diff --git a/lib/Target/X86/CMakeLists.txt b/lib/Target/X86/CMakeLists.txt index 7471373334f..fc4adddc149 100644 --- a/lib/Target/X86/CMakeLists.txt +++ b/lib/Target/X86/CMakeLists.txt @@ -11,7 +11,6 @@ tablegen(LLVM X86GenFastISel.inc -gen-fast-isel) tablegen(LLVM X86GenCallingConv.inc -gen-callingconv) tablegen(LLVM X86GenSubtargetInfo.inc -gen-subtarget) tablegen(LLVM X86GenEVEX2VEXTables.inc -gen-x86-EVEX2VEX-tables) -tablegen(LLVM X86GenFoldTables.inc -gen-x86-fold-tables) if(LLVM_BUILD_GLOBAL_ISEL) tablegen(LLVM X86GenRegisterBank.inc -gen-register-bank) tablegen(LLVM X86GenGlobalISel.inc -gen-global-isel) diff --git a/lib/Target/X86/X86InstrInfo.cpp b/lib/Target/X86/X86InstrInfo.cpp index 0aee30081a3..ff5d90c4e78 100644 --- a/lib/Target/X86/X86InstrInfo.cpp +++ b/lib/Target/X86/X86InstrInfo.cpp @@ -121,8 +121,172 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI) (STI.is64Bit() ? X86::RETQ : X86::RETL)), Subtarget(STI), RI(STI.getTargetTriple()) { -// Generated memory folding tables. -#include "X86GenFoldTables.inc" + static const X86MemoryFoldTableEntry MemoryFoldTable2Addr[] = { + { X86::ADC32ri, X86::ADC32mi, 0 }, + { X86::ADC32ri8, X86::ADC32mi8, 0 }, + { X86::ADC32rr, X86::ADC32mr, 0 }, + { X86::ADC64ri32, X86::ADC64mi32, 0 }, + { X86::ADC64ri8, X86::ADC64mi8, 0 }, + { X86::ADC64rr, X86::ADC64mr, 0 }, + { X86::ADD16ri, X86::ADD16mi, 0 }, + { X86::ADD16ri8, X86::ADD16mi8, 0 }, + { X86::ADD16ri_DB, X86::ADD16mi, TB_NO_REVERSE }, + { X86::ADD16ri8_DB, X86::ADD16mi8, TB_NO_REVERSE }, + { X86::ADD16rr, X86::ADD16mr, 0 }, + { X86::ADD16rr_DB, X86::ADD16mr, TB_NO_REVERSE }, + { X86::ADD32ri, X86::ADD32mi, 0 }, + { X86::ADD32ri8, X86::ADD32mi8, 0 }, + { X86::ADD32ri_DB, X86::ADD32mi, TB_NO_REVERSE }, + { X86::ADD32ri8_DB, X86::ADD32mi8, TB_NO_REVERSE }, + { X86::ADD32rr, X86::ADD32mr, 0 }, + { X86::ADD32rr_DB, X86::ADD32mr, TB_NO_REVERSE }, + { X86::ADD64ri32, X86::ADD64mi32, 0 }, + { X86::ADD64ri8, X86::ADD64mi8, 0 }, + { X86::ADD64ri32_DB,X86::ADD64mi32, TB_NO_REVERSE }, + { X86::ADD64ri8_DB, X86::ADD64mi8, TB_NO_REVERSE }, + { X86::ADD64rr, X86::ADD64mr, 0 }, + { X86::ADD64rr_DB, X86::ADD64mr, TB_NO_REVERSE }, + { X86::ADD8ri, X86::ADD8mi, 0 }, + { X86::ADD8rr, X86::ADD8mr, 0 }, + { X86::AND16ri, X86::AND16mi, 0 }, + { X86::AND16ri8, X86::AND16mi8, 0 }, + { X86::AND16rr, X86::AND16mr, 0 }, + { X86::AND32ri, X86::AND32mi, 0 }, + { X86::AND32ri8, X86::AND32mi8, 0 }, + { X86::AND32rr, X86::AND32mr, 0 }, + { X86::AND64ri32, X86::AND64mi32, 0 }, + { X86::AND64ri8, X86::AND64mi8, 0 }, + { X86::AND64rr, X86::AND64mr, 0 }, + { X86::AND8ri, X86::AND8mi, 0 }, + { X86::AND8rr, X86::AND8mr, 0 }, + { X86::DEC16r, X86::DEC16m, 0 }, + { X86::DEC32r, X86::DEC32m, 0 }, + { X86::DEC64r, X86::DEC64m, 0 }, + { X86::DEC8r, X86::DEC8m, 0 }, + { X86::INC16r, X86::INC16m, 0 }, + { X86::INC32r, X86::INC32m, 0 }, + { X86::INC64r, X86::INC64m, 0 }, + { X86::INC8r, X86::INC8m, 0 }, + { X86::NEG16r, X86::NEG16m, 0 }, + { X86::NEG32r, X86::NEG32m, 0 }, + { X86::NEG64r, X86::NEG64m, 0 }, + { X86::NEG8r, X86::NEG8m, 0 }, + { X86::NOT16r, X86::NOT16m, 0 }, + { X86::NOT32r, X86::NOT32m, 0 }, + { X86::NOT64r, X86::NOT64m, 0 }, + { X86::NOT8r, X86::NOT8m, 0 }, + { X86::OR16ri, X86::OR16mi, 0 }, + { X86::OR16ri8, X86::OR16mi8, 0 }, + { X86::OR16rr, X86::OR16mr, 0 }, + { X86::OR32ri, X86::OR32mi, 0 }, + { X86::OR32ri8, X86::OR32mi8, 0 }, + { X86::OR32rr, X86::OR32mr, 0 }, + { X86::OR64ri32, X86::OR64mi32, 0 }, + { X86::OR64ri8, X86::OR64mi8, 0 }, + { X86::OR64rr, X86::OR64mr, 0 }, + { X86::OR8ri, X86::OR8mi, 0 }, + { X86::OR8rr, X86::OR8mr, 0 }, + { X86::ROL16r1, X86::ROL16m1, 0 }, + { X86::ROL16rCL, X86::ROL16mCL, 0 }, + { X86::ROL16ri, X86::ROL16mi, 0 }, + { X86::ROL32r1, X86::ROL32m1, 0 }, + { X86::ROL32rCL, X86::ROL32mCL, 0 }, + { X86::ROL32ri, X86::ROL32mi, 0 }, + { X86::ROL64r1, X86::ROL64m1, 0 }, + { X86::ROL64rCL, X86::ROL64mCL, 0 }, + { X86::ROL64ri, X86::ROL64mi, 0 }, + { X86::ROL8r1, X86::ROL8m1, 0 }, + { X86::ROL8rCL, X86::ROL8mCL, 0 }, + { X86::ROL8ri, X86::ROL8mi, 0 }, + { X86::ROR16r1, X86::ROR16m1, 0 }, + { X86::ROR16rCL, X86::ROR16mCL, 0 }, + { X86::ROR16ri, X86::ROR16mi, 0 }, + { X86::ROR32r1, X86::ROR32m1, 0 }, + { X86::ROR32rCL, X86::ROR32mCL, 0 }, + { X86::ROR32ri, X86::ROR32mi, 0 }, + { X86::ROR64r1, X86::ROR64m1, 0 }, + { X86::ROR64rCL, X86::ROR64mCL, 0 }, + { X86::ROR64ri, X86::ROR64mi, 0 }, + { X86::ROR8r1, X86::ROR8m1, 0 }, + { X86::ROR8rCL, X86::ROR8mCL, 0 }, + { X86::ROR8ri, X86::ROR8mi, 0 }, + { X86::SAR16r1, X86::SAR16m1, 0 }, + { X86::SAR16rCL, X86::SAR16mCL, 0 }, + { X86::SAR16ri, X86::SAR16mi, 0 }, + { X86::SAR32r1, X86::SAR32m1, 0 }, + { X86::SAR32rCL, X86::SAR32mCL, 0 }, + { X86::SAR32ri, X86::SAR32mi, 0 }, + { X86::SAR64r1, X86::SAR64m1, 0 }, + { X86::SAR64rCL, X86::SAR64mCL, 0 }, + { X86::SAR64ri, X86::SAR64mi, 0 }, + { X86::SAR8r1, X86::SAR8m1, 0 }, + { X86::SAR8rCL, X86::SAR8mCL, 0 }, + { X86::SAR8ri, X86::SAR8mi, 0 }, + { X86::SBB32ri, X86::SBB32mi, 0 }, + { X86::SBB32ri8, X86::SBB32mi8, 0 }, + { X86::SBB32rr, X86::SBB32mr, 0 }, + { X86::SBB64ri32, X86::SBB64mi32, 0 }, + { X86::SBB64ri8, X86::SBB64mi8, 0 }, + { X86::SBB64rr, X86::SBB64mr, 0 }, + { X86::SHL16r1, X86::SHL16m1, 0 }, + { X86::SHL16rCL, X86::SHL16mCL, 0 }, + { X86::SHL16ri, X86::SHL16mi, 0 }, + { X86::SHL32r1, X86::SHL32m1, 0 }, + { X86::SHL32rCL, X86::SHL32mCL, 0 }, + { X86::SHL32ri, X86::SHL32mi, 0 }, + { X86::SHL64r1, X86::SHL64m1, 0 }, + { X86::SHL64rCL, X86::SHL64mCL, 0 }, + { X86::SHL64ri, X86::SHL64mi, 0 }, + { X86::SHL8r1, X86::SHL8m1, 0 }, + { X86::SHL8rCL, X86::SHL8mCL, 0 }, + { X86::SHL8ri, X86::SHL8mi, 0 }, + { X86::SHLD16rrCL, X86::SHLD16mrCL, 0 }, + { X86::SHLD16rri8, X86::SHLD16mri8, 0 }, + { X86::SHLD32rrCL, X86::SHLD32mrCL, 0 }, + { X86::SHLD32rri8, X86::SHLD32mri8, 0 }, + { X86::SHLD64rrCL, X86::SHLD64mrCL, 0 }, + { X86::SHLD64rri8, X86::SHLD64mri8, 0 }, + { X86::SHR16r1, X86::SHR16m1, 0 }, + { X86::SHR16rCL, X86::SHR16mCL, 0 }, + { X86::SHR16ri, X86::SHR16mi, 0 }, + { X86::SHR32r1, X86::SHR32m1, 0 }, + { X86::SHR32rCL, X86::SHR32mCL, 0 }, + { X86::SHR32ri, X86::SHR32mi, 0 }, + { X86::SHR64r1, X86::SHR64m1, 0 }, + { X86::SHR64rCL, X86::SHR64mCL, 0 }, + { X86::SHR64ri, X86::SHR64mi, 0 }, + { X86::SHR8r1, X86::SHR8m1, 0 }, + { X86::SHR8rCL, X86::SHR8mCL, 0 }, + { X86::SHR8ri, X86::SHR8mi, 0 }, + { X86::SHRD16rrCL, X86::SHRD16mrCL, 0 }, + { X86::SHRD16rri8, X86::SHRD16mri8, 0 }, + { X86::SHRD32rrCL, X86::SHRD32mrCL, 0 }, + { X86::SHRD32rri8, X86::SHRD32mri8, 0 }, + { X86::SHRD64rrCL, X86::SHRD64mrCL, 0 }, + { X86::SHRD64rri8, X86::SHRD64mri8, 0 }, + { X86::SUB16ri, X86::SUB16mi, 0 }, + { X86::SUB16ri8, X86::SUB16mi8, 0 }, + { X86::SUB16rr, X86::SUB16mr, 0 }, + { X86::SUB32ri, X86::SUB32mi, 0 }, + { X86::SUB32ri8, X86::SUB32mi8, 0 }, + { X86::SUB32rr, X86::SUB32mr, 0 }, + { X86::SUB64ri32, X86::SUB64mi32, 0 }, + { X86::SUB64ri8, X86::SUB64mi8, 0 }, + { X86::SUB64rr, X86::SUB64mr, 0 }, + { X86::SUB8ri, X86::SUB8mi, 0 }, + { X86::SUB8rr, X86::SUB8mr, 0 }, + { X86::XOR16ri, X86::XOR16mi, 0 }, + { X86::XOR16ri8, X86::XOR16mi8, 0 }, + { X86::XOR16rr, X86::XOR16mr, 0 }, + { X86::XOR32ri, X86::XOR32mi, 0 }, + { X86::XOR32ri8, X86::XOR32mi8, 0 }, + { X86::XOR32rr, X86::XOR32mr, 0 }, + { X86::XOR64ri32, X86::XOR64mi32, 0 }, + { X86::XOR64ri8, X86::XOR64mi8, 0 }, + { X86::XOR64rr, X86::XOR64mr, 0 }, + { X86::XOR8ri, X86::XOR8mi, 0 }, + { X86::XOR8rr, X86::XOR8mr, 0 } + }; for (X86MemoryFoldTableEntry Entry : MemoryFoldTable2Addr) { AddTableEntry(RegOp2MemOpTable2Addr, MemOp2RegOpTable, @@ -131,11 +295,746 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI) Entry.Flags | TB_INDEX_0 | TB_FOLDED_LOAD | TB_FOLDED_STORE); } + static const X86MemoryFoldTableEntry MemoryFoldTable0[] = { + { X86::BT16ri8, X86::BT16mi8, TB_FOLDED_LOAD }, + { X86::BT32ri8, X86::BT32mi8, TB_FOLDED_LOAD }, + { X86::BT64ri8, X86::BT64mi8, TB_FOLDED_LOAD }, + { X86::CALL32r, X86::CALL32m, TB_FOLDED_LOAD }, + { X86::CALL64r, X86::CALL64m, TB_FOLDED_LOAD }, + { X86::CMP16ri, X86::CMP16mi, TB_FOLDED_LOAD }, + { X86::CMP16ri8, X86::CMP16mi8, TB_FOLDED_LOAD }, + { X86::CMP16rr, X86::CMP16mr, TB_FOLDED_LOAD }, + { X86::CMP32ri, X86::CMP32mi, TB_FOLDED_LOAD }, + { X86::CMP32ri8, X86::CMP32mi8, TB_FOLDED_LOAD }, + { X86::CMP32rr, X86::CMP32mr, TB_FOLDED_LOAD }, + { X86::CMP64ri32, X86::CMP64mi32, TB_FOLDED_LOAD }, + { X86::CMP64ri8, X86::CMP64mi8, TB_FOLDED_LOAD }, + { X86::CMP64rr, X86::CMP64mr, TB_FOLDED_LOAD }, + { X86::CMP8ri, X86::CMP8mi, TB_FOLDED_LOAD }, + { X86::CMP8rr, X86::CMP8mr, TB_FOLDED_LOAD }, + { X86::DIV16r, X86::DIV16m, TB_FOLDED_LOAD }, + { X86::DIV32r, X86::DIV32m, TB_FOLDED_LOAD }, + { X86::DIV64r, X86::DIV64m, TB_FOLDED_LOAD }, + { X86::DIV8r, X86::DIV8m, TB_FOLDED_LOAD }, + { X86::EXTRACTPSrr, X86::EXTRACTPSmr, TB_FOLDED_STORE }, + { X86::IDIV16r, X86::IDIV16m, TB_FOLDED_LOAD }, + { X86::IDIV32r, X86::IDIV32m, TB_FOLDED_LOAD }, + { X86::IDIV64r, X86::IDIV64m, TB_FOLDED_LOAD }, + { X86::IDIV8r, X86::IDIV8m, TB_FOLDED_LOAD }, + { X86::IMUL16r, X86::IMUL16m, TB_FOLDED_LOAD }, + { X86::IMUL32r, X86::IMUL32m, TB_FOLDED_LOAD }, + { X86::IMUL64r, X86::IMUL64m, TB_FOLDED_LOAD }, + { X86::IMUL8r, X86::IMUL8m, TB_FOLDED_LOAD }, + { X86::JMP32r, X86::JMP32m, TB_FOLDED_LOAD }, + { X86::JMP64r, X86::JMP64m, TB_FOLDED_LOAD }, + { X86::MOV16ri, X86::MOV16mi, TB_FOLDED_STORE }, + { X86::MOV16rr, X86::MOV16mr, TB_FOLDED_STORE }, + { X86::MOV32ri, X86::MOV32mi, TB_FOLDED_STORE }, + { X86::MOV32rr, X86::MOV32mr, TB_FOLDED_STORE }, + { X86::MOV64ri32, X86::MOV64mi32, TB_FOLDED_STORE }, + { X86::MOV64rr, X86::MOV64mr, TB_FOLDED_STORE }, + { X86::MOV8ri, X86::MOV8mi, TB_FOLDED_STORE }, + { X86::MOV8rr, X86::MOV8mr, TB_FOLDED_STORE }, + { X86::MOV8rr_NOREX, X86::MOV8mr_NOREX, TB_FOLDED_STORE }, + { X86::MOVAPDrr, X86::MOVAPDmr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::MOVAPSrr, X86::MOVAPSmr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::MOVDQArr, X86::MOVDQAmr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::MOVDQUrr, X86::MOVDQUmr, TB_FOLDED_STORE }, + { X86::MOVPDI2DIrr, X86::MOVPDI2DImr, TB_FOLDED_STORE }, + { X86::MOVPQIto64rr,X86::MOVPQI2QImr, TB_FOLDED_STORE }, + { X86::MOVSDto64rr, X86::MOVSDto64mr, TB_FOLDED_STORE }, + { X86::MOVSS2DIrr, X86::MOVSS2DImr, TB_FOLDED_STORE }, + { X86::MOVUPDrr, X86::MOVUPDmr, TB_FOLDED_STORE }, + { X86::MOVUPSrr, X86::MOVUPSmr, TB_FOLDED_STORE }, + { X86::MUL16r, X86::MUL16m, TB_FOLDED_LOAD }, + { X86::MUL32r, X86::MUL32m, TB_FOLDED_LOAD }, + { X86::MUL64r, X86::MUL64m, TB_FOLDED_LOAD }, + { X86::MUL8r, X86::MUL8m, TB_FOLDED_LOAD }, + { X86::PEXTRDrr, X86::PEXTRDmr, TB_FOLDED_STORE }, + { X86::PEXTRQrr, X86::PEXTRQmr, TB_FOLDED_STORE }, + { X86::PUSH16r, X86::PUSH16rmm, TB_FOLDED_LOAD }, + { X86::PUSH32r, X86::PUSH32rmm, TB_FOLDED_LOAD }, + { X86::PUSH64r, X86::PUSH64rmm, TB_FOLDED_LOAD }, + { X86::SETAEr, X86::SETAEm, TB_FOLDED_STORE }, + { X86::SETAr, X86::SETAm, TB_FOLDED_STORE }, + { X86::SETBEr, X86::SETBEm, TB_FOLDED_STORE }, + { X86::SETBr, X86::SETBm, TB_FOLDED_STORE }, + { X86::SETEr, X86::SETEm, TB_FOLDED_STORE }, + { X86::SETGEr, X86::SETGEm, TB_FOLDED_STORE }, + { X86::SETGr, X86::SETGm, TB_FOLDED_STORE }, + { X86::SETLEr, X86::SETLEm, TB_FOLDED_STORE }, + { X86::SETLr, X86::SETLm, TB_FOLDED_STORE }, + { X86::SETNEr, X86::SETNEm, TB_FOLDED_STORE }, + { X86::SETNOr, X86::SETNOm, TB_FOLDED_STORE }, + { X86::SETNPr, X86::SETNPm, TB_FOLDED_STORE }, + { X86::SETNSr, X86::SETNSm, TB_FOLDED_STORE }, + { X86::SETOr, X86::SETOm, TB_FOLDED_STORE }, + { X86::SETPr, X86::SETPm, TB_FOLDED_STORE }, + { X86::SETSr, X86::SETSm, TB_FOLDED_STORE }, + { X86::TAILJMPr, X86::TAILJMPm, TB_FOLDED_LOAD }, + { X86::TAILJMPr64, X86::TAILJMPm64, TB_FOLDED_LOAD }, + { X86::TAILJMPr64_REX, X86::TAILJMPm64_REX, TB_FOLDED_LOAD }, + { X86::TEST16ri, X86::TEST16mi, TB_FOLDED_LOAD }, + { X86::TEST32ri, X86::TEST32mi, TB_FOLDED_LOAD }, + { X86::TEST64ri32, X86::TEST64mi32, TB_FOLDED_LOAD }, + { X86::TEST8ri, X86::TEST8mi, TB_FOLDED_LOAD }, + + // AVX 128-bit versions of foldable instructions + { X86::VEXTRACTPSrr,X86::VEXTRACTPSmr, TB_FOLDED_STORE }, + { X86::VEXTRACTF128rr, X86::VEXTRACTF128mr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::VMOVAPDrr, X86::VMOVAPDmr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::VMOVAPSrr, X86::VMOVAPSmr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::VMOVDQArr, X86::VMOVDQAmr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::VMOVDQUrr, X86::VMOVDQUmr, TB_FOLDED_STORE }, + { X86::VMOVPDI2DIrr,X86::VMOVPDI2DImr, TB_FOLDED_STORE }, + { X86::VMOVPQIto64rr, X86::VMOVPQI2QImr,TB_FOLDED_STORE }, + { X86::VMOVSDto64rr,X86::VMOVSDto64mr, TB_FOLDED_STORE }, + { X86::VMOVSS2DIrr, X86::VMOVSS2DImr, TB_FOLDED_STORE }, + { X86::VMOVUPDrr, X86::VMOVUPDmr, TB_FOLDED_STORE }, + { X86::VMOVUPSrr, X86::VMOVUPSmr, TB_FOLDED_STORE }, + { X86::VPEXTRDrr, X86::VPEXTRDmr, TB_FOLDED_STORE }, + { X86::VPEXTRQrr, X86::VPEXTRQmr, TB_FOLDED_STORE }, + + // AVX 256-bit foldable instructions + { X86::VEXTRACTI128rr, X86::VEXTRACTI128mr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::VMOVAPDYrr, X86::VMOVAPDYmr, TB_FOLDED_STORE | TB_ALIGN_32 }, + { X86::VMOVAPSYrr, X86::VMOVAPSYmr, TB_FOLDED_STORE | TB_ALIGN_32 }, + { X86::VMOVDQAYrr, X86::VMOVDQAYmr, TB_FOLDED_STORE | TB_ALIGN_32 }, + { X86::VMOVDQUYrr, X86::VMOVDQUYmr, TB_FOLDED_STORE }, + { X86::VMOVUPDYrr, X86::VMOVUPDYmr, TB_FOLDED_STORE }, + { X86::VMOVUPSYrr, X86::VMOVUPSYmr, TB_FOLDED_STORE }, + + // AVX-512 foldable instructions + { X86::VEXTRACTF32x4Zrr,X86::VEXTRACTF32x4Zmr, TB_FOLDED_STORE }, + { X86::VEXTRACTF32x8Zrr,X86::VEXTRACTF32x8Zmr, TB_FOLDED_STORE }, + { X86::VEXTRACTF64x2Zrr,X86::VEXTRACTF64x2Zmr, TB_FOLDED_STORE }, + { X86::VEXTRACTF64x4Zrr,X86::VEXTRACTF64x4Zmr, TB_FOLDED_STORE }, + { X86::VEXTRACTI32x4Zrr,X86::VEXTRACTI32x4Zmr, TB_FOLDED_STORE }, + { X86::VEXTRACTI32x8Zrr,X86::VEXTRACTI32x8Zmr, TB_FOLDED_STORE }, + { X86::VEXTRACTI64x2Zrr,X86::VEXTRACTI64x2Zmr, TB_FOLDED_STORE }, + { X86::VEXTRACTI64x4Zrr,X86::VEXTRACTI64x4Zmr, TB_FOLDED_STORE }, + { X86::VEXTRACTPSZrr, X86::VEXTRACTPSZmr, TB_FOLDED_STORE }, + { X86::VMOVAPDZrr, X86::VMOVAPDZmr, TB_FOLDED_STORE | TB_ALIGN_64 }, + { X86::VMOVAPSZrr, X86::VMOVAPSZmr, TB_FOLDED_STORE | TB_ALIGN_64 }, + { X86::VMOVDQA32Zrr, X86::VMOVDQA32Zmr, TB_FOLDED_STORE | TB_ALIGN_64 }, + { X86::VMOVDQA64Zrr, X86::VMOVDQA64Zmr, TB_FOLDED_STORE | TB_ALIGN_64 }, + { X86::VMOVDQU8Zrr, X86::VMOVDQU8Zmr, TB_FOLDED_STORE }, + { X86::VMOVDQU16Zrr, X86::VMOVDQU16Zmr, TB_FOLDED_STORE }, + { X86::VMOVDQU32Zrr, X86::VMOVDQU32Zmr, TB_FOLDED_STORE }, + { X86::VMOVDQU64Zrr, X86::VMOVDQU64Zmr, TB_FOLDED_STORE }, + { X86::VMOVPDI2DIZrr, X86::VMOVPDI2DIZmr, TB_FOLDED_STORE }, + { X86::VMOVPQIto64Zrr, X86::VMOVPQI2QIZmr, TB_FOLDED_STORE }, + { X86::VMOVSDto64Zrr, X86::VMOVSDto64Zmr, TB_FOLDED_STORE }, + { X86::VMOVSS2DIZrr, X86::VMOVSS2DIZmr, TB_FOLDED_STORE }, + { X86::VMOVUPDZrr, X86::VMOVUPDZmr, TB_FOLDED_STORE }, + { X86::VMOVUPSZrr, X86::VMOVUPSZmr, TB_FOLDED_STORE }, + { X86::VPEXTRDZrr, X86::VPEXTRDZmr, TB_FOLDED_STORE }, + { X86::VPEXTRQZrr, X86::VPEXTRQZmr, TB_FOLDED_STORE }, + { X86::VPMOVDBZrr, X86::VPMOVDBZmr, TB_FOLDED_STORE }, + { X86::VPMOVDWZrr, X86::VPMOVDWZmr, TB_FOLDED_STORE }, + { X86::VPMOVQDZrr, X86::VPMOVQDZmr, TB_FOLDED_STORE }, + { X86::VPMOVQWZrr, X86::VPMOVQWZmr, TB_FOLDED_STORE }, + { X86::VPMOVWBZrr, X86::VPMOVWBZmr, TB_FOLDED_STORE }, + { X86::VPMOVSDBZrr, X86::VPMOVSDBZmr, TB_FOLDED_STORE }, + { X86::VPMOVSDWZrr, X86::VPMOVSDWZmr, TB_FOLDED_STORE }, + { X86::VPMOVSQDZrr, X86::VPMOVSQDZmr, TB_FOLDED_STORE }, + { X86::VPMOVSQWZrr, X86::VPMOVSQWZmr, TB_FOLDED_STORE }, + { X86::VPMOVSWBZrr, X86::VPMOVSWBZmr, TB_FOLDED_STORE }, + { X86::VPMOVUSDBZrr, X86::VPMOVUSDBZmr, TB_FOLDED_STORE }, + { X86::VPMOVUSDWZrr, X86::VPMOVUSDWZmr, TB_FOLDED_STORE }, + { X86::VPMOVUSQDZrr, X86::VPMOVUSQDZmr, TB_FOLDED_STORE }, + { X86::VPMOVUSQWZrr, X86::VPMOVUSQWZmr, TB_FOLDED_STORE }, + { X86::VPMOVUSWBZrr, X86::VPMOVUSWBZmr, TB_FOLDED_STORE }, + + // AVX-512 foldable instructions (256-bit versions) + { X86::VEXTRACTF32x4Z256rr,X86::VEXTRACTF32x4Z256mr, TB_FOLDED_STORE }, + { X86::VEXTRACTF64x2Z256rr,X86::VEXTRACTF64x2Z256mr, TB_FOLDED_STORE }, + { X86::VEXTRACTI32x4Z256rr,X86::VEXTRACTI32x4Z256mr, TB_FOLDED_STORE }, + { X86::VEXTRACTI64x2Z256rr,X86::VEXTRACTI64x2Z256mr, TB_FOLDED_STORE }, + { X86::VMOVAPDZ256rr, X86::VMOVAPDZ256mr, TB_FOLDED_STORE | TB_ALIGN_32 }, + { X86::VMOVAPSZ256rr, X86::VMOVAPSZ256mr, TB_FOLDED_STORE | TB_ALIGN_32 }, + { X86::VMOVDQA32Z256rr, X86::VMOVDQA32Z256mr, TB_FOLDED_STORE | TB_ALIGN_32 }, + { X86::VMOVDQA64Z256rr, X86::VMOVDQA64Z256mr, TB_FOLDED_STORE | TB_ALIGN_32 }, + { X86::VMOVUPDZ256rr, X86::VMOVUPDZ256mr, TB_FOLDED_STORE }, + { X86::VMOVUPSZ256rr, X86::VMOVUPSZ256mr, TB_FOLDED_STORE }, + { X86::VMOVDQU8Z256rr, X86::VMOVDQU8Z256mr, TB_FOLDED_STORE }, + { X86::VMOVDQU16Z256rr, X86::VMOVDQU16Z256mr, TB_FOLDED_STORE }, + { X86::VMOVDQU32Z256rr, X86::VMOVDQU32Z256mr, TB_FOLDED_STORE }, + { X86::VMOVDQU64Z256rr, X86::VMOVDQU64Z256mr, TB_FOLDED_STORE }, + { X86::VPMOVDWZ256rr, X86::VPMOVDWZ256mr, TB_FOLDED_STORE }, + { X86::VPMOVQDZ256rr, X86::VPMOVQDZ256mr, TB_FOLDED_STORE }, + { X86::VPMOVWBZ256rr, X86::VPMOVWBZ256mr, TB_FOLDED_STORE }, + { X86::VPMOVSDWZ256rr, X86::VPMOVSDWZ256mr, TB_FOLDED_STORE }, + { X86::VPMOVSQDZ256rr, X86::VPMOVSQDZ256mr, TB_FOLDED_STORE }, + { X86::VPMOVSWBZ256rr, X86::VPMOVSWBZ256mr, TB_FOLDED_STORE }, + { X86::VPMOVUSDWZ256rr, X86::VPMOVUSDWZ256mr, TB_FOLDED_STORE }, + { X86::VPMOVUSQDZ256rr, X86::VPMOVUSQDZ256mr, TB_FOLDED_STORE }, + { X86::VPMOVUSWBZ256rr, X86::VPMOVUSWBZ256mr, TB_FOLDED_STORE }, + + // AVX-512 foldable instructions (128-bit versions) + { X86::VMOVAPDZ128rr, X86::VMOVAPDZ128mr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::VMOVAPSZ128rr, X86::VMOVAPSZ128mr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::VMOVDQA32Z128rr, X86::VMOVDQA32Z128mr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::VMOVDQA64Z128rr, X86::VMOVDQA64Z128mr, TB_FOLDED_STORE | TB_ALIGN_16 }, + { X86::VMOVUPDZ128rr, X86::VMOVUPDZ128mr, TB_FOLDED_STORE }, + { X86::VMOVUPSZ128rr, X86::VMOVUPSZ128mr, TB_FOLDED_STORE }, + { X86::VMOVDQU8Z128rr, X86::VMOVDQU8Z128mr, TB_FOLDED_STORE }, + { X86::VMOVDQU16Z128rr, X86::VMOVDQU16Z128mr, TB_FOLDED_STORE }, + { X86::VMOVDQU32Z128rr, X86::VMOVDQU32Z128mr, TB_FOLDED_STORE }, + { X86::VMOVDQU64Z128rr, X86::VMOVDQU64Z128mr, TB_FOLDED_STORE }, + + // F16C foldable instructions + { X86::VCVTPS2PHrr, X86::VCVTPS2PHmr, TB_FOLDED_STORE }, + { X86::VCVTPS2PHYrr, X86::VCVTPS2PHYmr, TB_FOLDED_STORE } + }; + for (X86MemoryFoldTableEntry Entry : MemoryFoldTable0) { AddTableEntry(RegOp2MemOpTable0, MemOp2RegOpTable, Entry.RegOp, Entry.MemOp, TB_INDEX_0 | Entry.Flags); } + static const X86MemoryFoldTableEntry MemoryFoldTable1[] = { + { X86::BSF16rr, X86::BSF16rm, 0 }, + { X86::BSF32rr, X86::BSF32rm, 0 }, + { X86::BSF64rr, X86::BSF64rm, 0 }, + { X86::BSR16rr, X86::BSR16rm, 0 }, + { X86::BSR32rr, X86::BSR32rm, 0 }, + { X86::BSR64rr, X86::BSR64rm, 0 }, + { X86::CMP16rr, X86::CMP16rm, 0 }, + { X86::CMP32rr, X86::CMP32rm, 0 }, + { X86::CMP64rr, X86::CMP64rm, 0 }, + { X86::CMP8rr, X86::CMP8rm, 0 }, + { X86::CVTSD2SSrr, X86::CVTSD2SSrm, 0 }, + { X86::CVTSI2SD64rr, X86::CVTSI2SD64rm, 0 }, + { X86::CVTSI2SDrr, X86::CVTSI2SDrm, 0 }, + { X86::CVTSI2SS64rr, X86::CVTSI2SS64rm, 0 }, + { X86::CVTSI2SSrr, X86::CVTSI2SSrm, 0 }, + { X86::CVTSS2SDrr, X86::CVTSS2SDrm, 0 }, + { X86::CVTTSD2SI64rr, X86::CVTTSD2SI64rm, 0 }, + { X86::CVTTSD2SIrr, X86::CVTTSD2SIrm, 0 }, + { X86::CVTTSS2SI64rr, X86::CVTTSS2SI64rm, 0 }, + { X86::CVTTSS2SIrr, X86::CVTTSS2SIrm, 0 }, + { X86::IMUL16rri, X86::IMUL16rmi, 0 }, + { X86::IMUL16rri8, X86::IMUL16rmi8, 0 }, + { X86::IMUL32rri, X86::IMUL32rmi, 0 }, + { X86::IMUL32rri8, X86::IMUL32rmi8, 0 }, + { X86::IMUL64rri32, X86::IMUL64rmi32, 0 }, + { X86::IMUL64rri8, X86::IMUL64rmi8, 0 }, + { X86::Int_COMISDrr, X86::Int_COMISDrm, TB_NO_REVERSE }, + { X86::Int_COMISSrr, X86::Int_COMISSrm, TB_NO_REVERSE }, + { X86::CVTSD2SI64rr, X86::CVTSD2SI64rm, TB_NO_REVERSE }, + { X86::CVTSD2SIrr, X86::CVTSD2SIrm, TB_NO_REVERSE }, + { X86::CVTSS2SI64rr, X86::CVTSS2SI64rm, TB_NO_REVERSE }, + { X86::CVTSS2SIrr, X86::CVTSS2SIrm, TB_NO_REVERSE }, + { X86::CVTDQ2PDrr, X86::CVTDQ2PDrm, TB_NO_REVERSE }, + { X86::CVTDQ2PSrr, X86::CVTDQ2PSrm, TB_ALIGN_16 }, + { X86::CVTPD2DQrr, X86::CVTPD2DQrm, TB_ALIGN_16 }, + { X86::CVTPD2PSrr, X86::CVTPD2PSrm, TB_ALIGN_16 }, + { X86::CVTPS2DQrr, X86::CVTPS2DQrm, TB_ALIGN_16 }, + { X86::CVTPS2PDrr, X86::CVTPS2PDrm, TB_NO_REVERSE }, + { X86::CVTTPD2DQrr, X86::CVTTPD2DQrm, TB_ALIGN_16 }, + { X86::CVTTPS2DQrr, X86::CVTTPS2DQrm, TB_ALIGN_16 }, + { X86::Int_CVTTSD2SI64rr,X86::Int_CVTTSD2SI64rm, TB_NO_REVERSE }, + { X86::Int_CVTTSD2SIrr, X86::Int_CVTTSD2SIrm, TB_NO_REVERSE }, + { X86::Int_CVTTSS2SI64rr,X86::Int_CVTTSS2SI64rm, TB_NO_REVERSE }, + { X86::Int_CVTTSS2SIrr, X86::Int_CVTTSS2SIrm, TB_NO_REVERSE }, + { X86::Int_UCOMISDrr, X86::Int_UCOMISDrm, TB_NO_REVERSE }, + { X86::Int_UCOMISSrr, X86::Int_UCOMISSrm, TB_NO_REVERSE }, + { X86::MOV16rr, X86::MOV16rm, 0 }, + { X86::MOV32rr, X86::MOV32rm, 0 }, + { X86::MOV64rr, X86::MOV64rm, 0 }, + { X86::MOV64toPQIrr, X86::MOVQI2PQIrm, 0 }, + { X86::MOV64toSDrr, X86::MOV64toSDrm, 0 }, + { X86::MOV8rr, X86::MOV8rm, 0 }, + { X86::MOVAPDrr, X86::MOVAPDrm, TB_ALIGN_16 }, + { X86::MOVAPSrr, X86::MOVAPSrm, TB_ALIGN_16 }, + { X86::MOVDDUPrr, X86::MOVDDUPrm, TB_NO_REVERSE }, + { X86::MOVDI2PDIrr, X86::MOVDI2PDIrm, 0 }, + { X86::MOVDI2SSrr, X86::MOVDI2SSrm, 0 }, + { X86::MOVDQArr, X86::MOVDQArm, TB_ALIGN_16 }, + { X86::MOVDQUrr, X86::MOVDQUrm, 0 }, + { X86::MOVSHDUPrr, X86::MOVSHDUPrm, TB_ALIGN_16 }, + { X86::MOVSLDUPrr, X86::MOVSLDUPrm, TB_ALIGN_16 }, + { X86::MOVSX16rr8, X86::MOVSX16rm8, 0 }, + { X86::MOVSX32rr16, X86::MOVSX32rm16, 0 }, + { X86::MOVSX32rr8, X86::MOVSX32rm8, 0 }, + { X86::MOVSX64rr16, X86::MOVSX64rm16, 0 }, + { X86::MOVSX64rr32, X86::MOVSX64rm32, 0 }, + { X86::MOVSX64rr8, X86::MOVSX64rm8, 0 }, + { X86::MOVUPDrr, X86::MOVUPDrm, 0 }, + { X86::MOVUPSrr, X86::MOVUPSrm, 0 }, + { X86::MOVZPQILo2PQIrr, X86::MOVQI2PQIrm, TB_NO_REVERSE }, + { X86::MOVZX16rr8, X86::MOVZX16rm8, 0 }, + { X86::MOVZX32rr16, X86::MOVZX32rm16, 0 }, + { X86::MOVZX32_NOREXrr8, X86::MOVZX32_NOREXrm8, 0 }, + { X86::MOVZX32rr8, X86::MOVZX32rm8, 0 }, + { X86::PABSBrr, X86::PABSBrm, TB_ALIGN_16 }, + { X86::PABSDrr, X86::PABSDrm, TB_ALIGN_16 }, + { X86::PABSWrr, X86::PABSWrm, TB_ALIGN_16 }, + { X86::PCMPESTRIrr, X86::PCMPESTRIrm, TB_ALIGN_16 }, + { X86::PCMPESTRM128rr, X86::PCMPESTRM128rm, TB_ALIGN_16 }, + { X86::PCMPISTRIrr, X86::PCMPISTRIrm, TB_ALIGN_16 }, + { X86::PCMPISTRM128rr, X86::PCMPISTRM128rm, TB_ALIGN_16 }, + { X86::PHMINPOSUWrr128, X86::PHMINPOSUWrm128, TB_ALIGN_16 }, + { X86::PMOVSXBDrr, X86::PMOVSXBDrm, TB_NO_REVERSE }, + { X86::PMOVSXBQrr, X86::PMOVSXBQrm, TB_NO_REVERSE }, + { X86::PMOVSXBWrr, X86::PMOVSXBWrm, TB_NO_REVERSE }, + { X86::PMOVSXDQrr, X86::PMOVSXDQrm, TB_NO_REVERSE }, + { X86::PMOVSXWDrr, X86::PMOVSXWDrm, TB_NO_REVERSE }, + { X86::PMOVSXWQrr, X86::PMOVSXWQrm, TB_NO_REVERSE }, + { X86::PMOVZXBDrr, X86::PMOVZXBDrm, TB_NO_REVERSE }, + { X86::PMOVZXBQrr, X86::PMOVZXBQrm, TB_NO_REVERSE }, + { X86::PMOVZXBWrr, X86::PMOVZXBWrm, TB_NO_REVERSE }, + { X86::PMOVZXDQrr, X86::PMOVZXDQrm, TB_NO_REVERSE }, + { X86::PMOVZXWDrr, X86::PMOVZXWDrm, TB_NO_REVERSE }, + { X86::PMOVZXWQrr, X86::PMOVZXWQrm, TB_NO_REVERSE }, + { X86::PSHUFDri, X86::PSHUFDmi, TB_ALIGN_16 }, + { X86::PSHUFHWri, X86::PSHUFHWmi, TB_ALIGN_16 }, + { X86::PSHUFLWri, X86::PSHUFLWmi, TB_ALIGN_16 }, + { X86::PTESTrr, X86::PTESTrm, TB_ALIGN_16 }, + { X86::RCPPSr, X86::RCPPSm, TB_ALIGN_16 }, + { X86::RCPSSr, X86::RCPSSm, 0 }, + { X86::RCPSSr_Int, X86::RCPSSm_Int, TB_NO_REVERSE }, + { X86::ROUNDPDr, X86::ROUNDPDm, TB_ALIGN_16 }, + { X86::ROUNDPSr, X86::ROUNDPSm, TB_ALIGN_16 }, + { X86::ROUNDSDr, X86::ROUNDSDm, 0 }, + { X86::ROUNDSSr, X86::ROUNDSSm, 0 }, + { X86::RSQRTPSr, X86::RSQRTPSm, TB_ALIGN_16 }, + { X86::RSQRTSSr, X86::RSQRTSSm, 0 }, + { X86::RSQRTSSr_Int, X86::RSQRTSSm_Int, TB_NO_REVERSE }, + { X86::SQRTPDr, X86::SQRTPDm, TB_ALIGN_16 }, + { X86::SQRTPSr, X86::SQRTPSm, TB_ALIGN_16 }, + { X86::SQRTSDr, X86::SQRTSDm, 0 }, + { X86::SQRTSDr_Int, X86::SQRTSDm_Int, TB_NO_REVERSE }, + { X86::SQRTSSr, X86::SQRTSSm, 0 }, + { X86::SQRTSSr_Int, X86::SQRTSSm_Int, TB_NO_REVERSE }, + { X86::TEST16rr, X86::TEST16rm, 0 }, + { X86::TEST32rr, X86::TEST32rm, 0 }, + { X86::TEST64rr, X86::TEST64rm, 0 }, + { X86::TEST8rr, X86::TEST8rm, 0 }, + // FIXME: TEST*rr EAX,EAX ---> CMP [mem], 0 + { X86::UCOMISDrr, X86::UCOMISDrm, 0 }, + { X86::UCOMISSrr, X86::UCOMISSrm, 0 }, + + // MMX version of foldable instructions + { X86::MMX_CVTPD2PIirr, X86::MMX_CVTPD2PIirm, 0 }, + { X86::MMX_CVTPI2PDirr, X86::MMX_CVTPI2PDirm, 0 }, + { X86::MMX_CVTPS2PIirr, X86::MMX_CVTPS2PIirm, 0 }, + { X86::MMX_CVTTPD2PIirr, X86::MMX_CVTTPD2PIirm, 0 }, + { X86::MMX_CVTTPS2PIirr, X86::MMX_CVTTPS2PIirm, 0 }, + { X86::MMX_MOVD64to64rr, X86::MMX_MOVQ64rm, 0 }, + { X86::MMX_PABSBrr64, X86::MMX_PABSBrm64, 0 }, + { X86::MMX_PABSDrr64, X86::MMX_PABSDrm64, 0 }, + { X86::MMX_PABSWrr64, X86::MMX_PABSWrm64, 0 }, + { X86::MMX_PSHUFWri, X86::MMX_PSHUFWmi, 0 }, + + // 3DNow! version of foldable instructions + { X86::PF2IDrr, X86::PF2IDrm, 0 }, + { X86::PF2IWrr, X86::PF2IWrm, 0 }, + { X86::PFRCPrr, X86::PFRCPrm, 0 }, + { X86::PFRSQRTrr, X86::PFRSQRTrm, 0 }, + { X86::PI2FDrr, X86::PI2FDrm, 0 }, + { X86::PI2FWrr, X86::PI2FWrm, 0 }, + { X86::PSWAPDrr, X86::PSWAPDrm, 0 }, + + // AVX 128-bit versions of foldable instructions + { X86::Int_VCOMISDrr, X86::Int_VCOMISDrm, TB_NO_REVERSE }, + { X86::Int_VCOMISSrr, X86::Int_VCOMISSrm, TB_NO_REVERSE }, + { X86::Int_VUCOMISDrr, X86::Int_VUCOMISDrm, TB_NO_REVERSE }, + { X86::Int_VUCOMISSrr, X86::Int_VUCOMISSrm, TB_NO_REVERSE }, + { X86::VCVTTSD2SI64rr, X86::VCVTTSD2SI64rm, 0 }, + { X86::Int_VCVTTSD2SI64rr,X86::Int_VCVTTSD2SI64rm,TB_NO_REVERSE }, + { X86::VCVTTSD2SIrr, X86::VCVTTSD2SIrm, 0 }, + { X86::Int_VCVTTSD2SIrr,X86::Int_VCVTTSD2SIrm, TB_NO_REVERSE }, + { X86::VCVTTSS2SI64rr, X86::VCVTTSS2SI64rm, 0 }, + { X86::Int_VCVTTSS2SI64rr,X86::Int_VCVTTSS2SI64rm,TB_NO_REVERSE }, + { X86::VCVTTSS2SIrr, X86::VCVTTSS2SIrm, 0 }, + { X86::Int_VCVTTSS2SIrr,X86::Int_VCVTTSS2SIrm, TB_NO_REVERSE }, + { X86::VCVTSD2SI64rr, X86::VCVTSD2SI64rm, TB_NO_REVERSE }, + { X86::VCVTSD2SIrr, X86::VCVTSD2SIrm, TB_NO_REVERSE }, + { X86::VCVTSS2SI64rr, X86::VCVTSS2SI64rm, TB_NO_REVERSE }, + { X86::VCVTSS2SIrr, X86::VCVTSS2SIrm, TB_NO_REVERSE }, + { X86::VCVTDQ2PDrr, X86::VCVTDQ2PDrm, TB_NO_REVERSE }, + { X86::VCVTDQ2PSrr, X86::VCVTDQ2PSrm, 0 }, + { X86::VCVTPD2DQrr, X86::VCVTPD2DQrm, 0 }, + { X86::VCVTPD2PSrr, X86::VCVTPD2PSrm, 0 }, + { X86::VCVTPS2DQrr, X86::VCVTPS2DQrm, 0 }, + { X86::VCVTPS2PDrr, X86::VCVTPS2PDrm, TB_NO_REVERSE }, + { X86::VCVTTPD2DQrr, X86::VCVTTPD2DQrm, 0 }, + { X86::VCVTTPS2DQrr, X86::VCVTTPS2DQrm, 0 }, + { X86::VMOV64toPQIrr, X86::VMOVQI2PQIrm, 0 }, + { X86::VMOV64toSDrr, X86::VMOV64toSDrm, 0 }, + { X86::VMOVAPDrr, X86::VMOVAPDrm, TB_ALIGN_16 }, + { X86::VMOVAPSrr, X86::VMOVAPSrm, TB_ALIGN_16 }, + { X86::VMOVDDUPrr, X86::VMOVDDUPrm, TB_NO_REVERSE }, + { X86::VMOVDI2PDIrr, X86::VMOVDI2PDIrm, 0 }, + { X86::VMOVDI2SSrr, X86::VMOVDI2SSrm, 0 }, + { X86::VMOVDQArr, X86::VMOVDQArm, TB_ALIGN_16 }, + { X86::VMOVDQUrr, X86::VMOVDQUrm, 0 }, + { X86::VMOVSLDUPrr, X86::VMOVSLDUPrm, 0 }, + { X86::VMOVSHDUPrr, X86::VMOVSHDUPrm, 0 }, + { X86::VMOVUPDrr, X86::VMOVUPDrm, 0 }, + { X86::VMOVUPSrr, X86::VMOVUPSrm, 0 }, + { X86::VMOVZPQILo2PQIrr,X86::VMOVQI2PQIrm, TB_NO_REVERSE }, + { X86::VPABSBrr, X86::VPABSBrm, 0 }, + { X86::VPABSDrr, X86::VPABSDrm, 0 }, + { X86::VPABSWrr, X86::VPABSWrm, 0 }, + { X86::VPCMPESTRIrr, X86::VPCMPESTRIrm, 0 }, + { X86::VPCMPESTRM128rr, X86::VPCMPESTRM128rm, 0 }, + { X86::VPCMPISTRIrr, X86::VPCMPISTRIrm, 0 }, + { X86::VPCMPISTRM128rr, X86::VPCMPISTRM128rm, 0 }, + { X86::VPHMINPOSUWrr128, X86::VPHMINPOSUWrm128, 0 }, + { X86::VPERMILPDri, X86::VPERMILPDmi, 0 }, + { X86::VPERMILPSri, X86::VPERMILPSmi, 0 }, + { X86::VPMOVSXBDrr, X86::VPMOVSXBDrm, TB_NO_REVERSE }, + { X86::VPMOVSXBQrr, X86::VPMOVSXBQrm, TB_NO_REVERSE }, + { X86::VPMOVSXBWrr, X86::VPMOVSXBWrm, TB_NO_REVERSE }, + { X86::VPMOVSXDQrr, X86::VPMOVSXDQrm, TB_NO_REVERSE }, + { X86::VPMOVSXWDrr, X86::VPMOVSXWDrm, TB_NO_REVERSE }, + { X86::VPMOVSXWQrr, X86::VPMOVSXWQrm, TB_NO_REVERSE }, + { X86::VPMOVZXBDrr, X86::VPMOVZXBDrm, TB_NO_REVERSE }, + { X86::VPMOVZXBQrr, X86::VPMOVZXBQrm, TB_NO_REVERSE }, + { X86::VPMOVZXBWrr, X86::VPMOVZXBWrm, TB_NO_REVERSE }, + { X86::VPMOVZXDQrr, X86::VPMOVZXDQrm, TB_NO_REVERSE }, + { X86::VPMOVZXWDrr, X86::VPMOVZXWDrm, TB_NO_REVERSE }, + { X86::VPMOVZXWQrr, X86::VPMOVZXWQrm, TB_NO_REVERSE }, + { X86::VPSHUFDri, X86::VPSHUFDmi, 0 }, + { X86::VPSHUFHWri, X86::VPSHUFHWmi, 0 }, + { X86::VPSHUFLWri, X86::VPSHUFLWmi, 0 }, + { X86::VPTESTrr, X86::VPTESTrm, 0 }, + { X86::VRCPPSr, X86::VRCPPSm, 0 }, + { X86::VROUNDPDr, X86::VROUNDPDm, 0 }, + { X86::VROUNDPSr, X86::VROUNDPSm, 0 }, + { X86::VRSQRTPSr, X86::VRSQRTPSm, 0 }, + { X86::VSQRTPDr, X86::VSQRTPDm, 0 }, + { X86::VSQRTPSr, X86::VSQRTPSm, 0 }, + { X86::VTESTPDrr, X86::VTESTPDrm, 0 }, + { X86::VTESTPSrr, X86::VTESTPSrm, 0 }, + { X86::VUCOMISDrr, X86::VUCOMISDrm, 0 }, + { X86::VUCOMISSrr, X86::VUCOMISSrm, 0 }, + + // AVX 256-bit foldable instructions + { X86::VCVTDQ2PDYrr, X86::VCVTDQ2PDYrm, TB_NO_REVERSE }, + { X86::VCVTDQ2PSYrr, X86::VCVTDQ2PSYrm, 0 }, + { X86::VCVTPD2DQYrr, X86::VCVTPD2DQYrm, 0 }, + { X86::VCVTPD2PSYrr, X86::VCVTPD2PSYrm, 0 }, + { X86::VCVTPS2DQYrr, X86::VCVTPS2DQYrm, 0 }, + { X86::VCVTPS2PDYrr, X86::VCVTPS2PDYrm, TB_NO_REVERSE }, + { X86::VCVTTPD2DQYrr, X86::VCVTTPD2DQYrm, 0 }, + { X86::VCVTTPS2DQYrr, X86::VCVTTPS2DQYrm, 0 }, + { X86::VMOVAPDYrr, X86::VMOVAPDYrm, TB_ALIGN_32 }, + { X86::VMOVAPSYrr, X86::VMOVAPSYrm, TB_ALIGN_32 }, + { X86::VMOVDDUPYrr, X86::VMOVDDUPYrm, 0 }, + { X86::VMOVDQAYrr, X86::VMOVDQAYrm, TB_ALIGN_32 }, + { X86::VMOVDQUYrr, X86::VMOVDQUYrm, 0 }, + { X86::VMOVSLDUPYrr, X86::VMOVSLDUPYrm, 0 }, + { X86::VMOVSHDUPYrr, X86::VMOVSHDUPYrm, 0 }, + { X86::VMOVUPDYrr, X86::VMOVUPDYrm, 0 }, + { X86::VMOVUPSYrr, X86::VMOVUPSYrm, 0 }, + { X86::VPERMILPDYri, X86::VPERMILPDYmi, 0 }, + { X86::VPERMILPSYri, X86::VPERMILPSYmi, 0 }, + { X86::VPTESTYrr, X86::VPTESTYrm, 0 }, + { X86::VRCPPSYr, X86::VRCPPSYm, 0 }, + { X86::VROUNDYPDr, X86::VROUNDYPDm, 0 }, + { X86::VROUNDYPSr, X86::VROUNDYPSm, 0 }, + { X86::VRSQRTPSYr, X86::VRSQRTPSYm, 0 }, + { X86::VSQRTPDYr, X86::VSQRTPDYm, 0 }, + { X86::VSQRTPSYr, X86::VSQRTPSYm, 0 }, + { X86::VTESTPDYrr, X86::VTESTPDYrm, 0 }, + { X86::VTESTPSYrr, X86::VTESTPSYrm, 0 }, + + // AVX2 foldable instructions + + // VBROADCASTS{SD}rr register instructions were an AVX2 addition while the + // VBROADCASTS{SD}rm memory instructions were available from AVX1. + // TB_NO_REVERSE prevents unfolding from introducing an illegal instruction + // on AVX1 targets. The VPBROADCAST instructions are all AVX2 instructions + // so they don't need an equivalent limitation. + { X86::VBROADCASTSSrr, X86::VBROADCASTSSrm, TB_NO_REVERSE }, + { X86::VBROADCASTSSYrr, X86::VBROADCASTSSYrm, TB_NO_REVERSE }, + { X86::VBROADCASTSDYrr, X86::VBROADCASTSDYrm, TB_NO_REVERSE }, + { X86::VPABSBYrr, X86::VPABSBYrm, 0 }, + { X86::VPABSDYrr, X86::VPABSDYrm, 0 }, + { X86::VPABSWYrr, X86::VPABSWYrm, 0 }, + { X86::VPBROADCASTBrr, X86::VPBROADCASTBrm, TB_NO_REVERSE }, + { X86::VPBROADCASTBYrr, X86::VPBROADCASTBYrm, TB_NO_REVERSE }, + { X86::VPBROADCASTDrr, X86::VPBROADCASTDrm, TB_NO_REVERSE }, + { X86::VPBROADCASTDYrr, X86::VPBROADCASTDYrm, TB_NO_REVERSE }, + { X86::VPBROADCASTQrr, X86::VPBROADCASTQrm, TB_NO_REVERSE }, + { X86::VPBROADCASTQYrr, X86::VPBROADCASTQYrm, TB_NO_REVERSE }, + { X86::VPBROADCASTWrr, X86::VPBROADCASTWrm, TB_NO_REVERSE }, + { X86::VPBROADCASTWYrr, X86::VPBROADCASTWYrm, TB_NO_REVERSE }, + { X86::VPERMPDYri, X86::VPERMPDYmi, 0 }, + { X86::VPERMQYri, X86::VPERMQYmi, 0 }, + { X86::VPMOVSXBDYrr, X86::VPMOVSXBDYrm, TB_NO_REVERSE }, + { X86::VPMOVSXBQYrr, X86::VPMOVSXBQYrm, TB_NO_REVERSE }, + { X86::VPMOVSXBWYrr, X86::VPMOVSXBWYrm, 0 }, + { X86::VPMOVSXDQYrr, X86::VPMOVSXDQYrm, 0 }, + { X86::VPMOVSXWDYrr, X86::VPMOVSXWDYrm, 0 }, + { X86::VPMOVSXWQYrr, X86::VPMOVSXWQYrm, TB_NO_REVERSE }, + { X86::VPMOVZXBDYrr, X86::VPMOVZXBDYrm, TB_NO_REVERSE }, + { X86::VPMOVZXBQYrr, X86::VPMOVZXBQYrm, TB_NO_REVERSE }, + { X86::VPMOVZXBWYrr, X86::VPMOVZXBWYrm, 0 }, + { X86::VPMOVZXDQYrr, X86::VPMOVZXDQYrm, 0 }, + { X86::VPMOVZXWDYrr, X86::VPMOVZXWDYrm, 0 }, + { X86::VPMOVZXWQYrr, X86::VPMOVZXWQYrm, TB_NO_REVERSE }, + { X86::VPSHUFDYri, X86::VPSHUFDYmi, 0 }, + { X86::VPSHUFHWYri, X86::VPSHUFHWYmi, 0 }, + { X86::VPSHUFLWYri, X86::VPSHUFLWYmi, 0 }, + + // XOP foldable instructions + { X86::VFRCZPDrr, X86::VFRCZPDrm, 0 }, + { X86::VFRCZPDrrY, X86::VFRCZPDrmY, 0 }, + { X86::VFRCZPSrr, X86::VFRCZPSrm, 0 }, + { X86::VFRCZPSrrY, X86::VFRCZPSrmY, 0 }, + { X86::VFRCZSDrr, X86::VFRCZSDrm, 0 }, + { X86::VFRCZSSrr, X86::VFRCZSSrm, 0 }, + { X86::VPHADDBDrr, X86::VPHADDBDrm, 0 }, + { X86::VPHADDBQrr, X86::VPHADDBQrm, 0 }, + { X86::VPHADDBWrr, X86::VPHADDBWrm, 0 }, + { X86::VPHADDDQrr, X86::VPHADDDQrm, 0 }, + { X86::VPHADDWDrr, X86::VPHADDWDrm, 0 }, + { X86::VPHADDWQrr, X86::VPHADDWQrm, 0 }, + { X86::VPHADDUBDrr, X86::VPHADDUBDrm, 0 }, + { X86::VPHADDUBQrr, X86::VPHADDUBQrm, 0 }, + { X86::VPHADDUBWrr, X86::VPHADDUBWrm, 0 }, + { X86::VPHADDUDQrr, X86::VPHADDUDQrm, 0 }, + { X86::VPHADDUWDrr, X86::VPHADDUWDrm, 0 }, + { X86::VPHADDUWQrr, X86::VPHADDUWQrm, 0 }, + { X86::VPHSUBBWrr, X86::VPHSUBBWrm, 0 }, + { X86::VPHSUBDQrr, X86::VPHSUBDQrm, 0 }, + { X86::VPHSUBWDrr, X86::VPHSUBWDrm, 0 }, + { X86::VPROTBri, X86::VPROTBmi, 0 }, + { X86::VPROTBrr, X86::VPROTBmr, 0 }, + { X86::VPROTDri, X86::VPROTDmi, 0 }, + { X86::VPROTDrr, X86::VPROTDmr, 0 }, + { X86::VPROTQri, X86::VPROTQmi, 0 }, + { X86::VPROTQrr, X86::VPROTQmr, 0 }, + { X86::VPROTWri, X86::VPROTWmi, 0 }, + { X86::VPROTWrr, X86::VPROTWmr, 0 }, + { X86::VPSHABrr, X86::VPSHABmr, 0 }, + { X86::VPSHADrr, X86::VPSHADmr, 0 }, + { X86::VPSHAQrr, X86::VPSHAQmr, 0 }, + { X86::VPSHAWrr, X86::VPSHAWmr, 0 }, + { X86::VPSHLBrr, X86::VPSHLBmr, 0 }, + { X86::VPSHLDrr, X86::VPSHLDmr, 0 }, + { X86::VPSHLQrr, X86::VPSHLQmr, 0 }, + { X86::VPSHLWrr, X86::VPSHLWmr, 0 }, + + // LWP foldable instructions + { X86::LWPINS32rri, X86::LWPINS32rmi, 0 }, + { X86::LWPINS64rri, X86::LWPINS64rmi, 0 }, + { X86::LWPVAL32rri, X86::LWPVAL32rmi, 0 }, + { X86::LWPVAL64rri, X86::LWPVAL64rmi, 0 }, + + // BMI/BMI2/LZCNT/POPCNT/TBM foldable instructions + { X86::BEXTR32rr, X86::BEXTR32rm, 0 }, + { X86::BEXTR64rr, X86::BEXTR64rm, 0 }, + { X86::BEXTRI32ri, X86::BEXTRI32mi, 0 }, + { X86::BEXTRI64ri, X86::BEXTRI64mi, 0 }, + { X86::BLCFILL32rr, X86::BLCFILL32rm, 0 }, + { X86::BLCFILL64rr, X86::BLCFILL64rm, 0 }, + { X86::BLCI32rr, X86::BLCI32rm, 0 }, + { X86::BLCI64rr, X86::BLCI64rm, 0 }, + { X86::BLCIC32rr, X86::BLCIC32rm, 0 }, + { X86::BLCIC64rr, X86::BLCIC64rm, 0 }, + { X86::BLCMSK32rr, X86::BLCMSK32rm, 0 }, + { X86::BLCMSK64rr, X86::BLCMSK64rm, 0 }, + { X86::BLCS32rr, X86::BLCS32rm, 0 }, + { X86::BLCS64rr, X86::BLCS64rm, 0 }, + { X86::BLSFILL32rr, X86::BLSFILL32rm, 0 }, + { X86::BLSFILL64rr, X86::BLSFILL64rm, 0 }, + { X86::BLSI32rr, X86::BLSI32rm, 0 }, + { X86::BLSI64rr, X86::BLSI64rm, 0 }, + { X86::BLSIC32rr, X86::BLSIC32rm, 0 }, + { X86::BLSIC64rr, X86::BLSIC64rm, 0 }, + { X86::BLSMSK32rr, X86::BLSMSK32rm, 0 }, + { X86::BLSMSK64rr, X86::BLSMSK64rm, 0 }, + { X86::BLSR32rr, X86::BLSR32rm, 0 }, + { X86::BLSR64rr, X86::BLSR64rm, 0 }, + { X86::BZHI32rr, X86::BZHI32rm, 0 }, + { X86::BZHI64rr, X86::BZHI64rm, 0 }, + { X86::LZCNT16rr, X86::LZCNT16rm, 0 }, + { X86::LZCNT32rr, X86::LZCNT32rm, 0 }, + { X86::LZCNT64rr, X86::LZCNT64rm, 0 }, + { X86::POPCNT16rr, X86::POPCNT16rm, 0 }, + { X86::POPCNT32rr, X86::POPCNT32rm, 0 }, + { X86::POPCNT64rr, X86::POPCNT64rm, 0 }, + { X86::RORX32ri, X86::RORX32mi, 0 }, + { X86::RORX64ri, X86::RORX64mi, 0 }, + { X86::SARX32rr, X86::SARX32rm, 0 }, + { X86::SARX64rr, X86::SARX64rm, 0 }, + { X86::SHRX32rr, X86::SHRX32rm, 0 }, + { X86::SHRX64rr, X86::SHRX64rm, 0 }, + { X86::SHLX32rr, X86::SHLX32rm, 0 }, + { X86::SHLX64rr, X86::SHLX64rm, 0 }, + { X86::T1MSKC32rr, X86::T1MSKC32rm, 0 }, + { X86::T1MSKC64rr, X86::T1MSKC64rm, 0 }, + { X86::TZCNT16rr, X86::TZCNT16rm, 0 }, + { X86::TZCNT32rr, X86::TZCNT32rm, 0 }, + { X86::TZCNT64rr, X86::TZCNT64rm, 0 }, + { X86::TZMSK32rr, X86::TZMSK32rm, 0 }, + { X86::TZMSK64rr, X86::TZMSK64rm, 0 }, + + // AVX-512 foldable instructions + { X86::VBROADCASTSSZr, X86::VBROADCASTSSZm, TB_NO_REVERSE }, + { X86::VBROADCASTSDZr, X86::VBROADCASTSDZm, TB_NO_REVERSE }, + { X86::VMOV64toPQIZrr, X86::VMOVQI2PQIZrm, 0 }, + { X86::VMOV64toSDZrr, X86::VMOV64toSDZrm, 0 }, + { X86::VMOVDI2PDIZrr, X86::VMOVDI2PDIZrm, 0 }, + { X86::VMOVDI2SSZrr, X86::VMOVDI2SSZrm, 0 }, + { X86::VMOVAPDZrr, X86::VMOVAPDZrm, TB_ALIGN_64 }, + { X86::VMOVAPSZrr, X86::VMOVAPSZrm, TB_ALIGN_64 }, + { X86::VMOVDQA32Zrr, X86::VMOVDQA32Zrm, TB_ALIGN_64 }, + { X86::VMOVDQA64Zrr, X86::VMOVDQA64Zrm, TB_ALIGN_64 }, + { X86::VMOVDQU8Zrr, X86::VMOVDQU8Zrm, 0 }, + { X86::VMOVDQU16Zrr, X86::VMOVDQU16Zrm, 0 }, + { X86::VMOVDQU32Zrr, X86::VMOVDQU32Zrm, 0 }, + { X86::VMOVDQU64Zrr, X86::VMOVDQU64Zrm, 0 }, + { X86::VMOVUPDZrr, X86::VMOVUPDZrm, 0 }, + { X86::VMOVUPSZrr, X86::VMOVUPSZrm, 0 }, + { X86::VMOVZPQILo2PQIZrr,X86::VMOVQI2PQIZrm, TB_NO_REVERSE }, + { X86::VPABSBZrr, X86::VPABSBZrm, 0 }, + { X86::VPABSDZrr, X86::VPABSDZrm, 0 }, + { X86::VPABSQZrr, X86::VPABSQZrm, 0 }, + { X86::VPABSWZrr, X86::VPABSWZrm, 0 }, + { X86::VPERMILPDZri, X86::VPERMILPDZmi, 0 }, + { X86::VPERMILPSZri, X86::VPERMILPSZmi, 0 }, + { X86::VPERMPDZri, X86::VPERMPDZmi, 0 }, + { X86::VPERMQZri, X86::VPERMQZmi, 0 }, + { X86::VPMOVSXBDZrr, X86::VPMOVSXBDZrm, 0 }, + { X86::VPMOVSXBQZrr, X86::VPMOVSXBQZrm, TB_NO_REVERSE }, + { X86::VPMOVSXBWZrr, X86::VPMOVSXBWZrm, 0 }, + { X86::VPMOVSXDQZrr, X86::VPMOVSXDQZrm, 0 }, + { X86::VPMOVSXWDZrr, X86::VPMOVSXWDZrm, 0 }, + { X86::VPMOVSXWQZrr, X86::VPMOVSXWQZrm, 0 }, + { X86::VPMOVZXBDZrr, X86::VPMOVZXBDZrm, 0 }, + { X86::VPMOVZXBQZrr, X86::VPMOVZXBQZrm, TB_NO_REVERSE }, + { X86::VPMOVZXBWZrr, X86::VPMOVZXBWZrm, 0 }, + { X86::VPMOVZXDQZrr, X86::VPMOVZXDQZrm, 0 }, + { X86::VPMOVZXWDZrr, X86::VPMOVZXWDZrm, 0 }, + { X86::VPMOVZXWQZrr, X86::VPMOVZXWQZrm, 0 }, + { X86::VPOPCNTDZrr, X86::VPOPCNTDZrm, 0 }, + { X86::VPOPCNTQZrr, X86::VPOPCNTQZrm, 0 }, + { X86::VPSHUFDZri, X86::VPSHUFDZmi, 0 }, + { X86::VPSHUFHWZri, X86::VPSHUFHWZmi, 0 }, + { X86::VPSHUFLWZri, X86::VPSHUFLWZmi, 0 }, + { X86::VPSLLDQZ512rr, X86::VPSLLDQZ512rm, 0 }, + { X86::VPSLLDZri, X86::VPSLLDZmi, 0 }, + { X86::VPSLLQZri, X86::VPSLLQZmi, 0 }, + { X86::VPSLLWZri, X86::VPSLLWZmi, 0 }, + { X86::VPSRADZri, X86::VPSRADZmi, 0 }, + { X86::VPSRAQZri, X86::VPSRAQZmi, 0 }, + { X86::VPSRAWZri, X86::VPSRAWZmi, 0 }, + { X86::VPSRLDQZ512rr, X86::VPSRLDQZ512rm, 0 }, + { X86::VPSRLDZri, X86::VPSRLDZmi, 0 }, + { X86::VPSRLQZri, X86::VPSRLQZmi, 0 }, + { X86::VPSRLWZri, X86::VPSRLWZmi, 0 }, + + // AVX-512 foldable instructions (256-bit versions) + { X86::VBROADCASTSSZ256r, X86::VBROADCASTSSZ256m, TB_NO_REVERSE }, + { X86::VBROADCASTSDZ256r, X86::VBROADCASTSDZ256m, TB_NO_REVERSE }, + { X86::VMOVAPDZ256rr, X86::VMOVAPDZ256rm, TB_ALIGN_32 }, + { X86::VMOVAPSZ256rr, X86::VMOVAPSZ256rm, TB_ALIGN_32 }, + { X86::VMOVDQA32Z256rr, X86::VMOVDQA32Z256rm, TB_ALIGN_32 }, + { X86::VMOVDQA64Z256rr, X86::VMOVDQA64Z256rm, TB_ALIGN_32 }, + { X86::VMOVDQU8Z256rr, X86::VMOVDQU8Z256rm, 0 }, + { X86::VMOVDQU16Z256rr, X86::VMOVDQU16Z256rm, 0 }, + { X86::VMOVDQU32Z256rr, X86::VMOVDQU32Z256rm, 0 }, + { X86::VMOVDQU64Z256rr, X86::VMOVDQU64Z256rm, 0 }, + { X86::VMOVUPDZ256rr, X86::VMOVUPDZ256rm, 0 }, + { X86::VMOVUPSZ256rr, X86::VMOVUPSZ256rm, 0 }, + { X86::VPABSBZ256rr, X86::VPABSBZ256rm, 0 }, + { X86::VPABSDZ256rr, X86::VPABSDZ256rm, 0 }, + { X86::VPABSQZ256rr, X86::VPABSQZ256rm, 0 }, + { X86::VPABSWZ256rr, X86::VPABSWZ256rm, 0 }, + { X86::VPERMILPDZ256ri, X86::VPERMILPDZ256mi, 0 }, + { X86::VPERMILPSZ256ri, X86::VPERMILPSZ256mi, 0 }, + { X86::VPERMPDZ256ri, X86::VPERMPDZ256mi, 0 }, + { X86::VPERMQZ256ri, X86::VPERMQZ256mi, 0 }, + { X86::VPMOVSXBDZ256rr, X86::VPMOVSXBDZ256rm, TB_NO_REVERSE }, + { X86::VPMOVSXBQZ256rr, X86::VPMOVSXBQZ256rm, TB_NO_REVERSE }, + { X86::VPMOVSXBWZ256rr, X86::VPMOVSXBWZ256rm, 0 }, + { X86::VPMOVSXDQZ256rr, X86::VPMOVSXDQZ256rm, 0 }, + { X86::VPMOVSXWDZ256rr, X86::VPMOVSXWDZ256rm, 0 }, + { X86::VPMOVSXWQZ256rr, X86::VPMOVSXWQZ256rm, TB_NO_REVERSE }, + { X86::VPMOVZXBDZ256rr, X86::VPMOVZXBDZ256rm, TB_NO_REVERSE }, + { X86::VPMOVZXBQZ256rr, X86::VPMOVZXBQZ256rm, TB_NO_REVERSE }, + { X86::VPMOVZXBWZ256rr, X86::VPMOVZXBWZ256rm, 0 }, + { X86::VPMOVZXDQZ256rr, X86::VPMOVZXDQZ256rm, 0 }, + { X86::VPMOVZXWDZ256rr, X86::VPMOVZXWDZ256rm, 0 }, + { X86::VPMOVZXWQZ256rr, X86::VPMOVZXWQZ256rm, TB_NO_REVERSE }, + { X86::VPSHUFDZ256ri, X86::VPSHUFDZ256mi, 0 }, + { X86::VPSHUFHWZ256ri, X86::VPSHUFHWZ256mi, 0 }, + { X86::VPSHUFLWZ256ri, X86::VPSHUFLWZ256mi, 0 }, + { X86::VPSLLDQZ256rr, X86::VPSLLDQZ256rm, 0 }, + { X86::VPSLLDZ256ri, X86::VPSLLDZ256mi, 0 }, + { X86::VPSLLQZ256ri, X86::VPSLLQZ256mi, 0 }, + { X86::VPSLLWZ256ri, X86::VPSLLWZ256mi, 0 }, + { X86::VPSRADZ256ri, X86::VPSRADZ256mi, 0 }, + { X86::VPSRAQZ256ri, X86::VPSRAQZ256mi, 0 }, + { X86::VPSRAWZ256ri, X86::VPSRAWZ256mi, 0 }, + { X86::VPSRLDQZ256rr, X86::VPSRLDQZ256rm, 0 }, + { X86::VPSRLDZ256ri, X86::VPSRLDZ256mi, 0 }, + { X86::VPSRLQZ256ri, X86::VPSRLQZ256mi, 0 }, + { X86::VPSRLWZ256ri, X86::VPSRLWZ256mi, 0 }, + + // AVX-512 foldable instructions (128-bit versions) + { X86::VBROADCASTSSZ128r, X86::VBROADCASTSSZ128m, TB_NO_REVERSE }, + { X86::VMOVAPDZ128rr, X86::VMOVAPDZ128rm, TB_ALIGN_16 }, + { X86::VMOVAPSZ128rr, X86::VMOVAPSZ128rm, TB_ALIGN_16 }, + { X86::VMOVDQA32Z128rr, X86::VMOVDQA32Z128rm, TB_ALIGN_16 }, + { X86::VMOVDQA64Z128rr, X86::VMOVDQA64Z128rm, TB_ALIGN_16 }, + { X86::VMOVDQU8Z128rr, X86::VMOVDQU8Z128rm, 0 }, + { X86::VMOVDQU16Z128rr, X86::VMOVDQU16Z128rm, 0 }, + { X86::VMOVDQU32Z128rr, X86::VMOVDQU32Z128rm, 0 }, + { X86::VMOVDQU64Z128rr, X86::VMOVDQU64Z128rm, 0 }, + { X86::VMOVUPDZ128rr, X86::VMOVUPDZ128rm, 0 }, + { X86::VMOVUPSZ128rr, X86::VMOVUPSZ128rm, 0 }, + { X86::VPABSBZ128rr, X86::VPABSBZ128rm, 0 }, + { X86::VPABSDZ128rr, X86::VPABSDZ128rm, 0 }, + { X86::VPABSQZ128rr, X86::VPABSQZ128rm, 0 }, + { X86::VPABSWZ128rr, X86::VPABSWZ128rm, 0 }, + { X86::VPERMILPDZ128ri, X86::VPERMILPDZ128mi, 0 }, + { X86::VPERMILPSZ128ri, X86::VPERMILPSZ128mi, 0 }, + { X86::VPMOVSXBDZ128rr, X86::VPMOVSXBDZ128rm, TB_NO_REVERSE }, + { X86::VPMOVSXBQZ128rr, X86::VPMOVSXBQZ128rm, TB_NO_REVERSE }, + { X86::VPMOVSXBWZ128rr, X86::VPMOVSXBWZ128rm, TB_NO_REVERSE }, + { X86::VPMOVSXDQZ128rr, X86::VPMOVSXDQZ128rm, TB_NO_REVERSE }, + { X86::VPMOVSXWDZ128rr, X86::VPMOVSXWDZ128rm, TB_NO_REVERSE }, + { X86::VPMOVSXWQZ128rr, X86::VPMOVSXWQZ128rm, TB_NO_REVERSE }, + { X86::VPMOVZXBDZ128rr, X86::VPMOVZXBDZ128rm, TB_NO_REVERSE }, + { X86::VPMOVZXBQZ128rr, X86::VPMOVZXBQZ128rm, TB_NO_REVERSE }, + { X86::VPMOVZXBWZ128rr, X86::VPMOVZXBWZ128rm, TB_NO_REVERSE }, + { X86::VPMOVZXDQZ128rr, X86::VPMOVZXDQZ128rm, TB_NO_REVERSE }, + { X86::VPMOVZXWDZ128rr, X86::VPMOVZXWDZ128rm, TB_NO_REVERSE }, + { X86::VPMOVZXWQZ128rr, X86::VPMOVZXWQZ128rm, TB_NO_REVERSE }, + { X86::VPSHUFDZ128ri, X86::VPSHUFDZ128mi, 0 }, + { X86::VPSHUFHWZ128ri, X86::VPSHUFHWZ128mi, 0 }, + { X86::VPSHUFLWZ128ri, X86::VPSHUFLWZ128mi, 0 }, + { X86::VPSLLDQZ128rr, X86::VPSLLDQZ128rm, 0 }, + { X86::VPSLLDZ128ri, X86::VPSLLDZ128mi, 0 }, + { X86::VPSLLQZ128ri, X86::VPSLLQZ128mi, 0 }, + { X86::VPSLLWZ128ri, X86::VPSLLWZ128mi, 0 }, + { X86::VPSRADZ128ri, X86::VPSRADZ128mi, 0 }, + { X86::VPSRAQZ128ri, X86::VPSRAQZ128mi, 0 }, + { X86::VPSRAWZ128ri, X86::VPSRAWZ128mi, 0 }, + { X86::VPSRLDQZ128rr, X86::VPSRLDQZ128rm, 0 }, + { X86::VPSRLDZ128ri, X86::VPSRLDZ128mi, 0 }, + { X86::VPSRLQZ128ri, X86::VPSRLQZ128mi, 0 }, + { X86::VPSRLWZ128ri, X86::VPSRLWZ128mi, 0 }, + + // F16C foldable instructions + { X86::VCVTPH2PSrr, X86::VCVTPH2PSrm, 0 }, + { X86::VCVTPH2PSYrr, X86::VCVTPH2PSYrm, 0 }, + + // AES foldable instructions + { X86::AESIMCrr, X86::AESIMCrm, TB_ALIGN_16 }, + { X86::AESKEYGENASSIST128rr, X86::AESKEYGENASSIST128rm, TB_ALIGN_16 }, + { X86::VAESIMCrr, X86::VAESIMCrm, 0 }, + { X86::VAESKEYGENASSIST128rr, X86::VAESKEYGENASSIST128rm, 0 } + }; + for (X86MemoryFoldTableEntry Entry : MemoryFoldTable1) { AddTableEntry(RegOp2MemOpTable1, MemOp2RegOpTable, Entry.RegOp, Entry.MemOp, @@ -143,6 +1042,1396 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI) Entry.Flags | TB_INDEX_1 | TB_FOLDED_LOAD); } + static const X86MemoryFoldTableEntry MemoryFoldTable2[] = { + { X86::ADC32rr, X86::ADC32rm, 0 }, + { X86::ADC64rr, X86::ADC64rm, 0 }, + { X86::ADD16rr, X86::ADD16rm, 0 }, + { X86::ADD16rr_DB, X86::ADD16rm, TB_NO_REVERSE }, + { X86::ADD32rr, X86::ADD32rm, 0 }, + { X86::ADD32rr_DB, X86::ADD32rm, TB_NO_REVERSE }, + { X86::ADD64rr, X86::ADD64rm, 0 }, + { X86::ADD64rr_DB, X86::ADD64rm, TB_NO_REVERSE }, + { X86::ADD8rr, X86::ADD8rm, 0 }, + { X86::ADDPDrr, X86::ADDPDrm, TB_ALIGN_16 }, + { X86::ADDPSrr, X86::ADDPSrm, TB_ALIGN_16 }, + { X86::ADDSDrr, X86::ADDSDrm, 0 }, + { X86::ADDSDrr_Int, X86::ADDSDrm_Int, TB_NO_REVERSE }, + { X86::ADDSSrr, X86::ADDSSrm, 0 }, + { X86::ADDSSrr_Int, X86::ADDSSrm_Int, TB_NO_REVERSE }, + { X86::ADDSUBPDrr, X86::ADDSUBPDrm, TB_ALIGN_16 }, + { X86::ADDSUBPSrr, X86::ADDSUBPSrm, TB_ALIGN_16 }, + { X86::AND16rr, X86::AND16rm, 0 }, + { X86::AND32rr, X86::AND32rm, 0 }, + { X86::AND64rr, X86::AND64rm, 0 }, + { X86::AND8rr, X86::AND8rm, 0 }, + { X86::ANDNPDrr, X86::ANDNPDrm, TB_ALIGN_16 }, + { X86::ANDNPSrr, X86::ANDNPSrm, TB_ALIGN_16 }, + { X86::ANDPDrr, X86::ANDPDrm, TB_ALIGN_16 }, + { X86::ANDPSrr, X86::ANDPSrm, TB_ALIGN_16 }, + { X86::BLENDPDrri, X86::BLENDPDrmi, TB_ALIGN_16 }, + { X86::BLENDPSrri, X86::BLENDPSrmi, TB_ALIGN_16 }, + { X86::BLENDVPDrr0, X86::BLENDVPDrm0, TB_ALIGN_16 }, + { X86::BLENDVPSrr0, X86::BLENDVPSrm0, TB_ALIGN_16 }, + { X86::CMOVA16rr, X86::CMOVA16rm, 0 }, + { X86::CMOVA32rr, X86::CMOVA32rm, 0 }, + { X86::CMOVA64rr, X86::CMOVA64rm, 0 }, + { X86::CMOVAE16rr, X86::CMOVAE16rm, 0 }, + { X86::CMOVAE32rr, X86::CMOVAE32rm, 0 }, + { X86::CMOVAE64rr, X86::CMOVAE64rm, 0 }, + { X86::CMOVB16rr, X86::CMOVB16rm, 0 }, + { X86::CMOVB32rr, X86::CMOVB32rm, 0 }, + { X86::CMOVB64rr, X86::CMOVB64rm, 0 }, + { X86::CMOVBE16rr, X86::CMOVBE16rm, 0 }, + { X86::CMOVBE32rr, X86::CMOVBE32rm, 0 }, + { X86::CMOVBE64rr, X86::CMOVBE64rm, 0 }, + { X86::CMOVE16rr, X86::CMOVE16rm, 0 }, + { X86::CMOVE32rr, X86::CMOVE32rm, 0 }, + { X86::CMOVE64rr, X86::CMOVE64rm, 0 }, + { X86::CMOVG16rr, X86::CMOVG16rm, 0 }, + { X86::CMOVG32rr, X86::CMOVG32rm, 0 }, + { X86::CMOVG64rr, X86::CMOVG64rm, 0 }, + { X86::CMOVGE16rr, X86::CMOVGE16rm, 0 }, + { X86::CMOVGE32rr, X86::CMOVGE32rm, 0 }, + { X86::CMOVGE64rr, X86::CMOVGE64rm, 0 }, + { X86::CMOVL16rr, X86::CMOVL16rm, 0 }, + { X86::CMOVL32rr, X86::CMOVL32rm, 0 }, + { X86::CMOVL64rr, X86::CMOVL64rm, 0 }, + { X86::CMOVLE16rr, X86::CMOVLE16rm, 0 }, + { X86::CMOVLE32rr, X86::CMOVLE32rm, 0 }, + { X86::CMOVLE64rr, X86::CMOVLE64rm, 0 }, + { X86::CMOVNE16rr, X86::CMOVNE16rm, 0 }, + { X86::CMOVNE32rr, X86::CMOVNE32rm, 0 }, + { X86::CMOVNE64rr, X86::CMOVNE64rm, 0 }, + { X86::CMOVNO16rr, X86::CMOVNO16rm, 0 }, + { X86::CMOVNO32rr, X86::CMOVNO32rm, 0 }, + { X86::CMOVNO64rr, X86::CMOVNO64rm, 0 }, + { X86::CMOVNP16rr, X86::CMOVNP16rm, 0 }, + { X86::CMOVNP32rr, X86::CMOVNP32rm, 0 }, + { X86::CMOVNP64rr, X86::CMOVNP64rm, 0 }, + { X86::CMOVNS16rr, X86::CMOVNS16rm, 0 }, + { X86::CMOVNS32rr, X86::CMOVNS32rm, 0 }, + { X86::CMOVNS64rr, X86::CMOVNS64rm, 0 }, + { X86::CMOVO16rr, X86::CMOVO16rm, 0 }, + { X86::CMOVO32rr, X86::CMOVO32rm, 0 }, + { X86::CMOVO64rr, X86::CMOVO64rm, 0 }, + { X86::CMOVP16rr, X86::CMOVP16rm, 0 }, + { X86::CMOVP32rr, X86::CMOVP32rm, 0 }, + { X86::CMOVP64rr, X86::CMOVP64rm, 0 }, + { X86::CMOVS16rr, X86::CMOVS16rm, 0 }, + { X86::CMOVS32rr, X86::CMOVS32rm, 0 }, + { X86::CMOVS64rr, X86::CMOVS64rm, 0 }, + { X86::CMPPDrri, X86::CMPPDrmi, TB_ALIGN_16 }, + { X86::CMPPSrri, X86::CMPPSrmi, TB_ALIGN_16 }, + { X86::CMPSDrr, X86::CMPSDrm, 0 }, + { X86::CMPSSrr, X86::CMPSSrm, 0 }, + { X86::CRC32r32r32, X86::CRC32r32m32, 0 }, + { X86::CRC32r64r64, X86::CRC32r64m64, 0 }, + { X86::DIVPDrr, X86::DIVPDrm, TB_ALIGN_16 }, + { X86::DIVPSrr, X86::DIVPSrm, TB_ALIGN_16 }, + { X86::DIVSDrr, X86::DIVSDrm, 0 }, + { X86::DIVSDrr_Int, X86::DIVSDrm_Int, TB_NO_REVERSE }, + { X86::DIVSSrr, X86::DIVSSrm, 0 }, + { X86::DIVSSrr_Int, X86::DIVSSrm_Int, TB_NO_REVERSE }, + { X86::DPPDrri, X86::DPPDrmi, TB_ALIGN_16 }, + { X86::DPPSrri, X86::DPPSrmi, TB_ALIGN_16 }, + { X86::HADDPDrr, X86::HADDPDrm, TB_ALIGN_16 }, + { X86::HADDPSrr, X86::HADDPSrm, TB_ALIGN_16 }, + { X86::HSUBPDrr, X86::HSUBPDrm, TB_ALIGN_16 }, + { X86::HSUBPSrr, X86::HSUBPSrm, TB_ALIGN_16 }, + { X86::IMUL16rr, X86::IMUL16rm, 0 }, + { X86::IMUL32rr, X86::IMUL32rm, 0 }, + { X86::IMUL64rr, X86::IMUL64rm, 0 }, + { X86::Int_CMPSDrr, X86::Int_CMPSDrm, TB_NO_REVERSE }, + { X86::Int_CMPSSrr, X86::Int_CMPSSrm, TB_NO_REVERSE }, + { X86::Int_CVTSD2SSrr, X86::Int_CVTSD2SSrm, TB_NO_REVERSE }, + { X86::Int_CVTSI2SD64rr,X86::Int_CVTSI2SD64rm, 0 }, + { X86::Int_CVTSI2SDrr, X86::Int_CVTSI2SDrm, 0 }, + { X86::Int_CVTSI2SS64rr,X86::Int_CVTSI2SS64rm, 0 }, + { X86::Int_CVTSI2SSrr, X86::Int_CVTSI2SSrm, 0 }, + { X86::Int_CVTSS2SDrr, X86::Int_CVTSS2SDrm, TB_NO_REVERSE }, + { X86::MAXPDrr, X86::MAXPDrm, TB_ALIGN_16 }, + { X86::MAXCPDrr, X86::MAXCPDrm, TB_ALIGN_16 }, + { X86::MAXPSrr, X86::MAXPSrm, TB_ALIGN_16 }, + { X86::MAXCPSrr, X86::MAXCPSrm, TB_ALIGN_16 }, + { X86::MAXSDrr, X86::MAXSDrm, 0 }, + { X86::MAXCSDrr, X86::MAXCSDrm, 0 }, + { X86::MAXSDrr_Int, X86::MAXSDrm_Int, TB_NO_REVERSE }, + { X86::MAXSSrr, X86::MAXSSrm, 0 }, + { X86::MAXCSSrr, X86::MAXCSSrm, 0 }, + { X86::MAXSSrr_Int, X86::MAXSSrm_Int, TB_NO_REVERSE }, + { X86::MINPDrr, X86::MINPDrm, TB_ALIGN_16 }, + { X86::MINCPDrr, X86::MINCPDrm, TB_ALIGN_16 }, + { X86::MINPSrr, X86::MINPSrm, TB_ALIGN_16 }, + { X86::MINCPSrr, X86::MINCPSrm, TB_ALIGN_16 }, + { X86::MINSDrr, X86::MINSDrm, 0 }, + { X86::MINCSDrr, X86::MINCSDrm, 0 }, + { X86::MINSDrr_Int, X86::MINSDrm_Int, TB_NO_REVERSE }, + { X86::MINSSrr, X86::MINSSrm, 0 }, + { X86::MINCSSrr, X86::MINCSSrm, 0 }, + { X86::MINSSrr_Int, X86::MINSSrm_Int, TB_NO_REVERSE }, + { X86::MOVLHPSrr, X86::MOVHPSrm, TB_NO_REVERSE }, + { X86::MPSADBWrri, X86::MPSADBWrmi, TB_ALIGN_16 }, + { X86::MULPDrr, X86::MULPDrm, TB_ALIGN_16 }, + { X86::MULPSrr, X86::MULPSrm, TB_ALIGN_16 }, + { X86::MULSDrr, X86::MULSDrm, 0 }, + { X86::MULSDrr_Int, X86::MULSDrm_Int, TB_NO_REVERSE }, + { X86::MULSSrr, X86::MULSSrm, 0 }, + { X86::MULSSrr_Int, X86::MULSSrm_Int, TB_NO_REVERSE }, + { X86::OR16rr, X86::OR16rm, 0 }, + { X86::OR32rr, X86::OR32rm, 0 }, + { X86::OR64rr, X86::OR64rm, 0 }, + { X86::OR8rr, X86::OR8rm, 0 }, + { X86::ORPDrr, X86::ORPDrm, TB_ALIGN_16 }, + { X86::ORPSrr, X86::ORPSrm, TB_ALIGN_16 }, + { X86::PACKSSDWrr, X86::PACKSSDWrm, TB_ALIGN_16 }, + { X86::PACKSSWBrr, X86::PACKSSWBrm, TB_ALIGN_16 }, + { X86::PACKUSDWrr, X86::PACKUSDWrm, TB_ALIGN_16 }, + { X86::PACKUSWBrr, X86::PACKUSWBrm, TB_ALIGN_16 }, + { X86::PADDBrr, X86::PADDBrm, TB_ALIGN_16 }, + { X86::PADDDrr, X86::PADDDrm, TB_ALIGN_16 }, + { X86::PADDQrr, X86::PADDQrm, TB_ALIGN_16 }, + { X86::PADDSBrr, X86::PADDSBrm, TB_ALIGN_16 }, + { X86::PADDSWrr, X86::PADDSWrm, TB_ALIGN_16 }, + { X86::PADDUSBrr, X86::PADDUSBrm, TB_ALIGN_16 }, + { X86::PADDUSWrr, X86::PADDUSWrm, TB_ALIGN_16 }, + { X86::PADDWrr, X86::PADDWrm, TB_ALIGN_16 }, + { X86::PALIGNRrri, X86::PALIGNRrmi, TB_ALIGN_16 }, + { X86::PANDNrr, X86::PANDNrm, TB_ALIGN_16 }, + { X86::PANDrr, X86::PANDrm, TB_ALIGN_16 }, + { X86::PAVGBrr, X86::PAVGBrm, TB_ALIGN_16 }, + { X86::PAVGWrr, X86::PAVGWrm, TB_ALIGN_16 }, + { X86::PBLENDVBrr0, X86::PBLENDVBrm0, TB_ALIGN_16 }, + { X86::PBLENDWrri, X86::PBLENDWrmi, TB_ALIGN_16 }, + { X86::PCLMULQDQrr, X86::PCLMULQDQrm, TB_ALIGN_16 }, + { X86::PCMPEQBrr, X86::PCMPEQBrm, TB_ALIGN_16 }, + { X86::PCMPEQDrr, X86::PCMPEQDrm, TB_ALIGN_16 }, + { X86::PCMPEQQrr, X86::PCMPEQQrm, TB_ALIGN_16 }, + { X86::PCMPEQWrr, X86::PCMPEQWrm, TB_ALIGN_16 }, + { X86::PCMPGTBrr, X86::PCMPGTBrm, TB_ALIGN_16 }, + { X86::PCMPGTDrr, X86::PCMPGTDrm, TB_ALIGN_16 }, + { X86::PCMPGTQrr, X86::PCMPGTQrm, TB_ALIGN_16 }, + { X86::PCMPGTWrr, X86::PCMPGTWrm, TB_ALIGN_16 }, + { X86::PHADDDrr, X86::PHADDDrm, TB_ALIGN_16 }, + { X86::PHADDWrr, X86::PHADDWrm, TB_ALIGN_16 }, + { X86::PHADDSWrr128, X86::PHADDSWrm128, TB_ALIGN_16 }, + { X86::PHSUBDrr, X86::PHSUBDrm, TB_ALIGN_16 }, + { X86::PHSUBSWrr128, X86::PHSUBSWrm128, TB_ALIGN_16 }, + { X86::PHSUBWrr, X86::PHSUBWrm, TB_ALIGN_16 }, + { X86::PINSRBrr, X86::PINSRBrm, 0 }, + { X86::PINSRDrr, X86::PINSRDrm, 0 }, + { X86::PINSRQrr, X86::PINSRQrm, 0 }, + { X86::PINSRWrri, X86::PINSRWrmi, 0 }, + { X86::PMADDUBSWrr, X86::PMADDUBSWrm, TB_ALIGN_16 }, + { X86::PMADDWDrr, X86::PMADDWDrm, TB_ALIGN_16 }, + { X86::PMAXSBrr, X86::PMAXSBrm, TB_ALIGN_16 }, + { X86::PMAXSDrr, X86::PMAXSDrm, TB_ALIGN_16 }, + { X86::PMAXSWrr, X86::PMAXSWrm, TB_ALIGN_16 }, + { X86::PMAXUBrr, X86::PMAXUBrm, TB_ALIGN_16 }, + { X86::PMAXUDrr, X86::PMAXUDrm, TB_ALIGN_16 }, + { X86::PMAXUWrr, X86::PMAXUWrm, TB_ALIGN_16 }, + { X86::PMINSBrr, X86::PMINSBrm, TB_ALIGN_16 }, + { X86::PMINSDrr, X86::PMINSDrm, TB_ALIGN_16 }, + { X86::PMINSWrr, X86::PMINSWrm, TB_ALIGN_16 }, + { X86::PMINUBrr, X86::PMINUBrm, TB_ALIGN_16 }, + { X86::PMINUDrr, X86::PMINUDrm, TB_ALIGN_16 }, + { X86::PMINUWrr, X86::PMINUWrm, TB_ALIGN_16 }, + { X86::PMULDQrr, X86::PMULDQrm, TB_ALIGN_16 }, + { X86::PMULHRSWrr, X86::PMULHRSWrm, TB_ALIGN_16 }, + { X86::PMULHUWrr, X86::PMULHUWrm, TB_ALIGN_16 }, + { X86::PMULHWrr, X86::PMULHWrm, TB_ALIGN_16 }, + { X86::PMULLDrr, X86::PMULLDrm, TB_ALIGN_16 }, + { X86::PMULLWrr, X86::PMULLWrm, TB_ALIGN_16 }, + { X86::PMULUDQrr, X86::PMULUDQrm, TB_ALIGN_16 }, + { X86::PORrr, X86::PORrm, TB_ALIGN_16 }, + { X86::PSADBWrr, X86::PSADBWrm, TB_ALIGN_16 }, + { X86::PSHUFBrr, X86::PSHUFBrm, TB_ALIGN_16 }, + { X86::PSIGNBrr128, X86::PSIGNBrm128, TB_ALIGN_16 }, + { X86::PSIGNWrr128, X86::PSIGNWrm128, TB_ALIGN_16 }, + { X86::PSIGNDrr128, X86::PSIGNDrm128, TB_ALIGN_16 }, + { X86::PSLLDrr, X86::PSLLDrm, TB_ALIGN_16 }, + { X86::PSLLQrr, X86::PSLLQrm, TB_ALIGN_16 }, + { X86::PSLLWrr, X86::PSLLWrm, TB_ALIGN_16 }, + { X86::PSRADrr, X86::PSRADrm, TB_ALIGN_16 }, + { X86::PSRAWrr, X86::PSRAWrm, TB_ALIGN_16 }, + { X86::PSRLDrr, X86::PSRLDrm, TB_ALIGN_16 }, + { X86::PSRLQrr, X86::PSRLQrm, TB_ALIGN_16 }, + { X86::PSRLWrr, X86::PSRLWrm, TB_ALIGN_16 }, + { X86::PSUBBrr, X86::PSUBBrm, TB_ALIGN_16 }, + { X86::PSUBDrr, X86::PSUBDrm, TB_ALIGN_16 }, + { X86::PSUBQrr, X86::PSUBQrm, TB_ALIGN_16 }, + { X86::PSUBSBrr, X86::PSUBSBrm, TB_ALIGN_16 }, + { X86::PSUBSWrr, X86::PSUBSWrm, TB_ALIGN_16 }, + { X86::PSUBUSBrr, X86::PSUBUSBrm, TB_ALIGN_16 }, + { X86::PSUBUSWrr, X86::PSUBUSWrm, TB_ALIGN_16 }, + { X86::PSUBWrr, X86::PSUBWrm, TB_ALIGN_16 }, + { X86::PUNPCKHBWrr, X86::PUNPCKHBWrm, TB_ALIGN_16 }, + { X86::PUNPCKHDQrr, X86::PUNPCKHDQrm, TB_ALIGN_16 }, + { X86::PUNPCKHQDQrr, X86::PUNPCKHQDQrm, TB_ALIGN_16 }, + { X86::PUNPCKHWDrr, X86::PUNPCKHWDrm, TB_ALIGN_16 }, + { X86::PUNPCKLBWrr, X86::PUNPCKLBWrm, TB_ALIGN_16 }, + { X86::PUNPCKLDQrr, X86::PUNPCKLDQrm, TB_ALIGN_16 }, + { X86::PUNPCKLQDQrr, X86::PUNPCKLQDQrm, TB_ALIGN_16 }, + { X86::PUNPCKLWDrr, X86::PUNPCKLWDrm, TB_ALIGN_16 }, + { X86::PXORrr, X86::PXORrm, TB_ALIGN_16 }, + { X86::ROUNDSDr_Int, X86::ROUNDSDm_Int, TB_NO_REVERSE }, + { X86::ROUNDSSr_Int, X86::ROUNDSSm_Int, TB_NO_REVERSE }, + { X86::SBB32rr, X86::SBB32rm, 0 }, + { X86::SBB64rr, X86::SBB64rm, 0 }, + { X86::SHUFPDrri, X86::SHUFPDrmi, TB_ALIGN_16 }, + { X86::SHUFPSrri, X86::SHUFPSrmi, TB_ALIGN_16 }, + { X86::SUB16rr, X86::SUB16rm, 0 }, + { X86::SUB32rr, X86::SUB32rm, 0 }, + { X86::SUB64rr, X86::SUB64rm, 0 }, + { X86::SUB8rr, X86::SUB8rm, 0 }, + { X86::SUBPDrr, X86::SUBPDrm, TB_ALIGN_16 }, + { X86::SUBPSrr, X86::SUBPSrm, TB_ALIGN_16 }, + { X86::SUBSDrr, X86::SUBSDrm, 0 }, + { X86::SUBSDrr_Int, X86::SUBSDrm_Int, TB_NO_REVERSE }, + { X86::SUBSSrr, X86::SUBSSrm, 0 }, + { X86::SUBSSrr_Int, X86::SUBSSrm_Int, TB_NO_REVERSE }, + // FIXME: TEST*rr -> swapped operand of TEST*mr. + { X86::UNPCKHPDrr, X86::UNPCKHPDrm, TB_ALIGN_16 }, + { X86::UNPCKHPSrr, X86::UNPCKHPSrm, TB_ALIGN_16 }, + { X86::UNPCKLPDrr, X86::UNPCKLPDrm, TB_ALIGN_16 }, + { X86::UNPCKLPSrr, X86::UNPCKLPSrm, TB_ALIGN_16 }, + { X86::XOR16rr, X86::XOR16rm, 0 }, + { X86::XOR32rr, X86::XOR32rm, 0 }, + { X86::XOR64rr, X86::XOR64rm, 0 }, + { X86::XOR8rr, X86::XOR8rm, 0 }, + { X86::XORPDrr, X86::XORPDrm, TB_ALIGN_16 }, + { X86::XORPSrr, X86::XORPSrm, TB_ALIGN_16 }, + + // MMX version of foldable instructions + { X86::MMX_CVTPI2PSirr, X86::MMX_CVTPI2PSirm, 0 }, + { X86::MMX_PACKSSDWirr, X86::MMX_PACKSSDWirm, 0 }, + { X86::MMX_PACKSSWBirr, X86::MMX_PACKSSWBirm, 0 }, + { X86::MMX_PACKUSWBirr, X86::MMX_PACKUSWBirm, 0 }, + { X86::MMX_PADDBirr, X86::MMX_PADDBirm, 0 }, + { X86::MMX_PADDDirr, X86::MMX_PADDDirm, 0 }, + { X86::MMX_PADDQirr, X86::MMX_PADDQirm, 0 }, + { X86::MMX_PADDSBirr, X86::MMX_PADDSBirm, 0 }, + { X86::MMX_PADDSWirr, X86::MMX_PADDSWirm, 0 }, + { X86::MMX_PADDUSBirr, X86::MMX_PADDUSBirm, 0 }, + { X86::MMX_PADDUSWirr, X86::MMX_PADDUSWirm, 0 }, + { X86::MMX_PADDWirr, X86::MMX_PADDWirm, 0 }, + { X86::MMX_PALIGNR64irr, X86::MMX_PALIGNR64irm, 0 }, + { X86::MMX_PANDNirr, X86::MMX_PANDNirm, 0 }, + { X86::MMX_PANDirr, X86::MMX_PANDirm, 0 }, + { X86::MMX_PAVGBirr, X86::MMX_PAVGBirm, 0 }, + { X86::MMX_PAVGWirr, X86::MMX_PAVGWirm, 0 }, + { X86::MMX_PCMPEQBirr, X86::MMX_PCMPEQBirm, 0 }, + { X86::MMX_PCMPEQDirr, X86::MMX_PCMPEQDirm, 0 }, + { X86::MMX_PCMPEQWirr, X86::MMX_PCMPEQWirm, 0 }, + { X86::MMX_PCMPGTBirr, X86::MMX_PCMPGTBirm, 0 }, + { X86::MMX_PCMPGTDirr, X86::MMX_PCMPGTDirm, 0 }, + { X86::MMX_PCMPGTWirr, X86::MMX_PCMPGTWirm, 0 }, + { X86::MMX_PHADDSWrr64, X86::MMX_PHADDSWrm64, 0 }, + { X86::MMX_PHADDWrr64, X86::MMX_PHADDWrm64, 0 }, + { X86::MMX_PHADDrr64, X86::MMX_PHADDrm64, 0 }, + { X86::MMX_PHSUBDrr64, X86::MMX_PHSUBDrm64, 0 }, + { X86::MMX_PHSUBSWrr64, X86::MMX_PHSUBSWrm64, 0 }, + { X86::MMX_PHSUBWrr64, X86::MMX_PHSUBWrm64, 0 }, + { X86::MMX_PINSRWirri, X86::MMX_PINSRWirmi, 0 }, + { X86::MMX_PMADDUBSWrr64, X86::MMX_PMADDUBSWrm64, 0 }, + { X86::MMX_PMADDWDirr, X86::MMX_PMADDWDirm, 0 }, + { X86::MMX_PMAXSWirr, X86::MMX_PMAXSWirm, 0 }, + { X86::MMX_PMAXUBirr, X86::MMX_PMAXUBirm, 0 }, + { X86::MMX_PMINSWirr, X86::MMX_PMINSWirm, 0 }, + { X86::MMX_PMINUBirr, X86::MMX_PMINUBirm, 0 }, + { X86::MMX_PMULHRSWrr64, X86::MMX_PMULHRSWrm64, 0 }, + { X86::MMX_PMULHUWirr, X86::MMX_PMULHUWirm, 0 }, + { X86::MMX_PMULHWirr, X86::MMX_PMULHWirm, 0 }, + { X86::MMX_PMULLWirr, X86::MMX_PMULLWirm, 0 }, + { X86::MMX_PMULUDQirr, X86::MMX_PMULUDQirm, 0 }, + { X86::MMX_PORirr, X86::MMX_PORirm, 0 }, + { X86::MMX_PSADBWirr, X86::MMX_PSADBWirm, 0 }, + { X86::MMX_PSHUFBrr64, X86::MMX_PSHUFBrm64, 0 }, + { X86::MMX_PSIGNBrr64, X86::MMX_PSIGNBrm64, 0 }, + { X86::MMX_PSIGNDrr64, X86::MMX_PSIGNDrm64, 0 }, + { X86::MMX_PSIGNWrr64, X86::MMX_PSIGNWrm64, 0 }, + { X86::MMX_PSLLDrr, X86::MMX_PSLLDrm, 0 }, + { X86::MMX_PSLLQrr, X86::MMX_PSLLQrm, 0 }, + { X86::MMX_PSLLWrr, X86::MMX_PSLLWrm, 0 }, + { X86::MMX_PSRADrr, X86::MMX_PSRADrm, 0 }, + { X86::MMX_PSRAWrr, X86::MMX_PSRAWrm, 0 }, + { X86::MMX_PSRLDrr, X86::MMX_PSRLDrm, 0 }, + { X86::MMX_PSRLQrr, X86::MMX_PSRLQrm, 0 }, + { X86::MMX_PSRLWrr, X86::MMX_PSRLWrm, 0 }, + { X86::MMX_PSUBBirr, X86::MMX_PSUBBirm, 0 }, + { X86::MMX_PSUBDirr, X86::MMX_PSUBDirm, 0 }, + { X86::MMX_PSUBQirr, X86::MMX_PSUBQirm, 0 }, + { X86::MMX_PSUBSBirr, X86::MMX_PSUBSBirm, 0 }, + { X86::MMX_PSUBSWirr, X86::MMX_PSUBSWirm, 0 }, + { X86::MMX_PSUBUSBirr, X86::MMX_PSUBUSBirm, 0 }, + { X86::MMX_PSUBUSWirr, X86::MMX_PSUBUSWirm, 0 }, + { X86::MMX_PSUBWirr, X86::MMX_PSUBWirm, 0 }, + { X86::MMX_PUNPCKHBWirr, X86::MMX_PUNPCKHBWirm, 0 }, + { X86::MMX_PUNPCKHDQirr, X86::MMX_PUNPCKHDQirm, 0 }, + { X86::MMX_PUNPCKHWDirr, X86::MMX_PUNPCKHWDirm, 0 }, + { X86::MMX_PUNPCKLBWirr, X86::MMX_PUNPCKLBWirm, 0 }, + { X86::MMX_PUNPCKLDQirr, X86::MMX_PUNPCKLDQirm, 0 }, + { X86::MMX_PUNPCKLWDirr, X86::MMX_PUNPCKLWDirm, 0 }, + { X86::MMX_PXORirr, X86::MMX_PXORirm, 0 }, + + // 3DNow! version of foldable instructions + { X86::PAVGUSBrr, X86::PAVGUSBrm, 0 }, + { X86::PFACCrr, X86::PFACCrm, 0 }, + { X86::PFADDrr, X86::PFADDrm, 0 }, + { X86::PFCMPEQrr, X86::PFCMPEQrm, 0 }, + { X86::PFCMPGErr, X86::PFCMPGErm, 0 }, + { X86::PFCMPGTrr, X86::PFCMPGTrm, 0 }, + { X86::PFMAXrr, X86::PFMAXrm, 0 }, + { X86::PFMINrr, X86::PFMINrm, 0 }, + { X86::PFMULrr, X86::PFMULrm, 0 }, + { X86::PFNACCrr, X86::PFNACCrm, 0 }, + { X86::PFPNACCrr, X86::PFPNACCrm, 0 }, + { X86::PFRCPIT1rr, X86::PFRCPIT1rm, 0 }, + { X86::PFRCPIT2rr, X86::PFRCPIT2rm, 0 }, + { X86::PFRSQIT1rr, X86::PFRSQIT1rm, 0 }, + { X86::PFSUBrr, X86::PFSUBrm, 0 }, + { X86::PFSUBRrr, X86::PFSUBRrm, 0 }, + { X86::PMULHRWrr, X86::PMULHRWrm, 0 }, + + // AVX 128-bit versions of foldable instructions + { X86::VCVTSI2SD64rr, X86::VCVTSI2SD64rm, 0 }, + { X86::Int_VCVTSI2SD64rr, X86::Int_VCVTSI2SD64rm, 0 }, + { X86::VCVTSI2SDrr, X86::VCVTSI2SDrm, 0 }, + { X86::Int_VCVTSI2SDrr, X86::Int_VCVTSI2SDrm, 0 }, + { X86::VCVTSI2SS64rr, X86::VCVTSI2SS64rm, 0 }, + { X86::Int_VCVTSI2SS64rr, X86::Int_VCVTSI2SS64rm, 0 }, + { X86::VCVTSI2SSrr, X86::VCVTSI2SSrm, 0 }, + { X86::Int_VCVTSI2SSrr, X86::Int_VCVTSI2SSrm, 0 }, + { X86::VADDPDrr, X86::VADDPDrm, 0 }, + { X86::VADDPSrr, X86::VADDPSrm, 0 }, + { X86::VADDSDrr, X86::VADDSDrm, 0 }, + { X86::VADDSDrr_Int, X86::VADDSDrm_Int, TB_NO_REVERSE }, + { X86::VADDSSrr, X86::VADDSSrm, 0 }, + { X86::VADDSSrr_Int, X86::VADDSSrm_Int, TB_NO_REVERSE }, + { 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, 0 }, + { X86::VDIVPSrr, X86::VDIVPSrm, 0 }, + { X86::VDIVSDrr, X86::VDIVSDrm, 0 }, + { X86::VDIVSDrr_Int, X86::VDIVSDrm_Int, TB_NO_REVERSE }, + { X86::VDIVSSrr, X86::VDIVSSrm, 0 }, + { X86::VDIVSSrr_Int, X86::VDIVSSrm_Int, TB_NO_REVERSE }, + { X86::VDPPDrri, X86::VDPPDrmi, 0 }, + { X86::VDPPSrri, X86::VDPPSrmi, 0 }, + { X86::VHADDPDrr, X86::VHADDPDrm, 0 }, + { X86::VHADDPSrr, X86::VHADDPSrm, 0 }, + { X86::VHSUBPDrr, X86::VHSUBPDrm, 0 }, + { X86::VHSUBPSrr, X86::VHSUBPSrm, 0 }, + { X86::Int_VCMPSDrr, X86::Int_VCMPSDrm, TB_NO_REVERSE }, + { X86::Int_VCMPSSrr, X86::Int_VCMPSSrm, TB_NO_REVERSE }, + { X86::VMAXCPDrr, X86::VMAXCPDrm, 0 }, + { X86::VMAXCPSrr, X86::VMAXCPSrm, 0 }, + { X86::VMAXCSDrr, X86::VMAXCSDrm, 0 }, + { X86::VMAXCSSrr, X86::VMAXCSSrm, 0 }, + { X86::VMAXPDrr, X86::VMAXPDrm, 0 }, + { X86::VMAXPSrr, X86::VMAXPSrm, 0 }, + { X86::VMAXSDrr, X86::VMAXSDrm, 0 }, + { X86::VMAXSDrr_Int, X86::VMAXSDrm_Int, TB_NO_REVERSE }, + { X86::VMAXSSrr, X86::VMAXSSrm, 0 }, + { X86::VMAXSSrr_Int, X86::VMAXSSrm_Int, TB_NO_REVERSE }, + { X86::VMINCPDrr, X86::VMINCPDrm, 0 }, + { X86::VMINCPSrr, X86::VMINCPSrm, 0 }, + { X86::VMINCSDrr, X86::VMINCSDrm, 0 }, + { X86::VMINCSSrr, X86::VMINCSSrm, 0 }, + { X86::VMINPDrr, X86::VMINPDrm, 0 }, + { X86::VMINPSrr, X86::VMINPSrm, 0 }, + { X86::VMINSDrr, X86::VMINSDrm, 0 }, + { X86::VMINSDrr_Int, X86::VMINSDrm_Int, TB_NO_REVERSE }, + { X86::VMINSSrr, X86::VMINSSrm, 0 }, + { X86::VMINSSrr_Int, X86::VMINSSrm_Int, TB_NO_REVERSE }, + { X86::VMOVLHPSrr, X86::VMOVHPSrm, TB_NO_REVERSE }, + { X86::VMPSADBWrri, X86::VMPSADBWrmi, 0 }, + { X86::VMULPDrr, X86::VMULPDrm, 0 }, + { X86::VMULPSrr, X86::VMULPSrm, 0 }, + { X86::VMULSDrr, X86::VMULSDrm, 0 }, + { X86::VMULSDrr_Int, X86::VMULSDrm_Int, TB_NO_REVERSE }, + { X86::VMULSSrr, X86::VMULSSrm, 0 }, + { X86::VMULSSrr_Int, X86::VMULSSrm_Int, TB_NO_REVERSE }, + { 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::VPALIGNRrri, X86::VPALIGNRrmi, 0 }, + { X86::VPANDNrr, X86::VPANDNrm, 0 }, + { X86::VPANDrr, X86::VPANDrm, 0 }, + { X86::VPAVGBrr, X86::VPAVGBrm, 0 }, + { X86::VPAVGWrr, X86::VPAVGWrm, 0 }, + { X86::VPBLENDVBrr, X86::VPBLENDVBrm, 0 }, + { X86::VPBLENDWrri, X86::VPBLENDWrmi, 0 }, + { X86::VPCLMULQDQrr, X86::VPCLMULQDQrm, 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::VPINSRBrr, X86::VPINSRBrm, 0 }, + { X86::VPINSRDrr, X86::VPINSRDrm, 0 }, + { X86::VPINSRQrr, X86::VPINSRQrm, 0 }, + { X86::VPINSRWrri, X86::VPINSRWrmi, 0 }, + { X86::VPMADDUBSWrr, X86::VPMADDUBSWrm, 0 }, + { X86::VPMADDWDrr, X86::VPMADDWDrm, 0 }, + { X86::VPMAXSBrr, X86::VPMAXSBrm, 0 }, + { X86::VPMAXSDrr, X86::VPMAXSDrm, 0 }, + { X86::VPMAXSWrr, X86::VPMAXSWrm, 0 }, + { X86::VPMAXUBrr, X86::VPMAXUBrm, 0 }, + { X86::VPMAXUDrr, X86::VPMAXUDrm, 0 }, + { X86::VPMAXUWrr, X86::VPMAXUWrm, 0 }, + { X86::VPMINSBrr, X86::VPMINSBrm, 0 }, + { X86::VPMINSDrr, X86::VPMINSDrm, 0 }, + { X86::VPMINSWrr, X86::VPMINSWrm, 0 }, + { X86::VPMINUBrr, X86::VPMINUBrm, 0 }, + { X86::VPMINUDrr, X86::VPMINUDrm, 0 }, + { X86::VPMINUWrr, X86::VPMINUWrm, 0 }, + { X86::VPMULDQrr, X86::VPMULDQrm, 0 }, + { X86::VPMULHRSWrr, X86::VPMULHRSWrm, 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::VPSIGNBrr128, X86::VPSIGNBrm128, 0 }, + { X86::VPSIGNWrr128, X86::VPSIGNWrm128, 0 }, + { X86::VPSIGNDrr128, X86::VPSIGNDrm128, 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::VPSUBQrr, X86::VPSUBQrm, 0 }, + { X86::VPSUBSBrr, X86::VPSUBSBrm, 0 }, + { X86::VPSUBSWrr, X86::VPSUBSWrm, 0 }, + { X86::VPSUBUSBrr, X86::VPSUBUSBrm, 0 }, + { X86::VPSUBUSWrr, X86::VPSUBUSWrm, 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::VRCPSSr, X86::VRCPSSm, 0 }, + { X86::VRCPSSr_Int, X86::VRCPSSm_Int, TB_NO_REVERSE }, + { X86::VRSQRTSSr, X86::VRSQRTSSm, 0 }, + { X86::VRSQRTSSr_Int, X86::VRSQRTSSm_Int, TB_NO_REVERSE }, + { X86::VROUNDSDr, X86::VROUNDSDm, 0 }, + { X86::VROUNDSDr_Int, X86::VROUNDSDm_Int, TB_NO_REVERSE }, + { X86::VROUNDSSr, X86::VROUNDSSm, 0 }, + { X86::VROUNDSSr_Int, X86::VROUNDSSm_Int, TB_NO_REVERSE }, + { X86::VSHUFPDrri, X86::VSHUFPDrmi, 0 }, + { X86::VSHUFPSrri, X86::VSHUFPSrmi, 0 }, + { X86::VSQRTSDr, X86::VSQRTSDm, 0 }, + { X86::VSQRTSDr_Int, X86::VSQRTSDm_Int, TB_NO_REVERSE }, + { X86::VSQRTSSr, X86::VSQRTSSm, 0 }, + { X86::VSQRTSSr_Int, X86::VSQRTSSm_Int, TB_NO_REVERSE }, + { X86::VSUBPDrr, X86::VSUBPDrm, 0 }, + { X86::VSUBPSrr, X86::VSUBPSrm, 0 }, + { X86::VSUBSDrr, X86::VSUBSDrm, 0 }, + { X86::VSUBSDrr_Int, X86::VSUBSDrm_Int, TB_NO_REVERSE }, + { X86::VSUBSSrr, X86::VSUBSSrm, 0 }, + { X86::VSUBSSrr_Int, X86::VSUBSSrm_Int, TB_NO_REVERSE }, + { 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, 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::VDPPSYrri, X86::VDPPSYrmi, 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::VMAXCPDYrr, X86::VMAXCPDYrm, 0 }, + { X86::VMAXCPSYrr, X86::VMAXCPSYrm, 0 }, + { X86::VMAXPDYrr, X86::VMAXPDYrm, 0 }, + { X86::VMAXPSYrr, X86::VMAXPSYrm, 0 }, + { X86::VMINCPDYrr, X86::VMINCPDYrm, 0 }, + { X86::VMINCPSYrr, X86::VMINCPSYrm, 0 }, + { X86::VMINPDYrr, X86::VMINPDYrm, 0 }, + { X86::VMINPSYrr, X86::VMINPSYrm, 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, 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::VPALIGNRYrri, X86::VPALIGNRYrmi, 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::VPBLENDVBYrr, X86::VPBLENDVBYrm, 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::VPERMPSYrr, X86::VPERMPSYrm, 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::VPMADDUBSWYrr, X86::VPMADDUBSWYrm, 0 }, + { X86::VPMADDWDYrr, X86::VPMADDWDYrm, 0 }, + { X86::VPMAXSBYrr, X86::VPMAXSBYrm, 0 }, + { X86::VPMAXSDYrr, X86::VPMAXSDYrm, 0 }, + { X86::VPMAXSWYrr, X86::VPMAXSWYrm, 0 }, + { X86::VPMAXUBYrr, X86::VPMAXUBYrm, 0 }, + { X86::VPMAXUDYrr, X86::VPMAXUDYrm, 0 }, + { X86::VPMAXUWYrr, X86::VPMAXUWYrm, 0 }, + { X86::VPMINSBYrr, X86::VPMINSBYrm, 0 }, + { X86::VPMINSDYrr, X86::VPMINSDYrm, 0 }, + { X86::VPMINSWYrr, X86::VPMINSWYrm, 0 }, + { X86::VPMINUBYrr, X86::VPMINUBYrm, 0 }, + { X86::VPMINUDYrr, X86::VPMINUDYrm, 0 }, + { X86::VPMINUWYrr, X86::VPMINUWYrm, 0 }, + { X86::VMPSADBWYrri, X86::VMPSADBWYrmi, 0 }, + { X86::VPMULDQYrr, X86::VPMULDQYrm, 0 }, + { X86::VPMULHRSWYrr, X86::VPMULHRSWYrm, 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::VPSIGNBYrr256, X86::VPSIGNBYrm256, 0 }, + { X86::VPSIGNWYrr256, X86::VPSIGNWYrm256, 0 }, + { X86::VPSIGNDYrr256, X86::VPSIGNDYrm256, 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::VPSUBQYrr, X86::VPSUBQYrm, 0 }, + { X86::VPSUBSBYrr, X86::VPSUBSBYrm, 0 }, + { X86::VPSUBSWYrr, X86::VPSUBSWYrm, 0 }, + { X86::VPSUBUSBYrr, X86::VPSUBUSBYrm, 0 }, + { X86::VPSUBUSWYrr, X86::VPSUBUSWYrm, 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 }, + + // FMA4 foldable patterns + { X86::VFMADDSS4rr, X86::VFMADDSS4mr, TB_ALIGN_NONE }, + { X86::VFMADDSS4rr_Int, X86::VFMADDSS4mr_Int, TB_NO_REVERSE }, + { X86::VFMADDSD4rr, X86::VFMADDSD4mr, TB_ALIGN_NONE }, + { X86::VFMADDSD4rr_Int, X86::VFMADDSD4mr_Int, TB_NO_REVERSE }, + { X86::VFMADDPS4rr, X86::VFMADDPS4mr, TB_ALIGN_NONE }, + { X86::VFMADDPD4rr, X86::VFMADDPD4mr, TB_ALIGN_NONE }, + { X86::VFMADDPS4Yrr, X86::VFMADDPS4Ymr, TB_ALIGN_NONE }, + { X86::VFMADDPD4Yrr, X86::VFMADDPD4Ymr, TB_ALIGN_NONE }, + { X86::VFNMADDSS4rr, X86::VFNMADDSS4mr, TB_ALIGN_NONE }, + { X86::VFNMADDSS4rr_Int, X86::VFNMADDSS4mr_Int, TB_NO_REVERSE }, + { X86::VFNMADDSD4rr, X86::VFNMADDSD4mr, TB_ALIGN_NONE }, + { X86::VFNMADDSD4rr_Int, X86::VFNMADDSD4mr_Int, TB_NO_REVERSE }, + { X86::VFNMADDPS4rr, X86::VFNMADDPS4mr, TB_ALIGN_NONE }, + { X86::VFNMADDPD4rr, X86::VFNMADDPD4mr, TB_ALIGN_NONE }, + { X86::VFNMADDPS4Yrr, X86::VFNMADDPS4Ymr, TB_ALIGN_NONE }, + { X86::VFNMADDPD4Yrr, X86::VFNMADDPD4Ymr, TB_ALIGN_NONE }, + { X86::VFMSUBSS4rr, X86::VFMSUBSS4mr, TB_ALIGN_NONE }, + { X86::VFMSUBSS4rr_Int, X86::VFMSUBSS4mr_Int, TB_NO_REVERSE }, + { X86::VFMSUBSD4rr, X86::VFMSUBSD4mr, TB_ALIGN_NONE }, + { X86::VFMSUBSD4rr_Int, X86::VFMSUBSD4mr_Int, TB_NO_REVERSE }, + { X86::VFMSUBPS4rr, X86::VFMSUBPS4mr, TB_ALIGN_NONE }, + { X86::VFMSUBPD4rr, X86::VFMSUBPD4mr, TB_ALIGN_NONE }, + { X86::VFMSUBPS4Yrr, X86::VFMSUBPS4Ymr, TB_ALIGN_NONE }, + { X86::VFMSUBPD4Yrr, X86::VFMSUBPD4Ymr, TB_ALIGN_NONE }, + { X86::VFNMSUBSS4rr, X86::VFNMSUBSS4mr, TB_ALIGN_NONE }, + { X86::VFNMSUBSS4rr_Int, X86::VFNMSUBSS4mr_Int, TB_NO_REVERSE }, + { X86::VFNMSUBSD4rr, X86::VFNMSUBSD4mr, TB_ALIGN_NONE }, + { X86::VFNMSUBSD4rr_Int, X86::VFNMSUBSD4mr_Int, TB_NO_REVERSE }, + { X86::VFNMSUBPS4rr, X86::VFNMSUBPS4mr, TB_ALIGN_NONE }, + { X86::VFNMSUBPD4rr, X86::VFNMSUBPD4mr, TB_ALIGN_NONE }, + { X86::VFNMSUBPS4Yrr, X86::VFNMSUBPS4Ymr, TB_ALIGN_NONE }, + { X86::VFNMSUBPD4Yrr, X86::VFNMSUBPD4Ymr, TB_ALIGN_NONE }, + { X86::VFMADDSUBPS4rr, X86::VFMADDSUBPS4mr, TB_ALIGN_NONE }, + { X86::VFMADDSUBPD4rr, X86::VFMADDSUBPD4mr, TB_ALIGN_NONE }, + { X86::VFMADDSUBPS4Yrr, X86::VFMADDSUBPS4Ymr, TB_ALIGN_NONE }, + { X86::VFMADDSUBPD4Yrr, X86::VFMADDSUBPD4Ymr, TB_ALIGN_NONE }, + { X86::VFMSUBADDPS4rr, X86::VFMSUBADDPS4mr, TB_ALIGN_NONE }, + { X86::VFMSUBADDPD4rr, X86::VFMSUBADDPD4mr, TB_ALIGN_NONE }, + { X86::VFMSUBADDPS4Yrr, X86::VFMSUBADDPS4Ymr, TB_ALIGN_NONE }, + { X86::VFMSUBADDPD4Yrr, X86::VFMSUBADDPD4Ymr, TB_ALIGN_NONE }, + + // XOP foldable instructions + { X86::VPCMOVrrr, X86::VPCMOVrmr, 0 }, + { X86::VPCMOVYrrr, X86::VPCMOVYrmr, 0 }, + { X86::VPCOMBri, X86::VPCOMBmi, 0 }, + { X86::VPCOMDri, X86::VPCOMDmi, 0 }, + { X86::VPCOMQri, X86::VPCOMQmi, 0 }, + { X86::VPCOMWri, X86::VPCOMWmi, 0 }, + { X86::VPCOMUBri, X86::VPCOMUBmi, 0 }, + { X86::VPCOMUDri, X86::VPCOMUDmi, 0 }, + { X86::VPCOMUQri, X86::VPCOMUQmi, 0 }, + { X86::VPCOMUWri, X86::VPCOMUWmi, 0 }, + { X86::VPERMIL2PDrr, X86::VPERMIL2PDmr, 0 }, + { X86::VPERMIL2PDYrr, X86::VPERMIL2PDYmr, 0 }, + { X86::VPERMIL2PSrr, X86::VPERMIL2PSmr, 0 }, + { X86::VPERMIL2PSYrr, X86::VPERMIL2PSYmr, 0 }, + { X86::VPMACSDDrr, X86::VPMACSDDrm, 0 }, + { X86::VPMACSDQHrr, X86::VPMACSDQHrm, 0 }, + { X86::VPMACSDQLrr, X86::VPMACSDQLrm, 0 }, + { X86::VPMACSSDDrr, X86::VPMACSSDDrm, 0 }, + { X86::VPMACSSDQHrr, X86::VPMACSSDQHrm, 0 }, + { X86::VPMACSSDQLrr, X86::VPMACSSDQLrm, 0 }, + { X86::VPMACSSWDrr, X86::VPMACSSWDrm, 0 }, + { X86::VPMACSSWWrr, X86::VPMACSSWWrm, 0 }, + { X86::VPMACSWDrr, X86::VPMACSWDrm, 0 }, + { X86::VPMACSWWrr, X86::VPMACSWWrm, 0 }, + { X86::VPMADCSSWDrr, X86::VPMADCSSWDrm, 0 }, + { X86::VPMADCSWDrr, X86::VPMADCSWDrm, 0 }, + { X86::VPPERMrrr, X86::VPPERMrmr, 0 }, + { X86::VPROTBrr, X86::VPROTBrm, 0 }, + { X86::VPROTDrr, X86::VPROTDrm, 0 }, + { X86::VPROTQrr, X86::VPROTQrm, 0 }, + { X86::VPROTWrr, X86::VPROTWrm, 0 }, + { X86::VPSHABrr, X86::VPSHABrm, 0 }, + { X86::VPSHADrr, X86::VPSHADrm, 0 }, + { X86::VPSHAQrr, X86::VPSHAQrm, 0 }, + { X86::VPSHAWrr, X86::VPSHAWrm, 0 }, + { X86::VPSHLBrr, X86::VPSHLBrm, 0 }, + { X86::VPSHLDrr, X86::VPSHLDrm, 0 }, + { X86::VPSHLQrr, X86::VPSHLQrm, 0 }, + { X86::VPSHLWrr, X86::VPSHLWrm, 0 }, + + // BMI/BMI2 foldable instructions + { X86::ANDN32rr, X86::ANDN32rm, 0 }, + { X86::ANDN64rr, X86::ANDN64rm, 0 }, + { X86::MULX32rr, X86::MULX32rm, 0 }, + { X86::MULX64rr, X86::MULX64rm, 0 }, + { X86::PDEP32rr, X86::PDEP32rm, 0 }, + { X86::PDEP64rr, X86::PDEP64rm, 0 }, + { X86::PEXT32rr, X86::PEXT32rm, 0 }, + { X86::PEXT64rr, X86::PEXT64rm, 0 }, + + // ADX foldable instructions + { X86::ADCX32rr, X86::ADCX32rm, 0 }, + { X86::ADCX64rr, X86::ADCX64rm, 0 }, + { X86::ADOX32rr, X86::ADOX32rm, 0 }, + { X86::ADOX64rr, X86::ADOX64rm, 0 }, + + // AVX-512 foldable instructions + { X86::VADDPDZrr, X86::VADDPDZrm, 0 }, + { X86::VADDPSZrr, X86::VADDPSZrm, 0 }, + { X86::VADDSDZrr, X86::VADDSDZrm, 0 }, + { X86::VADDSDZrr_Int, X86::VADDSDZrm_Int, TB_NO_REVERSE }, + { X86::VADDSSZrr, X86::VADDSSZrm, 0 }, + { X86::VADDSSZrr_Int, X86::VADDSSZrm_Int, TB_NO_REVERSE }, + { X86::VALIGNDZrri, X86::VALIGNDZrmi, 0 }, + { X86::VALIGNQZrri, X86::VALIGNQZrmi, 0 }, + { X86::VANDNPDZrr, X86::VANDNPDZrm, 0 }, + { X86::VANDNPSZrr, X86::VANDNPSZrm, 0 }, + { X86::VANDPDZrr, X86::VANDPDZrm, 0 }, + { X86::VANDPSZrr, X86::VANDPSZrm, 0 }, + { X86::VCMPPDZrri, X86::VCMPPDZrmi, 0 }, + { X86::VCMPPSZrri, X86::VCMPPSZrmi, 0 }, + { X86::VCMPSDZrr, X86::VCMPSDZrm, 0 }, + { X86::VCMPSDZrr_Int, X86::VCMPSDZrm_Int, TB_NO_REVERSE }, + { X86::VCMPSSZrr, X86::VCMPSSZrm, 0 }, + { X86::VCMPSSZrr_Int, X86::VCMPSSZrm_Int, TB_NO_REVERSE }, + { X86::VDIVPDZrr, X86::VDIVPDZrm, 0 }, + { X86::VDIVPSZrr, X86::VDIVPSZrm, 0 }, + { X86::VDIVSDZrr, X86::VDIVSDZrm, 0 }, + { X86::VDIVSDZrr_Int, X86::VDIVSDZrm_Int, TB_NO_REVERSE }, + { X86::VDIVSSZrr, X86::VDIVSSZrm, 0 }, + { X86::VDIVSSZrr_Int, X86::VDIVSSZrm_Int, TB_NO_REVERSE }, + { X86::VINSERTF32x4Zrr, X86::VINSERTF32x4Zrm, 0 }, + { X86::VINSERTF32x8Zrr, X86::VINSERTF32x8Zrm, 0 }, + { X86::VINSERTF64x2Zrr, X86::VINSERTF64x2Zrm, 0 }, + { X86::VINSERTF64x4Zrr, X86::VINSERTF64x4Zrm, 0 }, + { X86::VINSERTI32x4Zrr, X86::VINSERTI32x4Zrm, 0 }, + { X86::VINSERTI32x8Zrr, X86::VINSERTI32x8Zrm, 0 }, + { X86::VINSERTI64x2Zrr, X86::VINSERTI64x2Zrm, 0 }, + { X86::VINSERTI64x4Zrr, X86::VINSERTI64x4Zrm, 0 }, + { X86::VMAXCPDZrr, X86::VMAXCPDZrm, 0 }, + { X86::VMAXCPSZrr, X86::VMAXCPSZrm, 0 }, + { X86::VMAXCSDZrr, X86::VMAXCSDZrm, 0 }, + { X86::VMAXCSSZrr, X86::VMAXCSSZrm, 0 }, + { X86::VMAXPDZrr, X86::VMAXPDZrm, 0 }, + { X86::VMAXPSZrr, X86::VMAXPSZrm, 0 }, + { X86::VMAXSDZrr, X86::VMAXSDZrm, 0 }, + { X86::VMAXSDZrr_Int, X86::VMAXSDZrm_Int, TB_NO_REVERSE }, + { X86::VMAXSSZrr, X86::VMAXSSZrm, 0 }, + { X86::VMAXSSZrr_Int, X86::VMAXSSZrm_Int, TB_NO_REVERSE }, + { X86::VMINCPDZrr, X86::VMINCPDZrm, 0 }, + { X86::VMINCPSZrr, X86::VMINCPSZrm, 0 }, + { X86::VMINCSDZrr, X86::VMINCSDZrm, 0 }, + { X86::VMINCSSZrr, X86::VMINCSSZrm, 0 }, + { X86::VMINPDZrr, X86::VMINPDZrm, 0 }, + { X86::VMINPSZrr, X86::VMINPSZrm, 0 }, + { X86::VMINSDZrr, X86::VMINSDZrm, 0 }, + { X86::VMINSDZrr_Int, X86::VMINSDZrm_Int, TB_NO_REVERSE }, + { X86::VMINSSZrr, X86::VMINSSZrm, 0 }, + { X86::VMINSSZrr_Int, X86::VMINSSZrm_Int, TB_NO_REVERSE }, + { X86::VMOVLHPSZrr, X86::VMOVHPSZ128rm, TB_NO_REVERSE }, + { X86::VMULPDZrr, X86::VMULPDZrm, 0 }, + { X86::VMULPSZrr, X86::VMULPSZrm, 0 }, + { X86::VMULSDZrr, X86::VMULSDZrm, 0 }, + { X86::VMULSDZrr_Int, X86::VMULSDZrm_Int, TB_NO_REVERSE }, + { X86::VMULSSZrr, X86::VMULSSZrm, 0 }, + { X86::VMULSSZrr_Int, X86::VMULSSZrm_Int, TB_NO_REVERSE }, + { X86::VORPDZrr, X86::VORPDZrm, 0 }, + { X86::VORPSZrr, X86::VORPSZrm, 0 }, + { X86::VPACKSSDWZrr, X86::VPACKSSDWZrm, 0 }, + { X86::VPACKSSWBZrr, X86::VPACKSSWBZrm, 0 }, + { X86::VPACKUSDWZrr, X86::VPACKUSDWZrm, 0 }, + { X86::VPACKUSWBZrr, X86::VPACKUSWBZrm, 0 }, + { X86::VPADDBZrr, X86::VPADDBZrm, 0 }, + { X86::VPADDDZrr, X86::VPADDDZrm, 0 }, + { X86::VPADDQZrr, X86::VPADDQZrm, 0 }, + { X86::VPADDSBZrr, X86::VPADDSBZrm, 0 }, + { X86::VPADDSWZrr, X86::VPADDSWZrm, 0 }, + { X86::VPADDUSBZrr, X86::VPADDUSBZrm, 0 }, + { X86::VPADDUSWZrr, X86::VPADDUSWZrm, 0 }, + { X86::VPADDWZrr, X86::VPADDWZrm, 0 }, + { X86::VPALIGNRZrri, X86::VPALIGNRZrmi, 0 }, + { X86::VPANDDZrr, X86::VPANDDZrm, 0 }, + { X86::VPANDNDZrr, X86::VPANDNDZrm, 0 }, + { X86::VPANDNQZrr, X86::VPANDNQZrm, 0 }, + { X86::VPANDQZrr, X86::VPANDQZrm, 0 }, + { X86::VPAVGBZrr, X86::VPAVGBZrm, 0 }, + { X86::VPAVGWZrr, X86::VPAVGWZrm, 0 }, + { X86::VPCMPBZrri, X86::VPCMPBZrmi, 0 }, + { X86::VPCMPDZrri, X86::VPCMPDZrmi, 0 }, + { X86::VPCMPEQBZrr, X86::VPCMPEQBZrm, 0 }, + { X86::VPCMPEQDZrr, X86::VPCMPEQDZrm, 0 }, + { X86::VPCMPEQQZrr, X86::VPCMPEQQZrm, 0 }, + { X86::VPCMPEQWZrr, X86::VPCMPEQWZrm, 0 }, + { X86::VPCMPGTBZrr, X86::VPCMPGTBZrm, 0 }, + { X86::VPCMPGTDZrr, X86::VPCMPGTDZrm, 0 }, + { X86::VPCMPGTQZrr, X86::VPCMPGTQZrm, 0 }, + { X86::VPCMPGTWZrr, X86::VPCMPGTWZrm, 0 }, + { X86::VPCMPQZrri, X86::VPCMPQZrmi, 0 }, + { X86::VPCMPUBZrri, X86::VPCMPUBZrmi, 0 }, + { X86::VPCMPUDZrri, X86::VPCMPUDZrmi, 0 }, + { X86::VPCMPUQZrri, X86::VPCMPUQZrmi, 0 }, + { X86::VPCMPUWZrri, X86::VPCMPUWZrmi, 0 }, + { X86::VPCMPWZrri, X86::VPCMPWZrmi, 0 }, + { X86::VPERMBZrr, X86::VPERMBZrm, 0 }, + { X86::VPERMDZrr, X86::VPERMDZrm, 0 }, + { X86::VPERMILPDZrr, X86::VPERMILPDZrm, 0 }, + { X86::VPERMILPSZrr, X86::VPERMILPSZrm, 0 }, + { X86::VPERMPDZrr, X86::VPERMPDZrm, 0 }, + { X86::VPERMPSZrr, X86::VPERMPSZrm, 0 }, + { X86::VPERMQZrr, X86::VPERMQZrm, 0 }, + { X86::VPERMWZrr, X86::VPERMWZrm, 0 }, + { X86::VPINSRBZrr, X86::VPINSRBZrm, 0 }, + { X86::VPINSRDZrr, X86::VPINSRDZrm, 0 }, + { X86::VPINSRQZrr, X86::VPINSRQZrm, 0 }, + { X86::VPINSRWZrr, X86::VPINSRWZrm, 0 }, + { X86::VPMADDUBSWZrr, X86::VPMADDUBSWZrm, 0 }, + { X86::VPMADDWDZrr, X86::VPMADDWDZrm, 0 }, + { X86::VPMAXSBZrr, X86::VPMAXSBZrm, 0 }, + { X86::VPMAXSDZrr, X86::VPMAXSDZrm, 0 }, + { X86::VPMAXSQZrr, X86::VPMAXSQZrm, 0 }, + { X86::VPMAXSWZrr, X86::VPMAXSWZrm, 0 }, + { X86::VPMAXUBZrr, X86::VPMAXUBZrm, 0 }, + { X86::VPMAXUDZrr, X86::VPMAXUDZrm, 0 }, + { X86::VPMAXUQZrr, X86::VPMAXUQZrm, 0 }, + { X86::VPMAXUWZrr, X86::VPMAXUWZrm, 0 }, + { X86::VPMINSBZrr, X86::VPMINSBZrm, 0 }, + { X86::VPMINSDZrr, X86::VPMINSDZrm, 0 }, + { X86::VPMINSQZrr, X86::VPMINSQZrm, 0 }, + { X86::VPMINSWZrr, X86::VPMINSWZrm, 0 }, + { X86::VPMINUBZrr, X86::VPMINUBZrm, 0 }, + { X86::VPMINUDZrr, X86::VPMINUDZrm, 0 }, + { X86::VPMINUQZrr, X86::VPMINUQZrm, 0 }, + { X86::VPMINUWZrr, X86::VPMINUWZrm, 0 }, + { X86::VPMULDQZrr, X86::VPMULDQZrm, 0 }, + { X86::VPMULLDZrr, X86::VPMULLDZrm, 0 }, + { X86::VPMULLQZrr, X86::VPMULLQZrm, 0 }, + { X86::VPMULLWZrr, X86::VPMULLWZrm, 0 }, + { X86::VPMULUDQZrr, X86::VPMULUDQZrm, 0 }, + { X86::VPORDZrr, X86::VPORDZrm, 0 }, + { X86::VPORQZrr, X86::VPORQZrm, 0 }, + { X86::VPSADBWZ512rr, X86::VPSADBWZ512rm, 0 }, + { X86::VPSHUFBZrr, X86::VPSHUFBZrm, 0 }, + { X86::VPSLLDZrr, X86::VPSLLDZrm, 0 }, + { X86::VPSLLQZrr, X86::VPSLLQZrm, 0 }, + { X86::VPSLLVDZrr, X86::VPSLLVDZrm, 0 }, + { X86::VPSLLVQZrr, X86::VPSLLVQZrm, 0 }, + { X86::VPSLLVWZrr, X86::VPSLLVWZrm, 0 }, + { X86::VPSLLWZrr, X86::VPSLLWZrm, 0 }, + { X86::VPSRADZrr, X86::VPSRADZrm, 0 }, + { X86::VPSRAQZrr, X86::VPSRAQZrm, 0 }, + { X86::VPSRAVDZrr, X86::VPSRAVDZrm, 0 }, + { X86::VPSRAVQZrr, X86::VPSRAVQZrm, 0 }, + { X86::VPSRAVWZrr, X86::VPSRAVWZrm, 0 }, + { X86::VPSRAWZrr, X86::VPSRAWZrm, 0 }, + { X86::VPSRLDZrr, X86::VPSRLDZrm, 0 }, + { X86::VPSRLQZrr, X86::VPSRLQZrm, 0 }, + { X86::VPSRLVDZrr, X86::VPSRLVDZrm, 0 }, + { X86::VPSRLVQZrr, X86::VPSRLVQZrm, 0 }, + { X86::VPSRLVWZrr, X86::VPSRLVWZrm, 0 }, + { X86::VPSRLWZrr, X86::VPSRLWZrm, 0 }, + { X86::VPSUBBZrr, X86::VPSUBBZrm, 0 }, + { X86::VPSUBDZrr, X86::VPSUBDZrm, 0 }, + { X86::VPSUBQZrr, X86::VPSUBQZrm, 0 }, + { X86::VPSUBSBZrr, X86::VPSUBSBZrm, 0 }, + { X86::VPSUBSWZrr, X86::VPSUBSWZrm, 0 }, + { X86::VPSUBUSBZrr, X86::VPSUBUSBZrm, 0 }, + { X86::VPSUBUSWZrr, X86::VPSUBUSWZrm, 0 }, + { X86::VPSUBWZrr, X86::VPSUBWZrm, 0 }, + { X86::VPUNPCKHBWZrr, X86::VPUNPCKHBWZrm, 0 }, + { X86::VPUNPCKHDQZrr, X86::VPUNPCKHDQZrm, 0 }, + { X86::VPUNPCKHQDQZrr, X86::VPUNPCKHQDQZrm, 0 }, + { X86::VPUNPCKHWDZrr, X86::VPUNPCKHWDZrm, 0 }, + { X86::VPUNPCKLBWZrr, X86::VPUNPCKLBWZrm, 0 }, + { X86::VPUNPCKLDQZrr, X86::VPUNPCKLDQZrm, 0 }, + { X86::VPUNPCKLQDQZrr, X86::VPUNPCKLQDQZrm, 0 }, + { X86::VPUNPCKLWDZrr, X86::VPUNPCKLWDZrm, 0 }, + { X86::VPXORDZrr, X86::VPXORDZrm, 0 }, + { X86::VPXORQZrr, X86::VPXORQZrm, 0 }, + { X86::VSHUFPDZrri, X86::VSHUFPDZrmi, 0 }, + { X86::VSHUFPSZrri, X86::VSHUFPSZrmi, 0 }, + { X86::VSUBPDZrr, X86::VSUBPDZrm, 0 }, + { X86::VSUBPSZrr, X86::VSUBPSZrm, 0 }, + { X86::VSUBSDZrr, X86::VSUBSDZrm, 0 }, + { X86::VSUBSDZrr_Int, X86::VSUBSDZrm_Int, TB_NO_REVERSE }, + { X86::VSUBSSZrr, X86::VSUBSSZrm, 0 }, + { X86::VSUBSSZrr_Int, X86::VSUBSSZrm_Int, TB_NO_REVERSE }, + { X86::VUNPCKHPDZrr, X86::VUNPCKHPDZrm, 0 }, + { X86::VUNPCKHPSZrr, X86::VUNPCKHPSZrm, 0 }, + { X86::VUNPCKLPDZrr, X86::VUNPCKLPDZrm, 0 }, + { X86::VUNPCKLPSZrr, X86::VUNPCKLPSZrm, 0 }, + { X86::VXORPDZrr, X86::VXORPDZrm, 0 }, + { X86::VXORPSZrr, X86::VXORPSZrm, 0 }, + + // AVX-512{F,VL} foldable instructions + { X86::VADDPDZ128rr, X86::VADDPDZ128rm, 0 }, + { X86::VADDPDZ256rr, X86::VADDPDZ256rm, 0 }, + { X86::VADDPSZ128rr, X86::VADDPSZ128rm, 0 }, + { X86::VADDPSZ256rr, X86::VADDPSZ256rm, 0 }, + { X86::VALIGNDZ128rri, X86::VALIGNDZ128rmi, 0 }, + { X86::VALIGNDZ256rri, X86::VALIGNDZ256rmi, 0 }, + { X86::VALIGNQZ128rri, X86::VALIGNQZ128rmi, 0 }, + { X86::VALIGNQZ256rri, X86::VALIGNQZ256rmi, 0 }, + { X86::VANDNPDZ128rr, X86::VANDNPDZ128rm, 0 }, + { X86::VANDNPDZ256rr, X86::VANDNPDZ256rm, 0 }, + { X86::VANDNPSZ128rr, X86::VANDNPSZ128rm, 0 }, + { X86::VANDNPSZ256rr, X86::VANDNPSZ256rm, 0 }, + { X86::VANDPDZ128rr, X86::VANDPDZ128rm, 0 }, + { X86::VANDPDZ256rr, X86::VANDPDZ256rm, 0 }, + { X86::VANDPSZ128rr, X86::VANDPSZ128rm, 0 }, + { X86::VANDPSZ256rr, X86::VANDPSZ256rm, 0 }, + { X86::VCMPPDZ128rri, X86::VCMPPDZ128rmi, 0 }, + { X86::VCMPPDZ256rri, X86::VCMPPDZ256rmi, 0 }, + { X86::VCMPPSZ128rri, X86::VCMPPSZ128rmi, 0 }, + { X86::VCMPPSZ256rri, X86::VCMPPSZ256rmi, 0 }, + { X86::VDIVPDZ128rr, X86::VDIVPDZ128rm, 0 }, + { X86::VDIVPDZ256rr, X86::VDIVPDZ256rm, 0 }, + { X86::VDIVPSZ128rr, X86::VDIVPSZ128rm, 0 }, + { X86::VDIVPSZ256rr, X86::VDIVPSZ256rm, 0 }, + { X86::VINSERTF32x4Z256rr,X86::VINSERTF32x4Z256rm, 0 }, + { X86::VINSERTF64x2Z256rr,X86::VINSERTF64x2Z256rm, 0 }, + { X86::VINSERTI32x4Z256rr,X86::VINSERTI32x4Z256rm, 0 }, + { X86::VINSERTI64x2Z256rr,X86::VINSERTI64x2Z256rm, 0 }, + { X86::VMAXCPDZ128rr, X86::VMAXCPDZ128rm, 0 }, + { X86::VMAXCPDZ256rr, X86::VMAXCPDZ256rm, 0 }, + { X86::VMAXCPSZ128rr, X86::VMAXCPSZ128rm, 0 }, + { X86::VMAXCPSZ256rr, X86::VMAXCPSZ256rm, 0 }, + { X86::VMAXPDZ128rr, X86::VMAXPDZ128rm, 0 }, + { X86::VMAXPDZ256rr, X86::VMAXPDZ256rm, 0 }, + { X86::VMAXPSZ128rr, X86::VMAXPSZ128rm, 0 }, + { X86::VMAXPSZ256rr, X86::VMAXPSZ256rm, 0 }, + { X86::VMINCPDZ128rr, X86::VMINCPDZ128rm, 0 }, + { X86::VMINCPDZ256rr, X86::VMINCPDZ256rm, 0 }, + { X86::VMINCPSZ128rr, X86::VMINCPSZ128rm, 0 }, + { X86::VMINCPSZ256rr, X86::VMINCPSZ256rm, 0 }, + { X86::VMINPDZ128rr, X86::VMINPDZ128rm, 0 }, + { X86::VMINPDZ256rr, X86::VMINPDZ256rm, 0 }, + { X86::VMINPSZ128rr, X86::VMINPSZ128rm, 0 }, + { X86::VMINPSZ256rr, X86::VMINPSZ256rm, 0 }, + { X86::VMULPDZ128rr, X86::VMULPDZ128rm, 0 }, + { X86::VMULPDZ256rr, X86::VMULPDZ256rm, 0 }, + { X86::VMULPSZ128rr, X86::VMULPSZ128rm, 0 }, + { X86::VMULPSZ256rr, X86::VMULPSZ256rm, 0 }, + { X86::VORPDZ128rr, X86::VORPDZ128rm, 0 }, + { X86::VORPDZ256rr, X86::VORPDZ256rm, 0 }, + { X86::VORPSZ128rr, X86::VORPSZ128rm, 0 }, + { X86::VORPSZ256rr, X86::VORPSZ256rm, 0 }, + { X86::VPACKSSDWZ256rr, X86::VPACKSSDWZ256rm, 0 }, + { X86::VPACKSSDWZ128rr, X86::VPACKSSDWZ128rm, 0 }, + { X86::VPACKSSWBZ256rr, X86::VPACKSSWBZ256rm, 0 }, + { X86::VPACKSSWBZ128rr, X86::VPACKSSWBZ128rm, 0 }, + { X86::VPACKUSDWZ256rr, X86::VPACKUSDWZ256rm, 0 }, + { X86::VPACKUSDWZ128rr, X86::VPACKUSDWZ128rm, 0 }, + { X86::VPACKUSWBZ256rr, X86::VPACKUSWBZ256rm, 0 }, + { X86::VPACKUSWBZ128rr, X86::VPACKUSWBZ128rm, 0 }, + { X86::VPADDBZ128rr, X86::VPADDBZ128rm, 0 }, + { X86::VPADDBZ256rr, X86::VPADDBZ256rm, 0 }, + { X86::VPADDDZ128rr, X86::VPADDDZ128rm, 0 }, + { X86::VPADDDZ256rr, X86::VPADDDZ256rm, 0 }, + { X86::VPADDQZ128rr, X86::VPADDQZ128rm, 0 }, + { X86::VPADDQZ256rr, X86::VPADDQZ256rm, 0 }, + { X86::VPADDSBZ128rr, X86::VPADDSBZ128rm, 0 }, + { X86::VPADDSBZ256rr, X86::VPADDSBZ256rm, 0 }, + { X86::VPADDSWZ128rr, X86::VPADDSWZ128rm, 0 }, + { X86::VPADDSWZ256rr, X86::VPADDSWZ256rm, 0 }, + { X86::VPADDUSBZ128rr, X86::VPADDUSBZ128rm, 0 }, + { X86::VPADDUSBZ256rr, X86::VPADDUSBZ256rm, 0 }, + { X86::VPADDUSWZ128rr, X86::VPADDUSWZ128rm, 0 }, + { X86::VPADDUSWZ256rr, X86::VPADDUSWZ256rm, 0 }, + { X86::VPADDWZ128rr, X86::VPADDWZ128rm, 0 }, + { X86::VPADDWZ256rr, X86::VPADDWZ256rm, 0 }, + { X86::VPALIGNRZ128rri, X86::VPALIGNRZ128rmi, 0 }, + { X86::VPALIGNRZ256rri, X86::VPALIGNRZ256rmi, 0 }, + { X86::VPANDDZ128rr, X86::VPANDDZ128rm, 0 }, + { X86::VPANDDZ256rr, X86::VPANDDZ256rm, 0 }, + { X86::VPANDNDZ128rr, X86::VPANDNDZ128rm, 0 }, + { X86::VPANDNDZ256rr, X86::VPANDNDZ256rm, 0 }, + { X86::VPANDNQZ128rr, X86::VPANDNQZ128rm, 0 }, + { X86::VPANDNQZ256rr, X86::VPANDNQZ256rm, 0 }, + { X86::VPANDQZ128rr, X86::VPANDQZ128rm, 0 }, + { X86::VPANDQZ256rr, X86::VPANDQZ256rm, 0 }, + { X86::VPAVGBZ128rr, X86::VPAVGBZ128rm, 0 }, + { X86::VPAVGBZ256rr, X86::VPAVGBZ256rm, 0 }, + { X86::VPAVGWZ128rr, X86::VPAVGWZ128rm, 0 }, + { X86::VPAVGWZ256rr, X86::VPAVGWZ256rm, 0 }, + { X86::VPCMPBZ128rri, X86::VPCMPBZ128rmi, 0 }, + { X86::VPCMPBZ256rri, X86::VPCMPBZ256rmi, 0 }, + { X86::VPCMPDZ128rri, X86::VPCMPDZ128rmi, 0 }, + { X86::VPCMPDZ256rri, X86::VPCMPDZ256rmi, 0 }, + { X86::VPCMPEQBZ128rr, X86::VPCMPEQBZ128rm, 0 }, + { X86::VPCMPEQBZ256rr, X86::VPCMPEQBZ256rm, 0 }, + { X86::VPCMPEQDZ128rr, X86::VPCMPEQDZ128rm, 0 }, + { X86::VPCMPEQDZ256rr, X86::VPCMPEQDZ256rm, 0 }, + { X86::VPCMPEQQZ128rr, X86::VPCMPEQQZ128rm, 0 }, + { X86::VPCMPEQQZ256rr, X86::VPCMPEQQZ256rm, 0 }, + { X86::VPCMPEQWZ128rr, X86::VPCMPEQWZ128rm, 0 }, + { X86::VPCMPEQWZ256rr, X86::VPCMPEQWZ256rm, 0 }, + { X86::VPCMPGTBZ128rr, X86::VPCMPGTBZ128rm, 0 }, + { X86::VPCMPGTBZ256rr, X86::VPCMPGTBZ256rm, 0 }, + { X86::VPCMPGTDZ128rr, X86::VPCMPGTDZ128rm, 0 }, + { X86::VPCMPGTDZ256rr, X86::VPCMPGTDZ256rm, 0 }, + { X86::VPCMPGTQZ128rr, X86::VPCMPGTQZ128rm, 0 }, + { X86::VPCMPGTQZ256rr, X86::VPCMPGTQZ256rm, 0 }, + { X86::VPCMPGTWZ128rr, X86::VPCMPGTWZ128rm, 0 }, + { X86::VPCMPGTWZ256rr, X86::VPCMPGTWZ256rm, 0 }, + { X86::VPCMPQZ128rri, X86::VPCMPQZ128rmi, 0 }, + { X86::VPCMPQZ256rri, X86::VPCMPQZ256rmi, 0 }, + { X86::VPCMPUBZ128rri, X86::VPCMPUBZ128rmi, 0 }, + { X86::VPCMPUBZ256rri, X86::VPCMPUBZ256rmi, 0 }, + { X86::VPCMPUDZ128rri, X86::VPCMPUDZ128rmi, 0 }, + { X86::VPCMPUDZ256rri, X86::VPCMPUDZ256rmi, 0 }, + { X86::VPCMPUQZ128rri, X86::VPCMPUQZ128rmi, 0 }, + { X86::VPCMPUQZ256rri, X86::VPCMPUQZ256rmi, 0 }, + { X86::VPCMPUWZ128rri, X86::VPCMPUWZ128rmi, 0 }, + { X86::VPCMPUWZ256rri, X86::VPCMPUWZ256rmi, 0 }, + { X86::VPCMPWZ128rri, X86::VPCMPWZ128rmi, 0 }, + { X86::VPCMPWZ256rri, X86::VPCMPWZ256rmi, 0 }, + { X86::VPERMBZ128rr, X86::VPERMBZ128rm, 0 }, + { X86::VPERMBZ256rr, X86::VPERMBZ256rm, 0 }, + { X86::VPERMDZ256rr, X86::VPERMDZ256rm, 0 }, + { X86::VPERMILPDZ128rr, X86::VPERMILPDZ128rm, 0 }, + { X86::VPERMILPDZ256rr, X86::VPERMILPDZ256rm, 0 }, + { X86::VPERMILPSZ128rr, X86::VPERMILPSZ128rm, 0 }, + { X86::VPERMILPSZ256rr, X86::VPERMILPSZ256rm, 0 }, + { X86::VPERMPDZ256rr, X86::VPERMPDZ256rm, 0 }, + { X86::VPERMPSZ256rr, X86::VPERMPSZ256rm, 0 }, + { X86::VPERMQZ256rr, X86::VPERMQZ256rm, 0 }, + { X86::VPERMWZ128rr, X86::VPERMWZ128rm, 0 }, + { X86::VPERMWZ256rr, X86::VPERMWZ256rm, 0 }, + { X86::VPMADDUBSWZ128rr, X86::VPMADDUBSWZ128rm, 0 }, + { X86::VPMADDUBSWZ256rr, X86::VPMADDUBSWZ256rm, 0 }, + { X86::VPMADDWDZ128rr, X86::VPMADDWDZ128rm, 0 }, + { X86::VPMADDWDZ256rr, X86::VPMADDWDZ256rm, 0 }, + { X86::VPMAXSBZ128rr, X86::VPMAXSBZ128rm, 0 }, + { X86::VPMAXSBZ256rr, X86::VPMAXSBZ256rm, 0 }, + { X86::VPMAXSDZ128rr, X86::VPMAXSDZ128rm, 0 }, + { X86::VPMAXSDZ256rr, X86::VPMAXSDZ256rm, 0 }, + { X86::VPMAXSQZ128rr, X86::VPMAXSQZ128rm, 0 }, + { X86::VPMAXSQZ256rr, X86::VPMAXSQZ256rm, 0 }, + { X86::VPMAXSWZ128rr, X86::VPMAXSWZ128rm, 0 }, + { X86::VPMAXSWZ256rr, X86::VPMAXSWZ256rm, 0 }, + { X86::VPMAXUBZ128rr, X86::VPMAXUBZ128rm, 0 }, + { X86::VPMAXUBZ256rr, X86::VPMAXUBZ256rm, 0 }, + { X86::VPMAXUDZ128rr, X86::VPMAXUDZ128rm, 0 }, + { X86::VPMAXUDZ256rr, X86::VPMAXUDZ256rm, 0 }, + { X86::VPMAXUQZ128rr, X86::VPMAXUQZ128rm, 0 }, + { X86::VPMAXUQZ256rr, X86::VPMAXUQZ256rm, 0 }, + { X86::VPMAXUWZ128rr, X86::VPMAXUWZ128rm, 0 }, + { X86::VPMAXUWZ256rr, X86::VPMAXUWZ256rm, 0 }, + { X86::VPMINSBZ128rr, X86::VPMINSBZ128rm, 0 }, + { X86::VPMINSBZ256rr, X86::VPMINSBZ256rm, 0 }, + { X86::VPMINSDZ128rr, X86::VPMINSDZ128rm, 0 }, + { X86::VPMINSDZ256rr, X86::VPMINSDZ256rm, 0 }, + { X86::VPMINSQZ128rr, X86::VPMINSQZ128rm, 0 }, + { X86::VPMINSQZ256rr, X86::VPMINSQZ256rm, 0 }, + { X86::VPMINSWZ128rr, X86::VPMINSWZ128rm, 0 }, + { X86::VPMINSWZ256rr, X86::VPMINSWZ256rm, 0 }, + { X86::VPMINUBZ128rr, X86::VPMINUBZ128rm, 0 }, + { X86::VPMINUBZ256rr, X86::VPMINUBZ256rm, 0 }, + { X86::VPMINUDZ128rr, X86::VPMINUDZ128rm, 0 }, + { X86::VPMINUDZ256rr, X86::VPMINUDZ256rm, 0 }, + { X86::VPMINUQZ128rr, X86::VPMINUQZ128rm, 0 }, + { X86::VPMINUQZ256rr, X86::VPMINUQZ256rm, 0 }, + { X86::VPMINUWZ128rr, X86::VPMINUWZ128rm, 0 }, + { X86::VPMINUWZ256rr, X86::VPMINUWZ256rm, 0 }, + { X86::VPMULDQZ128rr, X86::VPMULDQZ128rm, 0 }, + { X86::VPMULDQZ256rr, X86::VPMULDQZ256rm, 0 }, + { X86::VPMULLDZ128rr, X86::VPMULLDZ128rm, 0 }, + { X86::VPMULLDZ256rr, X86::VPMULLDZ256rm, 0 }, + { X86::VPMULLQZ128rr, X86::VPMULLQZ128rm, 0 }, + { X86::VPMULLQZ256rr, X86::VPMULLQZ256rm, 0 }, + { X86::VPMULLWZ128rr, X86::VPMULLWZ128rm, 0 }, + { X86::VPMULLWZ256rr, X86::VPMULLWZ256rm, 0 }, + { X86::VPMULUDQZ128rr, X86::VPMULUDQZ128rm, 0 }, + { X86::VPMULUDQZ256rr, X86::VPMULUDQZ256rm, 0 }, + { X86::VPORDZ128rr, X86::VPORDZ128rm, 0 }, + { X86::VPORDZ256rr, X86::VPORDZ256rm, 0 }, + { X86::VPORQZ128rr, X86::VPORQZ128rm, 0 }, + { X86::VPORQZ256rr, X86::VPORQZ256rm, 0 }, + { X86::VPSADBWZ128rr, X86::VPSADBWZ128rm, 0 }, + { X86::VPSADBWZ256rr, X86::VPSADBWZ256rm, 0 }, + { X86::VPSHUFBZ128rr, X86::VPSHUFBZ128rm, 0 }, + { X86::VPSHUFBZ256rr, X86::VPSHUFBZ256rm, 0 }, + { X86::VPSLLDZ128rr, X86::VPSLLDZ128rm, 0 }, + { X86::VPSLLDZ256rr, X86::VPSLLDZ256rm, 0 }, + { X86::VPSLLQZ128rr, X86::VPSLLQZ128rm, 0 }, + { X86::VPSLLQZ256rr, X86::VPSLLQZ256rm, 0 }, + { X86::VPSLLVDZ128rr, X86::VPSLLVDZ128rm, 0 }, + { X86::VPSLLVDZ256rr, X86::VPSLLVDZ256rm, 0 }, + { X86::VPSLLVQZ128rr, X86::VPSLLVQZ128rm, 0 }, + { X86::VPSLLVQZ256rr, X86::VPSLLVQZ256rm, 0 }, + { X86::VPSLLVWZ128rr, X86::VPSLLVWZ128rm, 0 }, + { X86::VPSLLVWZ256rr, X86::VPSLLVWZ256rm, 0 }, + { X86::VPSLLWZ128rr, X86::VPSLLWZ128rm, 0 }, + { X86::VPSLLWZ256rr, X86::VPSLLWZ256rm, 0 }, + { X86::VPSRADZ128rr, X86::VPSRADZ128rm, 0 }, + { X86::VPSRADZ256rr, X86::VPSRADZ256rm, 0 }, + { X86::VPSRAQZ128rr, X86::VPSRAQZ128rm, 0 }, + { X86::VPSRAQZ256rr, X86::VPSRAQZ256rm, 0 }, + { X86::VPSRAVDZ128rr, X86::VPSRAVDZ128rm, 0 }, + { X86::VPSRAVDZ256rr, X86::VPSRAVDZ256rm, 0 }, + { X86::VPSRAVQZ128rr, X86::VPSRAVQZ128rm, 0 }, + { X86::VPSRAVQZ256rr, X86::VPSRAVQZ256rm, 0 }, + { X86::VPSRAVWZ128rr, X86::VPSRAVWZ128rm, 0 }, + { X86::VPSRAVWZ256rr, X86::VPSRAVWZ256rm, 0 }, + { X86::VPSRAWZ128rr, X86::VPSRAWZ128rm, 0 }, + { X86::VPSRAWZ256rr, X86::VPSRAWZ256rm, 0 }, + { X86::VPSRLDZ128rr, X86::VPSRLDZ128rm, 0 }, + { X86::VPSRLDZ256rr, X86::VPSRLDZ256rm, 0 }, + { X86::VPSRLQZ128rr, X86::VPSRLQZ128rm, 0 }, + { X86::VPSRLQZ256rr, X86::VPSRLQZ256rm, 0 }, + { X86::VPSRLVDZ128rr, X86::VPSRLVDZ128rm, 0 }, + { X86::VPSRLVDZ256rr, X86::VPSRLVDZ256rm, 0 }, + { X86::VPSRLVQZ128rr, X86::VPSRLVQZ128rm, 0 }, + { X86::VPSRLVQZ256rr, X86::VPSRLVQZ256rm, 0 }, + { X86::VPSRLVWZ128rr, X86::VPSRLVWZ128rm, 0 }, + { X86::VPSRLVWZ256rr, X86::VPSRLVWZ256rm, 0 }, + { X86::VPSRLWZ128rr, X86::VPSRLWZ128rm, 0 }, + { X86::VPSRLWZ256rr, X86::VPSRLWZ256rm, 0 }, + { X86::VPSUBBZ128rr, X86::VPSUBBZ128rm, 0 }, + { X86::VPSUBBZ256rr, X86::VPSUBBZ256rm, 0 }, + { X86::VPSUBDZ128rr, X86::VPSUBDZ128rm, 0 }, + { X86::VPSUBDZ256rr, X86::VPSUBDZ256rm, 0 }, + { X86::VPSUBQZ128rr, X86::VPSUBQZ128rm, 0 }, + { X86::VPSUBQZ256rr, X86::VPSUBQZ256rm, 0 }, + { X86::VPSUBSBZ128rr, X86::VPSUBSBZ128rm, 0 }, + { X86::VPSUBSBZ256rr, X86::VPSUBSBZ256rm, 0 }, + { X86::VPSUBSWZ128rr, X86::VPSUBSWZ128rm, 0 }, + { X86::VPSUBSWZ256rr, X86::VPSUBSWZ256rm, 0 }, + { X86::VPSUBUSBZ128rr, X86::VPSUBUSBZ128rm, 0 }, + { X86::VPSUBUSBZ256rr, X86::VPSUBUSBZ256rm, 0 }, + { X86::VPSUBUSWZ128rr, X86::VPSUBUSWZ128rm, 0 }, + { X86::VPSUBUSWZ256rr, X86::VPSUBUSWZ256rm, 0 }, + { X86::VPSUBWZ128rr, X86::VPSUBWZ128rm, 0 }, + { X86::VPSUBWZ256rr, X86::VPSUBWZ256rm, 0 }, + { X86::VPUNPCKHBWZ128rr, X86::VPUNPCKHBWZ128rm, 0 }, + { X86::VPUNPCKHBWZ256rr, X86::VPUNPCKHBWZ256rm, 0 }, + { X86::VPUNPCKHDQZ128rr, X86::VPUNPCKHDQZ128rm, 0 }, + { X86::VPUNPCKHDQZ256rr, X86::VPUNPCKHDQZ256rm, 0 }, + { X86::VPUNPCKHQDQZ128rr, X86::VPUNPCKHQDQZ128rm, 0 }, + { X86::VPUNPCKHQDQZ256rr, X86::VPUNPCKHQDQZ256rm, 0 }, + { X86::VPUNPCKHWDZ128rr, X86::VPUNPCKHWDZ128rm, 0 }, + { X86::VPUNPCKHWDZ256rr, X86::VPUNPCKHWDZ256rm, 0 }, + { X86::VPUNPCKLBWZ128rr, X86::VPUNPCKLBWZ128rm, 0 }, + { X86::VPUNPCKLBWZ256rr, X86::VPUNPCKLBWZ256rm, 0 }, + { X86::VPUNPCKLDQZ128rr, X86::VPUNPCKLDQZ128rm, 0 }, + { X86::VPUNPCKLDQZ256rr, X86::VPUNPCKLDQZ256rm, 0 }, + { X86::VPUNPCKLQDQZ128rr, X86::VPUNPCKLQDQZ128rm, 0 }, + { X86::VPUNPCKLQDQZ256rr, X86::VPUNPCKLQDQZ256rm, 0 }, + { X86::VPUNPCKLWDZ128rr, X86::VPUNPCKLWDZ128rm, 0 }, + { X86::VPUNPCKLWDZ256rr, X86::VPUNPCKLWDZ256rm, 0 }, + { X86::VPXORDZ128rr, X86::VPXORDZ128rm, 0 }, + { X86::VPXORDZ256rr, X86::VPXORDZ256rm, 0 }, + { X86::VPXORQZ128rr, X86::VPXORQZ128rm, 0 }, + { X86::VPXORQZ256rr, X86::VPXORQZ256rm, 0 }, + { X86::VSHUFPDZ128rri, X86::VSHUFPDZ128rmi, 0 }, + { X86::VSHUFPDZ256rri, X86::VSHUFPDZ256rmi, 0 }, + { X86::VSHUFPSZ128rri, X86::VSHUFPSZ128rmi, 0 }, + { X86::VSHUFPSZ256rri, X86::VSHUFPSZ256rmi, 0 }, + { X86::VSUBPDZ128rr, X86::VSUBPDZ128rm, 0 }, + { X86::VSUBPDZ256rr, X86::VSUBPDZ256rm, 0 }, + { X86::VSUBPSZ128rr, X86::VSUBPSZ128rm, 0 }, + { X86::VSUBPSZ256rr, X86::VSUBPSZ256rm, 0 }, + { X86::VUNPCKHPDZ128rr, X86::VUNPCKHPDZ128rm, 0 }, + { X86::VUNPCKHPDZ256rr, X86::VUNPCKHPDZ256rm, 0 }, + { X86::VUNPCKHPSZ128rr, X86::VUNPCKHPSZ128rm, 0 }, + { X86::VUNPCKHPSZ256rr, X86::VUNPCKHPSZ256rm, 0 }, + { X86::VUNPCKLPDZ128rr, X86::VUNPCKLPDZ128rm, 0 }, + { X86::VUNPCKLPDZ256rr, X86::VUNPCKLPDZ256rm, 0 }, + { X86::VUNPCKLPSZ128rr, X86::VUNPCKLPSZ128rm, 0 }, + { X86::VUNPCKLPSZ256rr, X86::VUNPCKLPSZ256rm, 0 }, + { X86::VXORPDZ128rr, X86::VXORPDZ128rm, 0 }, + { X86::VXORPDZ256rr, X86::VXORPDZ256rm, 0 }, + { X86::VXORPSZ128rr, X86::VXORPSZ128rm, 0 }, + { X86::VXORPSZ256rr, X86::VXORPSZ256rm, 0 }, + + // AVX-512 masked foldable instructions + { X86::VBROADCASTSSZrkz, X86::VBROADCASTSSZmkz, TB_NO_REVERSE }, + { X86::VBROADCASTSDZrkz, X86::VBROADCASTSDZmkz, TB_NO_REVERSE }, + { X86::VPABSBZrrkz, X86::VPABSBZrmkz, 0 }, + { X86::VPABSDZrrkz, X86::VPABSDZrmkz, 0 }, + { X86::VPABSQZrrkz, X86::VPABSQZrmkz, 0 }, + { X86::VPABSWZrrkz, X86::VPABSWZrmkz, 0 }, + { X86::VPERMILPDZrikz, X86::VPERMILPDZmikz, 0 }, + { X86::VPERMILPSZrikz, X86::VPERMILPSZmikz, 0 }, + { X86::VPERMPDZrikz, X86::VPERMPDZmikz, 0 }, + { X86::VPERMQZrikz, X86::VPERMQZmikz, 0 }, + { X86::VPMOVSXBDZrrkz, X86::VPMOVSXBDZrmkz, 0 }, + { X86::VPMOVSXBQZrrkz, X86::VPMOVSXBQZrmkz, TB_NO_REVERSE }, + { X86::VPMOVSXBWZrrkz, X86::VPMOVSXBWZrmkz, 0 }, + { X86::VPMOVSXDQZrrkz, X86::VPMOVSXDQZrmkz, 0 }, + { X86::VPMOVSXWDZrrkz, X86::VPMOVSXWDZrmkz, 0 }, + { X86::VPMOVSXWQZrrkz, X86::VPMOVSXWQZrmkz, 0 }, + { X86::VPMOVZXBDZrrkz, X86::VPMOVZXBDZrmkz, 0 }, + { X86::VPMOVZXBQZrrkz, X86::VPMOVZXBQZrmkz, TB_NO_REVERSE }, + { X86::VPMOVZXBWZrrkz, X86::VPMOVZXBWZrmkz, 0 }, + { X86::VPMOVZXDQZrrkz, X86::VPMOVZXDQZrmkz, 0 }, + { X86::VPMOVZXWDZrrkz, X86::VPMOVZXWDZrmkz, 0 }, + { X86::VPMOVZXWQZrrkz, X86::VPMOVZXWQZrmkz, 0 }, + { X86::VPOPCNTDZrrkz, X86::VPOPCNTDZrmkz, 0 }, + { X86::VPOPCNTQZrrkz, X86::VPOPCNTQZrmkz, 0 }, + { X86::VPSHUFDZrikz, X86::VPSHUFDZmikz, 0 }, + { X86::VPSHUFHWZrikz, X86::VPSHUFHWZmikz, 0 }, + { X86::VPSHUFLWZrikz, X86::VPSHUFLWZmikz, 0 }, + { X86::VPSLLDZrikz, X86::VPSLLDZmikz, 0 }, + { X86::VPSLLQZrikz, X86::VPSLLQZmikz, 0 }, + { X86::VPSLLWZrikz, X86::VPSLLWZmikz, 0 }, + { X86::VPSRADZrikz, X86::VPSRADZmikz, 0 }, + { X86::VPSRAQZrikz, X86::VPSRAQZmikz, 0 }, + { X86::VPSRAWZrikz, X86::VPSRAWZmikz, 0 }, + { X86::VPSRLDZrikz, X86::VPSRLDZmikz, 0 }, + { X86::VPSRLQZrikz, X86::VPSRLQZmikz, 0 }, + { X86::VPSRLWZrikz, X86::VPSRLWZmikz, 0 }, + + // AVX-512VL 256-bit masked foldable instructions + { X86::VBROADCASTSDZ256rkz, X86::VBROADCASTSDZ256mkz, TB_NO_REVERSE }, + { X86::VBROADCASTSSZ256rkz, X86::VBROADCASTSSZ256mkz, TB_NO_REVERSE }, + { X86::VPABSBZ256rrkz, X86::VPABSBZ256rmkz, 0 }, + { X86::VPABSDZ256rrkz, X86::VPABSDZ256rmkz, 0 }, + { X86::VPABSQZ256rrkz, X86::VPABSQZ256rmkz, 0 }, + { X86::VPABSWZ256rrkz, X86::VPABSWZ256rmkz, 0 }, + { X86::VPERMILPDZ256rikz, X86::VPERMILPDZ256mikz, 0 }, + { X86::VPERMILPSZ256rikz, X86::VPERMILPSZ256mikz, 0 }, + { X86::VPERMPDZ256rikz, X86::VPERMPDZ256mikz, 0 }, + { X86::VPERMQZ256rikz, X86::VPERMQZ256mikz, 0 }, + { X86::VPMOVSXBDZ256rrkz, X86::VPMOVSXBDZ256rmkz, TB_NO_REVERSE }, + { X86::VPMOVSXBQZ256rrkz, X86::VPMOVSXBQZ256rmkz, TB_NO_REVERSE }, + { X86::VPMOVSXBWZ256rrkz, X86::VPMOVSXBWZ256rmkz, 0 }, + { X86::VPMOVSXDQZ256rrkz, X86::VPMOVSXDQZ256rmkz, 0 }, + { X86::VPMOVSXWDZ256rrkz, X86::VPMOVSXWDZ256rmkz, 0 }, + { X86::VPMOVSXWQZ256rrkz, X86::VPMOVSXWQZ256rmkz, TB_NO_REVERSE }, + { X86::VPMOVZXBDZ256rrkz, X86::VPMOVZXBDZ256rmkz, TB_NO_REVERSE }, + { X86::VPMOVZXBQZ256rrkz, X86::VPMOVZXBQZ256rmkz, TB_NO_REVERSE }, + { X86::VPMOVZXBWZ256rrkz, X86::VPMOVZXBWZ256rmkz, 0 }, + { X86::VPMOVZXDQZ256rrkz, X86::VPMOVZXDQZ256rmkz, 0 }, + { X86::VPMOVZXWDZ256rrkz, X86::VPMOVZXWDZ256rmkz, 0 }, + { X86::VPMOVZXWQZ256rrkz, X86::VPMOVZXWQZ256rmkz, TB_NO_REVERSE }, + { X86::VPSHUFDZ256rikz, X86::VPSHUFDZ256mikz, 0 }, + { X86::VPSHUFHWZ256rikz, X86::VPSHUFHWZ256mikz, 0 }, + { X86::VPSHUFLWZ256rikz, X86::VPSHUFLWZ256mikz, 0 }, + { X86::VPSLLDZ256rikz, X86::VPSLLDZ256mikz, 0 }, + { X86::VPSLLQZ256rikz, X86::VPSLLQZ256mikz, 0 }, + { X86::VPSLLWZ256rikz, X86::VPSLLWZ256mikz, 0 }, + { X86::VPSRADZ256rikz, X86::VPSRADZ256mikz, 0 }, + { X86::VPSRAQZ256rikz, X86::VPSRAQZ256mikz, 0 }, + { X86::VPSRAWZ256rikz, X86::VPSRAWZ256mikz, 0 }, + { X86::VPSRLDZ256rikz, X86::VPSRLDZ256mikz, 0 }, + { X86::VPSRLQZ256rikz, X86::VPSRLQZ256mikz, 0 }, + { X86::VPSRLWZ256rikz, X86::VPSRLWZ256mikz, 0 }, + + // AVX-512VL 128-bit masked foldable instructions + { X86::VBROADCASTSSZ128rkz, X86::VBROADCASTSSZ128mkz, TB_NO_REVERSE }, + { X86::VPABSBZ128rrkz, X86::VPABSBZ128rmkz, 0 }, + { X86::VPABSDZ128rrkz, X86::VPABSDZ128rmkz, 0 }, + { X86::VPABSQZ128rrkz, X86::VPABSQZ128rmkz, 0 }, + { X86::VPABSWZ128rrkz, X86::VPABSWZ128rmkz, 0 }, + { X86::VPERMILPDZ128rikz, X86::VPERMILPDZ128mikz, 0 }, + { X86::VPERMILPSZ128rikz, X86::VPERMILPSZ128mikz, 0 }, + { X86::VPMOVSXBDZ128rrkz, X86::VPMOVSXBDZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVSXBQZ128rrkz, X86::VPMOVSXBQZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVSXBWZ128rrkz, X86::VPMOVSXBWZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVSXDQZ128rrkz, X86::VPMOVSXDQZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVSXWDZ128rrkz, X86::VPMOVSXWDZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVSXWQZ128rrkz, X86::VPMOVSXWQZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVZXBDZ128rrkz, X86::VPMOVZXBDZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVZXBQZ128rrkz, X86::VPMOVZXBQZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVZXBWZ128rrkz, X86::VPMOVZXBWZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVZXDQZ128rrkz, X86::VPMOVZXDQZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVZXWDZ128rrkz, X86::VPMOVZXWDZ128rmkz, TB_NO_REVERSE }, + { X86::VPMOVZXWQZ128rrkz, X86::VPMOVZXWQZ128rmkz, TB_NO_REVERSE }, + { X86::VPSHUFDZ128rikz, X86::VPSHUFDZ128mikz, 0 }, + { X86::VPSHUFHWZ128rikz, X86::VPSHUFHWZ128mikz, 0 }, + { X86::VPSHUFLWZ128rikz, X86::VPSHUFLWZ128mikz, 0 }, + { X86::VPSLLDZ128rikz, X86::VPSLLDZ128mikz, 0 }, + { X86::VPSLLQZ128rikz, X86::VPSLLQZ128mikz, 0 }, + { X86::VPSLLWZ128rikz, X86::VPSLLWZ128mikz, 0 }, + { X86::VPSRADZ128rikz, X86::VPSRADZ128mikz, 0 }, + { X86::VPSRAQZ128rikz, X86::VPSRAQZ128mikz, 0 }, + { X86::VPSRAWZ128rikz, X86::VPSRAWZ128mikz, 0 }, + { X86::VPSRLDZ128rikz, X86::VPSRLDZ128mikz, 0 }, + { X86::VPSRLQZ128rikz, X86::VPSRLQZ128mikz, 0 }, + { X86::VPSRLWZ128rikz, X86::VPSRLWZ128mikz, 0 }, + + // AES foldable instructions + { X86::AESDECLASTrr, X86::AESDECLASTrm, TB_ALIGN_16 }, + { X86::AESDECrr, X86::AESDECrm, TB_ALIGN_16 }, + { X86::AESENCLASTrr, X86::AESENCLASTrm, TB_ALIGN_16 }, + { X86::AESENCrr, X86::AESENCrm, TB_ALIGN_16 }, + { X86::VAESDECLASTrr, X86::VAESDECLASTrm, 0 }, + { X86::VAESDECrr, X86::VAESDECrm, 0 }, + { X86::VAESENCLASTrr, X86::VAESENCLASTrm, 0 }, + { X86::VAESENCrr, X86::VAESENCrm, 0 }, + + // SHA foldable instructions + { X86::SHA1MSG1rr, X86::SHA1MSG1rm, TB_ALIGN_16 }, + { X86::SHA1MSG2rr, X86::SHA1MSG2rm, TB_ALIGN_16 }, + { X86::SHA1NEXTErr, X86::SHA1NEXTErm, TB_ALIGN_16 }, + { X86::SHA1RNDS4rri, X86::SHA1RNDS4rmi, TB_ALIGN_16 }, + { X86::SHA256MSG1rr, X86::SHA256MSG1rm, TB_ALIGN_16 }, + { X86::SHA256MSG2rr, X86::SHA256MSG2rm, TB_ALIGN_16 }, + { X86::SHA256RNDS2rr, X86::SHA256RNDS2rm, TB_ALIGN_16 } + }; + for (X86MemoryFoldTableEntry Entry : MemoryFoldTable2) { AddTableEntry(RegOp2MemOpTable2, MemOp2RegOpTable, Entry.RegOp, Entry.MemOp, @@ -150,12 +2439,1105 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI) Entry.Flags | TB_INDEX_2 | TB_FOLDED_LOAD); } + static const X86MemoryFoldTableEntry MemoryFoldTable3[] = { + // FMA4 foldable patterns + { X86::VFMADDSS4rr, X86::VFMADDSS4rm, TB_ALIGN_NONE }, + { X86::VFMADDSS4rr_Int, X86::VFMADDSS4rm_Int, TB_NO_REVERSE }, + { X86::VFMADDSD4rr, X86::VFMADDSD4rm, TB_ALIGN_NONE }, + { X86::VFMADDSD4rr_Int, X86::VFMADDSD4rm_Int, TB_NO_REVERSE }, + { X86::VFMADDPS4rr, X86::VFMADDPS4rm, TB_ALIGN_NONE }, + { X86::VFMADDPD4rr, X86::VFMADDPD4rm, TB_ALIGN_NONE }, + { X86::VFMADDPS4Yrr, X86::VFMADDPS4Yrm, TB_ALIGN_NONE }, + { X86::VFMADDPD4Yrr, X86::VFMADDPD4Yrm, TB_ALIGN_NONE }, + { X86::VFNMADDSS4rr, X86::VFNMADDSS4rm, TB_ALIGN_NONE }, + { X86::VFNMADDSS4rr_Int, X86::VFNMADDSS4rm_Int, TB_NO_REVERSE }, + { X86::VFNMADDSD4rr, X86::VFNMADDSD4rm, TB_ALIGN_NONE }, + { X86::VFNMADDSD4rr_Int, X86::VFNMADDSD4rm_Int, TB_NO_REVERSE }, + { X86::VFNMADDPS4rr, X86::VFNMADDPS4rm, TB_ALIGN_NONE }, + { X86::VFNMADDPD4rr, X86::VFNMADDPD4rm, TB_ALIGN_NONE }, + { X86::VFNMADDPS4Yrr, X86::VFNMADDPS4Yrm, TB_ALIGN_NONE }, + { X86::VFNMADDPD4Yrr, X86::VFNMADDPD4Yrm, TB_ALIGN_NONE }, + { X86::VFMSUBSS4rr, X86::VFMSUBSS4rm, TB_ALIGN_NONE }, + { X86::VFMSUBSS4rr_Int, X86::VFMSUBSS4rm_Int, TB_NO_REVERSE }, + { X86::VFMSUBSD4rr, X86::VFMSUBSD4rm, TB_ALIGN_NONE }, + { X86::VFMSUBSD4rr_Int, X86::VFMSUBSD4rm_Int, TB_NO_REVERSE }, + { X86::VFMSUBPS4rr, X86::VFMSUBPS4rm, TB_ALIGN_NONE }, + { X86::VFMSUBPD4rr, X86::VFMSUBPD4rm, TB_ALIGN_NONE }, + { X86::VFMSUBPS4Yrr, X86::VFMSUBPS4Yrm, TB_ALIGN_NONE }, + { X86::VFMSUBPD4Yrr, X86::VFMSUBPD4Yrm, TB_ALIGN_NONE }, + { X86::VFNMSUBSS4rr, X86::VFNMSUBSS4rm, TB_ALIGN_NONE }, + { X86::VFNMSUBSS4rr_Int, X86::VFNMSUBSS4rm_Int, TB_NO_REVERSE }, + { X86::VFNMSUBSD4rr, X86::VFNMSUBSD4rm, TB_ALIGN_NONE }, + { X86::VFNMSUBSD4rr_Int, X86::VFNMSUBSD4rm_Int, TB_NO_REVERSE }, + { X86::VFNMSUBPS4rr, X86::VFNMSUBPS4rm, TB_ALIGN_NONE }, + { X86::VFNMSUBPD4rr, X86::VFNMSUBPD4rm, TB_ALIGN_NONE }, + { X86::VFNMSUBPS4Yrr, X86::VFNMSUBPS4Yrm, TB_ALIGN_NONE }, + { X86::VFNMSUBPD4Yrr, X86::VFNMSUBPD4Yrm, TB_ALIGN_NONE }, + { X86::VFMADDSUBPS4rr, X86::VFMADDSUBPS4rm, TB_ALIGN_NONE }, + { X86::VFMADDSUBPD4rr, X86::VFMADDSUBPD4rm, TB_ALIGN_NONE }, + { X86::VFMADDSUBPS4Yrr, X86::VFMADDSUBPS4Yrm, TB_ALIGN_NONE }, + { X86::VFMADDSUBPD4Yrr, X86::VFMADDSUBPD4Yrm, TB_ALIGN_NONE }, + { X86::VFMSUBADDPS4rr, X86::VFMSUBADDPS4rm, TB_ALIGN_NONE }, + { X86::VFMSUBADDPD4rr, X86::VFMSUBADDPD4rm, TB_ALIGN_NONE }, + { X86::VFMSUBADDPS4Yrr, X86::VFMSUBADDPS4Yrm, TB_ALIGN_NONE }, + { X86::VFMSUBADDPD4Yrr, X86::VFMSUBADDPD4Yrm, TB_ALIGN_NONE }, + + // XOP foldable instructions + { X86::VPCMOVrrr, X86::VPCMOVrrm, 0 }, + { X86::VPCMOVYrrr, X86::VPCMOVYrrm, 0 }, + { X86::VPERMIL2PDrr, X86::VPERMIL2PDrm, 0 }, + { X86::VPERMIL2PDYrr, X86::VPERMIL2PDYrm, 0 }, + { X86::VPERMIL2PSrr, X86::VPERMIL2PSrm, 0 }, + { X86::VPERMIL2PSYrr, X86::VPERMIL2PSYrm, 0 }, + { X86::VPPERMrrr, X86::VPPERMrrm, 0 }, + + // AVX-512 instructions with 3 source operands. + { X86::VPERMI2Brr, X86::VPERMI2Brm, 0 }, + { X86::VPERMI2Drr, X86::VPERMI2Drm, 0 }, + { X86::VPERMI2PSrr, X86::VPERMI2PSrm, 0 }, + { X86::VPERMI2PDrr, X86::VPERMI2PDrm, 0 }, + { X86::VPERMI2Qrr, X86::VPERMI2Qrm, 0 }, + { X86::VPERMI2Wrr, X86::VPERMI2Wrm, 0 }, + { X86::VPERMT2Brr, X86::VPERMT2Brm, 0 }, + { X86::VPERMT2Drr, X86::VPERMT2Drm, 0 }, + { X86::VPERMT2PSrr, X86::VPERMT2PSrm, 0 }, + { X86::VPERMT2PDrr, X86::VPERMT2PDrm, 0 }, + { X86::VPERMT2Qrr, X86::VPERMT2Qrm, 0 }, + { X86::VPERMT2Wrr, X86::VPERMT2Wrm, 0 }, + { X86::VPTERNLOGDZrri, X86::VPTERNLOGDZrmi, 0 }, + { X86::VPTERNLOGQZrri, X86::VPTERNLOGQZrmi, 0 }, + + // AVX-512VL 256-bit instructions with 3 source operands. + { X86::VPERMI2B256rr, X86::VPERMI2B256rm, 0 }, + { X86::VPERMI2D256rr, X86::VPERMI2D256rm, 0 }, + { X86::VPERMI2PD256rr, X86::VPERMI2PD256rm, 0 }, + { X86::VPERMI2PS256rr, X86::VPERMI2PS256rm, 0 }, + { X86::VPERMI2Q256rr, X86::VPERMI2Q256rm, 0 }, + { X86::VPERMI2W256rr, X86::VPERMI2W256rm, 0 }, + { X86::VPERMT2B256rr, X86::VPERMT2B256rm, 0 }, + { X86::VPERMT2D256rr, X86::VPERMT2D256rm, 0 }, + { X86::VPERMT2PD256rr, X86::VPERMT2PD256rm, 0 }, + { X86::VPERMT2PS256rr, X86::VPERMT2PS256rm, 0 }, + { X86::VPERMT2Q256rr, X86::VPERMT2Q256rm, 0 }, + { X86::VPERMT2W256rr, X86::VPERMT2W256rm, 0 }, + { X86::VPTERNLOGDZ256rri, X86::VPTERNLOGDZ256rmi, 0 }, + { X86::VPTERNLOGQZ256rri, X86::VPTERNLOGQZ256rmi, 0 }, + + // AVX-512VL 128-bit instructions with 3 source operands. + { X86::VPERMI2B128rr, X86::VPERMI2B128rm, 0 }, + { X86::VPERMI2D128rr, X86::VPERMI2D128rm, 0 }, + { X86::VPERMI2PD128rr, X86::VPERMI2PD128rm, 0 }, + { X86::VPERMI2PS128rr, X86::VPERMI2PS128rm, 0 }, + { X86::VPERMI2Q128rr, X86::VPERMI2Q128rm, 0 }, + { X86::VPERMI2W128rr, X86::VPERMI2W128rm, 0 }, + { X86::VPERMT2B128rr, X86::VPERMT2B128rm, 0 }, + { X86::VPERMT2D128rr, X86::VPERMT2D128rm, 0 }, + { X86::VPERMT2PD128rr, X86::VPERMT2PD128rm, 0 }, + { X86::VPERMT2PS128rr, X86::VPERMT2PS128rm, 0 }, + { X86::VPERMT2Q128rr, X86::VPERMT2Q128rm, 0 }, + { X86::VPERMT2W128rr, X86::VPERMT2W128rm, 0 }, + { X86::VPTERNLOGDZ128rri, X86::VPTERNLOGDZ128rmi, 0 }, + { X86::VPTERNLOGQZ128rri, X86::VPTERNLOGQZ128rmi, 0 }, + + // AVX-512 masked instructions + { X86::VADDPDZrrkz, X86::VADDPDZrmkz, 0 }, + { X86::VADDPSZrrkz, X86::VADDPSZrmkz, 0 }, + { X86::VADDSDZrr_Intkz, X86::VADDSDZrm_Intkz, TB_NO_REVERSE }, + { X86::VADDSSZrr_Intkz, X86::VADDSSZrm_Intkz, TB_NO_REVERSE }, + { X86::VALIGNDZrrikz, X86::VALIGNDZrmikz, 0 }, + { X86::VALIGNQZrrikz, X86::VALIGNQZrmikz, 0 }, + { X86::VANDNPDZrrkz, X86::VANDNPDZrmkz, 0 }, + { X86::VANDNPSZrrkz, X86::VANDNPSZrmkz, 0 }, + { X86::VANDPDZrrkz, X86::VANDPDZrmkz, 0 }, + { X86::VANDPSZrrkz, X86::VANDPSZrmkz, 0 }, + { X86::VDIVPDZrrkz, X86::VDIVPDZrmkz, 0 }, + { X86::VDIVPSZrrkz, X86::VDIVPSZrmkz, 0 }, + { X86::VDIVSDZrr_Intkz, X86::VDIVSDZrm_Intkz, TB_NO_REVERSE }, + { X86::VDIVSSZrr_Intkz, X86::VDIVSSZrm_Intkz, TB_NO_REVERSE }, + { X86::VINSERTF32x4Zrrkz, X86::VINSERTF32x4Zrmkz, 0 }, + { X86::VINSERTF32x8Zrrkz, X86::VINSERTF32x8Zrmkz, 0 }, + { X86::VINSERTF64x2Zrrkz, X86::VINSERTF64x2Zrmkz, 0 }, + { X86::VINSERTF64x4Zrrkz, X86::VINSERTF64x4Zrmkz, 0 }, + { X86::VINSERTI32x4Zrrkz, X86::VINSERTI32x4Zrmkz, 0 }, + { X86::VINSERTI32x8Zrrkz, X86::VINSERTI32x8Zrmkz, 0 }, + { X86::VINSERTI64x2Zrrkz, X86::VINSERTI64x2Zrmkz, 0 }, + { X86::VINSERTI64x4Zrrkz, X86::VINSERTI64x4Zrmkz, 0 }, + { X86::VMAXCPDZrrkz, X86::VMAXCPDZrmkz, 0 }, + { X86::VMAXCPSZrrkz, X86::VMAXCPSZrmkz, 0 }, + { X86::VMAXPDZrrkz, X86::VMAXPDZrmkz, 0 }, + { X86::VMAXPSZrrkz, X86::VMAXPSZrmkz, 0 }, + { X86::VMAXSDZrr_Intkz, X86::VMAXSDZrm_Intkz, 0 }, + { X86::VMAXSSZrr_Intkz, X86::VMAXSSZrm_Intkz, 0 }, + { X86::VMINCPDZrrkz, X86::VMINCPDZrmkz, 0 }, + { X86::VMINCPSZrrkz, X86::VMINCPSZrmkz, 0 }, + { X86::VMINPDZrrkz, X86::VMINPDZrmkz, 0 }, + { X86::VMINPSZrrkz, X86::VMINPSZrmkz, 0 }, + { X86::VMINSDZrr_Intkz, X86::VMINSDZrm_Intkz, 0 }, + { X86::VMINSSZrr_Intkz, X86::VMINSSZrm_Intkz, 0 }, + { X86::VMULPDZrrkz, X86::VMULPDZrmkz, 0 }, + { X86::VMULPSZrrkz, X86::VMULPSZrmkz, 0 }, + { X86::VMULSDZrr_Intkz, X86::VMULSDZrm_Intkz, TB_NO_REVERSE }, + { X86::VMULSSZrr_Intkz, X86::VMULSSZrm_Intkz, TB_NO_REVERSE }, + { X86::VORPDZrrkz, X86::VORPDZrmkz, 0 }, + { X86::VORPSZrrkz, X86::VORPSZrmkz, 0 }, + { X86::VPACKSSDWZrrkz, X86::VPACKSSDWZrmkz, 0 }, + { X86::VPACKSSWBZrrkz, X86::VPACKSSWBZrmkz, 0 }, + { X86::VPACKUSDWZrrkz, X86::VPACKUSDWZrmkz, 0 }, + { X86::VPACKUSWBZrrkz, X86::VPACKUSWBZrmkz, 0 }, + { X86::VPADDBZrrkz, X86::VPADDBZrmkz, 0 }, + { X86::VPADDDZrrkz, X86::VPADDDZrmkz, 0 }, + { X86::VPADDQZrrkz, X86::VPADDQZrmkz, 0 }, + { X86::VPADDSBZrrkz, X86::VPADDSBZrmkz, 0 }, + { X86::VPADDSWZrrkz, X86::VPADDSWZrmkz, 0 }, + { X86::VPADDUSBZrrkz, X86::VPADDUSBZrmkz, 0 }, + { X86::VPADDUSWZrrkz, X86::VPADDUSWZrmkz, 0 }, + { X86::VPADDWZrrkz, X86::VPADDWZrmkz, 0 }, + { X86::VPALIGNRZrrikz, X86::VPALIGNRZrmikz, 0 }, + { X86::VPANDDZrrkz, X86::VPANDDZrmkz, 0 }, + { X86::VPANDNDZrrkz, X86::VPANDNDZrmkz, 0 }, + { X86::VPANDNQZrrkz, X86::VPANDNQZrmkz, 0 }, + { X86::VPANDQZrrkz, X86::VPANDQZrmkz, 0 }, + { X86::VPAVGBZrrkz, X86::VPAVGBZrmkz, 0 }, + { X86::VPAVGWZrrkz, X86::VPAVGWZrmkz, 0 }, + { X86::VPERMBZrrkz, X86::VPERMBZrmkz, 0 }, + { X86::VPERMDZrrkz, X86::VPERMDZrmkz, 0 }, + { X86::VPERMILPDZrrkz, X86::VPERMILPDZrmkz, 0 }, + { X86::VPERMILPSZrrkz, X86::VPERMILPSZrmkz, 0 }, + { X86::VPERMPDZrrkz, X86::VPERMPDZrmkz, 0 }, + { X86::VPERMPSZrrkz, X86::VPERMPSZrmkz, 0 }, + { X86::VPERMQZrrkz, X86::VPERMQZrmkz, 0 }, + { X86::VPERMWZrrkz, X86::VPERMWZrmkz, 0 }, + { X86::VPMADDUBSWZrrkz, X86::VPMADDUBSWZrmkz, 0 }, + { X86::VPMADDWDZrrkz, X86::VPMADDWDZrmkz, 0 }, + { X86::VPMAXSBZrrkz, X86::VPMAXSBZrmkz, 0 }, + { X86::VPMAXSDZrrkz, X86::VPMAXSDZrmkz, 0 }, + { X86::VPMAXSQZrrkz, X86::VPMAXSQZrmkz, 0 }, + { X86::VPMAXSWZrrkz, X86::VPMAXSWZrmkz, 0 }, + { X86::VPMAXUBZrrkz, X86::VPMAXUBZrmkz, 0 }, + { X86::VPMAXUDZrrkz, X86::VPMAXUDZrmkz, 0 }, + { X86::VPMAXUQZrrkz, X86::VPMAXUQZrmkz, 0 }, + { X86::VPMAXUWZrrkz, X86::VPMAXUWZrmkz, 0 }, + { X86::VPMINSBZrrkz, X86::VPMINSBZrmkz, 0 }, + { X86::VPMINSDZrrkz, X86::VPMINSDZrmkz, 0 }, + { X86::VPMINSQZrrkz, X86::VPMINSQZrmkz, 0 }, + { X86::VPMINSWZrrkz, X86::VPMINSWZrmkz, 0 }, + { X86::VPMINUBZrrkz, X86::VPMINUBZrmkz, 0 }, + { X86::VPMINUDZrrkz, X86::VPMINUDZrmkz, 0 }, + { X86::VPMINUQZrrkz, X86::VPMINUQZrmkz, 0 }, + { X86::VPMINUWZrrkz, X86::VPMINUWZrmkz, 0 }, + { X86::VPMULLDZrrkz, X86::VPMULLDZrmkz, 0 }, + { X86::VPMULLQZrrkz, X86::VPMULLQZrmkz, 0 }, + { X86::VPMULLWZrrkz, X86::VPMULLWZrmkz, 0 }, + { X86::VPMULDQZrrkz, X86::VPMULDQZrmkz, 0 }, + { X86::VPMULUDQZrrkz, X86::VPMULUDQZrmkz, 0 }, + { X86::VPORDZrrkz, X86::VPORDZrmkz, 0 }, + { X86::VPORQZrrkz, X86::VPORQZrmkz, 0 }, + { X86::VPSHUFBZrrkz, X86::VPSHUFBZrmkz, 0 }, + { X86::VPSLLDZrrkz, X86::VPSLLDZrmkz, 0 }, + { X86::VPSLLQZrrkz, X86::VPSLLQZrmkz, 0 }, + { X86::VPSLLVDZrrkz, X86::VPSLLVDZrmkz, 0 }, + { X86::VPSLLVQZrrkz, X86::VPSLLVQZrmkz, 0 }, + { X86::VPSLLVWZrrkz, X86::VPSLLVWZrmkz, 0 }, + { X86::VPSLLWZrrkz, X86::VPSLLWZrmkz, 0 }, + { X86::VPSRADZrrkz, X86::VPSRADZrmkz, 0 }, + { X86::VPSRAQZrrkz, X86::VPSRAQZrmkz, 0 }, + { X86::VPSRAVDZrrkz, X86::VPSRAVDZrmkz, 0 }, + { X86::VPSRAVQZrrkz, X86::VPSRAVQZrmkz, 0 }, + { X86::VPSRAVWZrrkz, X86::VPSRAVWZrmkz, 0 }, + { X86::VPSRAWZrrkz, X86::VPSRAWZrmkz, 0 }, + { X86::VPSRLDZrrkz, X86::VPSRLDZrmkz, 0 }, + { X86::VPSRLQZrrkz, X86::VPSRLQZrmkz, 0 }, + { X86::VPSRLVDZrrkz, X86::VPSRLVDZrmkz, 0 }, + { X86::VPSRLVQZrrkz, X86::VPSRLVQZrmkz, 0 }, + { X86::VPSRLVWZrrkz, X86::VPSRLVWZrmkz, 0 }, + { X86::VPSRLWZrrkz, X86::VPSRLWZrmkz, 0 }, + { X86::VPSUBBZrrkz, X86::VPSUBBZrmkz, 0 }, + { X86::VPSUBDZrrkz, X86::VPSUBDZrmkz, 0 }, + { X86::VPSUBQZrrkz, X86::VPSUBQZrmkz, 0 }, + { X86::VPSUBSBZrrkz, X86::VPSUBSBZrmkz, 0 }, + { X86::VPSUBSWZrrkz, X86::VPSUBSWZrmkz, 0 }, + { X86::VPSUBUSBZrrkz, X86::VPSUBUSBZrmkz, 0 }, + { X86::VPSUBUSWZrrkz, X86::VPSUBUSWZrmkz, 0 }, + { X86::VPSUBWZrrkz, X86::VPSUBWZrmkz, 0 }, + { X86::VPUNPCKHBWZrrkz, X86::VPUNPCKHBWZrmkz, 0 }, + { X86::VPUNPCKHDQZrrkz, X86::VPUNPCKHDQZrmkz, 0 }, + { X86::VPUNPCKHQDQZrrkz, X86::VPUNPCKHQDQZrmkz, 0 }, + { X86::VPUNPCKHWDZrrkz, X86::VPUNPCKHWDZrmkz, 0 }, + { X86::VPUNPCKLBWZrrkz, X86::VPUNPCKLBWZrmkz, 0 }, + { X86::VPUNPCKLDQZrrkz, X86::VPUNPCKLDQZrmkz, 0 }, + { X86::VPUNPCKLQDQZrrkz, X86::VPUNPCKLQDQZrmkz, 0 }, + { X86::VPUNPCKLWDZrrkz, X86::VPUNPCKLWDZrmkz, 0 }, + { X86::VPXORDZrrkz, X86::VPXORDZrmkz, 0 }, + { X86::VPXORQZrrkz, X86::VPXORQZrmkz, 0 }, + { X86::VSHUFPDZrrikz, X86::VSHUFPDZrmikz, 0 }, + { X86::VSHUFPSZrrikz, X86::VSHUFPSZrmikz, 0 }, + { X86::VSUBPDZrrkz, X86::VSUBPDZrmkz, 0 }, + { X86::VSUBPSZrrkz, X86::VSUBPSZrmkz, 0 }, + { X86::VSUBSDZrr_Intkz, X86::VSUBSDZrm_Intkz, TB_NO_REVERSE }, + { X86::VSUBSSZrr_Intkz, X86::VSUBSSZrm_Intkz, TB_NO_REVERSE }, + { X86::VUNPCKHPDZrrkz, X86::VUNPCKHPDZrmkz, 0 }, + { X86::VUNPCKHPSZrrkz, X86::VUNPCKHPSZrmkz, 0 }, + { X86::VUNPCKLPDZrrkz, X86::VUNPCKLPDZrmkz, 0 }, + { X86::VUNPCKLPSZrrkz, X86::VUNPCKLPSZrmkz, 0 }, + { X86::VXORPDZrrkz, X86::VXORPDZrmkz, 0 }, + { X86::VXORPSZrrkz, X86::VXORPSZrmkz, 0 }, + + // AVX-512{F,VL} masked arithmetic instructions 256-bit + { X86::VADDPDZ256rrkz, X86::VADDPDZ256rmkz, 0 }, + { X86::VADDPSZ256rrkz, X86::VADDPSZ256rmkz, 0 }, + { X86::VALIGNDZ256rrikz, X86::VALIGNDZ256rmikz, 0 }, + { X86::VALIGNQZ256rrikz, X86::VALIGNQZ256rmikz, 0 }, + { X86::VANDNPDZ256rrkz, X86::VANDNPDZ256rmkz, 0 }, + { X86::VANDNPSZ256rrkz, X86::VANDNPSZ256rmkz, 0 }, + { X86::VANDPDZ256rrkz, X86::VANDPDZ256rmkz, 0 }, + { X86::VANDPSZ256rrkz, X86::VANDPSZ256rmkz, 0 }, + { X86::VDIVPDZ256rrkz, X86::VDIVPDZ256rmkz, 0 }, + { X86::VDIVPSZ256rrkz, X86::VDIVPSZ256rmkz, 0 }, + { X86::VINSERTF32x4Z256rrkz, X86::VINSERTF32x4Z256rmkz, 0 }, + { X86::VINSERTF64x2Z256rrkz, X86::VINSERTF64x2Z256rmkz, 0 }, + { X86::VINSERTI32x4Z256rrkz, X86::VINSERTI32x4Z256rmkz, 0 }, + { X86::VINSERTI64x2Z256rrkz, X86::VINSERTI64x2Z256rmkz, 0 }, + { X86::VMAXCPDZ256rrkz, X86::VMAXCPDZ256rmkz, 0 }, + { X86::VMAXCPSZ256rrkz, X86::VMAXCPSZ256rmkz, 0 }, + { X86::VMAXPDZ256rrkz, X86::VMAXPDZ256rmkz, 0 }, + { X86::VMAXPSZ256rrkz, X86::VMAXPSZ256rmkz, 0 }, + { X86::VMINCPDZ256rrkz, X86::VMINCPDZ256rmkz, 0 }, + { X86::VMINCPSZ256rrkz, X86::VMINCPSZ256rmkz, 0 }, + { X86::VMINPDZ256rrkz, X86::VMINPDZ256rmkz, 0 }, + { X86::VMINPSZ256rrkz, X86::VMINPSZ256rmkz, 0 }, + { X86::VMULPDZ256rrkz, X86::VMULPDZ256rmkz, 0 }, + { X86::VMULPSZ256rrkz, X86::VMULPSZ256rmkz, 0 }, + { X86::VORPDZ256rrkz, X86::VORPDZ256rmkz, 0 }, + { X86::VORPSZ256rrkz, X86::VORPSZ256rmkz, 0 }, + { X86::VPACKSSDWZ256rrkz, X86::VPACKSSDWZ256rmkz, 0 }, + { X86::VPACKSSWBZ256rrkz, X86::VPACKSSWBZ256rmkz, 0 }, + { X86::VPACKUSDWZ256rrkz, X86::VPACKUSDWZ256rmkz, 0 }, + { X86::VPACKUSWBZ256rrkz, X86::VPACKUSWBZ256rmkz, 0 }, + { X86::VPADDBZ256rrkz, X86::VPADDBZ256rmkz, 0 }, + { X86::VPADDDZ256rrkz, X86::VPADDDZ256rmkz, 0 }, + { X86::VPADDQZ256rrkz, X86::VPADDQZ256rmkz, 0 }, + { X86::VPADDSBZ256rrkz, X86::VPADDSBZ256rmkz, 0 }, + { X86::VPADDSWZ256rrkz, X86::VPADDSWZ256rmkz, 0 }, + { X86::VPADDUSBZ256rrkz, X86::VPADDUSBZ256rmkz, 0 }, + { X86::VPADDUSWZ256rrkz, X86::VPADDUSWZ256rmkz, 0 }, + { X86::VPADDWZ256rrkz, X86::VPADDWZ256rmkz, 0 }, + { X86::VPALIGNRZ256rrikz, X86::VPALIGNRZ256rmikz, 0 }, + { X86::VPANDDZ256rrkz, X86::VPANDDZ256rmkz, 0 }, + { X86::VPANDNDZ256rrkz, X86::VPANDNDZ256rmkz, 0 }, + { X86::VPANDNQZ256rrkz, X86::VPANDNQZ256rmkz, 0 }, + { X86::VPANDQZ256rrkz, X86::VPANDQZ256rmkz, 0 }, + { X86::VPAVGBZ256rrkz, X86::VPAVGBZ256rmkz, 0 }, + { X86::VPAVGWZ256rrkz, X86::VPAVGWZ256rmkz, 0 }, + { X86::VPERMBZ256rrkz, X86::VPERMBZ256rmkz, 0 }, + { X86::VPERMDZ256rrkz, X86::VPERMDZ256rmkz, 0 }, + { X86::VPERMILPDZ256rrkz, X86::VPERMILPDZ256rmkz, 0 }, + { X86::VPERMILPSZ256rrkz, X86::VPERMILPSZ256rmkz, 0 }, + { X86::VPERMPDZ256rrkz, X86::VPERMPDZ256rmkz, 0 }, + { X86::VPERMPSZ256rrkz, X86::VPERMPSZ256rmkz, 0 }, + { X86::VPERMQZ256rrkz, X86::VPERMQZ256rmkz, 0 }, + { X86::VPERMWZ256rrkz, X86::VPERMWZ256rmkz, 0 }, + { X86::VPMADDUBSWZ256rrkz, X86::VPMADDUBSWZ256rmkz, 0 }, + { X86::VPMADDWDZ256rrkz, X86::VPMADDWDZ256rmkz, 0 }, + { X86::VPMAXSBZ256rrkz, X86::VPMAXSBZ256rmkz, 0 }, + { X86::VPMAXSDZ256rrkz, X86::VPMAXSDZ256rmkz, 0 }, + { X86::VPMAXSQZ256rrkz, X86::VPMAXSQZ256rmkz, 0 }, + { X86::VPMAXSWZ256rrkz, X86::VPMAXSWZ256rmkz, 0 }, + { X86::VPMAXUBZ256rrkz, X86::VPMAXUBZ256rmkz, 0 }, + { X86::VPMAXUDZ256rrkz, X86::VPMAXUDZ256rmkz, 0 }, + { X86::VPMAXUQZ256rrkz, X86::VPMAXUQZ256rmkz, 0 }, + { X86::VPMAXUWZ256rrkz, X86::VPMAXUWZ256rmkz, 0 }, + { X86::VPMINSBZ256rrkz, X86::VPMINSBZ256rmkz, 0 }, + { X86::VPMINSDZ256rrkz, X86::VPMINSDZ256rmkz, 0 }, + { X86::VPMINSQZ256rrkz, X86::VPMINSQZ256rmkz, 0 }, + { X86::VPMINSWZ256rrkz, X86::VPMINSWZ256rmkz, 0 }, + { X86::VPMINUBZ256rrkz, X86::VPMINUBZ256rmkz, 0 }, + { X86::VPMINUDZ256rrkz, X86::VPMINUDZ256rmkz, 0 }, + { X86::VPMINUQZ256rrkz, X86::VPMINUQZ256rmkz, 0 }, + { X86::VPMINUWZ256rrkz, X86::VPMINUWZ256rmkz, 0 }, + { X86::VPMULDQZ256rrkz, X86::VPMULDQZ256rmkz, 0 }, + { X86::VPMULLDZ256rrkz, X86::VPMULLDZ256rmkz, 0 }, + { X86::VPMULLQZ256rrkz, X86::VPMULLQZ256rmkz, 0 }, + { X86::VPMULLWZ256rrkz, X86::VPMULLWZ256rmkz, 0 }, + { X86::VPMULUDQZ256rrkz, X86::VPMULUDQZ256rmkz, 0 }, + { X86::VPORDZ256rrkz, X86::VPORDZ256rmkz, 0 }, + { X86::VPORQZ256rrkz, X86::VPORQZ256rmkz, 0 }, + { X86::VPSHUFBZ256rrkz, X86::VPSHUFBZ256rmkz, 0 }, + { X86::VPSLLDZ256rrkz, X86::VPSLLDZ256rmkz, 0 }, + { X86::VPSLLQZ256rrkz, X86::VPSLLQZ256rmkz, 0 }, + { X86::VPSLLVDZ256rrkz, X86::VPSLLVDZ256rmkz, 0 }, + { X86::VPSLLVQZ256rrkz, X86::VPSLLVQZ256rmkz, 0 }, + { X86::VPSLLVWZ256rrkz, X86::VPSLLVWZ256rmkz, 0 }, + { X86::VPSLLWZ256rrkz, X86::VPSLLWZ256rmkz, 0 }, + { X86::VPSRADZ256rrkz, X86::VPSRADZ256rmkz, 0 }, + { X86::VPSRAQZ256rrkz, X86::VPSRAQZ256rmkz, 0 }, + { X86::VPSRAVDZ256rrkz, X86::VPSRAVDZ256rmkz, 0 }, + { X86::VPSRAVQZ256rrkz, X86::VPSRAVQZ256rmkz, 0 }, + { X86::VPSRAVWZ256rrkz, X86::VPSRAVWZ256rmkz, 0 }, + { X86::VPSRAWZ256rrkz, X86::VPSRAWZ256rmkz, 0 }, + { X86::VPSRLDZ256rrkz, X86::VPSRLDZ256rmkz, 0 }, + { X86::VPSRLQZ256rrkz, X86::VPSRLQZ256rmkz, 0 }, + { X86::VPSRLVDZ256rrkz, X86::VPSRLVDZ256rmkz, 0 }, + { X86::VPSRLVQZ256rrkz, X86::VPSRLVQZ256rmkz, 0 }, + { X86::VPSRLVWZ256rrkz, X86::VPSRLVWZ256rmkz, 0 }, + { X86::VPSRLWZ256rrkz, X86::VPSRLWZ256rmkz, 0 }, + { X86::VPSUBBZ256rrkz, X86::VPSUBBZ256rmkz, 0 }, + { X86::VPSUBDZ256rrkz, X86::VPSUBDZ256rmkz, 0 }, + { X86::VPSUBQZ256rrkz, X86::VPSUBQZ256rmkz, 0 }, + { X86::VPSUBSBZ256rrkz, X86::VPSUBSBZ256rmkz, 0 }, + { X86::VPSUBSWZ256rrkz, X86::VPSUBSWZ256rmkz, 0 }, + { X86::VPSUBUSBZ256rrkz, X86::VPSUBUSBZ256rmkz, 0 }, + { X86::VPSUBUSWZ256rrkz, X86::VPSUBUSWZ256rmkz, 0 }, + { X86::VPSUBWZ256rrkz, X86::VPSUBWZ256rmkz, 0 }, + { X86::VPUNPCKHBWZ256rrkz, X86::VPUNPCKHBWZ256rmkz, 0 }, + { X86::VPUNPCKHDQZ256rrkz, X86::VPUNPCKHDQZ256rmkz, 0 }, + { X86::VPUNPCKHQDQZ256rrkz, X86::VPUNPCKHQDQZ256rmkz, 0 }, + { X86::VPUNPCKHWDZ256rrkz, X86::VPUNPCKHWDZ256rmkz, 0 }, + { X86::VPUNPCKLBWZ256rrkz, X86::VPUNPCKLBWZ256rmkz, 0 }, + { X86::VPUNPCKLDQZ256rrkz, X86::VPUNPCKLDQZ256rmkz, 0 }, + { X86::VPUNPCKLQDQZ256rrkz, X86::VPUNPCKLQDQZ256rmkz, 0 }, + { X86::VPUNPCKLWDZ256rrkz, X86::VPUNPCKLWDZ256rmkz, 0 }, + { X86::VPXORDZ256rrkz, X86::VPXORDZ256rmkz, 0 }, + { X86::VPXORQZ256rrkz, X86::VPXORQZ256rmkz, 0 }, + { X86::VSHUFPDZ256rrikz, X86::VSHUFPDZ256rmikz, 0 }, + { X86::VSHUFPSZ256rrikz, X86::VSHUFPSZ256rmikz, 0 }, + { X86::VSUBPDZ256rrkz, X86::VSUBPDZ256rmkz, 0 }, + { X86::VSUBPSZ256rrkz, X86::VSUBPSZ256rmkz, 0 }, + { X86::VUNPCKHPDZ256rrkz, X86::VUNPCKHPDZ256rmkz, 0 }, + { X86::VUNPCKHPSZ256rrkz, X86::VUNPCKHPSZ256rmkz, 0 }, + { X86::VUNPCKLPDZ256rrkz, X86::VUNPCKLPDZ256rmkz, 0 }, + { X86::VUNPCKLPSZ256rrkz, X86::VUNPCKLPSZ256rmkz, 0 }, + { X86::VXORPDZ256rrkz, X86::VXORPDZ256rmkz, 0 }, + { X86::VXORPSZ256rrkz, X86::VXORPSZ256rmkz, 0 }, + + // AVX-512{F,VL} masked arithmetic instructions 128-bit + { X86::VADDPDZ128rrkz, X86::VADDPDZ128rmkz, 0 }, + { X86::VADDPSZ128rrkz, X86::VADDPSZ128rmkz, 0 }, + { X86::VALIGNDZ128rrikz, X86::VALIGNDZ128rmikz, 0 }, + { X86::VALIGNQZ128rrikz, X86::VALIGNQZ128rmikz, 0 }, + { X86::VANDNPDZ128rrkz, X86::VANDNPDZ128rmkz, 0 }, + { X86::VANDNPSZ128rrkz, X86::VANDNPSZ128rmkz, 0 }, + { X86::VANDPDZ128rrkz, X86::VANDPDZ128rmkz, 0 }, + { X86::VANDPSZ128rrkz, X86::VANDPSZ128rmkz, 0 }, + { X86::VDIVPDZ128rrkz, X86::VDIVPDZ128rmkz, 0 }, + { X86::VDIVPSZ128rrkz, X86::VDIVPSZ128rmkz, 0 }, + { X86::VMAXCPDZ128rrkz, X86::VMAXCPDZ128rmkz, 0 }, + { X86::VMAXCPSZ128rrkz, X86::VMAXCPSZ128rmkz, 0 }, + { X86::VMAXPDZ128rrkz, X86::VMAXPDZ128rmkz, 0 }, + { X86::VMAXPSZ128rrkz, X86::VMAXPSZ128rmkz, 0 }, + { X86::VMINCPDZ128rrkz, X86::VMINCPDZ128rmkz, 0 }, + { X86::VMINCPSZ128rrkz, X86::VMINCPSZ128rmkz, 0 }, + { X86::VMINPDZ128rrkz, X86::VMINPDZ128rmkz, 0 }, + { X86::VMINPSZ128rrkz, X86::VMINPSZ128rmkz, 0 }, + { X86::VMULPDZ128rrkz, X86::VMULPDZ128rmkz, 0 }, + { X86::VMULPSZ128rrkz, X86::VMULPSZ128rmkz, 0 }, + { X86::VORPDZ128rrkz, X86::VORPDZ128rmkz, 0 }, + { X86::VORPSZ128rrkz, X86::VORPSZ128rmkz, 0 }, + { X86::VPACKSSDWZ128rrkz, X86::VPACKSSDWZ128rmkz, 0 }, + { X86::VPACKSSWBZ128rrkz, X86::VPACKSSWBZ128rmkz, 0 }, + { X86::VPACKUSDWZ128rrkz, X86::VPACKUSDWZ128rmkz, 0 }, + { X86::VPACKUSWBZ128rrkz, X86::VPACKUSWBZ128rmkz, 0 }, + { X86::VPADDBZ128rrkz, X86::VPADDBZ128rmkz, 0 }, + { X86::VPADDDZ128rrkz, X86::VPADDDZ128rmkz, 0 }, + { X86::VPADDQZ128rrkz, X86::VPADDQZ128rmkz, 0 }, + { X86::VPADDSBZ128rrkz, X86::VPADDSBZ128rmkz, 0 }, + { X86::VPADDSWZ128rrkz, X86::VPADDSWZ128rmkz, 0 }, + { X86::VPADDUSBZ128rrkz, X86::VPADDUSBZ128rmkz, 0 }, + { X86::VPADDUSWZ128rrkz, X86::VPADDUSWZ128rmkz, 0 }, + { X86::VPADDWZ128rrkz, X86::VPADDWZ128rmkz, 0 }, + { X86::VPALIGNRZ128rrikz, X86::VPALIGNRZ128rmikz, 0 }, + { X86::VPANDDZ128rrkz, X86::VPANDDZ128rmkz, 0 }, + { X86::VPANDNDZ128rrkz, X86::VPANDNDZ128rmkz, 0 }, + { X86::VPANDNQZ128rrkz, X86::VPANDNQZ128rmkz, 0 }, + { X86::VPANDQZ128rrkz, X86::VPANDQZ128rmkz, 0 }, + { X86::VPAVGBZ128rrkz, X86::VPAVGBZ128rmkz, 0 }, + { X86::VPAVGWZ128rrkz, X86::VPAVGWZ128rmkz, 0 }, + { X86::VPERMBZ128rrkz, X86::VPERMBZ128rmkz, 0 }, + { X86::VPERMILPDZ128rrkz, X86::VPERMILPDZ128rmkz, 0 }, + { X86::VPERMILPSZ128rrkz, X86::VPERMILPSZ128rmkz, 0 }, + { X86::VPERMWZ128rrkz, X86::VPERMWZ128rmkz, 0 }, + { X86::VPMADDUBSWZ128rrkz, X86::VPMADDUBSWZ128rmkz, 0 }, + { X86::VPMADDWDZ128rrkz, X86::VPMADDWDZ128rmkz, 0 }, + { X86::VPMAXSBZ128rrkz, X86::VPMAXSBZ128rmkz, 0 }, + { X86::VPMAXSDZ128rrkz, X86::VPMAXSDZ128rmkz, 0 }, + { X86::VPMAXSQZ128rrkz, X86::VPMAXSQZ128rmkz, 0 }, + { X86::VPMAXSWZ128rrkz, X86::VPMAXSWZ128rmkz, 0 }, + { X86::VPMAXUBZ128rrkz, X86::VPMAXUBZ128rmkz, 0 }, + { X86::VPMAXUDZ128rrkz, X86::VPMAXUDZ128rmkz, 0 }, + { X86::VPMAXUQZ128rrkz, X86::VPMAXUQZ128rmkz, 0 }, + { X86::VPMAXUWZ128rrkz, X86::VPMAXUWZ128rmkz, 0 }, + { X86::VPMINSBZ128rrkz, X86::VPMINSBZ128rmkz, 0 }, + { X86::VPMINSDZ128rrkz, X86::VPMINSDZ128rmkz, 0 }, + { X86::VPMINSQZ128rrkz, X86::VPMINSQZ128rmkz, 0 }, + { X86::VPMINSWZ128rrkz, X86::VPMINSWZ128rmkz, 0 }, + { X86::VPMINUBZ128rrkz, X86::VPMINUBZ128rmkz, 0 }, + { X86::VPMINUDZ128rrkz, X86::VPMINUDZ128rmkz, 0 }, + { X86::VPMINUQZ128rrkz, X86::VPMINUQZ128rmkz, 0 }, + { X86::VPMINUWZ128rrkz, X86::VPMINUWZ128rmkz, 0 }, + { X86::VPMULDQZ128rrkz, X86::VPMULDQZ128rmkz, 0 }, + { X86::VPMULLDZ128rrkz, X86::VPMULLDZ128rmkz, 0 }, + { X86::VPMULLQZ128rrkz, X86::VPMULLQZ128rmkz, 0 }, + { X86::VPMULLWZ128rrkz, X86::VPMULLWZ128rmkz, 0 }, + { X86::VPMULUDQZ128rrkz, X86::VPMULUDQZ128rmkz, 0 }, + { X86::VPORDZ128rrkz, X86::VPORDZ128rmkz, 0 }, + { X86::VPORQZ128rrkz, X86::VPORQZ128rmkz, 0 }, + { X86::VPSHUFBZ128rrkz, X86::VPSHUFBZ128rmkz, 0 }, + { X86::VPSLLDZ128rrkz, X86::VPSLLDZ128rmkz, 0 }, + { X86::VPSLLQZ128rrkz, X86::VPSLLQZ128rmkz, 0 }, + { X86::VPSLLVDZ128rrkz, X86::VPSLLVDZ128rmkz, 0 }, + { X86::VPSLLVQZ128rrkz, X86::VPSLLVQZ128rmkz, 0 }, + { X86::VPSLLVWZ128rrkz, X86::VPSLLVWZ128rmkz, 0 }, + { X86::VPSLLWZ128rrkz, X86::VPSLLWZ128rmkz, 0 }, + { X86::VPSRADZ128rrkz, X86::VPSRADZ128rmkz, 0 }, + { X86::VPSRAQZ128rrkz, X86::VPSRAQZ128rmkz, 0 }, + { X86::VPSRAVDZ128rrkz, X86::VPSRAVDZ128rmkz, 0 }, + { X86::VPSRAVQZ128rrkz, X86::VPSRAVQZ128rmkz, 0 }, + { X86::VPSRAVWZ128rrkz, X86::VPSRAVWZ128rmkz, 0 }, + { X86::VPSRAWZ128rrkz, X86::VPSRAWZ128rmkz, 0 }, + { X86::VPSRLDZ128rrkz, X86::VPSRLDZ128rmkz, 0 }, + { X86::VPSRLQZ128rrkz, X86::VPSRLQZ128rmkz, 0 }, + { X86::VPSRLVDZ128rrkz, X86::VPSRLVDZ128rmkz, 0 }, + { X86::VPSRLVQZ128rrkz, X86::VPSRLVQZ128rmkz, 0 }, + { X86::VPSRLVWZ128rrkz, X86::VPSRLVWZ128rmkz, 0 }, + { X86::VPSRLWZ128rrkz, X86::VPSRLWZ128rmkz, 0 }, + { X86::VPSUBBZ128rrkz, X86::VPSUBBZ128rmkz, 0 }, + { X86::VPSUBDZ128rrkz, X86::VPSUBDZ128rmkz, 0 }, + { X86::VPSUBQZ128rrkz, X86::VPSUBQZ128rmkz, 0 }, + { X86::VPSUBSBZ128rrkz, X86::VPSUBSBZ128rmkz, 0 }, + { X86::VPSUBSWZ128rrkz, X86::VPSUBSWZ128rmkz, 0 }, + { X86::VPSUBUSBZ128rrkz, X86::VPSUBUSBZ128rmkz, 0 }, + { X86::VPSUBUSWZ128rrkz, X86::VPSUBUSWZ128rmkz, 0 }, + { X86::VPSUBWZ128rrkz, X86::VPSUBWZ128rmkz, 0 }, + { X86::VPUNPCKHBWZ128rrkz, X86::VPUNPCKHBWZ128rmkz, 0 }, + { X86::VPUNPCKHDQZ128rrkz, X86::VPUNPCKHDQZ128rmkz, 0 }, + { X86::VPUNPCKHQDQZ128rrkz, X86::VPUNPCKHQDQZ128rmkz, 0 }, + { X86::VPUNPCKHWDZ128rrkz, X86::VPUNPCKHWDZ128rmkz, 0 }, + { X86::VPUNPCKLBWZ128rrkz, X86::VPUNPCKLBWZ128rmkz, 0 }, + { X86::VPUNPCKLDQZ128rrkz, X86::VPUNPCKLDQZ128rmkz, 0 }, + { X86::VPUNPCKLQDQZ128rrkz, X86::VPUNPCKLQDQZ128rmkz, 0 }, + { X86::VPUNPCKLWDZ128rrkz, X86::VPUNPCKLWDZ128rmkz, 0 }, + { X86::VPXORDZ128rrkz, X86::VPXORDZ128rmkz, 0 }, + { X86::VPXORQZ128rrkz, X86::VPXORQZ128rmkz, 0 }, + { X86::VSHUFPDZ128rrikz, X86::VSHUFPDZ128rmikz, 0 }, + { X86::VSHUFPSZ128rrikz, X86::VSHUFPSZ128rmikz, 0 }, + { X86::VSUBPDZ128rrkz, X86::VSUBPDZ128rmkz, 0 }, + { X86::VSUBPSZ128rrkz, X86::VSUBPSZ128rmkz, 0 }, + { X86::VUNPCKHPDZ128rrkz, X86::VUNPCKHPDZ128rmkz, 0 }, + { X86::VUNPCKHPSZ128rrkz, X86::VUNPCKHPSZ128rmkz, 0 }, + { X86::VUNPCKLPDZ128rrkz, X86::VUNPCKLPDZ128rmkz, 0 }, + { X86::VUNPCKLPSZ128rrkz, X86::VUNPCKLPSZ128rmkz, 0 }, + { X86::VXORPDZ128rrkz, X86::VXORPDZ128rmkz, 0 }, + { X86::VXORPSZ128rrkz, X86::VXORPSZ128rmkz, 0 }, + + // AVX-512 masked foldable instructions + { X86::VBROADCASTSSZrk, X86::VBROADCASTSSZmk, TB_NO_REVERSE }, + { X86::VBROADCASTSDZrk, X86::VBROADCASTSDZmk, TB_NO_REVERSE }, + { X86::VPABSBZrrk, X86::VPABSBZrmk, 0 }, + { X86::VPABSDZrrk, X86::VPABSDZrmk, 0 }, + { X86::VPABSQZrrk, X86::VPABSQZrmk, 0 }, + { X86::VPABSWZrrk, X86::VPABSWZrmk, 0 }, + { X86::VPERMILPDZrik, X86::VPERMILPDZmik, 0 }, + { X86::VPERMILPSZrik, X86::VPERMILPSZmik, 0 }, + { X86::VPERMPDZrik, X86::VPERMPDZmik, 0 }, + { X86::VPERMQZrik, X86::VPERMQZmik, 0 }, + { X86::VPMOVSXBDZrrk, X86::VPMOVSXBDZrmk, 0 }, + { X86::VPMOVSXBQZrrk, X86::VPMOVSXBQZrmk, TB_NO_REVERSE }, + { X86::VPMOVSXBWZrrk, X86::VPMOVSXBWZrmk, 0 }, + { X86::VPMOVSXDQZrrk, X86::VPMOVSXDQZrmk, 0 }, + { X86::VPMOVSXWDZrrk, X86::VPMOVSXWDZrmk, 0 }, + { X86::VPMOVSXWQZrrk, X86::VPMOVSXWQZrmk, 0 }, + { X86::VPMOVZXBDZrrk, X86::VPMOVZXBDZrmk, 0 }, + { X86::VPMOVZXBQZrrk, X86::VPMOVZXBQZrmk, TB_NO_REVERSE }, + { X86::VPMOVZXBWZrrk, X86::VPMOVZXBWZrmk, 0 }, + { X86::VPMOVZXDQZrrk, X86::VPMOVZXDQZrmk, 0 }, + { X86::VPMOVZXWDZrrk, X86::VPMOVZXWDZrmk, 0 }, + { X86::VPMOVZXWQZrrk, X86::VPMOVZXWQZrmk, 0 }, + { X86::VPOPCNTDZrrk, X86::VPOPCNTDZrmk, 0 }, + { X86::VPOPCNTQZrrk, X86::VPOPCNTQZrmk, 0 }, + { X86::VPSHUFDZrik, X86::VPSHUFDZmik, 0 }, + { X86::VPSHUFHWZrik, X86::VPSHUFHWZmik, 0 }, + { X86::VPSHUFLWZrik, X86::VPSHUFLWZmik, 0 }, + { X86::VPSLLDZrik, X86::VPSLLDZmik, 0 }, + { X86::VPSLLQZrik, X86::VPSLLQZmik, 0 }, + { X86::VPSLLWZrik, X86::VPSLLWZmik, 0 }, + { X86::VPSRADZrik, X86::VPSRADZmik, 0 }, + { X86::VPSRAQZrik, X86::VPSRAQZmik, 0 }, + { X86::VPSRAWZrik, X86::VPSRAWZmik, 0 }, + { X86::VPSRLDZrik, X86::VPSRLDZmik, 0 }, + { X86::VPSRLQZrik, X86::VPSRLQZmik, 0 }, + { X86::VPSRLWZrik, X86::VPSRLWZmik, 0 }, + + // AVX-512VL 256-bit masked foldable instructions + { X86::VBROADCASTSSZ256rk, X86::VBROADCASTSSZ256mk, TB_NO_REVERSE }, + { X86::VBROADCASTSDZ256rk, X86::VBROADCASTSDZ256mk, TB_NO_REVERSE }, + { X86::VPABSBZ256rrk, X86::VPABSBZ256rmk, 0 }, + { X86::VPABSDZ256rrk, X86::VPABSDZ256rmk, 0 }, + { X86::VPABSQZ256rrk, X86::VPABSQZ256rmk, 0 }, + { X86::VPABSWZ256rrk, X86::VPABSWZ256rmk, 0 }, + { X86::VPERMILPDZ256rik, X86::VPERMILPDZ256mik, 0 }, + { X86::VPERMILPSZ256rik, X86::VPERMILPSZ256mik, 0 }, + { X86::VPERMPDZ256rik, X86::VPERMPDZ256mik, 0 }, + { X86::VPERMQZ256rik, X86::VPERMQZ256mik, 0 }, + { X86::VPMOVSXBDZ256rrk, X86::VPMOVSXBDZ256rmk, TB_NO_REVERSE }, + { X86::VPMOVSXBQZ256rrk, X86::VPMOVSXBQZ256rmk, TB_NO_REVERSE }, + { X86::VPMOVSXBWZ256rrk, X86::VPMOVSXBWZ256rmk, 0 }, + { X86::VPMOVSXDQZ256rrk, X86::VPMOVSXDQZ256rmk, 0 }, + { X86::VPMOVSXWDZ256rrk, X86::VPMOVSXWDZ256rmk, 0 }, + { X86::VPMOVSXWQZ256rrk, X86::VPMOVSXWQZ256rmk, TB_NO_REVERSE }, + { X86::VPMOVZXBDZ256rrk, X86::VPMOVZXBDZ256rmk, TB_NO_REVERSE }, + { X86::VPMOVZXBQZ256rrk, X86::VPMOVZXBQZ256rmk, TB_NO_REVERSE }, + { X86::VPMOVZXBWZ256rrk, X86::VPMOVZXBWZ256rmk, 0 }, + { X86::VPMOVZXDQZ256rrk, X86::VPMOVZXDQZ256rmk, 0 }, + { X86::VPMOVZXWDZ256rrk, X86::VPMOVZXWDZ256rmk, 0 }, + { X86::VPMOVZXWQZ256rrk, X86::VPMOVZXWQZ256rmk, TB_NO_REVERSE }, + { X86::VPSHUFDZ256rik, X86::VPSHUFDZ256mik, 0 }, + { X86::VPSHUFHWZ256rik, X86::VPSHUFHWZ256mik, 0 }, + { X86::VPSHUFLWZ256rik, X86::VPSHUFLWZ256mik, 0 }, + { X86::VPSLLDZ256rik, X86::VPSLLDZ256mik, 0 }, + { X86::VPSLLQZ256rik, X86::VPSLLQZ256mik, 0 }, + { X86::VPSLLWZ256rik, X86::VPSLLWZ256mik, 0 }, + { X86::VPSRADZ256rik, X86::VPSRADZ256mik, 0 }, + { X86::VPSRAQZ256rik, X86::VPSRAQZ256mik, 0 }, + { X86::VPSRAWZ256rik, X86::VPSRAWZ256mik, 0 }, + { X86::VPSRLDZ256rik, X86::VPSRLDZ256mik, 0 }, + { X86::VPSRLQZ256rik, X86::VPSRLQZ256mik, 0 }, + { X86::VPSRLWZ256rik, X86::VPSRLWZ256mik, 0 }, + + // AVX-512VL 128-bit masked foldable instructions + { X86::VBROADCASTSSZ128rk, X86::VBROADCASTSSZ128mk, TB_NO_REVERSE }, + { X86::VPABSBZ128rrk, X86::VPABSBZ128rmk, 0 }, + { X86::VPABSDZ128rrk, X86::VPABSDZ128rmk, 0 }, + { X86::VPABSQZ128rrk, X86::VPABSQZ128rmk, 0 }, + { X86::VPABSWZ128rrk, X86::VPABSWZ128rmk, 0 }, + { X86::VPERMILPDZ128rik, X86::VPERMILPDZ128mik, 0 }, + { X86::VPERMILPSZ128rik, X86::VPERMILPSZ128mik, 0 }, + { X86::VPMOVSXBDZ128rrk, X86::VPMOVSXBDZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVSXBQZ128rrk, X86::VPMOVSXBQZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVSXBWZ128rrk, X86::VPMOVSXBWZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVSXDQZ128rrk, X86::VPMOVSXDQZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVSXWDZ128rrk, X86::VPMOVSXWDZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVSXWQZ128rrk, X86::VPMOVSXWQZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVZXBDZ128rrk, X86::VPMOVZXBDZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVZXBQZ128rrk, X86::VPMOVZXBQZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVZXBWZ128rrk, X86::VPMOVZXBWZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVZXDQZ128rrk, X86::VPMOVZXDQZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVZXWDZ128rrk, X86::VPMOVZXWDZ128rmk, TB_NO_REVERSE }, + { X86::VPMOVZXWQZ128rrk, X86::VPMOVZXWQZ128rmk, TB_NO_REVERSE }, + { X86::VPSHUFDZ128rik, X86::VPSHUFDZ128mik, 0 }, + { X86::VPSHUFHWZ128rik, X86::VPSHUFHWZ128mik, 0 }, + { X86::VPSHUFLWZ128rik, X86::VPSHUFLWZ128mik, 0 }, + { X86::VPSLLDZ128rik, X86::VPSLLDZ128mik, 0 }, + { X86::VPSLLQZ128rik, X86::VPSLLQZ128mik, 0 }, + { X86::VPSLLWZ128rik, X86::VPSLLWZ128mik, 0 }, + { X86::VPSRADZ128rik, X86::VPSRADZ128mik, 0 }, + { X86::VPSRAQZ128rik, X86::VPSRAQZ128mik, 0 }, + { X86::VPSRAWZ128rik, X86::VPSRAWZ128mik, 0 }, + { X86::VPSRLDZ128rik, X86::VPSRLDZ128mik, 0 }, + { X86::VPSRLQZ128rik, X86::VPSRLQZ128mik, 0 }, + { X86::VPSRLWZ128rik, X86::VPSRLWZ128mik, 0 }, + }; + for (X86MemoryFoldTableEntry Entry : MemoryFoldTable3) { AddTableEntry(RegOp2MemOpTable3, MemOp2RegOpTable, Entry.RegOp, Entry.MemOp, // Index 3, folded load Entry.Flags | TB_INDEX_3 | TB_FOLDED_LOAD); } + auto I = X86InstrFMA3Info::rm_begin(); + auto E = X86InstrFMA3Info::rm_end(); + for (; I != E; ++I) { + if (!I.getGroup()->isKMasked()) { + // Intrinsic forms need to pass TB_NO_REVERSE. + if (I.getGroup()->isIntrinsic()) { + AddTableEntry(RegOp2MemOpTable3, MemOp2RegOpTable, + I.getRegOpcode(), I.getMemOpcode(), + TB_ALIGN_NONE | TB_INDEX_3 | TB_FOLDED_LOAD | TB_NO_REVERSE); + } else { + AddTableEntry(RegOp2MemOpTable3, MemOp2RegOpTable, + I.getRegOpcode(), I.getMemOpcode(), + TB_ALIGN_NONE | TB_INDEX_3 | TB_FOLDED_LOAD); + } + } + } + + static const X86MemoryFoldTableEntry MemoryFoldTable4[] = { + // AVX-512 foldable masked instructions + { X86::VADDPDZrrk, X86::VADDPDZrmk, 0 }, + { X86::VADDPSZrrk, X86::VADDPSZrmk, 0 }, + { X86::VADDSDZrr_Intk, X86::VADDSDZrm_Intk, TB_NO_REVERSE }, + { X86::VADDSSZrr_Intk, X86::VADDSSZrm_Intk, TB_NO_REVERSE }, + { X86::VALIGNDZrrik, X86::VALIGNDZrmik, 0 }, + { X86::VALIGNQZrrik, X86::VALIGNQZrmik, 0 }, + { X86::VANDNPDZrrk, X86::VANDNPDZrmk, 0 }, + { X86::VANDNPSZrrk, X86::VANDNPSZrmk, 0 }, + { X86::VANDPDZrrk, X86::VANDPDZrmk, 0 }, + { X86::VANDPSZrrk, X86::VANDPSZrmk, 0 }, + { X86::VDIVPDZrrk, X86::VDIVPDZrmk, 0 }, + { X86::VDIVPSZrrk, X86::VDIVPSZrmk, 0 }, + { X86::VDIVSDZrr_Intk, X86::VDIVSDZrm_Intk, TB_NO_REVERSE }, + { X86::VDIVSSZrr_Intk, X86::VDIVSSZrm_Intk, TB_NO_REVERSE }, + { X86::VINSERTF32x4Zrrk, X86::VINSERTF32x4Zrmk, 0 }, + { X86::VINSERTF32x8Zrrk, X86::VINSERTF32x8Zrmk, 0 }, + { X86::VINSERTF64x2Zrrk, X86::VINSERTF64x2Zrmk, 0 }, + { X86::VINSERTF64x4Zrrk, X86::VINSERTF64x4Zrmk, 0 }, + { X86::VINSERTI32x4Zrrk, X86::VINSERTI32x4Zrmk, 0 }, + { X86::VINSERTI32x8Zrrk, X86::VINSERTI32x8Zrmk, 0 }, + { X86::VINSERTI64x2Zrrk, X86::VINSERTI64x2Zrmk, 0 }, + { X86::VINSERTI64x4Zrrk, X86::VINSERTI64x4Zrmk, 0 }, + { X86::VMAXCPDZrrk, X86::VMAXCPDZrmk, 0 }, + { X86::VMAXCPSZrrk, X86::VMAXCPSZrmk, 0 }, + { X86::VMAXPDZrrk, X86::VMAXPDZrmk, 0 }, + { X86::VMAXPSZrrk, X86::VMAXPSZrmk, 0 }, + { X86::VMAXSDZrr_Intk, X86::VMAXSDZrm_Intk, 0 }, + { X86::VMAXSSZrr_Intk, X86::VMAXSSZrm_Intk, 0 }, + { X86::VMINCPDZrrk, X86::VMINCPDZrmk, 0 }, + { X86::VMINCPSZrrk, X86::VMINCPSZrmk, 0 }, + { X86::VMINPDZrrk, X86::VMINPDZrmk, 0 }, + { X86::VMINPSZrrk, X86::VMINPSZrmk, 0 }, + { X86::VMINSDZrr_Intk, X86::VMINSDZrm_Intk, 0 }, + { X86::VMINSSZrr_Intk, X86::VMINSSZrm_Intk, 0 }, + { X86::VMULPDZrrk, X86::VMULPDZrmk, 0 }, + { X86::VMULPSZrrk, X86::VMULPSZrmk, 0 }, + { X86::VMULSDZrr_Intk, X86::VMULSDZrm_Intk, TB_NO_REVERSE }, + { X86::VMULSSZrr_Intk, X86::VMULSSZrm_Intk, TB_NO_REVERSE }, + { X86::VORPDZrrk, X86::VORPDZrmk, 0 }, + { X86::VORPSZrrk, X86::VORPSZrmk, 0 }, + { X86::VPACKSSDWZrrk, X86::VPACKSSDWZrmk, 0 }, + { X86::VPACKSSWBZrrk, X86::VPACKSSWBZrmk, 0 }, + { X86::VPACKUSDWZrrk, X86::VPACKUSDWZrmk, 0 }, + { X86::VPACKUSWBZrrk, X86::VPACKUSWBZrmk, 0 }, + { X86::VPADDBZrrk, X86::VPADDBZrmk, 0 }, + { X86::VPADDDZrrk, X86::VPADDDZrmk, 0 }, + { X86::VPADDQZrrk, X86::VPADDQZrmk, 0 }, + { X86::VPADDSBZrrk, X86::VPADDSBZrmk, 0 }, + { X86::VPADDSWZrrk, X86::VPADDSWZrmk, 0 }, + { X86::VPADDUSBZrrk, X86::VPADDUSBZrmk, 0 }, + { X86::VPADDUSWZrrk, X86::VPADDUSWZrmk, 0 }, + { X86::VPADDWZrrk, X86::VPADDWZrmk, 0 }, + { X86::VPALIGNRZrrik, X86::VPALIGNRZrmik, 0 }, + { X86::VPANDDZrrk, X86::VPANDDZrmk, 0 }, + { X86::VPANDNDZrrk, X86::VPANDNDZrmk, 0 }, + { X86::VPANDNQZrrk, X86::VPANDNQZrmk, 0 }, + { X86::VPANDQZrrk, X86::VPANDQZrmk, 0 }, + { X86::VPAVGBZrrk, X86::VPAVGBZrmk, 0 }, + { X86::VPAVGWZrrk, X86::VPAVGWZrmk, 0 }, + { X86::VPERMBZrrk, X86::VPERMBZrmk, 0 }, + { X86::VPERMDZrrk, X86::VPERMDZrmk, 0 }, + { X86::VPERMI2Brrk, X86::VPERMI2Brmk, 0 }, + { X86::VPERMI2Drrk, X86::VPERMI2Drmk, 0 }, + { X86::VPERMI2PSrrk, X86::VPERMI2PSrmk, 0 }, + { X86::VPERMI2PDrrk, X86::VPERMI2PDrmk, 0 }, + { X86::VPERMI2Qrrk, X86::VPERMI2Qrmk, 0 }, + { X86::VPERMI2Wrrk, X86::VPERMI2Wrmk, 0 }, + { X86::VPERMILPDZrrk, X86::VPERMILPDZrmk, 0 }, + { X86::VPERMILPSZrrk, X86::VPERMILPSZrmk, 0 }, + { X86::VPERMPDZrrk, X86::VPERMPDZrmk, 0 }, + { X86::VPERMPSZrrk, X86::VPERMPSZrmk, 0 }, + { X86::VPERMQZrrk, X86::VPERMQZrmk, 0 }, + { X86::VPERMT2Brrk, X86::VPERMT2Brmk, 0 }, + { X86::VPERMT2Drrk, X86::VPERMT2Drmk, 0 }, + { X86::VPERMT2PSrrk, X86::VPERMT2PSrmk, 0 }, + { X86::VPERMT2PDrrk, X86::VPERMT2PDrmk, 0 }, + { X86::VPERMT2Qrrk, X86::VPERMT2Qrmk, 0 }, + { X86::VPERMT2Wrrk, X86::VPERMT2Wrmk, 0 }, + { X86::VPERMWZrrk, X86::VPERMWZrmk, 0 }, + { X86::VPMADDUBSWZrrk, X86::VPMADDUBSWZrmk, 0 }, + { X86::VPMADDWDZrrk, X86::VPMADDWDZrmk, 0 }, + { X86::VPMAXSBZrrk, X86::VPMAXSBZrmk, 0 }, + { X86::VPMAXSDZrrk, X86::VPMAXSDZrmk, 0 }, + { X86::VPMAXSQZrrk, X86::VPMAXSQZrmk, 0 }, + { X86::VPMAXSWZrrk, X86::VPMAXSWZrmk, 0 }, + { X86::VPMAXUBZrrk, X86::VPMAXUBZrmk, 0 }, + { X86::VPMAXUDZrrk, X86::VPMAXUDZrmk, 0 }, + { X86::VPMAXUQZrrk, X86::VPMAXUQZrmk, 0 }, + { X86::VPMAXUWZrrk, X86::VPMAXUWZrmk, 0 }, + { X86::VPMINSBZrrk, X86::VPMINSBZrmk, 0 }, + { X86::VPMINSDZrrk, X86::VPMINSDZrmk, 0 }, + { X86::VPMINSQZrrk, X86::VPMINSQZrmk, 0 }, + { X86::VPMINSWZrrk, X86::VPMINSWZrmk, 0 }, + { X86::VPMINUBZrrk, X86::VPMINUBZrmk, 0 }, + { X86::VPMINUDZrrk, X86::VPMINUDZrmk, 0 }, + { X86::VPMINUQZrrk, X86::VPMINUQZrmk, 0 }, + { X86::VPMINUWZrrk, X86::VPMINUWZrmk, 0 }, + { X86::VPMULDQZrrk, X86::VPMULDQZrmk, 0 }, + { X86::VPMULLDZrrk, X86::VPMULLDZrmk, 0 }, + { X86::VPMULLQZrrk, X86::VPMULLQZrmk, 0 }, + { X86::VPMULLWZrrk, X86::VPMULLWZrmk, 0 }, + { X86::VPMULUDQZrrk, X86::VPMULUDQZrmk, 0 }, + { X86::VPORDZrrk, X86::VPORDZrmk, 0 }, + { X86::VPORQZrrk, X86::VPORQZrmk, 0 }, + { X86::VPSHUFBZrrk, X86::VPSHUFBZrmk, 0 }, + { X86::VPSLLDZrrk, X86::VPSLLDZrmk, 0 }, + { X86::VPSLLQZrrk, X86::VPSLLQZrmk, 0 }, + { X86::VPSLLVDZrrk, X86::VPSLLVDZrmk, 0 }, + { X86::VPSLLVQZrrk, X86::VPSLLVQZrmk, 0 }, + { X86::VPSLLVWZrrk, X86::VPSLLVWZrmk, 0 }, + { X86::VPSLLWZrrk, X86::VPSLLWZrmk, 0 }, + { X86::VPSRADZrrk, X86::VPSRADZrmk, 0 }, + { X86::VPSRAQZrrk, X86::VPSRAQZrmk, 0 }, + { X86::VPSRAVDZrrk, X86::VPSRAVDZrmk, 0 }, + { X86::VPSRAVQZrrk, X86::VPSRAVQZrmk, 0 }, + { X86::VPSRAVWZrrk, X86::VPSRAVWZrmk, 0 }, + { X86::VPSRAWZrrk, X86::VPSRAWZrmk, 0 }, + { X86::VPSRLDZrrk, X86::VPSRLDZrmk, 0 }, + { X86::VPSRLQZrrk, X86::VPSRLQZrmk, 0 }, + { X86::VPSRLVDZrrk, X86::VPSRLVDZrmk, 0 }, + { X86::VPSRLVQZrrk, X86::VPSRLVQZrmk, 0 }, + { X86::VPSRLVWZrrk, X86::VPSRLVWZrmk, 0 }, + { X86::VPSRLWZrrk, X86::VPSRLWZrmk, 0 }, + { X86::VPSUBBZrrk, X86::VPSUBBZrmk, 0 }, + { X86::VPSUBDZrrk, X86::VPSUBDZrmk, 0 }, + { X86::VPSUBQZrrk, X86::VPSUBQZrmk, 0 }, + { X86::VPSUBSBZrrk, X86::VPSUBSBZrmk, 0 }, + { X86::VPSUBSWZrrk, X86::VPSUBSWZrmk, 0 }, + { X86::VPSUBUSBZrrk, X86::VPSUBUSBZrmk, 0 }, + { X86::VPSUBUSWZrrk, X86::VPSUBUSWZrmk, 0 }, + { X86::VPTERNLOGDZrrik, X86::VPTERNLOGDZrmik, 0 }, + { X86::VPTERNLOGQZrrik, X86::VPTERNLOGQZrmik, 0 }, + { X86::VPUNPCKHBWZrrk, X86::VPUNPCKHBWZrmk, 0 }, + { X86::VPUNPCKHDQZrrk, X86::VPUNPCKHDQZrmk, 0 }, + { X86::VPUNPCKHQDQZrrk, X86::VPUNPCKHQDQZrmk, 0 }, + { X86::VPUNPCKHWDZrrk, X86::VPUNPCKHWDZrmk, 0 }, + { X86::VPUNPCKLBWZrrk, X86::VPUNPCKLBWZrmk, 0 }, + { X86::VPUNPCKLDQZrrk, X86::VPUNPCKLDQZrmk, 0 }, + { X86::VPUNPCKLQDQZrrk, X86::VPUNPCKLQDQZrmk, 0 }, + { X86::VPUNPCKLWDZrrk, X86::VPUNPCKLWDZrmk, 0 }, + { X86::VPXORDZrrk, X86::VPXORDZrmk, 0 }, + { X86::VPXORQZrrk, X86::VPXORQZrmk, 0 }, + { X86::VSHUFPDZrrik, X86::VSHUFPDZrmik, 0 }, + { X86::VSHUFPSZrrik, X86::VSHUFPSZrmik, 0 }, + { X86::VSUBPDZrrk, X86::VSUBPDZrmk, 0 }, + { X86::VSUBPSZrrk, X86::VSUBPSZrmk, 0 }, + { X86::VSUBSDZrr_Intk, X86::VSUBSDZrm_Intk, TB_NO_REVERSE }, + { X86::VSUBSSZrr_Intk, X86::VSUBSSZrm_Intk, TB_NO_REVERSE }, + { X86::VUNPCKHPDZrrk, X86::VUNPCKHPDZrmk, 0 }, + { X86::VUNPCKHPSZrrk, X86::VUNPCKHPSZrmk, 0 }, + { X86::VUNPCKLPDZrrk, X86::VUNPCKLPDZrmk, 0 }, + { X86::VUNPCKLPSZrrk, X86::VUNPCKLPSZrmk, 0 }, + { X86::VXORPDZrrk, X86::VXORPDZrmk, 0 }, + { X86::VXORPSZrrk, X86::VXORPSZrmk, 0 }, + + // AVX-512{F,VL} foldable masked instructions 256-bit + { X86::VADDPDZ256rrk, X86::VADDPDZ256rmk, 0 }, + { X86::VADDPSZ256rrk, X86::VADDPSZ256rmk, 0 }, + { X86::VALIGNDZ256rrik, X86::VALIGNDZ256rmik, 0 }, + { X86::VALIGNQZ256rrik, X86::VALIGNQZ256rmik, 0 }, + { X86::VANDNPDZ256rrk, X86::VANDNPDZ256rmk, 0 }, + { X86::VANDNPSZ256rrk, X86::VANDNPSZ256rmk, 0 }, + { X86::VANDPDZ256rrk, X86::VANDPDZ256rmk, 0 }, + { X86::VANDPSZ256rrk, X86::VANDPSZ256rmk, 0 }, + { X86::VDIVPDZ256rrk, X86::VDIVPDZ256rmk, 0 }, + { X86::VDIVPSZ256rrk, X86::VDIVPSZ256rmk, 0 }, + { X86::VINSERTF32x4Z256rrk,X86::VINSERTF32x4Z256rmk, 0 }, + { X86::VINSERTF64x2Z256rrk,X86::VINSERTF64x2Z256rmk, 0 }, + { X86::VINSERTI32x4Z256rrk,X86::VINSERTI32x4Z256rmk, 0 }, + { X86::VINSERTI64x2Z256rrk,X86::VINSERTI64x2Z256rmk, 0 }, + { X86::VMAXCPDZ256rrk, X86::VMAXCPDZ256rmk, 0 }, + { X86::VMAXCPSZ256rrk, X86::VMAXCPSZ256rmk, 0 }, + { X86::VMAXPDZ256rrk, X86::VMAXPDZ256rmk, 0 }, + { X86::VMAXPSZ256rrk, X86::VMAXPSZ256rmk, 0 }, + { X86::VMINCPDZ256rrk, X86::VMINCPDZ256rmk, 0 }, + { X86::VMINCPSZ256rrk, X86::VMINCPSZ256rmk, 0 }, + { X86::VMINPDZ256rrk, X86::VMINPDZ256rmk, 0 }, + { X86::VMINPSZ256rrk, X86::VMINPSZ256rmk, 0 }, + { X86::VMULPDZ256rrk, X86::VMULPDZ256rmk, 0 }, + { X86::VMULPSZ256rrk, X86::VMULPSZ256rmk, 0 }, + { X86::VORPDZ256rrk, X86::VORPDZ256rmk, 0 }, + { X86::VORPSZ256rrk, X86::VORPSZ256rmk, 0 }, + { X86::VPACKSSDWZ256rrk, X86::VPACKSSDWZ256rmk, 0 }, + { X86::VPACKSSWBZ256rrk, X86::VPACKSSWBZ256rmk, 0 }, + { X86::VPACKUSDWZ256rrk, X86::VPACKUSDWZ256rmk, 0 }, + { X86::VPACKUSWBZ256rrk, X86::VPACKUSWBZ256rmk, 0 }, + { X86::VPADDBZ256rrk, X86::VPADDBZ256rmk, 0 }, + { X86::VPADDDZ256rrk, X86::VPADDDZ256rmk, 0 }, + { X86::VPADDQZ256rrk, X86::VPADDQZ256rmk, 0 }, + { X86::VPADDSBZ256rrk, X86::VPADDSBZ256rmk, 0 }, + { X86::VPADDSWZ256rrk, X86::VPADDSWZ256rmk, 0 }, + { X86::VPADDUSBZ256rrk, X86::VPADDUSBZ256rmk, 0 }, + { X86::VPADDUSWZ256rrk, X86::VPADDUSWZ256rmk, 0 }, + { X86::VPADDWZ256rrk, X86::VPADDWZ256rmk, 0 }, + { X86::VPALIGNRZ256rrik, X86::VPALIGNRZ256rmik, 0 }, + { X86::VPANDDZ256rrk, X86::VPANDDZ256rmk, 0 }, + { X86::VPANDNDZ256rrk, X86::VPANDNDZ256rmk, 0 }, + { X86::VPANDNQZ256rrk, X86::VPANDNQZ256rmk, 0 }, + { X86::VPANDQZ256rrk, X86::VPANDQZ256rmk, 0 }, + { X86::VPAVGBZ256rrk, X86::VPAVGBZ256rmk, 0 }, + { X86::VPAVGWZ256rrk, X86::VPAVGWZ256rmk, 0 }, + { X86::VPERMBZ256rrk, X86::VPERMBZ256rmk, 0 }, + { X86::VPERMDZ256rrk, X86::VPERMDZ256rmk, 0 }, + { X86::VPERMI2B256rrk, X86::VPERMI2B256rmk, 0 }, + { X86::VPERMI2D256rrk, X86::VPERMI2D256rmk, 0 }, + { X86::VPERMI2PD256rrk, X86::VPERMI2PD256rmk, 0 }, + { X86::VPERMI2PS256rrk, X86::VPERMI2PS256rmk, 0 }, + { X86::VPERMI2Q256rrk, X86::VPERMI2Q256rmk, 0 }, + { X86::VPERMI2W256rrk, X86::VPERMI2W256rmk, 0 }, + { X86::VPERMILPDZ256rrk, X86::VPERMILPDZ256rmk, 0 }, + { X86::VPERMILPSZ256rrk, X86::VPERMILPSZ256rmk, 0 }, + { X86::VPERMPDZ256rrk, X86::VPERMPDZ256rmk, 0 }, + { X86::VPERMPSZ256rrk, X86::VPERMPSZ256rmk, 0 }, + { X86::VPERMQZ256rrk, X86::VPERMQZ256rmk, 0 }, + { X86::VPERMT2B256rrk, X86::VPERMT2B256rmk, 0 }, + { X86::VPERMT2D256rrk, X86::VPERMT2D256rmk, 0 }, + { X86::VPERMT2PD256rrk, X86::VPERMT2PD256rmk, 0 }, + { X86::VPERMT2PS256rrk, X86::VPERMT2PS256rmk, 0 }, + { X86::VPERMT2Q256rrk, X86::VPERMT2Q256rmk, 0 }, + { X86::VPERMT2W256rrk, X86::VPERMT2W256rmk, 0 }, + { X86::VPERMWZ256rrk, X86::VPERMWZ256rmk, 0 }, + { X86::VPMADDUBSWZ256rrk, X86::VPMADDUBSWZ256rmk, 0 }, + { X86::VPMADDWDZ256rrk, X86::VPMADDWDZ256rmk, 0 }, + { X86::VPMAXSBZ256rrk, X86::VPMAXSBZ256rmk, 0 }, + { X86::VPMAXSDZ256rrk, X86::VPMAXSDZ256rmk, 0 }, + { X86::VPMAXSQZ256rrk, X86::VPMAXSQZ256rmk, 0 }, + { X86::VPMAXSWZ256rrk, X86::VPMAXSWZ256rmk, 0 }, + { X86::VPMAXUBZ256rrk, X86::VPMAXUBZ256rmk, 0 }, + { X86::VPMAXUDZ256rrk, X86::VPMAXUDZ256rmk, 0 }, + { X86::VPMAXUQZ256rrk, X86::VPMAXUQZ256rmk, 0 }, + { X86::VPMAXUWZ256rrk, X86::VPMAXUWZ256rmk, 0 }, + { X86::VPMINSBZ256rrk, X86::VPMINSBZ256rmk, 0 }, + { X86::VPMINSDZ256rrk, X86::VPMINSDZ256rmk, 0 }, + { X86::VPMINSQZ256rrk, X86::VPMINSQZ256rmk, 0 }, + { X86::VPMINSWZ256rrk, X86::VPMINSWZ256rmk, 0 }, + { X86::VPMINUBZ256rrk, X86::VPMINUBZ256rmk, 0 }, + { X86::VPMINUDZ256rrk, X86::VPMINUDZ256rmk, 0 }, + { X86::VPMINUQZ256rrk, X86::VPMINUQZ256rmk, 0 }, + { X86::VPMINUWZ256rrk, X86::VPMINUWZ256rmk, 0 }, + { X86::VPMULDQZ256rrk, X86::VPMULDQZ256rmk, 0 }, + { X86::VPMULLDZ256rrk, X86::VPMULLDZ256rmk, 0 }, + { X86::VPMULLQZ256rrk, X86::VPMULLQZ256rmk, 0 }, + { X86::VPMULLWZ256rrk, X86::VPMULLWZ256rmk, 0 }, + { X86::VPMULUDQZ256rrk, X86::VPMULUDQZ256rmk, 0 }, + { X86::VPORDZ256rrk, X86::VPORDZ256rmk, 0 }, + { X86::VPORQZ256rrk, X86::VPORQZ256rmk, 0 }, + { X86::VPSHUFBZ256rrk, X86::VPSHUFBZ256rmk, 0 }, + { X86::VPSLLDZ256rrk, X86::VPSLLDZ256rmk, 0 }, + { X86::VPSLLQZ256rrk, X86::VPSLLQZ256rmk, 0 }, + { X86::VPSLLVDZ256rrk, X86::VPSLLVDZ256rmk, 0 }, + { X86::VPSLLVQZ256rrk, X86::VPSLLVQZ256rmk, 0 }, + { X86::VPSLLVWZ256rrk, X86::VPSLLVWZ256rmk, 0 }, + { X86::VPSLLWZ256rrk, X86::VPSLLWZ256rmk, 0 }, + { X86::VPSRADZ256rrk, X86::VPSRADZ256rmk, 0 }, + { X86::VPSRAQZ256rrk, X86::VPSRAQZ256rmk, 0 }, + { X86::VPSRAVDZ256rrk, X86::VPSRAVDZ256rmk, 0 }, + { X86::VPSRAVQZ256rrk, X86::VPSRAVQZ256rmk, 0 }, + { X86::VPSRAVWZ256rrk, X86::VPSRAVWZ256rmk, 0 }, + { X86::VPSRAWZ256rrk, X86::VPSRAWZ256rmk, 0 }, + { X86::VPSRLDZ256rrk, X86::VPSRLDZ256rmk, 0 }, + { X86::VPSRLQZ256rrk, X86::VPSRLQZ256rmk, 0 }, + { X86::VPSRLVDZ256rrk, X86::VPSRLVDZ256rmk, 0 }, + { X86::VPSRLVQZ256rrk, X86::VPSRLVQZ256rmk, 0 }, + { X86::VPSRLVWZ256rrk, X86::VPSRLVWZ256rmk, 0 }, + { X86::VPSRLWZ256rrk, X86::VPSRLWZ256rmk, 0 }, + { X86::VPSUBBZ256rrk, X86::VPSUBBZ256rmk, 0 }, + { X86::VPSUBDZ256rrk, X86::VPSUBDZ256rmk, 0 }, + { X86::VPSUBQZ256rrk, X86::VPSUBQZ256rmk, 0 }, + { X86::VPSUBSBZ256rrk, X86::VPSUBSBZ256rmk, 0 }, + { X86::VPSUBSWZ256rrk, X86::VPSUBSWZ256rmk, 0 }, + { X86::VPSUBUSBZ256rrk, X86::VPSUBUSBZ256rmk, 0 }, + { X86::VPSUBUSWZ256rrk, X86::VPSUBUSWZ256rmk, 0 }, + { X86::VPSUBWZ256rrk, X86::VPSUBWZ256rmk, 0 }, + { X86::VPTERNLOGDZ256rrik, X86::VPTERNLOGDZ256rmik, 0 }, + { X86::VPTERNLOGQZ256rrik, X86::VPTERNLOGQZ256rmik, 0 }, + { X86::VPUNPCKHBWZ256rrk, X86::VPUNPCKHBWZ256rmk, 0 }, + { X86::VPUNPCKHDQZ256rrk, X86::VPUNPCKHDQZ256rmk, 0 }, + { X86::VPUNPCKHQDQZ256rrk, X86::VPUNPCKHQDQZ256rmk, 0 }, + { X86::VPUNPCKHWDZ256rrk, X86::VPUNPCKHWDZ256rmk, 0 }, + { X86::VPUNPCKLBWZ256rrk, X86::VPUNPCKLBWZ256rmk, 0 }, + { X86::VPUNPCKLDQZ256rrk, X86::VPUNPCKLDQZ256rmk, 0 }, + { X86::VPUNPCKLQDQZ256rrk, X86::VPUNPCKLQDQZ256rmk, 0 }, + { X86::VPUNPCKLWDZ256rrk, X86::VPUNPCKLWDZ256rmk, 0 }, + { X86::VPXORDZ256rrk, X86::VPXORDZ256rmk, 0 }, + { X86::VPXORQZ256rrk, X86::VPXORQZ256rmk, 0 }, + { X86::VSHUFPDZ256rrik, X86::VSHUFPDZ256rmik, 0 }, + { X86::VSHUFPSZ256rrik, X86::VSHUFPSZ256rmik, 0 }, + { X86::VSUBPDZ256rrk, X86::VSUBPDZ256rmk, 0 }, + { X86::VSUBPSZ256rrk, X86::VSUBPSZ256rmk, 0 }, + { X86::VUNPCKHPDZ256rrk, X86::VUNPCKHPDZ256rmk, 0 }, + { X86::VUNPCKHPSZ256rrk, X86::VUNPCKHPSZ256rmk, 0 }, + { X86::VUNPCKLPDZ256rrk, X86::VUNPCKLPDZ256rmk, 0 }, + { X86::VUNPCKLPSZ256rrk, X86::VUNPCKLPSZ256rmk, 0 }, + { X86::VXORPDZ256rrk, X86::VXORPDZ256rmk, 0 }, + { X86::VXORPSZ256rrk, X86::VXORPSZ256rmk, 0 }, + + // AVX-512{F,VL} foldable instructions 128-bit + { X86::VADDPDZ128rrk, X86::VADDPDZ128rmk, 0 }, + { X86::VADDPSZ128rrk, X86::VADDPSZ128rmk, 0 }, + { X86::VALIGNDZ128rrik, X86::VALIGNDZ128rmik, 0 }, + { X86::VALIGNQZ128rrik, X86::VALIGNQZ128rmik, 0 }, + { X86::VANDNPDZ128rrk, X86::VANDNPDZ128rmk, 0 }, + { X86::VANDNPSZ128rrk, X86::VANDNPSZ128rmk, 0 }, + { X86::VANDPDZ128rrk, X86::VANDPDZ128rmk, 0 }, + { X86::VANDPSZ128rrk, X86::VANDPSZ128rmk, 0 }, + { X86::VDIVPDZ128rrk, X86::VDIVPDZ128rmk, 0 }, + { X86::VDIVPSZ128rrk, X86::VDIVPSZ128rmk, 0 }, + { X86::VMAXCPDZ128rrk, X86::VMAXCPDZ128rmk, 0 }, + { X86::VMAXCPSZ128rrk, X86::VMAXCPSZ128rmk, 0 }, + { X86::VMAXPDZ128rrk, X86::VMAXPDZ128rmk, 0 }, + { X86::VMAXPSZ128rrk, X86::VMAXPSZ128rmk, 0 }, + { X86::VMINCPDZ128rrk, X86::VMINCPDZ128rmk, 0 }, + { X86::VMINCPSZ128rrk, X86::VMINCPSZ128rmk, 0 }, + { X86::VMINPDZ128rrk, X86::VMINPDZ128rmk, 0 }, + { X86::VMINPSZ128rrk, X86::VMINPSZ128rmk, 0 }, + { X86::VMULPDZ128rrk, X86::VMULPDZ128rmk, 0 }, + { X86::VMULPSZ128rrk, X86::VMULPSZ128rmk, 0 }, + { X86::VORPDZ128rrk, X86::VORPDZ128rmk, 0 }, + { X86::VORPSZ128rrk, X86::VORPSZ128rmk, 0 }, + { X86::VPACKSSDWZ128rrk, X86::VPACKSSDWZ128rmk, 0 }, + { X86::VPACKSSWBZ128rrk, X86::VPACKSSWBZ128rmk, 0 }, + { X86::VPACKUSDWZ128rrk, X86::VPACKUSDWZ128rmk, 0 }, + { X86::VPACKUSWBZ128rrk, X86::VPACKUSWBZ128rmk, 0 }, + { X86::VPADDBZ128rrk, X86::VPADDBZ128rmk, 0 }, + { X86::VPADDDZ128rrk, X86::VPADDDZ128rmk, 0 }, + { X86::VPADDQZ128rrk, X86::VPADDQZ128rmk, 0 }, + { X86::VPADDSBZ128rrk, X86::VPADDSBZ128rmk, 0 }, + { X86::VPADDSWZ128rrk, X86::VPADDSWZ128rmk, 0 }, + { X86::VPADDUSBZ128rrk, X86::VPADDUSBZ128rmk, 0 }, + { X86::VPADDUSWZ128rrk, X86::VPADDUSWZ128rmk, 0 }, + { X86::VPADDWZ128rrk, X86::VPADDWZ128rmk, 0 }, + { X86::VPALIGNRZ128rrik, X86::VPALIGNRZ128rmik, 0 }, + { X86::VPANDDZ128rrk, X86::VPANDDZ128rmk, 0 }, + { X86::VPANDNDZ128rrk, X86::VPANDNDZ128rmk, 0 }, + { X86::VPANDNQZ128rrk, X86::VPANDNQZ128rmk, 0 }, + { X86::VPANDQZ128rrk, X86::VPANDQZ128rmk, 0 }, + { X86::VPAVGBZ128rrk, X86::VPAVGBZ128rmk, 0 }, + { X86::VPAVGWZ128rrk, X86::VPAVGWZ128rmk, 0 }, + { X86::VPERMBZ128rrk, X86::VPERMBZ128rmk, 0 }, + { X86::VPERMI2B128rrk, X86::VPERMI2B128rmk, 0 }, + { X86::VPERMI2D128rrk, X86::VPERMI2D128rmk, 0 }, + { X86::VPERMI2PD128rrk, X86::VPERMI2PD128rmk, 0 }, + { X86::VPERMI2PS128rrk, X86::VPERMI2PS128rmk, 0 }, + { X86::VPERMI2Q128rrk, X86::VPERMI2Q128rmk, 0 }, + { X86::VPERMI2W128rrk, X86::VPERMI2W128rmk, 0 }, + { X86::VPERMILPDZ128rrk, X86::VPERMILPDZ128rmk, 0 }, + { X86::VPERMILPSZ128rrk, X86::VPERMILPSZ128rmk, 0 }, + { X86::VPERMT2B128rrk, X86::VPERMT2B128rmk, 0 }, + { X86::VPERMT2D128rrk, X86::VPERMT2D128rmk, 0 }, + { X86::VPERMT2PD128rrk, X86::VPERMT2PD128rmk, 0 }, + { X86::VPERMT2PS128rrk, X86::VPERMT2PS128rmk, 0 }, + { X86::VPERMT2Q128rrk, X86::VPERMT2Q128rmk, 0 }, + { X86::VPERMT2W128rrk, X86::VPERMT2W128rmk, 0 }, + { X86::VPERMWZ128rrk, X86::VPERMWZ128rmk, 0 }, + { X86::VPMADDUBSWZ128rrk, X86::VPMADDUBSWZ128rmk, 0 }, + { X86::VPMADDWDZ128rrk, X86::VPMADDWDZ128rmk, 0 }, + { X86::VPMAXSBZ128rrk, X86::VPMAXSBZ128rmk, 0 }, + { X86::VPMAXSDZ128rrk, X86::VPMAXSDZ128rmk, 0 }, + { X86::VPMAXSQZ128rrk, X86::VPMAXSQZ128rmk, 0 }, + { X86::VPMAXSWZ128rrk, X86::VPMAXSWZ128rmk, 0 }, + { X86::VPMAXUBZ128rrk, X86::VPMAXUBZ128rmk, 0 }, + { X86::VPMAXUDZ128rrk, X86::VPMAXUDZ128rmk, 0 }, + { X86::VPMAXUQZ128rrk, X86::VPMAXUQZ128rmk, 0 }, + { X86::VPMAXUWZ128rrk, X86::VPMAXUWZ128rmk, 0 }, + { X86::VPMINSBZ128rrk, X86::VPMINSBZ128rmk, 0 }, + { X86::VPMINSDZ128rrk, X86::VPMINSDZ128rmk, 0 }, + { X86::VPMINSQZ128rrk, X86::VPMINSQZ128rmk, 0 }, + { X86::VPMINSWZ128rrk, X86::VPMINSWZ128rmk, 0 }, + { X86::VPMINUBZ128rrk, X86::VPMINUBZ128rmk, 0 }, + { X86::VPMINUDZ128rrk, X86::VPMINUDZ128rmk, 0 }, + { X86::VPMINUQZ128rrk, X86::VPMINUQZ128rmk, 0 }, + { X86::VPMINUWZ128rrk, X86::VPMINUWZ128rmk, 0 }, + { X86::VPMULDQZ128rrk, X86::VPMULDQZ128rmk, 0 }, + { X86::VPMULLDZ128rrk, X86::VPMULLDZ128rmk, 0 }, + { X86::VPMULLQZ128rrk, X86::VPMULLQZ128rmk, 0 }, + { X86::VPMULLWZ128rrk, X86::VPMULLWZ128rmk, 0 }, + { X86::VPMULUDQZ128rrk, X86::VPMULUDQZ128rmk, 0 }, + { X86::VPORDZ128rrk, X86::VPORDZ128rmk, 0 }, + { X86::VPORQZ128rrk, X86::VPORQZ128rmk, 0 }, + { X86::VPSHUFBZ128rrk, X86::VPSHUFBZ128rmk, 0 }, + { X86::VPSLLDZ128rrk, X86::VPSLLDZ128rmk, 0 }, + { X86::VPSLLQZ128rrk, X86::VPSLLQZ128rmk, 0 }, + { X86::VPSLLVDZ128rrk, X86::VPSLLVDZ128rmk, 0 }, + { X86::VPSLLVQZ128rrk, X86::VPSLLVQZ128rmk, 0 }, + { X86::VPSLLVWZ128rrk, X86::VPSLLVWZ128rmk, 0 }, + { X86::VPSLLWZ128rrk, X86::VPSLLWZ128rmk, 0 }, + { X86::VPSRADZ128rrk, X86::VPSRADZ128rmk, 0 }, + { X86::VPSRAQZ128rrk, X86::VPSRAQZ128rmk, 0 }, + { X86::VPSRAVDZ128rrk, X86::VPSRAVDZ128rmk, 0 }, + { X86::VPSRAVQZ128rrk, X86::VPSRAVQZ128rmk, 0 }, + { X86::VPSRAVWZ128rrk, X86::VPSRAVWZ128rmk, 0 }, + { X86::VPSRAWZ128rrk, X86::VPSRAWZ128rmk, 0 }, + { X86::VPSRLDZ128rrk, X86::VPSRLDZ128rmk, 0 }, + { X86::VPSRLQZ128rrk, X86::VPSRLQZ128rmk, 0 }, + { X86::VPSRLVDZ128rrk, X86::VPSRLVDZ128rmk, 0 }, + { X86::VPSRLVQZ128rrk, X86::VPSRLVQZ128rmk, 0 }, + { X86::VPSRLVWZ128rrk, X86::VPSRLVWZ128rmk, 0 }, + { X86::VPSRLWZ128rrk, X86::VPSRLWZ128rmk, 0 }, + { X86::VPSUBBZ128rrk, X86::VPSUBBZ128rmk, 0 }, + { X86::VPSUBDZ128rrk, X86::VPSUBDZ128rmk, 0 }, + { X86::VPSUBQZ128rrk, X86::VPSUBQZ128rmk, 0 }, + { X86::VPSUBSBZ128rrk, X86::VPSUBSBZ128rmk, 0 }, + { X86::VPSUBSWZ128rrk, X86::VPSUBSWZ128rmk, 0 }, + { X86::VPSUBUSBZ128rrk, X86::VPSUBUSBZ128rmk, 0 }, + { X86::VPSUBUSWZ128rrk, X86::VPSUBUSWZ128rmk, 0 }, + { X86::VPSUBWZ128rrk, X86::VPSUBWZ128rmk, 0 }, + { X86::VPTERNLOGDZ128rrik, X86::VPTERNLOGDZ128rmik, 0 }, + { X86::VPTERNLOGQZ128rrik, X86::VPTERNLOGQZ128rmik, 0 }, + { X86::VPUNPCKHBWZ128rrk, X86::VPUNPCKHBWZ128rmk, 0 }, + { X86::VPUNPCKHDQZ128rrk, X86::VPUNPCKHDQZ128rmk, 0 }, + { X86::VPUNPCKHQDQZ128rrk, X86::VPUNPCKHQDQZ128rmk, 0 }, + { X86::VPUNPCKHWDZ128rrk, X86::VPUNPCKHWDZ128rmk, 0 }, + { X86::VPUNPCKLBWZ128rrk, X86::VPUNPCKLBWZ128rmk, 0 }, + { X86::VPUNPCKLDQZ128rrk, X86::VPUNPCKLDQZ128rmk, 0 }, + { X86::VPUNPCKLQDQZ128rrk, X86::VPUNPCKLQDQZ128rmk, 0 }, + { X86::VPUNPCKLWDZ128rrk, X86::VPUNPCKLWDZ128rmk, 0 }, + { X86::VPXORDZ128rrk, X86::VPXORDZ128rmk, 0 }, + { X86::VPXORQZ128rrk, X86::VPXORQZ128rmk, 0 }, + { X86::VSHUFPDZ128rrik, X86::VSHUFPDZ128rmik, 0 }, + { X86::VSHUFPSZ128rrik, X86::VSHUFPSZ128rmik, 0 }, + { X86::VSUBPDZ128rrk, X86::VSUBPDZ128rmk, 0 }, + { X86::VSUBPSZ128rrk, X86::VSUBPSZ128rmk, 0 }, + { X86::VUNPCKHPDZ128rrk, X86::VUNPCKHPDZ128rmk, 0 }, + { X86::VUNPCKHPSZ128rrk, X86::VUNPCKHPSZ128rmk, 0 }, + { X86::VUNPCKLPDZ128rrk, X86::VUNPCKLPDZ128rmk, 0 }, + { X86::VUNPCKLPSZ128rrk, X86::VUNPCKLPSZ128rmk, 0 }, + { X86::VXORPDZ128rrk, X86::VXORPDZ128rmk, 0 }, + { X86::VXORPSZ128rrk, X86::VXORPSZ128rmk, 0 }, + + // 512-bit three source instructions with zero masking. + { X86::VPERMI2Brrkz, X86::VPERMI2Brmkz, 0 }, + { X86::VPERMI2Drrkz, X86::VPERMI2Drmkz, 0 }, + { X86::VPERMI2PSrrkz, X86::VPERMI2PSrmkz, 0 }, + { X86::VPERMI2PDrrkz, X86::VPERMI2PDrmkz, 0 }, + { X86::VPERMI2Qrrkz, X86::VPERMI2Qrmkz, 0 }, + { X86::VPERMI2Wrrkz, X86::VPERMI2Wrmkz, 0 }, + { X86::VPERMT2Brrkz, X86::VPERMT2Brmkz, 0 }, + { X86::VPERMT2Drrkz, X86::VPERMT2Drmkz, 0 }, + { X86::VPERMT2PSrrkz, X86::VPERMT2PSrmkz, 0 }, + { X86::VPERMT2PDrrkz, X86::VPERMT2PDrmkz, 0 }, + { X86::VPERMT2Qrrkz, X86::VPERMT2Qrmkz, 0 }, + { X86::VPERMT2Wrrkz, X86::VPERMT2Wrmkz, 0 }, + { X86::VPTERNLOGDZrrikz, X86::VPTERNLOGDZrmikz, 0 }, + { X86::VPTERNLOGQZrrikz, X86::VPTERNLOGQZrmikz, 0 }, + + // 256-bit three source instructions with zero masking. + { X86::VPERMI2B256rrkz, X86::VPERMI2B256rmkz, 0 }, + { X86::VPERMI2D256rrkz, X86::VPERMI2D256rmkz, 0 }, + { X86::VPERMI2PD256rrkz, X86::VPERMI2PD256rmkz, 0 }, + { X86::VPERMI2PS256rrkz, X86::VPERMI2PS256rmkz, 0 }, + { X86::VPERMI2Q256rrkz, X86::VPERMI2Q256rmkz, 0 }, + { X86::VPERMI2W256rrkz, X86::VPERMI2W256rmkz, 0 }, + { X86::VPERMT2B256rrkz, X86::VPERMT2B256rmkz, 0 }, + { X86::VPERMT2D256rrkz, X86::VPERMT2D256rmkz, 0 }, + { X86::VPERMT2PD256rrkz, X86::VPERMT2PD256rmkz, 0 }, + { X86::VPERMT2PS256rrkz, X86::VPERMT2PS256rmkz, 0 }, + { X86::VPERMT2Q256rrkz, X86::VPERMT2Q256rmkz, 0 }, + { X86::VPERMT2W256rrkz, X86::VPERMT2W256rmkz, 0 }, + { X86::VPTERNLOGDZ256rrikz,X86::VPTERNLOGDZ256rmikz, 0 }, + { X86::VPTERNLOGQZ256rrikz,X86::VPTERNLOGQZ256rmikz, 0 }, + + // 128-bit three source instructions with zero masking. + { X86::VPERMI2B128rrkz, X86::VPERMI2B128rmkz, 0 }, + { X86::VPERMI2D128rrkz, X86::VPERMI2D128rmkz, 0 }, + { X86::VPERMI2PD128rrkz, X86::VPERMI2PD128rmkz, 0 }, + { X86::VPERMI2PS128rrkz, X86::VPERMI2PS128rmkz, 0 }, + { X86::VPERMI2Q128rrkz, X86::VPERMI2Q128rmkz, 0 }, + { X86::VPERMI2W128rrkz, X86::VPERMI2W128rmkz, 0 }, + { X86::VPERMT2B128rrkz, X86::VPERMT2B128rmkz, 0 }, + { X86::VPERMT2D128rrkz, X86::VPERMT2D128rmkz, 0 }, + { X86::VPERMT2PD128rrkz, X86::VPERMT2PD128rmkz, 0 }, + { X86::VPERMT2PS128rrkz, X86::VPERMT2PS128rmkz, 0 }, + { X86::VPERMT2Q128rrkz, X86::VPERMT2Q128rmkz, 0 }, + { X86::VPERMT2W128rrkz, X86::VPERMT2W128rmkz, 0 }, + { X86::VPTERNLOGDZ128rrikz,X86::VPTERNLOGDZ128rmikz, 0 }, + { X86::VPTERNLOGQZ128rrikz,X86::VPTERNLOGQZ128rmikz, 0 }, + }; for (X86MemoryFoldTableEntry Entry : MemoryFoldTable4) { AddTableEntry(RegOp2MemOpTable4, MemOp2RegOpTable, @@ -163,6 +3545,20 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI) // Index 4, folded load Entry.Flags | TB_INDEX_4 | TB_FOLDED_LOAD); } + for (I = X86InstrFMA3Info::rm_begin(); I != E; ++I) { + if (I.getGroup()->isKMasked()) { + // Intrinsics need to pass TB_NO_REVERSE. + if (I.getGroup()->isIntrinsic()) { + AddTableEntry(RegOp2MemOpTable4, MemOp2RegOpTable, + I.getRegOpcode(), I.getMemOpcode(), + TB_ALIGN_NONE | TB_INDEX_4 | TB_FOLDED_LOAD | TB_NO_REVERSE); + } else { + AddTableEntry(RegOp2MemOpTable4, MemOp2RegOpTable, + I.getRegOpcode(), I.getMemOpcode(), + TB_ALIGN_NONE | TB_INDEX_4 | TB_FOLDED_LOAD); + } + } + } } void diff --git a/test/CodeGen/X86/sse42-intrinsics-fast-isel.ll b/test/CodeGen/X86/sse42-intrinsics-fast-isel.ll index 19305d0dad6..383ab21bd40 100644 --- a/test/CodeGen/X86/sse42-intrinsics-fast-isel.ll +++ b/test/CodeGen/X86/sse42-intrinsics-fast-isel.ll @@ -354,8 +354,9 @@ declare i32 @llvm.x86.sse42.pcmpistriz128(<16 x i8>, <16 x i8>, i8) nounwind rea define i32 @test_mm_crc32_u8(i32 %a0, i8 %a1) { ; X32-LABEL: test_mm_crc32_u8: ; X32: # BB#0: +; X32-NEXT: movb {{[0-9]+}}(%esp), %cl ; X32-NEXT: movl {{[0-9]+}}(%esp), %eax -; X32-NEXT: crc32b {{[0-9]+}}(%esp), %eax +; X32-NEXT: crc32b %cl, %eax ; X32-NEXT: retl ; ; X64-LABEL: test_mm_crc32_u8: @@ -371,8 +372,9 @@ declare i32 @llvm.x86.sse42.crc32.32.8(i32, i8) nounwind readnone define i32 @test_mm_crc32_u16(i32 %a0, i16 %a1) { ; X32-LABEL: test_mm_crc32_u16: ; X32: # BB#0: +; X32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx ; X32-NEXT: movl {{[0-9]+}}(%esp), %eax -; X32-NEXT: crc32w {{[0-9]+}}(%esp), %eax +; X32-NEXT: crc32w %cx, %eax ; X32-NEXT: retl ; ; X64-LABEL: test_mm_crc32_u16: diff --git a/test/CodeGen/X86/stack-folding-fp-avx1.ll b/test/CodeGen/X86/stack-folding-fp-avx1.ll index f937d484ce0..4165aea8794 100644 --- a/test/CodeGen/X86/stack-folding-fp-avx1.ll +++ b/test/CodeGen/X86/stack-folding-fp-avx1.ll @@ -1651,9 +1651,26 @@ define <8 x float> @stack_fold_sqrtps_ymm(<8 x float> %a0) { } declare <8 x float> @llvm.x86.avx.sqrt.ps.256(<8 x float>) nounwind readnone -; TODO stack_fold_sqrtsd +define double @stack_fold_sqrtsd(double %a0) { + ;CHECK-LABEL: stack_fold_sqrtsd + ;CHECK: vsqrtsd {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 8-byte Folded Reload + %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"() + %2 = call double @llvm.sqrt.f64(double %a0) + ret double %2 +} +declare double @llvm.sqrt.f64(double) nounwind readnone + ; TODO stack_fold_sqrtsd_int -; TODO stack_fold_sqrtss + +define float @stack_fold_sqrtss(float %a0) { + ;CHECK-LABEL: stack_fold_sqrtss + ;CHECK: vsqrtss {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 4-byte Folded Reload + %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"() + %2 = call float @llvm.sqrt.f32(float %a0) + ret float %2 +} +declare float @llvm.sqrt.f32(float) nounwind readnone + ; TODO stack_fold_sqrtss_int define <2 x double> @stack_fold_subpd(<2 x double> %a0, <2 x double> %a1) { diff --git a/test/CodeGen/X86/vector-sqrt.ll b/test/CodeGen/X86/vector-sqrt.ll index 13088b7fa5f..c5ac4466b5f 100644 --- a/test/CodeGen/X86/vector-sqrt.ll +++ b/test/CodeGen/X86/vector-sqrt.ll @@ -5,10 +5,8 @@ define <2 x double> @sqrtd2(double* nocapture readonly %v) local_unnamed_addr #0 { ; CHECK-LABEL: sqrtd2: ; CHECK: # BB#0: # %entry -; CHECK-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero -; CHECK-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero -; CHECK-NEXT: vsqrtsd %xmm0, %xmm0, %xmm0 -; CHECK-NEXT: vsqrtsd %xmm1, %xmm1, %xmm1 +; CHECK-NEXT: vsqrtsd (%rdi), %xmm0, %xmm0 +; CHECK-NEXT: vsqrtsd 8(%rdi), %xmm1, %xmm1 ; CHECK-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0] ; CHECK-NEXT: retq entry: @@ -29,14 +27,10 @@ declare double @sqrt(double) local_unnamed_addr #1 define <4 x float> @sqrtf4(float* nocapture readonly %v) local_unnamed_addr #0 { ; CHECK-LABEL: sqrtf4: ; CHECK: # BB#0: # %entry -; CHECK-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero -; CHECK-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero -; CHECK-NEXT: vsqrtss %xmm0, %xmm0, %xmm0 -; CHECK-NEXT: vsqrtss %xmm1, %xmm1, %xmm1 -; CHECK-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero -; CHECK-NEXT: vsqrtss %xmm2, %xmm2, %xmm2 -; CHECK-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero -; CHECK-NEXT: vsqrtss %xmm3, %xmm3, %xmm3 +; CHECK-NEXT: vsqrtss (%rdi), %xmm0, %xmm0 +; CHECK-NEXT: vsqrtss 4(%rdi), %xmm1, %xmm1 +; CHECK-NEXT: vsqrtss 8(%rdi), %xmm2, %xmm2 +; CHECK-NEXT: vsqrtss 12(%rdi), %xmm3, %xmm3 ; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3] ; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],xmm2[0],xmm0[3] ; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm3[0] diff --git a/utils/TableGen/CMakeLists.txt b/utils/TableGen/CMakeLists.txt index 9933c8319d3..b2913afae12 100644 --- a/utils/TableGen/CMakeLists.txt +++ b/utils/TableGen/CMakeLists.txt @@ -35,7 +35,6 @@ add_tablegen(llvm-tblgen LLVM TableGen.cpp Types.cpp X86DisassemblerTables.cpp - X86FoldTablesEmitter.cpp X86EVEX2VEXTablesEmitter.cpp X86ModRMFilters.cpp X86RecognizableInstr.cpp diff --git a/utils/TableGen/TableGen.cpp b/utils/TableGen/TableGen.cpp index 329ce348727..00d20f1df6c 100644 --- a/utils/TableGen/TableGen.cpp +++ b/utils/TableGen/TableGen.cpp @@ -46,7 +46,6 @@ enum ActionType { GenAttributes, GenSearchableTables, GenGlobalISel, - GenX86FoldTables, GenX86EVEX2VEXTables, GenRegisterBank, }; @@ -98,8 +97,6 @@ namespace { "Generate generic binary-searchable table"), clEnumValN(GenGlobalISel, "gen-global-isel", "Generate GlobalISel selector"), - clEnumValN(GenX86FoldTables, "gen-x86-fold-tables", - "Generate X86 fold tables"), clEnumValN(GenX86EVEX2VEXTables, "gen-x86-EVEX2VEX-tables", "Generate X86 EVEX to VEX compress tables"), clEnumValN(GenRegisterBank, "gen-register-bank", @@ -193,9 +190,6 @@ bool LLVMTableGenMain(raw_ostream &OS, RecordKeeper &Records) { case GenGlobalISel: EmitGlobalISel(Records, OS); break; - case GenX86FoldTables: - EmitX86FoldTables(Records, OS); - break; case GenRegisterBank: EmitRegisterBank(Records, OS); break; diff --git a/utils/TableGen/TableGenBackends.h b/utils/TableGen/TableGenBackends.h index 53614df27c4..2512997e27f 100644 --- a/utils/TableGen/TableGenBackends.h +++ b/utils/TableGen/TableGenBackends.h @@ -81,7 +81,6 @@ void EmitCTags(RecordKeeper &RK, raw_ostream &OS); void EmitAttributes(RecordKeeper &RK, raw_ostream &OS); void EmitSearchableTables(RecordKeeper &RK, raw_ostream &OS); void EmitGlobalISel(RecordKeeper &RK, raw_ostream &OS); -void EmitX86FoldTables(RecordKeeper &RK, raw_ostream &OS); void EmitX86EVEX2VEXTables(RecordKeeper &RK, raw_ostream &OS); void EmitRegisterBank(RecordKeeper &RK, raw_ostream &OS); diff --git a/utils/TableGen/X86FoldTablesEmitter.cpp b/utils/TableGen/X86FoldTablesEmitter.cpp deleted file mode 100644 index 34f5fbc6ea3..00000000000 --- a/utils/TableGen/X86FoldTablesEmitter.cpp +++ /dev/null @@ -1,732 +0,0 @@ -//===- utils/TableGen/X86FoldTablesEmitter.cpp - X86 backend-*- C++ -*-===// -// -// The LLVM Compiler Infrastructure -// -// This file is distributed under the University of Illinois Open Source -// License. See LICENSE.TXT for details. -// -//===----------------------------------------------------------------------===// -// -// This tablegen backend is responsible for emitting the memory fold tables of -// the X86 backend instructions. -// -//===----------------------------------------------------------------------===// - -#include "CodeGenDAGPatterns.h" -#include "CodeGenTarget.h" -#include "X86RecognizableInstr.h" -#include "llvm/TableGen/Error.h" -#include "llvm/TableGen/TableGenBackend.h" - -using namespace llvm; - -namespace { - -// 3 possible strategies for the unfolding flag (TB_NO_REVERSE) of the -// manual added entries. -enum UnfoldStrategy { - UNFOLD, // Allow unfolding - NO_UNFOLD, // Prevent unfolding - NO_STRATEGY // Make decision according to operands' sizes -}; - -// Represents an entry in the manual mapped instructions set. -struct ManualMapEntry { - const char *RegInstStr; - const char *MemInstStr; - UnfoldStrategy Strategy; - - ManualMapEntry(const char *RegInstStr, const char *MemInstStr, - UnfoldStrategy Strategy = NO_STRATEGY) - : RegInstStr(RegInstStr), MemInstStr(MemInstStr), Strategy(Strategy) {} -}; - -class IsMatch; - -// List of instructions requiring explicitly aligned memory. -const char *const ExplicitAlign[] = {"MOVDQA", "MOVAPS", "MOVAPD", "MOVNTPS", - "MOVNTPD", "MOVNTDQ", "MOVNTDQA"}; - -// List of instructions NOT requiring explicit memory alignment. -const char *const ExplicitUnalign[] = {"MOVDQU", "MOVUPS", "MOVUPD"}; - -// For manually mapping instructions that do not match by their encoding. -const ManualMapEntry ManualMapSet[] = { - { "ADD16ri_DB", "ADD16mi", NO_UNFOLD }, - { "ADD16ri8_DB", "ADD16mi8", NO_UNFOLD }, - { "ADD16rr_DB", "ADD16mr", NO_UNFOLD }, - { "ADD32ri_DB", "ADD32mi", NO_UNFOLD }, - { "ADD32ri8_DB", "ADD32mi8", NO_UNFOLD }, - { "ADD32rr_DB", "ADD32mr", NO_UNFOLD }, - { "ADD64ri32_DB", "ADD64mi32", NO_UNFOLD }, - { "ADD64ri8_DB", "ADD64mi8", NO_UNFOLD }, - { "ADD64rr_DB", "ADD64mr", NO_UNFOLD }, - { "ADD16rr_DB", "ADD16rm", NO_UNFOLD }, - { "ADD32rr_DB", "ADD32rm", NO_UNFOLD }, - { "ADD64rr_DB", "ADD64rm", NO_UNFOLD }, - { "PUSH16r", "PUSH16rmm", NO_UNFOLD }, - { "PUSH32r", "PUSH32rmm", NO_UNFOLD }, - { "PUSH64r", "PUSH64rmm", NO_UNFOLD }, - { "TAILJMPr", "TAILJMPm", UNFOLD }, - { "TAILJMPr64", "TAILJMPm64", UNFOLD }, - { "TAILJMPr64_REX", "TAILJMPm64_REX", UNFOLD }, -}; - -// Do not add these instructions to any of the folding tables. -const char *const NoFoldSet[] = { - "TCRETURNri64", - "TCRETURNmi64", // Special dealing (in X86InstrCompiler.td under - "TCRETURNri", // "tailcall stuff" section). - "TCRETURNmi", - - // Never fold XCHG, the register and memory forms have different locking - // semantics. - "XCHG8rr", "XCHG8rm", - "XCHG16rr", "XCHG16rm", - "XCHG32rr", "XCHG32rm", - "XCHG64rr", "XCHG64rm", - - // Different calculations of the folded operand between - // memory and register forms (folding is illegal). - // - In their register form, the second register operand's relevant - // bits are only the first 4/5/6 (depending on mode and reg size). - // - In their memory form, the second register operand's relevant - // bits are only the first 16/32/64 (depending on mode and reg size). - "BT16rr", "BT32rr", "BT64rr", - "BT16mr", "BT32mr", "BT64mr", - "BTC16rr", "BTC32rr", "BTC64rr", - "BTC16mr", "BTC32mr", "BTC64mr", - "BTR16rr", "BTR32rr", "BTR64rr", - "BTR16mr", "BTR32mr", "BTR64mr", - "BTS16rr", "BTS32rr", "BTS64rr", - "BTS16mr", "BTS32mr", "BTS64mr", - - // insertps cannot be folded without adjusting the immediate. There's custom - // code to handle it in X86InstrInfo.cpp, ignore it here. - "INSERTPSrr", "INSERTPSrm", - "VINSERTPSrr", "VINSERTPSrm", "VINSERTPSZrr", "VINSERTPSZrm", - - // Memory folding is enabled only when optimizing for size by DAG - // patterns only. (issue detailed in D28744 review) - "VCVTSS2SDrm", "VCVTSS2SDrr", - "VCVTSS2SDZrm", "VCVTSS2SDZrr", - "VCVTSS2SDZrmk", "VCVTSS2SDZrrk", - "VCVTSS2SDZrmkz", "VCVTSS2SDZrrkz", - "VCVTSS2SDZrm_Int", "VCVTSS2SDZrr_Int", - "VCVTSS2SDZrm_Intk", "VCVTSS2SDZrr_Intk", - "VCVTSS2SDZrm_Intkz", "VCVTSS2SDZrr_Intkz", - "VCVTSD2SSrm", "VCVTSD2SSrr", - "VCVTSD2SSZrm", "VCVTSD2SSZrr", - "VCVTSD2SSZrmk", "VCVTSD2SSZrrk", - "VCVTSD2SSZrmkz", "VCVTSD2SSZrrkz", - "VCVTSD2SSZrm_Int", "VCVTSD2SSZrr_Int", - "VCVTSD2SSZrm_Intk", "VCVTSD2SSZrr_Intk", - "VCVTSD2SSZrm_Intkz", "VCVTSD2SSZrr_Intkz", - "VRCP14SSrm", "VRCP14SSrr", - "VRCP14SDrm", "VRCP14SDrr", - "VRSQRT14SSrm", "VRSQRT14SSrr", - "VRSQRT14SDrm", "VRSQRT14SDrr", - "VSQRTSSm", "VSQRTSSr", - "VSQRTSSm_Int", "VSQRTSSr_Int", - "VSQRTSSZm", "VSQRTSSZr", - "VSQRTSSZm_Int", "VSQRTSSZr_Int", - "VSQRTSSZm_Intk", "VSQRTSSZr_Intk", - "VSQRTSSZm_Intkz", "VSQRTSSZr_Intkz", - "VSQRTSDm", "VSQRTSDr", - "VSQRTSDm_Int", "VSQRTSDr_Int", - "VSQRTSDZm", "VSQRTSDZr", - "VSQRTSDZm_Int", "VSQRTSDZr_Int", - "VSQRTSDZm_Intk", "VSQRTSDZr_Intk", - "VSQRTSDZm_Intkz", "VSQRTSDZr_Intkz", -}; - -static bool isExplicitAlign(const CodeGenInstruction *Inst) { - return any_of(ExplicitAlign, [Inst](const char *InstStr) { - return Inst->TheDef->getName().find(InstStr) != StringRef::npos; - }); -} - -static bool isExplicitUnalign(const CodeGenInstruction *Inst) { - return any_of(ExplicitUnalign, [Inst](const char *InstStr) { - return Inst->TheDef->getName().find(InstStr) != StringRef::npos; - }); -} - -class X86FoldTablesEmitter { - RecordKeeper &Records; - CodeGenTarget Target; - - // Represents an entry in the folding table - class X86FoldTableEntry { - const CodeGenInstruction *RegInst; - const CodeGenInstruction *MemInst; - - public: - bool CannotUnfold = false; - bool IsLoad = false; - bool IsStore = false; - bool IsAligned = false; - unsigned int Alignment = 0; - - X86FoldTableEntry(const CodeGenInstruction *RegInst, - const CodeGenInstruction *MemInst) - : RegInst(RegInst), MemInst(MemInst) {} - - friend raw_ostream &operator<<(raw_ostream &OS, - const X86FoldTableEntry &E) { - OS << "{ X86::" << E.RegInst->TheDef->getName() - << ", X86::" << E.MemInst->TheDef->getName() << ", "; - - if (E.IsLoad) - OS << "TB_FOLDED_LOAD | "; - if (E.IsStore) - OS << "TB_FOLDED_STORE | "; - if (E.CannotUnfold) - OS << "TB_NO_REVERSE | "; - if (E.IsAligned) - OS << "TB_ALIGN_" << E.Alignment << " | "; - - OS << "0 },\n"; - - return OS; - } - }; - - typedef std::vector FoldTable; - // std::vector for each folding table. - // Table2Addr - Holds instructions which their memory form performs load+store - // Table#i - Holds instructions which the their memory form perform a load OR - // a store, and their #i'th operand is folded. - FoldTable Table2Addr; - FoldTable Table0; - FoldTable Table1; - FoldTable Table2; - FoldTable Table3; - FoldTable Table4; - -public: - X86FoldTablesEmitter(RecordKeeper &R) : Records(R), Target(R) {} - - // run - Generate the 6 X86 memory fold tables. - void run(raw_ostream &OS); - -private: - // Decides to which table to add the entry with the given instructions. - // S sets the strategy of adding the TB_NO_REVERSE flag. - void updateTables(const CodeGenInstruction *RegInstr, - const CodeGenInstruction *MemInstr, - const UnfoldStrategy S = NO_STRATEGY); - - // Generates X86FoldTableEntry with the given instructions and fill it with - // the appropriate flags - then adds it to Table. - void addEntryWithFlags(FoldTable &Table, const CodeGenInstruction *RegInstr, - const CodeGenInstruction *MemInstr, - const UnfoldStrategy S, const unsigned int FoldedInd); - - // Print the given table as a static const C++ array of type - // X86MemoryFoldTableEntry. - void printTable(const FoldTable &Table, std::string TableName, - raw_ostream &OS) { - OS << "\nstatic const X86MemoryFoldTableEntry MemoryFold" << TableName - << "[] = {\n"; - - for (const X86FoldTableEntry &E : Table) - OS.indent(2) << E; - - OS << "};\n"; - } -}; - -// Return true if one of the instruction's operands is a RST register class -static bool hasRSTRegClass(const CodeGenInstruction *Inst) { - return any_of(Inst->Operands, [](const CGIOperandList::OperandInfo &OpIn) { - return OpIn.Rec->getName() == "RST"; - }); -} - -// Return true if one of the instruction's operands is a ptr_rc_tailcall -static bool hasPtrTailcallRegClass(const CodeGenInstruction *Inst) { - return any_of(Inst->Operands, [](const CGIOperandList::OperandInfo &OpIn) { - return OpIn.Rec->getName() == "ptr_rc_tailcall"; - }); -} - -// Calculates the integer value representing the BitsInit object -static inline uint64_t getValueFromBitsInit(const BitsInit *B) { - assert(B->getNumBits() <= sizeof(uint64_t) * CHAR_BIT && - "BitInits' too long!"); - - uint64_t Value = 0; - for (unsigned i = 0, e = B->getNumBits(); i != e; ++i) { - BitInit *Bit = cast(B->getBit(i)); - Value |= uint64_t(Bit->getValue()) << i; - } - return Value; -} - -// Returns true if the two given BitsInits represent the same integer value -static inline bool equalBitsInits(const BitsInit *B1, const BitsInit *B2) { - if (B1->getNumBits() != B2->getNumBits()) - PrintFatalError("Comparing two BitsInits with different sizes!"); - - for (unsigned i = 0, e = B1->getNumBits(); i != e; ++i) { - BitInit *Bit1 = cast(B1->getBit(i)); - BitInit *Bit2 = cast(B2->getBit(i)); - if (Bit1->getValue() != Bit2->getValue()) - return false; - } - return true; -} - -// Return the size of the register operand -static inline unsigned int getRegOperandSize(const Record *RegRec) { - if (RegRec->isSubClassOf("RegisterOperand")) - RegRec = RegRec->getValueAsDef("RegClass"); - if (RegRec->isSubClassOf("RegisterClass")) - return RegRec->getValueAsListOfDefs("RegTypes")[0]->getValueAsInt("Size"); - - llvm_unreachable("Register operand's size not known!"); -} - -// Return the size of the memory operand -static inline unsigned int -getMemOperandSize(const Record *MemRec, const bool IntrinsicSensitive = false) { - if (MemRec->isSubClassOf("Operand")) { - // Intrinsic memory instructions use ssmem/sdmem. - if (IntrinsicSensitive && - (MemRec->getName() == "sdmem" || MemRec->getName() == "ssmem")) - return 128; - - StringRef Name = - MemRec->getValueAsDef("ParserMatchClass")->getValueAsString("Name"); - if (Name == "Mem8") - return 8; - if (Name == "Mem16") - return 16; - if (Name == "Mem32") - return 32; - if (Name == "Mem64") - return 64; - if (Name == "Mem80") - return 80; - if (Name == "Mem128") - return 128; - if (Name == "Mem256") - return 256; - if (Name == "Mem512") - return 512; - } - - llvm_unreachable("Memory operand's size not known!"); -} - -// Returns true if the record's list of defs includes the given def. -static inline bool hasDefInList(const Record *Rec, const StringRef List, - const StringRef Def) { - if (!Rec->isValueUnset(List)) { - return any_of(*(Rec->getValueAsListInit(List)), - [Def](const Init *I) { return I->getAsString() == Def; }); - } - return false; -} - -// Return true if the instruction defined as a register flavor. -static inline bool hasRegisterFormat(const Record *Inst) { - const BitsInit *FormBits = Inst->getValueAsBitsInit("FormBits"); - uint64_t FormBitsNum = getValueFromBitsInit(FormBits); - - // Values from X86Local namespace defined in X86RecognizableInstr.cpp - return FormBitsNum >= X86Local::MRMDestReg && FormBitsNum <= X86Local::MRM7r; -} - -// Return true if the instruction defined as a memory flavor. -static inline bool hasMemoryFormat(const Record *Inst) { - const BitsInit *FormBits = Inst->getValueAsBitsInit("FormBits"); - uint64_t FormBitsNum = getValueFromBitsInit(FormBits); - - // Values from X86Local namespace defined in X86RecognizableInstr.cpp - return FormBitsNum >= X86Local::MRMDestMem && FormBitsNum <= X86Local::MRM7m; -} - -static inline bool isNOREXRegClass(const Record *Op) { - return Op->getName().find("_NOREX") != StringRef::npos; -} - -static inline bool isRegisterOperand(const Record *Rec) { - return Rec->isSubClassOf("RegisterClass") || - Rec->isSubClassOf("RegisterOperand") || - Rec->isSubClassOf("PointerLikeRegClass"); -} - -static inline bool isMemoryOperand(const Record *Rec) { - return Rec->isSubClassOf("Operand") && - Rec->getValueAsString("OperandType") == "OPERAND_MEMORY"; -} - -static inline bool isImmediateOperand(const Record *Rec) { - return Rec->isSubClassOf("Operand") && - Rec->getValueAsString("OperandType") == "OPERAND_IMMEDIATE"; -} - -// Get the alternative instruction pointed by "FoldGenRegForm" field. -static inline const CodeGenInstruction * -getAltRegInst(const CodeGenInstruction *I, const RecordKeeper &Records, - const CodeGenTarget &Target) { - - StringRef AltRegInstStr = I->TheDef->getValueAsString("FoldGenRegForm"); - Record *AltRegInstRec = Records.getDef(AltRegInstStr); - assert(AltRegInstRec && - "Alternative register form instruction def not found"); - CodeGenInstruction &AltRegInst = Target.getInstruction(AltRegInstRec); - return &AltRegInst; -} - -// Function object - Operator() returns true if the given VEX instruction -// matches the EVEX instruction of this object. -class IsMatch { - const CodeGenInstruction *MemInst; - const RecordKeeper &Records; - -public: - IsMatch(const CodeGenInstruction *Inst, const RecordKeeper &Records) - : MemInst(Inst), Records(Records) {} - - bool operator()(const CodeGenInstruction *RegInst) { - Record *MemRec = MemInst->TheDef; - Record *RegRec = RegInst->TheDef; - - // Return false if one (at least) of the encoding fields of both - // instructions do not match. - if (RegRec->getValueAsDef("OpEnc") != MemRec->getValueAsDef("OpEnc") || - !equalBitsInits(RegRec->getValueAsBitsInit("Opcode"), - MemRec->getValueAsBitsInit("Opcode")) || - // VEX/EVEX fields - RegRec->getValueAsDef("OpPrefix") != - MemRec->getValueAsDef("OpPrefix") || - RegRec->getValueAsDef("OpMap") != MemRec->getValueAsDef("OpMap") || - RegRec->getValueAsDef("OpSize") != MemRec->getValueAsDef("OpSize") || - RegRec->getValueAsBit("hasVEX_4V") != - MemRec->getValueAsBit("hasVEX_4V") || - RegRec->getValueAsBit("hasEVEX_K") != - MemRec->getValueAsBit("hasEVEX_K") || - RegRec->getValueAsBit("hasEVEX_Z") != - MemRec->getValueAsBit("hasEVEX_Z") || - RegRec->getValueAsBit("hasEVEX_B") != - MemRec->getValueAsBit("hasEVEX_B") || - RegRec->getValueAsBit("hasEVEX_RC") != - MemRec->getValueAsBit("hasEVEX_RC") || - RegRec->getValueAsBit("hasREX_WPrefix") != - MemRec->getValueAsBit("hasREX_WPrefix") || - RegRec->getValueAsBit("hasLockPrefix") != - MemRec->getValueAsBit("hasLockPrefix") || - !equalBitsInits(RegRec->getValueAsBitsInit("EVEX_LL"), - MemRec->getValueAsBitsInit("EVEX_LL")) || - !equalBitsInits(RegRec->getValueAsBitsInit("VEX_WPrefix"), - MemRec->getValueAsBitsInit("VEX_WPrefix")) || - // Instruction's format - The register form's "Form" field should be - // the opposite of the memory form's "Form" field. - !areOppositeForms(RegRec->getValueAsBitsInit("FormBits"), - MemRec->getValueAsBitsInit("FormBits")) || - RegRec->getValueAsBit("isAsmParserOnly") != - MemRec->getValueAsBit("isAsmParserOnly")) - return false; - - // Make sure the sizes of the operands of both instructions suit each other. - // This is needed for instructions with intrinsic version (_Int). - // Where the only difference is the size of the operands. - // For example: VUCOMISDZrm and Int_VUCOMISDrm - // Also for instructions that their EVEX version was upgraded to work with - // k-registers. For example VPCMPEQBrm (xmm output register) and - // VPCMPEQBZ128rm (k register output register). - bool ArgFolded = false; - unsigned MemOutSize = MemRec->getValueAsDag("OutOperandList")->getNumArgs(); - unsigned RegOutSize = RegRec->getValueAsDag("OutOperandList")->getNumArgs(); - unsigned MemInSize = MemRec->getValueAsDag("InOperandList")->getNumArgs(); - unsigned RegInSize = RegRec->getValueAsDag("InOperandList")->getNumArgs(); - - // Instructions with one output in their memory form use the memory folded - // operand as source and destination (Read-Modify-Write). - unsigned RegStartIdx = - (MemOutSize + 1 == RegOutSize) && (MemInSize == RegInSize) ? 1 : 0; - - for (unsigned i = 0, e = MemInst->Operands.size(); i < e; i++) { - Record *MemOpRec = MemInst->Operands[i].Rec; - Record *RegOpRec = RegInst->Operands[i + RegStartIdx].Rec; - - if (MemOpRec == RegOpRec) - continue; - - if (isRegisterOperand(MemOpRec) && isRegisterOperand(RegOpRec)) { - if (getRegOperandSize(MemOpRec) != getRegOperandSize(RegOpRec) || - isNOREXRegClass(MemOpRec) != isNOREXRegClass(RegOpRec)) - return false; - } else if (isMemoryOperand(MemOpRec) && isMemoryOperand(RegOpRec)) { - if (getMemOperandSize(MemOpRec) != getMemOperandSize(RegOpRec)) - return false; - } else if (isImmediateOperand(MemOpRec) && isImmediateOperand(RegOpRec)) { - if (MemOpRec->getValueAsDef("Type") != RegOpRec->getValueAsDef("Type")) - return false; - } else { - // Only one operand can be folded. - if (ArgFolded) - return false; - - assert(isRegisterOperand(RegOpRec) && isMemoryOperand(MemOpRec)); - ArgFolded = true; - } - } - - return true; - } - -private: - // Return true of the 2 given forms are the opposite of each other. - bool areOppositeForms(const BitsInit *RegFormBits, - const BitsInit *MemFormBits) { - uint64_t MemFormNum = getValueFromBitsInit(MemFormBits); - uint64_t RegFormNum = getValueFromBitsInit(RegFormBits); - - if ((MemFormNum == X86Local::MRM0m && RegFormNum == X86Local::MRM0r) || - (MemFormNum == X86Local::MRM1m && RegFormNum == X86Local::MRM1r) || - (MemFormNum == X86Local::MRM2m && RegFormNum == X86Local::MRM2r) || - (MemFormNum == X86Local::MRM3m && RegFormNum == X86Local::MRM3r) || - (MemFormNum == X86Local::MRM4m && RegFormNum == X86Local::MRM4r) || - (MemFormNum == X86Local::MRM5m && RegFormNum == X86Local::MRM5r) || - (MemFormNum == X86Local::MRM6m && RegFormNum == X86Local::MRM6r) || - (MemFormNum == X86Local::MRM7m && RegFormNum == X86Local::MRM7r) || - (MemFormNum == X86Local::MRMXm && RegFormNum == X86Local::MRMXr) || - (MemFormNum == X86Local::MRMDestMem && - RegFormNum == X86Local::MRMDestReg) || - (MemFormNum == X86Local::MRMSrcMem && - RegFormNum == X86Local::MRMSrcReg) || - (MemFormNum == X86Local::MRMSrcMem4VOp3 && - RegFormNum == X86Local::MRMSrcReg4VOp3) || - (MemFormNum == X86Local::MRMSrcMemOp4 && - RegFormNum == X86Local::MRMSrcRegOp4)) - return true; - - return false; - } -}; - -} // end anonymous namespace - -void X86FoldTablesEmitter::addEntryWithFlags(FoldTable &Table, - const CodeGenInstruction *RegInstr, - const CodeGenInstruction *MemInstr, - const UnfoldStrategy S, - const unsigned int FoldedInd) { - - X86FoldTableEntry Result = X86FoldTableEntry(RegInstr, MemInstr); - Record *RegRec = RegInstr->TheDef; - Record *MemRec = MemInstr->TheDef; - - // Only table0 entries should explicitly specify a load or store flag. - if (&Table == &Table0) { - unsigned MemInOpsNum = MemRec->getValueAsDag("InOperandList")->getNumArgs(); - unsigned RegInOpsNum = RegRec->getValueAsDag("InOperandList")->getNumArgs(); - // If the instruction writes to the folded operand, it will appear as an - // output in the register form instruction and as an input in the memory - // form instruction. - // If the instruction reads from the folded operand, it well appear as in - // input in both forms. - if (MemInOpsNum == RegInOpsNum) - Result.IsLoad = true; - else - Result.IsStore = true; - } - - Record *RegOpRec = RegInstr->Operands[FoldedInd].Rec; - Record *MemOpRec = MemInstr->Operands[FoldedInd].Rec; - - // Unfolding code generates a load/store instruction according to the size of - // the register in the register form instruction. - // If the register's size is greater than the memory's operand size, do not - // allow unfolding. - if (S == UNFOLD) - Result.CannotUnfold = false; - else if (S == NO_UNFOLD) - Result.CannotUnfold = true; - else if (getRegOperandSize(RegOpRec) > getMemOperandSize(MemOpRec)) - Result.CannotUnfold = true; // S == NO_STRATEGY - - uint64_t Enc = getValueFromBitsInit(RegRec->getValueAsBitsInit("OpEncBits")); - if (isExplicitAlign(RegInstr)) { - // The instruction require explicitly aligned memory. - BitsInit *VectSize = RegRec->getValueAsBitsInit("VectSize"); - uint64_t Value = getValueFromBitsInit(VectSize); - Result.IsAligned = true; - Result.Alignment = Value; - } else if (Enc != X86Local::XOP && Enc != X86Local::VEX && - Enc != X86Local::EVEX) { - // Instructions with VEX encoding do not require alignment. - if (!isExplicitUnalign(RegInstr) && getMemOperandSize(MemOpRec) > 64) { - // SSE packed vector instructions require a 16 byte alignment. - Result.IsAligned = true; - Result.Alignment = 16; - } - } - - Table.push_back(Result); -} - -void X86FoldTablesEmitter::updateTables(const CodeGenInstruction *RegInstr, - const CodeGenInstruction *MemInstr, - const UnfoldStrategy S) { - - Record *RegRec = RegInstr->TheDef; - Record *MemRec = MemInstr->TheDef; - unsigned MemOutSize = MemRec->getValueAsDag("OutOperandList")->getNumArgs(); - unsigned RegOutSize = RegRec->getValueAsDag("OutOperandList")->getNumArgs(); - unsigned MemInSize = MemRec->getValueAsDag("InOperandList")->getNumArgs(); - unsigned RegInSize = RegRec->getValueAsDag("InOperandList")->getNumArgs(); - - // Instructions which have the WriteRMW value (Read-Modify-Write) should be - // added to Table2Addr. - if (hasDefInList(MemRec, "SchedRW", "WriteRMW") && MemOutSize != RegOutSize && - MemInSize == RegInSize) { - addEntryWithFlags(Table2Addr, RegInstr, MemInstr, S, 0); - return; - } - - if (MemInSize == RegInSize && MemOutSize == RegOutSize) { - // Load-Folding cases. - // If the i'th register form operand is a register and the i'th memory form - // operand is a memory operand, add instructions to Table#i. - for (unsigned i = RegOutSize, e = RegInstr->Operands.size(); i < e; i++) { - Record *RegOpRec = RegInstr->Operands[i].Rec; - Record *MemOpRec = MemInstr->Operands[i].Rec; - if (isRegisterOperand(RegOpRec) && isMemoryOperand(MemOpRec)) { - switch (i) { - default: llvm_unreachable("Unexpected operand count!"); - case 0: - addEntryWithFlags(Table0, RegInstr, MemInstr, S, 0); - return; - case 1: - addEntryWithFlags(Table1, RegInstr, MemInstr, S, 1); - return; - case 2: - addEntryWithFlags(Table2, RegInstr, MemInstr, S, 2); - return; - case 3: - addEntryWithFlags(Table3, RegInstr, MemInstr, S, 3); - return; - case 4: - addEntryWithFlags(Table4, RegInstr, MemInstr, S, 4); - return; - } - } - } - } else if (MemInSize == RegInSize + 1 && MemOutSize + 1 == RegOutSize) { - // Store-Folding cases. - // If the memory form instruction performs performs a store, the *output* - // register of the register form instructions disappear and instead a - // memory *input* operand appears in the memory form instruction. - // For example: - // MOVAPSrr => (outs VR128:$dst), (ins VR128:$src) - // MOVAPSmr => (outs), (ins f128mem:$dst, VR128:$src) - Record *RegOpRec = RegInstr->Operands[RegOutSize - 1].Rec; - Record *MemOpRec = MemInstr->Operands[RegOutSize - 1].Rec; - if (isRegisterOperand(RegOpRec) && isMemoryOperand(MemOpRec)) - addEntryWithFlags(Table0, RegInstr, MemInstr, S, 0); - } - - return; -} - -void X86FoldTablesEmitter::run(raw_ostream &OS) { - emitSourceFileHeader("X86 fold tables", OS); - - // Holds all memory instructions - std::vector MemInsts; - // Holds all register instructions - divided according to opcode. - std::map> RegInsts; - - ArrayRef NumberedInstructions = - Target.getInstructionsByEnumValue(); - - for (const CodeGenInstruction *Inst : NumberedInstructions) { - if (!Inst->TheDef->getNameInit() || !Inst->TheDef->isSubClassOf("X86Inst")) - continue; - - const Record *Rec = Inst->TheDef; - - // - Do not proceed matching if the instruction in NoFoldSet. - // - Instructions including RST register class operands are not relevant - // for memory folding (for further details check the explanation in - // lib/Target/X86/X86InstrFPStack.td file). - // - Some instructions (listed in the manual map above) use the register - // class ptr_rc_tailcall, which can be of a size 32 or 64, to ensure - // safe mapping of these instruction we manually map them and exclude - // them from the automation. - if (find(NoFoldSet, Rec->getName()) != std::end(NoFoldSet) || - hasRSTRegClass(Inst) || hasPtrTailcallRegClass(Inst)) - continue; - - // Add all the memory form instructions to MemInsts, and all the register - // form instructions to RegInsts[Opc], where Opc in the opcode of each - // instructions. this helps reducing the runtime of the backend. - if (hasMemoryFormat(Rec)) - MemInsts.push_back(Inst); - else if (hasRegisterFormat(Rec)) { - uint8_t Opc = getValueFromBitsInit(Rec->getValueAsBitsInit("Opcode")); - RegInsts[Opc].push_back(Inst); - } - } - - // For each memory form instruction, try to find its register form - // instruction. - for (const CodeGenInstruction *MemInst : MemInsts) { - uint8_t Opc = - getValueFromBitsInit(MemInst->TheDef->getValueAsBitsInit("Opcode")); - - if (RegInsts.count(Opc) == 0) - continue; - - // Two forms (memory & register) of the same instruction must have the same - // opcode. try matching only with register form instructions with the same - // opcode. - std::vector &OpcRegInsts = - RegInsts.find(Opc)->second; - - auto Match = find_if(OpcRegInsts, IsMatch(MemInst, Records)); - if (Match != OpcRegInsts.end()) { - const CodeGenInstruction *RegInst = *Match; - // If the matched instruction has it's "FoldGenRegForm" set, map the - // memory form instruction to the register form instruction pointed by - // this field - if (RegInst->TheDef->isValueUnset("FoldGenRegForm")) { - updateTables(RegInst, MemInst); - } else { - const CodeGenInstruction *AltRegInst = - getAltRegInst(RegInst, Records, Target); - updateTables(AltRegInst, MemInst); - } - OpcRegInsts.erase(Match); - } - } - - // Add the manually mapped instructions listed above. - for (const ManualMapEntry &Entry : ManualMapSet) { - Record *RegInstIter = Records.getDef(Entry.RegInstStr); - Record *MemInstIter = Records.getDef(Entry.MemInstStr); - - updateTables(&(Target.getInstruction(RegInstIter)), - &(Target.getInstruction(MemInstIter)), Entry.Strategy); - } - - // Print all tables to raw_ostream OS. - printTable(Table2Addr, "Table2Addr", OS); - printTable(Table0, "Table0", OS); - printTable(Table1, "Table1", OS); - printTable(Table2, "Table2", OS); - printTable(Table3, "Table3", OS); - printTable(Table4, "Table4", OS); -} - -namespace llvm { - -void EmitX86FoldTables(RecordKeeper &RK, raw_ostream &OS) { - X86FoldTablesEmitter(RK).run(OS); -} -} // namespace llvm