[ci] Move the cuda jobs to new infrastructure

Author: vgvassilev

.github/workflows/ci.yml

@@ -14,7 +14,51 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  # Pre-flight job to activate the cuda infrastructure
+  prepare-dell:
+    name: Activate self-host infrastructure
+    runs-on: [self-hosted, spotter]
+    steps:
+      - name: Send Magic Packet
+        env:
+          TARGET_IP: ${{ secrets.DELL_IP }}
+          MAC_ADDR: ${{ secrets.DELL_MAC }}
+          # The container has no ping, emulate it.
+          PING: "timeout 1 bash -c 'cat < /dev/null > /dev/tcp/${{ secrets.DELL_IP }}/22' 2>/dev/null"
+        run: |
+          # Mask the IP and potential broadcast to keep logs clean
+          echo "::add-mask::$TARGET_IP"
+          BROADCAST=$(echo $TARGET_IP | sed 's/\.[0-9]*$/ .255/' | tr -d ' ')
+          echo "::add-mask::$BROADCAST"
+
+          # Install tool silently
+          sudo apt-get update -qq && sudo apt-get install -y -qq wakeonlan > /dev/null
+
+          # Check if already awake (using the Bash TCP PING variable)
+          if eval "$PING"; then
+            echo "Target machine is already awake. Exiting."
+            exit 0
+          fi
+
+          # If offline, send WoL
+          echo "Machine is offline. Sending WoL..."
+          wakeonlan -i $BROADCAST $MAC_ADDR > /dev/null
+
+          # Wait & Verify Loop (checks every 10s for 4 minutes)
+          echo "Waiting for response (checking Port 22)..."
+          for i in {1..24}; do
+            if eval "$PING"; then
+              echo "Machine is online and SSH is ready."
+              exit 0
+            fi
+            sleep 10
+          done
+
+          echo "Error: Target hardware did not respond within the timeout period."
+          exit 1
+
   build:
+    timeout-minutes: 600 # If some self-host machine is not available
     name: ${{ matrix.name }}
     runs-on: ${{ matrix.os }}
     strategy:
@@ -114,7 +158,7 @@ jobs:
             debug_build: true
 
           - name: selfh-ubu22-gcc12-runtime19-analyzers
-            os: [self-hosted, cuda]
+            os: [self-hosted, cuda, heavy]
             compiler: gcc-12
             clang-runtime: '19'
             coverage: true
@@ -193,7 +237,7 @@ jobs:
             cuda: true
 
           - name: selfh-ubu22-clang16-runtime18-cuda
-            os: [self-hosted, cuda]
+            os: [self-hosted, cuda, heavy]
             runs-on: cuda
             compiler: clang-16
             clang-runtime: '18'