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

Convert V_SETALLONES/AVX_SETALLONES/AVX2_SETALLONES to Post-RA pseudos. 

llvm-svn: 162740
This commit is contained in:
Craig Topper 2012-08-28 07:30:47 +00:00
parent cae486c063
commit 72f51c3986
3 changed files with 10 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/lib/Target/X86/X86InstrInfo.cpp
View File

@ -3432,6 +3432,10 @@ bool X86InstrInfo::expandPostRAPseudo(MachineBasicBlock::iterator MI) const {
case X86::AVX_SET0:
assert(HasAVX && "AVX not supported");
return Expand2AddrUndef(MI, get(X86::VXORPSYrr));
case X86::V_SETALLONES:
return Expand2AddrUndef(MI, get(HasAVX ? X86::VPCMPEQDrr : X86::PCMPEQDrr));
case X86::AVX2_SETALLONES:
return Expand2AddrUndef(MI, get(X86::VPCMPEQDYrr));
case X86::TEST8ri_NOREX:
MI->setDesc(get(X86::TEST8ri));
return true;
@ -3789,7 +3793,6 @@ MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
break;
case X86::V_SET0:
case X86::V_SETALLONES:
case X86::AVX_SETALLONES:
Alignment = 16;
break;
case X86::FsFLD0SD:
@ -3825,7 +3828,6 @@ MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
switch (LoadMI->getOpcode()) {
case X86::V_SET0:
case X86::V_SETALLONES:
case X86::AVX_SETALLONES:
case X86::AVX2_SETALLONES:
case X86::AVX_SET0:
case X86::FsFLD0SD:
@ -3864,8 +3866,7 @@ MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
else
Ty = VectorType::get(Type::getInt32Ty(MF.getFunction()->getContext()), 4);
bool IsAllOnes = (Opc == X86::V_SETALLONES || Opc == X86::AVX_SETALLONES ||
Opc == X86::AVX2_SETALLONES);
bool IsAllOnes = (Opc == X86::V_SETALLONES || Opc == X86::AVX2_SETALLONES);
const Constant *C = IsAllOnes ? Constant::getAllOnesValue(Ty) :
Constant::getNullValue(Ty);
unsigned CPI = MCP.getConstantPoolIndex(C, Alignment);

16
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -436,19 +436,13 @@ def : Pat<(bc_v4i64 (v8f32 immAllZerosV)),
// We set canFoldAsLoad because this can be converted to a constant-pool
// load of an all-ones value if folding it would be beneficial.
// FIXME: Change encoding to pseudo! This is blocked right now by the x86
// JIT implementation, it does not expand the instructions below like
// X86MCInstLower does.
let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1,
isCodeGenOnly = 1, ExeDomain = SSEPackedInt in {
let Predicates = [HasAVX] in
def AVX_SETALLONES : PDI<0x76, MRMInitReg, (outs VR128:$dst), (ins), "",
[(set VR128:$dst, (v4i32 immAllOnesV))]>, VEX_4V;
def V_SETALLONES : PDI<0x76, MRMInitReg, (outs VR128:$dst), (ins), "",
[(set VR128:$dst, (v4i32 immAllOnesV))]>;
isPseudo = 1 in {
def V_SETALLONES : I<0, Pseudo, (outs VR128:$dst), (ins), "",
[(set VR128:$dst, (v4i32 immAllOnesV))]>;
let Predicates = [HasAVX2] in
def AVX2_SETALLONES : PDI<0x76, MRMInitReg, (outs VR256:$dst), (ins), "",
[(set VR256:$dst, (v8i32 immAllOnesV))]>, VEX_4V;
def AVX2_SETALLONES : I<0, Pseudo, (outs VR256:$dst), (ins), "",
[(set VR256:$dst, (v8i32 immAllOnesV))]>;
}

3
llvm/lib/Target/X86/X86MCInstLower.cpp
View File

@ -377,9 +377,6 @@ ReSimplify:
case X86::SETB_C64r: LowerUnaryToTwoAddr(OutMI, X86::SBB64rr); break;
case X86::MOV8r0: LowerUnaryToTwoAddr(OutMI, X86::XOR8rr); break;
case X86::MOV32r0: LowerUnaryToTwoAddr(OutMI, X86::XOR32rr); break;
case X86::V_SETALLONES: LowerUnaryToTwoAddr(OutMI, X86::PCMPEQDrr); break;
case X86::AVX_SETALLONES: LowerUnaryToTwoAddr(OutMI, X86::VPCMPEQDrr); break;
case X86::AVX2_SETALLONES: LowerUnaryToTwoAddr(OutMI, X86::VPCMPEQDYrr);break;
case X86::MOV16r0:
LowerSubReg32_Op0(OutMI, X86::MOV32r0); // MOV16r0 -> MOV32r0