"""D1: Debug hd=128 — check if the pipeline works with TMEM-P."""
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_hd(hd, n_kv=128, use_smem_p=False):
    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 = qf @ kf.T * scale
    attn_max = attn.max(dim=-1, keepdim=True)[0]
    attn_exp = torch.exp(attn - attn_max)
    attn_sum = attn_exp.sum(dim=-1, keepdim=True)
    ref_unnorm = attn_exp @ v.float()
    ref_lse = (torch.log(attn_sum.squeeze(-1)) + attn_max.squeeze(-1))[0].item()

    lse_tensor = torch.zeros(m, 1, 1, dtype=torch.float32, device='cuda')
    kernel = FmhaKernel(head_dim=hd, s_k=n_kv, use_smem_p=use_smem_p)
    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))

    mode = "SMEM-P" if use_smem_p else "TMEM-P"
    print(f'hd={hd} {mode}: 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()
    kernel_lse = lse_tensor[0, 0, 0].item()
    cos = torch.nn.functional.cosine_similarity(out.flatten().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)).item()
    lse_err = abs(kernel_lse - ref_lse)

    print(f'hd={hd} {mode}: cos={cos:.6f}  lse_err={lse_err:.6f}  {"PASS" if cos >= 0.99 else "FAIL"}')
    if cos < 0.99:
        print(f'  out[0,:4]={out[0,:4].tolist()}')
        print(f'  ref[0,:4]={ref_unnorm[0,:4].tolist()}')
    return cos


if __name__ == '__main__':
    print("=== D1 Debug: TMEM-P at various hd ===\n")
    test_hd(64, use_smem_p=False)
    test_hd(128, use_smem_p=False)
    test_hd(256, use_smem_p=False)