[PATCH] D19203: AMDGPU/SI: Add llvm.amdgcn.s.waitcnt.all intrinsic

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Sun Apr 17 15:28:58 PDT 2016

Previous message: [PATCH] D19203: AMDGPU/SI: Add llvm.amdgcn.s.waitcnt.all intrinsic
Next message: [llvm] r266577 - [X86] Be explicit about calls to setOperationAction for AVX2 and AVX512 rather than just looping over all vector types and conditinally matching them. NFC
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

arsenm added a comment.

What are the memory barrier requirements for GLSL? Do you need consistency between multiple workgroups?


http://reviews.llvm.org/D19203

Previous message: [PATCH] D19203: AMDGPU/SI: Add llvm.amdgcn.s.waitcnt.all intrinsic
Next message: [llvm] r266577 - [X86] Be explicit about calls to setOperationAction for AVX2 and AVX512 rather than just looping over all vector types and conditinally matching them. NFC
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list