diff options
| author | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-03-28 18:23:24 +0000 |
|---|---|---|
| committer | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-03-28 18:23:24 +0000 |
| commit | 9053f22eeb3ab0f1f0089e4e6b98093891d361bb (patch) | |
| tree | 11c61ba61147e3ae0804a088d1dd27f88b7ef980 | |
| parent | 486369fc1ada0559dbcd751a53d49c6e929b43e7 (diff) | |
| download | bcm5719-llvm-9053f22eeb3ab0f1f0089e4e6b98093891d361bb.tar.gz bcm5719-llvm-9053f22eeb3ab0f1f0089e4e6b98093891d361bb.zip | |
[AMDGPU] Split -amdgpu-early-inline-all option
Previously it was covered by the internalization. It turns out we cannot
run internalizer in FE, it break separate compilation tests. Thus early
inliner gets its own option.
Differential Revision: https://reviews.llvm.org/D31429
llvm-svn: 298935
| -rw-r--r-- | llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp | 16 | ||||
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/early-inline.ll | 2 |
2 files changed, 14 insertions, 4 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp index e8954c59479..c5302f7942f 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp @@ -95,6 +95,13 @@ static cl::opt<bool> InternalizeSymbols( cl::init(false), cl::Hidden); +// Option to inline all early. +static cl::opt<bool> EarlyInlineAll( + "amdgpu-early-inline-all", + cl::desc("Inline all functions early"), + cl::init(false), + cl::Hidden); + static cl::opt<bool> EnableSDWAPeephole( "amdgpu-sdwa-peephole", cl::desc("Enable SDWA peepholer"), @@ -273,12 +280,14 @@ void AMDGPUTargetMachine::adjustPassManager(PassManagerBuilder &Builder) { bool Internalize = InternalizeSymbols && (getOptLevel() > CodeGenOpt::None) && (getTargetTriple().getArch() == Triple::amdgcn); + bool EarlyInline = EarlyInlineAll && + (getOptLevel() > CodeGenOpt::None); bool AMDGPUAA = EnableAMDGPUAliasAnalysis && getOptLevel() > CodeGenOpt::None; Builder.addExtension( PassManagerBuilder::EP_ModuleOptimizerEarly, - [Internalize, AMDGPUAA](const PassManagerBuilder &, - legacy::PassManagerBase &PM) { + [Internalize, EarlyInline, AMDGPUAA](const PassManagerBuilder &, + legacy::PassManagerBase &PM) { if (AMDGPUAA) { PM.add(createAMDGPUAAWrapperPass()); PM.add(createAMDGPUExternalAAWrapperPass()); @@ -304,8 +313,9 @@ void AMDGPUTargetMachine::adjustPassManager(PassManagerBuilder &Builder) { return !GV.use_empty(); })); PM.add(createGlobalDCEPass()); - PM.add(createAMDGPUAlwaysInlinePass()); } + if (EarlyInline) + PM.add(createAMDGPUAlwaysInlinePass()); }); Builder.addExtension( diff --git a/llvm/test/CodeGen/AMDGPU/early-inline.ll b/llvm/test/CodeGen/AMDGPU/early-inline.ll index 8395ad818ab..8d1d7642d5f 100644 --- a/llvm/test/CodeGen/AMDGPU/early-inline.ll +++ b/llvm/test/CodeGen/AMDGPU/early-inline.ll @@ -1,4 +1,4 @@ -; RUN: opt -mtriple=amdgcn-- -O1 -S -inline-threshold=1 -amdgpu-internalize-symbols %s | FileCheck %s +; RUN: opt -mtriple=amdgcn-- -O1 -S -inline-threshold=1 -amdgpu-early-inline-all %s | FileCheck %s define i32 @callee(i32 %x) { entry: |
