replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[TailCall] Allow llvm.memcpy/memset/memmove to be tail calls when parent 

function return the intrinsics's first argument.

llvm.memcpy/memset/memmove return void but they will return the first
argument after they are expanded as libcalls. Now if the parent function
has any return value, llvm.memcpy cannot be turned into tail call after
expansion.

The patch is to handle that case in SelectionDAGBuilder so when caller
function return the same value as the first argument of llvm.memcpy,
tail call is allowed.

Differential Revision: https://reviews.llvm.org/D37406

llvm-svn: 312641
This commit is contained in:
Wei Mi 2017-09-06 16:05:17 +00:00
parent 949fac9e40
commit 818d50a93d
2 changed files with 35 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llvm/lib/CodeGen/Analysis.cpp
View File

@ -565,6 +565,17 @@ bool llvm::returnTypeIsEligibleForTailCall(const Function *F,
return false;
const Value *RetVal = Ret->getOperand(0), *CallVal = I;
// Intrinsic like llvm.memcpy has no return value, but will return the
// first argument if it is expanded as libcall.
const CallInst *Call = cast<CallInst>(I);
if (Function *F = Call->getCalledFunction()) {
Intrinsic::ID IID = F->getIntrinsicID();
if ((IID == Intrinsic::memcpy || IID == Intrinsic::memmove ||
IID == Intrinsic::memset) &&
RetVal == Call->getArgOperand(0))
return true;
}
SmallVector<unsigned, 4> RetPath, CallPath;
SmallVector<CompositeType *, 4> RetSubTypes, CallSubTypes;

24
llvm/test/CodeGen/X86/tailcall-mem-intrinsics.ll
View File

@ -24,6 +24,30 @@ entry:
ret void
}
; CHECK-LABEL: tail_memcpy_ret
; CHECK: jmp memcpy
define i8* @tail_memcpy_ret(i8* nocapture %p, i8* nocapture readonly %q, i32 %n) #0 {
entry:
tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %p, i8* %q, i32 %n, i32 1, i1 false)
ret i8* %p
}
; CHECK-LABEL: tail_memmove_ret
; CHECK: jmp memmove
define i8* @tail_memmove_ret(i8* nocapture %p, i8* nocapture readonly %q, i32 %n) #0 {
entry:
tail call void @llvm.memmove.p0i8.p0i8.i32(i8* %p, i8* %q, i32 %n, i32 1, i1 false)
ret i8* %p
}
; CHECK-LABEL: tail_memset_ret
; CHECK: jmp memset
define i8* @tail_memset_ret(i8* nocapture %p, i8 %c, i32 %n) #0 {
entry:
tail call void @llvm.memset.p0i8.i32(i8* %p, i8 %c, i32 %n, i32 1, i1 false)
ret i8* %p
}
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #0
declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #0
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) #0