"""D1 test: HEAD_DIM=512 only (faster iteration on compilation issues)."""
import torch, math, sys
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 = 512, 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')

    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_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, use_smem_p=False)
    pv_n_tile = kernel.pv_n_tile
    n_pv_tiles = kernel.n_pv_tiles
    stream = cuda.CUstream(torch.cuda.current_stream().cuda_stream)

    print(f'hd={hd}, pv_n_tile={pv_n_tile}, n_pv_tiles={n_pv_tiles}, n_k_sub_tiles={kernel.n_k_sub_tiles}, k_tile={kernel.k_tile}', flush=True)
    print(f'Compiling first PV tile...', flush=True)

    # Only compile the first PV tile to isolate compilation issues
    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))

    import time
    t0 = time.time()
    from cutlass.base_dsl.compiler import PtxasOptions, OptLevel
    compiled = cute.compile(kernel, mQ, mK, mV, mC, stream, mLSE)
    t1 = time.time()
    print(f'Compilation took {t1-t0:.1f}s', flush=True)

    # Run all PV tiles
    lse_val = None
    c = torch.zeros(m, hd, 1, dtype=torch.bfloat16, device='cuda')
    for nt in range(n_pv_tiles):
        v_start = nt * pv_n_tile
        v_end = v_start + pv_n_tile
        v_tile = v[:, v_start:v_end].contiguous()
        v_kernel = v_tile.unsqueeze(-1)
        c_tile = torch.zeros(m, pv_n_tile, 1, dtype=torch.bfloat16, device='cuda')
        lse_tensor.zero_()

        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))

        compiled(mQ, mK, mV, mC, stream, mLSE)
        torch.cuda.synchronize()
        print(f'  PV tile {nt}: done', flush=True)

        c[:, v_start:v_end, :] = c_tile
        if nt == 0:
            lse_val = lse_tensor[0, 0, 0].item()

    out_unnorm = c[:, :, 0].float()
    cos_unnorm = torch.nn.functional.cosine_similarity(
        out_unnorm.flatten().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)
    ).item()
    lse_err = abs(lse_val - ref_lse) if lse_val is not None else float('inf')

    status = "PASS" if cos_unnorm >= 0.99 else "FAIL"
    print(f'hd={hd}: cos_unnorm {cos_unnorm:.6f}  lse_err {lse_err:.6f}  {status}')

if __name__ == '__main__':
    test()