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 trait

InnerMatmulKernel

Trait for CPU matmul microkernels operating on pre-packed tiles.

Conforming types implement __inner_matmul__, which accumulates a (kernel_rows × TileN × TileK) block of the output matrix using a packed B tile in cache-friendly layout.

Implemented traits

AnyType, Copyable, Deinitable, ImplicitlyCopyable, Movable

Provided methods

__inner_matmul__

def __inner_matmul__[kernel_rows: Int, kernel_cols: Int, simd_size: Int](self, c: TileTensor[Engine=c.Engine, address_space=c.address_space, linear_idx_type=c.linear_idx_type], a: TileTensor[Engine=a.Engine, address_space=a.address_space, linear_idx_type=a.linear_idx_type], b_packed: TileTensor[Engine=b_packed.Engine, address_space=b_packed.address_space, linear_idx_type=b_packed.linear_idx_type], global_offset: GemmShape, global_bound: GemmShape, tile_n_k: IndexList[Int(2)], skip_boundary_check: Bool)

Accumulates one packed B tile into the corresponding C tile.

Parameters:

• ​kernel_rows (Int): Number of C rows the microkernel accumulates per tile.
• ​kernel_cols (Int): Number of C columns the microkernel accumulates per tile.
• ​simd_size (Int): SIMD vector width used by the inner accumulation.

Args:

• ​c (TileTensor[Engine=c.Engine, address_space=c.address_space, linear_idx_type=c.linear_idx_type]): Output tile to accumulate into.
• ​a (TileTensor[Engine=a.Engine, address_space=a.address_space, linear_idx_type=a.linear_idx_type]): Non-transposed left operand tile.
• ​b_packed (TileTensor[Engine=b_packed.Engine, address_space=b_packed.address_space, linear_idx_type=b_packed.linear_idx_type]): Pre-packed right operand panel (rank 3).
• ​global_offset (GemmShape): (M, N, K) offset of this tile in the full problem.
• ​global_bound (GemmShape): (M, N, K) bounds of the full problem.
• ​tile_n_k (IndexList[Int(2)]): Dynamic (N, K) extent of the tile to process.
• ​skip_boundary_check (Bool): Whether to skip partial-tile boundary handling.