Mojo function

store_C

store_C[c_type: DType, c_smem_layout: Layout, c_layout: Layout, c_desc_layout: Layout, num_accum_pipeline_stages: UInt, /, *, accum_type: DType, block_tile_shape: IndexList[3], mma_shape: IndexList[3], c_swizzle: TensorMapSwizzle = TensorMapSwizzle(3), cta_group: Int = 1, num_output_warps: UInt = UInt(4), max_tmem_cols: UInt = UInt(512)](c_smem_tile: LayoutTensor[c_type, c_smem_layout, MutableAnyOrigin, address_space=AddressSpace(3), alignment=128], c_tma_op: TMATensorTile[c_type, c_layout, c_desc_layout], accum_pipeline_consumer_state: PipelineState[num_accum_pipeline_stages], accum_full_mbar: UnsafePointer[SharedMemBarrier, address_space=AddressSpace(3), alignment=16], accum_empty_mbar: UnsafePointer[SharedMemBarrier, address_space=AddressSpace(3), alignment=16], tmem_addr: SIMD[uint32, 1], work_tile_coord: Tuple[UInt, UInt], elect_one_warp: Bool, stage_stride_cols: UInt)