6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-13 20:32:21 +00:00
Code Issues Projects Releases Wiki Activity

Prevent obscure and incorrect tail-call optimization.

Browse Source 
In this instance we are generating the tail-call during legalizeDAG.  The 2nd
floor call can't be a tail call because it clobbers %xmm1, which is defined by
the first floor call.  The first floor call can't be a tail-call because it's
not in the tail position.  The only reasonable way I could think to fix this
in a target-independent manner was to check for glue logic on the copy reg.

rdar://10930395


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@151877 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Chad Rosier 2012-03-02 02:50:46 +00:00
parent b83e2bbfbc
commit 74bab7f597
2 changed files with 34 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lib/Target/X86/X86ISelLowering.cpp
View File

@ -1589,6 +1589,11 @@ bool X86TargetLowering::isUsedByReturnOnly(SDNode *N) const {
Copy->getOpcode() != ISD::FP_EXTEND)
return false;
// If anything is glued to the copy, then we can't safely perform a tail call.
if (Copy->getOpcode() == ISD::CopyToReg &&
Copy->getNumOperands() == 4)
return false;
bool HasRet = false;
for (SDNode::use_iterator UI = Copy->use_begin(), UE = Copy->use_end();
UI != UE; ++UI) {

29
test/CodeGen/X86/sibcall-5.ll
View File

@ -1,5 +1,6 @@
; RUN: llc < %s -mtriple=i386-apple-darwin8 -mattr=+sse2 | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+sse2 | FileCheck %s --check-prefix=X64
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=-sse3 | FileCheck %s --check-prefix=X64_BAD
; Sibcall optimization of expanded libcalls.
; rdar://8707777
@ -29,3 +30,31 @@ entry:
declare float @sinf(float) nounwind readonly
declare double @sin(double) nounwind readonly
; rdar://10930395
%0 = type opaque
@"\01L_OBJC_SELECTOR_REFERENCES_2" = external hidden global i8*, section "__DATA, __objc_selrefs, literal_pointers, no_dead_strip"
define hidden { double, double } @foo2(%0* %self, i8* nocapture %_cmd) uwtable optsize ssp {
; X64_BAD: foo
; X64_BAD: call
; X64_BAD: call
; X64_BAD: call
%1 = load i8** @"\01L_OBJC_SELECTOR_REFERENCES_2", align 8, !invariant.load !0
%2 = bitcast %0* %self to i8*
%3 = tail call { double, double } bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to { double, double } (i8*, i8*)*)(i8* %2, i8* %1) optsize
%4 = extractvalue { double, double } %3, 0
%5 = extractvalue { double, double } %3, 1
%6 = tail call double @floor(double %4) optsize
%7 = tail call double @floor(double %5) optsize
%insert.i.i = insertvalue { double, double } undef, double %6, 0
%insert5.i.i = insertvalue { double, double } %insert.i.i, double %7, 1
ret { double, double } %insert5.i.i
}
declare i8* @objc_msgSend(i8*, i8*, ...)
declare double @floor(double) optsize
!0 = metadata !{}