[NewPM][AMDGPU] Run InternalizePass when -amdgpu-internalize-symbols

[aeubanks]

Summary

The legacy PM doesn't run EP_ModuleOptimizerEarly on -O0, so skip
running it here when given O0.

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

 #include "llvm/Pass.h"
 #include "llvm/Passes/PassBuilder.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Target/TargetLoweringObjectFile.h"
 #include "llvm/Transforms/IPO.h"
 #include "llvm/Transforms/IPO/AlwaysInliner.h"
+#include "llvm/Transforms/IPO/GlobalDCE.h"
+#include "llvm/Transforms/IPO/Internalize.h"
 #include "llvm/Transforms/IPO/PassManagerBuilder.h"
 #include "llvm/Transforms/Scalar.h"
 #include "llvm/Transforms/Scalar/GVN.h"
 #include "llvm/Transforms/Scalar/InferAddressSpaces.h"
 #include "llvm/Transforms/Utils.h"
 #include "llvm/Transforms/Utils/SimplifyLibCalls.h"
 #include "llvm/Transforms/Vectorize.h"
 #include <memory>
PB.registerPipelineStartEPCallback([DebugPassManager](
                                          PassBuilder::OptimizationLevel Level) {
     FunctionPassManager FPM(DebugPassManager);
     FPM.addPass(AMDGPUUseNativeCallsPass());
     if (EnableLibCallSimplify && Level != PassBuilder::OptimizationLevel::O0)
       FPM.addPass(AMDGPUSimplifyLibCallsPass());
     PM.addPass(createModuleToFunctionPassAdaptor(std::move(FPM)));
   });
 
+  PB.registerPipelineEarlySimplificationEPCallback(
+      [](ModulePassManager &PM, PassBuilder::OptimizationLevel Level) {
+        if (Level == PassBuilder::OptimizationLevel::O0)
+          return;
+
+        if (InternalizeSymbols) {
+          PM.addPass(InternalizePass(mustPreserveGV));
+          PM.addPass(GlobalDCEPass());
+        }
+      });
+
   PB.registerCGSCCOptimizerLateEPCallback(
       [this, DebugPassManager](CGSCCPassManager &PM,
                                PassBuilder::OptimizationLevel Level) {
           FunctionPassManager FPM(DebugPassManager);
 
           // Add infer address spaces pass to the opt pipeline after inlining
           // but before SROA to increase SROA opportunities.
           FPM.addPass(InferAddressSpacesPass());

llvm/test/CodeGen/AMDGPU/internalize.ll

-; RUN: opt -O1 -S -mtriple=amdgcn-unknown-amdhsa -amdgpu-internalize-symbols < %s | FileCheck -check-prefix=ALL -check-prefix=OPT %s
 ; RUN: opt -O0 -S -mtriple=amdgcn-unknown-amdhsa -amdgpu-internalize-symbols < %s | FileCheck -check-prefix=ALL -check-prefix=OPTNONE %s
+; RUN: opt -passes='default<O0>' -S -mtriple=amdgcn-unknown-amdhsa -amdgpu-internalize-symbols < %s | FileCheck -check-prefix=ALL -check-prefix=OPTNONE %s
+; RUN: opt -O1 -S -mtriple=amdgcn-unknown-amdhsa -amdgpu-internalize-symbols < %s | FileCheck -check-prefix=ALL -check-prefix=OPT %s
+; RUN: opt -passes='default<O1>' -S -mtriple=amdgcn-unknown-amdhsa -amdgpu-internalize-symbols < %s | FileCheck -check-prefix=ALL -check-prefix=OPT %s
 
 ; OPT-NOT: gvar_unused
 ; OPTNONE: gvar_unused
 @gvar_unused = addrspace(1) global i32 undef, align 4
 
 ; ALL: gvar_used
 @gvar_used = addrspace(1) global i32 undef, align 4