Commit Graph

2 Commits

Author SHA1 Message Date
Stanislav Mekhanoshin c078ca92eb [AMDGPU] Remove non-temporal flag from argument loads
Kernel arguments likely read by all workitems and should not bypass
cache. Fixes performance hit in sub-dword argument loads.

Differential Revision: https://reviews.llvm.org/D43249

llvm-svn: 325146
2018-02-14 18:05:14 +00:00
Changpeng Fang 4737e892de AMDGPU/SI: Add d16 support for image intrinsics.
Summary:
  This patch implements d16 support for image load, image store and image sample intrinsics.

Reviewers:
  Matt, Brian.

Differential Revision:
  https://reviews.llvm.org/D3991

llvm-svn: 322903
2018-01-18 22:08:53 +00:00