"""D1: Test raw unnormalized PV output (epilogue_tma_store without normalize)."""
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

for hd in [64, 128, 256]:
    torch.manual_seed(42)
    n = 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')
    c = torch.zeros(m, hd, 1, dtype=torch.bfloat16, device='cuda')

    # Reference: unnormalized PV = (softmax(QK^T) * scale) @ V  (without sum normalization)
    qf = q[:,:,0].float(); kf = k[:,:,0].float()
    scale = 1.0 / math.sqrt(hd)
    attn = qf @ kf.T * scale
    attn_unnorm = torch.exp(attn - attn.max(dim=-1, keepdim=True).values)  # unnormalized softmax
    ref_unnorm = attn_unnorm @ v.float()

    # Also compute properly normalized for comparison
    attn_norm = torch.softmax(attn, dim=-1)
    ref_norm = attn_norm @ v.float()

    v_kernel = v.unsqueeze(-1)
    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))
    stream = cuda.CUstream(torch.cuda.current_stream().cuda_stream)

    kernel = FmhaKernel(head_dim=hd, s_k=n)
    print(f'hd={hd}: Compiling...', flush=True)
    compiled = cute.compile(kernel, mQ, mK, mV, mC, stream)
    compiled(mQ, mK, mV, mC, stream)
    torch.cuda.synchronize()

    out = c[:,:,0].float()

    # Check against unnormalized reference
    cos_unnorm = torch.nn.functional.cosine_similarity(
        out.flatten().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)
    ).item()

    # Check against normalized reference (should be lower due to missing normalize)
    cos_norm = torch.nn.functional.cosine_similarity(
        out.flatten().unsqueeze(0), ref_norm.flatten().unsqueeze(0)
    ).item()

    print(f'hd={hd}: cos_unnorm={cos_unnorm:.6f}  cos_norm={cos_norm:.6f}')