github/ROCm
1
1
Fork 0
mirror of https://github.com/ROCm/ROCm.git synced 2026-01-10 07:08:08 -05:00
Code Issues Packages Projects Releases Wiki Activity

Sync develop into docs/6.3.3

Browse Source
This commit is contained in:
pbhandar-amd
2025-02-18 14:05:45 -05:00
committed by GitHub
parent a9aaabcc68 a89b135afb
commit 1b58c08394
5 changed files with 132 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.azuredevops/components/MIOpen.yml
View File

@@ -101,7 +101,7 @@ jobs:
-DMIOPEN_BACKEND=HIP
-DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/miopen-deps
-DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
-DGPU_TARGETS=$(JOB_GPU_TARGET)
-DMIOPEN_ENABLE_AI_KERNEL_TUNING=OFF
-DMIOPEN_ENABLE_AI_IMMED_MODE_FALLBACK=OFF
-DCMAKE_BUILD_TYPE=Release
@@ -129,6 +129,8 @@ jobs:
variables:
- group: common
- template: /.azuredevops/variables-global.yml
- name: ROCM_PATH
value: $(Agent.BuildDirectory)/rocm
pool: $(JOB_TEST_POOL)
workspace:
clean: all

12
.azuredevops/components/rocPyDecode.yml
View File

@@ -84,6 +84,7 @@ jobs:
echo "##vso[task.setvariable variable=PYBIND11_PATH;]$(python3 -c 'import pybind11; print(pybind11.get_cmake_dir())')"
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
parameters:
installEnabled: false
extraBuildFlags: >-
-DROCM_PATH=$(Agent.BuildDirectory)/rocm
-DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(PYTHON_USER_SITE)/pybind11;$(PYTHON_DIST_PACKAGES)/pybind11;$(PYBIND11_PATH)
@@ -91,6 +92,14 @@ jobs:
-DGPU_TARGETS=$(JOB_GPU_TARGET)
-DCMAKE_INSTALL_PREFIX_PYTHON=$(Build.BinariesDirectory)
-GNinja
- task: Bash@3
displayName: 'rocPyDecode install'
inputs:
targetType: inline
script: |
sudo cmake --build . --target install
sudo chown -R $(whoami):$(id -gn) $(Build.BinariesDirectory)
workingDirectory: $(Build.SourcesDirectory)/build
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:
gpuTarget: $(JOB_GPU_TARGET)
@@ -105,7 +114,8 @@ jobs:
script: |
export ROCM_PATH=$(Agent.BuildDirectory)/rocm
export HIP_INCLUDE_DIRS=$(Agent.BuildDirectory)/rocm/include/hip
python3 setup.py bdist_wheel
sudo python3 setup.py bdist_wheel
sudo chown -R $(whoami):$(id -gn) $(find . -name "*.whl")
workingDirectory: $(Build.SourcesDirectory)
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
parameters:

2
.azuredevops/components/rpp.yml
View File

@@ -29,6 +29,7 @@ parameters:
- clr
- half
- llvm-project
- rocm-cmake
- rocminfo
- ROCR-Runtime
- name: rocmTestDependencies
@@ -79,6 +80,7 @@ jobs:
-DHALF_INCLUDE_DIRS=$(Agent.BuildDirectory)/rocm/include
-DCMAKE_BUILD_TYPE=Release
-DGPU_TARGETS=$(JOB_GPU_TARGET)
-DROCM_PLATFORM_VERSION=$(NEXT_RELEASE_VERSION)
-GNinja
- template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
parameters:

34
.azuredevops/templates/steps/miopen-get-ck-build.yml
View File

@@ -20,41 +20,37 @@ steps:
ARTIFACT_NAME="composablekernel.${{ parameters.gpuTarget }}"
EXIT_CODE=0
# The commits that MIOpen reference are all merge commits from CK/develop to CK/amd-develop
# These commits are present on CK/amd-develop but not on CK/develop
# Ex-CI only builds CK/develop, so we need to find a commit present on both CK/develop and CK/amd-develop
# Try to find an Azure build for the specific CK commit called out in MIOpen's requirements.txt
CK_COMMIT=$(grep 'ROCm/composable_kernel' requirements.txt | sed -E 's/.*@([a-f0-9]{40}).*/\1/')
echo "Fetching CK build ID for commit $CK_COMMIT"
CK_COMMIT_URL="$GH_API/composable_kernel/commits/${CK_COMMIT}"
PARENT_COMMIT=$(curl -s $CK_COMMIT_URL | jq '.parents[1].sha' | tr -d '"')
echo "Found parent commit: $PARENT_COMMIT"
PARENT_CHECKS_URL="$GH_API/composable_kernel/commits/${PARENT_COMMIT}/check-runs"
CK_BUILD_ID=$(curl -s $PARENT_CHECKS_URL | \
CK_CHECKS_URL="$GH_API/composable_kernel/commits/${CK_COMMIT}/check-runs"
CK_BUILD_ID=$(curl -s $CK_CHECKS_URL | \
jq '.check_runs[] | select(.name == "composable_kernel" and .app.slug == "azure-pipelines") | .details_url' | \
tr -d '"' | grep -oP 'buildId=\K\d+')
if [ -z "$CK_BUILD_ID" ]; then
# If none found, use latest successful CK build instead
if [[ -z "$CK_BUILD_ID" ]]; then
echo "Did not find specific CK build ID"
LATEST_BUILD_URL="$AZ_API/build/builds?definitions=$(COMPOSABLE_KERNEL_PIPELINE_ID)&statusFilter=completed&resultFilter=succeeded&\$top=1&api-version=7.1"
CK_BUILD_ID=$(curl -s $LATEST_BUILD_URL | jq '.value[0].id')
echo "Found latest CK build ID: $CK_BUILD_ID"
EXIT_CODE=1
else
echo "Found specific CK build ID: $CK_BUILD_ID"
fi
AZURE_URL="$AZ_API/build/builds/$CK_BUILD_ID/artifacts?artifactName=$ARTIFACT_NAME&api-version=7.1"
ARTIFACT_URL=$(curl -s $AZURE_URL | jq '.resource.downloadUrl' | tr -d '"')
if [ -z "$ARTIFACT_URL" ]; then
echo "Did not find specific CK build artifact"
LATEST_BUILD_URL="$AZ_API/build/builds?definitions=$(COMPOSABLE_KERNEL_PIPELINE_ID)&status=completed&result=succeeded&\$top=1&api-version=7.1"
# If using the specific CK commit and it doesn't have any valid artifacts, use latest successful CK build instead
if { [[ -z "$ARTIFACT_URL" ]] || [[ "$ARTIFACT_URL" == "null" ]]; } && [[ $EXIT_CODE -eq 0 ]]; then
echo "Did not find valid specific CK build artifact"
LATEST_BUILD_URL="$AZ_API/build/builds?definitions=$(COMPOSABLE_KERNEL_PIPELINE_ID)&statusFilter=completed&resultFilter=succeeded&\$top=1&api-version=7.1"
CK_BUILD_ID=$(curl -s $LATEST_BUILD_URL | jq '.value[0].id')
echo "Found latest CK build ID: $CK_BUILD_ID"
AZURE_URL="$AZ_API/build/builds/$CK_BUILD_ID/artifacts?artifactName=$ARTIFACT_NAME&api-version=7.1"
ARTIFACT_URL=$(curl -s $AZURE_URL | jq '.resource.downloadUrl' | tr -d '"')
EXIT_CODE=2
elif [ $EXIT_CODE -eq 0 ]; then
echo "Found specific CK build ID: $CK_BUILD_ID"
fi
echo "Downloading CK artifact from $ARTIFACT_URL"
@@ -64,9 +60,13 @@ steps:
tar -zxvf $(System.ArtifactsDirectory)/$ARTIFACT_NAME/*.tar.gz -C $(Agent.BuildDirectory)/rocm
rm -r $(System.ArtifactsDirectory)/ck.zip $(System.ArtifactsDirectory)/$ARTIFACT_NAME
if [ $EXIT_CODE -ne 0 ]; then
if [[ $EXIT_CODE -ne 0 ]]; then
BUILD_COMMIT=$(curl -s $AZ_API/build/builds/$CK_BUILD_ID | jq '.sourceVersion' | tr -d '"')
echo "WARNING: couldn't find a CK build for commit $CK_COMMIT"
if [[ $EXIT_CODE -eq 1 ]]; then
echo "WARNING: couldn't find a CK build for commit $CK_COMMIT"
elif [[ $EXIT_CODE -eq 2 ]]; then
echo "WARNING: couldn't find a valid CK artifact for commit $CK_COMMIT"
fi
echo "Instead used latest CK build $CK_BUILD_ID for commit $BUILD_COMMIT"
fi
exit $EXIT_CODE

100
docs/reference/gpu-arch-specs.rst
View File

@@ -21,6 +21,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Model
- Architecture
- LLVM target name
- Device Major version
- Device Minor version
- VRAM (GiB)
- Compute Units
- Wavefront Size
@@ -36,6 +38,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI325X
- CDNA3
- gfx942
- 9
- 4
- 256
- 304 (38 per XCD)
- 64
@@ -51,6 +55,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI300X
- CDNA3
- gfx942
- 9
- 4
- 192
- 304 (38 per XCD)
- 64
@@ -66,6 +72,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI300A
- CDNA3
- gfx942
- 9
- 4
- 128
- 228 (38 per XCD)
- 64
@@ -81,6 +89,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI250X
- CDNA2
- gfx90a
- 9
- 0
- 128
- 220 (110 per GCD)
- 64
@@ -96,6 +106,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI250
- CDNA2
- gfx90a
- 9
- 0
- 128
- 208 (104 per GCD)
- 64
@@ -111,6 +123,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI210
- CDNA2
- gfx90a
- 9
- 0
- 64
- 104
- 64
@@ -126,6 +140,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI100
- CDNA
- gfx908
- 9
- 0
- 32
- 120
- 64
@@ -141,6 +157,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI60
- GCN5.1
- gfx906
- 9
- 0
- 32
- 64
- 64
@@ -156,6 +174,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI50 (32GB)
- GCN5.1
- gfx906
- 9
- 0
- 32
- 60
- 64
@@ -171,6 +191,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI50 (16GB)
- GCN5.1
- gfx906
- 9
- 0
- 16
- 60
- 64
@@ -186,6 +208,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI25
- GCN5.0
- gfx900
- 9
- 0
- 16 
- 64
- 64
@@ -201,6 +225,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI8
- GCN3.0
- gfx803
- 8
- 0
- 4
- 64
- 64
@@ -216,6 +242,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- MI6
- GCN4.0
- gfx803
- 8
- 0
- 16
- 36
- 64
@@ -238,6 +266,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Model
- Architecture
- LLVM target name
- Device Major version
- Device Minor version
- VRAM (GiB)
- Compute Units
- Wavefront Size
@@ -254,6 +284,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon PRO V710
- RDNA3
- gfx1101
- 11
- 0
- 28
- 54
- 32
@@ -270,6 +302,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon PRO W7900 Dual Slot
- RDNA3
- gfx1100
- 11
- 0
- 48
- 96
- 32
@@ -286,6 +320,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon PRO W7900
- RDNA3
- gfx1100
- 11
- 0
- 48
- 96
- 32
@@ -302,6 +338,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon PRO W7800
- RDNA3
- gfx1100
- 11
- 0
- 32
- 70
- 32
@@ -318,6 +356,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon PRO W7700
- RDNA3
- gfx1101
- 11
- 0
- 16
- 48
- 32
@@ -334,6 +374,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon PRO W6800
- RDNA2
- gfx1030
- 10
- 3
- 32
- 60
- 32
@@ -350,6 +392,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon PRO W6600
- RDNA2
- gfx1032
- 10
- 3
- 8
- 28
- 32
@@ -366,6 +410,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon PRO V620
- RDNA2
- gfx1030
- 10
- 3
- 32
- 72
- 32
@@ -382,6 +428,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon Pro W5500
- RDNA
- gfx1012
- 10
- 1
- 8
- 22
- 32
@@ -398,6 +446,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon Pro VII
- GCN5.1
- gfx906
- 9
- 0
- 16
- 60
- 64
@@ -421,6 +471,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Model
- Architecture
- LLVM target name
- Device Major version
- Device Minor version
- VRAM (GiB)
- Compute Units
- Wavefront Size
@@ -437,6 +489,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 7900 XTX
- RDNA3
- gfx1100
- 11
- 0
- 24
- 96
- 32
@@ -453,6 +507,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 7900 XT
- RDNA3
- gfx1100
- 11
- 0
- 20
- 84
- 32
@@ -469,6 +525,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 7900 GRE
- RDNA3
- gfx1100
- 11
- 0
- 16
- 80
- 32
@@ -485,6 +543,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 7800 XT
- RDNA3
- gfx1101
- 11
- 0
- 16
- 60
- 32
@@ -501,6 +561,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 7700 XT
- RDNA3
- gfx1101
- 11
- 0
- 12
- 54
- 32
@@ -517,6 +579,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 7600
- RDNA3
- gfx1102
- 11
- 0
- 8
- 32
- 32
@@ -533,6 +597,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 6950 XT
- RDNA2
- gfx1030
- 10
- 3
- 16
- 80
- 32
@@ -549,6 +615,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 6900 XT
- RDNA2
- gfx1030
- 10
- 3
- 16
- 80
- 32
@@ -565,6 +633,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 6800 XT
- RDNA2
- gfx1030
- 10
- 3
- 16
- 72
- 32
@@ -581,6 +651,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 6800
- RDNA2
- gfx1030
- 10
- 3
- 16
- 60
- 32
@@ -597,6 +669,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 6750 XT
- RDNA2
- gfx1031
- 10
- 3
- 12
- 40
- 32
@@ -613,6 +687,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 6700 XT
- RDNA2
- gfx1031
- 10
- 3
- 12
- 40
- 32
@@ -630,6 +706,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- RDNA2
- gfx1031
- 10
- 3
- 10
- 36
- 32
- 128
@@ -645,6 +723,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 6650 XT
- RDNA2
- gfx1032
- 10
- 3
- 8
- 32
- 32
@@ -661,6 +741,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 6600 XT
- RDNA2
- gfx1032
- 10
- 3
- 8
- 32
- 32
@@ -677,6 +759,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon RX 6600
- RDNA2
- gfx1032
- 10
- 3
- 8
- 28
- 32
@@ -693,6 +777,8 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
- Radeon VII
- GCN5.1
- gfx906
- 9
- 0
- 16
- 60
- 64
@@ -710,7 +796,7 @@ Glossary
========
For more information about the terms used, see the
:ref:`specific documents and guides <gpu-arch-documentation>`, or
:ref:`specific documents and guides <gpu-arch-documentation>`, or
:doc:`Understanding the HIP programming model<hip:understand/programming_model>`.
**LLVM target name**
@@ -718,6 +804,18 @@ For more information about the terms used, see the
Argument to pass to clang in ``--offload-arch`` to compile code for the given
architecture.
**Device major version**
Indicates the core instruction set of the GPU architecture. For example, a value
of 11 would correspond to Navi III (RDNA3).
**Device minor version**
Indicates a particular configuration, feature set, or variation within the group
represented by the device compute version. For example, different models within
the same major version might have varying levels of support for certain features
or optimizations.
**VRAM**
Amount of memory available on the GPU.