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

Teach X86 asm parser that VMOVAPSrr and other VEX-encoded register to register moves should be switched from using the MRMSrcReg form to the MRMDestReg form if the source register is a 64-bit extended register and the destination register is not. 

This allows the instruction to be encoded using the 2-byte VEX form instead of the 3-byte VEX form. The GNU assembler has similar behavior and instruction selection already does this.

llvm-svn: 192088
This commit is contained in:
Craig Topper 2013-10-07 05:42:48 +00:00
parent ad090d82f2
commit a0e0735e6a
3 changed files with 106 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
llvm/lib/Target/X86/AsmParser/X86AsmParser.cpp
View File

@ -2271,6 +2271,55 @@ processInstruction(MCInst &Inst,
case X86::SBB16i16: return convert16i16to16ri8(Inst, X86::SBB16ri8);
case X86::SBB32i32: return convert32i32to32ri8(Inst, X86::SBB32ri8);
case X86::SBB64i32: return convert64i32to64ri8(Inst, X86::SBB64ri8);
case X86::VMOVAPDrr:
case X86::VMOVAPDYrr:
case X86::VMOVAPSrr:
case X86::VMOVAPSYrr:
case X86::VMOVDQArr:
case X86::VMOVDQAYrr:
case X86::VMOVDQUrr:
case X86::VMOVDQUYrr:
case X86::VMOVUPDrr:
case X86::VMOVUPDYrr:
case X86::VMOVUPSrr:
case X86::VMOVUPSYrr: {
if (X86II::isX86_64ExtendedReg(Inst.getOperand(0).getReg()) ||
!X86II::isX86_64ExtendedReg(Inst.getOperand(1).getReg()))
return false;
unsigned NewOpc;
switch (Inst.getOpcode()) {
default: llvm_unreachable("Invalid opcode");
case X86::VMOVAPDrr: NewOpc = X86::VMOVAPDrr_REV; break;
case X86::VMOVAPDYrr: NewOpc = X86::VMOVAPDYrr_REV; break;
case X86::VMOVAPSrr: NewOpc = X86::VMOVAPSrr_REV; break;
case X86::VMOVAPSYrr: NewOpc = X86::VMOVAPSYrr_REV; break;
case X86::VMOVDQArr: NewOpc = X86::VMOVDQArr_REV; break;
case X86::VMOVDQAYrr: NewOpc = X86::VMOVDQAYrr_REV; break;
case X86::VMOVDQUrr: NewOpc = X86::VMOVDQUrr_REV; break;
case X86::VMOVDQUYrr: NewOpc = X86::VMOVDQUYrr_REV; break;
case X86::VMOVUPDrr: NewOpc = X86::VMOVUPDrr_REV; break;
case X86::VMOVUPDYrr: NewOpc = X86::VMOVUPDYrr_REV; break;
case X86::VMOVUPSrr: NewOpc = X86::VMOVUPSrr_REV; break;
case X86::VMOVUPSYrr: NewOpc = X86::VMOVUPSYrr_REV; break;
}
Inst.setOpcode(NewOpc);
return true;
}
case X86::VMOVSDrr:
case X86::VMOVSSrr: {
if (X86II::isX86_64ExtendedReg(Inst.getOperand(0).getReg()) ||
!X86II::isX86_64ExtendedReg(Inst.getOperand(2).getReg()))
return false;
unsigned NewOpc;
switch (Inst.getOpcode()) {
default: llvm_unreachable("Invalid opcode");
case X86::VMOVSDrr: NewOpc = X86::VMOVSDrr_REV; break;
case X86::VMOVSSrr: NewOpc = X86::VMOVSSrr_REV; break;
}
Inst.setOpcode(NewOpc);
return true;
}
}
}

2
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -1104,7 +1104,7 @@ let Predicates = [UseSSE1] in {
// Alias instruction to do FR32 or FR64 reg-to-reg copy using movaps. Upper
// bits are disregarded. FIXME: Set encoding to pseudo!
let neverHasSideEffects = 1, SchedRW = [WriteMove] in {
let isCodeGenOnly = 1, neverHasSideEffects = 1, SchedRW = [WriteMove] in {
def FsVMOVAPSrr : VPSI<0x28, MRMSrcReg, (outs FR32:$dst), (ins FR32:$src),
"movaps\t{$src, $dst|$dst, $src}", [],
IIC_SSE_MOVA_P_RR>, VEX;

56
llvm/test/MC/X86/x86_64-avx-encoding.s
View File

@ -4185,3 +4185,59 @@ _foo2:
// CHECK: vpgatherqd %xmm8, (%r15,%ymm9,2), %xmm10
// CHECK: encoding: [0xc4,0x02,0x3d,0x91,0x14,0x4f]
vpgatherqd %xmm8, (%r15,%ymm9,2), %xmm10
// CHECK: vmovaps %xmm0, %xmm8
// CHECK: encoding: [0xc5,0x78,0x28,0xc0]
vmovaps %xmm0, %xmm8
// CHECK: vmovaps %xmm8, %xmm0
// CHECK: encoding: [0xc5,0x78,0x29,0xc0]
vmovaps %xmm8, %xmm0
// CHECK: vmovaps %ymm0, %ymm8
// CHECK: encoding: [0xc5,0x7c,0x28,0xc0]
vmovaps %ymm0, %ymm8
// CHECK: vmovaps %ymm8, %ymm0
// CHECK: encoding: [0xc5,0x7c,0x29,0xc0]
vmovaps %ymm8, %ymm0
// CHECK: vmovups %xmm0, %xmm8
// CHECK: encoding: [0xc5,0x78,0x10,0xc0]
vmovups %xmm0, %xmm8
// CHECK: vmovups %xmm8, %xmm0
// CHECK: encoding: [0xc5,0x78,0x11,0xc0]
vmovups %xmm8, %xmm0
// CHECK: vmovups %ymm0, %ymm8
// CHECK: encoding: [0xc5,0x7c,0x10,0xc0]
vmovups %ymm0, %ymm8
// CHECK: vmovups %ymm8, %ymm0
// CHECK: encoding: [0xc5,0x7c,0x11,0xc0]
vmovups %ymm8, %ymm0
// CHECK: vmovss %xmm0, %xmm0, %xmm8
// CHECK: encoding: [0xc5,0x7a,0x10,0xc0]
vmovss %xmm0, %xmm0, %xmm8
// CHECK: vmovss %xmm0, %xmm8, %xmm0
// CHECK: encoding: [0xc5,0xba,0x10,0xc0]
vmovss %xmm0, %xmm8, %xmm0
// CHECK: vmovss %xmm8, %xmm0, %xmm0
// CHECK: encoding: [0xc5,0x7a,0x11,0xc0]
vmovss %xmm8, %xmm0, %xmm0
// CHECK: vmovsd %xmm0, %xmm0, %xmm8
// CHECK: encoding: [0xc5,0x7b,0x10,0xc0]
vmovsd %xmm0, %xmm0, %xmm8
// CHECK: vmovsd %xmm0, %xmm8, %xmm0
// CHECK: encoding: [0xc5,0xbb,0x10,0xc0]
vmovsd %xmm0, %xmm8, %xmm0
// CHECK: vmovsd %xmm8, %xmm0, %xmm0
// CHECK: encoding: [0xc5,0x7b,0x11,0xc0]
vmovsd %xmm8, %xmm0, %xmm0