Mojo struct
Inner_matmul_neon
struct Inner_matmul_neon
Implemented traits
AnyType,
Copyable,
ImplicitlyCopyable,
ImplicitlyDestructible,
InnerMatmulKernel,
Movable
Methods
__inner_matmul__
__inner_matmul__[kernel_rows: Int, kernel_cols: Int, simd_size: Int](self, c: TileTensor[c.dtype, c.LayoutType, c.origin, address_space=c.address_space, linear_idx_type=c.linear_idx_type, element_size=c.element_size], a: TileTensor[a.dtype, a.LayoutType, a.origin, address_space=a.address_space, linear_idx_type=a.linear_idx_type, element_size=a.element_size], b_packed: TileTensor[b_packed.dtype, b_packed.LayoutType, b_packed.origin, address_space=b_packed.address_space, linear_idx_type=b_packed.linear_idx_type, element_size=b_packed.element_size], global_offset: GemmShape, global_bound: GemmShape, tile_n_k: IndexList[2], skip_boundary_check: Bool)
Utility function on the inner loop. Run the inner kernel on the whole (kernel_rows, TileN, TileK) tile.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!