AMDGPU: Erase llvm.global_ctors/global_dtors after lowering

[arsenm]

Summary

We should be able to run the pass multiple times without breaking
anything. If we still need to track these for some reason, we could
replace with new entries for the kernels.

[python3kgae]

The change looks good.

Need to update the patch so per-merge checks could run.
It complains "The patch may not apply if it includes only the most recent of multiple local commits." now.

[sameerds]

llvm/test/CodeGen/AMDGPU/lower-ctor-dtor.ll

6

Using "CHECK-" as a prefix for a custom check prefix is a bit confusing. Why not just use something clearly distinct, like "ISA"?

[sameerds]

LGTM, other than the optional nit.

[arsenm]

9cc0779c4e2378e3121968078f09dde14288459d

llvm/lib/Target/AMDGPU/AMDGPUCtorDtorLowering.cpp

static bool createInitOrFiniKernel(Module &M, StringRef GlobalName,
   FunctionType *ConstructorTy = InitOrFiniKernel->getFunctionType();
 
   for (Value *V : GA->operands()) {
     auto *CS = cast<ConstantStruct>(V);
     IRB.CreateCall(ConstructorTy, CS->getOperand(1));
   }
 
   appendToUsed(M, {InitOrFiniKernel});
+
+  GV->eraseFromParent();
   return true;
 }
 
 static bool lowerCtorsAndDtors(Module &M) {
   bool Modified = false;
   Modified |= createInitOrFiniKernel(M, "llvm.global_ctors", /*IsCtor =*/true);
   Modified |= createInitOrFiniKernel(M, "llvm.global_dtors", /*IsCtor =*/false);
   return Modified;

llvm/test/CodeGen/AMDGPU/lower-ctor-dtor.ll

-; RUN: opt -S -mtriple=amdgcn--  -amdgpu-lower-ctor-dtor < %s | FileCheck %s
-; RUN: opt -S -mtriple=amdgcn--  -passes=amdgpu-lower-ctor-dtor < %s | FileCheck %s
+; RUN: opt -S -mtriple=amdgcn-- -amdgpu-lower-ctor-dtor < %s | FileCheck %s
+; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-ctor-dtor < %s | FileCheck %s
+
+; Make sure we get the same result if we run multiple times
+; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-ctor-dtor,amdgpu-lower-ctor-dtor < %s | FileCheck %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -filetype=obj -o - < %s | llvm-readelf -s - 2>&1 | FileCheck %s -check-prefix=CHECK-VIS
 
 @llvm.global_ctors = appending addrspace(1) global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 1, void ()* @foo, i8* null }]
 @llvm.global_dtors = appending addrspace(1) global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 1, void ()* @bar, i8* null }]
 
+; CHECK-NOT: @llvm.global_ctors
+; CHECK-NOT: @llvm.global_dtors
+
 ; CHECK-LABEL: amdgpu_kernel void @amdgcn.device.init() #0
 ; CHECK-NEXT: call void @foo
+; CHECK-NEXT: ret void
 
 ; CHECK-LABEL: amdgpu_kernel void @amdgcn.device.fini() #1
 ; CHECK-NEXT: call void @bar
+; CHECK-NEXT: ret void
+
+; CHECK-NOT: amdgcn.device.
 
 ; CHECK-VIS: FUNC   GLOBAL PROTECTED {{.*}} amdgcn.device.init
 ; CHECK-VIS: OBJECT GLOBAL DEFAULT {{.*}} amdgcn.device.init.kd
 ; CHECK-VIS: FUNC   GLOBAL PROTECTED {{.*}} amdgcn.device.fini
 ; CHECK-VIS: OBJECT   GLOBAL DEFAULT {{.*}} amdgcn.device.fini.kd
 
 define internal void @foo() {
   ret void
 }
 
 define internal void @bar() {
   ret void
 }
 
 ; CHECK: attributes #0 = { "device-init" }
 ; CHECK: attributes #1 = { "device-fini" }