#!/usr/bin/env python3
"""Helion v1.0 tiled matmul boundary from the official project example."""

import helion
import helion.language as hl
import torch


@helion.kernel()
def matmul(x: torch.Tensor, y: torch.Tensor) -> torch.Tensor:
    m, k = x.size()
    _k, n = y.size()
    output = torch.empty([m, n], dtype=x.dtype, device=x.device)
    for tile_m, tile_n in hl.tile([m, n]):
        accumulator = hl.zeros([tile_m, tile_n], dtype=torch.float32)
        for tile_k in hl.tile(k):
            accumulator = torch.addmm(
                accumulator, x[tile_m, tile_k], y[tile_k, tile_n]
            )
        output[tile_m, tile_n] = accumulator
    return output


if __name__ == "__main__":
    raise SystemExit("parser_only: GPU execution and reference comparison not captured")