Skip to content

gallivm: add load/store scratch support.

Dave Airlie requested to merge airlied/mesa:llvmpipe-cl-scratch-merge into master

Scratch space is per-thread space, so allocate the scratch size

  • vector width, and add a per-thread base offset to each load/store.

This is needed for OpenCL private memory space

Reviewed-by: Roland Scheidegger sroland@vmware.com

Merge request reports