Mojo function

matmul_sm100_fallback_kernel

matmul_sm100_fallback_kernel[a_type: DType, b_type: DType, c_type: DType, a_layout: Layout, b_layout: Layout, c_layout: Layout, a_desc_layout: Layout, b_desc_layout: Layout, block_tile_shape: IndexList[3], mma_shape: IndexList[3], transpose_b: Bool = True, cluster_shape: StaticTuple[SIMD[int32, 1], 3] = StaticTuple(1, 1, 1), a_swizzle: TensorMapSwizzle = TensorMapSwizzle(3), b_swizzle: TensorMapSwizzle = TensorMapSwizzle(3), num_threads: UInt = UInt(128), elementwise_lambda_fn: OptionalReg[fn[DType, Int, Int](IndexList[2], SIMD[$0, $1]) capturing -> None] = OptionalReg[fn[DType, Int, Int](IndexList[2], SIMD[$0, $1]) capturing -> None]({:i1 0, 1})](a_tma_op: TMATensorTile[a_type, a_layout, a_desc_layout], b_tma_op: TMATensorTile[b_type, b_layout, b_desc_layout], c: LayoutTensor[c_type, c_layout, MutableAnyOrigin], num_iters: UInt)