-
Notifications
You must be signed in to change notification settings - Fork 10.8k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[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
- Loading branch information
Showing
4 changed files
with
69 additions
and
7 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,33 @@ | ||
; 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" } | ||
; UNSAFE: attributes #1 = { norecurse nounwind "less-precise-fpmad"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" } | ||
|
||
; NOINFS: attributes #0 = { norecurse nounwind readnone "no-infs-fp-math"="true" } | ||
; NOINFS: attributes #1 = { norecurse nounwind "less-precise-fpmad"="false" "no-infs-fp-math"="true" "no-nans-fp-math"="false" "unsafe-fp-math"="false" } | ||
|
||
; NONANS: attributes #0 = { norecurse nounwind readnone "no-nans-fp-math"="true" } | ||
; NONANS: attributes #1 = { norecurse nounwind "less-precise-fpmad"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="true" "unsafe-fp-math"="false" } | ||
|
||
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" } |