maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/inline-attr.ll

34 lines
1.8 KiB
LLVM
Raw Normal View History

[AMDGPU] Set fast-math flags on functions given the options We have a single library build without relaxation options. When inlined library functions remove fast math attributes from the functions they are integrated into. This patch sets relaxation attributes on the functions after linking provided corresponding relaxation options are given. Math instructions inside the inlined functions remain to have no fast flags, but inlining does not prevent fast math transformations of a surrounding caller code anymore. Differential Revision: https://reviews.llvm.org/D38325 llvm-svn: 314568
2017-09-30 07:40:19 +08:00
; RUN: opt -mtriple=amdgcn--amdhsa -S -O3 -enable-unsafe-fp-math %s | FileCheck -check-prefix=GCN -check-prefix=UNSAFE %s
; RUN: opt -mtriple=amdgcn--amdhsa -S -O3 -enable-no-nans-fp-math %s | FileCheck -check-prefix=GCN -check-prefix=NONANS %s
; RUN: opt -mtriple=amdgcn--amdhsa -S -O3 -enable-no-infs-fp-math %s | FileCheck -check-prefix=GCN -check-prefix=NOINFS %s
; GCN: define float @foo(float %x) local_unnamed_addr #0 {
; GCN: define amdgpu_kernel void @caller(float addrspace(1)* nocapture %p) local_unnamed_addr #1 {
; GCN: %mul.i = fmul float %load, 1.500000e+01
; UNSAFE: attributes #0 = { norecurse nounwind readnone "less-precise-fpmad"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" }
Add, and infer, a nofree function attribute This patch adds a function attribute, nofree, to indicate that a function does not, directly or indirectly, call a memory-deallocation function (e.g., free, C++'s operator delete). Reviewers: jdoerfert Differential Revision: https://reviews.llvm.org/D49165 llvm-svn: 365336
2019-07-08 23:57:56 +08:00
; UNSAFE: attributes #1 = { nofree norecurse nounwind "less-precise-fpmad"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" }
[AMDGPU] Set fast-math flags on functions given the options We have a single library build without relaxation options. When inlined library functions remove fast math attributes from the functions they are integrated into. This patch sets relaxation attributes on the functions after linking provided corresponding relaxation options are given. Math instructions inside the inlined functions remain to have no fast flags, but inlining does not prevent fast math transformations of a surrounding caller code anymore. Differential Revision: https://reviews.llvm.org/D38325 llvm-svn: 314568
2017-09-30 07:40:19 +08:00
; NOINFS: attributes #0 = { norecurse nounwind readnone "no-infs-fp-math"="true" }
Add, and infer, a nofree function attribute This patch adds a function attribute, nofree, to indicate that a function does not, directly or indirectly, call a memory-deallocation function (e.g., free, C++'s operator delete). Reviewers: jdoerfert Differential Revision: https://reviews.llvm.org/D49165 llvm-svn: 365336
2019-07-08 23:57:56 +08:00
; NOINFS: attributes #1 = { nofree norecurse nounwind "less-precise-fpmad"="false" "no-infs-fp-math"="true" "no-nans-fp-math"="false" "unsafe-fp-math"="false" }
[AMDGPU] Set fast-math flags on functions given the options We have a single library build without relaxation options. When inlined library functions remove fast math attributes from the functions they are integrated into. This patch sets relaxation attributes on the functions after linking provided corresponding relaxation options are given. Math instructions inside the inlined functions remain to have no fast flags, but inlining does not prevent fast math transformations of a surrounding caller code anymore. Differential Revision: https://reviews.llvm.org/D38325 llvm-svn: 314568
2017-09-30 07:40:19 +08:00
; NONANS: attributes #0 = { norecurse nounwind readnone "no-nans-fp-math"="true" }
Add, and infer, a nofree function attribute This patch adds a function attribute, nofree, to indicate that a function does not, directly or indirectly, call a memory-deallocation function (e.g., free, C++'s operator delete). Reviewers: jdoerfert Differential Revision: https://reviews.llvm.org/D49165 llvm-svn: 365336
2019-07-08 23:57:56 +08:00
; NONANS: attributes #1 = { nofree norecurse nounwind "less-precise-fpmad"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="true" "unsafe-fp-math"="false" }
[AMDGPU] Set fast-math flags on functions given the options We have a single library build without relaxation options. When inlined library functions remove fast math attributes from the functions they are integrated into. This patch sets relaxation attributes on the functions after linking provided corresponding relaxation options are given. Math instructions inside the inlined functions remain to have no fast flags, but inlining does not prevent fast math transformations of a surrounding caller code anymore. Differential Revision: https://reviews.llvm.org/D38325 llvm-svn: 314568
2017-09-30 07:40:19 +08:00
define float @foo(float %x) #0 {
entry:
%mul = fmul float %x, 1.500000e+01
ret float %mul
}
define amdgpu_kernel void @caller(float addrspace(1)* %p) #1 {
entry:
%load = load float, float addrspace(1)* %p, align 4
%call = call fast float @foo(float %load) #0
store float %call, float addrspace(1)* %p, align 4
ret void
}
attributes #0 = { nounwind }
attributes #1 = { nounwind "less-precise-fpmad"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" }