make $MAKEOPTS package_test
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" *.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" *.rpm
popd
}
package_samples() {
if [ "$ASAN_CMAKE_PARAMS" == "true" ] ; then
echo "Disable the packaging of HIP samples" >&2
return
fi
WORKSPACE=`pwd`
if [ ! -e "$SAMPLES_SRC/CMakeLists.txt" ]; then
echo "HIP samples source not found at: $SAMPLES_SRC" >&2
echo "Using samples package from hip project: $BUILD_PATH" >&2
return
fi
rm -rf "$SAMPLES_BUILD_DIR"
mkdir -p "$SAMPLES_BUILD_DIR"
pushd "$SAMPLES_BUILD_DIR"
local CMAKE_PATH="$(getCmakePath)"
export HIP_PATH="$ROCM_INSTALL_PATH"
export ROCM_PATH="$ROCM_INSTALL_PATH"
cmake \
-DROCM_PATH="$ROCM_INSTALL_PATH" \
$(rocm_common_cmake_params) \
-DCMAKE_MODULE_PATH="$CMAKE_PATH/hip" \
-DCPACK_INSTALL_PREFIX="$ROCM_INSTALL_PATH" \
"$SAMPLES_SRC"
echo "Packaging hip samples from hip-tests project"
make $MAKEOPTS package_samples
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" *.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" *.rpm
popd
}
clean_hip_tests(){
rm -rf "$CATCH_BUILD_DIR"
rm -rf "$PACKAGE_SRC/hip-on-rocclr"
rm -rf "$PACKAGE_SRC/hipamd"
rm -rf "$PACKAGE_SRC/rocclr"
rm -rf "$PACKAGE_SRC/opencl-on-rocclr"
rm -rf "$PACKAGE_SRC/clr"
rm -rf "$PACKAGE_SRC/hip-tests"
rm -rf "$PACKAGE_SRC/hipother"
}
copy_hip_tests() {
clean_hip_tests
echo "Copy HIP & ROCclr Source and tests"
mkdir -p "$PACKAGE_SRC/hip-on-rocclr"
echo "Copying hip-on-rocclr"
progressCopy "$HIP_ON_ROCclr_ROOT" "$PACKAGE_SRC/hip-on-rocclr"
if [ -e "$CLR_ROOT/CMakeLists.txt" ]; then
mkdir -p "$PACKAGE_SRC/clr"
echo "Copying clr"
progressCopy "$CLR_ROOT" "$PACKAGE_SRC/clr"
else
mkdir -p "$PACKAGE_SRC/hipamd"
mkdir -p "$PACKAGE_SRC/rocclr"
mkdir -p "$PACKAGE_SRC/opencl-on-rocclr"
echo "Copying hipamd"
progressCopy "$HIPAMD_ROOT" "$PACKAGE_SRC/hipamd"
echo "Copying rocclr"
progressCopy "$ROCclr_ROOT" "$PACKAGE_SRC/rocclr"
echo "Copying opencl-on-rocclr"
progressCopy "$OPENCL_ON_ROCclr_ROOT" "$PACKAGE_SRC/opencl-on-rocclr"
fi
if [ -e "$HIPOTHER_ROOT/hipnv" ]; then
mkdir -p "$PACKAGE_SRC/hipother"
echo "Copying hipother"
progressCopy "$HIPOTHER_ROOT" "$PACKAGE_SRC/hipother"
fi
mkdir -p "$PACKAGE_SRC/hip-tests"
echo "Copying hip-tests"
progressCopy "$HIP_CATCH_TESTS_ROOT" "$PACKAGE_SRC/hip-tests"
}
package_hip_on_rocclr()
{
echo "Packagin HIP-on-ROCclr"
pushd "$BUILD_PATH"
cmake --build . -- $MAKEOPTS package
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" *.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" *.rpm
popd
}
print_output_directory() {
case ${PKGTYPE} in
("deb")
echo ${PACKAGE_DEB};;
("rpm")
echo ${PACKAGE_RPM};;
(*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
esac
exit
}
case $TARGET in
(clean) clean_hip_on_rocclr; clean_hip_tests ;;
(build) build_hip_on_rocclr; build_catch_tests; package_hip_on_rocclr; package_samples; copy_hip_tests;;
(outdir) print_output_directory ;;
(*) die "Invalid target $TARGET" ;;
esac
echo "Operation complete"

View File

@@ -1,65 +0,0 @@
#!/bin/bash
set -ex
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
set_component_src hipBLAS
build_hipblas() {
echo "Start build"
CXX="g++"
CLIENTS_SAMPLES="ON"
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
set_asan_env_vars
set_address_sanitizer_on
CLIENTS_SAMPLES="OFF"
fi
echo "C compiler: $CC"
echo "CXX compiler: $CXX"
echo "FC compiler: $FC"
cd $COMPONENT_SRC
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
rebuild_lapack
fi
cmake \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
-DUSE_CUDA=OFF \
-DBUILD_CLIENTS_TESTS=ON \
-DBUILD_CLIENTS_BENCHMARKS=ON \
-DBUILD_CLIENTS_SAMPLES="${CLIENTS_SAMPLES}" \
-DCPACK_SET_DESTDIR=OFF \
-DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \
"$COMPONENT_SRC"
cmake --build "$BUILD_DIR" -- -j${PROC}
cmake --build "$BUILD_DIR" -- install
cmake --build "$BUILD_DIR" -- package
rm -rf _CPack_Packages/ && find -name '*.o' -delete
mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
show_build_cache_stats
}
clean_hipblas() {
echo "Cleaning hipBLAS build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
echo "Done!"
}
stage2_command_args "$@"
case $TARGET in
build) build_hipblas ;;
outdir) print_output_directory ;;
clean) clean_hipblas ;;
*) die "Invalid target $TARGET" ;;
esac

View File

@@ -1,69 +0,0 @@
#!/bin/bash
set -ex
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
set_component_src hipBLASLt
build_hipblaslt() {
echo "Start build"
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
set_asan_env_vars
set_address_sanitizer_on
fi
cd $COMPONENT_SRC
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
rebuild_lapack
fi
if [ -n "$GPU_ARCHS" ]; then
GPU_TARGETS="$GPU_ARCHS"
else
# gfx90a:xnack+;gfx90a:xnack-;gfx940;gfx941;gfx942
GPU_TARGETS=all
fi
CXX=$(set_build_variables CXX)\
cmake \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
-DTensile_LOGIC= \
-DTensile_CODE_OBJECT_VERSION=default \
-DTensile_CPU_THREADS= \
-DTensile_LIBRARY_FORMAT=msgpack \
-DBUILD_CLIENTS_SAMPLES=ON \
-DBUILD_CLIENTS_TESTS=ON \
-DBUILD_CLIENTS_BENCHMARKS=ON \
-DCPACK_SET_DESTDIR=OFF \
-DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \
"$COMPONENT_SRC"
cmake --build "$BUILD_DIR" -- -j${PROC}
cmake --build "$BUILD_DIR" -- install
cmake --build "$BUILD_DIR" -- package
rm -rf _CPack_Packages/ && find -name '*.o' -delete
mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
show_build_cache_stats
}
clean_hipblaslt() {
echo "Cleaning hipBLASLt build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
echo "Done!"
}
stage2_command_args "$@"
case $TARGET in
build) build_hipblaslt ;;
outdir) print_output_directory ;;
clean) clean_hipblaslt ;;
*) die "Invalid target $TARGET" ;;
esac

View File

@@ -1,118 +0,0 @@
#!/bin/bash
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
printUsage() {
echo
echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
echo
echo "Options:"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -c, --clean Clean output and delete all intermediate work"
echo " -h, --help Prints this help"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
echo " -r, --release Makes a release build"
echo
return 0
}
API_NAME=hipcc
PROJ_NAME=$API_NAME
TARGET="build"
MAKEOPTS="$DASH_JAY"
BUILD_TYPE="Debug"
BUILD_DIR=$(getBuildPath $API_NAME)
PACKAGE_DEB=$(getPackageRoot)/deb/$API_NAME
PACKAGE_RPM=$(getPackageRoot)/rpm/$API_NAME
PACKAGE_SRC="$(getSrcPath)"
while [ "$1" != "" ];
do
case $1 in
(-a | --address_sanitizer)
ack_and_ignore_asan ;;
(-c | --clean)
TARGET="clean" ;;
(-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 1 ;;
(-r | --release)
BUILD_TYPE="RelWithDebInfo" ;;
(-h | --help)
printUsage ; exit 0 ;;
(*)
echo "Invalid option [$1]" >&2; printUsage; exit 1 ;;
esac
shift 1
done
clean() {
echo "Cleaning hipcc"
rm -rf $BUILD_DIR
echo "Cleaning up hipcc DEB and RPM packages"
rm -rf $PACKAGE_DEB
rm -rf $PACKAGE_RPM
}
copy_hipcc_sources() {
echo "Clean up hipcc build folder"
rm -rf "$PACKAGE_SRC/hipcc"
echo "Copy hipcc sources"
mkdir -p "$PACKAGE_SRC/hipcc"
progressCopy "$HIPCC_ROOT" "$PACKAGE_SRC/hipcc"
}
build() {
echo "Build hipcc binary"
mkdir -p "$BUILD_DIR"
pushd "$BUILD_DIR"
if ! [ -e "$HIPCC_ROOT/CMakeLists.txt" ] ; then
echo "No source for hipcc, exiting. this is not an error" >&2
exit 0
fi
cmake \
$(rocm_cmake_params) \
$(rocm_common_cmake_params) \
-DHIPCC_BACKWARD_COMPATIBILITY=OFF \
-DCMAKE_INSTALL_PREFIX="$OUT_DIR" \
$HIPCC_ROOT
popd
cmake --build "$BUILD_DIR" -- $MAKEOPTS
echo "Installing and Packaging hipcc"
cmake --build "$BUILD_DIR" -- $MAKEOPTS install
cmake --build "$BUILD_DIR" -- $MAKEOPTS package
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" $BUILD_DIR/hipcc*.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" $BUILD_DIR/hipcc*.rpm
}
print_output_directory() {
case ${PKGTYPE} in
("deb")
echo ${PACKAGE_DEB};;
("rpm")
echo ${PACKAGE_RPM};;
(*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1 ;;
esac
exit
}
case $TARGET in
(clean) clean ;;
(build) build ; copy_hipcc_sources ;;
(outdir) print_output_directory ;;
(*) die "Invalid target $TARGET" ;;
esac
echo "Operation complete"

Some files were not shown because too many files have changed in this diff Show More