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

[X86] Fix a bug in X86's peephole optimization. 

Peephole optimization was folding MOVSDrm, which is a zero-extending double
precision floating point load, into ADDPDrr, which is a SIMD add of two packed
double precision floating point values.

(before)
%vreg21<def> = MOVSDrm <fi#0>, 1, %noreg, 0, %noreg; mem:LD8[%7](align=16)(tbaa=<badref>) VR128:%vreg21
%vreg23<def,tied1> = ADDPDrr %vreg20<tied0>, %vreg21; VR128:%vreg23,%vreg20,%vreg21

(after)
%vreg23<def,tied1> = ADDPDrm %vreg20<tied0>, <fi#0>, 1, %noreg, 0, %noreg; mem:LD8[%7](align=16)(tbaa=<badref>) VR128:%vreg23,%vreg20

X86InstrInfo::foldMemoryOperandImpl already had the logic that prevented this
from happening. However the check wasn't being conducted for loads from stack
objects. This commit factors out the logic into a new function and uses it for
checking loads from stack slots are not zero-extending loads.

rdar://problem/18236850

llvm-svn: 217799
This commit is contained in:
Akira Hatanaka 2014-09-15 18:23:52 +00:00
parent fdacdb26af
commit 760814a7e1
2 changed files with 55 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
llvm/lib/Target/X86/X86InstrInfo.cpp
View File

@ -4423,6 +4423,25 @@ X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF, MachineInstr *MI,
return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, Size, Alignment);
}
static bool isPartialRegisterLoad(const MachineInstr &LoadMI,
const MachineFunction &MF) {
unsigned Opc = LoadMI.getOpcode();
unsigned RegSize =
MF.getRegInfo().getRegClass(LoadMI.getOperand(0).getReg())->getSize();
if ((Opc == X86::MOVSSrm || Opc == X86::VMOVSSrm) && RegSize > 4)
// These instructions only load 32 bits, we can't fold them if the
// destination register is wider than 32 bits (4 bytes).
return true;
if ((Opc == X86::MOVSDrm || Opc == X86::VMOVSDrm) && RegSize > 8)
// These instructions only load 64 bits, we can't fold them if the
// destination register is wider than 64 bits (8 bytes).
return true;
return false;
}
MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
MachineInstr *MI,
const SmallVectorImpl<unsigned> &Ops,
@ -4430,8 +4449,11 @@ MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
// If loading from a FrameIndex, fold directly from the FrameIndex.
unsigned NumOps = LoadMI->getDesc().getNumOperands();
int FrameIndex;
if (isLoadFromStackSlot(LoadMI, FrameIndex))
if (isLoadFromStackSlot(LoadMI, FrameIndex)) {
if (isPartialRegisterLoad(*LoadMI, MF))
return nullptr;
return foldMemoryOperandImpl(MF, MI, Ops, FrameIndex);
}
// Check switch flag
if (NoFusing) return nullptr;
@ -4542,19 +4564,7 @@ MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
break;
}
default: {
if ((LoadMI->getOpcode() == X86::MOVSSrm ||
LoadMI->getOpcode() == X86::VMOVSSrm) &&
MF.getRegInfo().getRegClass(LoadMI->getOperand(0).getReg())->getSize()
> 4)
// These instructions only load 32 bits, we can't fold them if the
// destination register is wider than 32 bits (4 bytes).
return nullptr;
if ((LoadMI->getOpcode() == X86::MOVSDrm ||
LoadMI->getOpcode() == X86::VMOVSDrm) &&
MF.getRegInfo().getRegClass(LoadMI->getOperand(0).getReg())->getSize()
> 8)
// These instructions only load 64 bits, we can't fold them if the
// destination register is wider than 64 bits (8 bytes).
if (isPartialRegisterLoad(*LoadMI, MF))
return nullptr;
// Folding a normal load. Just copy the load's address operands.

31
llvm/test/CodeGen/X86/peephole-fold-movsd.ll Normal file
View File

@ -0,0 +1,31 @@
; RUN: llc -march=x86-64 < %s | FileCheck %s
;
; Check that x86's peephole optimization doesn't fold a 64-bit load (movsd) into
; addpd.
; rdar://problem/18236850
%struct.S1 = type { double, double }
@g = common global %struct.S1 zeroinitializer, align 8
declare void @foo3(%struct.S1*)
; CHECK: movsd (%rsp), [[R0:%xmm[0-9]+]]
; CHECK: addpd [[R0]], %xmm{{[0-9]+}}
define void @foo1(double %a.coerce0, double %a.coerce1, double %b.coerce0, double %b.coerce1) {
%1 = alloca <2 x double>, align 16
%tmpcast = bitcast <2 x double>* %1 to %struct.S1*
call void @foo3(%struct.S1* %tmpcast) #2
%p2 = getelementptr inbounds %struct.S1* %tmpcast, i64 0, i32 0
%2 = load double* %p2, align 16
%p3 = getelementptr inbounds %struct.S1* %tmpcast, i64 0, i32 1
%3 = load double* %p3, align 8
%4 = insertelement <2 x double> undef, double %2, i32 0
%5 = insertelement <2 x double> %4, double 0.000000e+00, i32 1
%6 = insertelement <2 x double> undef, double %3, i32 1
%7 = insertelement <2 x double> %6, double 1.000000e+00, i32 0
%8 = fadd <2 x double> %5, %7
store <2 x double> %8, <2 x double>* bitcast (%struct.S1* @g to <2 x double>*), align 16
ret void
}