Mojo function
warpgroup_fence
warpgroup_fence[accum_type: DType, accum_layout: Layout, //](accum: LayoutTensor[accum_type, accum_layout, origin, address_space=AddressSpace(5), element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment])
Code motion fence to ensure the registers of the WGMMA instruction do not get touched by anything.
This has no impact on kernel correctness. It serves purely as an NVVM code motion barrier, preventing other operations from modifying the WGMMA instruction's registers during execution of the WGMMA instruction batch.
Parameters:
- accum_type (
DType
): Element data type of the tensor. - accum_layout (
Layout
): Register layout of the accumulator.
Args:
- accum (
LayoutTensor
): A LayoutTensor with the accum_type and accum_layout.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!