Trace runner (run_v3_trace.sh) + concurrent mb7 correctness test

microbench/connector_tax/layerwise/mb7_layerwise.py

@@ -193,6 +193,29 @@ async def main_async(a):
                     print(f"[mb7] busy: A_run={na} B_run={nb}")
                     break
 
+        # --- concurrent correctness mode: fire N transfers at once ----------
+        if a.concurrent > 1 and a.mode == "layerwise":
+            print(f"[mb7] CONCURRENT correctness: {a.concurrent} simultaneous "
+                  f"transfers per size (src=A stresses concurrent producing)")
+            all_ok = True
+            for sz in sizes:
+                tasks = [
+                    asyncio.create_task(measure_layerwise(
+                        client, A, B, src_eid, src_bp_addr,
+                        synth_prompt(sz * 1000 + j, sz), sz * 1000 + j))
+                    for j in range(a.concurrent)
+                ]
+                rows = await asyncio.gather(*tasks)
+                oks = [r["cached"] >= int(sz * 0.9) for r in rows]
+                all_ok = all_ok and all(oks)
+                print(f"  sz={sz:>6} x{a.concurrent}: cached="
+                      f"{[r['cached'] for r in rows]} correct={oks}")
+            print(f"[mb7] CONCURRENT correctness: "
+                  f"{'ALL PASS' if all_ok else 'FAILURE'}")
+            if loader:
+                await loader.stop()
+            return
+
         results = []
         for sz in sizes:
             for rep in range(a.repeats):
@@ -259,6 +282,9 @@ def main():
     p.add_argument("--repeats", type=int, default=3)
     p.add_argument("--bg-load", type=int, default=0,
                    help="N concurrent background decode streams across A+B")
+    p.add_argument("--concurrent", type=int, default=1,
+                   help="layerwise: fire N simultaneous transfers to test "
+                        "concurrent-producing correctness")
     p.add_argument("--out", default="mb7_result.json")
     args = p.parse_args()
     asyncio.run(main_async(args))