import torch
import torch.nn as nn
import torch.nn.functional as F


class Model(nn.Module):
    """
    Triangular multiplicative update – incoming edges.
    Mirror of the outgoing variant: updates pair (i,j) by aggregating over
    the shared index k via edges (k,i) and (k,j).
    """

    def __init__(self, pair_dim, hidden_dim):
        super().__init__()
        self.layer_norm_in = nn.LayerNorm(pair_dim)
        self.proj_a = nn.Linear(pair_dim, hidden_dim)
        self.gate_a = nn.Linear(pair_dim, hidden_dim)
        self.proj_b = nn.Linear(pair_dim, hidden_dim)
        self.gate_b = nn.Linear(pair_dim, hidden_dim)
        self.layer_norm_out = nn.LayerNorm(hidden_dim)
        self.out_proj = nn.Linear(hidden_dim, pair_dim)
        self.out_gate = nn.Linear(pair_dim, pair_dim)

    def forward(self, pair_repr: torch.Tensor, pair_mask: torch.Tensor) -> torch.Tensor:
        """
        Args:
            pair_repr: (B, N, N, pair_dim)
            pair_mask: (B, N, N)
        Returns:
            updated pair representation (B, N, N, pair_dim)
        """
        mask = pair_mask.unsqueeze(-1)
        x = self.layer_norm_in(pair_repr)

        a = self.proj_a(x) * torch.sigmoid(self.gate_a(x)) * mask  # (B, N, N, H)
        b = self.proj_b(x) * torch.sigmoid(self.gate_b(x)) * mask

        # Incoming: aggregate over k with a[k,i] * b[k,j]
        out = torch.einsum("bkih,bkjh->bijh", a, b)

        out = self.layer_norm_out(out)
        out = self.out_proj(out)
        out = torch.sigmoid(self.out_gate(pair_repr)) * out
        return out


pair_dim = 64
hidden_dim = 32
seq_len = 32
batch_size = 2


def get_inputs():
    p = popcorn_pri
    pair_repr = torch.randn(p.jitter_int(batch_size), p.jitter_int(seq_len), p.jitter_int(seq_len), pair_dim)
    pair_mask = torch.ones(p.jitter_int(batch_size), p.jitter_int(seq_len), p.jitter_int(seq_len))
    return [pair_repr, pair_mask]


def get_init_inputs():
    return [pair_dim, hidden_dim]

import torch
import torch.nn as nn
from torch.utils.cpp_extension import load_inline

cuda_source = """
#include <torch/extension.h>
#include <cuda.h>
#include <cuda_runtime.h>

__global__ void incoming_triangular_mul(
    const float* __restrict__ a,
    const float* __restrict__ b,
    float* __restrict__ out,
    int B, int N, int H
) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    int total = B * N * N * H;
    if (idx >= total) return;

    int h = idx % H;
    int j = (idx / H) % N;
    int i = (idx / (H * N)) % N;
    int batch = idx / (H * N * N);

    float sum = 0.0f;
    for (int k = 0; k < N; ++k) {
        float aval = a[((batch * N + k) * N + i) * H + h];
        float bval = b[((batch * N + k) * N + j) * H + h];
        sum += aval * bval;
    }
    out[((batch * N + i) * N + j) * H + h] = sum;
}

torch::Tensor incoming_mul_cuda(torch::Tensor a, torch::Tensor b) {
    auto B = a.size(0);
    auto N = a.size(1);
    auto H = a.size(3);
    auto out = torch::zeros({B, N, N, H}, a.options());
    int total = B * N * N * H;
    int threads = 256;
    int blocks = (total + threads - 1) / threads;
    incoming_triangular_mul<<<blocks, threads>>>(
        a.data_ptr<float>(), b.data_ptr<float>(), out.data_ptr<float>(),
        B, N, H
    );
    return out;
}
"""

cpp_source = """
torch::Tensor incoming_mul_cuda(torch::Tensor a, torch::Tensor b);
"""

module = load_inline(
    name='incoming_mul',
    cpp_sources=[cpp_source],
    cuda_sources=[cuda_source],
    functions=['incoming_mul_cuda'],
    verbose=True
)

class ModelNew(nn.Module):
    def __init__(self, pair_dim, hidden_dim):
        super().__init__()
        self.layer_norm_in = nn.LayerNorm(pair_dim)
        self.proj_a = nn.Linear(pair_dim, hidden_dim)
        self.gate_a = nn.Linear(pair_dim, hidden_dim)
        self.proj_b = nn.Linear(pair_dim, hidden_dim)
        self.gate_b = nn.Linear(pair_dim, hidden_dim)
        self.layer_norm_out = nn.LayerNorm(hidden_dim)
        self.out_proj = nn.Linear(hidden_dim, pair_dim)
        self.out_gate = nn.Linear(pair_dim, pair_dim)
        self.mul = module

    def forward(self, pair_repr: torch.Tensor, pair_mask: torch.Tensor) -> torch.Tensor:
        mask = pair_mask.unsqueeze(-1)
        x = self.layer_norm_in(pair_repr)
        a = self.proj_a(x) * torch.sigmoid(self.gate_a(x)) * mask
        b = self.proj_b(x) * torch.sigmoid(self.gate_b(x)) * mask
        out = self.mul.incoming_mul_cuda(a, b)
        out = self.layer_norm_out(out)
        out = self.out_proj(out)
        out = torch.sigmoid(self.out_gate(pair_repr)) * out
        return out