Open-IOV: initial public release

Open-IOV virtualizes NVIDIA GPUs so that unmodified guest drivers run with
real GPU functionality - CUDA first, 3D and video to follow - on unmodified
hosts, without a proprietary vGPU license and without patching any driver,
firmware or hypervisor.

Core principle: emulate the interface, pass through the work.

  kernel/     open-iov-vfio.ko - host VFIO mdev driver: virtual GPU device
              (PCI config space, BAR shadows, MSI-X), GSP boot emulation,
              GSP-RM message-queue/RPC emulation, memory model (GPU-VA to
              guest-PA discovery) and the semaphore-completion service that
              advances guest UVM progress.
  userspace/  libiov.so management API and examples.
  tools/      guest diagnostics, firmware analysis wrappers, RM probes.
  scripts/    stack manager, VM harness, build/load/test automation.
  config/     hardware/version profiles (the portability surface).
  docs/       documentation tree - start at docs/README.md.
  wiki/       long-form firmware and protocol deep dives.

Status: initialization works end to end for a stock 570.144 Linux guest on
Turing (TU104): driver probe, nvidia-smi, the full GSP-RM control battery,
object creation and the early CUDA/UVM start-up path. GPU work forwarding -
the step that makes CUDA kernels execute on real hardware - is the active
work item; see docs/04-implementation/01-known-knowns-and-unknowns.md.

License: BSD-3-Clause for the project; GPL-2.0 for kernel modules that link
GPL-only kernel interfaces. See LICENSE and docs/09-reference/legal-and-licensing.md.

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