From: Tom Stellard Date: Thu, 24 Oct 2013 16:38:33 +0000 (+0000) Subject: Inliner: Handle readonly attribute per argument when adding memcpy X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=4a6b6eea2d7c1a0fa8e3ee23e1fa73f0307d1115;p=oota-llvm.git 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 --- diff --git a/lib/Transforms/Utils/InlineFunction.cpp b/lib/Transforms/Utils/InlineFunction.cpp index dabb67b9219..585658a8811 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(Arg->getType())->getElementType(); + Type *AggTy = cast(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 diff --git a/test/Transforms/Inline/byval.ll b/test/Transforms/Inline/byval.ll index e601faf2bb3..3d41dc5a794 100644 --- a/test/Transforms/Inline/byval.ll +++ b/test/Transforms/Inline/byval.ll @@ -25,7 +25,7 @@ entry: store i64 2, i64* %tmp4, align 4 call void @f( %struct.ss* byval %S ) nounwind ret i32 0 -; CHECK: @test1() +; CHECK-LABEL: @test1() ; CHECK: %S1 = alloca %struct.ss ; CHECK: %S = alloca %struct.ss ; CHECK: call void @llvm.memcpy @@ -52,7 +52,7 @@ entry: store i64 2, i64* %tmp4, align 4 %X = call i32 @f2( %struct.ss* byval %S ) nounwind ret i32 %X -; CHECK: @test2() +; CHECK-LABEL: @test2() ; CHECK: %S = alloca %struct.ss ; CHECK-NOT: call void @llvm.memcpy ; CHECK: ret i32 @@ -74,7 +74,7 @@ entry: %S = alloca %struct.ss, align 1 ;; May not be aligned. call void @f3( %struct.ss* byval align 64 %S) nounwind ret void -; CHECK: @test3() +; CHECK-LABEL: @test3() ; CHECK: %S1 = alloca %struct.ss, align 64 ; CHECK: %S = alloca %struct.ss ; CHECK: call void @llvm.memcpy @@ -97,10 +97,35 @@ entry: %S = alloca %struct.ss, align 2 ; <%struct.ss*> [#uses=4] %X = call i32 @f4( %struct.ss* byval align 64 %S ) nounwind ret i32 %X -; CHECK: @test4() +; CHECK-LABEL: @test4() ; CHECK: %S = alloca %struct.ss, align 64 ; CHECK-NOT: call void @llvm.memcpy ; CHECK: call void @g3 ; CHECK: ret i32 4 } +; Inlining a byval struct should NOT cause an explicit copy +; into an alloca if the parameter is readonly + +define internal i32 @f5(%struct.ss* byval readonly %b) nounwind { +entry: + %tmp = getelementptr %struct.ss* %b, i32 0, i32 0 ; [#uses=2] + %tmp1 = load i32* %tmp, align 4 ; [#uses=1] + %tmp2 = add i32 %tmp1, 1 ; [#uses=1] + ret i32 %tmp2 +} + +define i32 @test5() nounwind { +entry: + %S = alloca %struct.ss ; <%struct.ss*> [#uses=4] + %tmp1 = getelementptr %struct.ss* %S, i32 0, i32 0 ; [#uses=1] + store i32 1, i32* %tmp1, align 8 + %tmp4 = getelementptr %struct.ss* %S, i32 0, i32 1 ; [#uses=1] + store i64 2, i64* %tmp4, align 4 + %X = call i32 @f5( %struct.ss* byval %S ) nounwind + ret i32 %X +; CHECK-LABEL: @test5() +; CHECK: %S = alloca %struct.ss +; CHECK-NOT: call void @llvm.memcpy +; CHECK: ret i32 +}