Function matmul_kernel

kernel.py:25–59

Basic tiled matmul. The agent improves this.

(
    A_ptr, B_ptr, C_ptr,
    M, N, K,
    stride_am, stride_ak,
    stride_bk, stride_bn,
    stride_cm, stride_cn,
    BLOCK_SIZE_M: tl.constexpr,
    BLOCK_SIZE_N: tl.constexpr,
    BLOCK_SIZE_K: tl.constexpr,
)

@triton.jit
def matmul_kernel(
    A_ptr, B_ptr, C_ptr,
    M, N, K,
    stride_am, stride_ak,
    stride_bk, stride_bn,
    stride_cm, stride_cn,
    BLOCK_SIZE_M: tl.constexpr,
    BLOCK_SIZE_N: tl.constexpr,
    BLOCK_SIZE_K: tl.constexpr,
):
    """Basic tiled matmul. The agent improves this."""
    pid_m = tl.program_id(0)
    pid_n = tl.program_id(1)

    offs_m = pid_m * BLOCK_SIZE_M + tl.arange(0, BLOCK_SIZE_M)
    offs_n = pid_n * BLOCK_SIZE_N + tl.arange(0, BLOCK_SIZE_N)
    offs_k = tl.arange(0, BLOCK_SIZE_K)

    a_ptrs = A_ptr + offs_m[:, None] * stride_am + offs_k[None, :] * stride_ak
    b_ptrs = B_ptr + offs_k[:, None] * stride_bk + offs_n[None, :] * stride_bn

    acc = tl.zeros((BLOCK_SIZE_M, BLOCK_SIZE_N), dtype=tl.float32)

    for k in range(0, K, BLOCK_SIZE_K):
        a = tl.load(a_ptrs, mask=(offs_m[:, None] < M) & (offs_k[None, :] < K), other=0.0)
        b = tl.load(b_ptrs, mask=(offs_k[:, None] < K) & (offs_n[None, :] < N), other=0.0)
        acc += tl.dot(a, b)
        a_ptrs += BLOCK_SIZE_K * stride_ak
        b_ptrs += BLOCK_SIZE_K * stride_bk
        offs_k += BLOCK_SIZE_K

    c = acc.to(C_ptr.dtype.element_ty)
    c_ptrs = C_ptr + offs_m[:, None] * stride_cm + offs_n[None, :] * stride_cn
    mask = (offs_m[:, None] < M) & (offs_n[None, :] < N)
    tl.store(c_ptrs, c, mask=mask)


def kernel_fn(A: torch.Tensor, B: torch.Tensor) -> torch.Tensor: