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 function
wgmma_desc_sbo_lbo
def wgmma_desc_sbo_lbo[dtype: DType, layout_t: TensorLayout, is_k_major: Bool = True, swizzle_mode: TensorMapSwizzle = TensorMapSwizzle.SWIZZLE_NONE]() -> Tuple[Int, Int]
Returns the (stride, leading) byte offsets of a WGMMA operand descriptor.
The two offsets are the sub-strides of the canonical descriptor layout, in 16 B units: mode 0's second sub-stride is the stride byte offset and mode 1's second sub-stride the leading byte offset. An MN-major operand swaps the two when the swizzle is off, per the PTX "asynchronous warpgroup-level majorness" table.
Parameters:
- βdtype (
DType): Element data type of the tensor. - βlayout_t (
TensorLayout): Type of the operand tile's layout, with mode 0 the MN extent and mode 1 the K extent. - βis_k_major (
Bool): Whether the operand is K-major (True) or MN-major (False). - βswizzle_mode (
TensorMapSwizzle): Memory access pattern swizzling mode.
Returns:
Tuple[Int, Int]: The stride byte offset (SBO) and leading byte offset (LBO).