Revert "R600: Make sure to inline all internal functions"

This reverts commit r220996.

It introduced layering violations causing link errors in many
configurations.

llvm-svn: 221020

llvm/lib/Target/R600/AMDGPU.h

@@ -57,7 +57,6 @@ extern char &SILoadStoreOptimizerID;
 FunctionPass *createAMDGPUPromoteAlloca(const AMDGPUSubtarget &ST);
 Pass *createAMDGPUStructurizeCFGPass();
 FunctionPass *createAMDGPUISelDag(TargetMachine &tm);
-ModulePass *createAMDGPUAlwaysInlinePass();
 
 /// \brief Creates an AMDGPU-specific Target Transformation Info pass.
 ImmutablePass *

llvm/lib/Target/R600/AMDGPUAlwaysInlinePass.cpp

@@ -1,66 +0,0 @@
-//===-- AMDGPUAlwaysInlinePass.cpp - Promote Allocas ----------------------===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-//
-/// \file
-/// This pass marks all internal functions as always_inline and creates
-/// duplicates of all other functions a marks the duplicates as always_inline.
-//
-//===----------------------------------------------------------------------===//
-
-#include "AMDGPU.h"
-#include "llvm/IR/Module.h"
-#include "llvm/Transforms/Utils/Cloning.h"
-
-using namespace llvm;
-
-namespace {
-
-class AMDGPUAlwaysInline : public ModulePass {
-
-  static char ID;
-
-public:
-  AMDGPUAlwaysInline() : ModulePass(ID) { }
-  bool runOnModule(Module &M) override;
-  const char *getPassName() const override { return "AMDGPU Always Inline Pass"; }
-};
-
-} // End anonymous namespace
-
-char AMDGPUAlwaysInline::ID = 0;
-
-bool AMDGPUAlwaysInline::runOnModule(Module &M) {
-
-  std::vector<Function*> FuncsToClone;
-  for (Module::iterator I = M.begin(), E = M.end(); I != E; ++I) {
-    Function &F = *I;
-    if (!F.hasLocalLinkage() && !F.isDeclaration() && !F.use_empty())
-      FuncsToClone.push_back(&F);
-  }
-
-  for (Function *F : FuncsToClone) {
-    ValueToValueMapTy VMap;
-    Function *NewFunc = CloneFunction(F, VMap, false);
-    NewFunc->setLinkage(GlobalValue::InternalLinkage);
-    F->getParent()->getFunctionList().push_back(NewFunc);
-    F->replaceAllUsesWith(NewFunc);
-  }
-
-  for (Module::iterator I = M.begin(), E = M.end(); I != E; ++I) {
-    Function &F = *I;
-    if (F.hasLocalLinkage()) {
-      F.addFnAttr(Attribute::AlwaysInline);
-    }
-  }
-  return false;
-}
-
-ModulePass *llvm::createAMDGPUAlwaysInlinePass() {
-  return new AMDGPUAlwaysInline();
-}

llvm/lib/Target/R600/AMDGPUTargetMachine.cpp

@@ -80,7 +80,6 @@ public:
     return nullptr;
   }
 
-  void addIRPasses() override;
   void addCodeGenPrepare() override;
   bool addPreISel() override;
   bool addInstSelector() override;
@@ -107,19 +106,6 @@ void AMDGPUTargetMachine::addAnalysisPasses(PassManagerBase &PM) {
   PM.add(createAMDGPUTargetTransformInfoPass(this));
 }
 
-void AMDGPUPassConfig::addIRPasses() {
-  // Function calls are not supported, so make sure we inline everything.
-  addPass(createAMDGPUAlwaysInlinePass());
-  addPass(createAlwaysInlinerPass());
-  // We need to add the barrier noop pass, otherwise adding the function
-  // inlining pass will cause all of the PassConfigs passes to be run
-  // one function at a time, which means if we have a nodule with two
-  // functions, then we will generate code for the first function
-  // without ever running any passes on the second.
-  addPass(createBarrierNoopPass());
-  TargetPassConfig::addIRPasses();
-}
-
 void AMDGPUPassConfig::addCodeGenPrepare() {
   const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>();
   if (ST.isPromoteAllocaEnabled()) {

llvm/test/CodeGen/R600/call.ll

@@ -1,7 +1,7 @@
 ; RUN: not llc -march=r600 -mcpu=SI -verify-machineinstrs< %s 2>&1 | FileCheck %s
 ; RUN: not llc -march=r600 -mcpu=cypress < %s 2>&1 | FileCheck %s
 
-; CHECK: error: unsupported call to function external_function in test_call_external
+; CHECK: error: unsupported call to function defined_function in test_call
 
 
 declare i32 @external_function(i32) nounwind

llvm/test/CodeGen/R600/inline-calls.ll

@@ -1,24 +0,0 @@
-; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck  %s
-; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck %s
-
-; CHECK-NOT: {{^}}func:
-define internal fastcc i32 @func(i32 %a) {
-entry:
-  %tmp0 = add i32 %a, 1
-  ret i32 %tmp0
-}
-
-; CHECK: {{^}}kernel:
-define void @kernel(i32 addrspace(1)* %out) {
-entry:
-  %tmp0 = call i32 @func(i32 1)
-  store i32 %tmp0, i32 addrspace(1)* %out
-  ret void
-}
-
-; CHECK: {{^}}kernel2:
-define void @kernel2(i32 addrspace(1)* %out) {
-entry:
-  call void @kernel(i32 addrspace(1)* %out)
-  ret void
-}