maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Feature/intrinsic-noduplicate.ll

10 lines
300 B
LLVM
Raw Normal View History

Expose "noduplicate" attribute as a property for intrinsics. The "noduplicate" function attribute exists to prevent certain optimizations from duplicating calls to the function. This is important on platforms where certain function call duplications are unsafe (for example execution barriers for CUDA and OpenCL). This patch makes it possible to specify intrinsics as "noduplicate" and translates that to the appropriate function attribute. llvm-svn: 204200
2014-03-19 07:51:07 +08:00
; RUN: llvm-as < %s | llvm-dis | FileCheck %s
[NVVM] Remove noduplicate attribute from synchronizing intrinsics. Summary: I've completed my audit of all the code that looks at noduplicate and added handling of convergent where appropriate, so we no longer need noduplicate on these intrinsics. Reviewers: jholewinski Subscribers: llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D18168 llvm-svn: 264107
2016-03-23 06:08:01 +08:00
; Make sure LLVM knows about the convergent attribute on the
NVPTX: Replace uses of cuda.syncthreads with nvvm.barrier0 Everywhere where cuda.syncthreads or __syncthreads is used, use the properly namespaced nvvm.barrier0 instead. llvm-svn: 274664
2016-07-07 04:02:45 +08:00
; llvm.nvvm.barrier0 intrinsic.
Expose "noduplicate" attribute as a property for intrinsics. The "noduplicate" function attribute exists to prevent certain optimizations from duplicating calls to the function. This is important on platforms where certain function call duplications are unsafe (for example execution barriers for CUDA and OpenCL). This patch makes it possible to specify intrinsics as "noduplicate" and translates that to the appropriate function attribute. llvm-svn: 204200
2014-03-19 07:51:07 +08:00
NVPTX: Replace uses of cuda.syncthreads with nvvm.barrier0 Everywhere where cuda.syncthreads or __syncthreads is used, use the properly namespaced nvvm.barrier0 instead. llvm-svn: 274664
2016-07-07 04:02:45 +08:00
declare void @llvm.nvvm.barrier0()
Expose "noduplicate" attribute as a property for intrinsics. The "noduplicate" function attribute exists to prevent certain optimizations from duplicating calls to the function. This is important on platforms where certain function call duplications are unsafe (for example execution barriers for CUDA and OpenCL). This patch makes it possible to specify intrinsics as "noduplicate" and translates that to the appropriate function attribute. llvm-svn: 204200
2014-03-19 07:51:07 +08:00
NVPTX: Replace uses of cuda.syncthreads with nvvm.barrier0 Everywhere where cuda.syncthreads or __syncthreads is used, use the properly namespaced nvvm.barrier0 instead. llvm-svn: 274664
2016-07-07 04:02:45 +08:00
; CHECK: declare void @llvm.nvvm.barrier0() #[[ATTRNUM:[0-9]+]]
[NVVM] Remove noduplicate attribute from synchronizing intrinsics. Summary: I've completed my audit of all the code that looks at noduplicate and added handling of convergent where appropriate, so we no longer need noduplicate on these intrinsics. Reviewers: jholewinski Subscribers: llvm-commits, jholewinski Differential Revision: http://reviews.llvm.org/D18168 llvm-svn: 264107
2016-03-23 06:08:01 +08:00
; CHECK: attributes #[[ATTRNUM]] = { convergent nounwind }