[ArgumentPromotion] Fix byval alignment handling.

[efriedma]

Summary

Make sure the alignment of the generated operations matches the alignment of the byval argument. Previously, we were just ignoring alignment and getting lucky.

While I'm here, also delete the unnecessary "tail" handling. Passing a pointer to a byval argument to a "tail" call is UB, so rewriting to an alloca doesn't require any special handling.

[fhahn]

LGTM, thanks!

It looks like all relevant tests have been updated to add parameter alignment. Could you also add a test without alignment and check that it is not transformed? (or perhaps such a test already exists)

[fhahn]

reverse ping :)

@efriedma are you still planning on landing this change?

[efriedma]

Sorry, forgot about this; I'll fix up the test and land it now.

llvm/lib/Transforms/IPO/ArgumentPromotion.cpp

doPromotion(Function *F, SmallPtrSetImpl<Argument *> &ArgsToPromote,
 
   F->getParent()->getFunctionList().insert(F->getIterator(), NF);
   NF->takeName(F);
 
   // Loop over all of the callers of the function, transforming the call sites
   // to pass in the loaded pointers.
   //
   SmallVector<Value *, 16> Args;
+  const DataLayout &DL = F->getParent()->getDataLayout();
   while (!F->use_empty()) {
     CallBase &CB = cast<CallBase>(*F->user_back());
     assert(CB.getCalledFunction() == F);
     const AttributeList &CallPAL = CB.getAttributes();
     IRBuilder<NoFolder> IRB(&CB);
 
     // Loop over the operands, inserting GEP and loads in the caller as
     // appropriate.
     auto AI = CB.arg_begin();
     ArgNo = 0;
     for (Function::arg_iterator I = F->arg_begin(), E = F->arg_end(); I != E;
          ++I, ++AI, ++ArgNo)
       if (!ArgsToPromote.count(&*I) && !ByValArgsToTransform.count(&*I)) {
         Args.push_back(*AI); // Unmodified argument
         ArgAttrVec.push_back(CallPAL.getParamAttributes(ArgNo));
       } else if (ByValArgsToTransform.count(&*I)) {
         // Emit a GEP and load for each element of the struct.
         Type *AgTy = cast<PointerType>(I->getType())->getElementType();
         StructType *STy = cast<StructType>(AgTy);
         Value *Idxs[2] = {
             ConstantInt::get(Type::getInt32Ty(F->getContext()), 0), nullptr};
+        const StructLayout *SL = DL.getStructLayout(STy);
+        Align StructAlign = *I->getParamAlign();
         for (unsigned i = 0, e = STy->getNumElements(); i != e; ++i) {
           Idxs[1] = ConstantInt::get(Type::getInt32Ty(F->getContext()), i);
           auto *Idx =
               IRB.CreateGEP(STy, *AI, Idxs, (*AI)->getName() + "." + Twine(i));
           // TODO: Tell AA about the new values?
-          Args.push_back(IRB.CreateLoad(STy->getElementType(i), Idx,
-                                        Idx->getName() + ".val"));
+          Align Alignment =
+              commonAlignment(StructAlign, SL->getElementOffset(i));
+          Args.push_back(IRB.CreateAlignedLoad(
+              STy->getElementType(i), Idx, Alignment, Idx->getName() + ".val"));
           ArgAttrVec.push_back(AttributeSet());
         }
       } else if (!I->use_empty()) {
         // Non-dead argument: insert GEPs and loads as appropriate.
         ScalarizeTable &ArgIndices = ScalarizedElements[&*I];
         // Store the Value* version of the indices in here, but declare it now
         // for reuse.
         std::vector<Value *> Ops;
if (!CB.use_empty()) {
       NewCS->takeName(&CB);
     }
 
     // Finally, remove the old call from the program, reducing the use-count of
     // F.
     CB.eraseFromParent();
   }
 
-  const DataLayout &DL = F->getParent()->getDataLayout();
-
   // Since we have now created the new function, splice the body of the old
   // function right into the new function, leaving the old rotting hulk of the
   // function empty.
   NF->getBasicBlockList().splice(NF->begin(), F->getBasicBlockList());
 
   // Loop over the argument list, transferring uses of the old arguments over to
   // the new arguments, also transferring over the names as well.
   for (Function::arg_iterator I = F->arg_begin(), E = F->arg_end(),
for (Function::arg_iterator I = F->arg_begin(), E = F->arg_end(),
 
     if (ByValArgsToTransform.count(&*I)) {
       // In the callee, we create an alloca, and store each of the new incoming
       // arguments into the alloca.
       Instruction *InsertPt = &NF->begin()->front();
 
       // Just add all the struct element types.
       Type *AgTy = cast<PointerType>(I->getType())->getElementType();
-      Value *TheAlloca = new AllocaInst(
-          AgTy, DL.getAllocaAddrSpace(), nullptr,
-          I->getParamAlign().getValueOr(DL.getPrefTypeAlign(AgTy)), "",
-          InsertPt);
+      Align StructAlign = *I->getParamAlign();
+      Value *TheAlloca = new AllocaInst(AgTy, DL.getAllocaAddrSpace(), nullptr,
+                                        StructAlign, "", InsertPt);
       StructType *STy = cast<StructType>(AgTy);
       Value *Idxs[2] = {ConstantInt::get(Type::getInt32Ty(F->getContext()), 0),
                         nullptr};
+      const StructLayout *SL = DL.getStructLayout(STy);
 
       for (unsigned i = 0, e = STy->getNumElements(); i != e; ++i) {
         Idxs[1] = ConstantInt::get(Type::getInt32Ty(F->getContext()), i);
         Value *Idx = GetElementPtrInst::Create(
             AgTy, TheAlloca, Idxs, TheAlloca->getName() + "." + Twine(i),
             InsertPt);
         I2->setName(I->getName() + "." + Twine(i));
-        new StoreInst(&*I2++, Idx, InsertPt);
+        Align Alignment = commonAlignment(StructAlign, SL->getElementOffset(i));
+        new StoreInst(&*I2++, Idx, false, Alignment, InsertPt);
       }
 
       // Anything that used the arg should now use the alloca.
       I->replaceAllUsesWith(TheAlloca);
       TheAlloca->takeName(&*I);
-
-      // If the alloca is used in a call, we must clear the tail flag since
-      // the callee now uses an alloca from the caller.
-      for (User *U : TheAlloca->users()) {
-        CallInst *Call = dyn_cast<CallInst>(U);
-        if (!Call)
-          continue;
-        Call->setTailCall(false);
-      }
       continue;
     }
 
     // There potentially are metadata uses for things like llvm.dbg.value.
     // Replace them with undef, after handling the other regular uses.
     auto RauwUndefMetadata = make_scope_exit(
         [&]() { I->replaceAllUsesWith(UndefValue::get(I->getType())); });
 
if (PtrArg->hasStructRetAttr()) {
         CB.removeParamAttr(ArgNo, Attribute::StructRet);
         CB.addParamAttr(ArgNo, Attribute::NoAlias);
       }
     }
 
     // If this is a byval argument, and if the aggregate type is small, just
     // pass the elements, which is always safe, if the passed value is densely
     // packed or if we can prove the padding bytes are never accessed.
-    bool isSafeToPromote = PtrArg->hasByValAttr() &&
+    //
+    // Only handle arguments with specified alignment; if it's unspecified, the
+    // actual alignment of the argument is target-specific.
+    bool isSafeToPromote = PtrArg->hasByValAttr() && PtrArg->getParamAlign() &&
                            (ArgumentPromotionPass::isDenselyPacked(AgTy, DL) ||
                             !canPaddingBeAccessed(PtrArg));
     if (isSafeToPromote) {
       if (StructType *STy = dyn_cast<StructType>(AgTy)) {
         if (MaxElements > 0 && STy->getNumElements() > MaxElements) {
           LLVM_DEBUG(dbgs() << "argpromotion disable promoting argument '"
                             << PtrArg->getName()
                             << "' because it would require adding more"

llvm/test/Transforms/ArgumentPromotion/attrs.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --scrub-attributes
 ; RUN: opt < %s -argpromotion -S | FileCheck %s
 ; RUN: opt < %s -passes=argpromotion -S | FileCheck %s
 
 %struct.ss = type { i32, i64 }
 
 ; Don't drop 'byval' on %X here.
-define internal void @f(%struct.ss* byval %b, i32* byval %X, i32 %i) nounwind {
+define internal void @f(%struct.ss* byval(%struct.ss) align 4 %b, i32* byval(i32) align 4 %X, i32 %i) nounwind {
 ; CHECK-LABEL: define {{[^@]+}}@f
-; CHECK-SAME: (i32 [[B_0:%.*]], i64 [[B_1:%.*]], i32* byval [[X:%.*]], i32 [[I:%.*]])
+; CHECK-SAME: (i32 [[B_0:%.*]], i64 [[B_1:%.*]], i32* byval(i32) align 4 [[X:%.*]], i32 [[I:%.*]]) [[ATTR0:#.*]] {
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[B:%.*]] = alloca [[STRUCT_SS:%.*]], align 8
+; CHECK-NEXT:    [[B:%.*]] = alloca [[STRUCT_SS:%.*]], align 4
 ; CHECK-NEXT:    [[DOT0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 0
 ; CHECK-NEXT:    store i32 [[B_0]], i32* [[DOT0]], align 4
 ; CHECK-NEXT:    [[DOT1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 1
 ; CHECK-NEXT:    store i64 [[B_1]], i64* [[DOT1]], align 4
 ; CHECK-NEXT:    [[TMP:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[TMP]], align 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[TMP1]], 1
 ; CHECK-NEXT:    store i32 [[TMP2]], i32* [[TMP]], align 4
entry:
 
   store i32 0, i32* %X
   ret void
 }
 
 ; Also make sure we don't drop the call zeroext attribute.
 define i32 @test(i32* %X) {
 ; CHECK-LABEL: define {{[^@]+}}@test
-; CHECK-SAME: (i32* [[X:%.*]])
+; CHECK-SAME: (i32* [[X:%.*]]) {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[S:%.*]] = alloca [[STRUCT_SS:%.*]], align 8
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
 ; CHECK-NEXT:    store i32 1, i32* [[TMP1]], align 8
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
 ; CHECK-NEXT:    store i64 2, i64* [[TMP4]], align 4
 ; CHECK-NEXT:    [[S_0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
 ; CHECK-NEXT:    [[S_0_VAL:%.*]] = load i32, i32* [[S_0]], align 4
 ; CHECK-NEXT:    [[S_1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
 ; CHECK-NEXT:    [[S_1_VAL:%.*]] = load i64, i64* [[S_1]], align 4
-; CHECK-NEXT:    call void @f(i32 [[S_0_VAL]], i64 [[S_1_VAL]], i32* byval [[X]], i32 zeroext 0)
+; CHECK-NEXT:    call void @f(i32 [[S_0_VAL]], i64 [[S_1_VAL]], i32* byval(i32) align 4 [[X]], i32 zeroext 0)
 ; CHECK-NEXT:    ret i32 0
 ;
 entry:
   %S = alloca %struct.ss
   %tmp1 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 0
   store i32 1, i32* %tmp1, align 8
   %tmp4 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 1
   store i64 2, i64* %tmp4, align 4
 
-  call void @f( %struct.ss* byval %S, i32* byval %X, i32 zeroext 0)
+  call void @f( %struct.ss* byval(%struct.ss) align 4 %S, i32* byval(i32) align 4 %X, i32 zeroext 0)
 
   ret i32 0
 }

llvm/test/Transforms/ArgumentPromotion/byval-2.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --scrub-attributes
 ; RUN: opt < %s -argpromotion -S | FileCheck %s
 ; RUN: opt < %s -passes=argpromotion -S | FileCheck %s
 
 ; Arg promotion eliminates the struct argument.
 ; FIXME: We should eliminate the i32* argument.
 
 %struct.ss = type { i32, i64 }
 
-define internal void @f(%struct.ss* byval  %b, i32* byval %X) nounwind  {
+define internal void @f(%struct.ss* byval(%struct.ss) align 8 %b, i32* byval(i32) align 4 %X) nounwind  {
 ; CHECK-LABEL: define {{[^@]+}}@f
-; CHECK-SAME: (i32 [[B_0:%.*]], i64 [[B_1:%.*]], i32* byval [[X:%.*]])
+; CHECK-SAME: (i32 [[B_0:%.*]], i64 [[B_1:%.*]], i32* byval(i32) align 4 [[X:%.*]]) [[ATTR0:#.*]] {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[B:%.*]] = alloca [[STRUCT_SS:%.*]], align 8
 ; CHECK-NEXT:    [[DOT0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 0
-; CHECK-NEXT:    store i32 [[B_0]], i32* [[DOT0]], align 4
+; CHECK-NEXT:    store i32 [[B_0]], i32* [[DOT0]], align 8
 ; CHECK-NEXT:    [[DOT1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 1
 ; CHECK-NEXT:    store i64 [[B_1]], i64* [[DOT1]], align 4
 ; CHECK-NEXT:    [[TMP:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[TMP]], align 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[TMP1]], 1
 ; CHECK-NEXT:    store i32 [[TMP2]], i32* [[TMP]], align 4
 ; CHECK-NEXT:    store i32 0, i32* [[X]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
   %tmp = getelementptr %struct.ss, %struct.ss* %b, i32 0, i32 0
   %tmp1 = load i32, i32* %tmp, align 4
   %tmp2 = add i32 %tmp1, 1
   store i32 %tmp2, i32* %tmp, align 4
 
   store i32 0, i32* %X
   ret void
 }
 
 define i32 @test(i32* %X) {
 ; CHECK-LABEL: define {{[^@]+}}@test
-; CHECK-SAME: (i32* [[X:%.*]])
+; CHECK-SAME: (i32* [[X:%.*]]) {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[S:%.*]] = alloca [[STRUCT_SS:%.*]], align 8
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
 ; CHECK-NEXT:    store i32 1, i32* [[TMP1]], align 8
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
 ; CHECK-NEXT:    store i64 2, i64* [[TMP4]], align 4
 ; CHECK-NEXT:    [[S_0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
-; CHECK-NEXT:    [[S_0_VAL:%.*]] = load i32, i32* [[S_0]], align 4
+; CHECK-NEXT:    [[S_0_VAL:%.*]] = load i32, i32* [[S_0]], align 8
 ; CHECK-NEXT:    [[S_1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
 ; CHECK-NEXT:    [[S_1_VAL:%.*]] = load i64, i64* [[S_1]], align 4
-; CHECK-NEXT:    call void @f(i32 [[S_0_VAL]], i64 [[S_1_VAL]], i32* byval [[X]])
+; CHECK-NEXT:    call void @f(i32 [[S_0_VAL]], i64 [[S_1_VAL]], i32* byval(i32) align 4 [[X]])
 ; CHECK-NEXT:    ret i32 0
 ;
 entry:
-  %S = alloca %struct.ss
+  %S = alloca %struct.ss, align 8
   %tmp1 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 0
   store i32 1, i32* %tmp1, align 8
   %tmp4 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 1
   store i64 2, i64* %tmp4, align 4
-  call void @f( %struct.ss* byval %S, i32* byval %X)
+  call void @f( %struct.ss* byval(%struct.ss) align 8 %S, i32* byval(i32) align 4 %X)
   ret i32 0
 }

llvm/test/Transforms/ArgumentPromotion/byval.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --scrub-attributes
 ; RUN: opt < %s -argpromotion -S | FileCheck %s
 ; RUN: opt < %s -passes=argpromotion -S | FileCheck %s
 
 target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
 
 %struct.ss = type { i32, i64 }
 
-define internal void @f(%struct.ss* byval  %b) nounwind  {
+define internal void @f(%struct.ss* byval(%struct.ss) align 4 %b) nounwind  {
 ; CHECK-LABEL: define {{[^@]+}}@f
-; CHECK-SAME: (i32 [[B_0:%.*]], i64 [[B_1:%.*]])
+; CHECK-SAME: (i32 [[B_0:%.*]], i64 [[B_1:%.*]]) [[ATTR0:#.*]] {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[B:%.*]] = alloca [[STRUCT_SS:%.*]], align 4
 ; CHECK-NEXT:    [[DOT0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 0
 ; CHECK-NEXT:    store i32 [[B_0]], i32* [[DOT0]], align 4
 ; CHECK-NEXT:    [[DOT1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 1
 ; CHECK-NEXT:    store i64 [[B_1]], i64* [[DOT1]], align 4
 ; CHECK-NEXT:    [[TMP:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[TMP]], align 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[TMP1]], 1
 ; CHECK-NEXT:    store i32 [[TMP2]], i32* [[TMP]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
   %tmp = getelementptr %struct.ss, %struct.ss* %b, i32 0, i32 0
   %tmp1 = load i32, i32* %tmp, align 4
   %tmp2 = add i32 %tmp1, 1
   store i32 %tmp2, i32* %tmp, align 4
   ret void
 }
 
 
-define internal void @g(%struct.ss* byval align 32 %b) nounwind {
+define internal void @g(%struct.ss* byval(%struct.ss) align 32 %b) nounwind {
 ; CHECK-LABEL: define {{[^@]+}}@g
-; CHECK-SAME: (i32 [[B_0:%.*]], i64 [[B_1:%.*]])
+; CHECK-SAME: (i32 [[B_0:%.*]], i64 [[B_1:%.*]]) [[ATTR0]] {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[B:%.*]] = alloca [[STRUCT_SS:%.*]], align 32
 ; CHECK-NEXT:    [[DOT0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 0
-; CHECK-NEXT:    store i32 [[B_0]], i32* [[DOT0]], align 4
+; CHECK-NEXT:    store i32 [[B_0]], i32* [[DOT0]], align 32
 ; CHECK-NEXT:    [[DOT1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 1
 ; CHECK-NEXT:    store i64 [[B_1]], i64* [[DOT1]], align 4
 ; CHECK-NEXT:    [[TMP:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[B]], i32 0, i32 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[TMP]], align 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[TMP1]], 1
 ; CHECK-NEXT:    store i32 [[TMP2]], i32* [[TMP]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
   %tmp = getelementptr %struct.ss, %struct.ss* %b, i32 0, i32 0
   %tmp1 = load i32, i32* %tmp, align 4
   %tmp2 = add i32 %tmp1, 1
   store i32 %tmp2, i32* %tmp, align 4
   ret void
 }
 
 
 define i32 @main() nounwind  {
-; CHECK-LABEL: define {{[^@]+}}@main()
+; CHECK-LABEL: define {{[^@]+}}@main
+; CHECK-SAME: () [[ATTR0]] {
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[S:%.*]] = alloca [[STRUCT_SS:%.*]], align 4
+; CHECK-NEXT:    [[S:%.*]] = alloca [[STRUCT_SS:%.*]], align 32
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
 ; CHECK-NEXT:    store i32 1, i32* [[TMP1]], align 8
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
 ; CHECK-NEXT:    store i64 2, i64* [[TMP4]], align 4
 ; CHECK-NEXT:    [[S_0:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
 ; CHECK-NEXT:    [[S_0_VAL:%.*]] = load i32, i32* [[S_0]], align 4
 ; CHECK-NEXT:    [[S_1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
 ; CHECK-NEXT:    [[S_1_VAL:%.*]] = load i64, i64* [[S_1]], align 4
 ; CHECK-NEXT:    call void @f(i32 [[S_0_VAL]], i64 [[S_1_VAL]])
 ; CHECK-NEXT:    [[S_01:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
-; CHECK-NEXT:    [[S_01_VAL:%.*]] = load i32, i32* [[S_01]], align 4
+; CHECK-NEXT:    [[S_01_VAL:%.*]] = load i32, i32* [[S_01]], align 32
 ; CHECK-NEXT:    [[S_12:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
 ; CHECK-NEXT:    [[S_12_VAL:%.*]] = load i64, i64* [[S_12]], align 4
 ; CHECK-NEXT:    call void @g(i32 [[S_01_VAL]], i64 [[S_12_VAL]])
 ; CHECK-NEXT:    ret i32 0
 ;
 entry:
-  %S = alloca %struct.ss
+  %S = alloca %struct.ss, align 32
   %tmp1 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 0
   store i32 1, i32* %tmp1, align 8
   %tmp4 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 1
   store i64 2, i64* %tmp4, align 4
-  call void @f(%struct.ss* byval %S) nounwind
-  call void @g(%struct.ss* byval %S) nounwind
+  call void @f(%struct.ss* byval(%struct.ss) align 4 %S) nounwind
+  call void @g(%struct.ss* byval(%struct.ss) align 32 %S) nounwind
   ret i32 0
 }
 
 

llvm/test/Transforms/ArgumentPromotion/dbg.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --scrub-attributes
 ; RUN: opt < %s -argpromotion -S | FileCheck %s
 ; RUN: opt < %s -passes=argpromotion -S | FileCheck %s
 
 declare void @sink(i32)
 
 define internal void @test(i32** %X) !dbg !2 {
 ; CHECK-LABEL: define {{[^@]+}}@test
-; CHECK-SAME: (i32 [[X_VAL_VAL:%.*]]) !dbg !3
+; CHECK-SAME: (i32 [[X_VAL_VAL:%.*]]) [[DBG3:!dbg !.*]] {
 ; CHECK-NEXT:    call void @sink(i32 [[X_VAL_VAL]])
 ; CHECK-NEXT:    ret void
 ;
   %1 = load i32*, i32** %X, align 8
   %2 = load i32, i32* %1, align 8
   call void @sink(i32 %2)
   ret void
 }
 
 %struct.pair = type { i32, i32 }
 
-define internal void @test_byval(%struct.pair* byval %P) {
+define internal void @test_byval(%struct.pair* byval(%struct.pair) align 4 %P) {
 ; CHECK-LABEL: define {{[^@]+}}@test_byval
-; CHECK-SAME: (i32 [[P_0:%.*]], i32 [[P_1:%.*]])
-; CHECK-NEXT:    [[P:%.*]] = alloca [[STRUCT_PAIR:%.*]], align 8
+; CHECK-SAME: (i32 [[P_0:%.*]], i32 [[P_1:%.*]]) {
+; CHECK-NEXT:    [[P:%.*]] = alloca [[STRUCT_PAIR:%.*]], align 4
 ; CHECK-NEXT:    [[DOT0:%.*]] = getelementptr [[STRUCT_PAIR]], %struct.pair* [[P]], i32 0, i32 0
 ; CHECK-NEXT:    store i32 [[P_0]], i32* [[DOT0]], align 4
 ; CHECK-NEXT:    [[DOT1:%.*]] = getelementptr [[STRUCT_PAIR]], %struct.pair* [[P]], i32 0, i32 1
 ; CHECK-NEXT:    store i32 [[P_1]], i32* [[DOT1]], align 4
 ; CHECK-NEXT:    ret void
 ;
   ret void
 }
 
 define void @caller(i32** %Y, %struct.pair* %P) {
 ; CHECK-LABEL: define {{[^@]+}}@caller
-; CHECK-SAME: (i32** [[Y:%.*]], %struct.pair* [[P:%.*]])
-; CHECK-NEXT:    [[Y_VAL:%.*]] = load i32*, i32** [[Y]], align 8, !dbg !4
-; CHECK-NEXT:    [[Y_VAL_VAL:%.*]] = load i32, i32* [[Y_VAL]], align 8, !dbg !4
-; CHECK-NEXT:    call void @test(i32 [[Y_VAL_VAL]]), !dbg !4
-; CHECK-NEXT:    [[P_0:%.*]] = getelementptr [[STRUCT_PAIR:%.*]], %struct.pair* [[P]], i32 0, i32 0, !dbg !5
-; CHECK-NEXT:    [[P_0_VAL:%.*]] = load i32, i32* [[P_0]], align 4, !dbg !5
-; CHECK-NEXT:    [[P_1:%.*]] = getelementptr [[STRUCT_PAIR]], %struct.pair* [[P]], i32 0, i32 1, !dbg !5
-; CHECK-NEXT:    [[P_1_VAL:%.*]] = load i32, i32* [[P_1]], align 4, !dbg !5
-; CHECK-NEXT:    call void @test_byval(i32 [[P_0_VAL]], i32 [[P_1_VAL]]), !dbg !5
+; CHECK-SAME: (i32** [[Y:%.*]], %struct.pair* [[P:%.*]]) {
+; CHECK-NEXT:    [[Y_VAL:%.*]] = load i32*, i32** [[Y]], align 8, [[DBG4:!dbg !.*]]
+; CHECK-NEXT:    [[Y_VAL_VAL:%.*]] = load i32, i32* [[Y_VAL]], align 8, [[DBG4]]
+; CHECK-NEXT:    call void @test(i32 [[Y_VAL_VAL]]), [[DBG4]]
+; CHECK-NEXT:    [[P_0:%.*]] = getelementptr [[STRUCT_PAIR:%.*]], %struct.pair* [[P]], i32 0, i32 0, [[DBG5:!dbg !.*]]
+; CHECK-NEXT:    [[P_0_VAL:%.*]] = load i32, i32* [[P_0]], align 4, [[DBG5]]
+; CHECK-NEXT:    [[P_1:%.*]] = getelementptr [[STRUCT_PAIR]], %struct.pair* [[P]], i32 0, i32 1, [[DBG5]]
+; CHECK-NEXT:    [[P_1_VAL:%.*]] = load i32, i32* [[P_1]], align 4, [[DBG5]]
+; CHECK-NEXT:    call void @test_byval(i32 [[P_0_VAL]], i32 [[P_1_VAL]]), [[DBG5]]
 ; CHECK-NEXT:    ret void
 ;
   call void @test(i32** %Y), !dbg !1
 
-  call void @test_byval(%struct.pair* %P), !dbg !6
+  call void @test_byval(%struct.pair* byval(%struct.pair) align 4 %P), !dbg !6
   ret void
 }
 
 
 !llvm.module.flags = !{!0}
 !llvm.dbg.cu = !{!3}
 
 !0 = !{i32 2, !"Debug Info Version", i32 3}
 !1 = !DILocation(line: 8, scope: !2)
 !2 = distinct !DISubprogram(name: "test", file: !5, line: 3, isLocal: true, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !3, scopeLine: 3, scope: null)
 !3 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, producer: "clang version 3.5.0 ", isOptimized: false, emissionKind: LineTablesOnly, file: !5)
 !5 = !DIFile(filename: "test.c", directory: "")
 !6 = !DILocation(line: 9, scope: !2)

llvm/test/Transforms/ArgumentPromotion/tail.ll

-; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --scrub-attributes
-; RUN: opt %s -argpromotion -S -o - | FileCheck %s
-; RUN: opt %s -passes=argpromotion -S -o - | FileCheck %s
-; PR14710
-
-target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
-
-%pair = type { i32, i32 }
-
-declare i8* @foo(%pair*)
-
-define internal void @bar(%pair* byval %Data) {
-; CHECK-LABEL: define {{[^@]+}}@bar
-; CHECK-SAME: (i32 [[DATA_0:%.*]], i32 [[DATA_1:%.*]])
-; CHECK-NEXT:    [[DATA:%.*]] = alloca [[PAIR:%.*]], align 8
-; CHECK-NEXT:    [[DOT0:%.*]] = getelementptr [[PAIR]], %pair* [[DATA]], i32 0, i32 0
-; CHECK-NEXT:    store i32 [[DATA_0]], i32* [[DOT0]], align 4
-; CHECK-NEXT:    [[DOT1:%.*]] = getelementptr [[PAIR]], %pair* [[DATA]], i32 0, i32 1
-; CHECK-NEXT:    store i32 [[DATA_1]], i32* [[DOT1]], align 4
-; CHECK-NEXT:    [[TMP1:%.*]] = call i8* @foo(%pair* [[DATA]])
-; CHECK-NEXT:    ret void
-;
-  tail call i8* @foo(%pair* %Data)
-  ret void
-}
-
-define void @zed(%pair* byval %Data) {
-; CHECK-LABEL: define {{[^@]+}}@zed
-; CHECK-SAME: (%pair* byval [[DATA:%.*]])
-; CHECK-NEXT:    [[DATA_0:%.*]] = getelementptr [[PAIR:%.*]], %pair* [[DATA]], i32 0, i32 0
-; CHECK-NEXT:    [[DATA_0_VAL:%.*]] = load i32, i32* [[DATA_0]], align 4
-; CHECK-NEXT:    [[DATA_1:%.*]] = getelementptr [[PAIR]], %pair* [[DATA]], i32 0, i32 1
-; CHECK-NEXT:    [[DATA_1_VAL:%.*]] = load i32, i32* [[DATA_1]], align 4
-; CHECK-NEXT:    call void @bar(i32 [[DATA_0_VAL]], i32 [[DATA_1_VAL]])
-; CHECK-NEXT:    ret void
-;
-  call void @bar(%pair* byval %Data)
-  ret void
-}