"""
FMHA D2: Multi-Head via per-head kernel launch (simple approach).

For DSV4 MQA, each query head shares the same K/V.
We launch the kernel once per (head, batch) pair.
"""
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_multihead(hd=64, n_h=1, batch=1, T=128, s_k=128):
    torch.manual_seed(42)

    q = torch.randn(batch, n_h, T, hd, dtype=torch.bfloat16, device='cuda')
    k = torch.randn(batch, s_k, hd, dtype=torch.bfloat16, device='cuda')
    v = torch.randn(batch, s_k, hd, dtype=torch.bfloat16, device='cuda')
    o = torch.zeros(batch, n_h, T, hd, dtype=torch.bfloat16, device='cuda')

    # FP32 reference
    qf = q.float()
    kf = k.float()
    vf = v.float()
    scale = 1.0 / math.sqrt(hd)

    ref_o = torch.zeros_like(qf)
    for b in range(batch):
        for h in range(n_h):
            attn = qf[b, h] @ kf[b].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_o[b, h] = (attn_exp / attn_sum) @ vf[b]

    # Run kernel per (head, batch)
    kernel = FmhaKernel(head_dim=hd, s_k=s_k, use_smem_p=False, normalize=False)
    pv_n_tile = kernel.pv_n_tile
    stream = cuda.CUstream(torch.cuda.current_stream().cuda_stream)

    # Compile once with first head's data
    q0 = q[0, 0].unsqueeze(-1)  # (T, hd, 1)
    k0 = k[0].unsqueeze(-1)     # (s_k, hd, 1)
    v0_tile = v[0, :, 0:pv_n_tile].contiguous()
    v0_k = v0_tile.unsqueeze(-1)
    c0 = torch.zeros(T, pv_n_tile, 1, dtype=torch.bfloat16, device='cuda')
    lse0 = torch.zeros(T, 1, 1, dtype=torch.float32, device='cuda')

    mQ = ct.from_dlpack(q0).mark_layout_dynamic(leading_dim=ct.get_leading_dim(q0))
    mK = ct.from_dlpack(k0).mark_layout_dynamic(leading_dim=ct.get_leading_dim(k0))
    mV = ct.from_dlpack(v0_k).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v0_k))
    mC = ct.from_dlpack(c0).mark_layout_dynamic(leading_dim=ct.get_leading_dim(c0))
    mLSE = ct.from_dlpack(lse0).mark_layout_dynamic(leading_dim=ct.get_leading_dim(lse0))

    print(f'  Compiling (hd={hd}, n_h={n_h}, batch={batch}, T={T}, s_k={s_k})...', flush=True)
    compiled = cute.compile(kernel, mQ, mK, mV, mC, stream, mLSE)

    for b in range(batch):
        for h in range(n_h):
            q_h = q[b, h].unsqueeze(-1)  # (T, hd, 1)
            k_b = k[b].unsqueeze(-1)     # (s_k, hd, 1)
            v_b = v[b]                    # (s_k, hd)
            c_h = torch.zeros(T, hd, dtype=torch.bfloat16, device='cuda')

            # Run per PV tile
            for nt in range(hd // pv_n_tile):
                v_start = nt * pv_n_tile
                v_end = v_start + pv_n_tile
                v_tile = v_b[:, v_start:v_end].contiguous()
                v_k = v_tile.unsqueeze(-1)
                c_tile = torch.zeros(T, pv_n_tile, 1, dtype=torch.bfloat16, device='cuda')
                lse0.zero_()

                mQ = ct.from_dlpack(q_h).mark_layout_dynamic(leading_dim=ct.get_leading_dim(q_h))
                mK = ct.from_dlpack(k_b).mark_layout_dynamic(leading_dim=ct.get_leading_dim(k_b))
                mV = ct.from_dlpack(v_k).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v_k))
                mC = ct.from_dlpack(c_tile).mark_layout_dynamic(leading_dim=ct.get_leading_dim(c_tile))
                mLSE = ct.from_dlpack(lse0).mark_layout_dynamic(leading_dim=ct.get_leading_dim(lse0))

                compiled(mQ, mK, mV, mC, stream, mLSE)
                c_h[:, v_start:v_end] = c_tile[:, :, 0]

            o[b, h] = c_h

    torch.cuda.synchronize()

    # Compare (normalized)
    o_norm = o.float()
    for b in range(batch):
        for h in range(n_h):
            qf_h = qf[b, h]
            kf_b = kf[b]
            attn = qf_h @ kf_b.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)
            o_norm[b, h] = (attn_exp / attn_sum) @ vf[b]

    cos = torch.nn.functional.cosine_similarity(
        o.flatten().unsqueeze(0), ref_o.flatten().unsqueeze(0)
    ).item()

    # Wait, o is the kernel output (un-normalized), ref_o is normalized. Need to compare properly.
    # Actually, the kernel with normalize=False outputs un-normalized O.
    # For a fair comparison, let me compute un-normalized reference.
    ref_unnorm = torch.zeros_like(ref_o)
    for b in range(batch):
        for h in range(n_h):
            qf_h = qf[b, h]
            kf_b = kf[b]
            attn = qf_h @ kf_b.T * scale
            attn_max = attn.max(dim=-1, keepdim=True)[0]
            attn_exp = torch.exp(attn - attn_max)
            ref_unnorm[b, h] = attn_exp @ vf[b]

    cos = torch.nn.functional.cosine_similarity(
        o.flatten().float().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)
    ).item()

    print(f'  hd={hd}, n_h={n_h}, batch={batch}, T={T}, s_k={s_k}: cos {cos:.6f}  {"PASS" if cos >= 0.99 else "FAIL"}')


def test():
    print("=== D2: Multi-Head (per-head launch) ===\n")

    # n_h=1 regression
    test_multihead(64, 1, 1, 128, 128)

    # n_h=2
    test_multihead(64, 2, 1, 128, 128)

    # n_h=8, batch=2
    test_multihead(64, 8, 2, 128, 128)


if __name__ == '__main__':
    test()