Mojo function

warp_specialized_gemm_output

warp_specialized_gemm_output[c_type: DType, accum_type: DType, c_layout: Layout, c_smem_layout: Layout, c_tma_layout: Layout, c_reg_layout: Layout, c_desc_layout: Layout, /, *, c_tile_shape: IndexList[2], c_swizzle: TensorMapSwizzle, wgmma_shape: IndexList[3], num_consumer: Int = 1, use_tma_store: Bool = False, 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}), elementwise_compute_lambda_fn: OptionalReg[fn[DType, Int, Int](IndexList[2], SIMD[$0, $1]) capturing -> SIMD[$0, $1]] = OptionalReg[fn[DType, Int, Int](IndexList[2], SIMD[$0, $1]) capturing -> SIMD[$0, $1]]({:i1 0, 1})](c_tma_op: TMATensorTile[c_type, c_tma_layout, c_desc_layout], c: LayoutTensor[c_type, c_layout, MutableAnyOrigin, address_space=address_space, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], c_smem_tile: LayoutTensor[c_type, c_smem_layout, MutableAnyOrigin, address_space=AddressSpace(3), alignment=128], c_reg_tile: LayoutTensor[accum_type, c_reg_layout, MutableAnyOrigin, address_space=AddressSpace(5)], warp_group_thread_idx: UInt, local_warp_group_idx: UInt, local_thread_idx: UInt, block_y: Int, block_x: Int)