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, 52 insertions, 0 deletions

diff --git a/tools/cuda-ab/perf/results-template.json b/tools/cuda-ab/perf/results-template.json
new file mode 100644
index 0000000..ab2a1d6
--- /dev/null
+++ b/tools/cuda-ab/perf/results-template.json
@@ -0,0 +1,52 @@
+{
+  "_comment": "Open-IOV near-native performance result (open-iov-perf/1). Copy to <stamp>-guest/results.json and fill from a fresh perf.sh run; never hand-edit numbers. See PLAN-AND-HARNESS.md section 6.",
+  "schema": "open-iov-perf/1",
+  "created": "YYYY-MM-DDTHH:MM:SSZ",
+  "role": "guest",
+  "runs": 10,
+  "device": "<guest-visible GPU name>",
+  "run_cfg": {
+    "n_warm": "100",
+    "n_malloc": "50",
+    "n_thru": "100",
+    "sizes": "4096,262144,4194304,16777216"
+  },
+  "verification": {
+    "status": "OK",
+    "bad": 0
+  },
+  "aggregate": {
+    "init_ms": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "malloc_first_ms": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "malloc_ms_p50": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "malloc_ms_p95": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "launch_first_ms": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "launch_warm_p50": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "launch_warm_p95": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "kernel_fma_ms": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "kernel_fma_gflops": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "throughput_kps": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "copy_htod_4096_gbps": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "copy_dtoh_4096_gbps": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "copy_htod_16777216_gbps": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "copy_dtoh_16777216_gbps": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []},
+    "clock64_median": {"n": 10, "mean": 0.0, "median": 0.0, "p50": 0.0, "p95": 0.0, "min": 0.0, "max": 0.0, "values": []}
+  },
+  "host_gr": {
+    "launches": [{"elapsed_ms": 189, "ok": 1, "submit_to_ok_ms": 7.887}],
+    "elapsed_ms": {"n": 2, "mean": 177.5, "median": 177.5, "p50": 177.5, "p95": 189, "min": 166, "max": 189, "values": [189, 166]},
+    "submit_to_ok_ms": {"n": 2, "mean": 7.9, "median": 7.9, "p50": 7.9, "p95": 7.887, "min": 7.887, "max": 7.95, "values": [7.887, 7.95]}
+  },
+  "counters": {
+    "before": {"work_gr": {"req": 0, "ok": 0}},
+    "after": {"work_gr": {"req": 2, "ok": 2}},
+    "delta": {"work_gr": {"req": 2, "ok": 2}}
+  },
+  "environment": {
+    "module_sha256": "<sha256 of kernel/vgsp.ko>",
+    "insmod_args": "<exact recipe used for this cycle>",
+    "host_gpu_clocks": "<nvidia-smi -q -d CLOCK digest>",
+    "guest_gpu_clocks": "<nvidia-smi -q -d CLOCK digest>",
+    "commit": "<git rev-parse HEAD>"
+  }
+}