[CI][Bench] Use GPU mask to match the CPU mask

and print produced results in CI, just FYI.

Author: lukaszstolarczuk

.github/workflows/benchmarks-reusable.yml

@@ -182,8 +182,8 @@ jobs:
 
     - name: Compute core range
       run: |
-        # Compute the core range for the first NUMA node, skipping the first 4 cores.
-        # This is to avoid the first cores that the kernel is likely to schedule more work on.
+        # Compute the core range for the first NUMA node; second node is for UMF jobs.
+        # Skip the first 4 cores - the kernel is likely to schedule more work on these.
         CORES=$(lscpu | awk '
           /NUMA node0 CPU|On-line CPU/ {line=$0}
           END {
@@ -192,8 +192,12 @@ jobs:
             sub(/^0/, "4", b[1])
             print b[1]
           }')
+        echo "Selected core: $CORES"
         echo "CORES=$CORES" >> $GITHUB_ENV
 
+        ZE_AFFINITY_MASK=0
+        echo "ZE_AFFINITY_MASK=$ZE_AFFINITY_MASK" >> $GITHUB_ENV
+
     - name: Run benchmarks
       working-directory: ${{ github.workspace }}/ur-repo/
       id: benchmarks
@@ -209,6 +213,10 @@ jobs:
         ${{ inputs.upload_report && '--output-html' || '' }}
         ${{ inputs.bench_script_params }}
 
+    - name: Print benchmark results
+      run: |
+        cat ${{ github.workspace }}/ur-repo/benchmark_results.md
+
     - name: Add comment to PR
       uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
       if: ${{ always() && inputs.pr_no != 0 }}