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

the X86 backend no longer needs to delete its own noop copies 

llvm-svn: 25923
This commit is contained in:
Chris Lattner 2006-02-03 02:59:58 +00:00
parent 1ef239afb4
commit a1eac9b978
1 changed files with 2 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llvm/lib/Target/X86/X86PeepholeOpt.cpp
View File

@ -7,7 +7,8 @@
//
//===----------------------------------------------------------------------===//
//
// This file contains a peephole optimizer for the X86.
// This file contains an immediate shrinker for the X86. FIXME: Remove when
// the dag isel makes this obsolete!
//
//===----------------------------------------------------------------------===//
@ -61,15 +62,6 @@ bool PH::PeepholeOptimize(MachineBasicBlock &MBB,
MachineInstr *Next = (NextI != MBB.end()) ? &*NextI : (MachineInstr*)0;
unsigned Size = 0;
switch (MI->getOpcode()) {
case X86::MOV8rr:
case X86::MOV16rr:
case X86::MOV32rr: // Destroy X = X copies...
if (MI->getOperand(0).getReg() == MI->getOperand(1).getReg()) {
I = MBB.erase(I);
return true;
}
return false;
// A large number of X86 instructions have forms which take an 8-bit
// immediate despite the fact that the operands are 16 or 32 bits. Because
// this can save three bytes of code size (and icache space), we want to