diff --git a/tests/unit/test_d1_smem128.py b/tests/unit/test_d1_smem128.py
new file mode 100644
index 00000000..f4d3754c
--- /dev/null
+++ b/tests/unit/test_d1_smem128.py
@@ -0,0 +1,49 @@
+"""D1: Test SMEM-P at hd=128 with debug prints."""
+import torch, math
+import cutlass.cute as cute
+import cutlass.torch as ct
+import cuda.bindings.driver as cuda
+from dsv4.kernels.attention.fmha import FmhaKernel
+
+
+def test_smem_p(hd, n_kv=128):
+    m = 128
+    torch.manual_seed(42)
+    q = torch.randn(m, hd, 1, dtype=torch.bfloat16, device='cuda')
+    k = torch.randn(n_kv, hd, 1, dtype=torch.bfloat16, device='cuda')
+    v = torch.randn(n_kv, hd, dtype=torch.bfloat16, device='cuda')
+
+    qf = q[:, :, 0].float()
+    kf = k[:, :, 0].float()
+    scale = 1.0 / math.sqrt(hd)
+    attn_max = (qf @ kf.T * scale).max(dim=-1, keepdim=True)[0]
+    attn_exp = torch.exp(qf @ kf.T * scale - attn_max)
+    attn_sum = attn_exp.sum(dim=-1, keepdim=True)
+    ref_unnorm = attn_exp @ v.float()
+
+    lse_tensor = torch.zeros(m, 1, 1, dtype=torch.float32, device='cuda')
+    kernel = FmhaKernel(head_dim=hd, s_k=n_kv, use_smem_p=True)
+    pv_n_tile = kernel.pv_n_tile
+    stream = cuda.CUstream(torch.cuda.current_stream().cuda_stream)
+
+    v_tile = v[:, 0:pv_n_tile].contiguous().unsqueeze(-1)
+    c_tile = torch.zeros(m, pv_n_tile, 1, dtype=torch.bfloat16, device='cuda')
+    mQ = ct.from_dlpack(q).mark_layout_dynamic(leading_dim=ct.get_leading_dim(q))
+    mK = ct.from_dlpack(k).mark_layout_dynamic(leading_dim=ct.get_leading_dim(k))
+    mV = ct.from_dlpack(v_tile).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v_tile))
+    mC = ct.from_dlpack(c_tile).mark_layout_dynamic(leading_dim=ct.get_leading_dim(c_tile))
+    mLSE = ct.from_dlpack(lse_tensor).mark_layout_dynamic(leading_dim=ct.get_leading_dim(lse_tensor))
+
+    print(f'hd={hd} SMEM-P: Compiling...', flush=True)
+    compiled = cute.compile(kernel, mQ, mK, mV, mC, stream, mLSE)
+    compiled(mQ, mK, mV, mC, stream, mLSE)
+    torch.cuda.synchronize()
+
+    out = c_tile[:, :, 0].float()
+    cos = torch.nn.functional.cosine_similarity(out.flatten().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)).item()
+    print(f'hd={hd} SMEM-P: cos={cos:.6f}  {"PASS" if cos >= 0.99 else "FAIL"}')
+    return cos
+
+
+if __name__ == '__main__':
+    test_smem_p(128)