diff options
author | Tom Stellard <thomas.stellard@amd.com> | 2013-10-24 16:38:33 +0000 |
---|---|---|
committer | Tom Stellard <thomas.stellard@amd.com> | 2013-10-24 16:38:33 +0000 |
commit | 4a6b6eea2d7c1a0fa8e3ee23e1fa73f0307d1115 (patch) | |
tree | 423e436e7d1d6a546fd7468d9e3d6dfe121a322e /lib/Transforms/Utils | |
parent | e662fb6083df86f4b46fe482d1043cf2fb4b74a1 (diff) | |
download | llvm-4a6b6eea2d7c1a0fa8e3ee23e1fa73f0307d1115.tar.gz llvm-4a6b6eea2d7c1a0fa8e3ee23e1fa73f0307d1115.tar.bz2 llvm-4a6b6eea2d7c1a0fa8e3ee23e1fa73f0307d1115.tar.xz |
Inliner: Handle readonly attribute per argument when adding memcpy
Patch by: Vincent Lejeune
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193356 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Transforms/Utils')
-rw-r--r-- | lib/Transforms/Utils/InlineFunction.cpp | 23 |
1 files changed, 13 insertions, 10 deletions
diff --git a/lib/Transforms/Utils/InlineFunction.cpp b/lib/Transforms/Utils/InlineFunction.cpp index dabb67b921..585658a881 100644 --- a/lib/Transforms/Utils/InlineFunction.cpp +++ b/lib/Transforms/Utils/InlineFunction.cpp @@ -337,33 +337,35 @@ static void UpdateCallGraphAfterInlining(CallSite CS, /// HandleByValArgument - When inlining a call site that has a byval argument, /// we have to make the implicit memcpy explicit by adding it. -static Value *HandleByValArgument(Value *Arg, Instruction *TheCall, +static Value *HandleByValArgument(Value *PassedValue, + const Argument *ArgumentSignature, + Instruction *TheCall, const Function *CalledFunc, InlineFunctionInfo &IFI, unsigned ByValAlignment) { - Type *AggTy = cast<PointerType>(Arg->getType())->getElementType(); + Type *AggTy = cast<PointerType>(PassedValue->getType())->getElementType(); // If the called function is readonly, then it could not mutate the caller's // copy of the byval'd memory. In this case, it is safe to elide the copy and // temporary. - if (CalledFunc->onlyReadsMemory()) { + if (CalledFunc->onlyReadsMemory() || ArgumentSignature->onlyReadsMemory()) { // If the byval argument has a specified alignment that is greater than the // passed in pointer, then we either have to round up the input pointer or // give up on this transformation. if (ByValAlignment <= 1) // 0 = unspecified, 1 = no particular alignment. - return Arg; + return PassedValue; // If the pointer is already known to be sufficiently aligned, or if we can // round it up to a larger alignment, then we don't need a temporary. - if (getOrEnforceKnownAlignment(Arg, ByValAlignment, + if (getOrEnforceKnownAlignment(PassedValue, ByValAlignment, IFI.TD) >= ByValAlignment) - return Arg; + return PassedValue; // Otherwise, we have to make a memcpy to get a safe alignment. This is bad // for code quality, but rarely happens and is required for correctness. } - LLVMContext &Context = Arg->getContext(); + LLVMContext &Context = PassedValue->getContext(); Type *VoidPtrTy = Type::getInt8PtrTy(Context); @@ -379,7 +381,7 @@ static Value *HandleByValArgument(Value *Arg, Instruction *TheCall, Function *Caller = TheCall->getParent()->getParent(); - Value *NewAlloca = new AllocaInst(AggTy, 0, Align, Arg->getName(), + Value *NewAlloca = new AllocaInst(AggTy, 0, Align, PassedValue->getName(), &*Caller->begin()->begin()); // Emit a memcpy. Type *Tys[3] = {VoidPtrTy, VoidPtrTy, Type::getInt64Ty(Context)}; @@ -387,7 +389,7 @@ static Value *HandleByValArgument(Value *Arg, Instruction *TheCall, Intrinsic::memcpy, Tys); Value *DestCast = new BitCastInst(NewAlloca, VoidPtrTy, "tmp", TheCall); - Value *SrcCast = new BitCastInst(Arg, VoidPtrTy, "tmp", TheCall); + Value *SrcCast = new BitCastInst(PassedValue, VoidPtrTy, "tmp", TheCall); Value *Size; if (IFI.TD == 0) @@ -588,13 +590,14 @@ bool llvm::InlineFunction(CallSite CS, InlineFunctionInfo &IFI, for (Function::const_arg_iterator I = CalledFunc->arg_begin(), E = CalledFunc->arg_end(); I != E; ++I, ++AI, ++ArgNo) { Value *ActualArg = *AI; + const Argument *Arg = I; // When byval arguments actually inlined, we need to make the copy implied // by them explicit. However, we don't do this if the callee is readonly // or readnone, because the copy would be unneeded: the callee doesn't // modify the struct. if (CS.isByValArgument(ArgNo)) { - ActualArg = HandleByValArgument(ActualArg, TheCall, CalledFunc, IFI, + ActualArg = HandleByValArgument(ActualArg, Arg, TheCall, CalledFunc, IFI, CalledFunc->getParamAlignment(ArgNo+1)); // Calls that we inline may use the new alloca, so we need to clear |