[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

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298935 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index e8954c59479822d3a5cee8a5123b7647c31ca266..c5302f7942fc6c7718f2533b97bd9e26acdc2216 100644 (file)
--- a/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/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/test/CodeGen/AMDGPU/early-inline.ll b/test/CodeGen/AMDGPU/early-inline.ll
index 8395ad818abe4e258ead7ab74af3b7e70f4b10be..8d1d7642d5f2b7009e163c4fa1c342d8050f41fd 100644 (file)
--- a/test/CodeGen/AMDGPU/early-inline.ll
+++ b/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: