WholeProgramDevirt: Create bitcast to i8* at each virtual call site.

[pcc]

Summary

We can't reuse the llvm.assume instruction's bitcast because it may not
dominate every user of the vtable pointer.

llvm/trunk/lib/Transforms/IPO/WholeProgramDevirt.cpp

Constant *DevirtModule::importGlobal(VTableSlot Slot, ArrayRef<uint64_t> Args,
   return GV;
 }
 
 void DevirtModule::applyUniqueRetValOpt(CallSiteInfo &CSInfo, StringRef FnName,
                                         bool IsOne,
                                         Constant *UniqueMemberAddr) {
   for (auto &&Call : CSInfo.CallSites) {
     IRBuilder<> B(Call.CS.getInstruction());
-    Value *Cmp = B.CreateICmp(IsOne ? ICmpInst::ICMP_EQ : ICmpInst::ICMP_NE,
-                              Call.VTable, UniqueMemberAddr);
+    Value *Cmp =
+        B.CreateICmp(IsOne ? ICmpInst::ICMP_EQ : ICmpInst::ICMP_NE,
+                     B.CreateBitCast(Call.VTable, Int8PtrTy), UniqueMemberAddr);
     Cmp = B.CreateZExt(Cmp, Call.CS->getType());
     Call.replaceAndErase("unique-ret-val", FnName, RemarksEnabled, OREGetter,
                          Cmp);
   }
   CSInfo.markDevirt();
 }
 
 bool DevirtModule::tryUniqueRetValOpt(
bool DevirtModule::tryUniqueRetValOpt(
   return false;
 }
 
 void DevirtModule::applyVirtualConstProp(CallSiteInfo &CSInfo, StringRef FnName,
                                          Constant *Byte, Constant *Bit) {
   for (auto Call : CSInfo.CallSites) {
     auto *RetType = cast<IntegerType>(Call.CS.getType());
     IRBuilder<> B(Call.CS.getInstruction());
-    Value *Addr = B.CreateGEP(Int8Ty, Call.VTable, Byte);
+    Value *Addr =
+        B.CreateGEP(Int8Ty, B.CreateBitCast(Call.VTable, Int8PtrTy), Byte);
     if (RetType->getBitWidth() == 1) {
       Value *Bits = B.CreateLoad(Addr);
       Value *BitsAndBit = B.CreateAnd(Bits, Bit);
       auto IsBitSet = B.CreateICmpNE(BitsAndBit, ConstantInt::get(Int8Ty, 0));
       Call.replaceAndErase("virtual-const-prop-1-bit", FnName, RemarksEnabled,
                            OREGetter, IsBitSet);
     } else {
       Value *ValAddr = B.CreateBitCast(Addr, RetType->getPointerTo());
for (auto I = TypeTestFunc->use_begin(), E = TypeTestFunc->use_end();
     // the vtable pointer before, as it may have been CSE'd with pointers from
     // other call sites, and we don't want to process call sites multiple times.
     if (!Assumes.empty()) {
       Metadata *TypeId =
           cast<MetadataAsValue>(CI->getArgOperand(1))->getMetadata();
       Value *Ptr = CI->getArgOperand(0)->stripPointerCasts();
       if (SeenPtrs.insert(Ptr).second) {
         for (DevirtCallSite Call : DevirtCalls) {
-          CallSlots[{TypeId, Call.Offset}].addCallSite(CI->getArgOperand(0),
-                                                       Call.CS, nullptr);
+          CallSlots[{TypeId, Call.Offset}].addCallSite(Ptr, Call.CS, nullptr);
         }
       }
     }
 
     // We no longer need the assumes or the type test.
     for (auto Assume : Assumes)
       Assume->eraseFromParent();
     // We can't use RecursivelyDeleteTriviallyDeadInstructions here because we

llvm/trunk/test/Transforms/WholeProgramDevirt/import-no-dominating-assume.ll

+; RUN: opt -S -wholeprogramdevirt -wholeprogramdevirt-summary-action=import -wholeprogramdevirt-read-summary=%S/Inputs/import-vcp.yaml < %s | FileCheck %s
+
+target datalayout = "e-p:64:64"
+target triple = "x86_64-unknown-linux-gnu"
+
+define i32 @call1(i1 %a, i8* %obj) {
+  %vtableptr = bitcast i8* %obj to [3 x i8*]**
+  %vtable = load [3 x i8*]*, [3 x i8*]** %vtableptr
+  br i1 %a, label %bb1, label %bb2
+
+bb1:
+  ; CHECK: {{.*}} = bitcast {{.*}} to i8*
+  %vtablei8_1 = bitcast [3 x i8*]* %vtable to i8*
+  %p1 = call i1 @llvm.type.test(i8* %vtablei8_1, metadata !"typeid1")
+  call void @llvm.assume(i1 %p1)
+  %fptrptr1 = getelementptr [3 x i8*], [3 x i8*]* %vtable, i32 0, i32 0
+  %fptr1 = load i8*, i8** %fptrptr1
+  %fptr1_casted = bitcast i8* %fptr1 to i32 (i8*, i32)*
+  ; CHECK: {{.*}} = bitcast {{.*}} to i8*
+  %result1 = call i32 %fptr1_casted(i8* %obj, i32 1)
+  br label %bb2
+
+  ; CHECK: :
+bb2:
+  %vtablei8_2 = bitcast [3 x i8*]* %vtable to i8*
+  %p = call i1 @llvm.type.test(i8* %vtablei8_2, metadata !"typeid1")
+  call void @llvm.assume(i1 %p)
+  %fptrptr2 = getelementptr [3 x i8*], [3 x i8*]* %vtable, i32 0, i32 0
+  %fptr2 = load i8*, i8** %fptrptr2
+  %fptr2_casted = bitcast i8* %fptr2 to i32 (i8*, i32)*
+  ; CHECK: {{.*}} = bitcast {{.*}} to i8*
+  %result2 = call i32 %fptr2_casted(i8* %obj, i32 1)
+  ret i32 %result2
+}
+
+declare void @llvm.assume(i1)
+declare i1 @llvm.type.test(i8*, metadata)

llvm/trunk/test/Transforms/WholeProgramDevirt/import.ll

define i32 @call1(i8* %obj) {
   %p = call i1 @llvm.type.test(i8* %vtablei8, metadata !"typeid1")
   call void @llvm.assume(i1 %p)
   %fptrptr = getelementptr [3 x i8*], [3 x i8*]* %vtable, i32 0, i32 0
   %fptr = load i8*, i8** %fptrptr
   %fptr_casted = bitcast i8* %fptr to i32 (i8*, i32)*
   ; SINGLE-IMPL: call i32 bitcast (void ()* @singleimpl1 to i32 (i8*, i32)*)
   %result = call i32 %fptr_casted(i8* %obj, i32 1)
   ; UNIFORM-RET-VAL: ret i32 42
+  ; VCP: {{.*}} = bitcast {{.*}} to i8*
   ; VCP: [[VT1:%.*]] = bitcast {{.*}} to i8*
   ; VCP: [[GEP1:%.*]] = getelementptr i8, i8* [[VT1]], i32 ptrtoint (i8* @__typeid_typeid1_0_1_byte to i32)
   ; VCP: [[BC1:%.*]] = bitcast i8* [[GEP1]] to i32*
   ; VCP: [[LOAD1:%.*]] = load i32, i32* [[BC1]]
   ; VCP: ret i32 [[LOAD1]]
   ret i32 %result
 }
 

llvm/trunk/test/Transforms/WholeProgramDevirt/unique-retval.ll

 define i1 @vf1(i8* %this) readnone {
   ret i1 1
 }
 
 ; CHECK: define i1 @call1
 define i1 @call1(i8* %obj) {
   %vtableptr = bitcast i8* %obj to [1 x i8*]**
   %vtable = load [1 x i8*]*, [1 x i8*]** %vtableptr
+  ; CHECK: {{.*}} = bitcast [1 x i8*]* {{.*}} to i8*
   ; CHECK: [[VT1:%[^ ]*]] = bitcast [1 x i8*]* {{.*}} to i8*
   %vtablei8 = bitcast [1 x i8*]* %vtable to i8*
   %p = call i1 @llvm.type.test(i8* %vtablei8, metadata !"typeid1")
   call void @llvm.assume(i1 %p)
   %fptrptr = getelementptr [1 x i8*], [1 x i8*]* %vtable, i32 0, i32 0
   %fptr = load i8*, i8** %fptrptr
   %fptr_casted = bitcast i8* %fptr to i1 (i8*)*
   ; CHECK: [[RES1:%[^ ]*]] = icmp eq i8* [[VT1]], bitcast ([1 x i8*]* @vt3 to i8*)

llvm/trunk/test/Transforms/WholeProgramDevirt/virtual-const-prop-begin.ll

 define i32 @vf4i32(i8* %this) readnone {
   ret i32 4
 }
 
 ; CHECK: define i1 @call1(
 define i1 @call1(i8* %obj) {
   %vtableptr = bitcast i8* %obj to [3 x i8*]**
   %vtable = load [3 x i8*]*, [3 x i8*]** %vtableptr
+  ; CHECK: {{.*}} = bitcast [3 x i8*]* {{.*}} to i8*
   ; CHECK: [[VT1:%[^ ]*]] = bitcast [3 x i8*]* {{.*}} to i8*
   %vtablei8 = bitcast [3 x i8*]* %vtable to i8*
   %p = call i1 @llvm.type.test(i8* %vtablei8, metadata !"typeid")
   call void @llvm.assume(i1 %p)
   %fptrptr = getelementptr [3 x i8*], [3 x i8*]* %vtable, i32 0, i32 0
   %fptr = load i8*, i8** %fptrptr
   %fptr_casted = bitcast i8* %fptr to i1 (i8*)*
   ; CHECK: [[VTGEP1:%[^ ]*]] = getelementptr i8, i8* [[VT1]], i32 -5
   ; CHECK: [[VTLOAD1:%[^ ]*]] = load i8, i8* [[VTGEP1]]
   ; CHECK: [[VTAND1:%[^ ]*]] = and i8 [[VTLOAD1]], 2
   ; CHECK: [[VTCMP1:%[^ ]*]] = icmp ne i8 [[VTAND1]], 0
   %result = call i1 %fptr_casted(i8* %obj)
   ; CHECK: ret i1 [[VTCMP1]]
   ret i1 %result
 }
 
 ; CHECK: define i1 @call2(
 define i1 @call2(i8* %obj) {
   %vtableptr = bitcast i8* %obj to [3 x i8*]**
   %vtable = load [3 x i8*]*, [3 x i8*]** %vtableptr
+  ; CHECK: {{.*}} = bitcast [3 x i8*]* {{.*}} to i8*
   ; CHECK: [[VT2:%[^ ]*]] = bitcast [3 x i8*]* {{.*}} to i8*
   %vtablei8 = bitcast [3 x i8*]* %vtable to i8*
   %p = call i1 @llvm.type.test(i8* %vtablei8, metadata !"typeid")
   call void @llvm.assume(i1 %p)
   %fptrptr = getelementptr [3 x i8*], [3 x i8*]* %vtable, i32 0, i32 1
   %fptr = load i8*, i8** %fptrptr
   %fptr_casted = bitcast i8* %fptr to i1 (i8*)*
   ; CHECK: [[VTGEP2:%[^ ]*]] = getelementptr i8, i8* [[VT2]], i32 -5
   ; CHECK: [[VTLOAD2:%[^ ]*]] = load i8, i8* [[VTGEP2]]
   ; CHECK: [[VTAND2:%[^ ]*]] = and i8 [[VTLOAD2]], 1
   ; CHECK: [[VTCMP2:%[^ ]*]] = icmp ne i8 [[VTAND2]], 0
   %result = call i1 %fptr_casted(i8* %obj)
   ; CHECK: ret i1 [[VTCMP2]]
   ret i1 %result
 }
 
 ; CHECK: define i32 @call3(
 define i32 @call3(i8* %obj) {
   %vtableptr = bitcast i8* %obj to [3 x i8*]**
   %vtable = load [3 x i8*]*, [3 x i8*]** %vtableptr
+  ; CHECK: {{.*}} = bitcast [3 x i8*]* {{.*}} to i8*
   ; CHECK: [[VT3:%[^ ]*]] = bitcast [3 x i8*]* {{.*}} to i8*
   %vtablei8 = bitcast [3 x i8*]* %vtable to i8*
   %p = call i1 @llvm.type.test(i8* %vtablei8, metadata !"typeid")
   call void @llvm.assume(i1 %p)
   %fptrptr = getelementptr [3 x i8*], [3 x i8*]* %vtable, i32 0, i32 2
   %fptr = load i8*, i8** %fptrptr
   %fptr_casted = bitcast i8* %fptr to i32 (i8*)*
   ; CHECK: [[VTGEP3:%[^ ]*]] = getelementptr i8, i8* [[VT3]], i32 -4

llvm/trunk/test/Transforms/WholeProgramDevirt/virtual-const-prop-end.ll

 define i32 @vf4i32(i8* %this) readnone {
   ret i32 4
 }
 
 ; CHECK: define i1 @call1(
 define i1 @call1(i8* %obj) {
   %vtableptr = bitcast i8* %obj to [3 x i8*]**
   %vtable = load [3 x i8*]*, [3 x i8*]** %vtableptr
+  ; CHECK: {{.*}} = bitcast [3 x i8*]* {{.*}} to i8*
   ; CHECK: [[VT1:%[^ ]*]] = bitcast [3 x i8*]* {{.*}} to i8*
   %vtablei8 = bitcast [3 x i8*]* %vtable to i8*
   %p = call i1 @llvm.type.test(i8* %vtablei8, metadata !"typeid")
   call void @llvm.assume(i1 %p)
   %fptrptr = getelementptr [3 x i8*], [3 x i8*]* %vtable, i32 0, i32 0
   %fptr = load i8*, i8** %fptrptr
   %fptr_casted = bitcast i8* %fptr to i1 (i8*)*
   ; CHECK: [[VTGEP1:%[^ ]*]] = getelementptr i8, i8* [[VT1]], i32 28
   ; CHECK: [[VTLOAD1:%[^ ]*]] = load i8, i8* [[VTGEP1]]
   ; CHECK: [[VTAND1:%[^ ]*]] = and i8 [[VTLOAD1]], 2
   ; CHECK: [[VTCMP1:%[^ ]*]] = icmp ne i8 [[VTAND1]], 0
   %result = call i1 %fptr_casted(i8* %obj)
   ; CHECK: ret i1 [[VTCMP1]]
   ret i1 %result
 }
 
 ; CHECK: define i1 @call2(
 define i1 @call2(i8* %obj) {
   %vtableptr = bitcast i8* %obj to [3 x i8*]**
   %vtable = load [3 x i8*]*, [3 x i8*]** %vtableptr
+  ; CHECK: {{.*}} = bitcast [3 x i8*]* {{.*}} to i8*
   ; CHECK: [[VT2:%[^ ]*]] = bitcast [3 x i8*]* {{.*}} to i8*
   %vtablei8 = bitcast [3 x i8*]* %vtable to i8*
   %p = call i1 @llvm.type.test(i8* %vtablei8, metadata !"typeid")
   call void @llvm.assume(i1 %p)
   %fptrptr = getelementptr [3 x i8*], [3 x i8*]* %vtable, i32 0, i32 1
   %fptr = load i8*, i8** %fptrptr
   %fptr_casted = bitcast i8* %fptr to i1 (i8*)*
   ; CHECK: [[VTGEP2:%[^ ]*]] = getelementptr i8, i8* [[VT2]], i32 28
   ; CHECK: [[VTLOAD2:%[^ ]*]] = load i8, i8* [[VTGEP2]]
   ; CHECK: [[VTAND2:%[^ ]*]] = and i8 [[VTLOAD2]], 1
   ; CHECK: [[VTCMP2:%[^ ]*]] = icmp ne i8 [[VTAND2]], 0
   %result = call i1 %fptr_casted(i8* %obj)
   ; CHECK: ret i1 [[VTCMP2]]
   ret i1 %result
 }
 
 ; CHECK: define i32 @call3(
 define i32 @call3(i8* %obj) {
   %vtableptr = bitcast i8* %obj to [3 x i8*]**
   %vtable = load [3 x i8*]*, [3 x i8*]** %vtableptr
+  ; CHECK: {{.*}} = bitcast [3 x i8*]* {{.*}} to i8*
   ; CHECK: [[VT3:%[^ ]*]] = bitcast [3 x i8*]* {{.*}} to i8*
   %vtablei8 = bitcast [3 x i8*]* %vtable to i8*
   %p = call i1 @llvm.type.test(i8* %vtablei8, metadata !"typeid")
   call void @llvm.assume(i1 %p)
   %fptrptr = getelementptr [3 x i8*], [3 x i8*]* %vtable, i32 0, i32 2
   %fptr = load i8*, i8** %fptrptr
   %fptr_casted = bitcast i8* %fptr to i32 (i8*)*
   ; CHECK: [[VTGEP3:%[^ ]*]] = getelementptr i8, i8* [[VT3]], i32 24