maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU: Ignore CodeObjectV3 when inlining 

This was inhibiting inlining of library functions when clang was
invoking the inliner directly. This is covering a bit of a mess with
subtarget feature handling, and this shouldn't be a subtarget
feature. The behavior is different depending on whether you are using
a -mattr flag in clang, or llc, opt.

llvm-svn: 353899
This commit is contained in:
Matt Arsenault 2019-02-12 23:30:11 +00:00
parent 749dc51e45
commit d24296e282
2 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
View File

@ -84,6 +84,7 @@ class GCNTTIImpl final : public BasicTTIImplBase<GCNTTIImpl> {
AMDGPU::FeatureSGPRInitBug,
AMDGPU::FeatureXNACK,
AMDGPU::FeatureTrapHandler,
AMDGPU::FeatureCodeObjectV3,
// Perf-tuning features
AMDGPU::FeatureFastFMAF32,

13
llvm/test/Transforms/Inline/AMDGPU/inline-target-cpu.ll
View File

@ -78,6 +78,17 @@ define i32 @call_func_without_loadstoreopt() #9 {
ret i32 %call
}
define i32 @enable_codeobjectv3() #10 {
ret i32 999
}
; CHECK-LABEL: @disable_codeobjectv3_call_codeobjectv3(
; CHECK-NEXT: ret i32 999
define i32 @disable_codeobjectv3_call_codeobjectv3() #11 {
%call = call i32 @enable_codeobjectv3()
ret i32 %call
}
attributes #0 = { nounwind }
attributes #1 = { nounwind "target-cpu"="fiji" }
attributes #2 = { nounwind "target-cpu"="fiji" "target-features"="+fp32-denormals" }
@ -88,3 +99,5 @@ attributes #6 = { nounwind "target-features"="-half-rate-64-ops" }
attributes #7 = { nounwind "target-features"="+half-rate-64-ops" }
attributes #8 = { nounwind "target-features"="-load-store-opt" }
attributes #9 = { nounwind "target-features"="+load-store-opt" }
attributes #10 = { nounwind "target-features"="+code-object-v3" }
attributes #11 = { nounwind "target-features"="-code-object-v3" }