replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[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
This commit is contained in:
Stanislav Mekhanoshin 2017-03-28 18:23:24 +00:00
parent 486369fc1a
commit 9053f22eeb
2 changed files with 14 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
View File

@ -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(

2
llvm/test/CodeGen/AMDGPU/early-inline.ll
View File

@ -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: