import torch
import torch.nn as nn


class Model(nn.Module):
    """
    Sparse message passing with CSR adjacency.

    For each destination node, aggregate weighted source-node features from the
    incoming edges in its CSR row. This is a core primitive in sparse graph
    neural network layers and graph convolution operators.
    """

    def __init__(self):
        super().__init__()

    def forward(
        self,
        row_ptr: torch.Tensor,
        col_idx: torch.Tensor,
        edge_weight: torch.Tensor,
        node_feat: torch.Tensor,
    ) -> torch.Tensor:
        num_nodes = row_ptr.numel() - 1
        feat_dim = node_feat.shape[1]
        out = torch.zeros(num_nodes, feat_dim, dtype=node_feat.dtype, device=node_feat.device)

        for dst in range(num_nodes):
            start = int(row_ptr[dst].item())
            end = int(row_ptr[dst + 1].item())
            if end > start:
                src = col_idx[start:end].long()
                weights = edge_weight[start:end].unsqueeze(-1)
                out[dst] = (node_feat[src] * weights).sum(dim=0)

        return out


num_nodes = 768
avg_degree = 20
feat_dim = 96




def get_inputs():
    return list(popcorn_pri.make_csr_graph_with_edge_weights(num_nodes, avg_degree, feat_dim))



def get_init_inputs():
    return []

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

cuda_source = r'''
#include <torch/extension.h>
#include <cuda.h>
#include <cuda_runtime.h>
#include <cstdint>

__global__ void sparse_agg_kernel(
    const int32_t* __restrict__ row_ptr,
    const int32_t* __restrict__ col_idx,
    const float* __restrict__ edge_weight,
    const float* __restrict__ node_feat,
    float* __restrict__ out,
    int num_nodes,
    int feat_dim
) {
    int dst = blockIdx.x * blockDim.x + threadIdx.x;
    if (dst >= num_nodes) return;

    int32_t start = row_ptr[dst];
    int32_t end = row_ptr[dst + 1];

    for (int f = 0; f < feat_dim; ++f) {
        float sum = 0.0f;
        for (int32_t e = start; e < end; ++e) {
            int32_t src = col_idx[e];
            float w = edge_weight[e];
            sum += w * node_feat[src * feat_dim + f];
        }
        out[dst * feat_dim + f] = sum;
    }
}

torch::Tensor sparse_agg_cuda(
    torch::Tensor row_ptr,
    torch::Tensor col_idx,
    torch::Tensor edge_weight,
    torch::Tensor node_feat
) {
    int num_nodes = row_ptr.size(0) - 1;
    int feat_dim = node_feat.size(1);

    auto out = torch::zeros({num_nodes, feat_dim}, node_feat.options());

    dim3 block(256);
    dim3 grid((num_nodes + 255) / 256);

    sparse_agg_kernel<<<grid, block>>>(
        row_ptr.data_ptr<int32_t>(),
        col_idx.data_ptr<int32_t>(),
        edge_weight.data_ptr<float>(),
        node_feat.data_ptr<float>(),
        out.data_ptr<float>(),
        num_nodes,
        feat_dim
    );

    return out;
}
'''

cpp_source = r'''
torch::Tensor sparse_agg_cuda(torch::Tensor row_ptr, torch::Tensor col_idx, torch::Tensor edge_weight, torch::Tensor node_feat);
'''

module = load_inline(
    name="sparse_agg",
    cpp_sources=cpp_source,
    cuda_sources=cuda_source,
    functions=["sparse_agg_cuda"],
    verbose=False,
)

class ModelNew(nn.Module):
    def __init__(self):
        super().__init__()
        self.module = module

    def forward(self, row_ptr, col_idx, edge_weight, node_feat):
        row_ptr = row_ptr.cuda().to(torch.int32).contiguous()
        col_idx = col_idx.cuda().to(torch.int32).contiguous()
        edge_weight = edge_weight.cuda().contiguous()
        node_feat = node_feat.cuda().contiguous()
        out = self.module.sparse_agg_cuda(row_ptr, col_idx, edge_weight, node_feat)
        return out.cpu()
```