Fix T_cmd=0 robustness: beats_iterbatch 阈值除零防护 (T_cmd<=0 判 MergeBatch 不胜出, 无命令节省) + 3 条回归测试

BMM/BMM_Theory/tests/test_branches.py

@@ -369,5 +369,55 @@ class TestTransposeModeling(unittest.TestCase):
             self.assertFalse(c4.passed, f"A 不转置时 K=8 应报 dValue 违规: {c4.detail}")
 
 
+class TestZeroCmdHandling(unittest.TestCase):
+    """T_cmd=0 (无 DMA 命令固定开销) 时整链路不得除零/崩溃, 建模语义正确."""
+
+    def test_beats_iterbatch_no_division_error(self):
+        # T_cmd=0 时阈值 b0*(T_comp+T_write)/T_cmd -> +inf, MergeBatch 必须判不胜出
+        from bmm_theory.hardware import NpuSpec
+        from bmm_theory.branches.merge_batch import MergeBatchBranch
+        spec0 = NpuSpec(t_cmd_ns=0.0)
+        mb = MergeBatchBranch(spec0)
+        for b, m, n, k in [(2048, 32, 32, 256), (128, 64, 64, 512), (256, 128, 128, 4096)]:
+            win, detail = mb.beats_iterbatch(mkcase(b, m, n, k))
+            self.assertFalse(win, f"T_cmd=0 时 MergeBatch 不应胜出: {detail}")
+            self.assertIn("T_cmd=0", detail)
+
+    def test_route_with_zero_cmd_no_crash(self):
+        # 整条路由链 (含仲裁) 在 T_cmd=0 下无异常, 时延有限且 MergeBatch 让位 IterBatch
+        from bmm_theory.hardware import NpuSpec
+        router = BranchRouter(NpuSpec(t_cmd_ns=0.0))
+        r = router.route(mkcase(2048, 32, 32, 256))  # 原 MergeBatch 典型胜场形状
+        self.assertEqual(r["branch"], "IterBatch")   # 命令节省消失 -> 无合并价值
+        self.assertIsNotNone(r["timing"])
+        shapes = [(128, 64, 64, 512), (64, 64, 64, 8192), (512, 128, 128, 128),
+                  (128, 128, 128, 1024), (32, 4096, 4096, 4096)]
+        for b, m, n, k in shapes:
+            rr = router.route(mkcase(b, m, n, k))
+            t = rr["timing"]
+            self.assertIsNotNone(t, f"{b},{m},{n},{k} 应有 timing")
+            self.assertGreater(t.t_total, 0.0)
+            self.assertEqual(t.t_total, t.t_total)  # 非 NaN
+
+    def test_zero_cmd_random_smoke(self):
+        # 随机小样本冒烟: 无异常/无 NaN
+        import random
+        from bmm_theory.hardware import NpuSpec
+        router = BranchRouter(NpuSpec(t_cmd_ns=0.0))
+        rng = random.Random(9)
+        for _ in range(300):
+            b = rng.choice([2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048])
+            m = rng.choice([8, 16, 32, 64, 128, 256, 512, 1024, 4096])
+            n = rng.choice([8, 16, 32, 64, 128, 256, 512, 1024, 4096])
+            k = rng.choice([16, 32, 64, 128, 256, 512, 1024, 4096, 16384])
+            c = BmmCase(case_id="z", batch_a=b, batch_b=b, m=m, n=n, k=k)
+            rr = router.route(c)
+            self.assertIsNotNone(rr["plan"])
+            t = rr["timing"]
+            self.assertIsNotNone(t)
+            self.assertGreater(t.t_total, 0.0)
+            self.assertEqual(t.t_total, t.t_total)
+
+
 if __name__ == "__main__":
     unittest.main()