llvm/test/Feature/intrinsic-noduplicate.ll
Justin Bogner 45d8d9a866 NVPTX: Replace uses of cuda.syncthreads with nvvm.barrier0
Everywhere where cuda.syncthreads or __syncthreads is used, use the
properly namespaced nvvm.barrier0 instead.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@274664 91177308-0d34-0410-b5e6-96231b3b80d8
2016-07-06 20:02:45 +00:00

10 lines
300 B
LLVM

; RUN: llvm-as < %s | llvm-dis | FileCheck %s
; Make sure LLVM knows about the convergent attribute on the
; llvm.nvvm.barrier0 intrinsic.
declare void @llvm.nvvm.barrier0()
; CHECK: declare void @llvm.nvvm.barrier0() #[[ATTRNUM:[0-9]+]]
; CHECK: attributes #[[ATTRNUM]] = { convergent nounwind }