tools/cuda-ab: P2 arbitrary-kernel suite expansion (regs/streams/printf), smiley push wiring, near-native perf harness (offline readiness; guest validation pending)

1 files changed, 27 insertions, 5 deletions

diff --git a/tools/cuda-ab/ab.sh b/tools/cuda-ab/ab.sh
index 5a290e4..d0326f8 100755
--- a/tools/cuda-ab/ab.sh
+++ b/tools/cuda-ab/ab.sh
@@ -11,7 +11,13 @@
 #   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 push     # push $WORKLOAD (default vector_add) to the VM
 #   tools/cuda-ab/ab.sh victory  # push victory_mail to the VM (runner executes it)
+#   tools/cuda-ab/ab.sh smiley   # push smiley (== WORKLOAD=smiley ./ab.sh push)
+#
+# WORKLOAD selects the program (<name>.cu -> run/<name>); guest execution uses
+# AB_GUEST_TIMEOUT seconds (default 300) because the first emulated CUDA call
+# can be much slower than a bare-metal launch.
 #
 # The binary links the CUDA runtime statically, so the guest needs no CUDA
 # toolkit - only the guest driver's libcuda.so.
@@ -24,6 +30,7 @@ RUN="$HERE/run"
 WORKLOAD="${WORKLOAD:-vector_add}"
 SRC="$HERE/$WORKLOAD.cu"
 BIN="$RUN/$WORKLOAD"
+AB_GUEST_TIMEOUT="${AB_GUEST_TIMEOUT:-300}"
 
 mkdir -p "$RUN"
 
@@ -39,8 +46,13 @@ run_host() {
 }
 
 push_bin() {
-	[ -x "$BIN" ] || build_host
-	local b64 chunk off total size
+	[ -f "$SRC" ] || { echo "no source for WORKLOAD=$WORKLOAD ($SRC)"; exit 1; }
+	# Rebuild when missing or older than the source, so a pushed binary is
+	# never stale relative to its .cu.
+	if [ ! -x "$BIN" ] || [ "$SRC" -nt "$BIN" ]; then
+		build_host
+	fi
+	local b64 chunk off total size out
 	b64=$(base64 -w0 "$BIN")
 	total=${#b64}
 	off=0
@@ -52,13 +64,18 @@ push_bin() {
 		"$VMEXEC" exec "echo -n '$chunk' >> /tmp/$WORKLOAD.b64" >/dev/null 2>&1
 		off=$((off + size))
 	done
-	"$VMEXEC" exec "base64 -d /tmp/$WORKLOAD.b64 > /tmp/$WORKLOAD && chmod +x /tmp/$WORKLOAD && rm -f /tmp/$WORKLOAD.b64 && echo PUSH_OK"
+	out=$("$VMEXEC" exec "base64 -d /tmp/$WORKLOAD.b64 > /tmp/$WORKLOAD && chmod +x /tmp/$WORKLOAD && rm -f /tmp/$WORKLOAD.b64 && echo PUSH_OK" 2>&1) || true
+	printf '%s\n' "$out"
+	case "$out" in
+	*PUSH_OK*) ;;
+	*) echo "push failed (no PUSH_OK)" >&2; exit 1 ;;
+	esac
 }
 
 run_guest() {
 	push_bin
 	echo "[*] guest run (emulated vGPU)"
-	"$VMEXEC" exec "/tmp/$WORKLOAD" 2>&1 | tee "$RUN/guest.txt"
+	"$VMEXEC" exec --timeout "$AB_GUEST_TIMEOUT" "/tmp/$WORKLOAD" 2>&1 | tee "$RUN/guest.txt"
 }
 
 compare() {
@@ -92,5 +109,10 @@ victory)
 	SRC="$HERE/$WORKLOAD.cu"
 	BIN="$RUN/$WORKLOAD"
 	push_bin ;;
-*)       echo "usage: $0 [host|guest|compare|all|victory]"; exit 1 ;;
+smiley)
+	WORKLOAD=smiley
+	SRC="$HERE/$WORKLOAD.cu"
+	BIN="$RUN/$WORKLOAD"
+	push_bin ;;
+*)       echo "usage: $0 [host|guest|compare|all|push|victory|smiley]"; exit 1 ;;
 esac