"""
D1: Minimal TMEM round-trip test.

Strategy: Run the s_k=256 kernel but SKIP the O rescale (force acc_scale=1.0).
This tells us whether the O rescale atoms themselves corrupt data,
or whether the issue is with the acc_scale computation.

If cos with acc_scale=1.0 ≈ 0.8 (same as before), the round-trip is broken.
If cos with acc_scale=1.0 ≈ 0.999, the round-trip works but acc_scale is wrong.
"""
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():
    # Test s_k=256 with the kernel — this exercises O rescale
    hd = 64
    s_k = 256
    m = 128
    torch.manual_seed(42)

    q = torch.randn(m, hd, 1, dtype=torch.bfloat16, device='cuda')
    k = torch.randn(s_k, hd, 1, dtype=torch.bfloat16, device='cuda')
    v = torch.randn(s_k, hd, dtype=torch.bfloat16, device='cuda')
    c = torch.zeros(m, hd, 1, dtype=torch.bfloat16, device='cuda')

    # FP32 reference
    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=s_k, use_smem_p=False, normalize=False)
    pv_n_tile = kernel.pv_n_tile

    stream = cuda.CUstream(torch.cuda.current_stream().cuda_stream)

    v_tile = v[:, 0:pv_n_tile].contiguous()
    v_kernel = v_tile.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_kernel).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v_kernel))
    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'Compiling s_k={s_k}...', 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_unnorm = torch.nn.functional.cosine_similarity(
        out.flatten().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)
    ).item()

    # Also compare per-row to see pattern
    n_bad = 0
    for i in range(m):
        rc = torch.nn.functional.cosine_similarity(
            out[i].unsqueeze(0), ref_unnorm[i].unsqueeze(0)
        ).item()
        if rc < 0.95:
            n_bad += 1
            if n_bad <= 3:
                print(f'  Row {i}: cos={rc:.6f}  out[:4]={out[i,:4].tolist()}  ref[:4]={ref_unnorm[i,:4].tolist()}')

    print(f'  cos_unnorm={cos_unnorm:.6f}  {n_bad}/{m} bad rows (cos<0.95)')

    # Now test: does a 1-KV-tile kernel produce perfect output?
    kernel1 = FmhaKernel(head_dim=hd, s_k=128, use_smem_p=False, normalize=False)
    k1 = k[:128]
    c1 = torch.zeros(m, pv_n_tile, 1, dtype=torch.bfloat16, device='cuda')

    mK1 = ct.from_dlpack(k1).mark_layout_dynamic(leading_dim=ct.get_leading_dim(k1))
    mC1 = ct.from_dlpack(c1).mark_layout_dynamic(leading_dim=ct.get_leading_dim(c1))

    ref1_unnorm = (torch.exp(qf @ k1[:, :, 0].float().T * scale -
                  (qf @ k1[:, :, 0].float().T * scale).max(dim=-1, keepdim=True)[0]) @ v[:128].float())

    print(f'Compiling s_k=128...', flush=True)
    compiled1 = cute.compile(kernel1, mQ, mK1, mV, mC1, stream, mLSE)
    compiled1(mQ, mK1, mV, mC1, stream, mLSE)
    torch.cuda.synchronize()

    out1 = c1[:, :, 0].float()
    cos1 = torch.nn.functional.cosine_similarity(
        out1.flatten().unsqueeze(0), ref1_unnorm.flatten().unsqueeze(0)
    ).item()
    print(f'  s_k=128: cos_unnorm={cos1:.6f}')


if __name__ == '__main__':
    test()