maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Fix an illegal tailcall opt where the callee returns a double via xmm while caller returns x86_fp80 via st0. rdar://12229511 

llvm-svn: 164588
This commit is contained in:
Evan Cheng 2012-09-25 05:32:34 +00:00
parent eada11bb13
commit 446ff28df1
3 changed files with 36 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -2198,7 +2198,7 @@ X86TargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
// Check if it's really possible to do a tail call.
isTailCall = IsEligibleForTailCallOptimization(Callee, CallConv,
isVarArg, SR != NotStructReturn,
MF.getFunction()->hasStructRetAttr(),
MF.getFunction()->hasStructRetAttr(), CLI.RetTy,
Outs, OutVals, Ins, DAG);
// Sibcalls are automatically detected tailcalls which do not require
@ -2718,6 +2718,7 @@ X86TargetLowering::IsEligibleForTailCallOptimization(SDValue Callee,
bool isVarArg,
bool isCalleeStructRet,
bool isCallerStructRet,
Type *RetTy,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins,
@ -2729,6 +2730,13 @@ X86TargetLowering::IsEligibleForTailCallOptimization(SDValue Callee,
// If -tailcallopt is specified, make fastcc functions tail-callable.
const MachineFunction &MF = DAG.getMachineFunction();
const Function *CallerF = DAG.getMachineFunction().getFunction();
// If the function return type is x86_fp80 and the callee return type is not,
// then the FP_EXTEND of the call result is not a nop. It's not safe to
// perform a tailcall optimization here.
if (CallerF->getReturnType()->isX86_FP80Ty() && !RetTy->isX86_FP80Ty())
return false;
CallingConv::ID CallerCC = CallerF->getCallingConv();
bool CCMatch = CallerCC == CalleeCC;

1
llvm/lib/Target/X86/X86ISelLowering.h
View File

@ -744,6 +744,7 @@ namespace llvm {
bool isVarArg,
bool isCalleeStructRet,
bool isCallerStructRet,
Type *RetTy,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins,

29
llvm/test/CodeGen/X86/tailcall-64.ll
View File

@ -1,6 +1,4 @@
; RUN: llc < %s | FileCheck %s
target datalayout = "e-p:64:64:64-S128-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f16:16:16-f32:32:32-f64:64:64-f128:128:128-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-apple-darwin11.4.0"
; RUN: llc -mtriple=x86_64-apple-macosx -mcpu=core2 < %s | FileCheck %s
declare i64 @testi()
@ -132,3 +130,28 @@ entry:
%call = tail call i32 (i8*, ...)* %0(i8* null, i32 0, i32 0, i32 0, i32 0, i32 0) nounwind
ret i32 %call
}
define x86_fp80 @fp80_call(x86_fp80 %x) nounwind {
entry:
; CHECK: fp80_call:
; CHECK: jmp _fp80_callee
%call = tail call x86_fp80 @fp80_callee(x86_fp80 %x) nounwind
ret x86_fp80 %call
}
declare x86_fp80 @fp80_callee(x86_fp80)
; rdar://12229511
define x86_fp80 @trunc_fp80(x86_fp80 %x) nounwind {
entry:
; CHECK: trunc_fp80
; CHECK: callq _trunc
; CHECK-NOT: jmp _trunc
; CHECK: ret
%conv = fptrunc x86_fp80 %x to double
%call = tail call double @trunc(double %conv) nounwind readnone
%conv1 = fpext double %call to x86_fp80
ret x86_fp80 %conv1
}
declare double @trunc(double) nounwind readnone