Mojo function

ds_read_tr16_b64_row

ds_read_tr16_b64_row(tile: TileTensor[tile.dtype, tile.LayoutType, tile.origin, address_space=AddressSpace.SHARED, linear_idx_type=tile.linear_idx_type, element_size=tile.element_size]) -> SIMD[tile.dtype, 4]

4×16 transposed LDS read via rocdl.ds.read.tr16.b64.

Each 16-lane "row" loads a 4×16 tile, with per-lane exchange so each lane gets a column of the tile as SIMD[dtype, 4].

Returns:

SIMD

View source

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!