Phase 4: Portable Architecture Implementation

- Firmware Analyzer: Runtime firmware signature computation (CRC32, SHA256) and pattern-based RPC handler address discovery
- Dynamic RPC Dispatcher: Version-aware dispatch with native firmware handlers (550/560/570/580) and emulation fallback
- Hardware Architecture Layer: Turing, Ampere, Blackwell configs with BAR layouts, doorbell offsets, MSI-X vectors
- Driver Version Adaptation Layer: Feature detection per driver version
- Declarative YAML configs for hardware (turing/ampere/blackwell) and versions (550/560/570/580)
- Kernel unit tests for GSP emulation (gsp_emulation_test.c)
- Test infrastructure scripts (test_gsp_emu.sh, test_guest_driver.sh, test_cuda_workloads.sh, test_graphics_workloads.sh, test_windows_guest.sh, test_vgpu_stack.sh)
- Updated kernel Makefile with new source files

1 files changed, 45 insertions, 0 deletions

diff --git a/scripts/test_cuda_workloads.sh b/scripts/test_cuda_workloads.sh
new file mode 100755
index 0000000..ba3663a
--- /dev/null
+++ b/scripts/test_cuda_workloads.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+# CUDA Workload Validation
+# Tests various CUDA workloads in the guest
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+OPEN_IOV_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+echo "=== CUDA Workload Validation ==="
+echo "Open-IOV root: $OPEN_IOV_ROOT"
+
+# Check if we're root
+if [ "$EUID" -ne 0 ]; then
+    echo "ERROR: This script must be run as root"
+    exit 1
+fi
+
+# This script assumes guest is already running with SSH on port 2222
+# and NVIDIA driver is installed
+
+GUEST_SSH="ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null root@localhost -p 2222"
+
+echo "Testing CUDA samples..."
+$GUEST_SSH "cd /usr/local/cuda/samples && find . -name 'Makefile' -execdir make \\; 2>&1 | tail -20"
+
+echo "Running vectorAdd..."
+$GUEST_SSH "cd /usr/local/cuda/samples/1_Utilities/vectorAdd && ./vectorAdd"
+
+echo "Running matrixMul..."
+$GUEST_SSH "cd /usr/local/cuda/samples/0_Simple/matrixMul && ./matrixMul"
+
+echo "Running simpleCUBLAS..."
+$GUEST_SSH "cd /usr/local/cuda/samples/7_CUDALibraries/simpleCUBLAS && ./simpleCUBLAS"
+
+echo "Running simpleCUFFT..."
+$GUEST_SSH "cd /usr/local/cuda/samples/7_CUDALibraries/simpleCUFFT && ./simpleCUFFT"
+
+echo "Running deviceQuery..."
+$GUEST_SSH "cd /usr/local/cuda/samples/1_Utilities/deviceQuery && ./deviceQuery"
+
+echo "Running bandwidthTest..."
+$GUEST_SSH "cd /usr/local/cuda/samples/1_Utilities/bandwidthTest && ./bandwidthTest"
+
+echo "=== CUDA Workload Validation Complete ==="
\ No newline at end of file