[ROCm][CI] Re-enable periodic-rocm-mi350; use gfx950.4 runners

.github/actionlint.yaml

@@ -68,6 +68,7 @@ self-hosted-runner:
     - linux.rocm.gpu.gfx942.1
     - linux.rocm.gpu.gfx942.2
     - linux.rocm.gpu.gfx942.4
+    - linux.rocm.gpu.gfx950.4
     - linux.rocm.gfx942.docker-cache
     # Org wise AWS `mac2.metal` runners (2020 Mac mini hardware powered by Apple silicon M1 processors)
     - macos-m1-stable

.github/pytorch-probot.yml

@@ -32,6 +32,7 @@ ciflow_push_tags:
 - ciflow/periodic
 - ciflow/periodic-rocm-mi200
 - ciflow/periodic-rocm-mi300
+- ciflow/periodic-rocm-mi350
 - ciflow/pull
 - ciflow/quantization-periodic
 - ciflow/riscv64

.github/workflows/periodic-rocm-mi350.yml

@@ -0,0 +1,84 @@
+# Owner(s): ["module: rocm"]
+name: periodic-rocm-mi350
+
+on:
+  schedule:
+    # We have several schedules so jobs can check github.event.schedule to activate only for a fraction of the runs.
+    # Also run less frequently on weekends.
+    - cron: 45 0,8,16 * * 1-5
+    - cron: 45 4 * * 0,6
+    - cron: 45 4,12,20 * * 1-5
+    - cron: 45 12 * * 0,6
+    - cron: 29 8 * * *  # about 1:29am PDT, for mem leak check and rerun disabled tests
+  push:
+    tags:
+      - ciflow/periodic/*
+      - ciflow/periodic-rocm-mi350/*
+    branches:
+      - release/*
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref_name }}-${{ github.ref_type == 'branch' && github.sha }}-${{ github.event_name == 'workflow_dispatch' && github.run_id }}-${{ github.event_name == 'schedule' }}-${{ github.event.schedule }}
+  cancel-in-progress: true
+
+permissions: read-all
+
+jobs:
+  llm-td:
+    if: github.repository_owner == 'pytorch'
+    name: before-test
+    uses: ./.github/workflows/llm_td_retrieval.yml
+    permissions:
+      id-token: write
+      contents: read
+
+  target-determination:
+    name: before-test
+    uses: ./.github/workflows/target_determination.yml
+    needs: llm-td
+    permissions:
+      id-token: write
+      contents: read
+
+  get-label-type:
+    name: get-label-type
+    uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@main
+    if: (github.event_name != 'schedule' || github.repository == 'pytorch/pytorch') && github.repository_owner == 'pytorch'
+    with:
+      triggering_actor: ${{ github.triggering_actor }}
+      issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
+      curr_branch: ${{ github.head_ref || github.ref_name }}
+      curr_ref_type: ${{ github.ref_type }}
+      check_experiments: amd-do
+
+  linux-noble-rocm-py3_12-build:
+    name: linux-noble-rocm-py3.12-mi350
+    uses: ./.github/workflows/_linux-build.yml
+    needs: get-label-type
+    with:
+      runner_prefix: ""
+      build-environment: linux-noble-rocm-py3.12-mi350
+      docker-image-name: ci-image:pytorch-linux-noble-rocm-n-py3
+      test-matrix: |
+        { include: [
+          { config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.amd-do-label-type }}linux.rocm.gpu.gfx950.4", owners: ["module:rocm", "oncall:distributed"] },
+          { config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.amd-do-label-type }}linux.rocm.gpu.gfx950.4", owners: ["module:rocm", "oncall:distributed"] },
+          { config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.amd-do-label-type }}linux.rocm.gpu.gfx950.4", owners: ["module:rocm", "oncall:distributed"] },
+        ]}
+    secrets: inherit
+
+  linux-noble-rocm-py3_12-test:
+    permissions:
+      id-token: write
+      contents: read
+    name: linux-noble-rocm-py3.12-mi350
+    uses: ./.github/workflows/_rocm-test.yml
+    needs:
+      - linux-noble-rocm-py3_12-build
+      - target-determination
+    with:
+      build-environment: ${{ needs.linux-noble-rocm-py3_12-build.outputs.build-environment }}
+      docker-image: ${{ needs.linux-noble-rocm-py3_12-build.outputs.docker-image }}
+      test-matrix: ${{ needs.linux-noble-rocm-py3_12-build.outputs.test-matrix }}
+    secrets: inherit

.github/workflows/upload-test-stats.yml

@@ -9,6 +9,7 @@ on:
       - periodic
       - periodic-rocm-mi200
       - periodic-rocm-mi300
+      - periodic-rocm-mi350
       - inductor
       - unstable
       - slow