Add SchedulerV2 (pe_accel), DPPolicy overrides, and new benchmarks

- Add cycle-accurate PE accelerator scheduler (SchedulerV2) with tiled
  GEMM/Math pipelines (DMA_IN → GEMM → MATH → DMA_WB)
- Add DPPolicy num_pes/num_cubes/num_sips overrides for single-PE testing
- Support tuple target_pe for targeting specific PE subsets
- Add gemm_single_pe and gpt3_qkv benchmarks
- Switch default topology to pe_scheduler_v2

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

benches/gemm_single_pe.py

@@ -0,0 +1,39 @@
+"""Single-PE GEMM benchmark via scheduler_v2 (pe_accel).
+
+Full host-to-PE pipeline:
+  Host → PCIE_EP → IO_CPU → M_CPU → PE_CPU → SchedulerV2 → PE_DMA → HBM
+
+Single PE: num_sips=1, num_cubes=1, num_pes=1 via DPPolicy override.
+Both operands use tl.ref (HBM-resident); scheduler_v2 tiles and streams
+per-tile DMA internally.
+
+Run:
+    kernbench run gemm_single_pe
+"""
+from kernbench.policy.placement.dp import DPPolicy
+
+# GEMM dimensions: (M, K) x (K, N) → (M, N)
+M, K, N = 32, 128, 32
+DTYPE = "f16"
+
+
+def _gemm_kernel(a_ptr, b_ptr, out_ptr, M, K, N, tl, DTYPE="f16"):
+    """Single-PE GEMM: out = a @ b. Both operands streamed from HBM by scheduler."""
+    M, K, N = int(M), int(K), int(N)
+
+    a = tl.ref(int(a_ptr), shape=(M, K), dtype=DTYPE)
+    b = tl.ref(int(b_ptr), shape=(K, N), dtype=DTYPE)
+    h = tl.composite(op="gemm", a=a, b=b, out_ptr=int(out_ptr))
+    tl.wait(h)
+
+
+def run(torch):
+    """Run the single-PE GEMM benchmark."""
+    dp = DPPolicy(cube="replicate", pe="replicate",
+                  num_sips=1, num_cubes=1, num_pes=1)
+
+    a   = torch.empty((M, K), dtype=DTYPE, dp=dp, name="a")
+    b   = torch.empty((K, N), dtype=DTYPE, dp=dp, name="b")
+    out = torch.empty((M, N), dtype=DTYPE, dp=dp, name="out")
+
+    torch.launch("gemm_single_pe", _gemm_kernel, a, b, out, M, K, N)