[ROCm] Update rocm.yml and add rocm-mi300.yml (#145398)

- Added another workflow to run the mi300 jobs post-merge.
- Updated rocm.yml to use mi200s instead of mi300s.
- Required to get an idea of how PRs are landing on our mi200s and mi300s.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/145398
Approved by: https://github.com/jeffdaily

Co-authored-by: Jeff Daily <jeff.daily@amd.com>

.github/workflows/rocm-mi300.yml

@@ -0,0 +1,58 @@
+name: rocm-mi300
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+  schedule:
+    - cron: 29 8 * * *  # about 1:29am PDT
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref_name }}-${{ github.ref_type == 'branch' && github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }}
+  cancel-in-progress: true
+
+permissions: read-all
+
+jobs:
+  target-determination:
+    if: github.repository_owner == 'pytorch'
+    name: before-test
+    uses: ./.github/workflows/target_determination.yml
+    permissions:
+      id-token: write
+      contents: read
+
+  linux-focal-rocm6_3-py3_10-build:
+    if: ${{ (github.event_name != 'schedule' || github.repository == 'pytorch/pytorch') && github.repository_owner == 'pytorch' }}
+    name: linux-focal-rocm6.3-py3.10
+    uses: ./.github/workflows/_linux-build.yml
+    with:
+      build-environment: linux-focal-rocm6.3-py3.10
+      docker-image-name: pytorch-linux-focal-rocm-n-py3
+      sync-tag: rocm-build
+      test-matrix: |
+        { include: [
+          { config: "default", shard: 1, num_shards: 6, runner: "linux.rocm.gpu.mi300.2" },
+          { config: "default", shard: 2, num_shards: 6, runner: "linux.rocm.gpu.mi300.2" },
+          { config: "default", shard: 3, num_shards: 6, runner: "linux.rocm.gpu.mi300.2" },
+          { config: "default", shard: 4, num_shards: 6, runner: "linux.rocm.gpu.mi300.2" },
+          { config: "default", shard: 5, num_shards: 6, runner: "linux.rocm.gpu.mi300.2" },
+          { config: "default", shard: 6, num_shards: 6, runner: "linux.rocm.gpu.mi300.2" },
+        ]}
+    secrets: inherit
+
+  linux-focal-rocm6_3-py3_10-test:
+    permissions:
+      id-token: write
+      contents: read
+    name: linux-focal-rocm6.3-py3.10
+    uses: ./.github/workflows/_rocm-test.yml
+    needs:
+      - linux-focal-rocm6_3-py3_10-build
+      - target-determination
+    with:
+      build-environment: linux-focal-rocm6.3-py3.10
+      docker-image: ${{ needs.linux-focal-rocm6_3-py3_10-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-focal-rocm6_3-py3_10-build.outputs.test-matrix }}
+    secrets: inherit

.github/workflows/rocm.yml

@@ -36,12 +36,12 @@ jobs:
       sync-tag: rocm-build
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 6, runner: "${{ github.event_name == 'push' && github.event.ref == 'refs/heads/main' && 'linux.rocm.gpu.mi300.2' || 'linux.rocm.gpu.2' }}" },
-          { config: "default", shard: 2, num_shards: 6, runner: "${{ github.event_name == 'push' && github.event.ref == 'refs/heads/main' && 'linux.rocm.gpu.mi300.2' || 'linux.rocm.gpu.2' }}" },
-          { config: "default", shard: 3, num_shards: 6, runner: "${{ github.event_name == 'push' && github.event.ref == 'refs/heads/main' && 'linux.rocm.gpu.mi300.2' || 'linux.rocm.gpu.2' }}" },
-          { config: "default", shard: 4, num_shards: 6, runner: "${{ github.event_name == 'push' && github.event.ref == 'refs/heads/main' && 'linux.rocm.gpu.mi300.2' || 'linux.rocm.gpu.2' }}" },
-          { config: "default", shard: 5, num_shards: 6, runner: "${{ github.event_name == 'push' && github.event.ref == 'refs/heads/main' && 'linux.rocm.gpu.mi300.2' || 'linux.rocm.gpu.2' }}" },
-          { config: "default", shard: 6, num_shards: 6, runner: "${{ github.event_name == 'push' && github.event.ref == 'refs/heads/main' && 'linux.rocm.gpu.mi300.2' || 'linux.rocm.gpu.2' }}" },
+          { config: "default", shard: 1, num_shards: 6, runner: "linux.rocm.gpu.2" },
+          { config: "default", shard: 2, num_shards: 6, runner: "linux.rocm.gpu.2" },
+          { config: "default", shard: 3, num_shards: 6, runner: "linux.rocm.gpu.2" },
+          { config: "default", shard: 4, num_shards: 6, runner: "linux.rocm.gpu.2" },
+          { config: "default", shard: 5, num_shards: 6, runner: "linux.rocm.gpu.2" },
+          { config: "default", shard: 6, num_shards: 6, runner: "linux.rocm.gpu.2" },
         ]}
     secrets: inherit
 

.github/workflows/trunk.yml

@@ -175,9 +175,9 @@ jobs:
       sync-tag: rocm-build
       test-matrix: |
         { include: [
-          { config: "default", shard: 1, num_shards: 2, runner: "${{ github.event_name == 'push' && github.event.ref == 'refs/heads/main' && 'linux.rocm.gpu.mi300.2' || 'linux.rocm.gpu.2' }}" },
-          { config: "default", shard: 2, num_shards: 2, runner: "${{ github.event_name == 'push' && github.event.ref == 'refs/heads/main' && 'linux.rocm.gpu.mi300.2' || 'linux.rocm.gpu.2' }}" },
-          { config: "distributed", shard: 1, num_shards: 1, runner: "${{ github.event_name == 'push' && github.event.ref == 'refs/heads/main' && 'linux.rocm.gpu.mi300.4' || 'linux.rocm.gpu.4' }}" },
+          { config: "default", shard: 1, num_shards: 2, runner: "linux.rocm.gpu.2" },
+          { config: "default", shard: 2, num_shards: 2, runner: "linux.rocm.gpu.2" },
+          { config: "distributed", shard: 1, num_shards: 1, runner: "linux.rocm.gpu.4" },
         ]}
     secrets: inherit