vgsp: host CUDA bridge + sema release recovery; greeneye simulator wave

- kernel: gsp_cuda_bridge (QMD launch capture, debugfs job/out/done, param+output resolution cached from inline writes), sema drain fixes (never hold/starve a channel), GR ring autopin + counter autoreg, per-page push reads, counter-derive gate; module builds clean
- tools/cuda-bridge: CUDA driver-API daemon executing mail/vadd kernels on the physical GPU, CUBB2/CBD2 v2 protocol, layout check + self-tests
- tools/guest-diag + tools/cuda-ab: scanner/pin fixes, victory push-only mode
- debug/risc-v-gsp-rm-vm: Phase S simulator wave (GSP device model, boot ladder, triage/re-demo harnesses, docs 30-41), GPGPU-sim scaffolding
- STATE-CURRENT/docs updates

1 files changed, 14 insertions, 7 deletions

diff --git a/tools/cuda-ab/ab.sh b/tools/cuda-ab/ab.sh
index 07f6b24..8ae05ee 100755
--- a/tools/cuda-ab/ab.sh
+++ b/tools/cuda-ab/ab.sh
@@ -11,6 +11,7 @@
 #   tools/cuda-ab/ab.sh guest    # push the binary + run in the running VM
 #   tools/cuda-ab/ab.sh compare  # diff the stable result lines
 #   tools/cuda-ab/ab.sh all      # host + guest + compare
+#   tools/cuda-ab/ab.sh victory  # push victory_mail to the VM (runner executes it)
 #
 # The binary links the CUDA runtime statically, so the guest needs no CUDA
 # toolkit - only the guest driver's libcuda.so.
@@ -20,8 +21,9 @@ HERE="$(cd "$(dirname "$0")" && pwd)"
 REPO="$(cd "$HERE/../.." && pwd)"
 VMEXEC="$REPO/scripts/vgpu_vm.py"
 RUN="$HERE/run"
-SRC="$HERE/vector_add.cu"
-BIN="$RUN/vector_add"
+WORKLOAD="${WORKLOAD:-vector_add}"
+SRC="$HERE/$WORKLOAD.cu"
+BIN="$RUN/$WORKLOAD"
 
 mkdir -p "$RUN"
 
@@ -44,19 +46,19 @@ push_bin() {
 	off=0
 	size=70000
 	echo "[*] pushing $(stat -c%s "$BIN") bytes to guest"
-	"$VMEXEC" exec "rm -f /tmp/vadd.b64" >/dev/null 2>&1
+	"$VMEXEC" exec "rm -f /tmp/$WORKLOAD.b64" >/dev/null 2>&1
 	while [ $off -lt $total ]; do
 		chunk=${b64:$off:$size}
-		"$VMEXEC" exec "echo -n '$chunk' >> /tmp/vadd.b64" >/dev/null 2>&1
+		"$VMEXEC" exec "echo -n '$chunk' >> /tmp/$WORKLOAD.b64" >/dev/null 2>&1
 		off=$((off + size))
 	done
-	"$VMEXEC" exec "base64 -d /tmp/vadd.b64 > /tmp/vector_add && chmod +x /tmp/vector_add && rm -f /tmp/vadd.b64 && echo PUSH_OK"
+	"$VMEXEC" exec "base64 -d /tmp/$WORKLOAD.b64 > /tmp/$WORKLOAD && chmod +x /tmp/$WORKLOAD && rm -f /tmp/$WORKLOAD.b64 && echo PUSH_OK"
 }
 
 run_guest() {
 	push_bin
 	echo "[*] guest run (emulated vGPU)"
-	"$VMEXEC" exec "/tmp/vector_add" 2>&1 | tee "$RUN/guest.txt"
+	"$VMEXEC" exec "/tmp/$WORKLOAD" 2>&1 | tee "$RUN/guest.txt"
 }
 
 compare() {
@@ -84,5 +86,10 @@ host)    run_host ;;
 guest)   run_guest ;;
 compare) compare ;;
 all)     run_host; run_guest; compare ;;
-*)       echo "usage: $0 [host|guest|compare|all]"; exit 1 ;;
+victory)
+	WORKLOAD=victory_mail
+	SRC="$HERE/$WORKLOAD.cu"
+	BIN="$RUN/$WORKLOAD"
+	push_bin ;;
+*)       echo "usage: $0 [host|guest|compare|all|victory]"; exit 1 ;;
 esac