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

Don't use implicit register operands to calculate L-bit for AVX instructions. Needed because super reg defs and kills are added as implicit operands on 128-bit instructions. Fixes PR13349. Patch by Jose Fonseca. 

llvm-svn: 160543
This commit is contained in:
Craig Topper 2012-07-20 07:03:46 +00:00
parent cd8a546b6c
commit 0b94e46ce3
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/X86/X86CodeEmitter.cpp
View File

@ -927,6 +927,8 @@ void Emitter<CodeEmitter>::emitVEXOpcodePrefix(uint64_t TSFlags,
for (unsigned i = 0; i != MI.getNumOperands(); ++i) {
if (!MI.getOperand(i).isReg())
continue;
if (MI.getOperand(i).isImplicit())
continue;
unsigned SrcReg = MI.getOperand(i).getReg();
if (SrcReg >= X86::YMM0 && SrcReg <= X86::YMM15)
VEX_L = 1;