"""Quick D1 regression test: HEAD_DIM=64 only, must match Stage C.
Kernel outputs un-normalized O + LSE (D5a path)."""
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():
    torch.manual_seed(42)
    hd, n = 64, 128
    m = 128
    q = torch.randn(m, hd, 1, dtype=torch.bfloat16, device='cuda')
    k = torch.randn(n, hd, 1, dtype=torch.bfloat16, device='cuda')
    v = torch.randn(n, hd, dtype=torch.bfloat16, device='cuda')
    v_kernel = v.unsqueeze(-1)
    c = torch.zeros(m, hd, 1, dtype=torch.bfloat16, device='cuda')

    # FP32 reference (un-normalized + normalized)
    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()
    ref_norm = (attn_exp / attn_sum) @ v.float()

    lse_tensor = torch.zeros(m, 1, 1, dtype=torch.float32, 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_kernel).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v_kernel))
    mC = ct.from_dlpack(c).mark_layout_dynamic(leading_dim=ct.get_leading_dim(c))
    mLSE = ct.from_dlpack(lse_tensor).mark_layout_dynamic(leading_dim=ct.get_leading_dim(lse_tensor))
    stream = cuda.CUstream(torch.cuda.current_stream().cuda_stream)

    # normalize=False: kernel outputs un-normalized O + LSE
    kernel = FmhaKernel(head_dim=hd, s_k=n, normalize=False)
    print(f'hd={hd}, n={n}: Compiling...', flush=True)
    compiled = cute.compile(kernel, mQ, mK, mV, mC, stream, mLSE)
    compiled(mQ, mK, mV, mC, stream, mLSE)
    torch.cuda.synchronize()

    out_unnorm = c[:, :, 0].float()
    out_norm = out_unnorm / attn_sum  # external normalization using row_sum
    cos_unnorm = torch.nn.functional.cosine_similarity(
        out_unnorm.flatten().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)
    ).item()
    cos_norm = torch.nn.functional.cosine_similarity(
        out_norm.flatten().unsqueeze(0), ref_norm.flatten().unsqueeze(0)
    ).item()
    print(f'hd={hd}, n={n}: cos_unnorm {cos_unnorm:.6f}  cos_norm {cos_norm:.6f}  {"PASS" if cos_norm >= 0.99 else "FAIL"}')

if __name__ == '__main__':
    test()