[HIP] Bump ROCm version to 7.2.1 (#21066)

Bump ROCm version on Linux from 7.2 to 7.2.1
Add gfx1102 target
Delete LLVM workaround since ROCm 7.2.1 has fix for ROCm 7.2 perf regression https://github.com/ROCm/rocm-systems/issues/2865

---------

Co-authored-by: Sigbjørn Skjæret <redacted>

diff --git a/.devops/rocm.Dockerfile b/.devops/rocm.Dockerfile
index 96aa9dfd40c736ffd38e43ad5c696a6cb64c3cae..525ddc7905113f885b42a0463084827555492840 100644 (file)
--- a/.devops/rocm.Dockerfile
+++ b/.devops/rocm.Dockerfile
@@ -1,8 +1,8 @@
 ARG UBUNTU_VERSION=24.04
 
 # This needs to generally match the container host's environment.
-ARG ROCM_VERSION=7.2
-ARG AMDGPU_VERSION=7.2
+ARG ROCM_VERSION=7.2.1
+ARG AMDGPU_VERSION=7.2.1
 
 # Target the ROCm build image
 ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
@@ -12,11 +12,11 @@ FROM ${BASE_ROCM_DEV_CONTAINER} AS build
 
 # Unless otherwise specified, we make a fat build.
 # This is mostly tied to rocBLAS supported archs.
-# check https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.2.0/reference/system-requirements.html
+# check https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.2.1/reference/system-requirements.html
 # check https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/docs/compatibility/compatibilityrad/native_linux/native_linux_compatibility.html
 # check https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/docs/compatibility/compatibilityryz/native_linux/native_linux_compatibility.html
 
-ARG ROCM_DOCKER_ARCH='gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1151;gfx1150;gfx1200;gfx1201'
+ARG ROCM_DOCKER_ARCH='gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1102;gfx1151;gfx1150;gfx1200;gfx1201'
 
 # Set ROCm architectures
 ENV AMDGPU_TARGETS=${ROCM_DOCKER_ARCH}

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 3e12b9d5057972bb7dd7c0eeb9da29280c62d03c..55167754a40d40797f86a1762fcbffb7564beb65 100644 (file)
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -941,7 +941,7 @@ jobs:
       - name: Grab rocWMMA package
         id: grab_rocwmma
         run: |
-          curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70200-43~24.04_amd64.deb"
+          curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2.1/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70201-81~24.04_amd64.deb"
           7z x rocwmma.deb
           7z x data.tar
 
@@ -984,7 +984,7 @@ jobs:
           cmake -G "Unix Makefiles" -B build -S . `
             -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" `
             -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" `
-            -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.0/include/" `
+            -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.1/include/" `
             -DCMAKE_BUILD_TYPE=Release `
             -DLLAMA_BUILD_BORINGSSL=ON `
             -DROCM_DIR="${env:HIP_PATH}" `

diff --git a/.github/workflows/hip-quality-check.yml b/.github/workflows/hip-quality-check.yml
index 474c0ad4158217564d15912518df025be27cf346..7dea09acf878fe74b2993f9ed1123da8d73dcee4 100644 (file)
--- a/.github/workflows/hip-quality-check.yml
+++ b/.github/workflows/hip-quality-check.yml
@@ -35,7 +35,7 @@ env:
 jobs:
   ubuntu-22-hip-quality-check:
     runs-on: ubuntu-22.04
-    container: rocm/dev-ubuntu-22.04:7.2
+    container: rocm/dev-ubuntu-22.04:7.2.1
     steps:
       - name: Clone
         id: checkout

diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index 48a9300f7f611d189d448dbb9e74ba8db1a8445e..3b49ead96bf5aaadfccb77f33548dd64f1e3ff9d 100644 (file)
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -639,8 +639,8 @@ jobs:
     strategy:
       matrix:
         include:
-          - ROCM_VERSION: "7.2"
-            gpu_targets: "gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1151;gfx1150;gfx1200;gfx1201"
+          - ROCM_VERSION: "7.2.1"
+            gpu_targets: "gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1102;gfx1151;gfx1150;gfx1200;gfx1201"
             build: 'x64'
 
     steps:
@@ -662,7 +662,7 @@ jobs:
           sudo apt install -y build-essential git cmake wget
 
       - name: Setup Legacy ROCm
-        if: matrix.ROCM_VERSION == '7.2'
+        if: matrix.ROCM_VERSION == '7.2.1'
         id: legacy_env
         run: |
           sudo mkdir --parents --mode=0755 /etc/apt/keyrings
@@ -683,7 +683,7 @@ jobs:
           sudo apt-get install -y libssl-dev rocm-hip-sdk
 
       - name: Setup TheRock
-        if: matrix.ROCM_VERSION != '7.2'
+        if: matrix.ROCM_VERSION != '7.2.1'
         id: therock_env
         run: |
           wget https://repo.amd.com/rocm/tarball/therock-dist-linux-gfx1151-${{ matrix.ROCM_VERSION }}.tar.gz
@@ -699,7 +699,6 @@ jobs:
         run: |
           cmake -B build -S . \
             -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
-            -DCMAKE_HIP_FLAGS="-mllvm --amdgpu-unroll-threshold-local=600" \
             -DCMAKE_BUILD_TYPE=Release \
             -DGGML_BACKEND_DL=ON \
             -DGGML_NATIVE=OFF \
@@ -717,17 +716,20 @@ jobs:
         id: tag
         uses: ./.github/actions/get-tag-name
 
+      - name: Get ROCm short version
+        run: echo "ROCM_VERSION_SHORT=$(echo '${{ matrix.ROCM_VERSION }}' | cut -d '.' -f 1,2)" >> $GITHUB_ENV
+
       - name: Pack artifacts
         id: pack_artifacts
         run: |
           cp LICENSE ./build/bin/
-          tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
+          tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-${{ env.ROCM_VERSION_SHORT }}-${{ matrix.build }}.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
 
       - name: Upload artifacts
         uses: actions/upload-artifact@v6
         with:
-          path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}.tar.gz
-          name: llama-bin-ubuntu-rocm-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}.tar.gz
+          path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-${{ env.ROCM_VERSION_SHORT }}-${{ matrix.build }}.tar.gz
+          name: llama-bin-ubuntu-rocm-${{ env.ROCM_VERSION_SHORT }}-${{ matrix.build }}.tar.gz
 
   windows-hip:
     runs-on: windows-2022
@@ -749,7 +751,7 @@ jobs:
       - name: Grab rocWMMA package
         id: grab_rocwmma
         run: |
-          curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70200-43~24.04_amd64.deb"
+          curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2.1/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70201-81~24.04_amd64.deb"
           7z x rocwmma.deb
           7z x data.tar
 
@@ -806,7 +808,7 @@ jobs:
           cmake -G "Unix Makefiles" -B build -S . `
             -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" `
             -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" `
-            -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.0/include/ -Wno-ignored-attributes -Wno-nested-anon-types" `
+            -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.1/include/ -Wno-ignored-attributes -Wno-nested-anon-types" `
             -DCMAKE_BUILD_TYPE=Release `
             -DGGML_BACKEND_DL=ON `
             -DGGML_NATIVE=OFF `