"""Quick LSE diagnostic: is the softmax correct at hd>64?"""
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_lse(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')
    c = torch.zeros(m, hd, 1, dtype=torch.bfloat16, device='cuda')

    # Reference LSE
    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_lse = torch.log(attn_sum.squeeze(-1)) + attn_max.squeeze(-1)

    lse_tensor = torch.zeros(m, 1, 1, dtype=torch.float32, device='cuda')
    kernel = FmhaKernel(head_dim=hd, s_k=n_kv)
    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}: Compiling...', flush=True)
    compiled = cute.compile(kernel, mQ, mK, mV, mC, stream, mLSE)
    compiled(mQ, mK, mV, mC, stream, mLSE)
    torch.cuda.synchronize()

    kernel_lse = lse_tensor[0, 0, 0].item()
    ref_lse_val = ref_lse[0].item()
    lse_err = abs(kernel_lse - ref_lse_val)
    print(f'hd={hd}: kernel_lse={kernel_lse:.6f}  ref_lse={ref_lse_val:.6f}  err={lse_err:.6f}  {"PASS" if lse_err < 0.01 else "FAIL"}')

    # Also check if P store to TMEM is correct by comparing O directly
    # Output the raw O (un-normalized) from the kernel
    out = c[:, :, 0].float()
    ref_unnorm = attn_exp @ v.float()
    cos = torch.nn.functional.cosine_similarity(out.flatten().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)).item()
    print(f'hd={hd}: cos_unnorm={cos:.6f}')


if __name__ == '__main__':
    for hd in [64, 128, 256]:
        test_lse(hd)