Compare commits

..

35 Commits

Author SHA1 Message Date
ammallya
f861f098ea Merge pull request #4326 from ROCm/ammallya-patch-1
Adding SPIRV-LLVM-Translator
2025-01-31 19:58:22 -08:00
ammallya
61ae584182 Adding SPIRV-LLVM-Translator 2025-01-31 16:31:49 -08:00
ammallya
c49adf0b36 Merge pull request #4321 from ammallya/amd-mainline
Changed manifest to point to mainline
2025-01-30 23:49:29 -08:00
ammallya
dcee340ede Changed manifest to point to mainline 2025-01-30 23:47:06 -08:00
ammallya
eb2b091a7d Changed ROCm source code to point to mainline 2024-09-23 19:19:30 -07:00
ammallya
cde3714d5d Update default.xml 2024-09-22 21:11:22 -07:00
ammallya
8838445540 Mainline pipeline 2024-09-22 20:40:58 -07:00
ammallya
95eb27cff7 Merge pull request #3789 from ammallya/amd-mainline
Updated default.xml
2024-09-22 20:39:12 -07:00
ammallya
6d03ead29a Merge branch 'ROCm:amd-mainline' into amd-mainline 2024-09-22 20:38:36 -07:00
ammallya
d640e6ecba Update default.xml 2024-09-22 17:13:46 -07:00
ammallya
4e11fc0c3a Update default.xml 2024-09-22 16:08:50 -07:00
ammallya
d405649696 Merge pull request #3787 from ammallya/amd-mainline
Updated xml file to point to new tag
2024-09-22 15:56:34 -07:00
ammallya
6595bd0e98 Update default.xml 2024-09-22 15:44:48 -07:00
ammallya
e171cd8f81 Update default.xml 2024-09-22 14:51:27 -07:00
ammallya
8c815485a8 Update default.xml 2024-09-22 14:43:12 -07:00
Sam Wu
87bc26e672 Merge pull request #3623 from samjwu/update62x
Update roc-6.2.x
2024-08-20 15:17:56 -06:00
Daniel Su
120e68b73f External CI: fix HIP pipeline ID for copyHIP (#3620) 2024-08-20 13:10:42 -04:00
Wang, Yanyao
1d79657057 fix README.md for Ubuntu24 docker 2024-08-20 10:00:23 -07:00
Wang, Yanyao
884b5a0ec2 Update build scripts for ROCm6.2 release 2024-08-20 10:00:23 -07:00
Daniel Su
a64e619931 External CI: use root disk for ROCm nightly build (#3619) 2024-08-20 12:07:16 -04:00
Joseph Macaranas
525f0a6b97 External CI: Pipeline dependency adjustments for hipBLAS-common (#3618) 2024-08-20 11:51:30 -04:00
Daniel Su
4d0fd51950 External CI: make llvm-project symlink optional (#3617) 2024-08-20 11:26:02 -04:00
Daniel Su
a3a6534f91 External CI: add hipBLAS-common to MIOpen (#3616) 2024-08-20 10:30:18 -04:00
dependabot[bot]
64d9d8fcfe Build(deps): Bump rocm-docs-core from 1.7.0 to 1.7.1 in /docs/sphinx (#3614)
Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.7.0 to 1.7.1.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.7.0...v1.7.1)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-19 17:00:01 -06:00
alexxu-amd
260c07e26f External CI: Add hipBLAS-common to hipBLASLt dependency list (#3613)
* add hipBLAS-common as dependency

* add test variables

* revert test variable
2024-08-19 18:55:04 -04:00
Daniel Su
b5220f9849 External CI: create llvm symlink in all components (#3612) 2024-08-19 16:20:58 -04:00
Daniel Su
1979d514f0 External CI: multi-gfx nightly ROCm builds (#3611) 2024-08-19 15:50:06 -04:00
Young Hui - AMD
96600b9a6d Update Compatibility Matrix for 6.2.0 (#3600)
* add rocAL, hipCC, CLR. Rearrange order of some items to align with stack diagram. Update UCC versions

* update llvm-project to point to docs page instead of GitHub
2024-08-16 16:42:53 -04:00
Peter Park
1e14ed1413 fix ROCdbgapi version number (#3605) 2024-08-16 16:23:04 -04:00
Daniel Su
8e135f9873 External CI: enable clr and rocMLIR latestFromBranch downloads (#3604) 2024-08-16 14:19:20 -04:00
Sam Wu
5273089b51 Merge pull request #3602 from amd-jnovotny/mi300a-memory-alloc-roc62x
Cherry-pick to roc-6.2.x: Add a section on increasing memory allocation to the MI300A system op…
2024-08-16 10:21:01 -06:00
Daniel Su
6cb11bf0c2 External CI: fix rocDecode CXX compiler (#3593) 2024-08-16 09:03:32 -04:00
Jeffrey Novotny
efe7917857 Add a section on increasing memory allocation to the MI300A system op… (#3587)
* Add a section on increasing memory allocation to the MI300A system optimization guide

* Addition to wordlist

* Change GB to GiB for consistency

* Standardize GiB/KiB spacing

* Minor wording changes
2024-08-16 08:40:39 -04:00
Jeffrey Novotny
91d4a7e0c9 Add a section on increasing memory allocation to the MI300A system op… (#3587)
* Add a section on increasing memory allocation to the MI300A system optimization guide

* Addition to wordlist

* Change GB to GiB for consistency

* Standardize GiB/KiB spacing

* Minor wording changes
2024-08-16 08:35:08 -04:00
Joseph Macaranas
4e9094e412 Fix for hipother External CI pipeline (#3597)
Recompilation of hip for AMD backend uses Microsoft-hosted agent, so no need to worry about VM costs if we re-build for any hipother repo changes.
2024-08-15 15:53:03 -04:00
76 changed files with 2002 additions and 971 deletions

View File

@@ -0,0 +1,96 @@
trigger: none
schedules:
- cron: "0 0 * * *"
displayName: Nightly build
branches:
include:
- main
always: true
variables:
ROCM_VERSION: '6.2.0'
GPU_ARCHS: 'gfx942'
DOCKER_IMAGE: 'rocm/rocm-build-ubuntu-24.04:6.2'
BUILD_USER: 'AzDevOps'
pool: rocmci
jobs:
- job: BuildROCm
timeoutInMinutes: 360
steps:
- script: |
sudo apt-get update
sudo apt-get install ca-certificates curl
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc
echo \
"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt-get update
sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
sudo chmod 666 /var/run/docker.sock
sudo docker run hello-world
docker info
displayName: 'Install Docker'
- script: |
mkdir -p ~/bin/
curl https://storage.googleapis.com/git-repo-downloads/repo > ~/bin/repo
chmod a+x ~/bin/repo
displayName: 'Install repo tool'
- script: |
sudo apt-get install -y git-lfs
displayName: 'Install git-lfs'
- script: |
mkdir -p ~/WORKSPACE/
cd ~/WORKSPACE/
export ROCM_VERSION=6.2.0
~/bin/repo init https://github.com/ROCm/ROCm.git -b amd-mainline
~/bin/repo sync
displayName: 'Step 1: Clone source code'
- script: |
sudo docker pull $(DOCKER_IMAGE)
displayName: 'Pull ROCm build Docker image'
- script: |
docker run \
-e ROCM_VERSION=${ROCM_VERSION} \
-e CCACHE_DIR=$HOME/.ccache \
-e CCACHE_ENABLED=true \
-e DOCK_WORK_FOLD=/src \
-w /src \
-v $HOME/WORKSPACE:/src \
-v /etc/passwd:/etc/passwd \
-v /etc/shadow:/etc/shadow \
-v ${HOME}/.ccache:${HOME}/.ccache \
-u $(id -u):$(id -g) \
$(DOCKER_IMAGE) \
bash -c "set -ex && \
cd /src && \
echo 'Contents of /src directory:' && \
ls -la && \
echo 'Starting rocm-dev build...' && \
make -f ROCm/tools/rocm-build/ROCm.mk -j \$(nproc) rocm-dev && \
echo 'rocm-dev build completed. Starting full build...' && \
make -f ROCm/tools/rocm-build/ROCm.mk -j \$(nproc) all && \
echo 'Full build completed.'"
displayName: 'Build ROCm in Docker container'
- task: PublishBuildArtifacts@1
inputs:
pathToPublish: '$HOME/WORKSPACE/out/ubuntu-24.04/24.04/deb'
artifactName: 'rocm-packages'
displayName: 'Publish ROCm packages'
- task: PublishBuildArtifacts@1
inputs:
pathToPublish: '$HOME/WORKSPACE/out/ubuntu-24.04/24.04/logs'
artifactName: 'build-logs'
displayName: 'Publish build logs'
condition: succeededOrFailed()

View File

@@ -3,19 +3,20 @@
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

@@ -36,7 +36,6 @@ Bluefield
Bootloader
CCD
CDNA
CHTML
CIFAR
CLI
CLion
@@ -70,7 +69,6 @@ Concretized
Conda
ConnectX
CuPy
Dashboarding
DDR
DF
DGEMM
@@ -224,7 +222,6 @@ Mellanox
Mellanox's
Meta's
MirroredStrategy
Mixtral
Multicore
Multithreaded
MyEnvironment
@@ -270,8 +267,6 @@ OpenMPI
OpenSSL
OpenVX
OpenXLA
Oversubscription
PagedAttention
PCC
PCI
PCIe
@@ -293,7 +288,6 @@ PowerShell
PyPi
PyTorch
Qcycles
Qwen
RAII
RAS
RCCL
@@ -560,7 +554,6 @@ hipfort
hipify
hipsolver
hipsparse
hlist
hotspotting
hpc
hpp
@@ -584,7 +577,6 @@ intra
invariants
invocating
ipo
jax
kdb
latencies
libfabric
@@ -604,7 +596,6 @@ migraphx
miopen
miopengemm
mivisionx
mjx
mkdir
mlirmiopen
mtypes

View File

@@ -76,8 +76,8 @@ The Build time will reduce significantly if we limit the GPU Architecture/s agai
mkdir -p ~/WORKSPACE/ # Or any folder name other than WORKSPACE
cd ~/WORKSPACE/
export ROCM_VERSION=6.1.0 # 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-${ROCM_VERSION}.xml
export ROCM_VERSION=6.2.0
~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.2.x -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
~/bin/repo sync
# --------------------------------------
@@ -87,9 +87,11 @@ export ROCM_VERSION=6.1.0 # or 6.1.1 6.1.2
# 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
docker pull rocm/rocm-build-ubuntu-20.04:6.2
# Ubuntu22.04 built from ROCm/tools/rocm-build/docker/ubuntu22/Dockerfile
docker pull rocm/rocm-build-ubuntu-22.04:6.1
docker pull rocm/rocm-build-ubuntu-22.04:6.2
# Ubuntu24.04 built from ROCm/tools/rocm-build/docker/ubuntu24/Dockerfile
docker pull rocm/rocm-build-ubuntu-24.04:6.2
# Start docker container and mount the source code folder:
docker run -ti \
@@ -108,10 +110,16 @@ docker run -ti \
# Option 2: Install required packages into the host machine
# For ubuntu20.04 system
cd ROCm/tools/rocm-build/docker/ubuntu20
cp * /tmp && cd /tmp
bash install-prerequisites.sh
# For ubuntu22.04 system
cd ROCm/tools/rocm-build/docker/ubuntu22
cp * /tmp && cd /tmp
bash install-prerequisities.sh
# For ubuntu24.04 system
cd ROCm/tools/rocm-build/docker/ubuntu24
cp * /tmp && cd /tmp
bash install-prerequisites.sh
# --------------------------------------
# Step 3: Run build command line
@@ -138,13 +146,17 @@ make -f ROCm/tools/rocm-build/ROCm.mk T_rocblas
out/ubuntu-20.04/20.04/deb/
# Find built packages in ubuntu22.04:
out/ubuntu-22.04/22.04/deb/
# Find built packages in ubuntu24.04:
out/ubuntu-24.04/24.04/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/
# Find built logs in ubuntu24.04:
out/ubuntu-24.04/24.04/logs/
# All logs pertaining to failed components, end with .errrors extension.
out/ubuntu-22.04/22.04/logs/rocblas.errors # Example
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.

View File

@@ -433,7 +433,7 @@ links in the *Version* column to go to the detailed component changelogs.
class="fab fa-github fa-lg"></i></a></td>
</tr>
<tr>
<td><a href="https://github.com/ROCm/tensile/">Tensile</a></td>
<td><a href="https://rocm.docs.amd.com/projects/tensile/en/docs-6.2.0">Tensile</a></td>
<td>4.40.0&nbsp;&Rightarrow;&nbsp;<a href="#tensile-4-41-0">4.41.0</a></td>
<td><a href="https://github.com/ROCm/tensile/releases/tag/rocm-6.2.0"><i
class="fab fa-github fa-lg"></i></a></td>
@@ -524,7 +524,7 @@ links in the *Version* column to go to the detailed component changelogs.
class="fab fa-github fa-lg"></i></a></td>
</tr>
<tr>
<td><a href="https://rocm.docs.amd.com/projects/rocprofiler/en/docs-6.2.0/">ROCProfiler</a></td>
<td><a href="https://rocm.docs.amd.com/projects/ROCProfiler/en/docs-6.2.0">ROCProfiler</a></td>
<td>2.0.0&nbsp;&Rightarrow;&nbsp;<a href="#rocprofiler-2-0-0">2.0.0</a></td>
<td><a href="https://github.com/ROCm/ROCProfiler/releases/tag/rocm-6.2.0"><i
class="fab fa-github fa-lg"></i></a></td>
@@ -536,7 +536,7 @@ links in the *Version* column to go to the detailed component changelogs.
class="fab fa-github fa-lg"></i></a></td>
</tr>
<tr >
<td><a href="https://rocm.docs.amd.com/projects/roctracer/en/docs-6.2.0/">ROCTracer</a></td>
<td><a href="https://rocm.docs.amd.com/projects/ROCTracer/en/docs-6.2.0">ROCTracer</a></td>
<td>4.1.0</td>
<td><a href="https://github.com/ROCm/ROCTracer/releases/tag/rocm-6.2.0"><i
class="fab fa-github fa-lg"></i></a></td>
@@ -546,7 +546,7 @@ links in the *Version* column to go to the detailed component changelogs.
<tr>
<th rowspan="5"></th>
<th rowspan="5">Development</th>
<td><a href="https://rocm.docs.amd.com/projects/HIPIFY/en/docs-6.2.0/">HIPIFY</a></td>
<td><a href="https://rocm.docs.amd.com/projects/HIPIFY/docs-6.2.0">HIPIFY</a></td>
<td>17.0.0&nbsp;&Rightarrow;&nbsp;<a href="#hipify-18-0-0">18.0.0</a></td>
<td><a href="https://github.com/ROCm/HIPIFY/releases/tag/rocm-6.2.0"><i
class="fab fa-github fa-lg"></i></a></td>
@@ -558,7 +558,7 @@ links in the *Version* column to go to the detailed component changelogs.
class="fab fa-github fa-lg"></i></a></td>
</tr>
<tr>
<td><a href="https://rocm.docs.amd.com/projects/ROCmCMakeBuildTools/en/docs-6.2.0/">ROCm CMake</a></td>
<td><a href="https://rocm.docs.amd.com/projects/rocm-cmake/en/docs-6.2.0">ROCm CMake</a></td>
<td>0.12.0&nbsp;&Rightarrow;&nbsp;<a href="#rocm-cmake-0-13-0">0.13.0</a></td>
<td><a href="https://github.com/ROCm/rocm-cmake/releases/tag/rocm-6.2.0"><i
class="fab fa-github fa-lg"></i></a></td>
@@ -989,7 +989,7 @@ on GitHub for more information.
* `Zihintntl` extension version was upgraded to 1.0 and is no longer experimental.
* Intrinsics were added for `Zk*`, `Zbb`, and `Zbc`. See
[Scalar Bit Manipulation Extension Intrinsics](https://github.com/riscv-non-isa/riscv-c-api-doc/blob/main/src/c-api.adoc#scalar-bit-manipulation-extension-intrinsics) in the RISC-V C API specification.
[Scalar Bit Manipulation Extension Intrinsics](https://github.com/riscv-non-isa/riscv-c-api-doc/blob/master/riscv-c-api.md#scalar-bit-manipulation-extension-intrinsics) in the RISC-V C API specification.
* Default ABI with F but without D was changed to ilp32f for RV32 and to lp64f for RV64.

View File

@@ -1,75 +1,78 @@
<?xml version="1.0" encoding="UTF-8"?>
<manifest>
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
<default revision="refs/tags/rocm-6.2.0"
<default revision="refs/heads/amd-mainline"
remote="rocm-org"
sync-c="true"
sync-j="4" />
<!--list of projects for ROCm-->
<project name="ROCK-Kernel-Driver" />
<project name="ROCR-Runtime" />
<project name="ROCT-Thunk-Interface" />
<project name="amdsmi" />
<project name="omniperf" />
<project name="omnitrace" />
<project name="rdc" />
<project name="rocm_bandwidth_test" />
<project name="rocm_smi_lib" />
<project name="rocm-core" />
<project name="rocm-examples" />
<project name="rocminfo" />
<project name="rocprofiler" />
<project name="rocprofiler-register" />
<project name="rocprofiler-sdk" />
<project name="roctracer" />
<project name="ROCm" revision="refs/heads/develop" />
<project name="ROCK-Kernel-Driver" revision="refs/heads/master" />
<project name="ROCR-Runtime" revision="refs/heads/amd-master"/>
<project name="amdsmi" />
<project name="rdc" />
<project name="rocm_bandwidth_test" revision="refs/heads/master" />
<project name="rocm_smi_lib" />
<project name="rocm-core" revision="refs/heads/amd-master" />
<project name="rocm-examples" revision="refs/heads/develop"/>
<project name="rocminfo" revision="refs/heads/amd-master" />
<project name="rocprofiler" />
<project name="rocprofiler-register" />
<project name="rocprofiler-sdk" />
<project name="rocprofiler-compute" />
<project name="rocprofiler-systems" />
<project name="roctracer" />
<!--HIP Projects-->
<project name="HIP" />
<project name="hip-tests" />
<project name="HIP-Examples" />
<project name="HIPIFY" />
<project name="clr" />
<project name="hipother" />
<project name="hip-tests" />
<project name="HIPIFY" />
<project name="clr" />
<project name="hipother" />
<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
<project name="half" />
<project name="half" revision="refs/heads/rocm" />
<project name="llvm-project" />
<project name="SPIRV-LLVM-Translator" path="llvm-project/llvm/projects/SPIRV-LLVM-Translator" />
<!-- gdb projects -->
<project name="ROCdbgapi" />
<project name="ROCgdb" />
<project name="ROCdbgapi" />
<project name="ROCgdb" revision="refs/heads/amd-mainline-rocgdb-15"/>
<project name="rocr_debug_agent" />
<!-- ROCm Libraries -->
<project groups="mathlibs" name="AMDMIGraphX" />
<project groups="mathlibs" name="MIOpen" />
<project groups="mathlibs" name="MIVisionX" />
<project groups="mathlibs" name="ROCmValidationSuite" />
<project groups="mathlibs" name="Tensile" />
<project groups="mathlibs" name="composable_kernel" />
<project groups="mathlibs" name="hipBLAS" />
<project groups="mathlibs" name="hipBLASLt" />
<project groups="mathlibs" name="hipCUB" />
<project groups="mathlibs" name="hipFFT" />
<project groups="mathlibs" name="hipRAND" />
<project groups="mathlibs" name="hipSOLVER" />
<project groups="mathlibs" name="hipSPARSE" />
<project groups="mathlibs" name="hipSPARSELt" />
<project groups="mathlibs" name="hipTensor" />
<project groups="mathlibs" name="hipfort" />
<project groups="mathlibs" name="rccl" />
<project groups="mathlibs" name="rocAL" />
<project groups="mathlibs" name="rocALUTION" />
<project groups="mathlibs" name="rocBLAS" />
<project groups="mathlibs" name="rocDecode" />
<project groups="mathlibs" name="rocPyDecode" />
<project groups="mathlibs" name="rocFFT" />
<project groups="mathlibs" name="rocPRIM" />
<project groups="mathlibs" name="rocRAND" />
<project groups="mathlibs" name="rocSOLVER" />
<project groups="mathlibs" name="rocSPARSE" />
<project groups="mathlibs" name="rocThrust" />
<project groups="mathlibs" name="rocWMMA" />
<project groups="mathlibs" name="rocm-cmake" />
<project groups="mathlibs" name="rpp" />
<project groups="mathlibs" name="AMDMIGraphX" revision="refs/heads/master" />
<project groups="mathlibs" name="MIOpen" revision="refs/heads/amd-master" />
<project groups="mathlibs" name="MIVisionX" revision="refs/heads/master" />
<project groups="mathlibs" name="ROCmValidationSuite" revision="refs/heads/master" />
<project groups="mathlibs" name="Tensile" revision="refs/heads/master" />
<project groups="mathlibs" name="composable_kernel" revision="refs/heads/amd-master"/>
<project groups="mathlibs" name="hipBLAS-common" revision="refs/heads/mainline" />
<project groups="mathlibs" name="hipBLAS" revision="refs/heads/mainline" />
<project groups="mathlibs" name="hipBLASLt" revision="refs/heads/mainline" />
<project groups="mathlibs" name="hipCUB" revision="refs/heads/mainline" />
<project groups="mathlibs" name="hipFFT" revision="refs/heads/mainline" />
<project groups="mathlibs" name="hipRAND" revision="refs/heads/mainline" />
<project groups="mathlibs" name="hipSOLVER" revision="refs/heads/mainline" />
<project groups="mathlibs" name="hipSPARSE" revision="refs/heads/mainline" />
<project groups="mathlibs" name="hipSPARSELt" revision="refs/heads/mainline" />
<project groups="mathlibs" name="hipTensor" revision="refs/heads/mainline" />
<project groups="mathlibs" name="hipfort" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rccl" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rocAL" revision="refs/heads/master" />
<project groups="mathlibs" name="rocALUTION" revision="refs/heads/mainline"/>
<project groups="mathlibs" name="rocBLAS" revision="refs/heads/mainline"/>
<project groups="mathlibs" name="rocDecode" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rocJPEG" revision="refs/heads/mainline"/>
<project groups="mathlibs" name="rocPyDecode" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rocFFT" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rocPRIM" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rocRAND" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rocSOLVER" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rocSPARSE" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rocThrust" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rocWMMA" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rocm-cmake" revision="refs/heads/mainline" />
<project groups="mathlibs" name="rpp" revision="refs/heads/master" />
<project groups="mathlibs" name="TransferBench" />
<!-- Projects for OpenMP-Extras -->
<project name="aomp" path="openmp-extras/aomp" />
<project name="aomp-extras" path="openmp-extras/aomp-extras" />
<project name="flang" path="openmp-extras/flang" />
<project name="aomp" path="openmp-extras/aomp" />
<project name="aomp-extras" path="openmp-extras/aomp-extras" />
<project name="flang" path="openmp-extras/flang" />
</manifest>

View File

@@ -17,7 +17,7 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
:stub-columns: 1
:doc:`Operating Systems <rocm-install-on-linux:reference/system-requirements>`, "Ubuntu 24.04","",""
,"Ubuntu 22.04.5 [#Ubuntu220405]_, 22.04.4","Ubuntu 22.04.5 [#Ubuntu220405]_, 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3"
,"Ubuntu 22.04.5 [#Ubuntu220405]_, 22.04.4","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, 9.3","RHEL 9.4 [#red-hat94]_, 9.3, 9.2","RHEL 9.3, 9.2"
,"RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
@@ -39,7 +39,7 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
,,,
FRAMEWORK SUPPORT,".. _framework-support-compatibility-matrix:",,
:doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>`,"2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
:doc:`TensorFlow <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1"
:doc:`TensorFlow <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"2.16.1, 2.15.1, 2.14.1","2.15, 2.14, 2.13","2.14, 2.13, 2.12"
:doc:`JAX <rocm-install-on-linux:install/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
,,,
@@ -134,7 +134,7 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
.. rubric:: Footnotes
.. [#Ubuntu220405] Preview support of Ubuntu 22.04.5 only
.. [#red-hat94] **For ROCm 6.1** - RHEL 9.4 is supported only on AMD Instinct MI300A.
.. [#red-hat94] RHEL 9.4 is supported only on AMD Instinct MI300A.
.. [#oracle89] Oracle Linux is supported only on AMD Instinct MI300X.
.. [#mi300_620] **For ROCm 6.2.0** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
.. [#mi300_612] **For ROCm 6.1.2** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4 and Oracle Linux.
@@ -161,14 +161,14 @@ Expand for full historical view of:
.. csv-table::
:file: ../data/reference/compatibility-matrix-historical-6.0.csv
:widths: 20,10,10,10,10,10,10,10
:widths: 20,10,10,10,10,10,10
:header-rows: 1
:stub-columns: 1
.. rubric:: Footnotes
.. [#Ubuntu220405-past-60] Preview support of Ubuntu 22.04.5 only
.. [#red-hat94-past-60] **For ROCm 6.1** - RHEL 9.4 is supported only on AMD Instinct MI300A.
.. [#red-hat94-past-60] RHEL 9.4 is supported only on AMD Instinct MI300A.
.. [#oracle89-past-60] Oracle Linux is supported only on AMD Instinct MI300X.
.. [#mi300_620-past-60] **For ROCm 6.2.0** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
.. [#mi300_612-past-60] **For ROCm 6.1.2** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4 and Oracle Linux.

View File

@@ -410,7 +410,7 @@ description, refer to the corresponding library data type support page.
- ❌/❌
- ❌/❌
*
- rocRAND (:doc:`details <rocrand:api-reference/data-type-support>`)
- rocRAND (:doc:`details <rocrand:data-type-support>`)
- -/✅
- -/✅
- -/✅

View File

@@ -82,7 +82,6 @@ article_pages = [
"file": "how-to/llm-fine-tuning-optimization/profiling-and-debugging",
"os": ["linux"],
},
{"file": "how-to/performance-validation/mi300x/vllm-benchmark", "os": ["linux"]},
{"file": "how-to/system-optimization/index", "os": ["linux"]},
{"file": "how-to/system-optimization/mi300x", "os": ["linux"]},
{"file": "how-to/system-optimization/mi200", "os": ["linux"]},

View File

@@ -1,114 +1,114 @@
ROCm Version,6.2.0, 6.1.5, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
:doc:`Operating Systems <rocm-install-on-linux:reference/system-requirements>`,Ubuntu 24.04,,,,,,
,"Ubuntu 22.04.5 [#Ubuntu220405-past-60]_, 22.04.4","Ubuntu 22.04.5 [#Ubuntu220405-past-60]_,22.04.4, 22.04.3","Ubuntu 22.04.5 [#Ubuntu220405-past-60]_,22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","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","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
,"RHEL 9.4, 9.3","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
,"RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
,"SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
,,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,,,
,.. _architecture-support-compatibility-matrix-past-60:,,,,,,
:doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3
,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2
,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA
,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3
,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
,.. _gpu-support-compatibility-matrix-past-60:,,,,,,
:doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
,,,,,,,
FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,
:doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>`,"2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
:doc:`TensorFlow <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
:doc:`JAX <rocm-install-on-linux:install/3rd-party/jax-install>`,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
`ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
,,,,,,,
THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix-past-60:,,,,,,
`UCC <https://github.com/ROCm/ucc>`_,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.2.0,>=1.2.0
`UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
,,,,,,,
THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix-past-60:,,,,,,
Thrust,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
CUB,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
,,,,,,,
ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix-past-60:,,,,,,
:doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
:doc:`MIGraphX <amdmigraphx:index>`,2.10.0,2.9.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
:doc:`MIOpen <miopen:index>`,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
:doc:`MIVisionX <mivisionx:index>`,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
:doc:`RPP <rpp:index>`,1.8.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
:doc:`rocAL <rocal:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
:doc:`rocDecode <rocdecode:index>`,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
:doc:`rocPyDecode <rocpydecode:index>`,0.1.0,N/A,N/A,N/A,N/A,N/A,N/A
,,,,,,,
COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,
:doc:`RCCL <rccl:index>`,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
,,,,,,,
MATH LIBS,.. _mathlibs-support-compatibility-matrix-past-60:,,,,,,
`half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0
:doc:`hipBLAS <hipblas:index>`,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
:doc:`hipBLASLt <hipblaslt:index>`,0.8.0,0.7.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
:doc:`hipFFT <hipfft:index>`,1.0.14,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
:doc:`hipFORT <hipfort:index>`,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
:doc:`hipRAND <hiprand:index>`,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
:doc:`hipSOLVER <hipsolver:index>`,2.2.0,2.1.1,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
:doc:`hipSPARSE <hipsparse:index>`,3.1.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
:doc:`hipSPARSELt <hipsparselt:index>`,0.2.1,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
:doc:`rocALUTION <rocalution:index>`,3.2.0,3.1.1,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
:doc:`rocBLAS <rocblas:index>`,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
:doc:`rocFFT <rocfft:index>`,1.0.28,1.0.27,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
:doc:`rocRAND <rocrand:index>`,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
:doc:`rocSOLVER <rocsolver:index>`,3.26.0,3.25.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
:doc:`rocSPARSE <rocsparse:index>`,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
:doc:`rocWMMA <rocwmma:index>`,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
`Tensile <https://github.com/ROCm/Tensile>`_,4.40.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
,,,,,,,
PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,
:doc:`hipCUB <hipcub:index>`,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
:doc:`hipTensor <hiptensor:index>`,1.3.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
:doc:`rocPRIM <rocprim:index>`,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
:doc:`rocThrust <rocthrust:index>`,3.0.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
,,,,,,,
SUPPORT LIBS,,,,,,,
`hipother <https://github.com/ROCm/hipother>`_,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
`rocm-core <https://github.com/ROCm/rocm-core>`_,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
`ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
,,,,,,,
SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,
:doc:`AMD SMI <amdsmi:index>`,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
:doc:`ROCm Data Center Tool <rdc:index>`,1.0.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
:doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
:doc:`ROCm SMI <rocm_smi_lib:index>`,7.3.0,7.2.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
:doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.2.0,rocm-6.1.5,rocm-6.1.2,rocm-6.1.1,rocm-6.1.0,rocm-6.0.2,rocm-6.0.0
,,,,,,,
PERFORMANCE TOOLS,,,,,,,
:doc:`Omniperf <omniperf:index>`,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
:doc:`Omnitrace <omnitrace:index>`,1.11.2,N/A,N/A,N/A,N/A,N/A,N/A
:doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
:doc:`ROCProfiler <rocprofiler:index>`,2.0.60200,2.0.60105,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
:doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.4.0,N/A,N/A,N/A,N/A,N/A,N/A
:doc:`ROCTracer <roctracer:index>`,4.1.60200,4.1.60105,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
,,,,,,,
DEVELOPMENT TOOLS,,,,,,,
:doc:`HIPIFY <hipify:index>`,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
:doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.13.0,0.12.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
:doc:`ROCdbgapi <rocdbgapi:index>`,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
:doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,14.2.0,14.1.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
`rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.3.0,0.3.0,0.3.0,0.3.0,N/A,N/A
:doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
,,,,,,,
COMPILERS,.. _compilers-support-compatibility-matrix-past-60:,,,,,,
`clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
:doc:`hipCC <hipcc:index>`,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
`Flang <https://github.com/ROCm/flang>`_,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
:doc:`llvm-project <llvm-project:index>`,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
`OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
,,,,,,,
RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,
:doc:`AMD CLR <hip:understand/amd_clr>`,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
:doc:`HIP <hip:index>`,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
`OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0
:doc:`ROCR-Runtime <rocr-runtime:index>`,1.13.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0
ROCm Version,6.2.0, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
:doc:`Operating Systems <rocm-install-on-linux:reference/system-requirements>`,Ubuntu 24.04,,,,,
,"Ubuntu 22.04.5 [#Ubuntu220405-past-60]_, 22.04.4","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","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","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
,"RHEL 9.4, 9.3","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
,"RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
,"SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,,,
,".. _architecture-support-compatibility-matrix-past-60:",,,,,
:doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3
,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2
,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA
,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3
,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
,".. _gpu-support-compatibility-matrix-past-60:",,,,,
:doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
,,,,,,
FRAMEWORK SUPPORT,".. _framework-support-compatibility-matrix-past-60:",,,,,
:doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>`,"2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
:doc:`TensorFlow <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"2.16.1, 2.15.1, 2.14.1","2.15, 2.14, 2.13","2.15, 2.14, 2.13","2.15, 2.14, 2.13","2.14, 2.13, 2.12","2.14, 2.13, 2.12"
:doc:`JAX <rocm-install-on-linux:install/3rd-party/jax-install>`,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
`ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
,,,,,,
THIRD PARTY COMMS,".. _thirdpartycomms-support-compatibility-matrix-past-60:",,,,,
`UCC <https://github.com/ROCm/ucc>`_,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.2.0,>=1.2.0
`UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
,,,,,,
THIRD PARTY ALGORITHM,".. _thirdpartyalgorithm-support-compatibility-matrix-past-60:",,,,,
Thrust,2.2.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
CUB,2.2.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
,,,,,,
ML & COMPUTER VISION,".. _mllibs-support-compatibility-matrix-past-60:",,,,,
:doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
:doc:`MIGraphX <amdmigraphx:index>`,2.10.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
:doc:`MIOpen <miopen:index>`,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
:doc:`MIVisionX <mivisionx:index>`,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
:doc:`RPP <rpp:index>`,1.8.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
:doc:`rocAL <rocal:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
:doc:`rocDecode <rocdecode:index>`,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
:doc:`rocPyDecode <rocpydecode:index>`,0.1.0,N/A,N/A,N/A,N/A,N/A
,,,,,,
COMMUNICATION,".. _commlibs-support-compatibility-matrix-past-60:",,,,,
:doc:`RCCL <rccl:index>`,2.20.5,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
,,,,,,
MATH LIBS,".. _mathlibs-support-compatibility-matrix-past-60:",,,,,
`half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0
:doc:`hipBLAS <hipblas:index>`,2.2.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
:doc:`hipBLASLt <hipblaslt:index>`,0.8.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
:doc:`hipFFT <hipfft:index>`,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
:doc:`hipFORT <hipfort:index>`,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
:doc:`hipRAND <hiprand:index>`,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
:doc:`hipSOLVER <hipsolver:index>`,2.2.0,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
:doc:`hipSPARSE <hipsparse:index>`,3.1.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
:doc:`hipSPARSELt <hipsparselt:index>`,0.2.1,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
:doc:`rocALUTION <rocalution:index>`,3.2.0,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
:doc:`rocBLAS <rocblas:index>`,4.2.0,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
:doc:`rocFFT <rocfft:index>`,1.0.28,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
:doc:`rocRAND <rocrand:index>`,3.1.0,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
:doc:`rocSOLVER <rocsolver:index>`,3.26.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
:doc:`rocSPARSE <rocsparse:index>`,3.2.0,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
:doc:`rocWMMA <rocwmma:index>`,1.5.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
`Tensile <https://github.com/ROCm/Tensile>`_,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
,,,,,,
PRIMITIVES,".. _primitivelibs-support-compatibility-matrix-past-60:",,,,,
:doc:`hipCUB <hipcub:index>`,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
:doc:`hipTensor <hiptensor:index>`,1.3.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
:doc:`rocPRIM <rocprim:index>`,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
:doc:`rocThrust <rocthrust:index>`,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
,,,,,,
SUPPORT LIBS,,,,,,
`hipother <https://github.com/ROCm/hipother>`_,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
`rocm-core <https://github.com/ROCm/rocm-core>`_,6.2.0,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
`ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
,,,,,,
SYSTEM MGMT TOOLS,".. _tools-support-compatibility-matrix-past-60:",,,,,
:doc:`AMD SMI <amdsmi:index>`,24.6.2,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
:doc:`ROCm Data Center Tool <rdc:index>`,1.0.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
:doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
:doc:`ROCm SMI <rocm_smi_lib:index>`,7.3.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
:doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,rocm-6.2.0,rocm-6.1.2,rocm-6.1.1,rocm-6.1.0,rocm-6.0.2,rocm-6.0.0
,,,,,,
PERFORMANCE TOOLS,,,,,,
:doc:`Omniperf <omniperf:index>`,2.0.1,N/A,N/A,N/A,N/A,N/A
:doc:`Omnitrace <omnitrace:index>`,1.11.2,N/A,N/A,N/A,N/A,N/A
:doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
:doc:`ROCProfiler <rocprofiler:index>`,2.0.60200,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
:doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.4.0,N/A,N/A,N/A,N/A,N/A
:doc:`ROCTracer <roctracer:index>`,4.1.60200,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
,,,,,,
DEVELOPMENT TOOLS,,,,,,
:doc:`HIPIFY <hipify:index>`,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
:doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.13.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
:doc:`ROCdbgapi <rocdbgapi:index>`,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
:doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,14.2.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
`rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.3.0,0.3.0,0.3.0,N/A,N/A
:doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
,,,,,,
COMPILERS,".. _compilers-support-compatibility-matrix-past-60:",,,,,
`clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
:doc:`hipCC <hipcc:index>`,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
`Flang <https://github.com/ROCm/flang>`_,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
:doc:`llvm-project <llvm-project:index>`,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
`OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
,,,,,,
RUNTIMES,".. _runtime-support-compatibility-matrix-past-60:",,,,,
:doc:`AMD CLR <hip:understand/amd_clr>`,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
:doc:`HIP <hip:index>`,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
`OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0
:doc:`ROCR-Runtime <rocr-runtime:index>`,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0
1 ROCm Version 6.2.0 6.1.5 6.1.2 6.1.1 6.1.0 6.0.2 6.0.0
2 :doc:`Operating Systems <rocm-install-on-linux:reference/system-requirements>` Ubuntu 24.04
3 Ubuntu 22.04.5 [#Ubuntu220405-past-60]_, 22.04.4 Ubuntu 22.04.5 [#Ubuntu220405-past-60]_,22.04.4, 22.04.3 Ubuntu 22.04.5 [#Ubuntu220405-past-60]_,22.04.4, 22.04.3 Ubuntu 22.04.4, 22.04.3 Ubuntu 22.04.4, 22.04.3 Ubuntu 22.04.4, 22.04.3 Ubuntu 22.04.4, 22.04.3 Ubuntu 22.04.4, 22.04.3
4 Ubuntu 20.04.6, 20.04.5 Ubuntu 20.04.6, 20.04.5 Ubuntu 20.04.6, 20.04.5 Ubuntu 20.04.6, 20.04.5 Ubuntu 20.04.6, 20.04.5 Ubuntu 20.04.6, 20.04.5
5 RHEL 9.4, 9.3 RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2 RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2 RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2 RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2 RHEL 9.3, 9.2 RHEL 9.3, 9.2
6 RHEL 8.10, 8.9 RHEL 8.9, 8.8 RHEL 8.9, 8.8 RHEL 8.9, 8.8 RHEL 8.9, 8.8 RHEL 8.9, 8.8 RHEL 8.9, 8.8
7 SLES 15 SP6, SP5 SLES 15 SP5, SP4 SLES 15 SP5, SP4 SLES 15 SP5, SP4 SLES 15 SP5, SP4 SLES 15 SP5, SP4 SLES 15 SP5, SP4
8 CentOS 7.9 CentOS 7.9 CentOS 7.9 CentOS 7.9 CentOS 7.9
9 Oracle Linux 8.9 [#oracle89-past-60]_ Oracle Linux 8.9 [#oracle89-past-60]_ Oracle Linux 8.9 [#oracle89-past-60]_ Oracle Linux 8.9 [#oracle89-past-60]_
10 .. _architecture-support-compatibility-matrix-past-60:
11 :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>` CDNA3 CDNA3 CDNA3 CDNA3 CDNA3 CDNA3 CDNA3
12 CDNA2 CDNA2 CDNA2 CDNA2 CDNA2 CDNA2 CDNA2
13 CDNA CDNA CDNA CDNA CDNA CDNA CDNA
14 RDNA3 RDNA3 RDNA3 RDNA3 RDNA3 RDNA3 RDNA3
15 RDNA2 RDNA2 RDNA2 RDNA2 RDNA2 RDNA2 RDNA2
16 .. _gpu-support-compatibility-matrix-past-60:
17 :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>` gfx1100 gfx1100 gfx1100 gfx1100 gfx1100 gfx1100 gfx1100
18 gfx1030 gfx1030 gfx1030 gfx1030 gfx1030 gfx1030 gfx1030
19 gfx942 [#mi300_620-past-60]_ gfx942 [#mi300_612-past-60]_ gfx942 [#mi300_612-past-60]_ gfx942 [#mi300_611-past-60]_ gfx942 [#mi300_610-past-60]_ gfx942 [#mi300_602-past-60]_ gfx942 [#mi300_600-past-60]_
20 gfx90a gfx90a gfx90a gfx90a gfx90a gfx90a gfx90a
21 gfx908 gfx908 gfx908 gfx908 gfx908 gfx908 gfx908
22
23 FRAMEWORK SUPPORT .. _framework-support-compatibility-matrix-past-60:
24 :doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>` 2.3, 2.2, 2.1, 2.0, 1.13 2.1, 2.0, 1.13 2.1, 2.0, 1.13 2.1, 2.0, 1.13 2.1, 2.0, 1.13 2.1, 2.0, 1.13 2.1, 2.0, 1.13
25 :doc:`TensorFlow <rocm-install-on-linux:install/3rd-party/tensorflow-install>` 2.16.1, 2.15.1, 2.14.1 2.15.0, 2.14.0, 2.13.1 2.15.0, 2.14.0, 2.13.1 2.15, 2.14, 2.13 2.15.0, 2.14.0, 2.13.1 2.15, 2.14, 2.13 2.15.0, 2.14.0, 2.13.1 2.15, 2.14, 2.13 2.14.0, 2.13.1, 2.12.1 2.14, 2.13, 2.12 2.14.0, 2.13.1, 2.12.1 2.14, 2.13, 2.12
26 :doc:`JAX <rocm-install-on-linux:install/3rd-party/jax-install>` 0.4.26 0.4.26 0.4.26 0.4.26 0.4.26 0.4.26 0.4.26
27 `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_ 1.17.3 1.17.3 1.17.3 1.17.3 1.17.3 1.14.1 1.14.1
28
29 THIRD PARTY COMMS .. _thirdpartycomms-support-compatibility-matrix-past-60:
30 `UCC <https://github.com/ROCm/ucc>`_ >=1.3.0 >=1.3.0 >=1.3.0 >=1.3.0 >=1.3.0 >=1.2.0 >=1.2.0
31 `UCX <https://github.com/ROCm/ucx>`_ >=1.15.0 >=1.14.1 >=1.14.1 >=1.14.1 >=1.14.1 >=1.14.1 >=1.14.1
32
33 THIRD PARTY ALGORITHM .. _thirdpartyalgorithm-support-compatibility-matrix-past-60:
34 Thrust 2.2.0 2.1.0 2.1.0 2.1.0 2.1.0 2.0.1 2.0.1
35 CUB 2.2.0 2.1.0 2.1.0 2.1.0 2.1.0 2.0.1 2.0.1
36
37 ML & COMPUTER VISION .. _mllibs-support-compatibility-matrix-past-60:
38 :doc:`Composable Kernel <composable_kernel:index>` 1.1.0 1.1.0 1.1.0 1.1.0 1.1.0 1.1.0 1.1.0
39 :doc:`MIGraphX <amdmigraphx:index>` 2.10.0 2.9.0 2.9.0 2.9.0 2.9.0 2.8.0 2.8.0
40 :doc:`MIOpen <miopen:index>` 3.2.0 3.1.0 3.1.0 3.1.0 3.1.0 3.0.0 3.0.0
41 :doc:`MIVisionX <mivisionx:index>` 3.0.0 2.5.0 2.5.0 2.5.0 2.5.0 2.5.0 2.5.0
42 :doc:`RPP <rpp:index>` 1.8.0 1.5.0 1.5.0 1.5.0 1.5.0 1.4.0 1.4.0
43 :doc:`rocAL <rocal:index>` 1.0.0 1.0.0 1.0.0 1.0.0 1.0.0 1.0.0 1.0.0
44 :doc:`rocDecode <rocdecode:index>` 0.6.0 0.6.0 0.6.0 0.5.0 0.5.0 N/A N/A
45 :doc:`rocPyDecode <rocpydecode:index>` 0.1.0 N/A N/A N/A N/A N/A N/A
46
47 COMMUNICATION .. _commlibs-support-compatibility-matrix-past-60:
48 :doc:`RCCL <rccl:index>` 2.20.5 2.18.6 2.18.6 2.18.6 2.18.6 2.18.3 2.18.3
49
50 MATH LIBS .. _mathlibs-support-compatibility-matrix-past-60:
51 `half <https://github.com/ROCm/half>`_ 1.12.0 1.12.0 1.12.0 1.12.0 1.12.0 1.12.0 1.12.0
52 :doc:`hipBLAS <hipblas:index>` 2.2.0 2.1.0 2.1.0 2.1.0 2.1.0 2.0.0 2.0.0
53 :doc:`hipBLASLt <hipblaslt:index>` 0.8.0 0.7.0 0.7.0 0.7.0 0.7.0 0.6.0 0.6.0
54 :doc:`hipFFT <hipfft:index>` 1.0.14 1.0.14 1.0.14 1.0.14 1.0.14 1.0.13 1.0.13
55 :doc:`hipFORT <hipfort:index>` 0.4.0 0.4.0 0.4.0 0.4.0 0.4.0 0.4.0 0.4.0
56 :doc:`hipRAND <hiprand:index>` 2.11.0 2.10.16 2.10.16 2.10.16 2.10.16 2.10.16 2.10.16
57 :doc:`hipSOLVER <hipsolver:index>` 2.2.0 2.1.1 2.1.1 2.1.1 2.1.0 2.0.0 2.0.0
58 :doc:`hipSPARSE <hipsparse:index>` 3.1.1 3.0.1 3.0.1 3.0.1 3.0.1 3.0.0 3.0.0
59 :doc:`hipSPARSELt <hipsparselt:index>` 0.2.1 0.2.0 0.2.0 0.1.0 0.1.0 0.1.0 0.1.0
60 :doc:`rocALUTION <rocalution:index>` 3.2.0 3.1.1 3.1.1 3.1.1 3.1.1 3.0.3 3.0.3
61 :doc:`rocBLAS <rocblas:index>` 4.2.0 4.1.2 4.1.2 4.1.0 4.1.0 4.0.0 4.0.0
62 :doc:`rocFFT <rocfft:index>` 1.0.28 1.0.27 1.0.27 1.0.27 1.0.26 1.0.25 1.0.23
63 :doc:`rocRAND <rocrand:index>` 3.1.0 3.0.1 3.0.1 3.0.1 3.0.1 3.0.0 2.10.17
64 :doc:`rocSOLVER <rocsolver:index>` 3.26.0 3.25.0 3.25.0 3.25.0 3.25.0 3.24.0 3.24.0
65 :doc:`rocSPARSE <rocsparse:index>` 3.2.0 3.1.2 3.1.2 3.1.2 3.1.2 3.0.2 3.0.2
66 :doc:`rocWMMA <rocwmma:index>` 1.5.0 1.4.0 1.4.0 1.4.0 1.4.0 1.3.0 1.3.0
67 `Tensile <https://github.com/ROCm/Tensile>`_ 4.40.0 4.40.0 4.40.0 4.40.0 4.40.0 4.39.0 4.39.0
68
69 PRIMITIVES .. _primitivelibs-support-compatibility-matrix-past-60:
70 :doc:`hipCUB <hipcub:index>` 3.2.0 3.1.0 3.1.0 3.1.0 3.1.0 3.0.0 3.0.0
71 :doc:`hipTensor <hiptensor:index>` 1.3.0 1.2.0 1.2.0 1.2.0 1.2.0 1.1.0 1.1.0
72 :doc:`rocPRIM <rocprim:index>` 3.2.0 3.1.0 3.1.0 3.1.0 3.1.0 3.0.0 3.0.0
73 :doc:`rocThrust <rocthrust:index>` 3.0.1 3.0.1 3.0.1 3.0.1 3.0.1 3.0.0 3.0.0
74
75 SUPPORT LIBS
76 `hipother <https://github.com/ROCm/hipother>`_ 6.2.41133 6.1.40093 6.1.40093 6.1.40092 6.1.40091 6.1.32831 6.1.32830
77 `rocm-core <https://github.com/ROCm/rocm-core>`_ 6.2.0 6.1.5 6.1.2 6.1.1 6.1.0 6.0.2 6.0.0
78 `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_ 20240607.1.4246 20240125.5.08 20240125.5.08 20240125.5.08 20240125.3.30 20231016.2.245 20231016.2.245
79
80 SYSTEM MGMT TOOLS .. _tools-support-compatibility-matrix-past-60:
81 :doc:`AMD SMI <amdsmi:index>` 24.6.2 24.5.1 24.5.1 24.5.1 24.4.1 23.4.2 23.4.2
82 :doc:`ROCm Data Center Tool <rdc:index>` 1.0.0 0.3.0 0.3.0 0.3.0 0.3.0 0.3.0 0.3.0
83 :doc:`rocminfo <rocminfo:index>` 1.0.0 1.0.0 1.0.0 1.0.0 1.0.0 1.0.0 1.0.0
84 :doc:`ROCm SMI <rocm_smi_lib:index>` 7.3.0 7.2.0 7.2.0 7.0.0 7.0.0 6.0.2 6.0.0
85 :doc:`ROCm Validation Suite <rocmvalidationsuite:index>` rocm-6.2.0 rocm-6.1.5 rocm-6.1.2 rocm-6.1.1 rocm-6.1.0 rocm-6.0.2 rocm-6.0.0
86
87 PERFORMANCE TOOLS
88 :doc:`Omniperf <omniperf:index>` 2.0.1 N/A N/A N/A N/A N/A N/A
89 :doc:`Omnitrace <omnitrace:index>` 1.11.2 N/A N/A N/A N/A N/A N/A
90 :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>` 1.4.0 1.4.0 1.4.0 1.4.0 1.4.0 1.4.0 1.4.0
91 :doc:`ROCProfiler <rocprofiler:index>` 2.0.60200 2.0.60105 2.0.60102 2.0.60101 2.0.60100 2.0.60002 2.0.60000
92 :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>` 0.4.0 N/A N/A N/A N/A N/A N/A
93 :doc:`ROCTracer <roctracer:index>` 4.1.60200 4.1.60105 4.1.60102 4.1.60101 4.1.60100 4.1.60002 4.1.60000
94
95 DEVELOPMENT TOOLS
96 :doc:`HIPIFY <hipify:index>` 18.0.0.24232 17.0.0.24193 17.0.0.24193 17.0.0.24154 17.0.0.24103 17.0.0.24012 17.0.0.23483
97 :doc:`ROCm CMake <rocmcmakebuildtools:index>` 0.13.0 0.12.0 0.12.0 0.12.0 0.12.0 0.11.0 0.11.0
98 :doc:`ROCdbgapi <rocdbgapi:index>` 0.76.0 0.71.0 0.71.0 0.71.0 0.71.0 0.71.0 0.71.0
99 :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>` 14.2.0 14.1.0 14.1.0 14.1.0 14.1.0 13.2.0 13.2.0
100 `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_ 0.4.0 0.3.0 0.3.0 0.3.0 0.3.0 N/A N/A
101 :doc:`ROCr Debug Agent <rocr_debug_agent:index>` 2.0.3 2.0.3 2.0.3 2.0.3 2.0.3 2.0.3 2.0.3
102
103 COMPILERS .. _compilers-support-compatibility-matrix-past-60:
104 `clang-ocl <https://github.com/ROCm/clang-ocl>`_ N/A 0.5.0 0.5.0 0.5.0 0.5.0 0.5.0 0.5.0
105 :doc:`hipCC <hipcc:index>` 1.1.1 1.0.0 1.0.0 1.0.0 1.0.0 1.0.0 1.0.0
106 `Flang <https://github.com/ROCm/flang>`_ 18.0.0.24232 17.0.0.24193 17.0.0.24193 17.0.0.24154 17.0.0.24103 17.0.0.24012 17.0.0.23483
107 :doc:`llvm-project <llvm-project:index>` 18.0.0.24232 17.0.0.24193 17.0.0.24193 17.0.0.24154 17.0.0.24103 17.0.0.24012 17.0.0.23483
108 `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_ 18.0.0.24232 17.0.0.24193 17.0.0.24193 17.0.0.24154 17.0.0.24103 17.0.0.24012 17.0.0.23483
109
110 RUNTIMES .. _runtime-support-compatibility-matrix-past-60:
111 :doc:`AMD CLR <hip:understand/amd_clr>` 6.2.41133 6.1.40093 6.1.40093 6.1.40092 6.1.40091 6.1.32831 6.1.32830
112 :doc:`HIP <hip:index>` 6.2.41133 6.1.40093 6.1.40093 6.1.40092 6.1.40091 6.1.32831 6.1.32830
113 `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_ 2.0.0 2.0.0 2.0.0 2.0.0 2.0.0 2.0.0 2.0.0
114 :doc:`ROCR-Runtime <rocr-runtime:index>` 1.13.0 1.13.0 1.13.0 1.13.0 1.13.0 1.12.0 1.12.0

View File

@@ -16,7 +16,7 @@ This section discusses how to implement `vLLM <https://docs.vllm.ai/en/latest>`_
vLLM inference
==============
vLLM is renowned for its PagedAttention algorithm that can reduce memory consumption and increase throughput thanks to
vLLM is renowned for its paged attention algorithm that can reduce memory consumption and increase throughput thanks to
its paging scheme. Instead of allocating GPU high-bandwidth memory (HBM) for the maximum output token lengths of the
models, the paged attention of vLLM allocates GPU HBM dynamically for its actual decoding lengths. This paged attention
is also effective when multiple requests share the same key and value contents for a large value of beam search or
@@ -137,10 +137,6 @@ Installing vLLM
Refer to :ref:`mi300x-vllm-optimization` for performance optimization tips.
ROCm provides a prebuilt optimized Docker image for validating the performance of LLM inference with vLLM
on the MI300X accelerator. The Docker image includes ROCm, vLLM, PyTorch, and tuning files in the CSV
format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
.. _fine-tuning-llms-tgi:
Hugging Face TGI

View File

@@ -189,9 +189,6 @@ Installing bitsandbytes
# Use -DBNB_ROCM_ARCH to specify target GPU arch
cmake -DBNB_ROCM_ARCH="gfx942" -DCOMPUTE_BACKEND=hip -S .
# Compile the project
make
# Install
python setup.py install
@@ -222,11 +219,12 @@ To get started with bitsandbytes primitives, use the following code as reference
Using bitsandbytes with Hugging Face Transformers
-------------------------------------------------
To load a Transformers model in 4-bit, set ``load_in_4bit=true`` in ``BitsAndBytesConfig``.
To load a Transformers model in 4-bit, set ``load_int_4bt=true`` in ``BitsAndBytesConfig``.
.. code-block:: python
from transformers import AutoModelForCausalLM, BitsAndBytesConfig
from transformers import AutoModelForCausalLM
from bitsandbytes import BitsAndBytesConfig
base_model_name = "NousResearch/Llama-2-7b-hf"
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
@@ -242,7 +240,8 @@ To load a model in 8-bit for inference, use the ``load_in_8bit`` option.
.. code-block:: python
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
from bitsandbytes import BitsAndBytesConfig
base_model_name = "NousResearch/Llama-2-7b-hf"

View File

@@ -1,334 +0,0 @@
.. meta::
:description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the unified
ROCm Docker image.
:keywords: model, MAD, automation, dashboarding, validate
***********************************************************
LLM inference performance validation on AMD Instinct MI300X
***********************************************************
.. _vllm-benchmark-unified-docker:
The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
a prebuilt, optimized environment designed for validating large language model
(LLM) inference performance on the AMD Instinct™ MI300X accelerator. This
ROCm vLLM Docker image integrates vLLM and PyTorch tailored specifically for the
MI300X accelerator and includes the following components:
* `ROCm 6.2.0 <https://github.com/ROCm/ROCm>`_
* `vLLM 0.4.3 <https://docs.vllm.ai/en/latest>`_
* `PyTorch 2.4.0 <https://github.com/pytorch/pytorch>`_
* Tuning files (in CSV format)
With this Docker image, you can quickly validate the expected inference
performance numbers on the MI300X accelerator. This topic also provides tips on
optimizing performance with popular AI models.
.. _vllm-benchmark-vllm:
.. note::
vLLM is a toolkit and library for LLM inference and
serving. It deploys the PagedAttention algorithm, which reduces memory
consumption and increases throughput by leveraging dynamic key and value
allocation in GPU memory. vLLM also incorporates many LLM acceleration
and quantization algorithms. In addition, AMD implements high-performance
custom kernels and modules in vLLM to enhance performance further. See
:ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for more
information.
Getting started
===============
Use the following procedures to reproduce the benchmark results on an
MI300X accelerator with the prebuilt vLLM Docker image.
.. _vllm-benchmark-get-started:
1. Disable NUMA auto-balancing.
To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
might hang until the periodic balancing is finalized. For more information,
see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
.. code-block:: shell
# disable automatic NUMA balancing
sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
# check if NUMA balancing is disabled (returns 0 if disabled)
cat /proc/sys/kernel/numa_balancing
0
2. Download the :ref:`ROCm vLLM Docker image <vllm-benchmark-unified-docker>`.
Use the following command to pull the Docker image from Docker Hub.
.. code-block:: shell
docker pull rocm/vllm:rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50
Once setup is complete, you can choose between two options to reproduce the
benchmark results:
- :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
- :ref:`Standalone benchmarking <vllm-benchmark-standalone>`
.. _vllm-benchmark-mad:
MAD-integrated benchmarking
===========================
Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
directory and install the required packages on the host machine.
.. code-block:: shell
git clone https://github.com/ROCm/MAD
cd MAD
pip install -r requirements.txt
Use this command to run a performance benchmark test of the Llama 3.1 8B model
on one GPU with ``float16`` data type in the host machine.
.. code-block:: shell
export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
python3 tools/run_models.py --tags pyt_vllm_llama-3.1-8b --keep-model-dir --live-output --timeout 28800
ROCm MAD launches a Docker container with the name
``container_ci-pyt_vllm_llama-3.1-8b``. The latency and throughput reports of the
model are collected in the following path: ``~/MAD/reports_float16/``
Although the following eight models are pre-configured to collect latency and
throughput performance data, users can also change the benchmarking parameters.
Refer to the :ref:`Standalone benchmarking <vllm-benchmark-standalone>` section.
Available models
----------------
.. hlist::
:columns: 3
* ``pyt_vllm_llama-3.1-8b``
* ``pyt_vllm_llama-3.1-70b``
* ``pyt_vllm_llama-3.1-405b``
* ``pyt_vllm_llama-2-7b``
* ``pyt_vllm_mistral-7b``
* ``pyt_vllm_qwen2-7b``
* ``pyt_vllm_jais-13b``
* ``pyt_vllm_jais-30b``
.. _vllm-benchmark-standalone:
Standalone benchmarking
=======================
You can run the vLLM benchmark tool independently by starting the
:ref:`Docker container <vllm-benchmark-get-started>` as shown in the following
snippet.
.. code-block::
docker pull rocm/vllm:rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50
docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name unified_docker_vllm rocm/vllm:rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50
In the Docker container, clone the ROCm MAD repository and navigate to the
benchmark scripts directory at ``~/MAD/scripts/vllm``.
.. code-block::
git clone https://github.com/ROCm/MAD
cd MAD/scripts/vllm
Multiprocessing distributed executor
--------------------------------------
To optimize vLLM performance, add the multiprocessing API server argument ``--distributed-executor-backend mp``.
Command
^^^^^^^^^^^^^^^^^^^^^^^^^
To start the benchmark, use the following command with the appropriate options.
See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
options and their descriptions.
.. code-block:: shell
./vllm_benchmark_report.sh -s $test_option -m $model_repo -g $num_gpu -d $datatype
See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
.. note::
The input sequence length, output sequence length, and tensor parallel (TP) are
already configured. You don't need to specify them with this script.
.. note::
If you encounter the following error, pass your access-authorized Hugging
Face token to the gated models.
.. code-block:: shell
OSError: You are trying to access a gated repo.
# pass your HF_TOKEN
export HF_TOKEN=$your_personal_hf_token
.. _vllm-benchmark-standalone-options:
Options
^^^^^^^^^^^^^^^^^^^^^^^^^
.. list-table::
:header-rows: 1
* - Name
- Options
- Description
* - ``$test_option``
- latency
- Measure decoding token latency
* -
- throughput
- Measure token generation throughput
* -
- all
- Measure both throughput and latency
* - ``$model_repo``
- ``meta-llama/Meta-Llama-3.1-8B-Instruct``
- Llama 3.1 8B
* - (``float16``)
- ``meta-llama/Meta-Llama-3.1-70B-Instruct``
- Llama 3.1 70B
* -
- ``meta-llama/Meta-Llama-3.1-405B-Instruct``
- Llama 3.1 405B
* -
- ``meta-llama/Llama-2-7b-chat-hf``
- Llama 2 7B
* -
- ``mistralai/Mixtral-8x7B-Instruct-v0.1``
- Mixtral 8x7B
* -
- ``mistralai/Mixtral-8x22B-Instruct-v0.1``
- Mixtral 8x22B
* -
- ``mistralai/Mistral-7B-Instruct-v0.3``
- Mixtral 7B
* -
- ``Qwen/Qwen2-7B-Instruct``
- Qwen2 7B
* -
- ``core42/jais-13b-chat``
- JAIS 13B
* -
- ``core42/jais-30b-chat-v3``
- JAIS 30B
* - ``$num_gpu``
- 1 or 8
- Number of GPUs
* - ``$datatype``
- ``float16``
- Data type
.. _vllm-benchmark-run-benchmark:
Running the benchmark on the MI300X accelerator
-----------------------------------------------
Here are some examples of running the benchmark with various options.
See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
options and their descriptions.
Latency benchmark example
^^^^^^^^^^^^^^^^^^^^^^^^^
Use this command to benchmark the latency of the Llama 3.1 8B model on one GPU with the ``float16`` data type.
.. code-block::
./vllm_benchmark_report.sh -s latency -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
Find the latency report at:
- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_latency_report.csv``
Throughput benchmark example
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Use this command to benchmark the throughput of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
.. code-block:: shell
./vllm_benchmark_report.sh -s throughput -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
Find the throughput reports at:
- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_throughput_report.csv``
.. raw:: html
<style>
mjx-container[jax="CHTML"][display="true"] {
text-align: left;
margin: 0;
}
</style>
.. note::
Throughput is calculated as:
- .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
- .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
Further reading
===============
- For application performance optimization strategies for HPC and AI workloads,
including inference with vLLM, see :doc:`/how-to/tuning-guides/mi300x/workload`.
- To learn more about the options for latency and throughput benchmark scripts,
see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
- To learn more about system settings and management practices to configure your system for
MI300X accelerators, see :doc:`/how-to/system-optimization/mi300x`.
- To learn how to run LLM models from Hugging Face or your own model, see
:doc:`Using ROCm for AI </how-to/rocm-for-ai/index>`.
- To learn how to optimize inference on LLMs, see
:doc:`Fine-tuning LLMs and inference optimization </how-to/llm-fine-tuning-optimization/index>`.
- For a list of other ready-made Docker images for ROCm, see the
:doc:`Docker image support matrix <rocm-install-on-linux:reference/docker-image-support-matrix>`.

View File

@@ -41,13 +41,6 @@ vLLM walkthrough
Refer to this developer blog for guidance on serving with vLLM `Inferencing and serving with vLLM on AMD GPUs — ROCm
Blogs <https://rocm.blogs.amd.com/artificial-intelligence/vllm/README.html>`_
Validating vLLM performance
---------------------------
ROCm provides a prebuilt optimized Docker image for validating the performance of LLM inference with vLLM
on the MI300X accelerator. The Docker image includes ROCm, vLLM, PyTorch, and tuning files in the CSV
format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
.. _rocm-for-ai-serve-hugging-face-tgi:
Serving using Hugging Face TGI

View File

@@ -22,25 +22,25 @@ If youre new to ROCm, refer to the :doc:`ROCm quick start install guide for L
<rocm-install-on-linux:install/quick-start>`.
If youre using a Radeon GPU for graphics-accelerated applications, refer to the
`Radeon installation instructions <https://rocm.docs.amd.com/projects/radeon/en/docs-6.1.3/docs/install/native_linux/install-radeon.html>`_.
:doc:`Radeon installation instructions <radeon:docs/install/install-radeon>`.
ROCm supports multiple :doc:`installation methods <rocm-install-on-linux:install/install-overview>`:
ROCm supports two methods for installation. There is no difference in the final ROCm installation between these two
methods. You can also opt for :ref:`single-version or multi-version installation
<rocm-install-on-linux:installation-types>`.
* :doc:`Using your Linux distribution's package manager <rocm-install-on-linux:install/native-install/index>`
* :doc:`Using your Linux distribution's package manager <rocm-install-on-linux:how-to/native-install/index>`
* :doc:`Using the AMDGPU installer <rocm-install-on-linux:install/amdgpu-install>`
* :ref:`Multi-version installation <rocm-install-on-linux:installation-types>`.
* :doc:`Using the AMDGPU installer <rocm-install-on-linux:how-to/amdgpu-install>`
.. grid:: 1
.. grid-item-card:: Post-install
Follow the :doc:`post-installation instructions <rocm-install-on-linux:install/post-install>` to
Follow the :doc:`post-installation instructions <rocm-install-on-linux:how-to/native-install/post-install>` to
configure your system linker, PATH, and verify the installation.
If you encounter any issues during installation, refer to the
:doc:`Installation troubleshooting <rocm-install-on-linux:reference/install-faq>` guide.
:doc:`Installation troubleshooting <rocm-install-on-linux:how-to/native-install/install-faq>` guide.
Machine learning frameworks
===========================

View File

@@ -365,9 +365,9 @@ installed.
## System management
For a complete guide on how to install/manage/uninstall ROCm on Linux, refer to
{doc}`Quick-start (Linux)<rocm-install-on-linux:install/quick-start>`. To verify that the installation was
{doc}`Quick-start (Linux)<rocm-install-on-linux:tutorial/quick-start>`. To verify that the installation was
successful, refer to the
{doc}`post-install instructions<rocm-install-on-linux:install/post-install>` and
{doc}`post-install instructions<rocm-install-on-linux:how-to/native-install/post-install>` and
[system tools](../../reference/rocm-tools.md). Should verification
fail, consult the [System Debugging Guide](../system-debugging.md).

View File

@@ -350,9 +350,9 @@ installed.
## System management
For a complete guide on how to install/manage/uninstall ROCm on Linux, refer to
{doc}`Quick-start (Linux)<rocm-install-on-linux:install/quick-start>`. For verifying that the
{doc}`Quick-start (Linux)<rocm-install-on-linux:tutorial/quick-start>`. For verifying that the
installation was successful, refer to the
{doc}`post-install instructions<rocm-install-on-linux:install/post-install>` and
{doc}`post-install instructions<rocm-install-on-linux:how-to/native-install/post-install>` and
[system tools](../../reference/rocm-tools.md). Should verification
fail, consult the [System Debugging Guide](../system-debugging.md).

View File

@@ -136,7 +136,7 @@ This section describes performance-based settings.
.. code-block:: shell
cat /sys/module/amdttm/parameters/pages_limit
cat /sys/module/ttm/parameters/pages_limit
To set the amount of allocatable memory to all available memory on all four APU devices, run these commands:
@@ -145,31 +145,20 @@ This section describes performance-based settings.
sudo modprobe amdttm pages_limit=134217728 page_pool_size=134217728
sudo modprobe amdgpu
These settings can also be hardcoded in the ``/etc/modprobe.d/amdttm.conf`` file or specified as boot
parameters.
To use the hardcoded method,
These settings can also be hardcoded in the ``/etc/modprobe.d/amdttm.conf`` file. To use this method,
the filesystem must already be set up when the kernel driver is loaded.
To hardcode the settings, add the following lines to ``/etc/modprobe.d/amdttm.conf``:
Add the following lines to ``/etc/modprobe.d/amdttm.conf``:
.. code-block:: shell
options amdttm pages_limit=134217728
options amdttm page_pool_size=134217728
If the filesystem is not already set up when the kernel driver is loaded, then the options
must be specified as boot parameters. To specify the settings
as boot parameters when loading the kernel, use this example as a guideline:
.. code-block:: shell
vmlinux-[...] amdttm.pages_limit=134217728 amdttm.page_pool_size=134217728 [...]
To verify the new settings and confirm the change, use this command:
.. code-block:: shell
cat /sys/module/amdttm/parameters/pages_limit
cat /sys/module/ttm/parameters/pages_limit
.. note::
@@ -251,13 +240,10 @@ This section describes performance-based settings.
* **Change affinity of ROCm helper threads**
Changing the affinity prevents internal ROCm threads from having their CPU core affinity mask
This change prevents internal ROCm threads from having their CPU core affinity mask
set to all CPU cores available. With this setting, the threads inherit their parent's
CPU core affinity mask. Before adjusting this setting, ensure you thoroughly understand
your system topology and how the application, runtime environment, and batch system
set the thread-to-core affinity. If you have any questions regarding this setting,
contact your MI300A platform vendor or the AMD support team.
To enable this setting, enter the following command:
CPU core affinity mask. If you have any questions regarding this setting,
contact your MI300A platform vendor. To enable this setting, enter the following command:
.. code-block:: shell
@@ -272,9 +258,9 @@ System management
========================================
For a complete guide on installing, managing, and uninstalling ROCm on Linux, see
:doc:`Quick-start (Linux)<rocm-install-on-linux:install/quick-start>`. To verify that the
:doc:`Quick-start (Linux)<rocm-install-on-linux:tutorial/quick-start>`. To verify that the
installation was successful, see the
:doc:`Post-installation instructions<rocm-install-on-linux:install/post-install>` and
:doc:`Post-installation instructions<rocm-install-on-linux:install/native-install/post-install>` and
:doc:`ROCm tools <../../reference/rocm-tools>` guides. If verification
fails, consult the :doc:`System debugging guide <../system-debugging>`.

View File

@@ -534,7 +534,7 @@ optimizing user applications.
For a complete guide on how to install, manage, or uninstall ROCm on Linux, refer to
:doc:`rocm-install-on-linux:install/quick-start`. For verifying that the
installation was successful, refer to the
:doc:`rocm-install-on-linux:install/post-install`.
:doc:`rocm-install-on-linux:install/native-install/post-install`.
Should verification fail, consult :doc:`/how-to/system-debugging`.
Hardware verification with ROCm

View File

@@ -8,8 +8,6 @@ accelerators. They include detailed instructions on system settings and
application tuning suggestions to help you fully leverage the capabilities of
these accelerators, thereby achieving optimal performance.
* :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`
* :doc:`/how-to/tuning-guides/mi300x/system`
* :doc:`/how-to/tuning-guides/mi300x/workload`

View File

@@ -150,10 +150,6 @@ the workload to validate improvements and ensure that the changes have had the
desired effect. Continuous iteration helps refine the performance gains and
address any new bottlenecks that may emerge.
ROCm provides a prebuilt optimized Docker image that has everything required to implement
the tips in this section. It includes ROCm, vLLM, PyTorch, and tuning files in the CSV
format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
.. _mi300x-profiling-tools:
Profiling tools
@@ -376,11 +372,6 @@ Refer to `vLLM documentation <https://docs.vllm.ai/en/latest/models/performance.
for additional performance tips. :ref:`fine-tuning-llms-vllm` describes vLLM
usage with ROCm.
ROCm provides a prebuilt optimized Docker image for validating the performance
of LLM inference with vLLM on the MI300X accelerator. The Docker image includes
ROCm, vLLM, PyTorch, and tuning files in the CSV format. For more information,
see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.
Maximize throughput
-------------------

View File

@@ -52,7 +52,14 @@ ROCm documentation is organized into the following categories:
* [Using ROCm for HPC](./how-to/rocm-for-hpc/index.rst)
* [Fine-tuning LLMs and inference optimization](./how-to/llm-fine-tuning-optimization/index.rst)
* [System optimization](./how-to/system-optimization/index.rst)
* [AMD Instinct MI300X performance validation and tuning](./how-to/tuning-guides/mi300x/index.rst)
* [AMD Instinct MI300X](./how-to/system-optimization/mi300x.rst)
* [AMD Instinct MI300A](./how-to/system-optimization/mi300a.rst)
* [AMD Instinct MI200](./how-to/system-optimization/mi200.md)
* [AMD Instinct MI100](./how-to/system-optimization/mi100.md)
* [AMD Instinct RDNA2](./how-to/system-optimization/w6000-v620.md)
* [AMD Instinct MI300X tuning guides](./how-to/tuning-guides/mi300x/index.rst)
* [System tuning](./how-to/tuning-guides/mi300x/system.rst)
* [Workload tuning](./how-to/tuning-guides/mi300x/workload.rst)
* [System debugging](./how-to/system-debugging.md)
* [GPU-enabled MPI](./how-to/gpu-enabled-mpi.rst)
* [Using advanced compiler features](./conceptual/compiler-topics.md)

View File

@@ -25,7 +25,6 @@
* {doc}`MIVisionX <mivisionx:index>`
* {doc}`rocAL <rocal:index>`
* {doc}`rocDecode <rocdecode:index>`
* {doc}`rocPyDecode <rocpydecode:index>`
* {doc}`ROCm Performance Primitives (RPP) <rpp:index>`
:::
@@ -54,6 +53,18 @@
* {doc}`RCCL <rccl:index>`
:::
(hip-runtime)=
:::{grid-item-card}
:class-card: sd-text-black
:img-top: ../data/reference/banner-hip.jpg
:img-alt: HIP APIs
:padding: 2
* {doc}`HIP runtime <hip:index>`
* {doc}`HIPIFY <hipify:index>`
:::
(math-apis)=
:::{grid-item-card}
@@ -67,7 +78,6 @@
* {doc}`hipBLASLt <hipblaslt:index>`
* {doc}`hipFFT <hipfft:index>` / {doc}`rocFFT <rocfft:index>`
* {doc}`hipfort <hipfort:index>`
* {doc}`hipRAND <hiprand:index>` / {doc}`rocRAND <rocrand:index>`
* {doc}`hipSOLVER <hipsolver:index>` / {doc}`rocSOLVER <rocsolver:index>`
* {doc}`hipSPARSE <hipsparse:index>` / {doc}`rocSPARSE <rocsparse:index>`
* {doc}`hipSPARSELt <hipsparselt:index>`
@@ -76,4 +86,16 @@
* [Tensile](https://github.com/ROCm/Tensile)
:::
(random-number-apis)=
:::{grid-item-card}
:class-card: sd-text-black
:img-top: ../data/reference/banner-random-number.jpg
:img-alt: Random number APIs
:padding: 2
* {doc}`hipRAND <hiprand:index>`
* {doc}`rocRAND <rocrand:index>`
:::
::::

View File

@@ -70,11 +70,9 @@ subtrees:
- file: how-to/system-optimization/w6000-v620.md
title: AMD RDNA 2
- file: how-to/tuning-guides/mi300x/index.rst
title: AMD MI300X performance validation and tuning
title: AMD MI300X tuning guides
subtrees:
- entries:
- file: how-to/performance-validation/mi300x/vllm-benchmark.rst
title: Performance validation
- file: how-to/tuning-guides/mi300x/system.rst
title: System tuning
- file: how-to/tuning-guides/mi300x/workload.rst

View File

@@ -1,2 +1,2 @@
rocm-docs-core==1.8.0
rocm-docs-core==1.7.1
sphinx-reredirects

View File

@@ -6,9 +6,9 @@
#
accessible-pygments==0.0.5
# via pydata-sphinx-theme
alabaster==1.0.0
alabaster==0.7.16
# via sphinx
babel==2.16.0
babel==2.15.0
# 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==2024.8.30
certifi==2024.7.4
# via requests
cffi==1.17.1
cffi==1.16.0
# via
# cryptography
# pynacl
@@ -26,7 +26,7 @@ charset-normalizer==3.3.2
# via requests
click==8.1.7
# via sphinx-external-toc
cryptography==43.0.1
cryptography==42.0.8
# via pyjwt
deprecated==1.2.14
# via pygithub
@@ -42,7 +42,7 @@ gitdb==4.0.11
# via gitpython
gitpython==3.1.43
# via rocm-docs-core
idna==3.10
idna==3.7
# via requests
imagesize==1.4.1
# via sphinx
@@ -56,11 +56,11 @@ markdown-it-py==3.0.0
# myst-parser
markupsafe==2.1.5
# via jinja2
mdit-py-plugins==0.4.2
mdit-py-plugins==0.4.1
# via myst-parser
mdurl==0.1.2
# via markdown-it-py
myst-parser==4.0.0
myst-parser==3.0.1
# via rocm-docs-core
packaging==24.1
# via
@@ -72,18 +72,18 @@ pydata-sphinx-theme==0.15.4
# via
# rocm-docs-core
# sphinx-book-theme
pygithub==2.4.0
pygithub==2.3.0
# via rocm-docs-core
pygments==2.18.0
# via
# accessible-pygments
# pydata-sphinx-theme
# sphinx
pyjwt[crypto]==2.9.0
pyjwt[crypto]==2.8.0
# via pygithub
pynacl==1.5.0
# via pygithub
pyyaml==6.0.2
pyyaml==6.0.1
# via
# myst-parser
# rocm-docs-core
@@ -92,15 +92,15 @@ requests==2.32.3
# via
# pygithub
# sphinx
rocm-docs-core==1.8.0
rocm-docs-core==1.7.1
# via -r requirements.in
smmap==5.0.1
# via gitdb
snowballstemmer==2.2.0
# via sphinx
soupsieve==2.6
soupsieve==2.5
# via beautifulsoup4
sphinx==8.0.2
sphinx==7.3.7
# via
# breathe
# myst-parser
@@ -116,25 +116,25 @@ sphinx-book-theme==1.1.3
# via rocm-docs-core
sphinx-copybutton==0.5.2
# via rocm-docs-core
sphinx-design==0.6.1
sphinx-design==0.6.0
# via rocm-docs-core
sphinx-external-toc==1.0.1
# via rocm-docs-core
sphinx-notfound-page==1.0.4
sphinx-notfound-page==1.0.2
# via rocm-docs-core
sphinx-reredirects==0.1.5
# via -r requirements.in
sphinxcontrib-applehelp==2.0.0
sphinxcontrib-applehelp==1.0.8
# via sphinx
sphinxcontrib-devhelp==2.0.0
sphinxcontrib-devhelp==1.0.6
# via sphinx
sphinxcontrib-htmlhelp==2.1.0
sphinxcontrib-htmlhelp==2.0.5
# via sphinx
sphinxcontrib-jsmath==1.0.1
# via sphinx
sphinxcontrib-qthelp==2.0.0
sphinxcontrib-qthelp==1.0.7
# via sphinx
sphinxcontrib-serializinghtml==2.0.0
sphinxcontrib-serializinghtml==1.1.10
# via sphinx
tomli==2.0.1
# via sphinx
@@ -142,7 +142,7 @@ typing-extensions==4.12.2
# via
# pydata-sphinx-theme
# pygithub
urllib3==2.2.3
urllib3==2.2.2
# via
# pygithub
# requests

58
temp.md Normal file
View File

@@ -0,0 +1,58 @@
## Components
The following table lists ROCm components and their individual versions for ROCm 6.2.0. Find an overview of officially
supported versions of ROCm components, third-party libraries, and frameworks in the
[Compatibility matrix](https://rocm.docs.amd.com/en/latest/release/docs/6.2.0/compatibility/compatibility-matrix).
| Category | Group | Name | Version | |
|----------|-------|------|---------|:-:|
| **Libraries** | **Machine learning and computer vision** | [Composable Kernel](https://rocm.docs.amd.com/projects/composable_kernel/en/docs/6.2.0) | 1.1.0 | [{fab}`github fa-lg`](https://github.com/ROCm/composable_kernel/releases/tag/rocm-6.2.0) |
| | | [MIGraphX](https://rocm.docs.amd.com/projects/AMDMIGraphX/en/docs/6.2.0) | 2.9&nbsp;&Rightarrow;&nbsp;[2.10](migraphx-2-10-0) | [{fab}`github fa-lg`](https://github.com/ROCm/AMDMIGraphX/releases/tag/rocm-6.2.0) |
| | | [MIOpen](https://rocm.docs.amd.com/projects/MIOpen/en/docs/6.2.0) | 3.1.0&nbsp;&Rightarrow;&nbsp;[3.2.0](miopen-3-2-0) | [{fab}`github fa-lg`](https://github.com/ROCm/MIOpen/releases/tag/rocm-6.2.0) |
| | | [MIVisionX](https://rocm.docs.amd.com/projects/MIVisionX/en/docs/6.2.0) | 2.5.0&nbsp;&Rightarrow;&nbsp;[3.0.0](mivisionx-3-0-0) | [{fab}`github fa-lg`](https://github.com/ROCm/MIVisionX/releases/tag/rocm-6.2.0) |
| | | [rocAL](https://rocm.docs.amd.com/projects/rocAL/en/docs/6.2.0) | 2.0.0 | [{fab}`github fa-lg`](https://github.com/ROCm/rocAL/releases/tag/rocm-6.2.0) |
| | | [rocDecode](https://rocm.docs.amd.com/projects/rocDecode/en/docs/6.2.0) | 0.6.0 | [{fab}`github fa-lg`](https://github.com/ROCm/rocDecode/releases/tag/rocm-6.2.0) |
| | | [rocPyDecode](https://rocm.docs.amd.com/projects/rocPyDecode/en/docs/6.2.0) | 0.1.0 | [{fab}`github fa-lg`](https://github.com/ROCm/rocPyDecode/releases/tag/rocm-6.2.0) |
| | | [RPP](https://rocm.docs.amd.com/projects/rpp/en/docs/6.2.0) | 1.5.0&nbsp;&Rightarrow;&nbsp;[1.8.0](rpp-1-8-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rpp/releases/tag/rocm-6.2.0) |
| | **Communication** | [rccl](https://rocm.docs.amd.com/projects/rccl/en/docs/6.2.0) | 2.18.6&nbsp;&Rightarrow;&nbsp;[2.20.5](rccl-2-20-5) | [{fab}`github fa-lg`](https://github.com/ROCm/rccl/releases/tag/rocm-6.2.0) |
| | **Math** | [hipBLAS](https://rocm.docs.amd.com/projects/hipBLAS/en/docs/6.2.0) | 2.1.0&nbsp;&Rightarrow;&nbsp;[2.2.0](hipblas-2-2-0) | [{fab}`github fa-lg`](https://github.com/ROCm/hipBLAS/releases/tag/rocm-6.2.0) |
| | | [hipBLASLt](https://rocm.docs.amd.com/projects/hipBLASLt/en/docs/6.2.0) | 0.7.0&nbsp;&Rightarrow;&nbsp;[0.8.0](hipblaslt-0-8-0) | [{fab}`github fa-lg`](https://github.com/ROCm/hipBLASLt/releases/tag/rocm-6.2.0) |
| | | [hipFFT](https://rocm.docs.amd.com/projects/hipFFT/en/docs/6.2.0) | [1.0.14](hipfft-1-0-14) | [{fab}`github fa-lg`](https://github.com/ROCm/hipFFT/releases/tag/rocm-6.2.0) |
| | | [hipfort](https://rocm.docs.amd.com/projects/hipfort/en/docs/6.2.0) | 0.4-0 | [{fab}`github fa-lg`](https://github.com/ROCm/hipfort/releases/tag/rocm-6.2.0) |
| | | [hipRAND](https://rocm.docs.amd.com/projects/hipRAND/en/docs/6.2.0) | 2.10.17&nbsp;&Rightarrow;&nbsp;[2.11.0](hiprand-2-11-0) | [{fab}`github fa-lg`](https://github.com/ROCm/hipRAND/releases/tag/rocm-6.2.0) |
| | | [hipSOLVER](https://rocm.docs.amd.com/projects/hipSOLVER/en/docs/6.2.0) | 2.1.1&nbsp;&Rightarrow;&nbsp;[2.2.0](hipsolver-2-2-0) | [{fab}`github fa-lg`](https://github.com/ROCm/hipSOLVER/releases/tag/rocm-6.2.0) |
| | | [hipSPARSE](https://rocm.docs.amd.com/projects/hipSPARSE/en/docs/6.2.0) | 3.0.1&nbsp;&Rightarrow;&nbsp;[3.1.1](hipsparse-3-1-1) | [{fab}`github fa-lg`](https://github.com/ROCm/hipSPARSE/releases/tag/rocm-6.2.0) |
| | | [hipSPARSELt](https://rocm.docs.amd.com/projects/hipSPARSELt/en/docs/6.2.0) | 0.2.0&nbsp;&Rightarrow;&nbsp;[0.2.1](hipsparselt-0-2-1) | [{fab}`github fa-lg`](https://github.com/ROCm/hipSPARSELt/releases/tag/rocm-6.2.0) |
| | | [rocALUTION](https://rocm.docs.amd.com/projects/rocALUTION/en/docs/6.2.0) | 3.1.1&nbsp;&Rightarrow;&nbsp;[3.2.0](rocalution-3-2-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rocALUTION/releases/tag/rocm-6.2.0) |
| | | [rocBLAS](https://rocm.docs.amd.com/projects/rocBLAS/en/docs/6.2.0) | 4.1.0&nbsp;&Rightarrow;&nbsp;[4.2.0](rocblas-4-2-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rocBLAS/releases/tag/rocm-6.2.0) |
| | | [rocFFT](https://rocm.docs.amd.com/projects/rocFFT/en/docs/6.2.0) | 1.0.27&nbsp;&Rightarrow;&nbsp;[1.0.28](rocfft-1-0-28) | [{fab}`github fa-lg`](https://github.com/ROCm/rocFFT/releases/tag/rocm-6.2.0) |
| | | [rocRAND](https://rocm.docs.amd.com/projects/rocRAND/en/docs/6.2.0) | 3.0.0&nbsp;&Rightarrow;&nbsp;[3.1.0](rocrand-3-1-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rocRAND/releases/tag/rocm-6.2.0) |
| | | [rocSOLVER](https://rocm.docs.amd.com/projects/rocSOLVER/en/docs/6.2.0) | 3.25.0&nbsp;&Rightarrow;&nbsp;[3.26.0](rocsolver-3-26-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rocSOLVER/releases/tag/rocm-6.2.0) |
| | | [rocSPARSE](https://rocm.docs.amd.com/projects/rocSPARSE/en/docs/6.2.0) | 3.1.1&nbsp;&Rightarrow;&nbsp;[3.2.0](rocsparse-3-2-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rocSPARSE/releases/tag/rocm-6.2.0) |
| | | [rocWMMA](https://rocm.docs.amd.com/projects/rocWMMA/en/docs/6.2.0) | 1.4.0&nbsp;&Rightarrow;&nbsp;[1.5.0](rocwmma-1-5-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rocWMMA/releases/tag/rocm-6.2.0) |
| | | [Tensile](https://rocm.docs.amd.com/projects/tensile/en/docs/6.2.0) | 4.40.0&nbsp;&Rightarrow;&nbsp;[4.41.0](tensile-4-41-0) | [{fab}`github fa-lg`](https://github.com/ROCm/tensile/releases/tag/rocm-6.2.0) |
| | **Primitives** | [hipCUB](https://rocm.docs.amd.com/projects/hipCUB/en/docs/6.2.0) | 3.1.0&nbsp;&Rightarrow;&nbsp;[3.2.0](hipcub-3-2-0) | [{fab}`github fa-lg`](https://github.com/ROCm/hipCUB/releases/tag/rocm-6.2.0) |
| | | [hipTensor](https://rocm.docs.amd.com/projects/hipTensor/en/docs/6.2.0) | 1.2.0&nbsp;&Rightarrow;&nbsp;[1.3.0](hiptensor-1-3-0) | [{fab}`github fa-lg`](https://github.com/ROCm/hipTensor/releases/tag/rocm-6.2.0) |
| | | [rocPRIM](https://rocm.docs.amd.com/projects/rocPRIM/en/docs/6.2.0) | 3.1.0&nbsp;&Rightarrow;&nbsp;[3.2.0](rocprim-3-2-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rocPRIM/releases/tag/rocm-6.2.0) |
| | | [rocThrust](https://rocm.docs.amd.com/projects/rocThrust/en/docs/6.2.0) | 3.0.0&nbsp;&Rightarrow;&nbsp;[3.1.0](rocthrust-3-1-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rocThrust/releases/tag/rocm-6.2.0) |
| **Tools** | **Development** | [HIPIFY](https://rocm.docs.amd.com/projects/HIPIFY/docs/6.2.0) | 17.0.0&nbsp;&Rightarrow;&nbsp;[18.0.0](hipify-18-0-0) | [{fab}`github fa-lg`](https://github.com/ROCm/HIPIFY/releases/tag/rocm-6.2.0) |
| | | [ROCdbgapi](https://rocm.docs.amd.com/projects/ROCdbgapi/en/docs/6.2.0) | 0.71.0&nbsp;&Rightarrow;&nbsp;[0.76.0](rocdbgapi-0-76-0) | [{fab}`github fa-lg`](https://github.com/ROCm/ROCdbgapi/releases/tag/rocm-6.2.0) |
| | | [ROCm CMake](https://rocm.docs.amd.com/projects/rocm-cmake/en/docs/6.2.0) | 0.12.0&nbsp;&Rightarrow;&nbsp;[0.13.0](rocm-cmake-0-13-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rocm-cmake/releases/tag/rocm-6.2.0) |
| | | [ROCm Debugger (ROCgdb)](https://rocm.docs.amd.com/projects/rocm-cmake/en/docs/6.2.0) | 13&nbsp;&Rightarrow;&nbsp;[15](rocgdb-15) | [{fab}`github fa-lg`](https://github.com/ROCm/ROCgdb/releases/tag/rocm-6.2.0) |
| | | [ROCr Debug Agent](https://rocm.docs.amd.com/projects/rocr_debug_agent/en/docs/6.2.0) | 2.0.3 | [{fab}`github fa-lg`](https://github.com/ROCm/rocr_debug_agent/releases/tag/rocm-6.2.0) |
| | **Performance** | [Omniperf](https://rocm.docs.amd.com/projects/omniperf/en/docs/6.2.0) | 2.0.1 | [{fab}`github fa-lg`](https://github.com/ROCm/omniperf/releases/tag/rocm-6.2.0) |
| | | [Omnitrace](https://rocm.docs.amd.com/projects/omnitrace/en/docs/6.2.0) | 1.11.2 | [{fab}`github fa-lg`](https://github.com/ROCm/omnitrace/releases/tag/rocm-6.2.0) |
| | | [ROCm Bandwidth Test](https://rocm.docs.amd.com/projects/rocm_bandwidth_test/en/docs/6.2.0) | 1.4.0 | [{fab}`github fa-lg`](https://github.com/ROCm/rocm_bandwidth_test/releases/tag/rocm-6.2.0) |
| | | [ROCProfiler](https://rocm.docs.amd.com/projects/ROCProfiler/en/docs/6.2.0) | 2.0.0&nbsp;&Rightarrow;&nbsp;[2.0.0](rocprofiler-2-0-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rocm_bandwidth_test/releases/tag/rocm-6.2.0) |
| | | [ROCProfiler-SDK](https://rocm.docs.amd.com/projects/rocprofiler-sdk/en/docs/6.2.0) | 0.4.0 | [{fab}`github fa-lg`](https://github.com/ROCm/rocm_bandwidth_test/releases/tag/rocm-6.2.0) |
| | | [ROCTracer](https://rocm.docs.amd.com/projects/ROCTracer/en/docs/6.2.0) | 4.1.0 | [{fab}`github fa-lg`](https://github.com/ROCm/rocm_bandwidth_test/releases/tag/rocm-6.2.0) |
| | **System** | [AMD SMI](https://rocm.docs.amd.com/projects/amdsmi/en/docs/6.2.0) | 24.5.2&nbsp;&Rightarrow;&nbsp;[24.6.1](amd-smi-24-6-1) | [{fab}`github fa-lg`](https://github.com/ROCm/rdc/releases/tag/rocm-6.2.0) |
| | | [rocminfo](https://rocm.docs.amd.com/projects/rdc/en/docs/6.2.0) | 1.0.0 | [{fab}`github fa-lg`](https://github.com/ROCm/rdc/releases/tag/rocm-6.2.0) |
| | | [ROCm Data Center Tool](https://rocm.docs.amd.com/projects/rdc/en/docs/6.2.0) | 0.3.0&nbsp;&Rightarrow;&nbsp;[1.0.0](rocm-data-center-tool-1-0-0) | [{fab}`github fa-lg`](https://github.com/ROCm/rdc/releases/tag/rocm-6.2.0) |
| | | [ROCm SMI](https://rocm.docs.amd.com/projects/rdc/en/docs/6.2.0) | 7.2.0 | [{fab}`github fa-lg`](https://github.com/ROCm/rdc/releases/tag/rocm-6.2.0) |
| | | [ROCm Validation Suite](https://rocm.docs.amd.com/projects/rdc/en/docs/6.2.0) | 1.0 | [{fab}`github fa-lg`](https://github.com/ROCm/rdc/releases/tag/rocm-6.2.0) |
| | | [TransferBench](https://rocm.docs.amd.com/projects/rdc/en/docs/6.2.0) | 1.5.0 | [{fab}`github fa-lg`](https://github.com/ROCm/rdc/releases/tag/rocm-6.2.0) |
| | **Compilers** | [hipCC](https://rocm.docs.amd.com/projects/hipCC/en/docs/6.2.0) | 1.0.0&nbsp;&Rightarrow;&nbsp;[1.1.1](hipcc-1-1-1) | [{fab}`github fa-lg`](https://github.com/ROCm/llvm-project/releases/tag/rocm-6.2.0) |
| | | [llvm-project](https://rocm.docs.amd.com/projects/llvm-project/en/docs/6.2.0) | 17.0.0&nbsp;&Rightarrow;&nbsp;[18.0.0](llvm-project-18-0-0) | [{fab}`github fa-lg`](https://github.com/ROCm/llvm-project/releases/tag/rocm-6.2.0) |
| **Runtimes** | | [HIP](https://rocm.docs.amd.com/projects/HIP/en/docs/6.2.0) | 6.1&nbsp;&Rightarrow;&nbsp;[6.2](hip-6-2-0) | [{fab}`github fa-lg`](https://github.com/ROCm/HIP/releases/tag/rocm-6.2.0) |
| | | [ROCr Runtime](https://rocm.docs.amd.com/projects/ROCr-Runtime/en/docs/6.2.0) | 6.1&nbsp;&Rightarrow;&nbsp;[6.2](hip-6-2-0) | [{fab}`github fa-lg`](https://github.com/ROCm/ROCR-Runtime/releases/tag/rocm-6.2.0) |

View File

@@ -67,16 +67,18 @@ endef
$(call adddep,amd_smi_lib,${ASAN_DEP})
$(call adddep,aqlprofile,${ASAN_DEP} hsa)
$(call adddep,clang-ocl,lightning rocm-cmake)
$(call adddep,comgr,lightning devicelibs)
$(call adddep,dbgapi,hsa comgr)
$(call adddep,devicelibs,lightning)
$(call adddep,hip_on_rocclr,${ASAN_DEP} rocclr rocprofiler-register)
$(call adddep,hip_on_rocclr,${ASAN_DEP} hsa comgr hipcc 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)
$(call adddep,omniperf,${ASAN_DEP})
$(call adddep,omnitrace,hipcc hsa hip_on_rocclr rocm_smi_lib rocprofiler roctracer)
$(call adddep,opencl_icd_loader,)
$(call adddep,opencl_on_rocclr,${ASAN_DEP} hsa comgr opencl_icd_loader)
$(call adddep,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)
@@ -87,14 +89,15 @@ $(call adddep,rocm-core,${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)
$(call adddep,rocprofiler-sdk,${ASAN_DEP} hsa aqlprofile opencl_on_rocclr hip_on_rocclr comgr)
$(call adddep,rocprofiler,${ASAN_DEP} hsa roctracer aqlprofile opencl_on_rocclr hip_on_rocclr comgr)
$(call adddep,rocr_debug_agent,${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 \
omniperf omnitrace rocm-core amd_smi_lib hipcc \
rocm_bandwidth_test rocr_debug_agent rocm-gdb
$(call adddep,rocm-dev,$(filter-out ${NOBUILD},${rocm-dev-components}))
@@ -117,6 +120,7 @@ $(call adddep,mivisionx,amdmigraphx miopen-hip rpp lightning hipcc)
$(call adddep,rccl,hip_on_rocclr hsa lightning hipcc rocm_smi_lib hipify_clang)
$(call adddep,rocalution,rocblas rocsparse rocrand lightning hipcc)
$(call adddep,rocblas,hip_on_rocclr openmp_extras lightning hipcc)
$(call adddep,rocal,mivisionx)
$(call adddep,rocdecode,hip_on_rocclr lightning hipcc)
$(call adddep,rocfft,hip_on_rocclr rocrand hiprand lightning hipcc openmp_extras)
$(call adddep,rocmvalidationsuite,hip_on_rocclr hsa rocblas rocm-core lightning hipcc rocm_smi_lib)
@@ -221,7 +225,7 @@ rocm-dev: T_rocm-dev
${OUT_DIR}/logs:
sudo mkdir -p -m 775 "${ROCM_INSTALL_PATH}" && \
sudo chown -R "$(shell id -u):$(shell id -g)" "${ROCM_INSTALL_PATH}"
sudo chown -R "$(shell id -u):$(shell id -g)" "/opt"
sudo chown -R "$(shell id -u):$(shell id -g)" "/home/$(shell id -un)"
mkdir -p "${@}"
mkdir -p ${HOME}/.ccache

View File

@@ -22,12 +22,13 @@ build_amdmigraphx() {
else
GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
fi
init_rocm_common_cmake_params
mkdir -p ${BUILD_DIR} && rm -rf ${BUILD_DIR}/* && mkdir -p ${HOME}/amdmigraphx && rm -rf ${HOME}/amdmigraphx/*
rbuild package -d "${HOME}/amdmigraphx" -B "${BUILD_DIR}" \
--cxx="${ROCM_PATH}/llvm/bin/clang++" \
--cc="${ROCM_PATH}/llvm/bin/clang" \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DCMAKE_MODULE_LINKER_FLAGS="-Wl,--enable-new-dtags -Wl,--rpath,$ROCM_LIB_RPATH" \
-DGPU_TARGETS="${GPU_TARGETS}" \
-DCMAKE_INSTALL_RPATH=""

View File

@@ -17,9 +17,7 @@ build_miopen_ck() {
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"
GPU_TARGETS="-DAMDGPU_TARGETS=${GPU_ARCHS}"
fi
if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
@@ -43,7 +41,7 @@ build_miopen_ck() {
${LAUNCHER_FLAGS} \
-DINSTANCES_ONLY=ON \
-DENABLE_ASAN_PACKAGING=true \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
"${GPU_TARGETS}" \
"$COMPONENT_SRC"
else
cmake -DBUILD_DEV=OFF \
@@ -63,9 +61,11 @@ build_miopen_ck() {
-DROCM_DISABLE_LDCONFIG=ON \
-DROCM_PATH=${ROCM_PATH} \
-DCPACK_GENERATOR="${PKGTYPE^^}" \
-DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
-DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
${LAUNCHER_FLAGS} \
-DINSTANCES_ONLY=ON \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
"${GPU_TARGETS}" \
"$COMPONENT_SRC"
fi
@@ -106,8 +106,6 @@ build_miopen_ckProf() {
architectures='gfx10 gfx11 gfx90 gfx94'
if [ -n "$GPU_ARCHS" ]; then
architectures=$(echo ${GPU_ARCHS} | awk -F';' '{for(i=1;i<=NF;i++) a[substr($i,1,5)]} END{for(i in a) printf i" "}')
else
architectures='gfx10 gfx11 gfx90 gfx94'
fi
for arch in ${architectures}

View File

@@ -28,9 +28,10 @@ build_hipblas() {
rebuild_lapack
fi
init_rocm_common_cmake_params
cmake \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DUSE_CUDA=OFF \
-DBUILD_CLIENTS_TESTS=ON \
-DBUILD_CLIENTS_BENCHMARKS=ON \

View File

@@ -27,11 +27,12 @@ build_hipblaslt() {
GPU_TARGETS=all
fi
init_rocm_common_cmake_params
CXX=$(set_build_variables CXX)\
cmake \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DTensile_LOGIC= \
-DTensile_CODE_OBJECT_VERSION=default \
-DTensile_CPU_THREADS= \

View File

@@ -17,6 +17,7 @@ build_hipcub() {
fi
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
init_rocm_common_cmake_params
if [ -n "$GPU_ARCHS" ]; then
GPU_TARGETS="$GPU_ARCHS"
@@ -27,7 +28,7 @@ build_hipcub() {
CXX=$(set_build_variables CXX)\
cmake \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip;${ROCM_PATH}/hip/cmake" \
-Drocprim_DIR="${ROCM_PATH}/rocprim" \
-DBUILD_TEST=ON \

View File

@@ -16,6 +16,7 @@ build_hipfft() {
cd $COMPONENT_SRC
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
init_rocm_common_cmake_params
if [ -n "$GPU_ARCHS" ]; then
GPU_TARGETS="$GPU_ARCHS"
@@ -26,7 +27,7 @@ build_hipfft() {
cmake \
-DCMAKE_CXX_COMPILER=$(set_build_variables CXX) \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
-DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip" \
-DCMAKE_SKIP_BUILD_RPATH=TRUE \

View File

@@ -61,7 +61,6 @@ build_hiprand() {
rm -rf _CPack_Packages/ && find -name '*.o' -delete
mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
$SCCACHE_BIN -s || echo "Unable to display sccache stats"
}
clean_hiprand() {

View File

@@ -27,10 +27,11 @@ build_hipsolver() {
rebuild_lapack
fi
init_rocm_common_cmake_params
cmake \
-DUSE_CUDA=OFF \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DBUILD_CLIENTS_TESTS=ON \
-DBUILD_CLIENTS_BENCHMARKS=ON \
-DBUILD_CLIENTS_SAMPLES=ON \

View File

@@ -22,11 +22,12 @@ build_hipsparse() {
echo "CXX compiler: $CXX"
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
init_rocm_common_cmake_params
cmake \
-DCPACK_SET_DESTDIR=OFF \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DUSE_CUDA=OFF \
-DBUILD_CLIENTS_SAMPLES=ON \
-DBUILD_CLIENTS_TESTS=ON \

View File

@@ -28,6 +28,7 @@ build_hipsparselt() {
cd $COMPONENT_SRC
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
init_rocm_common_cmake_params
if [ -n "$GPU_ARCHS" ]; then
GPU_TARGETS="$GPU_ARCHS"
@@ -41,7 +42,7 @@ build_hipsparselt() {
cmake \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DTensile_LOGIC= \
-DTensile_CODE_OBJECT_VERSION=default \
-DTensile_CPU_THREADS= \

View File

@@ -16,6 +16,8 @@ build_hiptensor() {
cd "$COMPONENT_SRC"
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
init_rocm_common_cmake_params
if [ -n "$GPU_ARCHS" ]; then
GPU_TARGETS="$GPU_ARCHS"
@@ -25,7 +27,7 @@ build_hiptensor() {
cmake \
-B "${BUILD_DIR}" \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
$(set_build_variables CMAKE_C_CXX) \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
${LAUNCHER_FLAGS} \

View File

@@ -17,7 +17,8 @@ printUsage() {
echo " -r, --release Build a release version of the package"
echo " -a, --address_sanitizer Enable address sanitizer (enabled by default)"
echo " -A --no_address_sanitizer Disable address sanitizer"
echo " -s, --static Supports static CI by accepting this param & not bailing out. No effect of the param though"
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
echo " -w, --wheel Creates python wheel package of rocm-llvm. It needs to be used along with -r option"
echo " -l, --build_llvm_static Build LLVM libraries statically linked. Default is to build dynamic linked libs"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
@@ -42,6 +43,7 @@ DEB_PATH="$(getDebPath lightning)"
RPM_PATH="$(getRpmPath lightning)"
INSTALL_PATH="${ROCM_INSTALL_PATH}/lib/llvm"
LLVM_ROOT_LCL="${LLVM_ROOT}"
ROCM_WHEEL_DIR="${BUILD_PATH}/_wheel"
TARGET="all"
MAKEOPTS="$DASH_JAY"
@@ -69,14 +71,29 @@ ASSERT_LLVM_VERSION_MINOR=""
SKIP_LIT_TESTS=0
BUILD_MANPAGES="ON"
STATIC_FLAG=
SANITIZER_AMDGPU=1
HSA_INC_PATH="$WORK_ROOT/ROCR-Runtime/src/inc"
COMGR_INC_PATH="$WORK_ROOT/llvm-project/amd/comgr/include"
VALID_STR=`getopt -o htcV:v:draAslo:BPNM --long help,alt,clean,assert_llvm_ver_major:,assert_llvm_ver_minor:,debug,release,address_sanitizer,no_address_sanitizer,static,build_llvm_static,build,package,skip_lit_tests,skip_man_pages,outdir: -- "$@"`
VALID_STR=`getopt -o htcV:v:draAswlo:BPNM --long help,alt,clean,assert_llvm_ver_major:,assert_llvm_ver_minor:,debug,release,address_sanitizer,no_address_sanitizer,static,build_llvm_static,wheel,build,package,skip_lit_tests,skip_man_pages,outdir: -- "$@"`
eval set -- "$VALID_STR"
set_dwarf_version(){
case "$DISTRO_ID" in
(sles*|rhel*)
SET_DWARF_VERSION_4="-gdwarf-4"
;;
(*)
SET_DWARF_VERSION_4=""
;;
esac
export CFLAGS="$CFLAGS $SET_DWARF_VERSION_4 "
export CXXFLAGS="$CXXFLAGS $SET_DWARF_VERSION_4 "
export ASMFLAGS="$ASMFLAGS $SET_DWARF_VERSION_4 "
}
while true ;
do
case "$1" in
@@ -95,6 +112,7 @@ do
(-r | --release)
BUILD_TYPE="Release" ; shift ;;
(-a | --address_sanitizer)
set_dwarf_version
SANITIZER_AMDGPU=1 ;
HSA_INC_PATH="$WORK_ROOT/hsa/runtime/opensrc/hsa-runtime/inc" ;
COMGR_INC_PATH="$WORK_ROOT/external/llvm-project/amd/comgr/include" ; shift ;;
@@ -103,9 +121,12 @@ do
unset HSA_INC_PATH ;
unset COMGR_INC_PATH ; shift ;;
(-s | --static)
SHARED_LIBS="OFF" ; shift ;;
SHARED_LIBS="OFF" ;
STATIC_FLAG="-DBUILD_SHARED_LIBS=$SHARED_LIBS" ; shift ;;
(-l | --build_llvm_static)
BUILD_LLVM_DYLIB="OFF"; shift ;;
(-w | --wheel)
WHEEL_PACKAGE=true ; shift ;;
(-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
(-B | --build)
@@ -151,6 +172,7 @@ else
fi
clean_lightning() {
rm -rf "$ROCM_WHEEL_DIR"
rm -rf "$BUILD_PATH"
rm -rf "$DEB_PATH"
rm -rf "$RPM_PATH"
@@ -196,7 +218,10 @@ LLVM_VERSION_MINOR=""
LLVM_VERSION_PATCH=""
LLVM_VERSION_SUFFIX=""
get_llvm_version() {
local LLVM_VERSIONS=($(awk '/set\(LLVM_VERSION/ {print substr($2,1,length($2)-1)}' ${LLVM_ROOT_LCL}/CMakeLists.txt))
local LLVM_VERSIONS=($(awk '/set\(LLVM_VERSION/ {print substr($2,1,length($2)-1)}' ${LLVM_ROOT_LCL}/../cmake/Modules/LLVMVersion.cmake))
if [ ${#LLVM_VERSIONS[@]} -eq 0 ]; then
LLVM_VERSIONS=($(awk '/set\(LLVM_VERSION/ {print substr($2,1,length($2)-1)}' ${LLVM_ROOT_LCL}/CMakeLists.txt))
fi
LLVM_VERSION_MAJOR=${LLVM_VERSIONS[0]}
LLVM_VERSION_MINOR=${LLVM_VERSIONS[1]}
LLVM_VERSION_PATCH=${LLVM_VERSIONS[2]}
@@ -260,15 +285,22 @@ build_lightning() {
if [ ! -e Makefile ]; then
echo "Building LLVM CMake environment"
if [ -e "$LLVM_ROOT_LCL/../flang/docs/AssumedRank.md" ]; then
FLANG_NEW=1
LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
else
echo "NOT building project flang"
fi
if [ -e "$LLVM_ROOT_LCL/../flang/AFARrelease" ]; then
FLANG_NEW=1
LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
ENABLE_RUNTIMES="$ENABLE_RUNTIMES;openmp";
else
if [[ "${JOB_NAME}" != *afar* ]] && [ -e "$LLVM_ROOT_LCL/../flang/DoROCmRelease" ]; then
FLANG_NEW=1
LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
else
echo "NOT building project flang"
fi
fi
set -x
cmake $(rocm_cmake_params) ${GEN_NINJA} \
${STATIC_FLAG} \
-DCMAKE_INSTALL_PREFIX="$INSTALL_PATH" \
-DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" \
-DLLVM_ENABLE_PROJECTS="$LLVM_PROJECTS" \
@@ -307,9 +339,9 @@ build_lightning() {
-DCMAKE_SHARED_LINKER_FLAGS=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_LLVM_LIB_RPATH \
-DROCM_LLVM_BACKWARD_COMPAT_LINK="$ROCM_INSTALL_PATH/llvm" \
-DROCM_LLVM_BACKWARD_COMPAT_LINK_TARGET="./lib/llvm" \
-DCLANG_LINK_FLANG_LEGACY=ON \
-DCMAKE_CXX_STANDARD=17 \
-DFLANG_INCLUDE_DOCS=OFF \
-DCLANG_LINK_FLANG_LEGACY=ON \
-DCMAKE_CXX_STANDARD=17 \
-DFLANG_INCLUDE_DOCS=OFF \
"$LLVM_ROOT_LCL"
set +x
echo "CMake complete"
@@ -326,8 +358,23 @@ build_lightning() {
echo "End Workaround for race condition"
cmake --build . -- $MAKEOPTS
case "$DISTRO_ID" in
(rhel*|centos*)
RHEL_BUILD=1
;;
(*)
RHEL_BUILD=0
;;
esac
if [ $SKIP_LIT_TESTS -eq 0 ]; then
if [ "$DISTRO_NAME" != "sles" ] && [ $BUILD_ALT != 1 ]; then
if [ $RHEL_BUILD -eq 1 ] && [ $BUILD_ALT != 1 ]; then
if [ $FLANG_NEW -eq 1 ]; then
cmake --build . -- $MAKEOPTS check-lld check-mlir
else
cmake --build . -- $MAKEOPTS check-lld
fi
elif [ "$DISTRO_NAME" != "sles" ] && [ $BUILD_ALT != 1 ]; then
if [ $FLANG_NEW -eq 1 ]; then
cmake --build . -- $MAKEOPTS check-llvm check-clang check-lld check-mlir
else
@@ -733,7 +780,7 @@ package_lightning_static() {
local amd_compiler_commands=("amdclang" "amdclang++" "amdclang-cl" "amdclang-cpp" "amdflang" "amdlld" "offload-arch")
local amd_man_pages=("amdclang.1.gz" "flang.1.gz" "amdflang.1.gz")
local core_bin=("amdgpu-arch" "amdgpu-offload-arch" "amdlld" "amdllvm" "clang" "clang++" "clang-${LLVM_VERSION_MAJOR}" "clang-cl"
"clang-cpp" "clang-build-select-link" "clang-offload-bundler" "clang-offload-packager" "clang-offload-wrapper" "flang" "flang-new"
"clang-cpp" "clang-build-select-link" "clang-offload-bundler" "clang-offload-packager" "clang-offload-wrapper" "clang-linker-wrapper" "clang-nvlink-wrapper" "flang" "flang-new"
"ld64.lld" "ld.lld" "llc" "lld" "lld-link" "llvm-ar" "llvm-bitcode-strip" "llvm-dwarfdump" "llvm-install-name-tool"
"llvm-link" "llvm-mc" "llvm-objcopy" "llvm-objdump" "llvm-otool" "llvm-ranlib" "llvm-readelf" "llvm-readobj" "llvm-strip"
"nvidia-arch" "nvptx-arch" "offload-arch" "opt" "wasm-ld" "amdclang" "amdclang++" "amdclang-${LLVM_VERSION_MAJOR}" "amdclang-cl"
@@ -934,7 +981,7 @@ package_lightning_static() {
if [ $BUILD_ALT -eq 0 ]; then
echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFile
echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFile
else
echo "cp -R $LLVM_PROJECT_ALT_ROOT/EULA \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
echo "cp -R $LLVM_PROJECT_ALT_ROOT/DISCLAIMER.txt \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
@@ -948,7 +995,6 @@ package_lightning_static() {
echo "cp -d \"$distBin/flang\" \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFile
# Copy the config files
if [ $BUILD_ALT -eq 0 ]; then
echo "cp -d \"$distBin\"/*.cfg \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFile
fi
@@ -970,14 +1016,12 @@ package_lightning_static() {
if [ "$BUILD_MANPAGES" == "ON" ]; then
if [ $BUILD_ALT -eq 0 ]; then
echo "mkdir -p \$RPM_BUILD_ROOT/$installPath/share/man/man1" >> $specFile
for i in "${core_man_pages[@]}"; do
if [ -f "$distMan/man1/$i" ]; then
echo "gzip -f $distMan/man1/$i" >> $specFile
echo "cp -d $distMan/man1/${i}.gz \$RPM_BUILD_ROOT/$installPath/share/man/man1/" >> $specFile
fi
done
if [ -f "$distMan/man1/clang.1.gz" ]; then
for i in "${amd_man_pages[@]}"; do
echo "ln -sf clang.1.gz \"$distMan/man1/$i\"" >> $specFile
@@ -1064,7 +1108,6 @@ package_lightning_static() {
contains "$bin" "${core_bin[@]}" "${amd_compiler_commands[@]}" && continue
echo "cp -d \"$i\" \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFileExtra
done
for i in "$distLib"/*; do
lib=$(basename "$i")
contains "$lib" "${core_lib[@]}" && continue
@@ -1072,18 +1115,15 @@ package_lightning_static() {
done
echo "cp -R $distInc \$RPM_BUILD_ROOT/$installPath" >> $specFileExtra
echo "rm -rf \$RPM_BUILD_ROOT/$installPath/lib/clang" >> $specFileExtra
if [ $FLANG_NEW -eq 1 ]; then
echo "rm -rf \$RPM_BUILD_ROOT/$installPath/include/flang" >> $specFileExtra
fi
if [ "$BUILD_MANPAGES" == "ON" ]; then
if [ $BUILD_ALT -eq 0 ]; then
echo "mkdir -p \$RPM_BUILD_ROOT/$installPath/share/man/man1" >> $specFileExtra
for i in "${extra_man_pages[@]}"; do
if [ -f "$distMan/man1/$i" ]; then
echo "gzip -f $distMan/man1/$i" >> $specFileExtra
@@ -1125,34 +1165,34 @@ package_docs() {
local packageName="rocm-llvm-docs"
local packageSummary="ROCm LLVM compiler documentation"
local packageSummaryLong="Documenation for LLVM $llvmParsedVersion"
local installPath="$ROCM_INSTALL_PATH/lib/llvm/share"
local packageArch="amd64"
local packageVersion="${llvmParsedVersion}.${LLVM_COMMIT_GITDATE}"
local packageMaintainer="ROCm Compiler Support <rocm.compiler.support@amd.com>"
local distDoc="$INSTALL_PATH/share/doc"
local distDoc="$INSTALL_PATH/share/doc/LLVM"
local licenseDir="$ROCM_INSTALL_PATH/share/doc/$packageName"
local packageDir="$BUILD_PATH/package"
local packageDeb="$packageDir/deb"
local controlFile="$packageDeb/DEBIAN/control"
local debDependencies="rocm-core"
local packageRpm="$packageDir/rpm"
local specFile="$packageDir/$packageName.spec"
local rpmRequires="rocm-core"
rm -rf "$packageDir"
echo "rm -rf $packageDir"
if [ "$PACKAGEEXT" = "deb" ]; then
mkdir -p "$packageDeb/$installPath"
mkdir "${controlFile%/*}"
mkdir -p "$packageDeb/$licenseDir"
mkdir "${controlFile%/*}"
cp -r "$LLVM_ROOT_LCL/LICENSE.TXT" "$packageDeb/$licenseDir"
cp -r "$distDoc" "$packageDeb/$installPath/doc"
cp -r "$distDoc" "$packageDeb/$licenseDir"
{
echo "Package: $packageName"
@@ -1162,6 +1202,7 @@ package_docs() {
echo "Maintainer: $packageMaintainer"
echo "Version: ${packageVersion}.${ROCM_LIBPATCH_VERSION}-${JOB_DESIGNATOR}${BUILD_ID}~${DISTRO_RELEASE}"
echo "Release: ${JOB_DESIGNATOR}${BUILD_ID}~${DISTRO_RELEASE}"
echo "Depends: $debDependencies"
echo "Recommends: $debRecommends"
echo "Description: $packageSummary"
echo " $packageSummaryLong"
@@ -1182,6 +1223,7 @@ package_docs() {
echo "Summary: $packageSummary" >> $specFile
echo "Group: System Environment/Libraries" >> $specFile
echo "License: ASL 2.0 with exceptions" >> $specFile
echo "Requires: $rpmRequires" >> $specFile
echo "%description" >> $specFile
echo "$packageSummaryLong" >> $specFile
@@ -1190,16 +1232,13 @@ package_docs() {
echo "%setup -T -D -c -n $packageName" >> $specFile
echo "%install" >> $specFile
echo "rm -rf \$RPM_BUILD_ROOT/$installPath" >> $specFile
echo "mkdir -p \$RPM_BUILD_ROOT/$installPath/doc" >> $specFile
echo "mkdir -p \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
echo "cp -R \"$distDoc\" \$RPM_BUILD_ROOT/$installPath" >> $specFile
echo "cp -R \"$distDoc\" \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
echo "%clean" >> $specFile
echo "rm -rf \$RPM_BUILD_ROOT/$installPath" >> $specFile
echo "%files " >> $specFile
echo "%defattr(-,root,root,-)" >> $specFile
@@ -1232,6 +1271,18 @@ build() {
fi
}
create_wheel_package() {
echo "Creating rocm-llvm wheel package"
mkdir -p "$ROCM_WHEEL_DIR"
cp -f $SCRIPT_ROOT/generate_setup_py.py $ROCM_WHEEL_DIR
cp -f $SCRIPT_ROOT/repackage_wheel.sh $ROCM_WHEEL_DIR
cd $ROCM_WHEEL_DIR
# Currently only supports python3.6
./repackage_wheel.sh $RPM_PATH/rocm-llvm*.rpm python3.6
# Copy the wheel created to RPM folder which will be uploaded to artifactory
mv "$ROCM_WHEEL_DIR"/dist/*.whl "$RPM_PATH"
}
case $TARGET in
(clean) clean_lightning ;;
(all)
@@ -1250,4 +1301,9 @@ case $TARGET in
(*) die "Invalid target $TARGET" ;;
esac
if [[ $WHEEL_PACKAGE == true ]]; then
echo "Wheel Package build started !!!!"
create_wheel_package
fi
echo "Operation complete"

View File

@@ -44,7 +44,7 @@ build_miopen_deps() {
cd "$COMPONENT_SRC"
# Commenting the rocMLIR & composable_kernel from requirements.txt
sed -i '/ROCmSoftwarePlatform\/rocMLIR@\|ROCmSoftwarePlatform\/composable_kernel@/s/^/#/' requirements.txt
sed -i '/ROCm\/rocMLIR@\|ROCm\/composable_kernel@/s/^/#/' requirements.txt
# Extract MLIR commit from requirements.txt
MLIR_COMMIT="$(awk '/rocMLIR/ {split($1, s, "@"); print s[2]}' requirements.txt)"

View File

@@ -13,7 +13,7 @@ build_miopen_hip() {
echo "Start build"
cd $COMPONENT_SRC
git config --global --add safe.directory "$COMPONENT_SRC"
checkout_lfs
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
@@ -22,8 +22,9 @@ build_miopen_hip() {
fi
mkdir "$BUILD_DIR" && cd "$BUILD_DIR"
init_rocm_common_cmake_params
cmake \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DMIOPEN_BACKEND=HIP \
-DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
-DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \

View File

@@ -16,6 +16,8 @@ build_mivisionx() {
BUILD_DEV=OFF
fi
init_rocm_common_cmake_params
if [ -n "$GPU_ARCHS" ]; then
GPU_TARGETS="$GPU_ARCHS"
else
@@ -23,7 +25,7 @@ build_mivisionx() {
fi
cmake \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DROCM_PATH="$ROCM_PATH" \
-DBUILD_DEV=$BUILD_DEV \
-DCMAKE_INSTALL_LIBDIR=$(getInstallLibDir) \

View File

@@ -0,0 +1,171 @@
#!/bin/bash
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
printUsage() {
echo
echo "Usage: ${BASH_SOURCE##*/} [options ...]"
echo
echo "Options:"
echo " -c, --clean Clean output and delete all intermediate work"
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
echo " -p, --package <type> Specify packaging format"
echo " -r, --release Make a release build instead of a debug build"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
echo " -w, --wheel Creates python wheel package of omniperf.
It needs to be used along with -r option"
echo " -h, --help Prints this help"
echo
echo "Possible values for <type>:"
echo " deb -> Debian format (default)"
echo " rpm -> RPM format"
echo
return 0
}
API_NAME="omniperf"
PROJ_NAME="$API_NAME"
LIB_NAME="lib${API_NAME}"
TARGET="build"
MAKETARGET="deb"
PACKAGE_ROOT="$(getPackageRoot)"
PACKAGE_LIB="$(getLibPath)"
BUILD_DIR="$(getBuildPath $API_NAME)"
PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
ROCM_WHEEL_DIR="${BUILD_DIR}/_wheel"
BUILD_TYPE="Debug"
MAKE_OPTS="$DASH_JAY -C $BUILD_DIR"
SHARED_LIBS="ON"
CLEAN_OR_OUT=0;
MAKETARGET="deb"
PKGTYPE="deb"
WHEEL_PACKAGE=false
#parse the arguments
VALID_STR=$(getopt -o hcraso:p:w --long help,clean,release,static,address_sanitizer,outdir:,package:,wheel -- "$@")
eval set -- "$VALID_STR"
while true ;
do
case "$1" in
-h | --help)
printUsage ; exit 0;;
-c | --clean)
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
-r | --release)
BUILD_TYPE="Release" ; shift ;;
-a | --address_sanitizer)
set_asan_env_vars
set_address_sanitizer_on ; shift ;;
-s | --static)
SHARED_LIBS="OFF" ; shift ;;
-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
-p | --package)
MAKETARGET="$2" ; shift 2 ;;
-w | --wheel)
WHEEL_PACKAGE=true ; shift ;;
--) shift; break;; # end delimiter
*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
esac
done
RET_CONFLICT=1
check_conflicting_options "$CLEAN_OR_OUT" "$PKGTYPE" "$MAKETARGET"
if [ $RET_CONFLICT -ge 30 ]; then
print_vars "$API_NAME" "$TARGET" "$BUILD_TYPE" "$SHARED_LIBS" "$CLEAN_OR_OUT" "$PKGTYPE" "$MAKETARGET"
exit $RET_CONFLICT
fi
clean() {
echo "Cleaning $PROJ_NAME"
rm -rf "$ROCM_WHEEL_DIR"
rm -rf "$BUILD_DIR"
rm -rf "$PACKAGE_DEB"
rm -rf "$PACKAGE_RPM"
rm -rf "$PACKAGE_ROOT/${PROJ_NAME:?}"
rm -rf "$PACKAGE_LIB/${LIB_NAME:?}"*
}
build() {
echo "Building $PROJ_NAME"
if [ "$DISTRO_ID" = centos-7 ]; then
echo "Skip make and uploading packages for Omniperf on Centos7 distro, due to python dependency"
exit 0
fi
if [ ! -d "$BUILD_DIR" ]; then
mkdir -p "$BUILD_DIR"
pushd "$BUILD_DIR" || exit
echo "ROCm CMake Params: $(rocm_cmake_params)"
echo "ROCm Common CMake Params: $(rocm_common_cmake_params)"
print_lib_type $SHARED_LIBS
cmake \
$(rocm_cmake_params) \
$(rocm_common_cmake_params) \
-DCHECK_PYTHON_DEPS=NO \
-DPYTHON_DEPS=${BUILD_DIR}/python-libs \
-DMOD_INSTALL_PATH=${BUILD_DIR}/modulefiles \
"$OMNIPERF_ROOT"
fi
make $MAKE_OPTS
make $MAKE_OPTS install
make $MAKE_OPTS package
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
}
create_wheel_package() {
echo "Creating Omniperf wheel package"
# Copy the setup.py generator to build folder
mkdir -p "$ROCM_WHEEL_DIR"
cp -f "$SCRIPT_ROOT"/generate_setup_py.py "$ROCM_WHEEL_DIR"
cp -f "$SCRIPT_ROOT"/repackage_wheel.sh "$ROCM_WHEEL_DIR"
cd "$ROCM_WHEEL_DIR" || exit
# Currently only supports python3.6
./repackage_wheel.sh "$BUILD_DIR"/*.rpm python3.6
# Copy the wheel created to RPM folder which will be uploaded to artifactory
copy_if WHL "WHL" "$PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
}
print_output_directory() {
case ${PKGTYPE} in
("deb")
echo "${PACKAGE_DEB}";;
("rpm")
echo "${PACKAGE_RPM}";;
(*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
esac
exit
}
verifyEnvSetup
case "$TARGET" in
(clean) clean ;;
(build) build ;;
(outdir) print_output_directory ;;
(*) die "Invalid target $TARGET" ;;
esac
if [[ $WHEEL_PACKAGE == true ]]; then
echo "Wheel Package build started !!!!"
create_wheel_package
fi
echo "Operation complete"

View File

@@ -0,0 +1,191 @@
#!/bin/bash
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
printUsage() {
echo
echo "Usage: ${BASH_SOURCE##*/} [options ...]"
echo
echo "Options:"
echo " -c, --clean Clean output and delete all intermediate work"
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
echo " -p, --package <type> Specify packaging format"
echo " -r, --release Make a release build instead of a debug build"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
echo " -w, --wheel Creates python wheel package of omnitrace.
It needs to be used along with -r option"
echo " -h, --help Prints this help"
echo
echo "Possible values for <type>:"
echo " deb -> Debian format (default)"
echo " rpm -> RPM format"
echo
return 0
}
API_NAME="omnitrace"
PROJ_NAME="$API_NAME"
LIB_NAME="lib${API_NAME}"
TARGET="build"
MAKETARGET="deb"
PACKAGE_ROOT="$(getPackageRoot)"
PACKAGE_LIB="$(getLibPath)"
BUILD_DIR="$(getBuildPath $API_NAME)"
PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
BUILD_TYPE="Debug"
MAKE_OPTS="-j 8"
SHARED_LIBS="ON"
CLEAN_OR_OUT=0
MAKETARGET="deb"
PKGTYPE="deb"
ASAN=0
#parse the arguments
VALID_STR=$(getopt -o hcraso:p:w --long help,clean,release,address_sanitizer,static,outdir:,package:,wheel -- "$@")
eval set -- "$VALID_STR"
while true; do
case "$1" in
-h | --help)
printUsage
exit 0
;;
-c | --clean)
TARGET="clean"
((CLEAN_OR_OUT |= 1))
shift
;;
-r | --release)
BUILD_TYPE="RelWithDebInfo"
shift
;;
-a | --address_sanitizer)
ack_and_ignore_asan
ASAN=1
shift
;;
-s | --static)
SHARED_LIBS="OFF"
shift
;;
-o | --outdir)
TARGET="outdir"
PKGTYPE=$2
((CLEAN_OR_OUT |= 2))
shift 2
;;
-p | --package)
MAKETARGET="$2"
shift 2
;;
-w | --wheel)
echo "omnitrace: wheel build option accepted and ignored"
shift
;;
--)
shift
break
;;
*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] " >&2
exit 20
;;
esac
done
RET_CONFLICT=1
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
if [ $RET_CONFLICT -ge 30 ]; then
print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
exit $RET_CONFLICT
fi
clean() {
echo "Cleaning $PROJ_NAME"
rm -rf "$BUILD_DIR"
rm -rf "$PACKAGE_DEB"
rm -rf "$PACKAGE_RPM"
rm -rf "$PACKAGE_ROOT/${PROJ_NAME:?}"
rm -rf "$PACKAGE_LIB/${LIB_NAME:?}"*
}
build_omnitrace() {
echo "Building $PROJ_NAME"
if [ "$DISTRO_ID" = "mariner-2.0" ] || [ "$DISTRO_ID" = "ubuntu-24.04" ] || [ "$DISTRO_ID" = "azurelinux-3.0" ]; then
echo "Skip make and uploading packages for Omnitrace on \"${DISTRO_ID}\" distro"
exit 0
fi
if [ $ASAN == 1 ]; then
echo "Skip make and uploading packages for Omnitrace on ASAN build"
exit 0
fi
if [ ! -d "$BUILD_DIR" ]; then
mkdir -p "$BUILD_DIR"
echo "Created build directory: $BUILD_DIR"
fi
echo "Build directory: $BUILD_DIR"
pushd "$BUILD_DIR" || exit
print_lib_type $SHARED_LIBS
echo "ROCm CMake Params: $(rocm_cmake_params)"
echo "ROCm Common CMake Params: $(rocm_common_cmake_params)"
if [ $ASAN == 1 ]; then
echo "Address Sanitizer path"
else
cmake \
$(rocm_cmake_params) \
$(rocm_common_cmake_params) \
-DOMNITRACE_BUILD_{LIBUNWIND,DYNINST}=ON \
-DDYNINST_BUILD_{TBB,BOOST,ELFUTILS,LIBIBERTY}=ON \
"$OMNITRACE_ROOT"
fi
popd || exit
echo "Make Options: $MAKE_OPTS"
cmake --build "$BUILD_DIR" --target all -- $MAKE_OPTS
cmake --build "$BUILD_DIR" --target install -- $MAKE_OPTS
cmake --build "$BUILD_DIR" --target package -- $MAKE_OPTS
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
}
print_output_directory() {
case ${PKGTYPE} in
"deb")
echo "${PACKAGE_DEB}"
;;
"rpm")
echo "${PACKAGE_RPM}"
;;
*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2
exit 1
;;
esac
exit
}
verifyEnvSetup
case "$TARGET" in
clean) clean ;;
build) build_omnitrace ;;
outdir) print_output_directory ;;
*) die "Invalid target $TARGET" ;;
esac
echo "Operation complete"

View File

@@ -0,0 +1,141 @@
#!/bin/bash
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
PROJ_NAME=OpenCL-ICD-Loader
TARGET="build"
MAKEOPTS="$DASH_JAY"
BUILD_TYPE="Debug"
PACKAGE_ROOT="$(getPackageRoot)"
PACKAGE_DEB="$PACKAGE_ROOT/deb/${PROJ_NAME,,}"
PACKAGE_RPM="$PACKAGE_ROOT/rpm/${PROJ_NAME,,}"
CLEAN_OR_OUT=0;
PKGTYPE="deb"
MAKETARGET="deb"
API_NAME="rocm-opencl-icd-loader"
printUsage() {
echo
echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
echo
echo "Options:"
echo " -c, --clean Clean output and delete all intermediate work"
echo " -p, --package <type> Specify packaging format"
echo " -r, --release Make a release build instead of a debug build"
echo " -h, --help Prints this help"
echo " -o, --outdir Print path of output directory containing packages"
echo " -s, --static Component/Build does not support static builds just accepting this param & ignore. No effect of the param on this build"
echo
echo "Possible values for <type>:"
echo " deb -> Debian format (default)"
echo " rpm -> RPM format"
echo
return 0
}
RET_CONFLICT=1
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
if [ $RET_CONFLICT -ge 30 ]; then
print_vars $TARGET $BUILD_TYPE $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
exit $RET_CONFLICT
fi
clean_opencl_icd_loader() {
echo "Cleaning $PROJ_NAME"
rm -rf "$PACKAGE_DEB"
rm -rf "$PACKAGE_RPM"
rm -rf "$PACKAGE_ROOT/${PROJ_NAME,,}"
}
copy_pkg_files_to_rocm() {
local comp_folder=$1
local comp_pkg_name=$2
cd "${OUT_DIR}/${PKGTYPE}/${comp_folder}"|| exit 2
if [ "${PKGTYPE}" = 'deb' ]; then
dpkg-deb -x ${comp_pkg_name}_*.deb pkg/
else
mkdir pkg && pushd pkg/ || exit 2
if [[ "${comp_pkg_name}" != *-dev* ]]; then
rpm2cpio ../${comp_pkg_name}-*.rpm | cpio -idmv
else
rpm2cpio ../${comp_pkg_name}el-*.rpm | cpio -idmv
fi
popd || exit 2
fi
ls ./pkg -alt
cp -r ./pkg/*/rocm*/* "${ROCM_PATH}" || exit 2
rm -rf pkg/
}
build_opencl_icd_loader() {
echo "Downloading $PROJ_NAME" package
if [ "$DISTRO_NAME" = ubuntu ]; then
mkdir -p "$PACKAGE_DEB"
local rocm_ver=${ROCM_VERSION}
if [ ${ROCM_VERSION##*.} = 0 ]; then
rocm_ver=${ROCM_VERSION%.*}
fi
local url="https://repo.radeon.com/rocm/apt/${rocm_ver}/pool/main/r/${API_NAME}/"
local package
package=$(curl -s "$url" | grep -Po 'href="\K[^"]*' | grep "${DISTRO_RELEASE}" | head -n 1)
if [ -z "$package" ]; then
echo "No package found for Ubuntu version $DISTRO_RELEASE"
exit 1
fi
wget -t3 -P "$PACKAGE_DEB" "${url}${package}"
copy_pkg_files_to_rocm ${PROJ_NAME,,} ${API_NAME}
else
echo "$DISTRO_ID is not supported..."
exit 2
fi
echo "Installing $PROJ_NAME" package
}
print_output_directory() {
case ${PKGTYPE} in
("deb")
echo ${PACKAGE_DEB};;
("rpm")
echo ${PACKAGE_RPM};;
(*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
esac
exit
}
VALID_STR=`getopt -o hcraswlo:p: --long help,clean,release,outdir:,package: -- "$@"`
eval set -- "$VALID_STR"
while true ;
do
case "$1" in
(-c | --clean )
TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
(-r | --release )
BUILD_TYPE="RelWithDebInfo" ; shift ;;
(-h | --help )
printUsage ; exit 0 ;;
(-a | --address_sanitizer)
ack_and_ignore_asan ; shift ;;
(-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
(-p | --package)
MAKETARGET="$2" ; shift 2;;
(-s | --static)
echo "-s parameter accepted but ignored" ; shift ;;
--) shift; break;;
(*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
esac
done
case $TARGET in
(clean) clean_opencl_icd_loader ;;
(build) build_opencl_icd_loader ;;
(outdir) print_output_directory ;;
(*) die "Invalid target $TARGET" ;;
esac
echo "Operation complete"

View File

@@ -26,14 +26,16 @@ build_rccl() {
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
fi
init_rocm_common_cmake_params
CC=${ROCM_PATH}/bin/amdclang \
CXX=$(set_build_variables CXX) \
cmake \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
-DHIP_COMPILER=clang \
-DCMAKE_PREFIX_PATH="${ROCM_PATH};${ROCM_PATH}/share/rocm/cmake/" \
${LAUNCHER_FLAGS} \
-DCPACK_GENERATOR="${PKGTYPE^^}" \
-DROCM_PATCH_VERSION=$ROCM_LIBPATCH_VERSION \
-DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \

53
tools/rocm-build/build_rocal.sh Executable file
View File

@@ -0,0 +1,53 @@
#!/bin/bash
set -ex
source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
set_component_src rocAL
build_rocal() {
if [ "$DISTRO_ID" = "mariner-2.0" ] ; then
echo "Not building rocal for ${DISTRO_ID}. Exiting..."
return 0
fi
echo "Start build"
# Enable ASAN
if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
set_asan_env_vars
set_address_sanitizer_on
fi
mkdir -p $BUILD_DIR && cd $BUILD_DIR
python3 ${COMPONENT_SRC}/rocAL-setup.py
cmake -DAMDRPP_PATH=$ROCM_PATH ${COMPONENT_SRC}
make -j${PROC}
cmake --build . --target PyPackageInstall
sudo make install
sudo make package
sudo chown -R $(id -u):$(id -g) ${BUILD_DIR}
rm -rf _CPack_Packages/ && find -name '*.o' -delete
mkdir -p $PACKAGE_DIR
cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
show_build_cache_stats
}
clean_rocal() {
echo "Cleaning rocAL build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
echo "Done!"
}
stage2_command_args "$@"
case $TARGET in
build) build_rocal ;;
outdir) print_output_directory ;;
clean) clean_rocal ;;
*) die "Invalid target $TARGET" ;;
esac

View File

@@ -22,6 +22,7 @@ build_rocalution() {
echo "CXX compiler: $CXX"
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
init_rocm_common_cmake_params
if [ -n "$GPU_ARCHS" ]; then
GPU_TARGETS="$GPU_ARCHS"
@@ -32,7 +33,7 @@ build_rocalution() {
cmake \
-DSUPPORT_HIP=ON \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
-DCPACK_SET_DESTDIR=OFF \
-DBUILD_CLIENTS_SAMPLES=ON \

View File

@@ -28,11 +28,12 @@ build_rocblas() {
else
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack+;gfx90a:xnack-;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
fi
init_rocm_common_cmake_params
cmake \
-DCMAKE_TOOLCHAIN_FILE=toolchain-linux.cmake \
-DBUILD_DIR="${BUILD_DIR}" \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DROCM_DIR="${ROCM_PATH}" \
${LAUNCHER_FLAGS} \
-DCMAKE_PREFIX_PATH="${DEPS_DIR};${ROCM_PATH}" \

View File

@@ -4,15 +4,16 @@ source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
set_component_src rocDecode
BUILD_DEV=ON
build_rocdecode() {
if [ "$DISTRO_ID" = "centos-7" ] ; then
if [ "$DISTRO_ID" = "centos-7" ] || [ "$DISTRO_ID" = "sles-15.4" ] ; then
echo "Not building rocDecode for ${DISTRO_ID}. Exiting..."
return 0
fi
echo "Start build"
mkdir -p $BUILD_DIR && cd $BUILD_DIR
python3 ${COMPONENT_SRC}/rocDecode-setup.py --developer OFF
cmake ${COMPONENT_SRC}
cmake -DROCM_DEP_ROCMCORE=ON ${COMPONENT_SRC}
make -j8
make install
make package

View File

@@ -16,6 +16,7 @@ build_rocfft() {
set_address_sanitizer_on
fi
mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
init_rocm_common_cmake_params
if [ -n "$GPU_ARCHS" ]; then
GPU_TARGETS="$GPU_ARCHS"
@@ -26,7 +27,7 @@ build_rocfft() {
CXX="${ROCM_PATH}/bin/hipcc" \
cmake \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
-DUSE_HIP_CLANG=ON \
-DHIP_COMPILER=clang \

View File

@@ -10,11 +10,13 @@ printUsage() {
echo " -c, --clean Clean output and delete all intermediate work"
echo " -r, --release Build a release version of the package"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -s, --static Supports static CI by accepting this param & not bailing out. No effect of the param though"
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
echo " -w, --wheel Creates python wheel package of rocm-cmake.
It needs to be used along with -r option"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
echo " -p, --package <type> Specify packaging format"
echo " -h, --help Prints this help"
echo " -h, --help Prints this help"
echo
echo
@@ -30,6 +32,7 @@ ROCM_CMAKE_BUILD_DIR="$(getBuildPath rocm-cmake)"
ROCM_CMAKE_BUILD_DIR="$(getBuildPath rocm-cmake)"
ROCM_CMAKE_PACKAGE_DEB="$(getPackageRoot)/deb/rocm-cmake"
ROCM_CMAKE_PACKAGE_RPM="$(getPackageRoot)/rpm/rocm-cmake"
ROCM_WHEEL_DIR="${ROCM_CMAKE_BUILD_DIR}/_wheel"
ROCM_CMAKE_BUILD_TYPE="debug"
BUILD_TYPE="Debug"
SHARED_LIBS="ON"
@@ -37,7 +40,7 @@ CLEAN_OR_OUT=0;
PKGTYPE="deb"
MAKETARGET="deb"
VALID_STR=`getopt -o hcraso:p: --long help,clean,release,static,address_sanitizer,outdir:,package: -- "$@"`
VALID_STR=`getopt -o hcraswo:p: --long help,clean,release,static,wheel,address_sanitizer,outdir:,package: -- "$@"`
eval set -- "$VALID_STR"
while true ;
@@ -53,6 +56,8 @@ do
ack_and_ignore_asan ; shift ;;
(-s | --static)
SHARED_LIBS="OFF" ; shift ;;
(-w | --wheel)
WHEEL_PACKAGE=true ; shift ;;
(-o | --outdir)
TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
(-p | --package)
@@ -73,6 +78,7 @@ fi
clean_rocm_cmake() {
rm -rf "$ROCM_WHEEL_DIR"
rm -rf $ROCM_CMAKE_BUILD_DIR
rm -rf $ROCM_CMAKE_PACKAGE_DEB
rm -rf $ROCM_CMAKE_PACKAGE_RPM
@@ -87,6 +93,7 @@ build_rocm_cmake() {
cmake \
$(rocm_cmake_params) \
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
-DCPACK_SET_DESTDIR="OFF" \
-DROCM_DISABLE_LDCONFIG=ON \
$ROCM_CMAKE_ROOT
@@ -99,6 +106,19 @@ build_rocm_cmake() {
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$ROCM_CMAKE_PACKAGE_RPM" $ROCM_CMAKE_BUILD_DIR/rocm-cmake*.rpm
}
create_wheel_package() {
echo "Creating rocm-cmake wheel package"
# Copy the setup.py generator to build folder
mkdir -p $ROCM_WHEEL_DIR
cp -f $SCRIPT_ROOT/generate_setup_py.py $ROCM_WHEEL_DIR
cp -f $SCRIPT_ROOT/repackage_wheel.sh $ROCM_WHEEL_DIR
cd $ROCM_WHEEL_DIR
# Currently only supports python3.6
./repackage_wheel.sh $ROCM_CMAKE_BUILD_DIR/rocm-cmake*.rpm python3.6
# Copy the wheel created to RPM folder which will be uploaded to artifactory
copy_if WHL "WHL" "$ROCM_CMAKE_PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
}
print_output_directory() {
case ${PKGTYPE} in
("deb")
@@ -118,4 +138,9 @@ case $TARGET in
(*) die "Invalid target $TARGET" ;;
esac
if [[ $WHEEL_PACKAGE == true ]]; then
echo "Wheel Package build started !!!!"
create_wheel_package
fi
echo "Operation complete"

View File

@@ -24,13 +24,14 @@ build_rocprim() {
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
fi
init_rocm_common_cmake_params
CXX="${ROCM_PATH}/bin/hipcc" \
cmake \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
-DBUILD_BENCHMARK=OFF \
-DBUILD_BENCHMARK=OFF \
-DBUILD_SHARED_LIBS=ON \
-DBUILD_TEST=ON \
-DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip;${ROCM_PATH}/hip/cmake" \
"$COMPONENT_SRC"

View File

@@ -0,0 +1,222 @@
#!/bin/bash
source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
printUsage() {
echo
echo "Usage: ${BASH_SOURCE##*/} [options ...]"
echo
echo "Options:"
echo " -c, --clean Clean output and delete all intermediate work"
echo " -s, --static Build static lib (.a). build instead of dynamic/shared(.so) "
echo " -w, --wheel Creates python wheel package of rocprofiler-sdk.
It needs to be used along with -r option"
echo " -p, --package <type> Specify packaging format"
echo " -r, --release Make a release build instead of a debug build"
echo " -a, --address_sanitizer Enable address sanitizer"
echo " -o, --outdir <pkg_type> Print path of output directory containing packages of
type referred to by pkg_type"
echo " -h, --help Prints this help"
echo
echo "Possible values for <type>:"
echo " deb -> Debian format (default)"
echo " rpm -> RPM format"
echo
return 0
}
API_NAME="rocprofiler-sdk"
PROJ_NAME="$API_NAME"
LIB_NAME="lib${API_NAME}"
TARGET="build"
MAKETARGET="deb"
PACKAGE_ROOT="$(getPackageRoot)"
PACKAGE_LIB="$(getLibPath)"
PACKAGE_INCLUDE="$(getIncludePath)"
BUILD_DIR="$(getBuildPath $API_NAME)"
PACKAGE_DEB="$(getPackageRoot)/deb/$API_NAME"
PACKAGE_RPM="$(getPackageRoot)/rpm/$API_NAME"
ROCM_WHEEL_DIR="${BUILD_DIR}/_wheel"
PACKAGE_PREFIX="$ROCM_INSTALL_PATH"
BUILD_TYPE="Debug"
MAKE_OPTS="$DASH_JAY"
SHARED_LIBS="ON"
CLEAN_OR_OUT=0
MAKETARGET="deb"
PKGTYPE="deb"
GPU_LIST="gfx900;gfx906;gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1031;gfx1100;gfx1101;gfx1102"
ASAN=0
VALID_STR=$(getopt -o hcrawso:p: --long help,clean,release,static,address_sanitizer,wheel,outdir:,package: -- "$@")
eval set -- "$VALID_STR"
while true; do
case "$1" in
-h | --help)
printUsage
exit 0
;;
-c | --clean)
TARGET="clean"
((CLEAN_OR_OUT |= 1))
shift
;;
-r | --release)
BUILD_TYPE="RelWithDebInfo"
shift
;;
-a | --address_sanitizer)
set_address_sanitizer_on
set_asan_env_vars
ASAN=1
shift
;;
-s | --static)
SHARED_LIBS="OFF"
shift
;;
-w | --wheel)
WHEEL_PACKAGE=true
shift
;;
-o | --outdir)
TARGET="outdir"
PKGTYPE=$2
OUT_DIR_SPECIFIED=1
((CLEAN_OR_OUT |= 2))
shift 2
;;
-p | --package)
MAKETARGET="$2"
shift 2
;;
--)
shift
break
;; # end delimiter
*)
echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] " >&2
exit 20
;;
esac
done
RET_CONFLICT=1
check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
if [ $RET_CONFLICT -ge 30 ]; then
print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
exit $RET_CONFLICT
fi
clean() {
echo "Cleaning $PROJ_NAME"
rm -rf "$ROCM_WHEEL_DIR"
rm -rf "$BUILD_DIR"
rm -rf "$PACKAGE_DEB"
rm -rf "$PACKAGE_RPM"
rm -rf "$PACKAGE_ROOT/${PROJ_NAME}"
rm -rf "$PACKAGE_ROOT/libexec/${PROJ_NAME}"
rm -rf "$PACKAGE_INCLUDE/${PROJ_NAME}"
rm -rf "$PACKAGE_LIB/${LIB_NAME}"*
rm -rf "$PACKAGE_LIB/${PROJ_NAME}"
}
build_rocprofiler-sdk() {
if [ ! -f "${ROCPROFILER_SDK_ROOT}/CMakeLists.txt" ]; then
echo "Warning: $ROCPROFILER_SDK_ROOT not found"
else
echo "Building $PROJ_NAME"
PACKAGE_CMAKE="$(getCmakePath)"
if [ ! -d "$BUILD_DIR" ]; then
mkdir -p "$BUILD_DIR"
pushd "$BUILD_DIR"
print_lib_type $SHARED_LIBS
if [ $ASAN == 1 ]; then
cmake \
$(rocm_cmake_params) \
$(rocm_common_cmake_params) \
-DAMDDeviceLibs_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/AMDDeviceLibs" \
-Dhip_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hip" \
-Dhip-lang_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hip-lang" \
-Damd_comgr_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/amd_comgr" \
-Dhsa-runtime64_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hsa-runtime64" \
-Dhsakmt_DIR="${ROCM_INSTALL_PATH}/lib/asan/cmake/hsakmt" \
-DCMAKE_HIP_COMPILER_ROCM_ROOT="${ROCM_INSTALL_PATH}" \
-DCMAKE_PREFIX_PATH="${ROCM_INSTALL_PATH};${ROCM_INSTALL_PATH}/lib/asan" \
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
-DGPU_TARGETS="$GPU_LIST" \
-DCPACK_DEBIAN_PACKAGE_SHLIBDEPS=OFF \
-DPython3_EXECUTABLE=$(which python3) \
"$ROCPROFILER_SDK_ROOT"
else
cmake \
$(rocm_cmake_params) \
$(rocm_common_cmake_params) \
-DCMAKE_PREFIX_PATH="${ROCM_INSTALL_PATH}" \
-DBUILD_SHARED_LIBS=$SHARED_LIBS \
-DGPU_TARGETS="$GPU_LIST" \
-DROCPROFILER_BUILD_SAMPLES=ON \
-DROCPROFILER_BUILD_TESTS=ON \
-DCPACK_DEBIAN_PACKAGE_SHLIBDEPS=OFF \
-DPython3_EXECUTABLE=$(which python3) \
"$ROCPROFILER_SDK_ROOT"
fi
popd
fi
cmake --build "$BUILD_DIR" --target all -- $MAKE_OPTS
cmake --build "$BUILD_DIR" --target install -- $MAKE_OPTS
cmake --build "$BUILD_DIR" --target package -- $MAKE_OPTS
copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" "$BUILD_DIR/${API_NAME}"*.deb
copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" "$BUILD_DIR/${API_NAME}"*.rpm
fi
}
create_wheel_package() {
echo "Creating rocprofiler sdk wheel package"
mkdir -p "$ROCM_WHEEL_DIR"
cp -f "$SCRIPT_ROOT"/generate_setup_py.py "$ROCM_WHEEL_DIR"
cp -f "$SCRIPT_ROOT"/repackage_wheel.sh "$ROCM_WHEEL_DIR"
cd "$ROCM_WHEEL_DIR"
# Currently only supports python3.6
./repackage_wheel.sh "$BUILD_DIR"/*.rpm python3.6
# Copy the wheel created to RPM folder which will be uploaded to artifactory
copy_if WHL "WHL" "$PACKAGE_RPM" "$ROCM_WHEEL_DIR"/dist/*.whl
}
print_output_directory() {
case ${PKGTYPE} in
"deb")
echo ${PACKAGE_DEB}
;;
"rpm")
echo ${PACKAGE_RPM}
;;
*)
echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2
exit 1
;;
esac
exit
}
verifyEnvSetup
case "$TARGET" in
clean) clean ;;
build) build_rocprofiler-sdk ;;
outdir) print_output_directory ;;
*) die "Invalid target $TARGET" ;;
esac
if [[ $WHEEL_PACKAGE == true ]]; then
echo "Wheel Package build started !!!!"
create_wheel_package
fi
echo "Operation complete"

View File

@@ -25,10 +25,12 @@ build_rocrand() {
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
fi
init_rocm_common_cmake_params
CXX=$(set_build_variables CXX)\
cmake \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
-DBUILD_TEST=ON \
-DBUILD_BENCHMARK=ON \

View File

@@ -28,11 +28,13 @@ build_rocsolver() {
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
fi
init_rocm_common_cmake_params
CXX="${ROCM_PATH}/bin/hipcc" \
cmake \
-DCPACK_SET_DESTDIR=OFF \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-Drocblas_DIR="${ROCM_PATH}/rocblas/lib/cmake/rocblas" \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
-DBUILD_CLIENTS_TESTS=ON \

View File

@@ -27,12 +27,14 @@ build_rocsparse() {
fi
ROCSPARSE_TEST_MIRROR=$MIRROR \
CXX=$(set_build_variables CXX)\
CC=$(set_build_variables CC)\
export CXX=$(set_build_variables CXX)\
export CC=$(set_build_variables CC)\
init_rocm_common_cmake_params
cmake \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}"\
-DBUILD_CLIENTS_SAMPLES=ON \
-DBUILD_CLIENTS_TESTS=ON \
-DBUILD_CLIENTS_BENCHMARKS=ON \

View File

@@ -27,10 +27,12 @@ build_rocthrust() {
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
fi
init_rocm_common_cmake_params
CXX=$(set_build_variables CXX)\
cmake \
${LAUNCHER_FLAGS} \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
-DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip;${ROCM_PATH}/hip/cmake" \
-DROCPRIM_ROOT="${ROCM_PATH}/rocprim" \

View File

@@ -27,9 +27,11 @@ build_rocwmma() {
GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1100;gfx1101"
fi
init_rocm_common_cmake_params
CXX=$(set_build_variables CXX)\
cmake \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
${LAUNCHER_FLAGS} \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
-DROCWMMA_BUILD_VALIDATION_TESTS=ON \

View File

@@ -12,7 +12,7 @@ ROCM_LLVM_LIB_RPATH="\$ORIGIN/llvm/lib"
rpp_specific_cmake_params() {
local rpp_cmake_params
if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
rpp_cmake_params="-DCMAKE_EXE_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_EXE_RPATH:$LLVM_LIBDIR"
rpp_cmake_params="-DCMAKE_EXE_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_ASAN_EXE_RPATH:$LLVM_LIBDIR"
else
rpp_cmake_params=""
fi
@@ -41,14 +41,16 @@ build_rpp() {
GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100"
fi
init_rocm_common_cmake_params
cmake \
$(rocm_common_cmake_params) \
"${rocm_math_common_cmake_params[@]}" \
${LAUNCHER_FLAGS} \
-DBACKEND=HIP \
-DCMAKE_INSTALL_LIBDIR=$(getInstallLibDir) \
$(rpp_specific_cmake_params) \
-DAMDGPU_TARGETS=${GPU_TARGETS} \
-DCMAKE_SHARED_LINKER_FLAGS_INIT="-fno-openmp-implicit-rpath -Wl,--enable-new-dtags,--rpath,${ROCM_LIB_RPATH}:${DEPS_DIR}/lib:${ROCM_LLVM_LIB_RPATH}" \
-DCMAKE_SHARED_LINKER_FLAGS_INIT="-fno-openmp-implicit-rpath -Wl,--enable-new-dtags,--build-id=sha1,--rpath,${ROCM_LIB_RPATH}:${DEPS_DIR}/lib:${ROCM_LLVM_LIB_RPATH}" \
-DCMAKE_PREFIX_PATH="${DEPS_DIR};${ROCM_PATH}" \
"$COMPONENT_SRC"

View File

@@ -189,6 +189,65 @@ echo " PKGTYPE= $6 "
echo " MAKETARGET = $7 "
}
rocm_math_common_cmake_params=()
init_rocm_common_cmake_params(){
local retCmakeParams=${1:-rocm_math_common_cmake_params}
local SET_BUILD_TYPE=${BUILD_TYPE:-'RelWithDebInfo'}
local ASAN_LIBDIR="lib/asan"
local CMAKE_PATH=$(getCmakePath)
# Common cmake parameters can be set
# component build scripts can use this function
local cmake_params
if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
cmake_params=(
"-DCMAKE_PREFIX_PATH=$CMAKE_PATH;${ROCM_PATH}/$ASAN_LIBDIR;$ROCM_PATH/llvm;$ROCM_PATH"
"-DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_ASAN_LIB_RPATH"
"-DCMAKE_EXE_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_ASAN_EXE_RPATH"
"-DENABLE_ASAN_PACKAGING=true"
)
else
cmake_params=(
"-DCMAKE_PREFIX_PATH=${ROCM_PATH}/llvm;${ROCM_PATH}"
"-DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_LIB_RPATH"
"-DCMAKE_EXE_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_EXE_RPATH"
)
fi
cmake_params+=(
"-DCMAKE_VERBOSE_MAKEFILE=1"
"-DCMAKE_BUILD_TYPE=${SET_BUILD_TYPE}"
"-DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE"
"-DCMAKE_INSTALL_PREFIX=${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=${ROCM_PATH}"
)
#TODO :remove if clause once debug related issues are fixed
if [ "${DISABLE_DEBUG_PACKAGE}" == "true" ] ; then
SET_BUILD_TYPE=${BUILD_TYPE:-'Release'}
cmake_params+=(
"-DCPACK_DEBIAN_DEBUGINFO_PACKAGE=FALSE"
"-DCPACK_RPM_DEBUGINFO_PACKAGE=FALSE"
"-DCPACK_RPM_INSTALL_WITH_EXEC=FALSE"
"-DCMAKE_BUILD_TYPE=${SET_BUILD_TYPE}"
)
elif [ "$SET_BUILD_TYPE" == "RelWithDebInfo" ] || [ "$SET_BUILD_TYPE" == "Debug" ]; then
# RelWithDebinfo optimization level -O2 is having performance impact
# So overriding the same to -O3
cmake_params+=(
"-DCPACK_DEBIAN_DEBUGINFO_PACKAGE=TRUE"
"-DCPACK_RPM_DEBUGINFO_PACKAGE=TRUE"
"-DCPACK_RPM_INSTALL_WITH_EXEC=TRUE"
"-DCMAKE_CXX_FLAGS_RELWITHDEBINFO=-O3 -g -DNDEBUG"
)
fi
eval "${retCmakeParams}=( \"\${cmake_params[@]}\" ) "
}
# Common cmake parameters can be set
# component build scripts can use this function
rocm_common_cmake_params() {

View File

@@ -2,7 +2,6 @@
set -ex
apt-get update
DEBIAN_FRONTEND=noninteractive DEBCONF_NONINTERACTIVE_SEEN=true apt-get install --no-install-recommends -y $(grep -v '^#' /tmp/packages)
apt-get clean
@@ -105,7 +104,7 @@ git clone --recurse-submodules -b v1.61.0 https://github.com/grpc/grpc
cd grpc
mkdir -p cmake/build
cd cmake/build
cmake -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF -DCMAKE_INSTALL_PREFIX=/usr/grpc -DCMAKE_CXX_STANDARD=14 ../..
cmake -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF -DCMAKE_INSTALL_PREFIX=/usr/grpc -DCMAKE_CXX_STANDARD=14 -DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,'$ORIGIN' ../..
make -j$(nproc)
make install
cd /
@@ -120,11 +119,11 @@ mv amd-blis-mt /usr/blis
cd /
rm -rf /tmp/blis
## Download aocl-linux-aocc-4.0_1_amd64.deb
## Download aocl-linux-gcc-4.2.0_1_amd64.deb
mkdir -p /tmp/aocl
cd /tmp/aocl
wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-0/aocl-linux-aocc-4.0_1_amd64.deb
apt install ./aocl-linux-aocc-4.0_1_amd64.deb
wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-2/aocl-linux-gcc-4.2.0_1_amd64.deb
apt install ./aocl-linux-gcc-4.2.0_1_amd64.deb
rm -rf /tmp/aocl
## lapack(3.9.1v)
@@ -180,8 +179,7 @@ cd ninja-1.11.1.g95dee.kitware.jobserver-1
cp ninja /usr/local/bin/
rm -rf /tmp/ninja
# Install pre-built FFmpeg and dependencies
# See docker/build-deps for instructions on how to build these packages
# Install FFmpeg from source
wget -qO- https://www.ffmpeg.org/releases/ffmpeg-4.4.2.tar.gz | tar -xzv -C /usr/local
command -v lbzip2

View File

@@ -8,6 +8,7 @@ bison
bridge-utils
build-essential
bzip2
ccache
check
chrpath
cifs-utils
@@ -97,6 +98,7 @@ libva-dev
libvirt-clients
libvirt-daemon-system
libyaml-cpp-dev
libzstd-dev
llvm
llvm-6.0-dev
llvm-dev
@@ -119,9 +121,11 @@ python3-yaml
python3.8-dev
re2c
redis-tools
# Eventually we should be able to remove rpm for debian builds.
rpm
rsync
ssh
# This makes life more pleasent inside the container
strace
sudo
systemtap-sdt-dev

View File

@@ -1,6 +1,6 @@
#! /usr/bin/bash
set -ex
set -x
apt-get -y update
DEBIAN_FRONTEND=noninteractive DEBCONF_NONINTERACTIVE_SEEN=true apt-get install --no-install-recommends -y $(sed 's/#.*//' /tmp/packages)
@@ -60,7 +60,6 @@ apt install -y sharp
apt clean
rm -rf /var/cache/apt/ /var/lib/apt/lists/* mlnx /etc/apt/sources.list.d/sharp.list
apt update
apt -y install libunwind-dev
apt -y install libgoogle-glog-dev
@@ -118,12 +117,12 @@ git clone --recurse-submodules -b v1.61.0 https://github.com/grpc/grpc
cd grpc
mkdir -p build
cd build
cmake -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF -DCMAKE_INSTALL_PREFIX=/usr/grpc -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_STANDARD=14 ..
cmake -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF -DCMAKE_INSTALL_PREFIX=/usr/grpc -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_STANDARD=14 -DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,'$ORIGIN' ..
make -j $(nproc) install
rm -rf /tmp/grpc
## rocBLAS Pre-requisites
## Download prebuilt AMD multithreaded (2.0)
## Download prebuilt AMD multithreaded blis (2.0)
## Reference : https://github.com/ROCmSoftwarePlatform/rocBLAS/blob/develop/install.sh#L403
mkdir -p /tmp/blis
cd /tmp/blis
@@ -131,12 +130,13 @@ wget -O - https://github.com/amd/blis/releases/download/2.0/aocl-blis-mt-ubuntu-
mv amd-blis-mt /usr/blis
cd /
rm -rf /tmp/blis
## rocBLAS Pre-requisites(SWDEV-404612)
## Download aocl-linux-aocc-4.0_1_amd64
## Download aocl-linux-gcc-4.2.0_1_amd64.deb
mkdir -p /tmp/aocl
cd /tmp/aocl
wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-0/aocl-linux-aocc-4.0_1_amd64.deb
apt install ./aocl-linux-aocc-4.0_1_amd64.deb
wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-2/aocl-linux-gcc-4.2.0_1_amd64.deb
apt install ./aocl-linux-gcc-4.2.0_1_amd64.deb
rm -rf /tmp/aocl
## hipBLAS Pre-requisites
@@ -194,9 +194,62 @@ cd ninja-1.11.1.g95dee.kitware.jobserver-1
cp ninja /usr/local/bin/
rm -rf /tmp/ninja
# Install pre-built FFmpeg and dependencies
# See docker/build-deps for instructions on how to build these packages
wget -qO- https://www.ffmpeg.org/releases/ffmpeg-4.4.2.tar.gz | tar -xzv -C /usr/local
# Install FFmpeg and dependencies
# Build NASM
mkdir -p /tmp/nasm-2.15.05
cd /tmp
wget -qO- "https://distfiles.macports.org/nasm/nasm-2.15.05.tar.bz2" | tar -xvj
cd nasm-2.15.05
./autogen.sh
./configure --prefix="/usr/local"
make -j$(nproc) install
rm -rf /tmp/nasm-2.15.05
# Build YASM
mkdir -p /tmp/yasm-1.3.0
cd /tmp
wget -qO- "http://www.tortall.net/projects/yasm/releases/yasm-1.3.0.tar.gz" | tar -xvz
cd yasm-1.3.0
./configure --prefix="/usr/local"
make -j$(nproc) install
rm -rf /tmp/yasm-1.3.0
# Build x264
mkdir -p /tmp/x264-snapshot-20191217-2245-stable
cd /tmp
wget -qO- "https://download.videolan.org/pub/videolan/x264/snapshots/x264-snapshot-20191217-2245-stable.tar.bz2" | tar -xvj
cd /tmp/x264-snapshot-20191217-2245-stable
PKG_CONFIG_PATH="/usr/local/lib/pkgconfig" ./configure --prefix="/usr/local" --enable-shared
make -j$(nproc) install
rm -rf /tmp/x264-snapshot-20191217-2245-stable
# Build x265
mkdir -p /tmp/x265_2.7
cd /tmp
wget -qO- "https://get.videolan.org/x265/x265_2.7.tar.gz" | tar -xvz
cd /tmp/x265_2.7/build/linux
cmake -G "Unix Makefiles" -DCMAKE_INSTALL_PREFIX="/usr/local" -DENABLE_SHARED:bool=on ../../source
make -j$(nproc) install
rm -rf /tmp/x265_2.7
# Build fdk-aac
mkdir -p /tmp/fdk-aac-2.0.2
cd /tmp
wget -qO- "https://sourceforge.net/projects/opencore-amr/files/fdk-aac/fdk-aac-2.0.2.tar.gz" | tar -xvz
cd /tmp/fdk-aac-2.0.2
autoreconf -fiv
./configure --prefix="/usr/local" --enable-shared --disable-static
make -j$(nproc) install
rm -rf /tmp/fdk-aac-2.0.2
# Build FFmpeg
cd /tmp
git clone -b release/4.4 https://git.ffmpeg.org/ffmpeg.git ffmpeg
cd ffmpeg
PKG_CONFIG_PATH="/usr/local/lib/pkgconfig"
./configure --prefix="/usr/local" --extra-cflags="-I/usr/local/include" --extra-ldflags="-L/usr/local/lib" --extra-libs=-lpthread --extra-libs=-lm --enable-shared --disable-static --enable-libx264 --enable-libx265 --enable-libfdk-aac --enable-gpl --enable-nonfree
make -j$(nproc) install
rm -rf /tmp/ffmpeg
cp /tmp/local-pin-600 /etc/apt/preferences.d
@@ -212,21 +265,21 @@ make -j -C build
cd /tmp/Gbenchmark/build
make install
# Build boost-1.82.0 from source for RPP
# Build boost-1.85.0 from source for RPP
# Installing in a non-standard location since the test packages of hipFFT and rocFFT pick up the version of
# the installed Boost library and declare a package dependency on that specific version of Boost.
# For example, if this was installed in the standard location it would declare a dependency on libboost-dev(el)1.82.0
# For example, if this was installed in the standard location it would declare a dependency on libboost-dev(el)1.85.0
# which is not available as a package in any distro.
# Once this is fixed, we can remove the Boost package from the requirements list and install this
# in the standard location
mkdir -p /tmp/boost-1.82.0
cd /tmp/boost-1.82.0
wget -nv https://sourceforge.net/projects/boost/files/boost/1.82.0/boost_1_82_0.tar.bz2 -O ./boost_1_82_0.tar.bz2
tar -xf boost_1_82_0.tar.bz2 --use-compress-program="/usr/local/bin/compressor"
cd boost_1_82_0
mkdir -p /tmp/boost-1.85.0
cd /tmp/boost-1.85.0
wget -nv https://sourceforge.net/projects/boost/files/boost/1.85.0/boost_1_85_0.tar.bz2 -O ./boost_1_85_0.tar.bz2
tar -xf boost_1_85_0.tar.bz2 --use-compress-program="/usr/local/bin/compressor"
cd boost_1_85_0
./bootstrap.sh --prefix=${RPP_DEPS_LOCATION} --with-python=python3
./b2 stage -j$(nproc) threading=multi link=shared cxxflags="-std=c++11"
./b2 install threading=multi link=shared --with-system --with-filesystem
./b2 stage -j$(nproc) threading=multi link=static cxxflags="-std=c++11 -fpic" cflags="-fpic"
./b2 install threading=multi link=static --with-system --with-filesystem
rm -rf /tmp/boost-1.82.0
rm -rf /tmp/boost-1.85.0

View File

@@ -8,6 +8,7 @@ bison
bridge-utils
build-essential
bzip2
ccache
check
chrpath
cifs-utils
@@ -99,6 +100,7 @@ libva-dev
libvirt-clients
libvirt-daemon-system
libyaml-cpp-dev
libzstd-dev
llvm
llvm-dev
llvm-runtime
@@ -137,3 +139,4 @@ unzip
vim
wget
xsltproc
zlib1g-dev

View File

@@ -0,0 +1,11 @@
FROM ubuntu:noble as builder
COPY packages /tmp/packages
COPY local-pin-600 /tmp/local-pin-600
COPY install-prerequisities.sh /tmp/install-prerequisities.sh
RUN chmod +x /tmp/install-prerequisities.sh
ENV KBUILD_PKG_ROOTCMD=
ENV RPP_DEPS_LOCATION=/usr/local/rpp-deps
ENV PATH="/opt/venv/bin:$PATH"
ENV PATH=$PATH:"/usr/local/bin"
RUN /tmp/install-prerequisities.sh
WORKDIR /src

View File

@@ -0,0 +1,27 @@
## Steps to build the Docker Image
1. Clone this repositry
```bash
git clone https://github.com/ROCm/rocm-build.git
```
2. Go into the OS specific docker directory in build-infra
```bash
cd rocm-build/build/docker/ubuntu24
```
3. Build the docker image
```bash
docker build -t <docker Image Name> .
```
replace the `<docker Image Name>` with the new Docker image Name of your choice,
4. After successful build, verify your \<docker Image Name\> in the list all available docker images.
```bash
docker images
```

View File

@@ -0,0 +1,237 @@
#! /usr/bin/bash
set -ex
# The following assumes that you have a cache, e.g.
# https://docs.docker.com/engine/examples/apt-cacher-ng/
# Comment out if it breaks things
echo 'Acquire::http { Proxy "http://rocm-ci-services.amd.com:3142"; };' > /etc/apt/apt.conf.d/01proxy
apt-get update
DEBIAN_FRONTEND=noninteractive DEBCONF_NONINTERACTIVE_SEEN=true apt-get install --no-install-recommends -y $(sed 's/#.*//' /tmp/packages)
update-ccache-symlinks
apt-get upgrade
apt-get clean
rm -rf /var/cache/apt/ /var/lib/apt/lists/* /etc/apt/apt.conf.d/01proxy
#Install 2.17.1 version of git as we are seeing issues with 2.25 , where it was not allowing to add git submodules if the user is different for parent git directory
curl -o git.tar.gz https://cdn.kernel.org/pub/software/scm/git/git-2.17.1.tar.gz
tar -zxf git.tar.gz
cd git-*
make prefix=/usr/local all
make prefix=/usr/local install
git --version
# venv for python to be able to run pip3 without --break-system-packages
python3 -m venv /opt/venv
pip3 install --no-cache-dir setuptools wheel tox
pip3 install --no-cache-dir --pre CppHeaderParser argparse requests lxml barectf recommonmark jinja2==3.0.0 websockets matplotlib numpy scipy minimal msgpack pytest sphinx joblib PyYAML==5.3.1 rocm-docs-core cmake==3.25.2 pandas myst-parser
# Allow sudo for everyone user
echo 'ALL ALL=(ALL) NOPASSWD:ALL' > /etc/sudoers.d/everyone
# Install OCaml packages to build LLVM's OCaml bindings to be used in lightning compiler test pipeline
wget -nv https://sourceforge.net/projects/opam.mirror/files/2.1.4/opam-2.1.4-x86_64-linux -O /usr/local/bin/opam
chmod +x /usr/local/bin/opam
opam init --yes --disable-sandboxing
opam install ctypes --yes
# Install and modify git-repo (#!/usr/bin/env python -> #!/usr/bin/env python3)
curl https://storage.googleapis.com/git-repo-downloads/repo > /usr/bin/repo
chmod a+x /usr/bin/repo
# Build ccache from the source
cd /tmp
git clone https://github.com/ccache/ccache -b v4.7.5
cd ccache
mkdir build
cd build
cmake -DCMAKE_BUILD_TYPE=Release ..
make
make install
cd /tmp
rm -rf ccache
#Install older version of hwloc-devel package for rocrtst
curl -lO https://download.open-mpi.org/release/hwloc/v1.11/hwloc-1.11.13.tar.bz2
tar -xvf hwloc-1.11.13.tar.bz2
cd hwloc-1.11.13
./configure
make
make install
cp /usr/local/lib/libhwloc.so.5 /usr/lib
hwloc-info --version
# Install gtest
mkdir -p /tmp/gtest
cd /tmp/gtest
wget https://github.com/google/googletest/archive/refs/tags/v1.14.0.zip -O googletest.zip
unzip googletest.zip
cd googletest-1.14.0/
mkdir build
cd build
cmake ..
make -j$(nproc)
make install
rm -rf /tmp/gtest
## Install gRPC from source
## RDC Pre-requisites
GRPC_ARCHIVE=grpc-1.61.0.tar.gz
mkdir /tmp/grpc
mkdir /usr/grpc
cd /tmp
git clone --recurse-submodules -b v1.61.0 https://github.com/grpc/grpc
cd grpc
mkdir -p build
cd build
cmake -DgRPC_INSTALL=ON -DBUILD_SHARED_LIBS=ON -DgRPC_BUILD_TESTS=OFF -DCMAKE_INSTALL_PREFIX=/usr/grpc -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_STANDARD=14 -DCMAKE_SHARED_LINKER_FLAGS_INIT=-Wl,--enable-new-dtags,--build-id=sha1,--rpath,'$ORIGIN' ..
make -j $(nproc) install
rm -rf /tmp/grpc
## rocBLAS Pre-requisites(ROCMOPS-3856)
## Download prebuilt AMD multithreaded blis (2.0)
## Reference : https://github.com/ROCmSoftwarePlatform/rocBLAS/blob/develop/install.sh#L403
mkdir -p /tmp/blis
cd /tmp/blis
wget -O - https://github.com/amd/blis/releases/download/2.0/aocl-blis-mt-ubuntu-2.0.tar.gz | tar xfz -
mv amd-blis-mt /usr/blis
cd /
rm -rf /tmp/blis
## rocBLAS Pre-requisites(SWDEV-404612)
## Download aocl-linux-gcc-4.2.0_1_amd64.deb
mkdir -p /tmp/aocl
cd /tmp/aocl
wget -nv https://download.amd.com/developer/eula/aocl/aocl-4-2/aocl-linux-gcc-4.2.0_1_amd64.deb
apt install ./aocl-linux-gcc-4.2.0_1_amd64.deb
rm -rf /tmp/aocl
## hipBLAS Pre-requisites
## lapack(3.9.1v)
## Reference https://github.com/ROCmSoftwarePlatform/rocSOLVER/blob/develop/install.sh#L174
lapack_version=3.9.1
lapack_srcdir=lapack-$lapack_version
lapack_blddir=lapack-$lapack_version-bld
mkdir -p /tmp/lapack
cd /tmp/lapack
rm -rf "$lapack_srcdir" "$lapack_blddir"
wget -O - https://github.com/Reference-LAPACK/lapack/archive/refs/tags/v3.9.1.tar.gz | tar xzf -
cmake -H$lapack_srcdir -B$lapack_blddir -DCMAKE_BUILD_TYPE=Release -DCMAKE_Fortran_FLAGS=-fno-optimize-sibling-calls -DBUILD_TESTING=OFF -DCBLAS=ON -DLAPACKE=OFF
make -j$(nproc) -C "$lapack_blddir"
make -C "$lapack_blddir" install
cd $lapack_blddir
cp -r ./include/* /usr/local/include/
cp -r ./lib/* /usr/local/lib
cd /
rm -rf /tmp/lapack
## rocSOLVER Pre-requisites
## FMT(7.1.3v)
## Reference https://github.com/ROCmSoftwarePlatform/rocSOLVER/blob/develop/install.sh#L152
fmt_version=7.1.3
fmt_srcdir=fmt-$fmt_version
fmt_blddir=fmt-$fmt_version-bld
mkdir -p /tmp/fmt
cd /tmp/fmt
rm -rf "$fmt_srcdir" "$fmt_blddir"
wget -O - https://github.com/fmtlib/fmt/archive/refs/tags/7.1.3.tar.gz | tar xzf -
cmake -H$fmt_srcdir -B$fmt_blddir -DCMAKE_BUILD_TYPE=Release -DCMAKE_POSITION_INDEPENDENT_CODE=ON -DCMAKE_CXX_STANDARD=17 -DCMAKE_CXX_EXTENSIONS=OFF -DCMAKE_CXX_STANDARD_REQUIRED=ON -DFMT_DOC=OFF -DFMT_TEST=OFF
make -j$(nproc) -C "$fmt_blddir"
make -C "$fmt_blddir" install
# Build and install libjpeg-turbo
mkdir -p /tmp/libjpeg-turbo
cd /tmp/libjpeg-turbo
wget -nv https://github.com/rrawther/libjpeg-turbo/archive/refs/heads/2.0.6.2.zip -O libjpeg-turbo-2.0.6.2.zip
unzip libjpeg-turbo-2.0.6.2.zip
cd libjpeg-turbo-2.0.6.2
mkdir build
cd build
cmake -DCMAKE_INSTALL_PREFIX=/usr -DCMAKE_BUILD_TYPE=RELEASE -DENABLE_STATIC=FALSE -DCMAKE_INSTALL_DEFAULT_LIBDIR=lib ..
make -j$(nproc) install
rm -rf /tmp/libjpeg-turbo
# Get released ninja from source
mkdir -p /tmp/ninja
cd /tmp/ninja
wget -nv https://codeload.github.com/Kitware/ninja/zip/refs/tags/v1.11.1.g95dee.kitware.jobserver-1 -O ninja.zip
unzip ninja.zip
cd ninja-1.11.1.g95dee.kitware.jobserver-1
./configure.py --bootstrap
cp ninja /usr/local/bin/
rm -rf /tmp/ninja
# Install FFmpeg and dependencies
# Build NASM
mkdir -p /tmp/nasm-2.15.05
cd /tmp
wget -qO- "https://distfiles.macports.org/nasm/nasm-2.15.05.tar.bz2" | tar -xvj
cd nasm-2.15.05
./autogen.sh
./configure --prefix="/usr/local"
make -j$(nproc) install
rm -rf /tmp/nasm-2.15.05
# Build YASM
mkdir -p /tmp/yasm-1.3.0
cd /tmp
wget -qO- "http://www.tortall.net/projects/yasm/releases/yasm-1.3.0.tar.gz" | tar -xvz
cd yasm-1.3.0
./configure --prefix="/usr/local"
make -j$(nproc) install
rm -rf /tmp/yasm-1.3.0
# Build x264
mkdir -p /tmp/x264-snapshot-20191217-2245-stable
cd /tmp
wget -qO- "https://download.videolan.org/pub/videolan/x264/snapshots/x264-snapshot-20191217-2245-stable.tar.bz2" | tar -xvj
cd /tmp/x264-snapshot-20191217-2245-stable
PKG_CONFIG_PATH="/usr/local/lib/pkgconfig" ./configure --prefix="/usr/local" --enable-shared
make -j$(nproc) install
rm -rf /tmp/x264-snapshot-20191217-2245-stable
# Build x265
mkdir -p /tmp/x265_2.7
cd /tmp
wget -qO- "https://get.videolan.org/x265/x265_2.7.tar.gz" | tar -xvz
cd /tmp/x265_2.7/build/linux
cmake -G "Unix Makefiles" -DCMAKE_INSTALL_PREFIX="/usr/local" -DENABLE_SHARED:bool=on ../../source
make -j$(nproc) install
rm -rf /tmp/x265_2.7
# Build fdk-aac
mkdir -p /tmp/fdk-aac-2.0.2
cd /tmp
wget -qO- "https://sourceforge.net/projects/opencore-amr/files/fdk-aac/fdk-aac-2.0.2.tar.gz" | tar -xvz
cd /tmp/fdk-aac-2.0.2
autoreconf -fiv
./configure --prefix="/usr/local" --enable-shared --disable-static
make -j$(nproc) install
rm -rf /tmp/fdk-aac-2.0.2
# Build FFmpeg
cd /tmp
rm -rf ffmpeg
git clone -b release/4.4 https://git.ffmpeg.org/ffmpeg.git ffmpeg
cd ffmpeg
PKG_CONFIG_PATH="/usr/local/lib/pkgconfig"
./configure --prefix="/usr/local" --extra-cflags="-I/usr/local/include" --extra-ldflags="-L/usr/local/lib" --extra-libs=-lpthread --extra-libs=-lm --enable-shared --disable-static --enable-libx264 --enable-libx265 --enable-libfdk-aac --enable-gpl --enable-nonfree
make -j$(nproc) install
rm -rf /tmp/ffmpeg
cp /tmp/local-pin-600 /etc/apt/preferences.d
command -v lbzip2
ln -sf $(command -v lbzip2) /usr/local/bin/compressor || ln -sf $(command -v bzip2) /usr/local/bin/compressor
# Install Google Benchmark (ROCMOPS-5283)
mkdir -p /tmp/Gbenchmark
cd /tmp/Gbenchmark
wget -qO- https://github.com/google/benchmark/archive/refs/tags/v1.6.1.tar.gz | tar xz
cmake -Sbenchmark-1.6.1 -Bbuild -DCMAKE_BUILD_TYPE=Release -DBUILD_SHARED_LIBS=OFF -DBENCHMARK_ENABLE_TESTING=OFF -DCMAKE_CXX_STANDARD=14
make -j -C build
cd /tmp/Gbenchmark/build
make install

View File

@@ -0,0 +1,3 @@
Package: *
Pin: origin ""
Pin-Priority: 600

View File

@@ -0,0 +1,140 @@
# List of packages needed for stage1 build
apt-utils
aria2
autoconf
automake
bc
bison
bridge-utils
build-essential
bzip2
ccache
check
chrpath
cifs-utils
cmake
cpio
curl
devscripts
dos2unix
doxygen
fakeroot
flex
freeglut3-dev
g++
g++-multilib
# gawk is needed for aomp
gawk
gcc
gcc-multilib
gfortran
git-lfs
gnupg
googletest
graphviz
kernel-wedge
# kmod for kernel build
kmod
lbzip2
# less is needed by repo
less
libass-dev
libatlas-base-dev
libbabeltrace-dev
libboost-all-dev
libboost-dev
libboost-filesystem-dev
libboost-program-options-dev
libboost-system-dev
libbz2-dev
libc++-dev
libc++1
libc++abi-dev
libc++abi1
libc6-dev-i386
libcap-dev
libcurl4-openssl-dev
libdrm-dev
libdw-dev
libdw1
libdwarf-dev
libelf-dev
libelf1
libexpat1-dev
libfftw3-dev
libfile-find-rule-perl
libgflags-dev
libglew-dev
libgmp-dev
libgoogle-glog-dev
libgtk2.0-dev
libhdf5-dev
libjpeg-dev
libleveldb-dev
liblmdb-dev
liblzma-dev
libmpfr-dev
libmpich-dev
libmsgpack-dev
libncurses-dev
libnuma-dev
libomp-dev
libopenblas-dev
libpci-dev
libpci3
libpciaccess-dev
libpciaccess0
libprotobuf-dev
libpython3-dev
libreadline-dev
libsnappy-dev
libssl-dev
libsuitesparse-dev
libsystemd-dev
libtool
liburi-encode-perl
libva-dev
libvirt-clients
libvirt-daemon-system
libyaml-cpp-dev
llvm
llvm-dev
llvm-runtime
mesa-common-dev
mpich
ocaml
ocaml-findlib
patchelf
pigz
pkg-config
protobuf-compiler
python-is-python3
python3-barectf
python3-dev
python3-pip
python3-pip-whl
python3-requests
python3-venv
python3-yaml
python3-yaml
re2c
redis-tools
# hipclang needs rpm
rpm
rsync
ssh
# This makes life more pleasent inside the container
strace
sudo
systemtap-sdt-dev
texinfo
texlive
texlive-extra-utils
texlive-plain-generic
texlive-xetex
unzip
vim
wget
xsltproc
xxd
zlib1g-dev

View File

@@ -123,9 +123,12 @@ if [ -d "$HSA_OPENSOURCE_ROOT/ROCT-Thunk-Interface" ]; then
export THUNK_ROOT=$HSA_OPENSOURCE_ROOT/ROCT-Thunk-Interface
fi
export AQLPROFILE_ROOT=$WORK_ROOT/hsa/aqlprofile
export OMNIPERF_ROOT=$WORK_ROOT/omniperf
export ROCPROFILER_ROOT=$WORK_ROOT/rocprofiler
export ROCTRACER_ROOT=$WORK_ROOT/roctracer
export ROCPROFILER_REGISTER_ROOT=$WORK_ROOT/rocprofiler-register
export ROCPROFILER_SDK_ROOT=$WORK_ROOT/rocprofiler-sdk
export OMNITRACE_ROOT=$WORK_ROOT/omnitrace
export RDC_ROOT=$WORK_ROOT/rdc
export RDCTST_ROOT=$RDC_ROOT/tests/rdc_tests
export UTILS_ROOT=$WORK_ROOT/rocm-utils
@@ -147,7 +150,6 @@ export ROCM_CORE_ROOT=$WORK_ROOT/rocm-core
export ROCM_CMAKE_ROOT=$WORK_ROOT/rocm-cmake
export ROCM_BANDWIDTH_TEST_ROOT=$WORK_ROOT/rocm_bandwidth_test
export ROCMINFO_ROOT=$WORK_ROOT/rocminfo
export CLANG_OCL_ROOT=$WORK_ROOT/clang-ocl
export ROCR_DEBUG_AGENT_ROOT=$WORK_ROOT/rocr_debug_agent
export COMGR_ROOT=$LLVM_PROJECT_ROOT/amd/comgr
export COMGR_LIB_PATH=$OUT_DIR/build/amd_comgr
@@ -179,7 +181,7 @@ export BUILD_ARTIFACTS=$OUT_DIR/$PACKAGEEXT
export HIPCC_COMPILE_FLAGS_APPEND="-O3 -Wno-format-nonliteral -parallel-jobs=4"
export HIPCC_LINK_FLAGS_APPEND="-O3 -parallel-jobs=4"
export PATH="${ROCM_PATH}/lib/llvm/bin:${PATH}"
export PATH="${ROCM_PATH}/bin:${ROCM_PATH}/lib/llvm/bin:${PATH}"
export LC_ALL=C.UTF-8
export LANG=C.UTF-8

View File

@@ -1,71 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<manifest>
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
<default revision="refs/tags/rocm-6.1.0"
remote="rocm-org"
sync-c="true"
sync-j="4" />
<!--list of projects for ROCm-->
<project name="ROCm" revision="roc-6.1.x" />
<project name="ROCK-Kernel-Driver" />
<project name="ROCT-Thunk-Interface" />
<project name="ROCR-Runtime" />
<project name="amdsmi" />
<project name="rocm_smi_lib" />
<project name="rocm-core" />
<project name="rocm-cmake" />
<project name="rocminfo" />
<project name="rocm_bandwidth_test" />
<project name="rocprofiler" />
<project name="rocprofiler-register" />
<project name="roctracer" />
<project name="clang-ocl" />
<project name="rdc" />
<!--HIP Projects-->
<project name="HIP" />
<project name="hip-tests" />
<project name="HIP-Examples" />
<project name="clr" />
<project name="hipother" />
<project name="HIPIFY" />
<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
<project name="llvm-project" />
<project name="half" />
<!-- gdb projects -->
<project name="ROCgdb" />
<project name="ROCdbgapi" />
<project name="rocr_debug_agent" />
<!-- ROCm Libraries -->
<project groups="mathlibs" name="rocBLAS" />
<project groups="mathlibs" name="Tensile" />
<project groups="mathlibs" name="hipTensor" />
<project groups="mathlibs" name="hipBLAS" />
<project groups="mathlibs" name="hipBLASLt" />
<project groups="mathlibs" name="rocFFT" />
<project groups="mathlibs" name="hipFFT" />
<project groups="mathlibs" name="rocRAND" />
<project groups="mathlibs" name="hipRAND" />
<project groups="mathlibs" name="rocSPARSE" />
<project groups="mathlibs" name="hipSPARSELt" />
<project groups="mathlibs" name="rocSOLVER" />
<project groups="mathlibs" name="hipSOLVER" />
<project groups="mathlibs" name="hipSPARSE" />
<project groups="mathlibs" name="rocALUTION" />
<project groups="mathlibs" name="rocThrust" />
<project groups="mathlibs" name="hipCUB" />
<project groups="mathlibs" name="rocPRIM" />
<project groups="mathlibs" name="rocWMMA" />
<project groups="mathlibs" name="rccl" />
<project groups="mathlibs" name="MIOpen" />
<project groups="mathlibs" name="MIVisionX" />
<project groups="mathlibs" name="ROCmValidationSuite" />
<project groups="mathlibs" name="composable_kernel" />
<project groups="mathlibs" name="hipfort" />
<project groups="mathlibs" name="rocDecode" />
<project groups="mathlibs" name="AMDMIGraphX" />
<project groups="mathlibs" name="rpp" />
<!-- Projects for OpenMP-Extras -->
<project name="aomp" path="openmp-extras/aomp" />
<project name="aomp-extras" path="openmp-extras/aomp-extras" />
<project name="flang" path="openmp-extras/flang" />
</manifest>

View File

@@ -1,71 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<manifest>
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
<default revision="refs/tags/rocm-6.1.1"
remote="rocm-org"
sync-c="true"
sync-j="4" />
<!--list of projects for ROCm-->
<project name="ROCm" revision="roc-6.1.x" />
<project name="ROCK-Kernel-Driver" />
<project name="ROCT-Thunk-Interface" />
<project name="ROCR-Runtime" />
<project name="amdsmi" />
<project name="rocm_smi_lib" />
<project name="rocm-core" />
<project name="rocm-cmake" />
<project name="rocminfo" />
<project name="rocm_bandwidth_test" />
<project name="rocprofiler" />
<project name="rocprofiler-register" />
<project name="roctracer" />
<project name="clang-ocl" />
<project name="rdc" />
<!--HIP Projects-->
<project name="HIP" />
<project name="hip-tests" />
<project name="HIP-Examples" />
<project name="clr" />
<project name="hipother" />
<project name="HIPIFY" />
<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
<project name="llvm-project" />
<project name="half" />
<!-- gdb projects -->
<project name="ROCgdb" />
<project name="ROCdbgapi" />
<project name="rocr_debug_agent" />
<!-- ROCm Libraries -->
<project groups="mathlibs" name="rocBLAS" />
<project groups="mathlibs" name="Tensile" />
<project groups="mathlibs" name="hipTensor" />
<project groups="mathlibs" name="hipBLAS" />
<project groups="mathlibs" name="hipBLASLt" />
<project groups="mathlibs" name="rocFFT" />
<project groups="mathlibs" name="hipFFT" />
<project groups="mathlibs" name="rocRAND" />
<project groups="mathlibs" name="hipRAND" />
<project groups="mathlibs" name="rocSPARSE" />
<project groups="mathlibs" name="hipSPARSELt" />
<project groups="mathlibs" name="rocSOLVER" />
<project groups="mathlibs" name="hipSOLVER" />
<project groups="mathlibs" name="hipSPARSE" />
<project groups="mathlibs" name="rocALUTION" />
<project groups="mathlibs" name="rocThrust" />
<project groups="mathlibs" name="hipCUB" />
<project groups="mathlibs" name="rocPRIM" />
<project groups="mathlibs" name="rocWMMA" />
<project groups="mathlibs" name="rccl" />
<project groups="mathlibs" name="MIOpen" />
<project groups="mathlibs" name="MIVisionX" />
<project groups="mathlibs" name="ROCmValidationSuite" />
<project groups="mathlibs" name="composable_kernel" />
<project groups="mathlibs" name="hipfort" />
<project groups="mathlibs" name="rocDecode" />
<project groups="mathlibs" name="AMDMIGraphX" />
<project groups="mathlibs" name="rpp" />
<!-- Projects for OpenMP-Extras -->
<project name="aomp" path="openmp-extras/aomp" />
<project name="aomp-extras" path="openmp-extras/aomp-extras" />
<project name="flang" path="openmp-extras/flang" />
</manifest>

View File

@@ -1,71 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<manifest>
<remote name="rocm-org" fetch="https://github.com/ROCm/" />
<default revision="refs/tags/rocm-6.1.2"
remote="rocm-org"
sync-c="true"
sync-j="4" />
<!--list of projects for ROCm-->
<project name="ROCm" revision="roc-6.1.x" />
<project name="ROCK-Kernel-Driver" />
<project name="ROCT-Thunk-Interface" />
<project name="ROCR-Runtime" />
<project name="amdsmi" />
<project name="rocm_smi_lib" />
<project name="rocm-core" />
<project name="rocm-cmake" />
<project name="rocminfo" />
<project name="rocm_bandwidth_test" />
<project name="rocprofiler" />
<project name="rocprofiler-register" />
<project name="roctracer" />
<project name="clang-ocl" />
<project name="rdc" />
<!--HIP Projects-->
<project name="HIP" />
<project name="hip-tests" />
<project name="HIP-Examples" />
<project name="clr" />
<project name="hipother" />
<project name="HIPIFY" />
<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
<project name="llvm-project" />
<project name="half" />
<!-- gdb projects -->
<project name="ROCgdb" />
<project name="ROCdbgapi" />
<project name="rocr_debug_agent" />
<!-- ROCm Libraries -->
<project groups="mathlibs" name="rocBLAS" />
<project groups="mathlibs" name="Tensile" />
<project groups="mathlibs" name="hipTensor" />
<project groups="mathlibs" name="hipBLAS" />
<project groups="mathlibs" name="hipBLASLt" />
<project groups="mathlibs" name="rocFFT" />
<project groups="mathlibs" name="hipFFT" />
<project groups="mathlibs" name="rocRAND" />
<project groups="mathlibs" name="hipRAND" />
<project groups="mathlibs" name="rocSPARSE" />
<project groups="mathlibs" name="hipSPARSELt" />
<project groups="mathlibs" name="rocSOLVER" />
<project groups="mathlibs" name="hipSOLVER" />
<project groups="mathlibs" name="hipSPARSE" />
<project groups="mathlibs" name="rocALUTION" />
<project groups="mathlibs" name="rocThrust" />
<project groups="mathlibs" name="hipCUB" />
<project groups="mathlibs" name="rocPRIM" />
<project groups="mathlibs" name="rocWMMA" />
<project groups="mathlibs" name="rccl" />
<project groups="mathlibs" name="MIOpen" />
<project groups="mathlibs" name="MIVisionX" />
<project groups="mathlibs" name="ROCmValidationSuite" />
<project groups="mathlibs" name="composable_kernel" />
<project groups="mathlibs" name="hipfort" />
<project groups="mathlibs" name="rocDecode" />
<project groups="mathlibs" name="AMDMIGraphX" />
<project groups="mathlibs" name="rpp" />
<!-- Projects for OpenMP-Extras -->
<project name="aomp" path="openmp-extras/aomp" />
<project name="aomp-extras" path="openmp-extras/aomp-extras" />
<project name="flang" path="openmp-extras/flang" />
</manifest>

View File

@@ -6,30 +6,29 @@
sync-c="true"
sync-j="4" />
<!--list of projects for ROCm-->
<project name="ROCm" revision="roc-6.2.x" />
<project name="ROCK-Kernel-Driver" />
<project name="ROCR-Runtime" />
<project name="ROCT-Thunk-Interface" />
<project name="amdsmi" />
<project name="omniperf" />
<project name="omnitrace" />
<project name="rdc" />
<project name="roc-core" />
<project name="rocm_bandwidth_test" />
<project name="rocm_smi_lib" />
<project name="rocm-core" />
<project name="rocminfo" />
<project name="rocm-examples" />
<project name="rocm-prof" />
<project name="rocm-prof-register" />
<project name="rocm-prof-sdk" />
<project name="rocm-tracer" />
<project name="ROCK-Kernel-Driver" />
<project name="ROCR-Runtime" />
<project name="ROCT-Thunk-Interface" />
<project name="ROCm" revision="roc-6.2.x" />
<project name="rocprofiler" />
<project name="rocprofiler-register" />
<project name="rocprofiler-sdk" />
<project name="roctracer" />
<!--HIP Projects-->
<project name="clr" />
<project name="HIPIFY" />
<project name="HIP" />
<project name="hip-other" />
<project name="hip-tests" />
<project name="HIP-Examples" />
<project name="HIPIFY" />
<project name="clr" />
<project name="hipother" />
<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
<project name="half" />
<project name="llvm-project" />
@@ -72,4 +71,4 @@
<project name="aomp" path="openmp-extras/aomp" />
<project name="aomp-extras" path="openmp-extras/aomp-extras" />
<project name="flang" path="openmp-extras/flang" />
</manifest>
</manifest>