For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Mojo struct
RegisterToGMemWriter
struct RegisterToGMemWriter[c_type: DType, dst_layout: TensorLayout, dst_origin: MutOrigin, dst_engine: TensorEngine, dst_linear_idx_type: DType, //, wgmma_shape: Tuple[Int, Int, Int], num_consumer: Int, N: Int, check_runtime_bounds: Bool = False, swapAB: Bool = False]
Writer for transferring accumulator registers directly to global memory.
This writer handles the direct copy from register tiles to global memory tiles, with proper thread distribution and alignment. It supports optional epilogue processing, compute lambda transformations, and bounds checking.
Parameters
- c_type (
DType): Output data type. - dst_layout (
TensorLayout): Layout of the destination tensor. - dst_origin (
MutOrigin): Origin type of the destination tensor. - dst_engine (
TensorEngine): Engine of the destination tensor. - dst_linear_idx_type (
DType): Linear index type for destination tensor. - wgmma_shape (
Tuple[Int, Int, Int]): Shape of the WGMMA operation [M, N, K]. - num_consumer (
Int): Number of consumer warp groups. - N (
Int): Matrix N dimension. - check_runtime_bounds (
Bool): Whether to perform bounds checking on N dimension. - swapAB (
Bool): Whether to swap the A and B matrices.
Fields
- thread_info (
ThreadInfo): - dst (
RegisterToGMemWriter[wgmma_shape, num_consumer, N, check_runtime_bounds, swapAB].DstType): - num_m_mmas (
Int): - tile_coords (
OptionalReg[TileCoordinates]): - max_row (
OptionalReg[UInt32]):
Implemented traits
AnyType,
Copyable,
Deinitable,
ImplicitlyCopyable,
Movable,
RegTileWriter,
RegisterPassable,
TrivialRegisterPassable
comptime members
c_frag_size
comptime c_frag_size = ((SIMD((load_from_mem wgmma_shape.__getitem_param__[Int(0)]())) * SIMD((load_from_mem wgmma_shape.__getitem_param__[Int(1)]()))) // _resolve_warpgroup_size())
DstType
comptime DstType = TileTensor[c_type, dst_layout, dst_origin, Engine=dst_engine, linear_idx_type=dst_linear_idx_type]
num_m_frag_mat
comptime num_m_frag_mat = ((SIMD((load_from_mem wgmma_shape.__getitem_param__[Int(0)]())) // Int(4)) // Int(8))
num_n_frag_mat
comptime num_n_frag_mat = (SIMD((load_from_mem wgmma_shape.__getitem_param__[Int(1)]())) // Int(8))
Methods
__init__
def __init__(dst: TileTensor[c_type, dst_layout, dst_origin, Engine=dst_engine, linear_idx_type=dst_linear_idx_type], warp_group_thread_idx: Int, num_m_mmas: Int, tile_coords: OptionalReg[TileCoordinates] = None, max_row: OptionalReg[UInt32] = None) -> Self
Initialize the register-to-global-memory writer.
Args:
- dst (
TileTensor[c_type, dst_layout, dst_origin, Engine=dst_engine, linear_idx_type=dst_linear_idx_type]): Destination tensor in global memory. - warp_group_thread_idx (
Int): Thread index within the warp group. - num_m_mmas (
Int): Number of MMA tiles in M dimension. - tile_coords (
OptionalReg[TileCoordinates]): Optional tile coordinates for epilogue processing. - max_row (
OptionalReg[UInt32]): Optional maximum valid M coordinate (for epilogue).
write_tile
def write_tile(self, c_reg_tile: TileTensor[Engine=c_reg_tile.Engine, address_space=AddressSpace.LOCAL, linear_idx_type=c_reg_tile.linear_idx_type], coords: Tuple[Int, Int])
Write a single MMA tile from registers to global memory.
Args:
- c_reg_tile (
TileTensor[Engine=c_reg_tile.Engine, address_space=AddressSpace.LOCAL, linear_idx_type=c_reg_tile.linear_idx_type]): Register tile containing accumulator values. - coords (
Tuple[Int, Int]): Tile coordinates (row, column) in the destination matrix.