[llvm-commits] [llvm] r171024 - in /llvm/trunk: lib/Target/X86/X86InstrInfo.cpp test/CodeGen/X86/fold-vex.ll
Nadav Rotem
nrotem at apple.com
Mon Dec 24 01:40:34 PST 2012
Author: nadav
Date: Mon Dec 24 03:40:33 2012
New Revision: 171024
URL: http://llvm.org/viewvc/llvm-project?rev=171024&view=rev
Log:
Some x86 instructions can load/store one of the operands to memory. On SSE, this memory needs to be aligned.
When these instructions are encoded in VEX (on AVX) there is no such requirement. This changes the folding
tables and removes the alignment restrictions from VEX-encoded instructions.
Added:
llvm/trunk/test/CodeGen/X86/fold-vex.ll
Modified:
llvm/trunk/lib/Target/X86/X86InstrInfo.cpp
Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrInfo.cpp?rev=171024&r1=171023&r2=171024&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86InstrInfo.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86InstrInfo.cpp Mon Dec 24 03:40:33 2012
@@ -854,31 +854,31 @@
{ X86::Int_VCVTSI2SSrr, X86::Int_VCVTSI2SSrm, 0 },
{ X86::VCVTSS2SDrr, X86::VCVTSS2SDrm, 0 },
{ X86::Int_VCVTSS2SDrr, X86::Int_VCVTSS2SDrm, 0 },
- { X86::VCVTTPD2DQrr, X86::VCVTTPD2DQXrm, TB_ALIGN_16 },
- { X86::VCVTTPS2DQrr, X86::VCVTTPS2DQrm, TB_ALIGN_16 },
+ { X86::VCVTTPD2DQrr, X86::VCVTTPD2DQXrm, 0 },
+ { X86::VCVTTPS2DQrr, X86::VCVTTPS2DQrm, 0 },
{ X86::VRSQRTSSr, X86::VRSQRTSSm, 0 },
{ X86::VSQRTSDr, X86::VSQRTSDm, 0 },
{ X86::VSQRTSSr, X86::VSQRTSSm, 0 },
- { X86::VADDPDrr, X86::VADDPDrm, TB_ALIGN_16 },
- { X86::VADDPSrr, X86::VADDPSrm, TB_ALIGN_16 },
+ { X86::VADDPDrr, X86::VADDPDrm, 0 },
+ { X86::VADDPSrr, X86::VADDPSrm, 0 },
{ X86::VADDSDrr, X86::VADDSDrm, 0 },
{ X86::VADDSSrr, X86::VADDSSrm, 0 },
- { X86::VADDSUBPDrr, X86::VADDSUBPDrm, TB_ALIGN_16 },
- { X86::VADDSUBPSrr, X86::VADDSUBPSrm, TB_ALIGN_16 },
- { X86::VANDNPDrr, X86::VANDNPDrm, TB_ALIGN_16 },
- { X86::VANDNPSrr, X86::VANDNPSrm, TB_ALIGN_16 },
- { X86::VANDPDrr, X86::VANDPDrm, TB_ALIGN_16 },
- { X86::VANDPSrr, X86::VANDPSrm, TB_ALIGN_16 },
- { X86::VBLENDPDrri, X86::VBLENDPDrmi, TB_ALIGN_16 },
- { X86::VBLENDPSrri, X86::VBLENDPSrmi, TB_ALIGN_16 },
- { X86::VBLENDVPDrr, X86::VBLENDVPDrm, TB_ALIGN_16 },
- { X86::VBLENDVPSrr, X86::VBLENDVPSrm, TB_ALIGN_16 },
- { X86::VCMPPDrri, X86::VCMPPDrmi, TB_ALIGN_16 },
- { X86::VCMPPSrri, X86::VCMPPSrmi, TB_ALIGN_16 },
+ { X86::VADDSUBPDrr, X86::VADDSUBPDrm, 0 },
+ { X86::VADDSUBPSrr, X86::VADDSUBPSrm, 0 },
+ { X86::VANDNPDrr, X86::VANDNPDrm, 0 },
+ { X86::VANDNPSrr, X86::VANDNPSrm, 0 },
+ { X86::VANDPDrr, X86::VANDPDrm, 0 },
+ { X86::VANDPSrr, X86::VANDPSrm, 0 },
+ { X86::VBLENDPDrri, X86::VBLENDPDrmi, 0 },
+ { X86::VBLENDPSrri, X86::VBLENDPSrmi, 0 },
+ { X86::VBLENDVPDrr, X86::VBLENDVPDrm, 0 },
+ { X86::VBLENDVPSrr, X86::VBLENDVPSrm, 0 },
+ { X86::VCMPPDrri, X86::VCMPPDrmi, 0 },
+ { X86::VCMPPSrri, X86::VCMPPSrmi, 0 },
{ X86::VCMPSDrr, X86::VCMPSDrm, 0 },
{ X86::VCMPSSrr, X86::VCMPSSrm, 0 },
- { X86::VDIVPDrr, X86::VDIVPDrm, TB_ALIGN_16 },
- { X86::VDIVPSrr, X86::VDIVPSrm, TB_ALIGN_16 },
+ { X86::VDIVPDrr, X86::VDIVPDrm, 0 },
+ { X86::VDIVPSrr, X86::VDIVPSrm, 0 },
{ X86::VDIVSDrr, X86::VDIVSDrm, 0 },
{ X86::VDIVSSrr, X86::VDIVSSrm, 0 },
{ X86::VFsANDNPDrr, X86::VFsANDNPDrm, TB_ALIGN_16 },
@@ -916,252 +916,252 @@
{ X86::VMULPSrr, X86::VMULPSrm, TB_ALIGN_16 },
{ X86::VMULSDrr, X86::VMULSDrm, 0 },
{ X86::VMULSSrr, X86::VMULSSrm, 0 },
- { X86::VORPDrr, X86::VORPDrm, TB_ALIGN_16 },
- { X86::VORPSrr, X86::VORPSrm, TB_ALIGN_16 },
- { X86::VPACKSSDWrr, X86::VPACKSSDWrm, TB_ALIGN_16 },
- { X86::VPACKSSWBrr, X86::VPACKSSWBrm, TB_ALIGN_16 },
- { X86::VPACKUSDWrr, X86::VPACKUSDWrm, TB_ALIGN_16 },
- { X86::VPACKUSWBrr, X86::VPACKUSWBrm, TB_ALIGN_16 },
- { X86::VPADDBrr, X86::VPADDBrm, TB_ALIGN_16 },
- { X86::VPADDDrr, X86::VPADDDrm, TB_ALIGN_16 },
- { X86::VPADDQrr, X86::VPADDQrm, TB_ALIGN_16 },
- { X86::VPADDSBrr, X86::VPADDSBrm, TB_ALIGN_16 },
- { X86::VPADDSWrr, X86::VPADDSWrm, TB_ALIGN_16 },
- { X86::VPADDUSBrr, X86::VPADDUSBrm, TB_ALIGN_16 },
- { X86::VPADDUSWrr, X86::VPADDUSWrm, TB_ALIGN_16 },
- { X86::VPADDWrr, X86::VPADDWrm, TB_ALIGN_16 },
- { X86::VPALIGNR128rr, X86::VPALIGNR128rm, TB_ALIGN_16 },
- { X86::VPANDNrr, X86::VPANDNrm, TB_ALIGN_16 },
- { X86::VPANDrr, X86::VPANDrm, TB_ALIGN_16 },
- { X86::VPAVGBrr, X86::VPAVGBrm, TB_ALIGN_16 },
- { X86::VPAVGWrr, X86::VPAVGWrm, TB_ALIGN_16 },
- { X86::VPBLENDWrri, X86::VPBLENDWrmi, TB_ALIGN_16 },
- { X86::VPCMPEQBrr, X86::VPCMPEQBrm, TB_ALIGN_16 },
- { X86::VPCMPEQDrr, X86::VPCMPEQDrm, TB_ALIGN_16 },
- { X86::VPCMPEQQrr, X86::VPCMPEQQrm, TB_ALIGN_16 },
- { X86::VPCMPEQWrr, X86::VPCMPEQWrm, TB_ALIGN_16 },
- { X86::VPCMPGTBrr, X86::VPCMPGTBrm, TB_ALIGN_16 },
- { X86::VPCMPGTDrr, X86::VPCMPGTDrm, TB_ALIGN_16 },
- { X86::VPCMPGTQrr, X86::VPCMPGTQrm, TB_ALIGN_16 },
- { X86::VPCMPGTWrr, X86::VPCMPGTWrm, TB_ALIGN_16 },
- { X86::VPHADDDrr, X86::VPHADDDrm, TB_ALIGN_16 },
- { X86::VPHADDSWrr128, X86::VPHADDSWrm128, TB_ALIGN_16 },
- { X86::VPHADDWrr, X86::VPHADDWrm, TB_ALIGN_16 },
- { X86::VPHSUBDrr, X86::VPHSUBDrm, TB_ALIGN_16 },
- { X86::VPHSUBSWrr128, X86::VPHSUBSWrm128, TB_ALIGN_16 },
- { X86::VPHSUBWrr, X86::VPHSUBWrm, TB_ALIGN_16 },
- { X86::VPERMILPDrr, X86::VPERMILPDrm, TB_ALIGN_16 },
- { X86::VPERMILPSrr, X86::VPERMILPSrm, TB_ALIGN_16 },
- { X86::VPINSRWrri, X86::VPINSRWrmi, TB_ALIGN_16 },
- { X86::VPMADDUBSWrr128, X86::VPMADDUBSWrm128, TB_ALIGN_16 },
- { X86::VPMADDWDrr, X86::VPMADDWDrm, TB_ALIGN_16 },
- { X86::VPMAXSWrr, X86::VPMAXSWrm, TB_ALIGN_16 },
- { X86::VPMAXUBrr, X86::VPMAXUBrm, TB_ALIGN_16 },
- { X86::VPMINSWrr, X86::VPMINSWrm, TB_ALIGN_16 },
- { X86::VPMINUBrr, X86::VPMINUBrm, TB_ALIGN_16 },
- { X86::VPMINSBrr, X86::VPMINSBrm, TB_ALIGN_16 },
- { X86::VPMINSDrr, X86::VPMINSDrm, TB_ALIGN_16 },
- { X86::VPMINUDrr, X86::VPMINUDrm, TB_ALIGN_16 },
- { X86::VPMINUWrr, X86::VPMINUWrm, TB_ALIGN_16 },
- { X86::VPMAXSBrr, X86::VPMAXSBrm, TB_ALIGN_16 },
- { X86::VPMAXSDrr, X86::VPMAXSDrm, TB_ALIGN_16 },
- { X86::VPMAXUDrr, X86::VPMAXUDrm, TB_ALIGN_16 },
- { X86::VPMAXUWrr, X86::VPMAXUWrm, TB_ALIGN_16 },
- { X86::VPMULDQrr, X86::VPMULDQrm, TB_ALIGN_16 },
- { X86::VPMULHRSWrr128, X86::VPMULHRSWrm128, TB_ALIGN_16 },
- { X86::VPMULHUWrr, X86::VPMULHUWrm, TB_ALIGN_16 },
- { X86::VPMULHWrr, X86::VPMULHWrm, TB_ALIGN_16 },
- { X86::VPMULLDrr, X86::VPMULLDrm, TB_ALIGN_16 },
- { X86::VPMULLWrr, X86::VPMULLWrm, TB_ALIGN_16 },
- { X86::VPMULUDQrr, X86::VPMULUDQrm, TB_ALIGN_16 },
- { X86::VPORrr, X86::VPORrm, TB_ALIGN_16 },
- { X86::VPSADBWrr, X86::VPSADBWrm, TB_ALIGN_16 },
- { X86::VPSHUFBrr, X86::VPSHUFBrm, TB_ALIGN_16 },
- { X86::VPSIGNBrr, X86::VPSIGNBrm, TB_ALIGN_16 },
- { X86::VPSIGNWrr, X86::VPSIGNWrm, TB_ALIGN_16 },
- { X86::VPSIGNDrr, X86::VPSIGNDrm, TB_ALIGN_16 },
- { X86::VPSLLDrr, X86::VPSLLDrm, TB_ALIGN_16 },
- { X86::VPSLLQrr, X86::VPSLLQrm, TB_ALIGN_16 },
- { X86::VPSLLWrr, X86::VPSLLWrm, TB_ALIGN_16 },
- { X86::VPSRADrr, X86::VPSRADrm, TB_ALIGN_16 },
- { X86::VPSRAWrr, X86::VPSRAWrm, TB_ALIGN_16 },
- { X86::VPSRLDrr, X86::VPSRLDrm, TB_ALIGN_16 },
- { X86::VPSRLQrr, X86::VPSRLQrm, TB_ALIGN_16 },
- { X86::VPSRLWrr, X86::VPSRLWrm, TB_ALIGN_16 },
- { X86::VPSUBBrr, X86::VPSUBBrm, TB_ALIGN_16 },
- { X86::VPSUBDrr, X86::VPSUBDrm, TB_ALIGN_16 },
- { X86::VPSUBSBrr, X86::VPSUBSBrm, TB_ALIGN_16 },
- { X86::VPSUBSWrr, X86::VPSUBSWrm, TB_ALIGN_16 },
- { X86::VPSUBWrr, X86::VPSUBWrm, TB_ALIGN_16 },
- { X86::VPUNPCKHBWrr, X86::VPUNPCKHBWrm, TB_ALIGN_16 },
- { X86::VPUNPCKHDQrr, X86::VPUNPCKHDQrm, TB_ALIGN_16 },
- { X86::VPUNPCKHQDQrr, X86::VPUNPCKHQDQrm, TB_ALIGN_16 },
- { X86::VPUNPCKHWDrr, X86::VPUNPCKHWDrm, TB_ALIGN_16 },
- { X86::VPUNPCKLBWrr, X86::VPUNPCKLBWrm, TB_ALIGN_16 },
- { X86::VPUNPCKLDQrr, X86::VPUNPCKLDQrm, TB_ALIGN_16 },
- { X86::VPUNPCKLQDQrr, X86::VPUNPCKLQDQrm, TB_ALIGN_16 },
- { X86::VPUNPCKLWDrr, X86::VPUNPCKLWDrm, TB_ALIGN_16 },
- { X86::VPXORrr, X86::VPXORrm, TB_ALIGN_16 },
- { X86::VSHUFPDrri, X86::VSHUFPDrmi, TB_ALIGN_16 },
- { X86::VSHUFPSrri, X86::VSHUFPSrmi, TB_ALIGN_16 },
- { X86::VSUBPDrr, X86::VSUBPDrm, TB_ALIGN_16 },
- { X86::VSUBPSrr, X86::VSUBPSrm, TB_ALIGN_16 },
+ { X86::VORPDrr, X86::VORPDrm, 0 },
+ { X86::VORPSrr, X86::VORPSrm, 0 },
+ { X86::VPACKSSDWrr, X86::VPACKSSDWrm, 0 },
+ { X86::VPACKSSWBrr, X86::VPACKSSWBrm, 0 },
+ { X86::VPACKUSDWrr, X86::VPACKUSDWrm, 0 },
+ { X86::VPACKUSWBrr, X86::VPACKUSWBrm, 0 },
+ { X86::VPADDBrr, X86::VPADDBrm, 0 },
+ { X86::VPADDDrr, X86::VPADDDrm, 0 },
+ { X86::VPADDQrr, X86::VPADDQrm, 0 },
+ { X86::VPADDSBrr, X86::VPADDSBrm, 0 },
+ { X86::VPADDSWrr, X86::VPADDSWrm, 0 },
+ { X86::VPADDUSBrr, X86::VPADDUSBrm, 0 },
+ { X86::VPADDUSWrr, X86::VPADDUSWrm, 0 },
+ { X86::VPADDWrr, X86::VPADDWrm, 0 },
+ { X86::VPALIGNR128rr, X86::VPALIGNR128rm, 0 },
+ { X86::VPANDNrr, X86::VPANDNrm, 0 },
+ { X86::VPANDrr, X86::VPANDrm, 0 },
+ { X86::VPAVGBrr, X86::VPAVGBrm, 0 },
+ { X86::VPAVGWrr, X86::VPAVGWrm, 0 },
+ { X86::VPBLENDWrri, X86::VPBLENDWrmi, 0 },
+ { X86::VPCMPEQBrr, X86::VPCMPEQBrm, 0 },
+ { X86::VPCMPEQDrr, X86::VPCMPEQDrm, 0 },
+ { X86::VPCMPEQQrr, X86::VPCMPEQQrm, 0 },
+ { X86::VPCMPEQWrr, X86::VPCMPEQWrm, 0 },
+ { X86::VPCMPGTBrr, X86::VPCMPGTBrm, 0 },
+ { X86::VPCMPGTDrr, X86::VPCMPGTDrm, 0 },
+ { X86::VPCMPGTQrr, X86::VPCMPGTQrm, 0 },
+ { X86::VPCMPGTWrr, X86::VPCMPGTWrm, 0 },
+ { X86::VPHADDDrr, X86::VPHADDDrm, 0 },
+ { X86::VPHADDSWrr128, X86::VPHADDSWrm128, 0 },
+ { X86::VPHADDWrr, X86::VPHADDWrm, 0 },
+ { X86::VPHSUBDrr, X86::VPHSUBDrm, 0 },
+ { X86::VPHSUBSWrr128, X86::VPHSUBSWrm128, 0 },
+ { X86::VPHSUBWrr, X86::VPHSUBWrm, 0 },
+ { X86::VPERMILPDrr, X86::VPERMILPDrm, 0 },
+ { X86::VPERMILPSrr, X86::VPERMILPSrm, 0 },
+ { X86::VPINSRWrri, X86::VPINSRWrmi, 0 },
+ { X86::VPMADDUBSWrr128, X86::VPMADDUBSWrm128, 0 },
+ { X86::VPMADDWDrr, X86::VPMADDWDrm, 0 },
+ { X86::VPMAXSWrr, X86::VPMAXSWrm, 0 },
+ { X86::VPMAXUBrr, X86::VPMAXUBrm, 0 },
+ { X86::VPMINSWrr, X86::VPMINSWrm, 0 },
+ { X86::VPMINUBrr, X86::VPMINUBrm, 0 },
+ { X86::VPMINSBrr, X86::VPMINSBrm, 0 },
+ { X86::VPMINSDrr, X86::VPMINSDrm, 0 },
+ { X86::VPMINUDrr, X86::VPMINUDrm, 0 },
+ { X86::VPMINUWrr, X86::VPMINUWrm, 0 },
+ { X86::VPMAXSBrr, X86::VPMAXSBrm, 0 },
+ { X86::VPMAXSDrr, X86::VPMAXSDrm, 0 },
+ { X86::VPMAXUDrr, X86::VPMAXUDrm, 0 },
+ { X86::VPMAXUWrr, X86::VPMAXUWrm, 0 },
+ { X86::VPMULDQrr, X86::VPMULDQrm, 0 },
+ { X86::VPMULHRSWrr128, X86::VPMULHRSWrm128, 0 },
+ { X86::VPMULHUWrr, X86::VPMULHUWrm, 0 },
+ { X86::VPMULHWrr, X86::VPMULHWrm, 0 },
+ { X86::VPMULLDrr, X86::VPMULLDrm, 0 },
+ { X86::VPMULLWrr, X86::VPMULLWrm, 0 },
+ { X86::VPMULUDQrr, X86::VPMULUDQrm, 0 },
+ { X86::VPORrr, X86::VPORrm, 0 },
+ { X86::VPSADBWrr, X86::VPSADBWrm, 0 },
+ { X86::VPSHUFBrr, X86::VPSHUFBrm, 0 },
+ { X86::VPSIGNBrr, X86::VPSIGNBrm, 0 },
+ { X86::VPSIGNWrr, X86::VPSIGNWrm, 0 },
+ { X86::VPSIGNDrr, X86::VPSIGNDrm, 0 },
+ { X86::VPSLLDrr, X86::VPSLLDrm, 0 },
+ { X86::VPSLLQrr, X86::VPSLLQrm, 0 },
+ { X86::VPSLLWrr, X86::VPSLLWrm, 0 },
+ { X86::VPSRADrr, X86::VPSRADrm, 0 },
+ { X86::VPSRAWrr, X86::VPSRAWrm, 0 },
+ { X86::VPSRLDrr, X86::VPSRLDrm, 0 },
+ { X86::VPSRLQrr, X86::VPSRLQrm, 0 },
+ { X86::VPSRLWrr, X86::VPSRLWrm, 0 },
+ { X86::VPSUBBrr, X86::VPSUBBrm, 0 },
+ { X86::VPSUBDrr, X86::VPSUBDrm, 0 },
+ { X86::VPSUBSBrr, X86::VPSUBSBrm, 0 },
+ { X86::VPSUBSWrr, X86::VPSUBSWrm, 0 },
+ { X86::VPSUBWrr, X86::VPSUBWrm, 0 },
+ { X86::VPUNPCKHBWrr, X86::VPUNPCKHBWrm, 0 },
+ { X86::VPUNPCKHDQrr, X86::VPUNPCKHDQrm, 0 },
+ { X86::VPUNPCKHQDQrr, X86::VPUNPCKHQDQrm, 0 },
+ { X86::VPUNPCKHWDrr, X86::VPUNPCKHWDrm, 0 },
+ { X86::VPUNPCKLBWrr, X86::VPUNPCKLBWrm, 0 },
+ { X86::VPUNPCKLDQrr, X86::VPUNPCKLDQrm, 0 },
+ { X86::VPUNPCKLQDQrr, X86::VPUNPCKLQDQrm, 0 },
+ { X86::VPUNPCKLWDrr, X86::VPUNPCKLWDrm, 0 },
+ { X86::VPXORrr, X86::VPXORrm, 0 },
+ { X86::VSHUFPDrri, X86::VSHUFPDrmi, 0 },
+ { X86::VSHUFPSrri, X86::VSHUFPSrmi, 0 },
+ { X86::VSUBPDrr, X86::VSUBPDrm, 0 },
+ { X86::VSUBPSrr, X86::VSUBPSrm, 0 },
{ X86::VSUBSDrr, X86::VSUBSDrm, 0 },
{ X86::VSUBSSrr, X86::VSUBSSrm, 0 },
- { X86::VUNPCKHPDrr, X86::VUNPCKHPDrm, TB_ALIGN_16 },
- { X86::VUNPCKHPSrr, X86::VUNPCKHPSrm, TB_ALIGN_16 },
- { X86::VUNPCKLPDrr, X86::VUNPCKLPDrm, TB_ALIGN_16 },
- { X86::VUNPCKLPSrr, X86::VUNPCKLPSrm, TB_ALIGN_16 },
- { X86::VXORPDrr, X86::VXORPDrm, TB_ALIGN_16 },
- { X86::VXORPSrr, X86::VXORPSrm, TB_ALIGN_16 },
+ { X86::VUNPCKHPDrr, X86::VUNPCKHPDrm, 0 },
+ { X86::VUNPCKHPSrr, X86::VUNPCKHPSrm, 0 },
+ { X86::VUNPCKLPDrr, X86::VUNPCKLPDrm, 0 },
+ { X86::VUNPCKLPSrr, X86::VUNPCKLPSrm, 0 },
+ { X86::VXORPDrr, X86::VXORPDrm, 0 },
+ { X86::VXORPSrr, X86::VXORPSrm, 0 },
// AVX 256-bit foldable instructions
- { X86::VADDPDYrr, X86::VADDPDYrm, TB_ALIGN_32 },
- { X86::VADDPSYrr, X86::VADDPSYrm, TB_ALIGN_32 },
- { X86::VADDSUBPDYrr, X86::VADDSUBPDYrm, TB_ALIGN_32 },
- { X86::VADDSUBPSYrr, X86::VADDSUBPSYrm, TB_ALIGN_32 },
- { X86::VANDNPDYrr, X86::VANDNPDYrm, TB_ALIGN_32 },
- { X86::VANDNPSYrr, X86::VANDNPSYrm, TB_ALIGN_32 },
- { X86::VANDPDYrr, X86::VANDPDYrm, TB_ALIGN_32 },
- { X86::VANDPSYrr, X86::VANDPSYrm, TB_ALIGN_32 },
- { X86::VBLENDPDYrri, X86::VBLENDPDYrmi, TB_ALIGN_32 },
- { X86::VBLENDPSYrri, X86::VBLENDPSYrmi, TB_ALIGN_32 },
- { X86::VBLENDVPDYrr, X86::VBLENDVPDYrm, TB_ALIGN_32 },
- { X86::VBLENDVPSYrr, X86::VBLENDVPSYrm, TB_ALIGN_32 },
- { X86::VCMPPDYrri, X86::VCMPPDYrmi, TB_ALIGN_32 },
- { X86::VCMPPSYrri, X86::VCMPPSYrmi, TB_ALIGN_32 },
- { X86::VDIVPDYrr, X86::VDIVPDYrm, TB_ALIGN_32 },
- { X86::VDIVPSYrr, X86::VDIVPSYrm, TB_ALIGN_32 },
- { X86::VHADDPDYrr, X86::VHADDPDYrm, TB_ALIGN_32 },
- { X86::VHADDPSYrr, X86::VHADDPSYrm, TB_ALIGN_32 },
- { X86::VHSUBPDYrr, X86::VHSUBPDYrm, TB_ALIGN_32 },
- { X86::VHSUBPSYrr, X86::VHSUBPSYrm, TB_ALIGN_32 },
- { X86::VINSERTF128rr, X86::VINSERTF128rm, TB_ALIGN_32 },
- { X86::VMAXPDYrr, X86::VMAXPDYrm, TB_ALIGN_32 },
- { X86::VMAXPDYrr_Int, X86::VMAXPDYrm_Int, TB_ALIGN_32 },
- { X86::VMAXPSYrr, X86::VMAXPSYrm, TB_ALIGN_32 },
- { X86::VMAXPSYrr_Int, X86::VMAXPSYrm_Int, TB_ALIGN_32 },
- { X86::VMINPDYrr, X86::VMINPDYrm, TB_ALIGN_32 },
- { X86::VMINPDYrr_Int, X86::VMINPDYrm_Int, TB_ALIGN_32 },
- { X86::VMINPSYrr, X86::VMINPSYrm, TB_ALIGN_32 },
- { X86::VMINPSYrr_Int, X86::VMINPSYrm_Int, TB_ALIGN_32 },
- { X86::VMULPDYrr, X86::VMULPDYrm, TB_ALIGN_32 },
- { X86::VMULPSYrr, X86::VMULPSYrm, TB_ALIGN_32 },
- { X86::VORPDYrr, X86::VORPDYrm, TB_ALIGN_32 },
- { X86::VORPSYrr, X86::VORPSYrm, TB_ALIGN_32 },
- { X86::VPERM2F128rr, X86::VPERM2F128rm, TB_ALIGN_32 },
- { X86::VPERMILPDYrr, X86::VPERMILPDYrm, TB_ALIGN_32 },
- { X86::VPERMILPSYrr, X86::VPERMILPSYrm, TB_ALIGN_32 },
- { X86::VSHUFPDYrri, X86::VSHUFPDYrmi, TB_ALIGN_32 },
- { X86::VSHUFPSYrri, X86::VSHUFPSYrmi, TB_ALIGN_32 },
- { X86::VSUBPDYrr, X86::VSUBPDYrm, TB_ALIGN_32 },
- { X86::VSUBPSYrr, X86::VSUBPSYrm, TB_ALIGN_32 },
- { X86::VUNPCKHPDYrr, X86::VUNPCKHPDYrm, TB_ALIGN_32 },
- { X86::VUNPCKHPSYrr, X86::VUNPCKHPSYrm, TB_ALIGN_32 },
- { X86::VUNPCKLPDYrr, X86::VUNPCKLPDYrm, TB_ALIGN_32 },
- { X86::VUNPCKLPSYrr, X86::VUNPCKLPSYrm, TB_ALIGN_32 },
- { X86::VXORPDYrr, X86::VXORPDYrm, TB_ALIGN_32 },
- { X86::VXORPSYrr, X86::VXORPSYrm, TB_ALIGN_32 },
+ { X86::VADDPDYrr, X86::VADDPDYrm, 0 },
+ { X86::VADDPSYrr, X86::VADDPSYrm, 0 },
+ { X86::VADDSUBPDYrr, X86::VADDSUBPDYrm, 0 },
+ { X86::VADDSUBPSYrr, X86::VADDSUBPSYrm, 0 },
+ { X86::VANDNPDYrr, X86::VANDNPDYrm, 0 },
+ { X86::VANDNPSYrr, X86::VANDNPSYrm, 0 },
+ { X86::VANDPDYrr, X86::VANDPDYrm, 0 },
+ { X86::VANDPSYrr, X86::VANDPSYrm, 0 },
+ { X86::VBLENDPDYrri, X86::VBLENDPDYrmi, 0 },
+ { X86::VBLENDPSYrri, X86::VBLENDPSYrmi, 0 },
+ { X86::VBLENDVPDYrr, X86::VBLENDVPDYrm, 0 },
+ { X86::VBLENDVPSYrr, X86::VBLENDVPSYrm, 0 },
+ { X86::VCMPPDYrri, X86::VCMPPDYrmi, 0 },
+ { X86::VCMPPSYrri, X86::VCMPPSYrmi, 0 },
+ { X86::VDIVPDYrr, X86::VDIVPDYrm, 0 },
+ { X86::VDIVPSYrr, X86::VDIVPSYrm, 0 },
+ { X86::VHADDPDYrr, X86::VHADDPDYrm, 0 },
+ { X86::VHADDPSYrr, X86::VHADDPSYrm, 0 },
+ { X86::VHSUBPDYrr, X86::VHSUBPDYrm, 0 },
+ { X86::VHSUBPSYrr, X86::VHSUBPSYrm, 0 },
+ { X86::VINSERTF128rr, X86::VINSERTF128rm, 0 },
+ { X86::VMAXPDYrr, X86::VMAXPDYrm, 0 },
+ { X86::VMAXPDYrr_Int, X86::VMAXPDYrm_Int, 0 },
+ { X86::VMAXPSYrr, X86::VMAXPSYrm, 0 },
+ { X86::VMAXPSYrr_Int, X86::VMAXPSYrm_Int, 0 },
+ { X86::VMINPDYrr, X86::VMINPDYrm, 0 },
+ { X86::VMINPDYrr_Int, X86::VMINPDYrm_Int, 0 },
+ { X86::VMINPSYrr, X86::VMINPSYrm, 0 },
+ { X86::VMINPSYrr_Int, X86::VMINPSYrm_Int, 0 },
+ { X86::VMULPDYrr, X86::VMULPDYrm, 0 },
+ { X86::VMULPSYrr, X86::VMULPSYrm, 0 },
+ { X86::VORPDYrr, X86::VORPDYrm, 0 },
+ { X86::VORPSYrr, X86::VORPSYrm, 0 },
+ { X86::VPERM2F128rr, X86::VPERM2F128rm, 0 },
+ { X86::VPERMILPDYrr, X86::VPERMILPDYrm, 0 },
+ { X86::VPERMILPSYrr, X86::VPERMILPSYrm, 0 },
+ { X86::VSHUFPDYrri, X86::VSHUFPDYrmi, 0 },
+ { X86::VSHUFPSYrri, X86::VSHUFPSYrmi, 0 },
+ { X86::VSUBPDYrr, X86::VSUBPDYrm, 0 },
+ { X86::VSUBPSYrr, X86::VSUBPSYrm, 0 },
+ { X86::VUNPCKHPDYrr, X86::VUNPCKHPDYrm, 0 },
+ { X86::VUNPCKHPSYrr, X86::VUNPCKHPSYrm, 0 },
+ { X86::VUNPCKLPDYrr, X86::VUNPCKLPDYrm, 0 },
+ { X86::VUNPCKLPSYrr, X86::VUNPCKLPSYrm, 0 },
+ { X86::VXORPDYrr, X86::VXORPDYrm, 0 },
+ { X86::VXORPSYrr, X86::VXORPSYrm, 0 },
// AVX2 foldable instructions
- { X86::VINSERTI128rr, X86::VINSERTI128rm, TB_ALIGN_16 },
- { X86::VPACKSSDWYrr, X86::VPACKSSDWYrm, TB_ALIGN_32 },
- { X86::VPACKSSWBYrr, X86::VPACKSSWBYrm, TB_ALIGN_32 },
- { X86::VPACKUSDWYrr, X86::VPACKUSDWYrm, TB_ALIGN_32 },
- { X86::VPACKUSWBYrr, X86::VPACKUSWBYrm, TB_ALIGN_32 },
- { X86::VPADDBYrr, X86::VPADDBYrm, TB_ALIGN_32 },
- { X86::VPADDDYrr, X86::VPADDDYrm, TB_ALIGN_32 },
- { X86::VPADDQYrr, X86::VPADDQYrm, TB_ALIGN_32 },
- { X86::VPADDSBYrr, X86::VPADDSBYrm, TB_ALIGN_32 },
- { X86::VPADDSWYrr, X86::VPADDSWYrm, TB_ALIGN_32 },
- { X86::VPADDUSBYrr, X86::VPADDUSBYrm, TB_ALIGN_32 },
- { X86::VPADDUSWYrr, X86::VPADDUSWYrm, TB_ALIGN_32 },
- { X86::VPADDWYrr, X86::VPADDWYrm, TB_ALIGN_32 },
- { X86::VPALIGNR256rr, X86::VPALIGNR256rm, TB_ALIGN_32 },
- { X86::VPANDNYrr, X86::VPANDNYrm, TB_ALIGN_32 },
- { X86::VPANDYrr, X86::VPANDYrm, TB_ALIGN_32 },
- { X86::VPAVGBYrr, X86::VPAVGBYrm, TB_ALIGN_32 },
- { X86::VPAVGWYrr, X86::VPAVGWYrm, TB_ALIGN_32 },
- { X86::VPBLENDDrri, X86::VPBLENDDrmi, TB_ALIGN_32 },
- { X86::VPBLENDDYrri, X86::VPBLENDDYrmi, TB_ALIGN_32 },
- { X86::VPBLENDWYrri, X86::VPBLENDWYrmi, TB_ALIGN_32 },
- { X86::VPCMPEQBYrr, X86::VPCMPEQBYrm, TB_ALIGN_32 },
- { X86::VPCMPEQDYrr, X86::VPCMPEQDYrm, TB_ALIGN_32 },
- { X86::VPCMPEQQYrr, X86::VPCMPEQQYrm, TB_ALIGN_32 },
- { X86::VPCMPEQWYrr, X86::VPCMPEQWYrm, TB_ALIGN_32 },
- { X86::VPCMPGTBYrr, X86::VPCMPGTBYrm, TB_ALIGN_32 },
- { X86::VPCMPGTDYrr, X86::VPCMPGTDYrm, TB_ALIGN_32 },
- { X86::VPCMPGTQYrr, X86::VPCMPGTQYrm, TB_ALIGN_32 },
- { X86::VPCMPGTWYrr, X86::VPCMPGTWYrm, TB_ALIGN_32 },
- { X86::VPERM2I128rr, X86::VPERM2I128rm, TB_ALIGN_32 },
- { X86::VPERMDYrr, X86::VPERMDYrm, TB_ALIGN_32 },
- { X86::VPERMPDYri, X86::VPERMPDYmi, TB_ALIGN_32 },
- { X86::VPERMPSYrr, X86::VPERMPSYrm, TB_ALIGN_32 },
- { X86::VPERMQYri, X86::VPERMQYmi, TB_ALIGN_32 },
- { X86::VPHADDDYrr, X86::VPHADDDYrm, TB_ALIGN_32 },
- { X86::VPHADDSWrr256, X86::VPHADDSWrm256, TB_ALIGN_32 },
- { X86::VPHADDWYrr, X86::VPHADDWYrm, TB_ALIGN_32 },
- { X86::VPHSUBDYrr, X86::VPHSUBDYrm, TB_ALIGN_32 },
- { X86::VPHSUBSWrr256, X86::VPHSUBSWrm256, TB_ALIGN_32 },
- { X86::VPHSUBWYrr, X86::VPHSUBWYrm, TB_ALIGN_32 },
- { X86::VPMADDUBSWrr256, X86::VPMADDUBSWrm256, TB_ALIGN_32 },
- { X86::VPMADDWDYrr, X86::VPMADDWDYrm, TB_ALIGN_32 },
- { X86::VPMAXSWYrr, X86::VPMAXSWYrm, TB_ALIGN_32 },
- { X86::VPMAXUBYrr, X86::VPMAXUBYrm, TB_ALIGN_32 },
- { X86::VPMINSWYrr, X86::VPMINSWYrm, TB_ALIGN_32 },
- { X86::VPMINUBYrr, X86::VPMINUBYrm, TB_ALIGN_32 },
- { X86::VPMINSBYrr, X86::VPMINSBYrm, TB_ALIGN_32 },
- { X86::VPMINSDYrr, X86::VPMINSDYrm, TB_ALIGN_32 },
- { X86::VPMINUDYrr, X86::VPMINUDYrm, TB_ALIGN_32 },
- { X86::VPMINUWYrr, X86::VPMINUWYrm, TB_ALIGN_32 },
- { X86::VPMAXSBYrr, X86::VPMAXSBYrm, TB_ALIGN_32 },
- { X86::VPMAXSDYrr, X86::VPMAXSDYrm, TB_ALIGN_32 },
- { X86::VPMAXUDYrr, X86::VPMAXUDYrm, TB_ALIGN_32 },
- { X86::VPMAXUWYrr, X86::VPMAXUWYrm, TB_ALIGN_32 },
- { X86::VMPSADBWYrri, X86::VMPSADBWYrmi, TB_ALIGN_32 },
- { X86::VPMULDQYrr, X86::VPMULDQYrm, TB_ALIGN_32 },
- { X86::VPMULHRSWrr256, X86::VPMULHRSWrm256, TB_ALIGN_32 },
- { X86::VPMULHUWYrr, X86::VPMULHUWYrm, TB_ALIGN_32 },
- { X86::VPMULHWYrr, X86::VPMULHWYrm, TB_ALIGN_32 },
- { X86::VPMULLDYrr, X86::VPMULLDYrm, TB_ALIGN_32 },
- { X86::VPMULLWYrr, X86::VPMULLWYrm, TB_ALIGN_32 },
- { X86::VPMULUDQYrr, X86::VPMULUDQYrm, TB_ALIGN_32 },
- { X86::VPORYrr, X86::VPORYrm, TB_ALIGN_32 },
- { X86::VPSADBWYrr, X86::VPSADBWYrm, TB_ALIGN_32 },
- { X86::VPSHUFBYrr, X86::VPSHUFBYrm, TB_ALIGN_32 },
- { X86::VPSIGNBYrr, X86::VPSIGNBYrm, TB_ALIGN_32 },
- { X86::VPSIGNWYrr, X86::VPSIGNWYrm, TB_ALIGN_32 },
- { X86::VPSIGNDYrr, X86::VPSIGNDYrm, TB_ALIGN_32 },
- { X86::VPSLLDYrr, X86::VPSLLDYrm, TB_ALIGN_16 },
- { X86::VPSLLQYrr, X86::VPSLLQYrm, TB_ALIGN_16 },
- { X86::VPSLLWYrr, X86::VPSLLWYrm, TB_ALIGN_16 },
- { X86::VPSLLVDrr, X86::VPSLLVDrm, TB_ALIGN_16 },
- { X86::VPSLLVDYrr, X86::VPSLLVDYrm, TB_ALIGN_32 },
- { X86::VPSLLVQrr, X86::VPSLLVQrm, TB_ALIGN_16 },
- { X86::VPSLLVQYrr, X86::VPSLLVQYrm, TB_ALIGN_32 },
- { X86::VPSRADYrr, X86::VPSRADYrm, TB_ALIGN_16 },
- { X86::VPSRAWYrr, X86::VPSRAWYrm, TB_ALIGN_16 },
- { X86::VPSRAVDrr, X86::VPSRAVDrm, TB_ALIGN_16 },
- { X86::VPSRAVDYrr, X86::VPSRAVDYrm, TB_ALIGN_32 },
- { X86::VPSRLDYrr, X86::VPSRLDYrm, TB_ALIGN_16 },
- { X86::VPSRLQYrr, X86::VPSRLQYrm, TB_ALIGN_16 },
- { X86::VPSRLWYrr, X86::VPSRLWYrm, TB_ALIGN_16 },
- { X86::VPSRLVDrr, X86::VPSRLVDrm, TB_ALIGN_16 },
- { X86::VPSRLVDYrr, X86::VPSRLVDYrm, TB_ALIGN_32 },
- { X86::VPSRLVQrr, X86::VPSRLVQrm, TB_ALIGN_16 },
- { X86::VPSRLVQYrr, X86::VPSRLVQYrm, TB_ALIGN_32 },
- { X86::VPSUBBYrr, X86::VPSUBBYrm, TB_ALIGN_32 },
- { X86::VPSUBDYrr, X86::VPSUBDYrm, TB_ALIGN_32 },
- { X86::VPSUBSBYrr, X86::VPSUBSBYrm, TB_ALIGN_32 },
- { X86::VPSUBSWYrr, X86::VPSUBSWYrm, TB_ALIGN_32 },
- { X86::VPSUBWYrr, X86::VPSUBWYrm, TB_ALIGN_32 },
- { X86::VPUNPCKHBWYrr, X86::VPUNPCKHBWYrm, TB_ALIGN_32 },
- { X86::VPUNPCKHDQYrr, X86::VPUNPCKHDQYrm, TB_ALIGN_32 },
- { X86::VPUNPCKHQDQYrr, X86::VPUNPCKHQDQYrm, TB_ALIGN_16 },
- { X86::VPUNPCKHWDYrr, X86::VPUNPCKHWDYrm, TB_ALIGN_32 },
- { X86::VPUNPCKLBWYrr, X86::VPUNPCKLBWYrm, TB_ALIGN_32 },
- { X86::VPUNPCKLDQYrr, X86::VPUNPCKLDQYrm, TB_ALIGN_32 },
- { X86::VPUNPCKLQDQYrr, X86::VPUNPCKLQDQYrm, TB_ALIGN_32 },
- { X86::VPUNPCKLWDYrr, X86::VPUNPCKLWDYrm, TB_ALIGN_32 },
- { X86::VPXORYrr, X86::VPXORYrm, TB_ALIGN_32 },
+ { X86::VINSERTI128rr, X86::VINSERTI128rm, 0 },
+ { X86::VPACKSSDWYrr, X86::VPACKSSDWYrm, 0 },
+ { X86::VPACKSSWBYrr, X86::VPACKSSWBYrm, 0 },
+ { X86::VPACKUSDWYrr, X86::VPACKUSDWYrm, 0 },
+ { X86::VPACKUSWBYrr, X86::VPACKUSWBYrm, 0 },
+ { X86::VPADDBYrr, X86::VPADDBYrm, 0 },
+ { X86::VPADDDYrr, X86::VPADDDYrm, 0 },
+ { X86::VPADDQYrr, X86::VPADDQYrm, 0 },
+ { X86::VPADDSBYrr, X86::VPADDSBYrm, 0 },
+ { X86::VPADDSWYrr, X86::VPADDSWYrm, 0 },
+ { X86::VPADDUSBYrr, X86::VPADDUSBYrm, 0 },
+ { X86::VPADDUSWYrr, X86::VPADDUSWYrm, 0 },
+ { X86::VPADDWYrr, X86::VPADDWYrm, 0 },
+ { X86::VPALIGNR256rr, X86::VPALIGNR256rm, 0 },
+ { X86::VPANDNYrr, X86::VPANDNYrm, 0 },
+ { X86::VPANDYrr, X86::VPANDYrm, 0 },
+ { X86::VPAVGBYrr, X86::VPAVGBYrm, 0 },
+ { X86::VPAVGWYrr, X86::VPAVGWYrm, 0 },
+ { X86::VPBLENDDrri, X86::VPBLENDDrmi, 0 },
+ { X86::VPBLENDDYrri, X86::VPBLENDDYrmi, 0 },
+ { X86::VPBLENDWYrri, X86::VPBLENDWYrmi, 0 },
+ { X86::VPCMPEQBYrr, X86::VPCMPEQBYrm, 0 },
+ { X86::VPCMPEQDYrr, X86::VPCMPEQDYrm, 0 },
+ { X86::VPCMPEQQYrr, X86::VPCMPEQQYrm, 0 },
+ { X86::VPCMPEQWYrr, X86::VPCMPEQWYrm, 0 },
+ { X86::VPCMPGTBYrr, X86::VPCMPGTBYrm, 0 },
+ { X86::VPCMPGTDYrr, X86::VPCMPGTDYrm, 0 },
+ { X86::VPCMPGTQYrr, X86::VPCMPGTQYrm, 0 },
+ { X86::VPCMPGTWYrr, X86::VPCMPGTWYrm, 0 },
+ { X86::VPERM2I128rr, X86::VPERM2I128rm, 0 },
+ { X86::VPERMDYrr, X86::VPERMDYrm, 0 },
+ { X86::VPERMPDYri, X86::VPERMPDYmi, 0 },
+ { X86::VPERMPSYrr, X86::VPERMPSYrm, 0 },
+ { X86::VPERMQYri, X86::VPERMQYmi, 0 },
+ { X86::VPHADDDYrr, X86::VPHADDDYrm, 0 },
+ { X86::VPHADDSWrr256, X86::VPHADDSWrm256, 0 },
+ { X86::VPHADDWYrr, X86::VPHADDWYrm, 0 },
+ { X86::VPHSUBDYrr, X86::VPHSUBDYrm, 0 },
+ { X86::VPHSUBSWrr256, X86::VPHSUBSWrm256, 0 },
+ { X86::VPHSUBWYrr, X86::VPHSUBWYrm, 0 },
+ { X86::VPMADDUBSWrr256, X86::VPMADDUBSWrm256, 0 },
+ { X86::VPMADDWDYrr, X86::VPMADDWDYrm, 0 },
+ { X86::VPMAXSWYrr, X86::VPMAXSWYrm, 0 },
+ { X86::VPMAXUBYrr, X86::VPMAXUBYrm, 0 },
+ { X86::VPMINSWYrr, X86::VPMINSWYrm, 0 },
+ { X86::VPMINUBYrr, X86::VPMINUBYrm, 0 },
+ { X86::VPMINSBYrr, X86::VPMINSBYrm, 0 },
+ { X86::VPMINSDYrr, X86::VPMINSDYrm, 0 },
+ { X86::VPMINUDYrr, X86::VPMINUDYrm, 0 },
+ { X86::VPMINUWYrr, X86::VPMINUWYrm, 0 },
+ { X86::VPMAXSBYrr, X86::VPMAXSBYrm, 0 },
+ { X86::VPMAXSDYrr, X86::VPMAXSDYrm, 0 },
+ { X86::VPMAXUDYrr, X86::VPMAXUDYrm, 0 },
+ { X86::VPMAXUWYrr, X86::VPMAXUWYrm, 0 },
+ { X86::VMPSADBWYrri, X86::VMPSADBWYrmi, 0 },
+ { X86::VPMULDQYrr, X86::VPMULDQYrm, 0 },
+ { X86::VPMULHRSWrr256, X86::VPMULHRSWrm256, 0 },
+ { X86::VPMULHUWYrr, X86::VPMULHUWYrm, 0 },
+ { X86::VPMULHWYrr, X86::VPMULHWYrm, 0 },
+ { X86::VPMULLDYrr, X86::VPMULLDYrm, 0 },
+ { X86::VPMULLWYrr, X86::VPMULLWYrm, 0 },
+ { X86::VPMULUDQYrr, X86::VPMULUDQYrm, 0 },
+ { X86::VPORYrr, X86::VPORYrm, 0 },
+ { X86::VPSADBWYrr, X86::VPSADBWYrm, 0 },
+ { X86::VPSHUFBYrr, X86::VPSHUFBYrm, 0 },
+ { X86::VPSIGNBYrr, X86::VPSIGNBYrm, 0 },
+ { X86::VPSIGNWYrr, X86::VPSIGNWYrm, 0 },
+ { X86::VPSIGNDYrr, X86::VPSIGNDYrm, 0 },
+ { X86::VPSLLDYrr, X86::VPSLLDYrm, 0 },
+ { X86::VPSLLQYrr, X86::VPSLLQYrm, 0 },
+ { X86::VPSLLWYrr, X86::VPSLLWYrm, 0 },
+ { X86::VPSLLVDrr, X86::VPSLLVDrm, 0 },
+ { X86::VPSLLVDYrr, X86::VPSLLVDYrm, 0 },
+ { X86::VPSLLVQrr, X86::VPSLLVQrm, 0 },
+ { X86::VPSLLVQYrr, X86::VPSLLVQYrm, 0 },
+ { X86::VPSRADYrr, X86::VPSRADYrm, 0 },
+ { X86::VPSRAWYrr, X86::VPSRAWYrm, 0 },
+ { X86::VPSRAVDrr, X86::VPSRAVDrm, 0 },
+ { X86::VPSRAVDYrr, X86::VPSRAVDYrm, 0 },
+ { X86::VPSRLDYrr, X86::VPSRLDYrm, 0 },
+ { X86::VPSRLQYrr, X86::VPSRLQYrm, 0 },
+ { X86::VPSRLWYrr, X86::VPSRLWYrm, 0 },
+ { X86::VPSRLVDrr, X86::VPSRLVDrm, 0 },
+ { X86::VPSRLVDYrr, X86::VPSRLVDYrm, 0 },
+ { X86::VPSRLVQrr, X86::VPSRLVQrm, 0 },
+ { X86::VPSRLVQYrr, X86::VPSRLVQYrm, 0 },
+ { X86::VPSUBBYrr, X86::VPSUBBYrm, 0 },
+ { X86::VPSUBDYrr, X86::VPSUBDYrm, 0 },
+ { X86::VPSUBSBYrr, X86::VPSUBSBYrm, 0 },
+ { X86::VPSUBSWYrr, X86::VPSUBSWYrm, 0 },
+ { X86::VPSUBWYrr, X86::VPSUBWYrm, 0 },
+ { X86::VPUNPCKHBWYrr, X86::VPUNPCKHBWYrm, 0 },
+ { X86::VPUNPCKHDQYrr, X86::VPUNPCKHDQYrm, 0 },
+ { X86::VPUNPCKHQDQYrr, X86::VPUNPCKHQDQYrm, 0 },
+ { X86::VPUNPCKHWDYrr, X86::VPUNPCKHWDYrm, 0 },
+ { X86::VPUNPCKLBWYrr, X86::VPUNPCKLBWYrm, 0 },
+ { X86::VPUNPCKLDQYrr, X86::VPUNPCKLDQYrm, 0 },
+ { X86::VPUNPCKLQDQYrr, X86::VPUNPCKLQDQYrm, 0 },
+ { X86::VPUNPCKLWDYrr, X86::VPUNPCKLWDYrm, 0 },
+ { X86::VPXORYrr, X86::VPXORYrm, 0 },
// FIXME: add AVX 256-bit foldable instructions
// FMA4 foldable patterns
Added: llvm/trunk/test/CodeGen/X86/fold-vex.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/fold-vex.ll?rev=171024&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/X86/fold-vex.ll (added)
+++ llvm/trunk/test/CodeGen/X86/fold-vex.ll Mon Dec 24 03:40:33 2012
@@ -0,0 +1,16 @@
+; RUN: llc < %s -mcpu=corei7-avx -march=x86-64 | FileCheck %s
+
+;CHECK: @test
+; No need to load from memory. The operand will be loaded as part of th AND instr.
+;CHECK-NOT: vmovaps
+;CHECK: vandps
+;CHECK: ret
+
+define void @test1(<8 x i32>* %p0, <8 x i32> %in1) nounwind {
+entry:
+ %in0 = load <8 x i32>* %p0, align 2
+ %a = and <8 x i32> %in0, %in1
+ store <8 x i32> %a, <8 x i32>* undef
+ ret void
+}
+
More information about the llvm-commits
mailing list