"""
D1: Minimal O rescale test with just s_k=256 at hd=64.
Tests the exact same thing as test_d1_multi_kv but simpler.
"""
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 = 64
    s_k = 256
    m = 128
    n_kv_tiles = s_k // 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 (full attention)
    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_norm = (attn_exp / attn_sum) @ v.float()

    # Per-tile references for debugging
    # Tile 0 only
    kf0 = k[:128, :, 0].float()
    attn0 = qf @ kf0.T * scale
    attn_max0 = attn0.max(dim=-1, keepdim=True)[0]
    attn_exp0 = torch.exp(attn0 - attn_max0)
    ref0 = attn_exp0 @ v[:128].float()

    # Tile 1 only (with rescale from tile 0's max)
    kf1 = k[128:, :, 0].float()
    attn1 = qf @ kf1.T * scale
    new_max = torch.max(attn_max0, (qf @ kf1.T * scale).max(dim=-1, keepdim=True)[0])
    acc_scale = torch.exp(attn_max0 - new_max)
    attn_exp1 = torch.exp(attn1 - new_max)
    ref_rescaled = acc_scale * ref0 + attn_exp1 @ v[128:].float()

    print(f"  Tile-0 only O[0,:4] = {ref0[0,:4].tolist()}")
    print(f"  Rescaled O[0,:4]    = {ref_rescaled[0,:4].tolist()}")
    print(f"  Full ref O[0,:4]    = {ref_unnorm[0,:4].tolist()}")
    print(f"  acc_scale range     = [{acc_scale.min().item():.4f}, {acc_scale.max().item():.4f}]")

    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
    n_pv_tiles = kernel.n_pv_tiles

    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 (n_kv_tiles={n_kv_tiles})...', flush=True)
    compiled = cute.compile(kernel, mQ, mK, mV, mC, stream, mLSE)

    lse_val = None
    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()

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

    out_unnorm = c[:, :, 0].float()
    out_norm = out_unnorm / attn_sum

    cos_unnorm = torch.nn.functional.cosine_similarity(
        out_unnorm.flatten().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)
    ).item()
    cos_norm = torch.nn.functional.cosine_similarity(
        out_norm.flatten().unsqueeze(0), ref_norm.flatten().unsqueeze(0)
    ).item()

    print(f"  cos_unnorm={cos_unnorm:.6f}  cos_norm={cos_norm:.6f}")
    print(f"  out[0,:4]={out_unnorm[0,:4].tolist()}")
    print(f"  lse_val={lse_val}")
    print(f"  {'PASS' if cos_unnorm >= 0.99 else 'FAIL'}")


if __name__ == '__main__':
    test()