-//===- X86InstrInfo.cpp - X86 Instruction Information -----------*- C++ -*-===//
+//===-- X86InstrInfo.cpp - X86 Instruction Information --------------------===//
//
// The LLVM Compiler Infrastructure
//
#include "X86InstrInfo.h"
#include "X86.h"
-#include "X86GenInstrInfo.inc"
#include "X86InstrBuilder.h"
#include "X86MachineFunctionInfo.h"
#include "X86Subtarget.h"
#include "llvm/LLVMContext.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/CodeGen/MachineConstantPool.h"
+#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/LiveVariables.h"
-#include "llvm/CodeGen/PseudoSourceValue.h"
+#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCInst.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetOptions.h"
-#include "llvm/MC/MCAsmInfo.h"
#include <limits>
+#define GET_INSTRINFO_CTOR
+#include "X86GenInstrInfo.inc"
+
using namespace llvm;
static cl::opt<bool>
cl::desc("Re-materialize load from stub in PIC mode"),
cl::init(false), cl::Hidden);
+enum {
+ // Select which memory operand is being unfolded.
+ // (stored in bits 0 - 3)
+ TB_INDEX_0 = 0,
+ TB_INDEX_1 = 1,
+ TB_INDEX_2 = 2,
+ TB_INDEX_3 = 3,
+ TB_INDEX_MASK = 0xf,
+
+ // Do not insert the reverse map (MemOp -> RegOp) into the table.
+ // This may be needed because there is a many -> one mapping.
+ TB_NO_REVERSE = 1 << 4,
+
+ // Do not insert the forward map (RegOp -> MemOp) into the table.
+ // This is needed for Native Client, which prohibits branch
+ // instructions from using a memory operand.
+ TB_NO_FORWARD = 1 << 5,
+
+ TB_FOLDED_LOAD = 1 << 6,
+ TB_FOLDED_STORE = 1 << 7,
+
+ // Minimum alignment required for load/store.
+ // Used for RegOp->MemOp conversion.
+ // (stored in bits 8 - 15)
+ TB_ALIGN_SHIFT = 8,
+ TB_ALIGN_NONE = 0 << TB_ALIGN_SHIFT,
+ TB_ALIGN_16 = 16 << TB_ALIGN_SHIFT,
+ TB_ALIGN_32 = 32 << TB_ALIGN_SHIFT,
+ TB_ALIGN_MASK = 0xff << TB_ALIGN_SHIFT
+};
+
+struct X86OpTblEntry {
+ uint16_t RegOp;
+ uint16_t MemOp;
+ uint16_t Flags;
+};
+
X86InstrInfo::X86InstrInfo(X86TargetMachine &tm)
- : TargetInstrInfoImpl(X86Insts, array_lengthof(X86Insts)),
+ : X86GenInstrInfo((tm.getSubtarget<X86Subtarget>().is64Bit()
+ ? X86::ADJCALLSTACKDOWN64
+ : X86::ADJCALLSTACKDOWN32),
+ (tm.getSubtarget<X86Subtarget>().is64Bit()
+ ? X86::ADJCALLSTACKUP64
+ : X86::ADJCALLSTACKUP32)),
TM(tm), RI(tm, *this) {
- enum {
- TB_NOT_REVERSABLE = 1U << 31,
- TB_FLAGS = TB_NOT_REVERSABLE
- };
-
- static const unsigned OpTbl2Addr[][2] = {
- { X86::ADC32ri, X86::ADC32mi },
- { X86::ADC32ri8, X86::ADC32mi8 },
- { X86::ADC32rr, X86::ADC32mr },
- { X86::ADC64ri32, X86::ADC64mi32 },
- { X86::ADC64ri8, X86::ADC64mi8 },
- { X86::ADC64rr, X86::ADC64mr },
- { X86::ADD16ri, X86::ADD16mi },
- { X86::ADD16ri8, X86::ADD16mi8 },
- { X86::ADD16ri_DB, X86::ADD16mi | TB_NOT_REVERSABLE },
- { X86::ADD16ri8_DB, X86::ADD16mi8 | TB_NOT_REVERSABLE },
- { X86::ADD16rr, X86::ADD16mr },
- { X86::ADD16rr_DB, X86::ADD16mr | TB_NOT_REVERSABLE },
- { X86::ADD32ri, X86::ADD32mi },
- { X86::ADD32ri8, X86::ADD32mi8 },
- { X86::ADD32ri_DB, X86::ADD32mi | TB_NOT_REVERSABLE },
- { X86::ADD32ri8_DB, X86::ADD32mi8 | TB_NOT_REVERSABLE },
- { X86::ADD32rr, X86::ADD32mr },
- { X86::ADD32rr_DB, X86::ADD32mr | TB_NOT_REVERSABLE },
- { X86::ADD64ri32, X86::ADD64mi32 },
- { X86::ADD64ri8, X86::ADD64mi8 },
- { X86::ADD64ri32_DB,X86::ADD64mi32 | TB_NOT_REVERSABLE },
- { X86::ADD64ri8_DB, X86::ADD64mi8 | TB_NOT_REVERSABLE },
- { X86::ADD64rr, X86::ADD64mr },
- { X86::ADD64rr_DB, X86::ADD64mr | TB_NOT_REVERSABLE },
- { X86::ADD8ri, X86::ADD8mi },
- { X86::ADD8rr, X86::ADD8mr },
- { X86::AND16ri, X86::AND16mi },
- { X86::AND16ri8, X86::AND16mi8 },
- { X86::AND16rr, X86::AND16mr },
- { X86::AND32ri, X86::AND32mi },
- { X86::AND32ri8, X86::AND32mi8 },
- { X86::AND32rr, X86::AND32mr },
- { X86::AND64ri32, X86::AND64mi32 },
- { X86::AND64ri8, X86::AND64mi8 },
- { X86::AND64rr, X86::AND64mr },
- { X86::AND8ri, X86::AND8mi },
- { X86::AND8rr, X86::AND8mr },
- { X86::DEC16r, X86::DEC16m },
- { X86::DEC32r, X86::DEC32m },
- { X86::DEC64_16r, X86::DEC64_16m },
- { X86::DEC64_32r, X86::DEC64_32m },
- { X86::DEC64r, X86::DEC64m },
- { X86::DEC8r, X86::DEC8m },
- { X86::INC16r, X86::INC16m },
- { X86::INC32r, X86::INC32m },
- { X86::INC64_16r, X86::INC64_16m },
- { X86::INC64_32r, X86::INC64_32m },
- { X86::INC64r, X86::INC64m },
- { X86::INC8r, X86::INC8m },
- { X86::NEG16r, X86::NEG16m },
- { X86::NEG32r, X86::NEG32m },
- { X86::NEG64r, X86::NEG64m },
- { X86::NEG8r, X86::NEG8m },
- { X86::NOT16r, X86::NOT16m },
- { X86::NOT32r, X86::NOT32m },
- { X86::NOT64r, X86::NOT64m },
- { X86::NOT8r, X86::NOT8m },
- { X86::OR16ri, X86::OR16mi },
- { X86::OR16ri8, X86::OR16mi8 },
- { X86::OR16rr, X86::OR16mr },
- { X86::OR32ri, X86::OR32mi },
- { X86::OR32ri8, X86::OR32mi8 },
- { X86::OR32rr, X86::OR32mr },
- { X86::OR64ri32, X86::OR64mi32 },
- { X86::OR64ri8, X86::OR64mi8 },
- { X86::OR64rr, X86::OR64mr },
- { X86::OR8ri, X86::OR8mi },
- { X86::OR8rr, X86::OR8mr },
- { X86::ROL16r1, X86::ROL16m1 },
- { X86::ROL16rCL, X86::ROL16mCL },
- { X86::ROL16ri, X86::ROL16mi },
- { X86::ROL32r1, X86::ROL32m1 },
- { X86::ROL32rCL, X86::ROL32mCL },
- { X86::ROL32ri, X86::ROL32mi },
- { X86::ROL64r1, X86::ROL64m1 },
- { X86::ROL64rCL, X86::ROL64mCL },
- { X86::ROL64ri, X86::ROL64mi },
- { X86::ROL8r1, X86::ROL8m1 },
- { X86::ROL8rCL, X86::ROL8mCL },
- { X86::ROL8ri, X86::ROL8mi },
- { X86::ROR16r1, X86::ROR16m1 },
- { X86::ROR16rCL, X86::ROR16mCL },
- { X86::ROR16ri, X86::ROR16mi },
- { X86::ROR32r1, X86::ROR32m1 },
- { X86::ROR32rCL, X86::ROR32mCL },
- { X86::ROR32ri, X86::ROR32mi },
- { X86::ROR64r1, X86::ROR64m1 },
- { X86::ROR64rCL, X86::ROR64mCL },
- { X86::ROR64ri, X86::ROR64mi },
- { X86::ROR8r1, X86::ROR8m1 },
- { X86::ROR8rCL, X86::ROR8mCL },
- { X86::ROR8ri, X86::ROR8mi },
- { X86::SAR16r1, X86::SAR16m1 },
- { X86::SAR16rCL, X86::SAR16mCL },
- { X86::SAR16ri, X86::SAR16mi },
- { X86::SAR32r1, X86::SAR32m1 },
- { X86::SAR32rCL, X86::SAR32mCL },
- { X86::SAR32ri, X86::SAR32mi },
- { X86::SAR64r1, X86::SAR64m1 },
- { X86::SAR64rCL, X86::SAR64mCL },
- { X86::SAR64ri, X86::SAR64mi },
- { X86::SAR8r1, X86::SAR8m1 },
- { X86::SAR8rCL, X86::SAR8mCL },
- { X86::SAR8ri, X86::SAR8mi },
- { X86::SBB32ri, X86::SBB32mi },
- { X86::SBB32ri8, X86::SBB32mi8 },
- { X86::SBB32rr, X86::SBB32mr },
- { X86::SBB64ri32, X86::SBB64mi32 },
- { X86::SBB64ri8, X86::SBB64mi8 },
- { X86::SBB64rr, X86::SBB64mr },
- { X86::SHL16rCL, X86::SHL16mCL },
- { X86::SHL16ri, X86::SHL16mi },
- { X86::SHL32rCL, X86::SHL32mCL },
- { X86::SHL32ri, X86::SHL32mi },
- { X86::SHL64rCL, X86::SHL64mCL },
- { X86::SHL64ri, X86::SHL64mi },
- { X86::SHL8rCL, X86::SHL8mCL },
- { X86::SHL8ri, X86::SHL8mi },
- { X86::SHLD16rrCL, X86::SHLD16mrCL },
- { X86::SHLD16rri8, X86::SHLD16mri8 },
- { X86::SHLD32rrCL, X86::SHLD32mrCL },
- { X86::SHLD32rri8, X86::SHLD32mri8 },
- { X86::SHLD64rrCL, X86::SHLD64mrCL },
- { X86::SHLD64rri8, X86::SHLD64mri8 },
- { X86::SHR16r1, X86::SHR16m1 },
- { X86::SHR16rCL, X86::SHR16mCL },
- { X86::SHR16ri, X86::SHR16mi },
- { X86::SHR32r1, X86::SHR32m1 },
- { X86::SHR32rCL, X86::SHR32mCL },
- { X86::SHR32ri, X86::SHR32mi },
- { X86::SHR64r1, X86::SHR64m1 },
- { X86::SHR64rCL, X86::SHR64mCL },
- { X86::SHR64ri, X86::SHR64mi },
- { X86::SHR8r1, X86::SHR8m1 },
- { X86::SHR8rCL, X86::SHR8mCL },
- { X86::SHR8ri, X86::SHR8mi },
- { X86::SHRD16rrCL, X86::SHRD16mrCL },
- { X86::SHRD16rri8, X86::SHRD16mri8 },
- { X86::SHRD32rrCL, X86::SHRD32mrCL },
- { X86::SHRD32rri8, X86::SHRD32mri8 },
- { X86::SHRD64rrCL, X86::SHRD64mrCL },
- { X86::SHRD64rri8, X86::SHRD64mri8 },
- { X86::SUB16ri, X86::SUB16mi },
- { X86::SUB16ri8, X86::SUB16mi8 },
- { X86::SUB16rr, X86::SUB16mr },
- { X86::SUB32ri, X86::SUB32mi },
- { X86::SUB32ri8, X86::SUB32mi8 },
- { X86::SUB32rr, X86::SUB32mr },
- { X86::SUB64ri32, X86::SUB64mi32 },
- { X86::SUB64ri8, X86::SUB64mi8 },
- { X86::SUB64rr, X86::SUB64mr },
- { X86::SUB8ri, X86::SUB8mi },
- { X86::SUB8rr, X86::SUB8mr },
- { X86::XOR16ri, X86::XOR16mi },
- { X86::XOR16ri8, X86::XOR16mi8 },
- { X86::XOR16rr, X86::XOR16mr },
- { X86::XOR32ri, X86::XOR32mi },
- { X86::XOR32ri8, X86::XOR32mi8 },
- { X86::XOR32rr, X86::XOR32mr },
- { X86::XOR64ri32, X86::XOR64mi32 },
- { X86::XOR64ri8, X86::XOR64mi8 },
- { X86::XOR64rr, X86::XOR64mr },
- { X86::XOR8ri, X86::XOR8mi },
- { X86::XOR8rr, X86::XOR8mr }
+
+ static const X86OpTblEntry OpTbl2Addr[] = {
+ { 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::DEC64_16r, X86::DEC64_16m, 0 },
+ { X86::DEC64_32r, X86::DEC64_32m, 0 },
+ { X86::DEC64r, X86::DEC64m, 0 },
+ { X86::DEC8r, X86::DEC8m, 0 },
+ { X86::INC16r, X86::INC16m, 0 },
+ { X86::INC32r, X86::INC32m, 0 },
+ { X86::INC64_16r, X86::INC64_16m, 0 },
+ { X86::INC64_32r, X86::INC64_32m, 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::SHL16rCL, X86::SHL16mCL, 0 },
+ { X86::SHL16ri, X86::SHL16mi, 0 },
+ { X86::SHL32rCL, X86::SHL32mCL, 0 },
+ { X86::SHL32ri, X86::SHL32mi, 0 },
+ { X86::SHL64rCL, X86::SHL64mCL, 0 },
+ { X86::SHL64ri, X86::SHL64mi, 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 (unsigned i = 0, e = array_lengthof(OpTbl2Addr); i != e; ++i) {
- unsigned RegOp = OpTbl2Addr[i][0];
- unsigned MemOp = OpTbl2Addr[i][1] & ~TB_FLAGS;
- assert(!RegOp2MemOpTable2Addr.count(RegOp) && "Duplicated entries?");
- RegOp2MemOpTable2Addr[RegOp] = std::make_pair(MemOp, 0U);
-
- // If this is not a reversable operation (because there is a many->one)
- // mapping, don't insert the reverse of the operation into MemOp2RegOpTable.
- if (OpTbl2Addr[i][1] & TB_NOT_REVERSABLE)
- continue;
-
- // Index 0, folded load and store, no alignment requirement.
- unsigned AuxInfo = 0 | (1 << 4) | (1 << 5);
-
- assert(!MemOp2RegOpTable.count(MemOp) &&
- "Duplicated entries in unfolding maps?");
- MemOp2RegOpTable[MemOp] = std::make_pair(RegOp, AuxInfo);
- }
-
- // If the third value is 1, then it's folding either a load or a store.
- static const unsigned OpTbl0[][4] = {
- { X86::BT16ri8, X86::BT16mi8, 1, 0 },
- { X86::BT32ri8, X86::BT32mi8, 1, 0 },
- { X86::BT64ri8, X86::BT64mi8, 1, 0 },
- { X86::CALL32r, X86::CALL32m, 1, 0 },
- { X86::CALL64r, X86::CALL64m, 1, 0 },
- { X86::WINCALL64r, X86::WINCALL64m, 1, 0 },
- { X86::CMP16ri, X86::CMP16mi, 1, 0 },
- { X86::CMP16ri8, X86::CMP16mi8, 1, 0 },
- { X86::CMP16rr, X86::CMP16mr, 1, 0 },
- { X86::CMP32ri, X86::CMP32mi, 1, 0 },
- { X86::CMP32ri8, X86::CMP32mi8, 1, 0 },
- { X86::CMP32rr, X86::CMP32mr, 1, 0 },
- { X86::CMP64ri32, X86::CMP64mi32, 1, 0 },
- { X86::CMP64ri8, X86::CMP64mi8, 1, 0 },
- { X86::CMP64rr, X86::CMP64mr, 1, 0 },
- { X86::CMP8ri, X86::CMP8mi, 1, 0 },
- { X86::CMP8rr, X86::CMP8mr, 1, 0 },
- { X86::DIV16r, X86::DIV16m, 1, 0 },
- { X86::DIV32r, X86::DIV32m, 1, 0 },
- { X86::DIV64r, X86::DIV64m, 1, 0 },
- { X86::DIV8r, X86::DIV8m, 1, 0 },
- { X86::EXTRACTPSrr, X86::EXTRACTPSmr, 0, 16 },
- { X86::FsMOVAPDrr, X86::MOVSDmr | TB_NOT_REVERSABLE , 0, 0 },
- { X86::FsMOVAPSrr, X86::MOVSSmr | TB_NOT_REVERSABLE , 0, 0 },
- { X86::IDIV16r, X86::IDIV16m, 1, 0 },
- { X86::IDIV32r, X86::IDIV32m, 1, 0 },
- { X86::IDIV64r, X86::IDIV64m, 1, 0 },
- { X86::IDIV8r, X86::IDIV8m, 1, 0 },
- { X86::IMUL16r, X86::IMUL16m, 1, 0 },
- { X86::IMUL32r, X86::IMUL32m, 1, 0 },
- { X86::IMUL64r, X86::IMUL64m, 1, 0 },
- { X86::IMUL8r, X86::IMUL8m, 1, 0 },
- { X86::JMP32r, X86::JMP32m, 1, 0 },
- { X86::JMP64r, X86::JMP64m, 1, 0 },
- { X86::MOV16ri, X86::MOV16mi, 0, 0 },
- { X86::MOV16rr, X86::MOV16mr, 0, 0 },
- { X86::MOV32ri, X86::MOV32mi, 0, 0 },
- { X86::MOV32rr, X86::MOV32mr, 0, 0 },
- { X86::MOV64ri32, X86::MOV64mi32, 0, 0 },
- { X86::MOV64rr, X86::MOV64mr, 0, 0 },
- { X86::MOV8ri, X86::MOV8mi, 0, 0 },
- { X86::MOV8rr, X86::MOV8mr, 0, 0 },
- { X86::MOV8rr_NOREX, X86::MOV8mr_NOREX, 0, 0 },
- { X86::MOVAPDrr, X86::MOVAPDmr, 0, 16 },
- { X86::MOVAPSrr, X86::MOVAPSmr, 0, 16 },
- { X86::MOVDQArr, X86::MOVDQAmr, 0, 16 },
- { X86::MOVPDI2DIrr, X86::MOVPDI2DImr, 0, 0 },
- { X86::MOVPQIto64rr,X86::MOVPQI2QImr, 0, 0 },
- { X86::MOVSDto64rr, X86::MOVSDto64mr, 0, 0 },
- { X86::MOVSS2DIrr, X86::MOVSS2DImr, 0, 0 },
- { X86::MOVUPDrr, X86::MOVUPDmr, 0, 0 },
- { X86::MOVUPSrr, X86::MOVUPSmr, 0, 0 },
- { X86::MUL16r, X86::MUL16m, 1, 0 },
- { X86::MUL32r, X86::MUL32m, 1, 0 },
- { X86::MUL64r, X86::MUL64m, 1, 0 },
- { X86::MUL8r, X86::MUL8m, 1, 0 },
- { X86::SETAEr, X86::SETAEm, 0, 0 },
- { X86::SETAr, X86::SETAm, 0, 0 },
- { X86::SETBEr, X86::SETBEm, 0, 0 },
- { X86::SETBr, X86::SETBm, 0, 0 },
- { X86::SETEr, X86::SETEm, 0, 0 },
- { X86::SETGEr, X86::SETGEm, 0, 0 },
- { X86::SETGr, X86::SETGm, 0, 0 },
- { X86::SETLEr, X86::SETLEm, 0, 0 },
- { X86::SETLr, X86::SETLm, 0, 0 },
- { X86::SETNEr, X86::SETNEm, 0, 0 },
- { X86::SETNOr, X86::SETNOm, 0, 0 },
- { X86::SETNPr, X86::SETNPm, 0, 0 },
- { X86::SETNSr, X86::SETNSm, 0, 0 },
- { X86::SETOr, X86::SETOm, 0, 0 },
- { X86::SETPr, X86::SETPm, 0, 0 },
- { X86::SETSr, X86::SETSm, 0, 0 },
- { X86::TAILJMPr, X86::TAILJMPm, 1, 0 },
- { X86::TAILJMPr64, X86::TAILJMPm64, 1, 0 },
- { X86::TEST16ri, X86::TEST16mi, 1, 0 },
- { X86::TEST32ri, X86::TEST32mi, 1, 0 },
- { X86::TEST64ri32, X86::TEST64mi32, 1, 0 },
- { X86::TEST8ri, X86::TEST8mi, 1, 0 }
+ unsigned RegOp = OpTbl2Addr[i].RegOp;
+ unsigned MemOp = OpTbl2Addr[i].MemOp;
+ unsigned Flags = OpTbl2Addr[i].Flags;
+ AddTableEntry(RegOp2MemOpTable2Addr, MemOp2RegOpTable,
+ RegOp, MemOp,
+ // Index 0, folded load and store, no alignment requirement.
+ Flags | TB_INDEX_0 | TB_FOLDED_LOAD | TB_FOLDED_STORE);
+ }
+
+ static const X86OpTblEntry OpTbl0[] = {
+ { 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 | TB_ALIGN_16 },
+ { X86::FsMOVAPDrr, X86::MOVSDmr, TB_FOLDED_STORE | TB_NO_REVERSE },
+ { X86::FsMOVAPSrr, X86::MOVSSmr, TB_FOLDED_STORE | TB_NO_REVERSE },
+ { 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::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::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::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 | TB_ALIGN_16 },
+ { X86::FsVMOVAPDrr, X86::VMOVSDmr, TB_FOLDED_STORE | TB_NO_REVERSE },
+ { X86::FsVMOVAPSrr, X86::VMOVSSmr, TB_FOLDED_STORE | TB_NO_REVERSE },
+ { 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::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 },
+ // 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::VMOVUPDYrr, X86::VMOVUPDYmr, TB_FOLDED_STORE },
+ { X86::VMOVUPSYrr, X86::VMOVUPSYmr, TB_FOLDED_STORE }
};
for (unsigned i = 0, e = array_lengthof(OpTbl0); i != e; ++i) {
- unsigned RegOp = OpTbl0[i][0];
- unsigned MemOp = OpTbl0[i][1] & ~TB_FLAGS;
- unsigned FoldedLoad = OpTbl0[i][2];
- unsigned Align = OpTbl0[i][3];
- assert(!RegOp2MemOpTable0.count(RegOp) && "Duplicated entries?");
- RegOp2MemOpTable0[RegOp] = std::make_pair(MemOp, Align);
-
- // If this is not a reversable operation (because there is a many->one)
- // mapping, don't insert the reverse of the operation into MemOp2RegOpTable.
- if (OpTbl0[i][1] & TB_NOT_REVERSABLE)
- continue;
-
- // Index 0, folded load or store.
- unsigned AuxInfo = 0 | (FoldedLoad << 4) | ((FoldedLoad^1) << 5);
- assert(!MemOp2RegOpTable.count(MemOp) && "Duplicated entries?");
- MemOp2RegOpTable[MemOp] = std::make_pair(RegOp, AuxInfo);
- }
-
- static const unsigned OpTbl1[][3] = {
- { 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::FsMOVAPDrr, X86::MOVSDrm | TB_NOT_REVERSABLE , 0 },
- { X86::FsMOVAPSrr, X86::MOVSSrm | TB_NOT_REVERSABLE , 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_CMPSDrr, X86::Int_CMPSDrm, 0 },
- { X86::Int_CMPSSrr, X86::Int_CMPSSrm, 0 },
- { X86::Int_COMISDrr, X86::Int_COMISDrm, 0 },
- { X86::Int_COMISSrr, X86::Int_COMISSrm, 0 },
- { X86::Int_CVTDQ2PDrr, X86::Int_CVTDQ2PDrm, 16 },
- { X86::Int_CVTDQ2PSrr, X86::Int_CVTDQ2PSrm, 16 },
- { X86::Int_CVTPD2DQrr, X86::Int_CVTPD2DQrm, 16 },
- { X86::Int_CVTPD2PSrr, X86::Int_CVTPD2PSrm, 16 },
- { X86::Int_CVTPS2DQrr, X86::Int_CVTPS2DQrm, 16 },
- { X86::Int_CVTPS2PDrr, X86::Int_CVTPS2PDrm, 0 },
- { X86::CVTSD2SI64rr, X86::CVTSD2SI64rm, 0 },
- { X86::CVTSD2SIrr, X86::CVTSD2SIrm, 0 },
- { X86::Int_CVTSD2SSrr, X86::Int_CVTSD2SSrm, 0 },
- { 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, 0 },
- { X86::Int_CVTSS2SI64rr,X86::Int_CVTSS2SI64rm, 0 },
- { X86::Int_CVTSS2SIrr, X86::Int_CVTSS2SIrm, 0 },
- { X86::CVTTPD2DQrr, X86::CVTTPD2DQrm, 16 },
- { X86::CVTTPS2DQrr, X86::CVTTPS2DQrm, 16 },
- { X86::Int_CVTTSD2SI64rr,X86::Int_CVTTSD2SI64rm, 0 },
- { X86::Int_CVTTSD2SIrr, X86::Int_CVTTSD2SIrm, 0 },
- { X86::Int_CVTTSS2SI64rr,X86::Int_CVTTSS2SI64rm, 0 },
- { X86::Int_CVTTSS2SIrr, X86::Int_CVTTSS2SIrm, 0 },
- { X86::Int_UCOMISDrr, X86::Int_UCOMISDrm, 0 },
- { X86::Int_UCOMISSrr, X86::Int_UCOMISSrm, 0 },
- { 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, 16 },
- { X86::MOVAPSrr, X86::MOVAPSrm, 16 },
- { X86::MOVDDUPrr, X86::MOVDDUPrm, 0 },
- { X86::MOVDI2PDIrr, X86::MOVDI2PDIrm, 0 },
- { X86::MOVDI2SSrr, X86::MOVDI2SSrm, 0 },
- { X86::MOVDQArr, X86::MOVDQArm, 16 },
- { X86::MOVSHDUPrr, X86::MOVSHDUPrm, 16 },
- { X86::MOVSLDUPrr, X86::MOVSLDUPrm, 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, 16 },
- { X86::MOVUPSrr, X86::MOVUPSrm, 0 },
- { X86::MOVZDI2PDIrr, X86::MOVZDI2PDIrm, 0 },
- { X86::MOVZQI2PQIrr, X86::MOVZQI2PQIrm, 0 },
- { X86::MOVZPQILo2PQIrr, X86::MOVZPQILo2PQIrm, 16 },
- { X86::MOVZX16rr8, X86::MOVZX16rm8, 0 },
- { X86::MOVZX32rr16, X86::MOVZX32rm16, 0 },
- { X86::MOVZX32_NOREXrr8, X86::MOVZX32_NOREXrm8, 0 },
- { X86::MOVZX32rr8, X86::MOVZX32rm8, 0 },
- { X86::MOVZX64rr16, X86::MOVZX64rm16, 0 },
- { X86::MOVZX64rr32, X86::MOVZX64rm32, 0 },
- { X86::MOVZX64rr8, X86::MOVZX64rm8, 0 },
- { X86::PSHUFDri, X86::PSHUFDmi, 16 },
- { X86::PSHUFHWri, X86::PSHUFHWmi, 16 },
- { X86::PSHUFLWri, X86::PSHUFLWmi, 16 },
- { X86::RCPPSr, X86::RCPPSm, 16 },
- { X86::RCPPSr_Int, X86::RCPPSm_Int, 16 },
- { X86::RSQRTPSr, X86::RSQRTPSm, 16 },
- { X86::RSQRTPSr_Int, X86::RSQRTPSm_Int, 16 },
- { X86::RSQRTSSr, X86::RSQRTSSm, 0 },
- { X86::RSQRTSSr_Int, X86::RSQRTSSm_Int, 0 },
- { X86::SQRTPDr, X86::SQRTPDm, 16 },
- { X86::SQRTPDr_Int, X86::SQRTPDm_Int, 16 },
- { X86::SQRTPSr, X86::SQRTPSm, 16 },
- { X86::SQRTPSr_Int, X86::SQRTPSm_Int, 16 },
- { X86::SQRTSDr, X86::SQRTSDm, 0 },
- { X86::SQRTSDr_Int, X86::SQRTSDm_Int, 0 },
- { X86::SQRTSSr, X86::SQRTSSm, 0 },
- { X86::SQRTSSr_Int, X86::SQRTSSm_Int, 0 },
- { X86::TEST16rr, X86::TEST16rm, 0 },
- { X86::TEST32rr, X86::TEST32rm, 0 },
- { X86::TEST64rr, X86::TEST64rm, 0 },
- { X86::TEST8rr, X86::TEST8rm, 0 },
+ unsigned RegOp = OpTbl0[i].RegOp;
+ unsigned MemOp = OpTbl0[i].MemOp;
+ unsigned Flags = OpTbl0[i].Flags;
+ AddTableEntry(RegOp2MemOpTable0, MemOp2RegOpTable,
+ RegOp, MemOp, TB_INDEX_0 | Flags);
+ }
+
+ static const X86OpTblEntry OpTbl1[] = {
+ { 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::FsMOVAPDrr, X86::MOVSDrm, TB_NO_REVERSE },
+ { X86::FsMOVAPSrr, X86::MOVSSrm, TB_NO_REVERSE },
+ { 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, 0 },
+ { X86::Int_COMISSrr, X86::Int_COMISSrm, 0 },
+ { X86::CVTSD2SI64rr, X86::CVTSD2SI64rm, 0 },
+ { X86::CVTSD2SIrr, X86::CVTSD2SIrm, 0 },
+ { X86::CVTSS2SI64rr, X86::CVTSS2SI64rm, 0 },
+ { X86::CVTSS2SIrr, X86::CVTSS2SIrm, 0 },
+ { X86::Int_CVTSD2SSrr, X86::Int_CVTSD2SSrm, 0 },
+ { 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, 0 },
+ { X86::CVTTPD2DQrr, X86::CVTTPD2DQrm, TB_ALIGN_16 },
+ { X86::CVTTPS2DQrr, X86::CVTTPS2DQrm, TB_ALIGN_16 },
+ { X86::Int_CVTTSD2SI64rr,X86::Int_CVTTSD2SI64rm, 0 },
+ { X86::Int_CVTTSD2SIrr, X86::Int_CVTTSD2SIrm, 0 },
+ { X86::Int_CVTTSS2SI64rr,X86::Int_CVTTSS2SI64rm, 0 },
+ { X86::Int_CVTTSS2SIrr, X86::Int_CVTTSS2SIrm, 0 },
+ { X86::Int_UCOMISDrr, X86::Int_UCOMISDrm, 0 },
+ { X86::Int_UCOMISSrr, X86::Int_UCOMISSrm, 0 },
+ { 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, 0 },
+ { X86::MOVDI2PDIrr, X86::MOVDI2PDIrm, 0 },
+ { X86::MOVDI2SSrr, X86::MOVDI2SSrm, 0 },
+ { X86::MOVDQArr, X86::MOVDQArm, TB_ALIGN_16 },
+ { 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, TB_ALIGN_16 },
+ { X86::MOVUPSrr, X86::MOVUPSrm, 0 },
+ { X86::MOVZDI2PDIrr, X86::MOVZDI2PDIrm, 0 },
+ { X86::MOVZQI2PQIrr, X86::MOVZQI2PQIrm, 0 },
+ { X86::MOVZPQILo2PQIrr, X86::MOVZPQILo2PQIrm, TB_ALIGN_16 },
+ { X86::MOVZX16rr8, X86::MOVZX16rm8, 0 },
+ { X86::MOVZX32rr16, X86::MOVZX32rm16, 0 },
+ { X86::MOVZX32_NOREXrr8, X86::MOVZX32_NOREXrm8, 0 },
+ { X86::MOVZX32rr8, X86::MOVZX32rm8, 0 },
+ { X86::MOVZX64rr16, X86::MOVZX64rm16, 0 },
+ { X86::MOVZX64rr32, X86::MOVZX64rm32, 0 },
+ { X86::MOVZX64rr8, X86::MOVZX64rm8, 0 },
+ { X86::PABSBrr128, X86::PABSBrm128, TB_ALIGN_16 },
+ { X86::PABSDrr128, X86::PABSDrm128, TB_ALIGN_16 },
+ { X86::PABSWrr128, X86::PABSWrm128, TB_ALIGN_16 },
+ { X86::PSHUFDri, X86::PSHUFDmi, TB_ALIGN_16 },
+ { X86::PSHUFHWri, X86::PSHUFHWmi, TB_ALIGN_16 },
+ { X86::PSHUFLWri, X86::PSHUFLWmi, TB_ALIGN_16 },
+ { X86::RCPPSr, X86::RCPPSm, TB_ALIGN_16 },
+ { X86::RCPPSr_Int, X86::RCPPSm_Int, TB_ALIGN_16 },
+ { X86::RSQRTPSr, X86::RSQRTPSm, TB_ALIGN_16 },
+ { X86::RSQRTPSr_Int, X86::RSQRTPSm_Int, TB_ALIGN_16 },
+ { X86::RSQRTSSr, X86::RSQRTSSm, 0 },
+ { X86::RSQRTSSr_Int, X86::RSQRTSSm_Int, 0 },
+ { X86::SQRTPDr, X86::SQRTPDm, TB_ALIGN_16 },
+ { X86::SQRTPDr_Int, X86::SQRTPDm_Int, TB_ALIGN_16 },
+ { X86::SQRTPSr, X86::SQRTPSm, TB_ALIGN_16 },
+ { X86::SQRTPSr_Int, X86::SQRTPSm_Int, TB_ALIGN_16 },
+ { X86::SQRTSDr, X86::SQRTSDm, 0 },
+ { X86::SQRTSDr_Int, X86::SQRTSDm_Int, 0 },
+ { X86::SQRTSSr, X86::SQRTSSm, 0 },
+ { X86::SQRTSSr_Int, X86::SQRTSSm_Int, 0 },
+ { 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 }
+ { X86::UCOMISDrr, X86::UCOMISDrm, 0 },
+ { X86::UCOMISSrr, X86::UCOMISSrm, 0 },
+ // AVX 128-bit versions of foldable instructions
+ { X86::Int_VCOMISDrr, X86::Int_VCOMISDrm, 0 },
+ { X86::Int_VCOMISSrr, X86::Int_VCOMISSrm, 0 },
+ { X86::Int_VUCOMISDrr, X86::Int_VUCOMISDrm, 0 },
+ { X86::Int_VUCOMISSrr, X86::Int_VUCOMISSrm, 0 },
+ { X86::VCVTTSD2SI64rr, X86::VCVTTSD2SI64rm, 0 },
+ { X86::Int_VCVTTSD2SI64rr,X86::Int_VCVTTSD2SI64rm,0 },
+ { X86::VCVTTSD2SIrr, X86::VCVTTSD2SIrm, 0 },
+ { X86::Int_VCVTTSD2SIrr,X86::Int_VCVTTSD2SIrm, 0 },
+ { X86::VCVTTSS2SI64rr, X86::VCVTTSS2SI64rm, 0 },
+ { X86::Int_VCVTTSS2SI64rr,X86::Int_VCVTTSS2SI64rm,0 },
+ { X86::VCVTTSS2SIrr, X86::VCVTTSS2SIrm, 0 },
+ { X86::Int_VCVTTSS2SIrr,X86::Int_VCVTTSS2SIrm, 0 },
+ { X86::VCVTSD2SI64rr, X86::VCVTSD2SI64rm, 0 },
+ { X86::VCVTSD2SIrr, X86::VCVTSD2SIrm, 0 },
+ { X86::VCVTSS2SI64rr, X86::VCVTSS2SI64rm, 0 },
+ { X86::VCVTSS2SIrr, X86::VCVTSS2SIrm, 0 },
+ { X86::FsVMOVAPDrr, X86::VMOVSDrm, TB_NO_REVERSE },
+ { X86::FsVMOVAPSrr, X86::VMOVSSrm, TB_NO_REVERSE },
+ { 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, 0 },
+ { X86::VMOVDI2PDIrr, X86::VMOVDI2PDIrm, 0 },
+ { X86::VMOVDI2SSrr, X86::VMOVDI2SSrm, 0 },
+ { X86::VMOVDQArr, X86::VMOVDQArm, TB_ALIGN_16 },
+ { X86::VMOVSLDUPrr, X86::VMOVSLDUPrm, TB_ALIGN_16 },
+ { X86::VMOVSHDUPrr, X86::VMOVSHDUPrm, TB_ALIGN_16 },
+ { X86::VMOVUPDrr, X86::VMOVUPDrm, TB_ALIGN_16 },
+ { X86::VMOVUPSrr, X86::VMOVUPSrm, 0 },
+ { X86::VMOVZDI2PDIrr, X86::VMOVZDI2PDIrm, 0 },
+ { X86::VMOVZQI2PQIrr, X86::VMOVZQI2PQIrm, 0 },
+ { X86::VMOVZPQILo2PQIrr,X86::VMOVZPQILo2PQIrm, TB_ALIGN_16 },
+ { X86::VPABSBrr128, X86::VPABSBrm128, TB_ALIGN_16 },
+ { X86::VPABSDrr128, X86::VPABSDrm128, TB_ALIGN_16 },
+ { X86::VPABSWrr128, X86::VPABSWrm128, TB_ALIGN_16 },
+ { X86::VPERMILPDri, X86::VPERMILPDmi, TB_ALIGN_16 },
+ { X86::VPERMILPSri, X86::VPERMILPSmi, TB_ALIGN_16 },
+ { X86::VPSHUFDri, X86::VPSHUFDmi, TB_ALIGN_16 },
+ { X86::VPSHUFHWri, X86::VPSHUFHWmi, TB_ALIGN_16 },
+ { X86::VPSHUFLWri, X86::VPSHUFLWmi, TB_ALIGN_16 },
+ { X86::VRCPPSr, X86::VRCPPSm, TB_ALIGN_16 },
+ { X86::VRCPPSr_Int, X86::VRCPPSm_Int, TB_ALIGN_16 },
+ { X86::VRSQRTPSr, X86::VRSQRTPSm, TB_ALIGN_16 },
+ { X86::VRSQRTPSr_Int, X86::VRSQRTPSm_Int, TB_ALIGN_16 },
+ { X86::VSQRTPDr, X86::VSQRTPDm, TB_ALIGN_16 },
+ { X86::VSQRTPDr_Int, X86::VSQRTPDm_Int, TB_ALIGN_16 },
+ { X86::VSQRTPSr, X86::VSQRTPSm, TB_ALIGN_16 },
+ { X86::VSQRTPSr_Int, X86::VSQRTPSm_Int, TB_ALIGN_16 },
+ { X86::VUCOMISDrr, X86::VUCOMISDrm, 0 },
+ { X86::VUCOMISSrr, X86::VUCOMISSrm, 0 },
+ // AVX 256-bit foldable instructions
+ { X86::VMOVAPDYrr, X86::VMOVAPDYrm, TB_ALIGN_32 },
+ { X86::VMOVAPSYrr, X86::VMOVAPSYrm, TB_ALIGN_32 },
+ { X86::VMOVDQAYrr, X86::VMOVDQAYrm, TB_ALIGN_32 },
+ { X86::VMOVUPDYrr, X86::VMOVUPDYrm, 0 },
+ { X86::VMOVUPSYrr, X86::VMOVUPSYrm, 0 },
+ { X86::VPERMILPDYri, X86::VPERMILPDYmi, TB_ALIGN_32 },
+ { X86::VPERMILPSYri, X86::VPERMILPSYmi, TB_ALIGN_32 },
+ // AVX2 foldable instructions
+ { X86::VPABSBrr256, X86::VPABSBrm256, TB_ALIGN_32 },
+ { X86::VPABSDrr256, X86::VPABSDrm256, TB_ALIGN_32 },
+ { X86::VPABSWrr256, X86::VPABSWrm256, TB_ALIGN_32 },
+ { X86::VPSHUFDYri, X86::VPSHUFDYmi, TB_ALIGN_32 },
+ { X86::VPSHUFHWYri, X86::VPSHUFHWYmi, TB_ALIGN_32 },
+ { X86::VPSHUFLWYri, X86::VPSHUFLWYmi, TB_ALIGN_32 },
+ { X86::VRCPPSYr, X86::VRCPPSYm, TB_ALIGN_32 },
+ { X86::VRCPPSYr_Int, X86::VRCPPSYm_Int, TB_ALIGN_32 },
+ { X86::VRSQRTPSYr, X86::VRSQRTPSYm, TB_ALIGN_32 },
+ { X86::VRSQRTPSYr_Int, X86::VRSQRTPSYm_Int, TB_ALIGN_32 },
+ { X86::VSQRTPDYr, X86::VSQRTPDYm, TB_ALIGN_32 },
+ { X86::VSQRTPDYr_Int, X86::VSQRTPDYm_Int, TB_ALIGN_32 },
+ { X86::VSQRTPSYr, X86::VSQRTPSYm, TB_ALIGN_32 },
+ { X86::VSQRTPSYr_Int, X86::VSQRTPSYm_Int, TB_ALIGN_32 },
};
for (unsigned i = 0, e = array_lengthof(OpTbl1); i != e; ++i) {
- unsigned RegOp = OpTbl1[i][0];
- unsigned MemOp = OpTbl1[i][1] & ~TB_FLAGS;
- unsigned Align = OpTbl1[i][2];
- assert(!RegOp2MemOpTable1.count(RegOp) && "Duplicate entries");
- RegOp2MemOpTable1[RegOp] = std::make_pair(MemOp, Align);
-
- // If this is not a reversable operation (because there is a many->one)
- // mapping, don't insert the reverse of the operation into MemOp2RegOpTable.
- if (OpTbl1[i][1] & TB_NOT_REVERSABLE)
- continue;
-
- // Index 1, folded load
- unsigned AuxInfo = 1 | (1 << 4);
- assert(!MemOp2RegOpTable.count(MemOp) && "Duplicate entries");
- MemOp2RegOpTable[MemOp] = std::make_pair(RegOp, AuxInfo);
- }
-
- static const unsigned OpTbl2[][3] = {
- { X86::ADC32rr, X86::ADC32rm, 0 },
- { X86::ADC64rr, X86::ADC64rm, 0 },
- { X86::ADD16rr, X86::ADD16rm, 0 },
- { X86::ADD16rr_DB, X86::ADD16rm | TB_NOT_REVERSABLE, 0 },
- { X86::ADD32rr, X86::ADD32rm, 0 },
- { X86::ADD32rr_DB, X86::ADD32rm | TB_NOT_REVERSABLE, 0 },
- { X86::ADD64rr, X86::ADD64rm, 0 },
- { X86::ADD64rr_DB, X86::ADD64rm | TB_NOT_REVERSABLE, 0 },
- { X86::ADD8rr, X86::ADD8rm, 0 },
- { X86::ADDPDrr, X86::ADDPDrm, 16 },
- { X86::ADDPSrr, X86::ADDPSrm, 16 },
- { X86::ADDSDrr, X86::ADDSDrm, 0 },
- { X86::ADDSSrr, X86::ADDSSrm, 0 },
- { X86::ADDSUBPDrr, X86::ADDSUBPDrm, 16 },
- { X86::ADDSUBPSrr, X86::ADDSUBPSrm, 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, 16 },
- { X86::ANDNPSrr, X86::ANDNPSrm, 16 },
- { X86::ANDPDrr, X86::ANDPDrm, 16 },
- { X86::ANDPSrr, X86::ANDPSrm, 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, 16 },
- { X86::CMPPSrri, X86::CMPPSrmi, 16 },
- { X86::CMPSDrr, X86::CMPSDrm, 0 },
- { X86::CMPSSrr, X86::CMPSSrm, 0 },
- { X86::DIVPDrr, X86::DIVPDrm, 16 },
- { X86::DIVPSrr, X86::DIVPSrm, 16 },
- { X86::DIVSDrr, X86::DIVSDrm, 0 },
- { X86::DIVSSrr, X86::DIVSSrm, 0 },
- { X86::FsANDNPDrr, X86::FsANDNPDrm, 16 },
- { X86::FsANDNPSrr, X86::FsANDNPSrm, 16 },
- { X86::FsANDPDrr, X86::FsANDPDrm, 16 },
- { X86::FsANDPSrr, X86::FsANDPSrm, 16 },
- { X86::FsORPDrr, X86::FsORPDrm, 16 },
- { X86::FsORPSrr, X86::FsORPSrm, 16 },
- { X86::FsXORPDrr, X86::FsXORPDrm, 16 },
- { X86::FsXORPSrr, X86::FsXORPSrm, 16 },
- { X86::HADDPDrr, X86::HADDPDrm, 16 },
- { X86::HADDPSrr, X86::HADDPSrm, 16 },
- { X86::HSUBPDrr, X86::HSUBPDrm, 16 },
- { X86::HSUBPSrr, X86::HSUBPSrm, 16 },
- { X86::IMUL16rr, X86::IMUL16rm, 0 },
- { X86::IMUL32rr, X86::IMUL32rm, 0 },
- { X86::IMUL64rr, X86::IMUL64rm, 0 },
- { X86::MAXPDrr, X86::MAXPDrm, 16 },
- { X86::MAXPDrr_Int, X86::MAXPDrm_Int, 16 },
- { X86::MAXPSrr, X86::MAXPSrm, 16 },
- { X86::MAXPSrr_Int, X86::MAXPSrm_Int, 16 },
- { X86::MAXSDrr, X86::MAXSDrm, 0 },
- { X86::MAXSDrr_Int, X86::MAXSDrm_Int, 0 },
- { X86::MAXSSrr, X86::MAXSSrm, 0 },
- { X86::MAXSSrr_Int, X86::MAXSSrm_Int, 0 },
- { X86::MINPDrr, X86::MINPDrm, 16 },
- { X86::MINPDrr_Int, X86::MINPDrm_Int, 16 },
- { X86::MINPSrr, X86::MINPSrm, 16 },
- { X86::MINPSrr_Int, X86::MINPSrm_Int, 16 },
- { X86::MINSDrr, X86::MINSDrm, 0 },
- { X86::MINSDrr_Int, X86::MINSDrm_Int, 0 },
- { X86::MINSSrr, X86::MINSSrm, 0 },
- { X86::MINSSrr_Int, X86::MINSSrm_Int, 0 },
- { X86::MULPDrr, X86::MULPDrm, 16 },
- { X86::MULPSrr, X86::MULPSrm, 16 },
- { X86::MULSDrr, X86::MULSDrm, 0 },
- { X86::MULSSrr, X86::MULSSrm, 0 },
- { X86::OR16rr, X86::OR16rm, 0 },
- { X86::OR32rr, X86::OR32rm, 0 },
- { X86::OR64rr, X86::OR64rm, 0 },
- { X86::OR8rr, X86::OR8rm, 0 },
- { X86::ORPDrr, X86::ORPDrm, 16 },
- { X86::ORPSrr, X86::ORPSrm, 16 },
- { X86::PACKSSDWrr, X86::PACKSSDWrm, 16 },
- { X86::PACKSSWBrr, X86::PACKSSWBrm, 16 },
- { X86::PACKUSWBrr, X86::PACKUSWBrm, 16 },
- { X86::PADDBrr, X86::PADDBrm, 16 },
- { X86::PADDDrr, X86::PADDDrm, 16 },
- { X86::PADDQrr, X86::PADDQrm, 16 },
- { X86::PADDSBrr, X86::PADDSBrm, 16 },
- { X86::PADDSWrr, X86::PADDSWrm, 16 },
- { X86::PADDWrr, X86::PADDWrm, 16 },
- { X86::PANDNrr, X86::PANDNrm, 16 },
- { X86::PANDrr, X86::PANDrm, 16 },
- { X86::PAVGBrr, X86::PAVGBrm, 16 },
- { X86::PAVGWrr, X86::PAVGWrm, 16 },
- { X86::PCMPEQBrr, X86::PCMPEQBrm, 16 },
- { X86::PCMPEQDrr, X86::PCMPEQDrm, 16 },
- { X86::PCMPEQWrr, X86::PCMPEQWrm, 16 },
- { X86::PCMPGTBrr, X86::PCMPGTBrm, 16 },
- { X86::PCMPGTDrr, X86::PCMPGTDrm, 16 },
- { X86::PCMPGTWrr, X86::PCMPGTWrm, 16 },
- { X86::PINSRWrri, X86::PINSRWrmi, 16 },
- { X86::PMADDWDrr, X86::PMADDWDrm, 16 },
- { X86::PMAXSWrr, X86::PMAXSWrm, 16 },
- { X86::PMAXUBrr, X86::PMAXUBrm, 16 },
- { X86::PMINSWrr, X86::PMINSWrm, 16 },
- { X86::PMINUBrr, X86::PMINUBrm, 16 },
- { X86::PMULDQrr, X86::PMULDQrm, 16 },
- { X86::PMULHUWrr, X86::PMULHUWrm, 16 },
- { X86::PMULHWrr, X86::PMULHWrm, 16 },
- { X86::PMULLDrr, X86::PMULLDrm, 16 },
- { X86::PMULLWrr, X86::PMULLWrm, 16 },
- { X86::PMULUDQrr, X86::PMULUDQrm, 16 },
- { X86::PORrr, X86::PORrm, 16 },
- { X86::PSADBWrr, X86::PSADBWrm, 16 },
- { X86::PSLLDrr, X86::PSLLDrm, 16 },
- { X86::PSLLQrr, X86::PSLLQrm, 16 },
- { X86::PSLLWrr, X86::PSLLWrm, 16 },
- { X86::PSRADrr, X86::PSRADrm, 16 },
- { X86::PSRAWrr, X86::PSRAWrm, 16 },
- { X86::PSRLDrr, X86::PSRLDrm, 16 },
- { X86::PSRLQrr, X86::PSRLQrm, 16 },
- { X86::PSRLWrr, X86::PSRLWrm, 16 },
- { X86::PSUBBrr, X86::PSUBBrm, 16 },
- { X86::PSUBDrr, X86::PSUBDrm, 16 },
- { X86::PSUBSBrr, X86::PSUBSBrm, 16 },
- { X86::PSUBSWrr, X86::PSUBSWrm, 16 },
- { X86::PSUBWrr, X86::PSUBWrm, 16 },
- { X86::PUNPCKHBWrr, X86::PUNPCKHBWrm, 16 },
- { X86::PUNPCKHDQrr, X86::PUNPCKHDQrm, 16 },
- { X86::PUNPCKHQDQrr, X86::PUNPCKHQDQrm, 16 },
- { X86::PUNPCKHWDrr, X86::PUNPCKHWDrm, 16 },
- { X86::PUNPCKLBWrr, X86::PUNPCKLBWrm, 16 },
- { X86::PUNPCKLDQrr, X86::PUNPCKLDQrm, 16 },
- { X86::PUNPCKLQDQrr, X86::PUNPCKLQDQrm, 16 },
- { X86::PUNPCKLWDrr, X86::PUNPCKLWDrm, 16 },
- { X86::PXORrr, X86::PXORrm, 16 },
- { X86::SBB32rr, X86::SBB32rm, 0 },
- { X86::SBB64rr, X86::SBB64rm, 0 },
- { X86::SHUFPDrri, X86::SHUFPDrmi, 16 },
- { X86::SHUFPSrri, X86::SHUFPSrmi, 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, 16 },
- { X86::SUBPSrr, X86::SUBPSrm, 16 },
- { X86::SUBSDrr, X86::SUBSDrm, 0 },
- { X86::SUBSSrr, X86::SUBSSrm, 0 },
+ unsigned RegOp = OpTbl1[i].RegOp;
+ unsigned MemOp = OpTbl1[i].MemOp;
+ unsigned Flags = OpTbl1[i].Flags;
+ AddTableEntry(RegOp2MemOpTable1, MemOp2RegOpTable,
+ RegOp, MemOp,
+ // Index 1, folded load
+ Flags | TB_INDEX_1 | TB_FOLDED_LOAD);
+ }
+
+ static const X86OpTblEntry OpTbl2[] = {
+ { 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::ADDSSrr, X86::ADDSSrm, 0 },
+ { 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::DIVPDrr, X86::DIVPDrm, TB_ALIGN_16 },
+ { X86::DIVPSrr, X86::DIVPSrm, TB_ALIGN_16 },
+ { X86::DIVSDrr, X86::DIVSDrm, 0 },
+ { X86::DIVSSrr, X86::DIVSSrm, 0 },
+ { X86::FsANDNPDrr, X86::FsANDNPDrm, TB_ALIGN_16 },
+ { X86::FsANDNPSrr, X86::FsANDNPSrm, TB_ALIGN_16 },
+ { X86::FsANDPDrr, X86::FsANDPDrm, TB_ALIGN_16 },
+ { X86::FsANDPSrr, X86::FsANDPSrm, TB_ALIGN_16 },
+ { X86::FsORPDrr, X86::FsORPDrm, TB_ALIGN_16 },
+ { X86::FsORPSrr, X86::FsORPSrm, TB_ALIGN_16 },
+ { X86::FsXORPDrr, X86::FsXORPDrm, TB_ALIGN_16 },
+ { X86::FsXORPSrr, X86::FsXORPSrm, 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, 0 },
+ { X86::Int_CMPSSrr, X86::Int_CMPSSrm, 0 },
+ { X86::MAXPDrr, X86::MAXPDrm, TB_ALIGN_16 },
+ { X86::MAXPDrr_Int, X86::MAXPDrm_Int, TB_ALIGN_16 },
+ { X86::MAXPSrr, X86::MAXPSrm, TB_ALIGN_16 },
+ { X86::MAXPSrr_Int, X86::MAXPSrm_Int, TB_ALIGN_16 },
+ { X86::MAXSDrr, X86::MAXSDrm, 0 },
+ { X86::MAXSDrr_Int, X86::MAXSDrm_Int, 0 },
+ { X86::MAXSSrr, X86::MAXSSrm, 0 },
+ { X86::MAXSSrr_Int, X86::MAXSSrm_Int, 0 },
+ { X86::MINPDrr, X86::MINPDrm, TB_ALIGN_16 },
+ { X86::MINPDrr_Int, X86::MINPDrm_Int, TB_ALIGN_16 },
+ { X86::MINPSrr, X86::MINPSrm, TB_ALIGN_16 },
+ { X86::MINPSrr_Int, X86::MINPSrm_Int, TB_ALIGN_16 },
+ { X86::MINSDrr, X86::MINSDrm, 0 },
+ { X86::MINSDrr_Int, X86::MINSDrm_Int, 0 },
+ { X86::MINSSrr, X86::MINSSrm, 0 },
+ { X86::MINSSrr_Int, X86::MINSSrm_Int, 0 },
+ { 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::MULSSrr, X86::MULSSrm, 0 },
+ { 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::PALIGNR128rr, X86::PALIGNR128rm, 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::PBLENDWrri, X86::PBLENDWrmi, 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::PINSRWrri, X86::PINSRWrmi, TB_ALIGN_16 },
+ { X86::PMADDUBSWrr128, X86::PMADDUBSWrm128, TB_ALIGN_16 },
+ { X86::PMADDWDrr, X86::PMADDWDrm, TB_ALIGN_16 },
+ { X86::PMAXSWrr, X86::PMAXSWrm, TB_ALIGN_16 },
+ { X86::PMAXUBrr, X86::PMAXUBrm, TB_ALIGN_16 },
+ { X86::PMINSWrr, X86::PMINSWrm, TB_ALIGN_16 },
+ { X86::PMINUBrr, X86::PMINUBrm, TB_ALIGN_16 },
+ { X86::PMULDQrr, X86::PMULDQrm, TB_ALIGN_16 },
+ { X86::PMULHRSWrr128, X86::PMULHRSWrm128, 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::PSIGNBrr, X86::PSIGNBrm, TB_ALIGN_16 },
+ { X86::PSIGNWrr, X86::PSIGNWrm, TB_ALIGN_16 },
+ { X86::PSIGNDrr, X86::PSIGNDrm, 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::PSUBSBrr, X86::PSUBSBrm, TB_ALIGN_16 },
+ { X86::PSUBSWrr, X86::PSUBSWrm, 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::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::SUBSSrr, X86::SUBSSrm, 0 },
// FIXME: TEST*rr -> swapped operand of TEST*mr.
- { X86::UNPCKHPDrr, X86::UNPCKHPDrm, 16 },
- { X86::UNPCKHPSrr, X86::UNPCKHPSrm, 16 },
- { X86::UNPCKLPDrr, X86::UNPCKLPDrm, 16 },
- { X86::UNPCKLPSrr, X86::UNPCKLPSrm, 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, 16 },
- { X86::XORPSrr, X86::XORPSrm, 16 }
+ { 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 },
+ // AVX 128-bit versions of foldable instructions
+ { X86::VCVTSD2SSrr, X86::VCVTSD2SSrm, 0 },
+ { X86::Int_VCVTSD2SSrr, X86::Int_VCVTSD2SSrm, 0 },
+ { 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::VCVTSS2SDrr, X86::VCVTSS2SDrm, 0 },
+ { X86::Int_VCVTSS2SDrr, X86::Int_VCVTSS2SDrm, 0 },
+ { X86::VCVTTPD2DQrr, X86::VCVTTPD2DQXrm, TB_ALIGN_16 },
+ { X86::VCVTTPS2DQrr, X86::VCVTTPS2DQrm, TB_ALIGN_16 },
+ { X86::VRSQRTSSr, X86::VRSQRTSSm, 0 },
+ { X86::VSQRTSDr, X86::VSQRTSDm, 0 },
+ { X86::VSQRTSSr, X86::VSQRTSSm, 0 },
+ { X86::VADDPDrr, X86::VADDPDrm, TB_ALIGN_16 },
+ { X86::VADDPSrr, X86::VADDPSrm, TB_ALIGN_16 },
+ { X86::VADDSDrr, X86::VADDSDrm, 0 },
+ { X86::VADDSSrr, X86::VADDSSrm, 0 },
+ { X86::VADDSUBPDrr, X86::VADDSUBPDrm, TB_ALIGN_16 },
+ { X86::VADDSUBPSrr, X86::VADDSUBPSrm, TB_ALIGN_16 },
+ { X86::VANDNPDrr, X86::VANDNPDrm, TB_ALIGN_16 },
+ { X86::VANDNPSrr, X86::VANDNPSrm, TB_ALIGN_16 },
+ { X86::VANDPDrr, X86::VANDPDrm, TB_ALIGN_16 },
+ { X86::VANDPSrr, X86::VANDPSrm, TB_ALIGN_16 },
+ { X86::VBLENDPDrri, X86::VBLENDPDrmi, TB_ALIGN_16 },
+ { X86::VBLENDPSrri, X86::VBLENDPSrmi, TB_ALIGN_16 },
+ { X86::VBLENDVPDrr, X86::VBLENDVPDrm, TB_ALIGN_16 },
+ { X86::VBLENDVPSrr, X86::VBLENDVPSrm, TB_ALIGN_16 },
+ { X86::VCMPPDrri, X86::VCMPPDrmi, TB_ALIGN_16 },
+ { X86::VCMPPSrri, X86::VCMPPSrmi, TB_ALIGN_16 },
+ { X86::VCMPSDrr, X86::VCMPSDrm, 0 },
+ { X86::VCMPSSrr, X86::VCMPSSrm, 0 },
+ { X86::VDIVPDrr, X86::VDIVPDrm, TB_ALIGN_16 },
+ { X86::VDIVPSrr, X86::VDIVPSrm, TB_ALIGN_16 },
+ { X86::VDIVSDrr, X86::VDIVSDrm, 0 },
+ { X86::VDIVSSrr, X86::VDIVSSrm, 0 },
+ { X86::VFsANDNPDrr, X86::VFsANDNPDrm, TB_ALIGN_16 },
+ { X86::VFsANDNPSrr, X86::VFsANDNPSrm, TB_ALIGN_16 },
+ { X86::VFsANDPDrr, X86::VFsANDPDrm, TB_ALIGN_16 },
+ { X86::VFsANDPSrr, X86::VFsANDPSrm, TB_ALIGN_16 },
+ { X86::VFsORPDrr, X86::VFsORPDrm, TB_ALIGN_16 },
+ { X86::VFsORPSrr, X86::VFsORPSrm, TB_ALIGN_16 },
+ { X86::VFsXORPDrr, X86::VFsXORPDrm, TB_ALIGN_16 },
+ { X86::VFsXORPSrr, X86::VFsXORPSrm, TB_ALIGN_16 },
+ { X86::VHADDPDrr, X86::VHADDPDrm, TB_ALIGN_16 },
+ { X86::VHADDPSrr, X86::VHADDPSrm, TB_ALIGN_16 },
+ { X86::VHSUBPDrr, X86::VHSUBPDrm, TB_ALIGN_16 },
+ { X86::VHSUBPSrr, X86::VHSUBPSrm, TB_ALIGN_16 },
+ { X86::Int_VCMPSDrr, X86::Int_VCMPSDrm, 0 },
+ { X86::Int_VCMPSSrr, X86::Int_VCMPSSrm, 0 },
+ { X86::VMAXPDrr, X86::VMAXPDrm, TB_ALIGN_16 },
+ { X86::VMAXPDrr_Int, X86::VMAXPDrm_Int, TB_ALIGN_16 },
+ { X86::VMAXPSrr, X86::VMAXPSrm, TB_ALIGN_16 },
+ { X86::VMAXPSrr_Int, X86::VMAXPSrm_Int, TB_ALIGN_16 },
+ { X86::VMAXSDrr, X86::VMAXSDrm, 0 },
+ { X86::VMAXSDrr_Int, X86::VMAXSDrm_Int, 0 },
+ { X86::VMAXSSrr, X86::VMAXSSrm, 0 },
+ { X86::VMAXSSrr_Int, X86::VMAXSSrm_Int, 0 },
+ { X86::VMINPDrr, X86::VMINPDrm, TB_ALIGN_16 },
+ { X86::VMINPDrr_Int, X86::VMINPDrm_Int, TB_ALIGN_16 },
+ { X86::VMINPSrr, X86::VMINPSrm, TB_ALIGN_16 },
+ { X86::VMINPSrr_Int, X86::VMINPSrm_Int, TB_ALIGN_16 },
+ { X86::VMINSDrr, X86::VMINSDrm, 0 },
+ { X86::VMINSDrr_Int, X86::VMINSDrm_Int, 0 },
+ { X86::VMINSSrr, X86::VMINSSrm, 0 },
+ { X86::VMINSSrr_Int, X86::VMINSSrm_Int, 0 },
+ { X86::VMPSADBWrri, X86::VMPSADBWrmi, TB_ALIGN_16 },
+ { X86::VMULPDrr, X86::VMULPDrm, TB_ALIGN_16 },
+ { X86::VMULPSrr, X86::VMULPSrm, TB_ALIGN_16 },
+ { X86::VMULSDrr, X86::VMULSDrm, 0 },
+ { X86::VMULSSrr, X86::VMULSSrm, 0 },
+ { X86::VORPDrr, X86::VORPDrm, TB_ALIGN_16 },
+ { X86::VORPSrr, X86::VORPSrm, TB_ALIGN_16 },
+ { X86::VPACKSSDWrr, X86::VPACKSSDWrm, TB_ALIGN_16 },
+ { X86::VPACKSSWBrr, X86::VPACKSSWBrm, TB_ALIGN_16 },
+ { X86::VPACKUSDWrr, X86::VPACKUSDWrm, TB_ALIGN_16 },
+ { X86::VPACKUSWBrr, X86::VPACKUSWBrm, TB_ALIGN_16 },
+ { X86::VPADDBrr, X86::VPADDBrm, TB_ALIGN_16 },
+ { X86::VPADDDrr, X86::VPADDDrm, TB_ALIGN_16 },
+ { X86::VPADDQrr, X86::VPADDQrm, TB_ALIGN_16 },
+ { X86::VPADDSBrr, X86::VPADDSBrm, TB_ALIGN_16 },
+ { X86::VPADDSWrr, X86::VPADDSWrm, TB_ALIGN_16 },
+ { X86::VPADDUSBrr, X86::VPADDUSBrm, TB_ALIGN_16 },
+ { X86::VPADDUSWrr, X86::VPADDUSWrm, TB_ALIGN_16 },
+ { X86::VPADDWrr, X86::VPADDWrm, TB_ALIGN_16 },
+ { X86::VPALIGNR128rr, X86::VPALIGNR128rm, TB_ALIGN_16 },
+ { X86::VPANDNrr, X86::VPANDNrm, TB_ALIGN_16 },
+ { X86::VPANDrr, X86::VPANDrm, TB_ALIGN_16 },
+ { X86::VPAVGBrr, X86::VPAVGBrm, TB_ALIGN_16 },
+ { X86::VPAVGWrr, X86::VPAVGWrm, TB_ALIGN_16 },
+ { X86::VPBLENDWrri, X86::VPBLENDWrmi, TB_ALIGN_16 },
+ { X86::VPCMPEQBrr, X86::VPCMPEQBrm, TB_ALIGN_16 },
+ { X86::VPCMPEQDrr, X86::VPCMPEQDrm, TB_ALIGN_16 },
+ { X86::VPCMPEQQrr, X86::VPCMPEQQrm, TB_ALIGN_16 },
+ { X86::VPCMPEQWrr, X86::VPCMPEQWrm, TB_ALIGN_16 },
+ { X86::VPCMPGTBrr, X86::VPCMPGTBrm, TB_ALIGN_16 },
+ { X86::VPCMPGTDrr, X86::VPCMPGTDrm, TB_ALIGN_16 },
+ { X86::VPCMPGTQrr, X86::VPCMPGTQrm, TB_ALIGN_16 },
+ { X86::VPCMPGTWrr, X86::VPCMPGTWrm, TB_ALIGN_16 },
+ { X86::VPHADDDrr, X86::VPHADDDrm, TB_ALIGN_16 },
+ { X86::VPHADDSWrr128, X86::VPHADDSWrm128, TB_ALIGN_16 },
+ { X86::VPHADDWrr, X86::VPHADDWrm, TB_ALIGN_16 },
+ { X86::VPHSUBDrr, X86::VPHSUBDrm, TB_ALIGN_16 },
+ { X86::VPHSUBSWrr128, X86::VPHSUBSWrm128, TB_ALIGN_16 },
+ { X86::VPHSUBWrr, X86::VPHSUBWrm, TB_ALIGN_16 },
+ { X86::VPERMILPDrr, X86::VPERMILPDrm, TB_ALIGN_16 },
+ { X86::VPERMILPSrr, X86::VPERMILPSrm, TB_ALIGN_16 },
+ { X86::VPINSRWrri, X86::VPINSRWrmi, TB_ALIGN_16 },
+ { X86::VPMADDUBSWrr128, X86::VPMADDUBSWrm128, TB_ALIGN_16 },
+ { X86::VPMADDWDrr, X86::VPMADDWDrm, TB_ALIGN_16 },
+ { X86::VPMAXSWrr, X86::VPMAXSWrm, TB_ALIGN_16 },
+ { X86::VPMAXUBrr, X86::VPMAXUBrm, TB_ALIGN_16 },
+ { X86::VPMINSWrr, X86::VPMINSWrm, TB_ALIGN_16 },
+ { X86::VPMINUBrr, X86::VPMINUBrm, TB_ALIGN_16 },
+ { X86::VPMULDQrr, X86::VPMULDQrm, TB_ALIGN_16 },
+ { X86::VPMULHRSWrr128, X86::VPMULHRSWrm128, TB_ALIGN_16 },
+ { X86::VPMULHUWrr, X86::VPMULHUWrm, TB_ALIGN_16 },
+ { X86::VPMULHWrr, X86::VPMULHWrm, TB_ALIGN_16 },
+ { X86::VPMULLDrr, X86::VPMULLDrm, TB_ALIGN_16 },
+ { X86::VPMULLWrr, X86::VPMULLWrm, TB_ALIGN_16 },
+ { X86::VPMULUDQrr, X86::VPMULUDQrm, TB_ALIGN_16 },
+ { X86::VPORrr, X86::VPORrm, TB_ALIGN_16 },
+ { X86::VPSADBWrr, X86::VPSADBWrm, TB_ALIGN_16 },
+ { X86::VPSHUFBrr, X86::VPSHUFBrm, TB_ALIGN_16 },
+ { X86::VPSIGNBrr, X86::VPSIGNBrm, TB_ALIGN_16 },
+ { X86::VPSIGNWrr, X86::VPSIGNWrm, TB_ALIGN_16 },
+ { X86::VPSIGNDrr, X86::VPSIGNDrm, TB_ALIGN_16 },
+ { X86::VPSLLDrr, X86::VPSLLDrm, TB_ALIGN_16 },
+ { X86::VPSLLQrr, X86::VPSLLQrm, TB_ALIGN_16 },
+ { X86::VPSLLWrr, X86::VPSLLWrm, TB_ALIGN_16 },
+ { X86::VPSRADrr, X86::VPSRADrm, TB_ALIGN_16 },
+ { X86::VPSRAWrr, X86::VPSRAWrm, TB_ALIGN_16 },
+ { X86::VPSRLDrr, X86::VPSRLDrm, TB_ALIGN_16 },
+ { X86::VPSRLQrr, X86::VPSRLQrm, TB_ALIGN_16 },
+ { X86::VPSRLWrr, X86::VPSRLWrm, TB_ALIGN_16 },
+ { X86::VPSUBBrr, X86::VPSUBBrm, TB_ALIGN_16 },
+ { X86::VPSUBDrr, X86::VPSUBDrm, TB_ALIGN_16 },
+ { X86::VPSUBSBrr, X86::VPSUBSBrm, TB_ALIGN_16 },
+ { X86::VPSUBSWrr, X86::VPSUBSWrm, TB_ALIGN_16 },
+ { X86::VPSUBWrr, X86::VPSUBWrm, TB_ALIGN_16 },
+ { X86::VPUNPCKHBWrr, X86::VPUNPCKHBWrm, TB_ALIGN_16 },
+ { X86::VPUNPCKHDQrr, X86::VPUNPCKHDQrm, TB_ALIGN_16 },
+ { X86::VPUNPCKHQDQrr, X86::VPUNPCKHQDQrm, TB_ALIGN_16 },
+ { X86::VPUNPCKHWDrr, X86::VPUNPCKHWDrm, TB_ALIGN_16 },
+ { X86::VPUNPCKLBWrr, X86::VPUNPCKLBWrm, TB_ALIGN_16 },
+ { X86::VPUNPCKLDQrr, X86::VPUNPCKLDQrm, TB_ALIGN_16 },
+ { X86::VPUNPCKLQDQrr, X86::VPUNPCKLQDQrm, TB_ALIGN_16 },
+ { X86::VPUNPCKLWDrr, X86::VPUNPCKLWDrm, TB_ALIGN_16 },
+ { X86::VPXORrr, X86::VPXORrm, TB_ALIGN_16 },
+ { X86::VSHUFPDrri, X86::VSHUFPDrmi, TB_ALIGN_16 },
+ { X86::VSHUFPSrri, X86::VSHUFPSrmi, TB_ALIGN_16 },
+ { X86::VSUBPDrr, X86::VSUBPDrm, TB_ALIGN_16 },
+ { X86::VSUBPSrr, X86::VSUBPSrm, TB_ALIGN_16 },
+ { X86::VSUBSDrr, X86::VSUBSDrm, 0 },
+ { X86::VSUBSSrr, X86::VSUBSSrm, 0 },
+ { X86::VUNPCKHPDrr, X86::VUNPCKHPDrm, TB_ALIGN_16 },
+ { X86::VUNPCKHPSrr, X86::VUNPCKHPSrm, TB_ALIGN_16 },
+ { X86::VUNPCKLPDrr, X86::VUNPCKLPDrm, TB_ALIGN_16 },
+ { X86::VUNPCKLPSrr, X86::VUNPCKLPSrm, TB_ALIGN_16 },
+ { X86::VXORPDrr, X86::VXORPDrm, TB_ALIGN_16 },
+ { X86::VXORPSrr, X86::VXORPSrm, TB_ALIGN_16 },
+ // AVX 256-bit foldable instructions
+ { X86::VADDPDYrr, X86::VADDPDYrm, TB_ALIGN_32 },
+ { X86::VADDPSYrr, X86::VADDPSYrm, TB_ALIGN_32 },
+ { X86::VADDSUBPDYrr, X86::VADDSUBPDYrm, TB_ALIGN_32 },
+ { X86::VADDSUBPSYrr, X86::VADDSUBPSYrm, TB_ALIGN_32 },
+ { X86::VANDNPDYrr, X86::VANDNPDYrm, TB_ALIGN_32 },
+ { X86::VANDNPSYrr, X86::VANDNPSYrm, TB_ALIGN_32 },
+ { X86::VANDPDYrr, X86::VANDPDYrm, TB_ALIGN_32 },
+ { X86::VANDPSYrr, X86::VANDPSYrm, TB_ALIGN_32 },
+ { X86::VBLENDPDYrri, X86::VBLENDPDYrmi, TB_ALIGN_32 },
+ { X86::VBLENDPSYrri, X86::VBLENDPSYrmi, TB_ALIGN_32 },
+ { X86::VBLENDVPDYrr, X86::VBLENDVPDYrm, TB_ALIGN_32 },
+ { X86::VBLENDVPSYrr, X86::VBLENDVPSYrm, TB_ALIGN_32 },
+ { X86::VCMPPDYrri, X86::VCMPPDYrmi, TB_ALIGN_32 },
+ { X86::VCMPPSYrri, X86::VCMPPSYrmi, TB_ALIGN_32 },
+ { X86::VDIVPDYrr, X86::VDIVPDYrm, TB_ALIGN_32 },
+ { X86::VDIVPSYrr, X86::VDIVPSYrm, TB_ALIGN_32 },
+ { X86::VHADDPDYrr, X86::VHADDPDYrm, TB_ALIGN_32 },
+ { X86::VHADDPSYrr, X86::VHADDPSYrm, TB_ALIGN_32 },
+ { X86::VHSUBPDYrr, X86::VHSUBPDYrm, TB_ALIGN_32 },
+ { X86::VHSUBPSYrr, X86::VHSUBPSYrm, TB_ALIGN_32 },
+ { X86::VINSERTF128rr, X86::VINSERTF128rm, TB_ALIGN_32 },
+ { X86::VMAXPDYrr, X86::VMAXPDYrm, TB_ALIGN_32 },
+ { X86::VMAXPDYrr_Int, X86::VMAXPDYrm_Int, TB_ALIGN_32 },
+ { X86::VMAXPSYrr, X86::VMAXPSYrm, TB_ALIGN_32 },
+ { X86::VMAXPSYrr_Int, X86::VMAXPSYrm_Int, TB_ALIGN_32 },
+ { X86::VMINPDYrr, X86::VMINPDYrm, TB_ALIGN_32 },
+ { X86::VMINPDYrr_Int, X86::VMINPDYrm_Int, TB_ALIGN_32 },
+ { X86::VMINPSYrr, X86::VMINPSYrm, TB_ALIGN_32 },
+ { X86::VMINPSYrr_Int, X86::VMINPSYrm_Int, TB_ALIGN_32 },
+ { X86::VMULPDYrr, X86::VMULPDYrm, TB_ALIGN_32 },
+ { X86::VMULPSYrr, X86::VMULPSYrm, TB_ALIGN_32 },
+ { X86::VORPDYrr, X86::VORPDYrm, TB_ALIGN_32 },
+ { X86::VORPSYrr, X86::VORPSYrm, TB_ALIGN_32 },
+ { X86::VPERM2F128rr, X86::VPERM2F128rm, TB_ALIGN_32 },
+ { X86::VPERMILPDYrr, X86::VPERMILPDYrm, TB_ALIGN_32 },
+ { X86::VPERMILPSYrr, X86::VPERMILPSYrm, TB_ALIGN_32 },
+ { X86::VSHUFPDYrri, X86::VSHUFPDYrmi, TB_ALIGN_32 },
+ { X86::VSHUFPSYrri, X86::VSHUFPSYrmi, TB_ALIGN_32 },
+ { X86::VSUBPDYrr, X86::VSUBPDYrm, TB_ALIGN_32 },
+ { X86::VSUBPSYrr, X86::VSUBPSYrm, TB_ALIGN_32 },
+ { X86::VUNPCKHPDYrr, X86::VUNPCKHPDYrm, TB_ALIGN_32 },
+ { X86::VUNPCKHPSYrr, X86::VUNPCKHPSYrm, TB_ALIGN_32 },
+ { X86::VUNPCKLPDYrr, X86::VUNPCKLPDYrm, TB_ALIGN_32 },
+ { X86::VUNPCKLPSYrr, X86::VUNPCKLPSYrm, TB_ALIGN_32 },
+ { X86::VXORPDYrr, X86::VXORPDYrm, TB_ALIGN_32 },
+ { X86::VXORPSYrr, X86::VXORPSYrm, TB_ALIGN_32 },
+ // AVX2 foldable instructions
+ { X86::VINSERTI128rr, X86::VINSERTI128rm, TB_ALIGN_16 },
+ { X86::VPACKSSDWYrr, X86::VPACKSSDWYrm, TB_ALIGN_32 },
+ { X86::VPACKSSWBYrr, X86::VPACKSSWBYrm, TB_ALIGN_32 },
+ { X86::VPACKUSDWYrr, X86::VPACKUSDWYrm, TB_ALIGN_32 },
+ { X86::VPACKUSWBYrr, X86::VPACKUSWBYrm, TB_ALIGN_32 },
+ { X86::VPADDBYrr, X86::VPADDBYrm, TB_ALIGN_32 },
+ { X86::VPADDDYrr, X86::VPADDDYrm, TB_ALIGN_32 },
+ { X86::VPADDQYrr, X86::VPADDQYrm, TB_ALIGN_32 },
+ { X86::VPADDSBYrr, X86::VPADDSBYrm, TB_ALIGN_32 },
+ { X86::VPADDSWYrr, X86::VPADDSWYrm, TB_ALIGN_32 },
+ { X86::VPADDUSBYrr, X86::VPADDUSBYrm, TB_ALIGN_32 },
+ { X86::VPADDUSWYrr, X86::VPADDUSWYrm, TB_ALIGN_32 },
+ { X86::VPADDWYrr, X86::VPADDWYrm, TB_ALIGN_32 },
+ { X86::VPALIGNR256rr, X86::VPALIGNR256rm, TB_ALIGN_32 },
+ { X86::VPANDNYrr, X86::VPANDNYrm, TB_ALIGN_32 },
+ { X86::VPANDYrr, X86::VPANDYrm, TB_ALIGN_32 },
+ { X86::VPAVGBYrr, X86::VPAVGBYrm, TB_ALIGN_32 },
+ { X86::VPAVGWYrr, X86::VPAVGWYrm, TB_ALIGN_32 },
+ { X86::VPBLENDDrri, X86::VPBLENDDrmi, TB_ALIGN_32 },
+ { X86::VPBLENDDYrri, X86::VPBLENDDYrmi, TB_ALIGN_32 },
+ { X86::VPBLENDWYrri, X86::VPBLENDWYrmi, TB_ALIGN_32 },
+ { X86::VPCMPEQBYrr, X86::VPCMPEQBYrm, TB_ALIGN_32 },
+ { X86::VPCMPEQDYrr, X86::VPCMPEQDYrm, TB_ALIGN_32 },
+ { X86::VPCMPEQQYrr, X86::VPCMPEQQYrm, TB_ALIGN_32 },
+ { X86::VPCMPEQWYrr, X86::VPCMPEQWYrm, TB_ALIGN_32 },
+ { X86::VPCMPGTBYrr, X86::VPCMPGTBYrm, TB_ALIGN_32 },
+ { X86::VPCMPGTDYrr, X86::VPCMPGTDYrm, TB_ALIGN_32 },
+ { X86::VPCMPGTQYrr, X86::VPCMPGTQYrm, TB_ALIGN_32 },
+ { X86::VPCMPGTWYrr, X86::VPCMPGTWYrm, TB_ALIGN_32 },
+ { X86::VPERM2I128rr, X86::VPERM2I128rm, TB_ALIGN_32 },
+ { X86::VPERMDYrr, X86::VPERMDYrm, TB_ALIGN_32 },
+ { X86::VPERMPDYri, X86::VPERMPDYmi, TB_ALIGN_32 },
+ { X86::VPERMPSYrr, X86::VPERMPSYrm, TB_ALIGN_32 },
+ { X86::VPERMQYri, X86::VPERMQYmi, TB_ALIGN_32 },
+ { X86::VPHADDDYrr, X86::VPHADDDYrm, TB_ALIGN_32 },
+ { X86::VPHADDSWrr256, X86::VPHADDSWrm256, TB_ALIGN_32 },
+ { X86::VPHADDWYrr, X86::VPHADDWYrm, TB_ALIGN_32 },
+ { X86::VPHSUBDYrr, X86::VPHSUBDYrm, TB_ALIGN_32 },
+ { X86::VPHSUBSWrr256, X86::VPHSUBSWrm256, TB_ALIGN_32 },
+ { X86::VPHSUBWYrr, X86::VPHSUBWYrm, TB_ALIGN_32 },
+ { X86::VPMADDUBSWrr256, X86::VPMADDUBSWrm256, TB_ALIGN_32 },
+ { X86::VPMADDWDYrr, X86::VPMADDWDYrm, TB_ALIGN_32 },
+ { X86::VPMAXSWYrr, X86::VPMAXSWYrm, TB_ALIGN_32 },
+ { X86::VPMAXUBYrr, X86::VPMAXUBYrm, TB_ALIGN_32 },
+ { X86::VPMINSWYrr, X86::VPMINSWYrm, TB_ALIGN_32 },
+ { X86::VPMINUBYrr, X86::VPMINUBYrm, TB_ALIGN_32 },
+ { X86::VMPSADBWYrri, X86::VMPSADBWYrmi, TB_ALIGN_32 },
+ { X86::VPMULDQYrr, X86::VPMULDQYrm, TB_ALIGN_32 },
+ { X86::VPMULHRSWrr256, X86::VPMULHRSWrm256, TB_ALIGN_32 },
+ { X86::VPMULHUWYrr, X86::VPMULHUWYrm, TB_ALIGN_32 },
+ { X86::VPMULHWYrr, X86::VPMULHWYrm, TB_ALIGN_32 },
+ { X86::VPMULLDYrr, X86::VPMULLDYrm, TB_ALIGN_32 },
+ { X86::VPMULLWYrr, X86::VPMULLWYrm, TB_ALIGN_32 },
+ { X86::VPMULUDQYrr, X86::VPMULUDQYrm, TB_ALIGN_32 },
+ { X86::VPORYrr, X86::VPORYrm, TB_ALIGN_32 },
+ { X86::VPSADBWYrr, X86::VPSADBWYrm, TB_ALIGN_32 },
+ { X86::VPSHUFBYrr, X86::VPSHUFBYrm, TB_ALIGN_32 },
+ { X86::VPSIGNBYrr, X86::VPSIGNBYrm, TB_ALIGN_32 },
+ { X86::VPSIGNWYrr, X86::VPSIGNWYrm, TB_ALIGN_32 },
+ { X86::VPSIGNDYrr, X86::VPSIGNDYrm, TB_ALIGN_32 },
+ { X86::VPSLLDYrr, X86::VPSLLDYrm, TB_ALIGN_16 },
+ { X86::VPSLLQYrr, X86::VPSLLQYrm, TB_ALIGN_16 },
+ { X86::VPSLLWYrr, X86::VPSLLWYrm, TB_ALIGN_16 },
+ { X86::VPSLLVDrr, X86::VPSLLVDrm, TB_ALIGN_16 },
+ { X86::VPSLLVDYrr, X86::VPSLLVDYrm, TB_ALIGN_32 },
+ { X86::VPSLLVQrr, X86::VPSLLVQrm, TB_ALIGN_16 },
+ { X86::VPSLLVQYrr, X86::VPSLLVQYrm, TB_ALIGN_32 },
+ { X86::VPSRADYrr, X86::VPSRADYrm, TB_ALIGN_16 },
+ { X86::VPSRAWYrr, X86::VPSRAWYrm, TB_ALIGN_16 },
+ { X86::VPSRAVDrr, X86::VPSRAVDrm, TB_ALIGN_16 },
+ { X86::VPSRAVDYrr, X86::VPSRAVDYrm, TB_ALIGN_32 },
+ { X86::VPSRLDYrr, X86::VPSRLDYrm, TB_ALIGN_16 },
+ { X86::VPSRLQYrr, X86::VPSRLQYrm, TB_ALIGN_16 },
+ { X86::VPSRLWYrr, X86::VPSRLWYrm, TB_ALIGN_16 },
+ { X86::VPSRLVDrr, X86::VPSRLVDrm, TB_ALIGN_16 },
+ { X86::VPSRLVDYrr, X86::VPSRLVDYrm, TB_ALIGN_32 },
+ { X86::VPSRLVQrr, X86::VPSRLVQrm, TB_ALIGN_16 },
+ { X86::VPSRLVQYrr, X86::VPSRLVQYrm, TB_ALIGN_32 },
+ { X86::VPSUBBYrr, X86::VPSUBBYrm, TB_ALIGN_32 },
+ { X86::VPSUBDYrr, X86::VPSUBDYrm, TB_ALIGN_32 },
+ { X86::VPSUBSBYrr, X86::VPSUBSBYrm, TB_ALIGN_32 },
+ { X86::VPSUBSWYrr, X86::VPSUBSWYrm, TB_ALIGN_32 },
+ { X86::VPSUBWYrr, X86::VPSUBWYrm, TB_ALIGN_32 },
+ { X86::VPUNPCKHBWYrr, X86::VPUNPCKHBWYrm, TB_ALIGN_32 },
+ { X86::VPUNPCKHDQYrr, X86::VPUNPCKHDQYrm, TB_ALIGN_32 },
+ { X86::VPUNPCKHQDQYrr, X86::VPUNPCKHQDQYrm, TB_ALIGN_16 },
+ { X86::VPUNPCKHWDYrr, X86::VPUNPCKHWDYrm, TB_ALIGN_32 },
+ { X86::VPUNPCKLBWYrr, X86::VPUNPCKLBWYrm, TB_ALIGN_32 },
+ { X86::VPUNPCKLDQYrr, X86::VPUNPCKLDQYrm, TB_ALIGN_32 },
+ { X86::VPUNPCKLQDQYrr, X86::VPUNPCKLQDQYrm, TB_ALIGN_32 },
+ { X86::VPUNPCKLWDYrr, X86::VPUNPCKLWDYrm, TB_ALIGN_32 },
+ { X86::VPXORYrr, X86::VPXORYrm, TB_ALIGN_32 },
+ // FIXME: add AVX 256-bit foldable instructions
};
for (unsigned i = 0, e = array_lengthof(OpTbl2); i != e; ++i) {
- unsigned RegOp = OpTbl2[i][0];
- unsigned MemOp = OpTbl2[i][1] & ~TB_FLAGS;
- unsigned Align = OpTbl2[i][2];
-
- assert(!RegOp2MemOpTable2.count(RegOp) && "Duplicate entry!");
- RegOp2MemOpTable2[RegOp] = std::make_pair(MemOp, Align);
-
- // If this is not a reversable operation (because there is a many->one)
- // mapping, don't insert the reverse of the operation into MemOp2RegOpTable.
- if (OpTbl2[i][1] & TB_NOT_REVERSABLE)
- continue;
-
- // Index 2, folded load
- unsigned AuxInfo = 2 | (1 << 4);
- assert(!MemOp2RegOpTable.count(MemOp) &&
- "Duplicated entries in unfolding maps?");
- MemOp2RegOpTable[MemOp] = std::make_pair(RegOp, AuxInfo);
+ unsigned RegOp = OpTbl2[i].RegOp;
+ unsigned MemOp = OpTbl2[i].MemOp;
+ unsigned Flags = OpTbl2[i].Flags;
+ AddTableEntry(RegOp2MemOpTable2, MemOp2RegOpTable,
+ RegOp, MemOp,
+ // Index 2, folded load
+ Flags | TB_INDEX_2 | TB_FOLDED_LOAD);
+ }
+
+ static const X86OpTblEntry OpTbl3[] = {
+ // FMA foldable instructions
+ { X86::VFMADDSSr231r, X86::VFMADDSSr231m, 0 },
+ { X86::VFMADDSDr231r, X86::VFMADDSDr231m, 0 },
+ { X86::VFMADDSSr132r, X86::VFMADDSSr132m, 0 },
+ { X86::VFMADDSDr132r, X86::VFMADDSDr132m, 0 },
+ { X86::VFMADDSSr213r, X86::VFMADDSSr213m, 0 },
+ { X86::VFMADDSDr213r, X86::VFMADDSDr213m, 0 },
+ { X86::VFMADDSSr132r_Int, X86::VFMADDSSr132m_Int, 0 },
+ { X86::VFMADDSDr132r_Int, X86::VFMADDSDr132m_Int, 0 },
+
+ { X86::VFMADDPSr231r, X86::VFMADDPSr231m, TB_ALIGN_16 },
+ { X86::VFMADDPDr231r, X86::VFMADDPDr231m, TB_ALIGN_16 },
+ { X86::VFMADDPSr132r, X86::VFMADDPSr132m, TB_ALIGN_16 },
+ { X86::VFMADDPDr132r, X86::VFMADDPDr132m, TB_ALIGN_16 },
+ { X86::VFMADDPSr213r, X86::VFMADDPSr213m, TB_ALIGN_16 },
+ { X86::VFMADDPDr213r, X86::VFMADDPDr213m, TB_ALIGN_16 },
+ { X86::VFMADDPSr231rY, X86::VFMADDPSr231mY, TB_ALIGN_32 },
+ { X86::VFMADDPDr231rY, X86::VFMADDPDr231mY, TB_ALIGN_32 },
+ { X86::VFMADDPSr132rY, X86::VFMADDPSr132mY, TB_ALIGN_32 },
+ { X86::VFMADDPDr132rY, X86::VFMADDPDr132mY, TB_ALIGN_32 },
+ { X86::VFMADDPSr213rY, X86::VFMADDPSr213mY, TB_ALIGN_32 },
+ { X86::VFMADDPDr213rY, X86::VFMADDPDr213mY, TB_ALIGN_32 },
+ { X86::VFMADDPSr132r_Int, X86::VFMADDPSr132m_Int, TB_ALIGN_16 },
+ { X86::VFMADDPDr132r_Int, X86::VFMADDPDr132m_Int, TB_ALIGN_16 },
+ { X86::VFMADDPSr132rY_Int, X86::VFMADDPSr132mY_Int, TB_ALIGN_32 },
+ { X86::VFMADDPDr132rY_Int, X86::VFMADDPDr132mY_Int, TB_ALIGN_32 },
+
+ { X86::VFNMADDSSr231r, X86::VFNMADDSSr231m, 0 },
+ { X86::VFNMADDSDr231r, X86::VFNMADDSDr231m, 0 },
+ { X86::VFNMADDSSr132r, X86::VFNMADDSSr132m, 0 },
+ { X86::VFNMADDSDr132r, X86::VFNMADDSDr132m, 0 },
+ { X86::VFNMADDSSr213r, X86::VFNMADDSSr213m, 0 },
+ { X86::VFNMADDSDr213r, X86::VFNMADDSDr213m, 0 },
+ { X86::VFNMADDSSr132r_Int, X86::VFNMADDSSr132m_Int, 0 },
+ { X86::VFNMADDSDr132r_Int, X86::VFNMADDSDr132m_Int, 0 },
+
+ { X86::VFNMADDPSr231r, X86::VFNMADDPSr231m, TB_ALIGN_16 },
+ { X86::VFNMADDPDr231r, X86::VFNMADDPDr231m, TB_ALIGN_16 },
+ { X86::VFNMADDPSr132r, X86::VFNMADDPSr132m, TB_ALIGN_16 },
+ { X86::VFNMADDPDr132r, X86::VFNMADDPDr132m, TB_ALIGN_16 },
+ { X86::VFNMADDPSr213r, X86::VFNMADDPSr213m, TB_ALIGN_16 },
+ { X86::VFNMADDPDr213r, X86::VFNMADDPDr213m, TB_ALIGN_16 },
+ { X86::VFNMADDPSr231rY, X86::VFNMADDPSr231mY, TB_ALIGN_32 },
+ { X86::VFNMADDPDr231rY, X86::VFNMADDPDr231mY, TB_ALIGN_32 },
+ { X86::VFNMADDPSr132rY, X86::VFNMADDPSr132mY, TB_ALIGN_32 },
+ { X86::VFNMADDPDr132rY, X86::VFNMADDPDr132mY, TB_ALIGN_32 },
+ { X86::VFNMADDPSr213rY, X86::VFNMADDPSr213mY, TB_ALIGN_32 },
+ { X86::VFNMADDPDr213rY, X86::VFNMADDPDr213mY, TB_ALIGN_32 },
+ { X86::VFNMADDPSr132r_Int, X86::VFNMADDPSr132m_Int, TB_ALIGN_16 },
+ { X86::VFNMADDPDr132r_Int, X86::VFNMADDPDr132m_Int, TB_ALIGN_16 },
+ { X86::VFNMADDPSr132rY_Int, X86::VFNMADDPSr132mY_Int, TB_ALIGN_32 },
+ { X86::VFNMADDPDr132rY_Int, X86::VFNMADDPDr132mY_Int, TB_ALIGN_32 },
+
+ { X86::VFMSUBSSr231r, X86::VFMSUBSSr231m, 0 },
+ { X86::VFMSUBSDr231r, X86::VFMSUBSDr231m, 0 },
+ { X86::VFMSUBSSr132r, X86::VFMSUBSSr132m, 0 },
+ { X86::VFMSUBSDr132r, X86::VFMSUBSDr132m, 0 },
+ { X86::VFMSUBSSr213r, X86::VFMSUBSSr213m, 0 },
+ { X86::VFMSUBSDr213r, X86::VFMSUBSDr213m, 0 },
+ { X86::VFMSUBSSr132r_Int, X86::VFMSUBSSr132m_Int, 0 },
+ { X86::VFMSUBSDr132r_Int, X86::VFMSUBSDr132m_Int, 0 },
+
+ { X86::VFMSUBPSr231r, X86::VFMSUBPSr231m, TB_ALIGN_16 },
+ { X86::VFMSUBPDr231r, X86::VFMSUBPDr231m, TB_ALIGN_16 },
+ { X86::VFMSUBPSr132r, X86::VFMSUBPSr132m, TB_ALIGN_16 },
+ { X86::VFMSUBPDr132r, X86::VFMSUBPDr132m, TB_ALIGN_16 },
+ { X86::VFMSUBPSr213r, X86::VFMSUBPSr213m, TB_ALIGN_16 },
+ { X86::VFMSUBPDr213r, X86::VFMSUBPDr213m, TB_ALIGN_16 },
+ { X86::VFMSUBPSr231rY, X86::VFMSUBPSr231mY, TB_ALIGN_32 },
+ { X86::VFMSUBPDr231rY, X86::VFMSUBPDr231mY, TB_ALIGN_32 },
+ { X86::VFMSUBPSr132rY, X86::VFMSUBPSr132mY, TB_ALIGN_32 },
+ { X86::VFMSUBPDr132rY, X86::VFMSUBPDr132mY, TB_ALIGN_32 },
+ { X86::VFMSUBPSr213rY, X86::VFMSUBPSr213mY, TB_ALIGN_32 },
+ { X86::VFMSUBPDr213rY, X86::VFMSUBPDr213mY, TB_ALIGN_32 },
+ { X86::VFMSUBPSr132r_Int, X86::VFMSUBPSr132m_Int, TB_ALIGN_16 },
+ { X86::VFMSUBPDr132r_Int, X86::VFMSUBPDr132m_Int, TB_ALIGN_16 },
+ { X86::VFMSUBPSr132rY_Int, X86::VFMSUBPSr132mY_Int, TB_ALIGN_32 },
+ { X86::VFMSUBPDr132rY_Int, X86::VFMSUBPDr132mY_Int, TB_ALIGN_32 },
+
+ { X86::VFNMSUBSSr231r, X86::VFNMSUBSSr231m, 0 },
+ { X86::VFNMSUBSDr231r, X86::VFNMSUBSDr231m, 0 },
+ { X86::VFNMSUBSSr132r, X86::VFNMSUBSSr132m, 0 },
+ { X86::VFNMSUBSDr132r, X86::VFNMSUBSDr132m, 0 },
+ { X86::VFNMSUBSSr213r, X86::VFNMSUBSSr213m, 0 },
+ { X86::VFNMSUBSDr213r, X86::VFNMSUBSDr213m, 0 },
+ { X86::VFNMSUBSSr132r_Int, X86::VFNMSUBSSr132m_Int, 0 },
+ { X86::VFNMSUBSDr132r_Int, X86::VFNMSUBSDr132m_Int, 0 },
+
+ { X86::VFNMSUBPSr231r, X86::VFNMSUBPSr231m, TB_ALIGN_16 },
+ { X86::VFNMSUBPDr231r, X86::VFNMSUBPDr231m, TB_ALIGN_16 },
+ { X86::VFNMSUBPSr132r, X86::VFNMSUBPSr132m, TB_ALIGN_16 },
+ { X86::VFNMSUBPDr132r, X86::VFNMSUBPDr132m, TB_ALIGN_16 },
+ { X86::VFNMSUBPSr213r, X86::VFNMSUBPSr213m, TB_ALIGN_16 },
+ { X86::VFNMSUBPDr213r, X86::VFNMSUBPDr213m, TB_ALIGN_16 },
+ { X86::VFNMSUBPSr231rY, X86::VFNMSUBPSr231mY, TB_ALIGN_32 },
+ { X86::VFNMSUBPDr231rY, X86::VFNMSUBPDr231mY, TB_ALIGN_32 },
+ { X86::VFNMSUBPSr132rY, X86::VFNMSUBPSr132mY, TB_ALIGN_32 },
+ { X86::VFNMSUBPDr132rY, X86::VFNMSUBPDr132mY, TB_ALIGN_32 },
+ { X86::VFNMSUBPSr213rY, X86::VFNMSUBPSr213mY, TB_ALIGN_32 },
+ { X86::VFNMSUBPDr213rY, X86::VFNMSUBPDr213mY, TB_ALIGN_32 },
+ { X86::VFNMSUBPSr132r_Int, X86::VFNMSUBPSr132m_Int, TB_ALIGN_16 },
+ { X86::VFNMSUBPDr132r_Int, X86::VFNMSUBPDr132m_Int, TB_ALIGN_16 },
+ { X86::VFNMSUBPSr132rY_Int, X86::VFNMSUBPSr132mY_Int, TB_ALIGN_32 },
+ { X86::VFNMSUBPDr132rY_Int, X86::VFNMSUBPDr132mY_Int, TB_ALIGN_32 },
+
+ { X86::VFMADDSUBPSr231r, X86::VFMADDSUBPSr231m, TB_ALIGN_16 },
+ { X86::VFMADDSUBPDr231r, X86::VFMADDSUBPDr231m, TB_ALIGN_16 },
+ { X86::VFMADDSUBPSr132r, X86::VFMADDSUBPSr132m, TB_ALIGN_16 },
+ { X86::VFMADDSUBPDr132r, X86::VFMADDSUBPDr132m, TB_ALIGN_16 },
+ { X86::VFMADDSUBPSr213r, X86::VFMADDSUBPSr213m, TB_ALIGN_16 },
+ { X86::VFMADDSUBPDr213r, X86::VFMADDSUBPDr213m, TB_ALIGN_16 },
+ { X86::VFMADDSUBPSr231rY, X86::VFMADDSUBPSr231mY, TB_ALIGN_32 },
+ { X86::VFMADDSUBPDr231rY, X86::VFMADDSUBPDr231mY, TB_ALIGN_32 },
+ { X86::VFMADDSUBPSr132rY, X86::VFMADDSUBPSr132mY, TB_ALIGN_32 },
+ { X86::VFMADDSUBPDr132rY, X86::VFMADDSUBPDr132mY, TB_ALIGN_32 },
+ { X86::VFMADDSUBPSr213rY, X86::VFMADDSUBPSr213mY, TB_ALIGN_32 },
+ { X86::VFMADDSUBPDr213rY, X86::VFMADDSUBPDr213mY, TB_ALIGN_32 },
+ { X86::VFMADDSUBPSr132r_Int, X86::VFMADDSUBPSr132m_Int, TB_ALIGN_16 },
+ { X86::VFMADDSUBPDr132r_Int, X86::VFMADDSUBPDr132m_Int, TB_ALIGN_16 },
+ { X86::VFMADDSUBPSr132rY_Int, X86::VFMADDSUBPSr132mY_Int, TB_ALIGN_32 },
+ { X86::VFMADDSUBPDr132rY_Int, X86::VFMADDSUBPDr132mY_Int, TB_ALIGN_32 },
+
+ { X86::VFMSUBADDPSr231r, X86::VFMSUBADDPSr231m, TB_ALIGN_16 },
+ { X86::VFMSUBADDPDr231r, X86::VFMSUBADDPDr231m, TB_ALIGN_16 },
+ { X86::VFMSUBADDPSr132r, X86::VFMSUBADDPSr132m, TB_ALIGN_16 },
+ { X86::VFMSUBADDPDr132r, X86::VFMSUBADDPDr132m, TB_ALIGN_16 },
+ { X86::VFMSUBADDPSr213r, X86::VFMSUBADDPSr213m, TB_ALIGN_16 },
+ { X86::VFMSUBADDPDr213r, X86::VFMSUBADDPDr213m, TB_ALIGN_16 },
+ { X86::VFMSUBADDPSr231rY, X86::VFMSUBADDPSr231mY, TB_ALIGN_32 },
+ { X86::VFMSUBADDPDr231rY, X86::VFMSUBADDPDr231mY, TB_ALIGN_32 },
+ { X86::VFMSUBADDPSr132rY, X86::VFMSUBADDPSr132mY, TB_ALIGN_32 },
+ { X86::VFMSUBADDPDr132rY, X86::VFMSUBADDPDr132mY, TB_ALIGN_32 },
+ { X86::VFMSUBADDPSr213rY, X86::VFMSUBADDPSr213mY, TB_ALIGN_32 },
+ { X86::VFMSUBADDPDr213rY, X86::VFMSUBADDPDr213mY, TB_ALIGN_32 },
+ { X86::VFMSUBADDPSr132r_Int, X86::VFMSUBADDPSr132m_Int, TB_ALIGN_16 },
+ { X86::VFMSUBADDPDr132r_Int, X86::VFMSUBADDPDr132m_Int, TB_ALIGN_16 },
+ { X86::VFMSUBADDPSr132rY_Int, X86::VFMSUBADDPSr132mY_Int, TB_ALIGN_32 },
+ { X86::VFMSUBADDPDr132rY_Int, X86::VFMSUBADDPDr132mY_Int, TB_ALIGN_32 },
+ };
+
+ for (unsigned i = 0, e = array_lengthof(OpTbl3); i != e; ++i) {
+ unsigned RegOp = OpTbl3[i].RegOp;
+ unsigned MemOp = OpTbl3[i].MemOp;
+ unsigned Flags = OpTbl3[i].Flags;
+ AddTableEntry(RegOp2MemOpTable3, MemOp2RegOpTable,
+ RegOp, MemOp,
+ // Index 3, folded load
+ Flags | TB_INDEX_3 | TB_FOLDED_LOAD);
}
+
+}
+
+void
+X86InstrInfo::AddTableEntry(RegOp2MemOpTableType &R2MTable,
+ MemOp2RegOpTableType &M2RTable,
+ unsigned RegOp, unsigned MemOp, unsigned Flags) {
+ if ((Flags & TB_NO_FORWARD) == 0) {
+ assert(!R2MTable.count(RegOp) && "Duplicate entry!");
+ R2MTable[RegOp] = std::make_pair(MemOp, Flags);
+ }
+ if ((Flags & TB_NO_REVERSE) == 0) {
+ assert(!M2RTable.count(MemOp) &&
+ "Duplicated entries in unfolding maps?");
+ M2RTable[MemOp] = std::make_pair(RegOp, Flags);
+ }
}
bool
switch (MI.getOpcode()) {
default:
llvm_unreachable(0);
- break;
case X86::MOVSX16rr8:
case X86::MOVZX16rr8:
case X86::MOVSX32rr8:
static bool isFrameLoadOpcode(int Opcode) {
switch (Opcode) {
- default: break;
+ default:
+ return false;
case X86::MOV8rm:
case X86::MOV16rm:
case X86::MOV32rm:
case X86::MOVAPSrm:
case X86::MOVAPDrm:
case X86::MOVDQArm:
+ case X86::VMOVSSrm:
+ case X86::VMOVSDrm:
+ case X86::VMOVAPSrm:
+ case X86::VMOVAPDrm:
+ case X86::VMOVDQArm:
+ case X86::VMOVAPSYrm:
+ case X86::VMOVAPDYrm:
+ case X86::VMOVDQAYrm:
case X86::MMX_MOVD64rm:
case X86::MMX_MOVQ64rm:
return true;
- break;
}
- return false;
}
static bool isFrameStoreOpcode(int Opcode) {
case X86::MOVAPSmr:
case X86::MOVAPDmr:
case X86::MOVDQAmr:
+ case X86::VMOVSSmr:
+ case X86::VMOVSDmr:
+ case X86::VMOVAPSmr:
+ case X86::VMOVAPDmr:
+ case X86::VMOVDQAmr:
+ case X86::VMOVAPSYmr:
+ case X86::VMOVAPDYmr:
+ case X86::VMOVDQAYmr:
case X86::MMX_MOVD64mr:
case X86::MMX_MOVQ64mr:
case X86::MMX_MOVNTQmr:
return false;
}
-unsigned X86InstrInfo::isLoadFromStackSlot(const MachineInstr *MI,
+unsigned X86InstrInfo::isLoadFromStackSlot(const MachineInstr *MI,
int &FrameIndex) const {
if (isFrameLoadOpcode(MI->getOpcode()))
if (MI->getOperand(0).getSubReg() == 0 && isFrameOperand(MI, 1, FrameIndex))
return 0;
}
-unsigned X86InstrInfo::isLoadFromStackSlotPostFE(const MachineInstr *MI,
+unsigned X86InstrInfo::isLoadFromStackSlotPostFE(const MachineInstr *MI,
int &FrameIndex) const {
if (isFrameLoadOpcode(MI->getOpcode())) {
unsigned Reg;
return 0;
}
-bool X86InstrInfo::hasLoadFromStackSlot(const MachineInstr *MI,
- const MachineMemOperand *&MMO,
- int &FrameIndex) const {
- for (MachineInstr::mmo_iterator o = MI->memoperands_begin(),
- oe = MI->memoperands_end();
- o != oe;
- ++o) {
- if ((*o)->isLoad() && (*o)->getValue())
- if (const FixedStackPseudoSourceValue *Value =
- dyn_cast<const FixedStackPseudoSourceValue>((*o)->getValue())) {
- FrameIndex = Value->getFrameIndex();
- MMO = *o;
- return true;
- }
- }
- return false;
-}
-
unsigned X86InstrInfo::isStoreToStackSlot(const MachineInstr *MI,
int &FrameIndex) const {
if (isFrameStoreOpcode(MI->getOpcode()))
return 0;
}
-bool X86InstrInfo::hasStoreToStackSlot(const MachineInstr *MI,
- const MachineMemOperand *&MMO,
- int &FrameIndex) const {
- for (MachineInstr::mmo_iterator o = MI->memoperands_begin(),
- oe = MI->memoperands_end();
- o != oe;
- ++o) {
- if ((*o)->isStore() && (*o)->getValue())
- if (const FixedStackPseudoSourceValue *Value =
- dyn_cast<const FixedStackPseudoSourceValue>((*o)->getValue())) {
- FrameIndex = Value->getFrameIndex();
- MMO = *o;
- return true;
- }
- }
- return false;
-}
-
/// regIsPICBase - Return true if register is PIC base (i.e.g defined by
/// X86::MOVPC32r.
static bool regIsPICBase(unsigned BaseReg, const MachineRegisterInfo &MRI) {
case X86::MOVSDrm:
case X86::MOVAPSrm:
case X86::MOVUPSrm:
- case X86::MOVUPSrm_Int:
case X86::MOVAPDrm:
case X86::MOVDQArm:
+ case X86::VMOVSSrm:
+ case X86::VMOVSDrm:
+ case X86::VMOVAPSrm:
+ case X86::VMOVUPSrm:
+ case X86::VMOVAPDrm:
+ case X86::VMOVDQArm:
+ case X86::VMOVAPSYrm:
+ case X86::VMOVUPSYrm:
+ case X86::VMOVAPDYrm:
+ case X86::VMOVDQAYrm:
case X86::MMX_MOVD64rm:
case X86::MMX_MOVQ64rm:
+ case X86::FsVMOVAPSrm:
+ case X86::FsVMOVAPDrm:
case X86::FsMOVAPSrm:
case X86::FsMOVAPDrm: {
// Loads from constant pools are trivially rematerializable.
isPICBase = true;
}
return isPICBase;
- }
+ }
return false;
}
-
+
case X86::LEA32r:
case X86::LEA64r: {
if (MI->getOperand(2).isImm() &&
MachineBasicBlock::iterator I) {
MachineBasicBlock::iterator E = MBB.end();
- // It's always safe to clobber EFLAGS at the end of a block.
- if (I == E)
- return true;
-
// For compile time consideration, if we are not able to determine the
// safety after visiting 4 instructions in each direction, we will assume
// it's not safe.
MachineBasicBlock::iterator Iter = I;
- for (unsigned i = 0; i < 4; ++i) {
+ for (unsigned i = 0; Iter != E && i < 4; ++i) {
bool SeenDef = false;
for (unsigned j = 0, e = Iter->getNumOperands(); j != e; ++j) {
MachineOperand &MO = Iter->getOperand(j);
+ if (MO.isRegMask() && MO.clobbersPhysReg(X86::EFLAGS))
+ SeenDef = true;
if (!MO.isReg())
continue;
if (MO.getReg() == X86::EFLAGS) {
// Skip over DBG_VALUE.
while (Iter != E && Iter->isDebugValue())
++Iter;
+ }
- // If we make it to the end of the block, it's safe to clobber EFLAGS.
- if (Iter == E)
- return true;
+ // It is safe to clobber EFLAGS at the end of a block of no successor has it
+ // live in.
+ if (Iter == E) {
+ for (MachineBasicBlock::succ_iterator SI = MBB.succ_begin(),
+ SE = MBB.succ_end(); SI != SE; ++SI)
+ if ((*SI)->isLiveIn(X86::EFLAGS))
+ return false;
+ return true;
}
MachineBasicBlock::iterator B = MBB.begin();
bool SawKill = false;
for (unsigned j = 0, e = Iter->getNumOperands(); j != e; ++j) {
MachineOperand &MO = Iter->getOperand(j);
+ // A register mask may clobber EFLAGS, but we should still look for a
+ // live EFLAGS def.
+ if (MO.isRegMask() && MO.clobbersPhysReg(X86::EFLAGS))
+ SawKill = true;
if (MO.isReg() && MO.getReg() == X86::EFLAGS) {
if (MO.isDef()) return MO.isDead();
if (MO.isKill()) SawKill = true;
MachineRegisterInfo &RegInfo = MFI->getParent()->getRegInfo();
unsigned leaInReg = RegInfo.createVirtualRegister(&X86::GR32_NOSPRegClass);
unsigned leaOutReg = RegInfo.createVirtualRegister(&X86::GR32RegClass);
-
+
// Build and insert into an implicit UNDEF value. This is OK because
- // well be shifting and then extracting the lower 16-bits.
+ // well be shifting and then extracting the lower 16-bits.
// This has the potential to cause partial register stall. e.g.
// movw (%rbp,%rcx,2), %dx
// leal -65(%rdx), %esi
switch (MIOpc) {
default:
llvm_unreachable(0);
- break;
case X86::SHL16ri: {
unsigned ShAmt = MI->getOperand(2).getImm();
MIB.addReg(0).addImm(1 << ShAmt)
case X86::ADD16ri8:
case X86::ADD16ri_DB:
case X86::ADD16ri8_DB:
- addRegOffset(MIB, leaInReg, true, MI->getOperand(2).getImm());
+ addRegOffset(MIB, leaInReg, true, MI->getOperand(2).getImm());
break;
case X86::ADD16rr:
case X86::ADD16rr_DB: {
} else {
leaInReg2 = RegInfo.createVirtualRegister(&X86::GR32_NOSPRegClass);
// Build and insert into an implicit UNDEF value. This is OK because
- // well be shifting and then extracting the lower 16-bits.
- BuildMI(*MFI, MIB, MI->getDebugLoc(), get(X86::IMPLICIT_DEF), leaInReg2);
+ // well be shifting and then extracting the lower 16-bits.
+ BuildMI(*MFI, &*MIB, MI->getDebugLoc(), get(X86::IMPLICIT_DEF),leaInReg2);
InsMI2 =
- BuildMI(*MFI, MIB, MI->getDebugLoc(), get(TargetOpcode::COPY))
+ BuildMI(*MFI, &*MIB, MI->getDebugLoc(), get(TargetOpcode::COPY))
.addReg(leaInReg2, RegState::Define, X86::sub_16bit)
.addReg(Src2, getKillRegState(isKill2));
addRegReg(MIB, leaInReg, true, leaInReg2, true);
case X86::SHUFPSrri: {
assert(MI->getNumOperands() == 4 && "Unknown shufps instruction!");
if (!TM.getSubtarget<X86Subtarget>().hasSSE2()) return 0;
-
+
unsigned B = MI->getOperand(1).getReg();
unsigned C = MI->getOperand(2).getReg();
if (B != C) return 0;
.addReg(B, getKillRegState(isKill)).addImm(M);
break;
}
+ case X86::SHUFPDrri: {
+ assert(MI->getNumOperands() == 4 && "Unknown shufpd instruction!");
+ if (!TM.getSubtarget<X86Subtarget>().hasSSE2()) return 0;
+
+ unsigned B = MI->getOperand(1).getReg();
+ unsigned C = MI->getOperand(2).getReg();
+ if (B != C) return 0;
+ unsigned A = MI->getOperand(0).getReg();
+ unsigned M = MI->getOperand(3).getImm();
+
+ // Convert to PSHUFD mask.
+ M = ((M & 1) << 1) | ((M & 1) << 3) | ((M & 2) << 4) | ((M & 2) << 6)| 0x44;
+
+ NewMI = BuildMI(MF, MI->getDebugLoc(), get(X86::PSHUFDri))
+ .addReg(A, RegState::Define | getDeadRegState(isDead))
+ .addReg(B, getKillRegState(isKill)).addImm(M);
+ break;
+ }
case X86::SHL64ri: {
assert(MI->getNumOperands() >= 3 && "Unknown shift instruction!");
// NOTE: LEA doesn't produce flags like shift does, but LLVM never uses
assert(MI->getNumOperands() >= 2 && "Unknown inc instruction!");
unsigned Opc = MIOpc == X86::INC64r ? X86::LEA64r
: (is64Bit ? X86::LEA64_32r : X86::LEA32r);
+ const TargetRegisterClass *RC = MIOpc == X86::INC64r ?
+ (const TargetRegisterClass*)&X86::GR64_NOSPRegClass :
+ (const TargetRegisterClass*)&X86::GR32_NOSPRegClass;
// LEA can't handle RSP.
if (TargetRegisterInfo::isVirtualRegister(Src) &&
- !MF.getRegInfo().constrainRegClass(Src,
- MIOpc == X86::INC64r ? X86::GR64_NOSPRegisterClass :
- X86::GR32_NOSPRegisterClass))
+ !MF.getRegInfo().constrainRegClass(Src, RC))
return 0;
NewMI = addRegOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
assert(MI->getNumOperands() >= 2 && "Unknown dec instruction!");
unsigned Opc = MIOpc == X86::DEC64r ? X86::LEA64r
: (is64Bit ? X86::LEA64_32r : X86::LEA32r);
+ const TargetRegisterClass *RC = MIOpc == X86::DEC64r ?
+ (const TargetRegisterClass*)&X86::GR64_NOSPRegClass :
+ (const TargetRegisterClass*)&X86::GR32_NOSPRegClass;
// LEA can't handle RSP.
if (TargetRegisterInfo::isVirtualRegister(Src) &&
- !MF.getRegInfo().constrainRegClass(Src,
- MIOpc == X86::DEC64r ? X86::GR64_NOSPRegisterClass :
- X86::GR32_NOSPRegisterClass))
+ !MF.getRegInfo().constrainRegClass(Src, RC))
return 0;
NewMI = addRegOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
case X86::ADD32rr_DB: {
assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
unsigned Opc;
- TargetRegisterClass *RC;
+ const TargetRegisterClass *RC;
if (MIOpc == X86::ADD64rr || MIOpc == X86::ADD64rr_DB) {
Opc = X86::LEA64r;
- RC = X86::GR64_NOSPRegisterClass;
+ RC = &X86::GR64_NOSPRegClass;
} else {
Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
- RC = X86::GR32_NOSPRegisterClass;
+ RC = &X86::GR32_NOSPRegClass;
}
-
+
unsigned Src2 = MI->getOperand(2).getReg();
bool isKill2 = MI->getOperand(2).isKill();
LV->replaceKillInstruction(Dest, MI, NewMI);
}
- MFI->insert(MBBI, NewMI); // Insert the new inst
+ MFI->insert(MBBI, NewMI); // Insert the new inst
return NewMI;
}
}
}
+/// getCMovFromCond - Return a cmov(rr) opcode for the given condition and
+/// register size in bytes.
+static unsigned getCMovFromCond(X86::CondCode CC, unsigned RegBytes) {
+ static const unsigned Opc[16][3] = {
+ { X86::CMOVA16rr, X86::CMOVA32rr, X86::CMOVA64rr },
+ { X86::CMOVAE16rr, X86::CMOVAE32rr, X86::CMOVAE64rr },
+ { X86::CMOVB16rr, X86::CMOVB32rr, X86::CMOVB64rr },
+ { X86::CMOVBE16rr, X86::CMOVBE32rr, X86::CMOVBE64rr },
+ { X86::CMOVE16rr, X86::CMOVE32rr, X86::CMOVE64rr },
+ { X86::CMOVG16rr, X86::CMOVG32rr, X86::CMOVG64rr },
+ { X86::CMOVGE16rr, X86::CMOVGE32rr, X86::CMOVGE64rr },
+ { X86::CMOVL16rr, X86::CMOVL32rr, X86::CMOVL64rr },
+ { X86::CMOVLE16rr, X86::CMOVLE32rr, X86::CMOVLE64rr },
+ { X86::CMOVNE16rr, X86::CMOVNE32rr, X86::CMOVNE64rr },
+ { X86::CMOVNO16rr, X86::CMOVNO32rr, X86::CMOVNO64rr },
+ { X86::CMOVNP16rr, X86::CMOVNP32rr, X86::CMOVNP64rr },
+ { X86::CMOVNS16rr, X86::CMOVNS32rr, X86::CMOVNS64rr },
+ { X86::CMOVO16rr, X86::CMOVO32rr, X86::CMOVO64rr },
+ { X86::CMOVP16rr, X86::CMOVP32rr, X86::CMOVP64rr },
+ { X86::CMOVS16rr, X86::CMOVS32rr, X86::CMOVS64rr }
+ };
+
+ assert(CC < 16 && "Can only handle standard cond codes");
+ switch(RegBytes) {
+ default: llvm_unreachable("Illegal register size!");
+ case 2: return Opc[CC][0];
+ case 4: return Opc[CC][1];
+ case 8: return Opc[CC][2];
+ }
+}
+
bool X86InstrInfo::isUnpredicatedTerminator(const MachineInstr *MI) const {
- const TargetInstrDesc &TID = MI->getDesc();
- if (!TID.isTerminator()) return false;
-
+ if (!MI->isTerminator()) return false;
+
// Conditional branch is a special case.
- if (TID.isBranch() && !TID.isBarrier())
+ if (MI->isBranch() && !MI->isBarrier())
return true;
- if (!TID.isPredicable())
+ if (!MI->isPredicable())
return true;
return !isPredicated(MI);
}
-bool X86InstrInfo::AnalyzeBranch(MachineBasicBlock &MBB,
+bool X86InstrInfo::AnalyzeBranch(MachineBasicBlock &MBB,
MachineBasicBlock *&TBB,
MachineBasicBlock *&FBB,
SmallVectorImpl<MachineOperand> &Cond,
// A terminator that isn't a branch can't easily be handled by this
// analysis.
- if (!I->getDesc().isBranch())
+ if (!I->isBranch())
return true;
// Handle unconditional branches.
.addMBB(UnCondBrIter->getOperand(0).getMBB());
BuildMI(MBB, UnCondBrIter, MBB.findDebugLoc(I), get(X86::JMP_4))
.addMBB(TargetBB);
- MBB.addSuccessor(TargetBB);
OldInst->eraseFromParent();
UnCondBrIter->eraseFromParent();
I = MBB.end();
++Count;
}
-
+
return Count;
}
return Count;
}
+bool X86InstrInfo::
+canInsertSelect(const MachineBasicBlock &MBB,
+ const SmallVectorImpl<MachineOperand> &Cond,
+ unsigned TrueReg, unsigned FalseReg,
+ int &CondCycles, int &TrueCycles, int &FalseCycles) const {
+ // Not all subtargets have cmov instructions.
+ if (!TM.getSubtarget<X86Subtarget>().hasCMov())
+ return false;
+ if (Cond.size() != 1)
+ return false;
+ // We cannot do the composite conditions, at least not in SSA form.
+ if ((X86::CondCode)Cond[0].getImm() > X86::COND_S)
+ return false;
+
+ // Check register classes.
+ const MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
+ const TargetRegisterClass *RC =
+ RI.getCommonSubClass(MRI.getRegClass(TrueReg), MRI.getRegClass(FalseReg));
+ if (!RC)
+ return false;
+
+ // We have cmov instructions for 16, 32, and 64 bit general purpose registers.
+ if (X86::GR16RegClass.hasSubClassEq(RC) ||
+ X86::GR32RegClass.hasSubClassEq(RC) ||
+ X86::GR64RegClass.hasSubClassEq(RC)) {
+ // This latency applies to Pentium M, Merom, Wolfdale, Nehalem, and Sandy
+ // Bridge. Probably Ivy Bridge as well.
+ CondCycles = 2;
+ TrueCycles = 2;
+ FalseCycles = 2;
+ return true;
+ }
+
+ // Can't do vectors.
+ return false;
+}
+
+void X86InstrInfo::insertSelect(MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator I, DebugLoc DL,
+ unsigned DstReg,
+ const SmallVectorImpl<MachineOperand> &Cond,
+ unsigned TrueReg, unsigned FalseReg) const {
+ MachineRegisterInfo &MRI = MBB.getParent()->getRegInfo();
+ assert(Cond.size() == 1 && "Invalid Cond array");
+ unsigned Opc = getCMovFromCond((X86::CondCode)Cond[0].getImm(),
+ MRI.getRegClass(DstReg)->getSize());
+ BuildMI(MBB, I, DL, get(Opc), DstReg).addReg(FalseReg).addReg(TrueReg);
+}
+
/// isHReg - Test if the given register is a physical h register.
static bool isHReg(unsigned Reg) {
return X86::GR8_ABCD_HRegClass.contains(Reg);
}
// Try and copy between VR128/VR64 and GR64 registers.
-static unsigned CopyToFromAsymmetricReg(unsigned DestReg, unsigned SrcReg) {
+static unsigned CopyToFromAsymmetricReg(unsigned DestReg, unsigned SrcReg,
+ bool HasAVX) {
// SrcReg(VR128) -> DestReg(GR64)
// SrcReg(VR64) -> DestReg(GR64)
// SrcReg(GR64) -> DestReg(VR128)
if (X86::GR64RegClass.contains(DestReg)) {
if (X86::VR128RegClass.contains(SrcReg)) {
// Copy from a VR128 register to a GR64 register.
- return X86::MOVPQIto64rr;
+ return HasAVX ? X86::VMOVPQIto64rr : X86::MOVPQIto64rr;
} else if (X86::VR64RegClass.contains(SrcReg)) {
// Copy from a VR64 register to a GR64 register.
return X86::MOVSDto64rr;
} else if (X86::GR64RegClass.contains(SrcReg)) {
// Copy from a GR64 register to a VR128 register.
if (X86::VR128RegClass.contains(DestReg))
- return X86::MOV64toPQIrr;
+ return HasAVX ? X86::VMOV64toPQIrr : X86::MOV64toPQIrr;
// Copy from a GR64 register to a VR64 register.
else if (X86::VR64RegClass.contains(DestReg))
return X86::MOV64toSDrr;
}
+ // SrcReg(FR32) -> DestReg(GR32)
+ // SrcReg(GR32) -> DestReg(FR32)
+
+ if (X86::GR32RegClass.contains(DestReg) && X86::FR32RegClass.contains(SrcReg))
+ // Copy from a FR32 register to a GR32 register.
+ return HasAVX ? X86::VMOVSS2DIrr : X86::MOVSS2DIrr;
+
+ if (X86::FR32RegClass.contains(DestReg) && X86::GR32RegClass.contains(SrcReg))
+ // Copy from a GR32 register to a FR32 register.
+ return HasAVX ? X86::VMOVDI2SSrr : X86::MOVDI2SSrr;
+
return 0;
}
unsigned DestReg, unsigned SrcReg,
bool KillSrc) const {
// First deal with the normal symmetric copies.
+ bool HasAVX = TM.getSubtarget<X86Subtarget>().hasAVX();
unsigned Opc = 0;
if (X86::GR64RegClass.contains(DestReg, SrcReg))
Opc = X86::MOV64rr;
// Copying to or from a physical H register on x86-64 requires a NOREX
// move. Otherwise use a normal move.
if ((isHReg(DestReg) || isHReg(SrcReg)) &&
- TM.getSubtarget<X86Subtarget>().is64Bit())
+ TM.getSubtarget<X86Subtarget>().is64Bit()) {
Opc = X86::MOV8rr_NOREX;
- else
+ // Both operands must be encodable without an REX prefix.
+ assert(X86::GR8_NOREXRegClass.contains(SrcReg, DestReg) &&
+ "8-bit H register can not be copied outside GR8_NOREX");
+ } else
Opc = X86::MOV8rr;
} else if (X86::VR128RegClass.contains(DestReg, SrcReg))
- Opc = X86::MOVAPSrr;
+ Opc = HasAVX ? X86::VMOVAPSrr : X86::MOVAPSrr;
+ else if (X86::VR256RegClass.contains(DestReg, SrcReg))
+ Opc = X86::VMOVAPSYrr;
else if (X86::VR64RegClass.contains(DestReg, SrcReg))
Opc = X86::MMX_MOVQ64rr;
else
- Opc = CopyToFromAsymmetricReg(DestReg, SrcReg);
+ Opc = CopyToFromAsymmetricReg(DestReg, SrcReg, HasAVX);
if (Opc) {
BuildMI(MBB, MI, DL, get(Opc), DestReg)
bool isStackAligned,
const TargetMachine &TM,
bool load) {
- switch (RC->getID()) {
+ bool HasAVX = TM.getSubtarget<X86Subtarget>().hasAVX();
+ switch (RC->getSize()) {
default:
- llvm_unreachable("Unknown regclass");
- case X86::GR64RegClassID:
- case X86::GR64_ABCDRegClassID:
- case X86::GR64_NOREXRegClassID:
- case X86::GR64_NOREX_NOSPRegClassID:
- case X86::GR64_NOSPRegClassID:
- case X86::GR64_TCRegClassID:
- return load ? X86::MOV64rm : X86::MOV64mr;
- case X86::GR32RegClassID:
- case X86::GR32_ABCDRegClassID:
- case X86::GR32_ADRegClassID:
- case X86::GR32_NOREXRegClassID:
- case X86::GR32_NOSPRegClassID:
- case X86::GR32_TCRegClassID:
- return load ? X86::MOV32rm : X86::MOV32mr;
- case X86::GR16RegClassID:
- case X86::GR16_ABCDRegClassID:
- case X86::GR16_NOREXRegClassID:
- return load ? X86::MOV16rm : X86::MOV16mr;
- case X86::GR8RegClassID:
- // Copying to or from a physical H register on x86-64 requires a NOREX
- // move. Otherwise use a normal move.
- if (isHReg(Reg) &&
- TM.getSubtarget<X86Subtarget>().is64Bit())
- return load ? X86::MOV8rm_NOREX : X86::MOV8mr_NOREX;
- else
- return load ? X86::MOV8rm : X86::MOV8mr;
- case X86::GR8_ABCD_LRegClassID:
- case X86::GR8_NOREXRegClassID:
- return load ? X86::MOV8rm :X86::MOV8mr;
- case X86::GR8_ABCD_HRegClassID:
+ llvm_unreachable("Unknown spill size");
+ case 1:
+ assert(X86::GR8RegClass.hasSubClassEq(RC) && "Unknown 1-byte regclass");
if (TM.getSubtarget<X86Subtarget>().is64Bit())
- return load ? X86::MOV8rm_NOREX : X86::MOV8mr_NOREX;
- else
- return load ? X86::MOV8rm : X86::MOV8mr;
- case X86::RFP80RegClassID:
+ // Copying to or from a physical H register on x86-64 requires a NOREX
+ // move. Otherwise use a normal move.
+ if (isHReg(Reg) || X86::GR8_ABCD_HRegClass.hasSubClassEq(RC))
+ return load ? X86::MOV8rm_NOREX : X86::MOV8mr_NOREX;
+ return load ? X86::MOV8rm : X86::MOV8mr;
+ case 2:
+ assert(X86::GR16RegClass.hasSubClassEq(RC) && "Unknown 2-byte regclass");
+ return load ? X86::MOV16rm : X86::MOV16mr;
+ case 4:
+ if (X86::GR32RegClass.hasSubClassEq(RC))
+ return load ? X86::MOV32rm : X86::MOV32mr;
+ if (X86::FR32RegClass.hasSubClassEq(RC))
+ return load ?
+ (HasAVX ? X86::VMOVSSrm : X86::MOVSSrm) :
+ (HasAVX ? X86::VMOVSSmr : X86::MOVSSmr);
+ if (X86::RFP32RegClass.hasSubClassEq(RC))
+ return load ? X86::LD_Fp32m : X86::ST_Fp32m;
+ llvm_unreachable("Unknown 4-byte regclass");
+ case 8:
+ if (X86::GR64RegClass.hasSubClassEq(RC))
+ return load ? X86::MOV64rm : X86::MOV64mr;
+ if (X86::FR64RegClass.hasSubClassEq(RC))
+ return load ?
+ (HasAVX ? X86::VMOVSDrm : X86::MOVSDrm) :
+ (HasAVX ? X86::VMOVSDmr : X86::MOVSDmr);
+ if (X86::VR64RegClass.hasSubClassEq(RC))
+ return load ? X86::MMX_MOVQ64rm : X86::MMX_MOVQ64mr;
+ if (X86::RFP64RegClass.hasSubClassEq(RC))
+ return load ? X86::LD_Fp64m : X86::ST_Fp64m;
+ llvm_unreachable("Unknown 8-byte regclass");
+ case 10:
+ assert(X86::RFP80RegClass.hasSubClassEq(RC) && "Unknown 10-byte regclass");
return load ? X86::LD_Fp80m : X86::ST_FpP80m;
- case X86::RFP64RegClassID:
- return load ? X86::LD_Fp64m : X86::ST_Fp64m;
- case X86::RFP32RegClassID:
- return load ? X86::LD_Fp32m : X86::ST_Fp32m;
- case X86::FR32RegClassID:
- return load ? X86::MOVSSrm : X86::MOVSSmr;
- case X86::FR64RegClassID:
- return load ? X86::MOVSDrm : X86::MOVSDmr;
- case X86::VR128RegClassID:
+ case 16: {
+ assert(X86::VR128RegClass.hasSubClassEq(RC) && "Unknown 16-byte regclass");
+ // If stack is realigned we can use aligned stores.
+ if (isStackAligned)
+ return load ?
+ (HasAVX ? X86::VMOVAPSrm : X86::MOVAPSrm) :
+ (HasAVX ? X86::VMOVAPSmr : X86::MOVAPSmr);
+ else
+ return load ?
+ (HasAVX ? X86::VMOVUPSrm : X86::MOVUPSrm) :
+ (HasAVX ? X86::VMOVUPSmr : X86::MOVUPSmr);
+ }
+ case 32:
+ assert(X86::VR256RegClass.hasSubClassEq(RC) && "Unknown 32-byte regclass");
// If stack is realigned we can use aligned stores.
if (isStackAligned)
- return load ? X86::MOVAPSrm : X86::MOVAPSmr;
+ return load ? X86::VMOVAPSYrm : X86::VMOVAPSYmr;
else
- return load ? X86::MOVUPSrm : X86::MOVUPSmr;
- case X86::VR64RegClassID:
- return load ? X86::MMX_MOVQ64rm : X86::MMX_MOVQ64mr;
+ return load ? X86::VMOVUPSYrm : X86::VMOVUPSYmr;
}
}
const MachineFunction &MF = *MBB.getParent();
assert(MF.getFrameInfo()->getObjectSize(FrameIdx) >= RC->getSize() &&
"Stack slot too small for store");
- bool isAligned = (RI.getStackAlignment() >= 16) || RI.canRealignStack(MF);
+ unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
+ bool isAligned = (TM.getFrameLowering()->getStackAlignment() >= Alignment) ||
+ RI.canRealignStack(MF);
unsigned Opc = getStoreRegOpcode(SrcReg, RC, isAligned, TM);
DebugLoc DL = MBB.findDebugLoc(MI);
addFrameReference(BuildMI(MBB, MI, DL, get(Opc)), FrameIdx)
MachineInstr::mmo_iterator MMOBegin,
MachineInstr::mmo_iterator MMOEnd,
SmallVectorImpl<MachineInstr*> &NewMIs) const {
- bool isAligned = MMOBegin != MMOEnd && (*MMOBegin)->getAlignment() >= 16;
+ unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
+ bool isAligned = MMOBegin != MMOEnd &&
+ (*MMOBegin)->getAlignment() >= Alignment;
unsigned Opc = getStoreRegOpcode(SrcReg, RC, isAligned, TM);
DebugLoc DL;
MachineInstrBuilder MIB = BuildMI(MF, DL, get(Opc));
const TargetRegisterClass *RC,
const TargetRegisterInfo *TRI) const {
const MachineFunction &MF = *MBB.getParent();
- bool isAligned = (RI.getStackAlignment() >= 16) || RI.canRealignStack(MF);
+ unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
+ bool isAligned = (TM.getFrameLowering()->getStackAlignment() >= Alignment) ||
+ RI.canRealignStack(MF);
unsigned Opc = getLoadRegOpcode(DestReg, RC, isAligned, TM);
DebugLoc DL = MBB.findDebugLoc(MI);
addFrameReference(BuildMI(MBB, MI, DL, get(Opc), DestReg), FrameIdx);
MachineInstr::mmo_iterator MMOBegin,
MachineInstr::mmo_iterator MMOEnd,
SmallVectorImpl<MachineInstr*> &NewMIs) const {
- bool isAligned = MMOBegin != MMOEnd && (*MMOBegin)->getAlignment() >= 16;
+ unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
+ bool isAligned = MMOBegin != MMOEnd &&
+ (*MMOBegin)->getAlignment() >= Alignment;
unsigned Opc = getLoadRegOpcode(DestReg, RC, isAligned, TM);
DebugLoc DL;
MachineInstrBuilder MIB = BuildMI(MF, DL, get(Opc), DestReg);
NewMIs.push_back(MIB);
}
-bool X86InstrInfo::spillCalleeSavedRegisters(MachineBasicBlock &MBB,
- MachineBasicBlock::iterator MI,
- const std::vector<CalleeSavedInfo> &CSI,
- const TargetRegisterInfo *TRI) const {
- if (CSI.empty())
- return false;
+bool X86InstrInfo::
+analyzeCompare(const MachineInstr *MI, unsigned &SrcReg, unsigned &SrcReg2,
+ int &CmpMask, int &CmpValue) const {
+ switch (MI->getOpcode()) {
+ default: break;
+ case X86::CMP64ri32:
+ case X86::CMP64ri8:
+ case X86::CMP32ri:
+ case X86::CMP32ri8:
+ case X86::CMP16ri:
+ case X86::CMP16ri8:
+ case X86::CMP8ri:
+ SrcReg = MI->getOperand(0).getReg();
+ SrcReg2 = 0;
+ CmpMask = ~0;
+ CmpValue = MI->getOperand(1).getImm();
+ return true;
+ case X86::CMP64rr:
+ case X86::CMP32rr:
+ case X86::CMP16rr:
+ case X86::CMP8rr:
+ SrcReg = MI->getOperand(0).getReg();
+ SrcReg2 = MI->getOperand(1).getReg();
+ CmpMask = ~0;
+ CmpValue = 0;
+ return true;
+ }
+ return false;
+}
- DebugLoc DL = MBB.findDebugLoc(MI);
+/// getSwappedConditionForSET - assume the flags are set by MI(a,b), return
+/// the opcode if we modify the instructions such that flags are
+/// set by MI(b,a).
+static unsigned getSwappedConditionForSET(unsigned SETOpc) {
+ switch (SETOpc) {
+ default: return 0;
+ case X86::SETEr: return X86::SETEr;
+ case X86::SETEm: return X86::SETEm;
+ case X86::SETNEr: return X86::SETNEr;
+ case X86::SETNEm: return X86::SETNEm;
+ case X86::SETLr: return X86::SETGr;
+ case X86::SETLm: return X86::SETGm;
+ case X86::SETLEr: return X86::SETGEr;
+ case X86::SETLEm: return X86::SETGEm;
+ case X86::SETGr: return X86::SETLr;
+ case X86::SETGm: return X86::SETLm;
+ case X86::SETGEr: return X86::SETLEr;
+ case X86::SETGEm: return X86::SETLEm;
+ case X86::SETBr: return X86::SETAr;
+ case X86::SETBm: return X86::SETAm;
+ case X86::SETBEr: return X86::SETAEr;
+ case X86::SETBEm: return X86::SETAEm;
+ case X86::SETAr: return X86::SETBr;
+ case X86::SETAm: return X86::SETBm;
+ case X86::SETAEr: return X86::SETBEr;
+ case X86::SETAEm: return X86::SETBEm;
+ }
+}
- bool is64Bit = TM.getSubtarget<X86Subtarget>().is64Bit();
- bool isWin64 = TM.getSubtarget<X86Subtarget>().isTargetWin64();
- unsigned SlotSize = is64Bit ? 8 : 4;
+/// getSwappedConditionForBranch - assume the flags are set by MI(a,b), return
+/// the opcode if we modify the instructions such that flags are
+/// set by MI(b,a).
+static unsigned getSwappedConditionForBranch(unsigned BranchOpc) {
+ switch (BranchOpc) {
+ default: return 0;
+ case X86::JE_4: return X86::JE_4;
+ case X86::JNE_4: return X86::JNE_4;
+ case X86::JL_4: return X86::JG_4;
+ case X86::JLE_4: return X86::JGE_4;
+ case X86::JG_4: return X86::JL_4;
+ case X86::JGE_4: return X86::JLE_4;
+ case X86::JB_4: return X86::JA_4;
+ case X86::JBE_4: return X86::JAE_4;
+ case X86::JA_4: return X86::JB_4;
+ case X86::JAE_4: return X86::JBE_4;
+ }
+}
- MachineFunction &MF = *MBB.getParent();
- unsigned FPReg = RI.getFrameRegister(MF);
- X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
- unsigned CalleeFrameSize = 0;
-
- unsigned Opc = is64Bit ? X86::PUSH64r : X86::PUSH32r;
- for (unsigned i = CSI.size(); i != 0; --i) {
- unsigned Reg = CSI[i-1].getReg();
- // Add the callee-saved register as live-in. It's killed at the spill.
- MBB.addLiveIn(Reg);
- if (Reg == FPReg)
- // X86RegisterInfo::emitPrologue will handle spilling of frame register.
- continue;
- if (!X86::VR128RegClass.contains(Reg) && !isWin64) {
- CalleeFrameSize += SlotSize;
- BuildMI(MBB, MI, DL, get(Opc)).addReg(Reg, RegState::Kill);
- } else {
- const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
- storeRegToStackSlot(MBB, MI, Reg, true, CSI[i-1].getFrameIdx(),
- RC, &RI);
- }
+/// getSwappedConditionForCMov - assume the flags are set by MI(a,b), return
+/// the opcode if we modify the instructions such that flags are
+/// set by MI(b,a).
+static unsigned getSwappedConditionForCMov(unsigned CMovOpc) {
+ switch (CMovOpc) {
+ default: return 0;
+ case X86::CMOVE16rm: return X86::CMOVE16rm;
+ case X86::CMOVE16rr: return X86::CMOVE16rr;
+ case X86::CMOVE32rm: return X86::CMOVE32rm;
+ case X86::CMOVE32rr: return X86::CMOVE32rr;
+ case X86::CMOVE64rm: return X86::CMOVE64rm;
+ case X86::CMOVE64rr: return X86::CMOVE64rr;
+ case X86::CMOVNE16rm: return X86::CMOVNE16rm;
+ case X86::CMOVNE16rr: return X86::CMOVNE16rr;
+ case X86::CMOVNE32rm: return X86::CMOVNE32rm;
+ case X86::CMOVNE32rr: return X86::CMOVNE32rr;
+ case X86::CMOVNE64rm: return X86::CMOVNE64rm;
+ case X86::CMOVNE64rr: return X86::CMOVNE64rr;
+
+ case X86::CMOVL16rm: return X86::CMOVG16rm;
+ case X86::CMOVL16rr: return X86::CMOVG16rr;
+ case X86::CMOVL32rm: return X86::CMOVG32rm;
+ case X86::CMOVL32rr: return X86::CMOVG32rr;
+ case X86::CMOVL64rm: return X86::CMOVG64rm;
+ case X86::CMOVL64rr: return X86::CMOVG64rr;
+ case X86::CMOVLE16rm: return X86::CMOVGE16rm;
+ case X86::CMOVLE16rr: return X86::CMOVGE16rr;
+ case X86::CMOVLE32rm: return X86::CMOVGE32rm;
+ case X86::CMOVLE32rr: return X86::CMOVGE32rr;
+ case X86::CMOVLE64rm: return X86::CMOVGE64rm;
+ case X86::CMOVLE64rr: return X86::CMOVGE64rr;
+
+ case X86::CMOVG16rm: return X86::CMOVL16rm;
+ case X86::CMOVG16rr: return X86::CMOVL16rr;
+ case X86::CMOVG32rm: return X86::CMOVL32rm;
+ case X86::CMOVG32rr: return X86::CMOVL32rr;
+ case X86::CMOVG64rm: return X86::CMOVL64rm;
+ case X86::CMOVG64rr: return X86::CMOVL64rr;
+ case X86::CMOVGE16rm: return X86::CMOVLE16rm;
+ case X86::CMOVGE16rr: return X86::CMOVLE16rr;
+ case X86::CMOVGE32rm: return X86::CMOVLE32rm;
+ case X86::CMOVGE32rr: return X86::CMOVLE32rr;
+ case X86::CMOVGE64rm: return X86::CMOVLE64rm;
+ case X86::CMOVGE64rr: return X86::CMOVLE64rr;
+
+ case X86::CMOVB16rm: return X86::CMOVA16rm;
+ case X86::CMOVB16rr: return X86::CMOVA16rr;
+ case X86::CMOVB32rm: return X86::CMOVA32rm;
+ case X86::CMOVB32rr: return X86::CMOVA32rr;
+ case X86::CMOVB64rm: return X86::CMOVA64rm;
+ case X86::CMOVB64rr: return X86::CMOVA64rr;
+ case X86::CMOVBE16rm: return X86::CMOVAE16rm;
+ case X86::CMOVBE16rr: return X86::CMOVAE16rr;
+ case X86::CMOVBE32rm: return X86::CMOVAE32rm;
+ case X86::CMOVBE32rr: return X86::CMOVAE32rr;
+ case X86::CMOVBE64rm: return X86::CMOVAE64rm;
+ case X86::CMOVBE64rr: return X86::CMOVAE64rr;
+
+ case X86::CMOVA16rm: return X86::CMOVB16rm;
+ case X86::CMOVA16rr: return X86::CMOVB16rr;
+ case X86::CMOVA32rm: return X86::CMOVB32rm;
+ case X86::CMOVA32rr: return X86::CMOVB32rr;
+ case X86::CMOVA64rm: return X86::CMOVB64rm;
+ case X86::CMOVA64rr: return X86::CMOVB64rr;
+ case X86::CMOVAE16rm: return X86::CMOVBE16rm;
+ case X86::CMOVAE16rr: return X86::CMOVBE16rr;
+ case X86::CMOVAE32rm: return X86::CMOVBE32rm;
+ case X86::CMOVAE32rr: return X86::CMOVBE32rr;
+ case X86::CMOVAE64rm: return X86::CMOVBE64rm;
+ case X86::CMOVAE64rr: return X86::CMOVBE64rr;
}
+}
- X86FI->setCalleeSavedFrameSize(CalleeFrameSize);
- return true;
+/// isRedundantFlagInstr - check whether the first instruction, whose only
+/// purpose is to update flags, can be made redundant.
+/// CMPrr can be made redundant by SUBrr if the operands are the same.
+/// This function can be extended later on.
+/// SrcReg, SrcRegs: register operands for FlagI.
+/// ImmValue: immediate for FlagI if it takes an immediate.
+inline static bool isRedundantFlagInstr(MachineInstr *FlagI, unsigned SrcReg,
+ unsigned SrcReg2, int ImmValue,
+ MachineInstr *OI) {
+ if (((FlagI->getOpcode() == X86::CMP64rr &&
+ OI->getOpcode() == X86::SUB64rr) ||
+ (FlagI->getOpcode() == X86::CMP32rr &&
+ OI->getOpcode() == X86::SUB32rr)||
+ (FlagI->getOpcode() == X86::CMP16rr &&
+ OI->getOpcode() == X86::SUB16rr)||
+ (FlagI->getOpcode() == X86::CMP8rr &&
+ OI->getOpcode() == X86::SUB8rr)) &&
+ ((OI->getOperand(1).getReg() == SrcReg &&
+ OI->getOperand(2).getReg() == SrcReg2) ||
+ (OI->getOperand(1).getReg() == SrcReg2 &&
+ OI->getOperand(2).getReg() == SrcReg)))
+ return true;
+
+ if (((FlagI->getOpcode() == X86::CMP64ri32 &&
+ OI->getOpcode() == X86::SUB64ri32) ||
+ (FlagI->getOpcode() == X86::CMP64ri8 &&
+ OI->getOpcode() == X86::SUB64ri8) ||
+ (FlagI->getOpcode() == X86::CMP32ri &&
+ OI->getOpcode() == X86::SUB32ri) ||
+ (FlagI->getOpcode() == X86::CMP32ri8 &&
+ OI->getOpcode() == X86::SUB32ri8) ||
+ (FlagI->getOpcode() == X86::CMP16ri &&
+ OI->getOpcode() == X86::SUB16ri) ||
+ (FlagI->getOpcode() == X86::CMP16ri8 &&
+ OI->getOpcode() == X86::SUB16ri8) ||
+ (FlagI->getOpcode() == X86::CMP8ri &&
+ OI->getOpcode() == X86::SUB8ri)) &&
+ OI->getOperand(1).getReg() == SrcReg &&
+ OI->getOperand(2).getImm() == ImmValue)
+ return true;
+ return false;
}
-bool X86InstrInfo::restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
- MachineBasicBlock::iterator MI,
- const std::vector<CalleeSavedInfo> &CSI,
- const TargetRegisterInfo *TRI) const {
- if (CSI.empty())
- return false;
+/// optimizeCompareInstr - Check if there exists an earlier instruction that
+/// operates on the same source operands and sets flags in the same way as
+/// Compare; remove Compare if possible.
+bool X86InstrInfo::
+optimizeCompareInstr(MachineInstr *CmpInstr, unsigned SrcReg, unsigned SrcReg2,
+ int CmpMask, int CmpValue,
+ const MachineRegisterInfo *MRI) const {
+ // Get the unique definition of SrcReg.
+ MachineInstr *MI = MRI->getUniqueVRegDef(SrcReg);
+ if (!MI) return false;
+
+ // CmpInstr is the first instruction of the BB.
+ MachineBasicBlock::iterator I = CmpInstr, Def = MI;
+
+ // We are searching for an earlier instruction that can make CmpInstr
+ // redundant and that instruction will be saved in Sub.
+ MachineInstr *Sub = NULL;
+ const TargetRegisterInfo *TRI = &getRegisterInfo();
+
+ // We iterate backward, starting from the instruction before CmpInstr and
+ // stop when reaching the definition of a source register or done with the BB.
+ // RI points to the instruction before CmpInstr.
+ // If the definition is in this basic block, RE points to the definition;
+ // otherwise, RE is the rend of the basic block.
+ MachineBasicBlock::reverse_iterator
+ RI = MachineBasicBlock::reverse_iterator(I),
+ RE = CmpInstr->getParent() == MI->getParent() ?
+ MachineBasicBlock::reverse_iterator(++Def) /* points to MI */ :
+ CmpInstr->getParent()->rend();
+ for (; RI != RE; ++RI) {
+ MachineInstr *Instr = &*RI;
+ // Check whether CmpInstr can be made redundant by the current instruction.
+ if (isRedundantFlagInstr(CmpInstr, SrcReg, SrcReg2, CmpValue, Instr)) {
+ Sub = Instr;
+ break;
+ }
- DebugLoc DL = MBB.findDebugLoc(MI);
+ if (Instr->modifiesRegister(X86::EFLAGS, TRI) ||
+ Instr->readsRegister(X86::EFLAGS, TRI))
+ // This instruction modifies or uses EFLAGS.
+ // We can't remove CmpInstr.
+ return false;
+ }
- MachineFunction &MF = *MBB.getParent();
- unsigned FPReg = RI.getFrameRegister(MF);
- bool is64Bit = TM.getSubtarget<X86Subtarget>().is64Bit();
- bool isWin64 = TM.getSubtarget<X86Subtarget>().isTargetWin64();
- unsigned Opc = is64Bit ? X86::POP64r : X86::POP32r;
- for (unsigned i = 0, e = CSI.size(); i != e; ++i) {
- unsigned Reg = CSI[i].getReg();
- if (Reg == FPReg)
- // X86RegisterInfo::emitEpilogue will handle restoring of frame register.
+ // Return false if no candidates exist.
+ if (!Sub)
+ return false;
+
+ bool IsSwapped = (SrcReg2 != 0 && Sub->getOperand(1).getReg() == SrcReg2 &&
+ Sub->getOperand(2).getReg() == SrcReg);
+
+ // Scan forward from the instruction after CmpInstr for uses of EFLAGS.
+ // It is safe to remove CmpInstr if EFLAGS is redefined or killed.
+ // If we are done with the basic block, we need to check whether EFLAGS is
+ // live-out.
+ bool IsSafe = false;
+ SmallVector<std::pair<MachineInstr*, unsigned /*NewOpc*/>, 4> OpsToUpdate;
+ MachineBasicBlock::iterator E = CmpInstr->getParent()->end();
+ for (++I; I != E; ++I) {
+ const MachineInstr &Instr = *I;
+ if (Instr.modifiesRegister(X86::EFLAGS, TRI)) {
+ // It is safe to remove CmpInstr if EFLAGS is updated again.
+ IsSafe = true;
+ break;
+ }
+ if (!Instr.readsRegister(X86::EFLAGS, TRI))
continue;
- if (!X86::VR128RegClass.contains(Reg) && !isWin64) {
- BuildMI(MBB, MI, DL, get(Opc), Reg);
- } else {
- const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
- loadRegFromStackSlot(MBB, MI, Reg, CSI[i].getFrameIdx(),
- RC, &RI);
+
+ // EFLAGS is used by this instruction.
+ if (IsSwapped) {
+ // If we have SUB(r1, r2) and CMP(r2, r1), the condition code needs
+ // to be changed from r2 > r1 to r1 < r2, from r2 < r1 to r1 > r2, etc.
+ unsigned NewOpc = getSwappedConditionForSET(Instr.getOpcode());
+ if (!NewOpc) NewOpc = getSwappedConditionForBranch(Instr.getOpcode());
+ if (!NewOpc) NewOpc = getSwappedConditionForCMov(Instr.getOpcode());
+ if (!NewOpc) return false;
+
+ // Push the MachineInstr to OpsToUpdate.
+ // If it is safe to remove CmpInstr, the condition code of these
+ // instructions will be modified.
+ OpsToUpdate.push_back(std::make_pair(&*I, NewOpc));
+ }
+ if (Instr.killsRegister(X86::EFLAGS, TRI)) {
+ IsSafe = true;
+ break;
}
}
+
+ // If EFLAGS is not killed nor re-defined, we should check whether it is
+ // live-out. If it is live-out, do not optimize.
+ if (IsSwapped && !IsSafe) {
+ MachineBasicBlock *MBB = CmpInstr->getParent();
+ for (MachineBasicBlock::succ_iterator SI = MBB->succ_begin(),
+ SE = MBB->succ_end(); SI != SE; ++SI)
+ if ((*SI)->isLiveIn(X86::EFLAGS))
+ return false;
+ }
+
+ // Make sure Sub instruction defines EFLAGS.
+ assert(Sub->getNumOperands() >= 4 && Sub->getOperand(3).isReg() &&
+ Sub->getOperand(3).getReg() == X86::EFLAGS &&
+ "EFLAGS should be the 4th operand of SUBrr or SUBri.");
+ Sub->getOperand(3).setIsDef(true);
+ CmpInstr->eraseFromParent();
+
+ // Modify the condition code of instructions in OpsToUpdate.
+ for (unsigned i = 0, e = OpsToUpdate.size(); i < e; i++)
+ OpsToUpdate[i].first->setDesc(get(OpsToUpdate[i].second));
+ return true;
+}
+
+/// Expand2AddrUndef - Expand a single-def pseudo instruction to a two-addr
+/// instruction with two undef reads of the register being defined. This is
+/// used for mapping:
+/// %xmm4 = V_SET0
+/// to:
+/// %xmm4 = PXORrr %xmm4<undef>, %xmm4<undef>
+///
+static bool Expand2AddrUndef(MachineInstr *MI, const MCInstrDesc &Desc) {
+ assert(Desc.getNumOperands() == 3 && "Expected two-addr instruction.");
+ unsigned Reg = MI->getOperand(0).getReg();
+ MI->setDesc(Desc);
+
+ // MachineInstr::addOperand() will insert explicit operands before any
+ // implicit operands.
+ MachineInstrBuilder(MI).addReg(Reg, RegState::Undef)
+ .addReg(Reg, RegState::Undef);
+ // But we don't trust that.
+ assert(MI->getOperand(1).getReg() == Reg &&
+ MI->getOperand(2).getReg() == Reg && "Misplaced operand");
return true;
}
+bool X86InstrInfo::expandPostRAPseudo(MachineBasicBlock::iterator MI) const {
+ bool HasAVX = TM.getSubtarget<X86Subtarget>().hasAVX();
+ switch (MI->getOpcode()) {
+ case X86::V_SET0:
+ case X86::FsFLD0SS:
+ case X86::FsFLD0SD:
+ return Expand2AddrUndef(MI, get(HasAVX ? X86::VXORPSrr : X86::XORPSrr));
+ case X86::TEST8ri_NOREX:
+ MI->setDesc(get(X86::TEST8ri));
+ return true;
+ }
+ return false;
+}
+
MachineInstr*
X86InstrInfo::emitFrameIndexDebugValue(MachineFunction &MF,
int FrameIx, uint64_t Offset,
MIB.addOperand(MOs[i]);
if (NumAddrOps < 4) // FrameIndex only
addOffset(MIB, 0);
-
+
// Loop over the rest of the ri operands, converting them over.
unsigned NumOps = MI->getDesc().getNumOperands()-2;
for (unsigned i = 0; i != NumOps; ++i) {
MachineInstr *NewMI = MF.CreateMachineInstr(TII.get(Opcode),
MI->getDebugLoc(), true);
MachineInstrBuilder MIB(NewMI);
-
+
for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
MachineOperand &MO = MI->getOperand(i);
if (i == OpNo) {
bool isTwoAddrFold = false;
unsigned NumOps = MI->getDesc().getNumOperands();
bool isTwoAddr = NumOps > 1 &&
- MI->getDesc().getOperandConstraint(1, TOI::TIED_TO) != -1;
+ MI->getDesc().getOperandConstraint(1, MCOI::TIED_TO) != -1;
+
+ // FIXME: AsmPrinter doesn't know how to handle
+ // X86II::MO_GOT_ABSOLUTE_ADDRESS after folding.
+ if (MI->getOpcode() == X86::ADD32ri &&
+ MI->getOperand(2).getTargetFlags() == X86II::MO_GOT_ABSOLUTE_ADDRESS)
+ return NULL;
MachineInstr *NewMI = NULL;
// Folding a memory location into the two-address part of a two-address
if (isTwoAddr && NumOps >= 2 && i < 2 &&
MI->getOperand(0).isReg() &&
MI->getOperand(1).isReg() &&
- MI->getOperand(0).getReg() == MI->getOperand(1).getReg()) {
+ MI->getOperand(0).getReg() == MI->getOperand(1).getReg()) {
OpcodeTablePtr = &RegOp2MemOpTable2Addr;
isTwoAddrFold = true;
} else if (i == 0) { // If operand 0
NewMI = MakeM0Inst(*this, X86::MOV8mi, MOs, MI);
if (NewMI)
return NewMI;
-
+
OpcodeTablePtr = &RegOp2MemOpTable0;
} else if (i == 1) {
OpcodeTablePtr = &RegOp2MemOpTable1;
} else if (i == 2) {
OpcodeTablePtr = &RegOp2MemOpTable2;
}
-
+
// If table selected...
if (OpcodeTablePtr) {
// Find the Opcode to fuse
OpcodeTablePtr->find(MI->getOpcode());
if (I != OpcodeTablePtr->end()) {
unsigned Opcode = I->second.first;
- unsigned MinAlign = I->second.second;
+ unsigned MinAlign = (I->second.second & TB_ALIGN_MASK) >> TB_ALIGN_SHIFT;
if (Align < MinAlign)
return NULL;
bool NarrowToMOV32rm = false;
if (Size) {
- unsigned RCSize = MI->getDesc().OpInfo[i].getRegClass(&RI)->getSize();
+ unsigned RCSize = getRegClass(MI->getDesc(), i, &RI, MF)->getSize();
if (Size < RCSize) {
// Check if it's safe to fold the load. If the size of the object is
// narrower than the load width, then it's not.
return NewMI;
}
}
-
- // No fusion
+
+ // No fusion
if (PrintFailedFusing && !MI->isCopy())
dbgs() << "We failed to fuse operand " << i << " in " << *MI;
return NULL;
}
+/// hasPartialRegUpdate - Return true for all instructions that only update
+/// the first 32 or 64-bits of the destination register and leave the rest
+/// unmodified. This can be used to avoid folding loads if the instructions
+/// only update part of the destination register, and the non-updated part is
+/// not needed. e.g. cvtss2sd, sqrtss. Unfolding the load from these
+/// instructions breaks the partial register dependency and it can improve
+/// performance. e.g.:
+///
+/// movss (%rdi), %xmm0
+/// cvtss2sd %xmm0, %xmm0
+///
+/// Instead of
+/// cvtss2sd (%rdi), %xmm0
+///
+/// FIXME: This should be turned into a TSFlags.
+///
+static bool hasPartialRegUpdate(unsigned Opcode) {
+ switch (Opcode) {
+ case X86::CVTSI2SSrr:
+ case X86::CVTSI2SS64rr:
+ case X86::CVTSI2SDrr:
+ case X86::CVTSI2SD64rr:
+ case X86::CVTSD2SSrr:
+ case X86::Int_CVTSD2SSrr:
+ case X86::CVTSS2SDrr:
+ case X86::Int_CVTSS2SDrr:
+ case X86::RCPSSr:
+ case X86::RCPSSr_Int:
+ case X86::ROUNDSDr:
+ case X86::ROUNDSDr_Int:
+ case X86::ROUNDSSr:
+ case X86::ROUNDSSr_Int:
+ case X86::RSQRTSSr:
+ case X86::RSQRTSSr_Int:
+ case X86::SQRTSSr:
+ case X86::SQRTSSr_Int:
+ // AVX encoded versions
+ case X86::VCVTSD2SSrr:
+ case X86::Int_VCVTSD2SSrr:
+ case X86::VCVTSS2SDrr:
+ case X86::Int_VCVTSS2SDrr:
+ case X86::VRCPSSr:
+ case X86::VROUNDSDr:
+ case X86::VROUNDSDr_Int:
+ case X86::VROUNDSSr:
+ case X86::VROUNDSSr_Int:
+ case X86::VRSQRTSSr:
+ case X86::VSQRTSSr:
+ return true;
+ }
+
+ return false;
+}
+
+/// getPartialRegUpdateClearance - Inform the ExeDepsFix pass how many idle
+/// instructions we would like before a partial register update.
+unsigned X86InstrInfo::
+getPartialRegUpdateClearance(const MachineInstr *MI, unsigned OpNum,
+ const TargetRegisterInfo *TRI) const {
+ if (OpNum != 0 || !hasPartialRegUpdate(MI->getOpcode()))
+ return 0;
+
+ // If MI is marked as reading Reg, the partial register update is wanted.
+ const MachineOperand &MO = MI->getOperand(0);
+ unsigned Reg = MO.getReg();
+ if (TargetRegisterInfo::isVirtualRegister(Reg)) {
+ if (MO.readsReg() || MI->readsVirtualRegister(Reg))
+ return 0;
+ } else {
+ if (MI->readsRegister(Reg, TRI))
+ return 0;
+ }
+
+ // If any of the preceding 16 instructions are reading Reg, insert a
+ // dependency breaking instruction. The magic number is based on a few
+ // Nehalem experiments.
+ return 16;
+}
+
+void X86InstrInfo::
+breakPartialRegDependency(MachineBasicBlock::iterator MI, unsigned OpNum,
+ const TargetRegisterInfo *TRI) const {
+ unsigned Reg = MI->getOperand(OpNum).getReg();
+ if (X86::VR128RegClass.contains(Reg)) {
+ // These instructions are all floating point domain, so xorps is the best
+ // choice.
+ bool HasAVX = TM.getSubtarget<X86Subtarget>().hasAVX();
+ unsigned Opc = HasAVX ? X86::VXORPSrr : X86::XORPSrr;
+ BuildMI(*MI->getParent(), MI, MI->getDebugLoc(), get(Opc), Reg)
+ .addReg(Reg, RegState::Undef).addReg(Reg, RegState::Undef);
+ } else if (X86::VR256RegClass.contains(Reg)) {
+ // Use vxorps to clear the full ymm register.
+ // It wants to read and write the xmm sub-register.
+ unsigned XReg = TRI->getSubReg(Reg, X86::sub_xmm);
+ BuildMI(*MI->getParent(), MI, MI->getDebugLoc(), get(X86::VXORPSrr), XReg)
+ .addReg(XReg, RegState::Undef).addReg(XReg, RegState::Undef)
+ .addReg(Reg, RegState::ImplicitDefine);
+ } else
+ return;
+ MI->addRegisterKilled(Reg, TRI, true);
+}
MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
MachineInstr *MI,
const SmallVectorImpl<unsigned> &Ops,
int FrameIndex) const {
- // Check switch flag
+ // Check switch flag
if (NoFusing) return NULL;
- if (!MF.getFunction()->hasFnAttr(Attribute::OptimizeForSize))
- switch (MI->getOpcode()) {
- case X86::CVTSD2SSrr:
- case X86::Int_CVTSD2SSrr:
- case X86::CVTSS2SDrr:
- case X86::Int_CVTSS2SDrr:
- case X86::RCPSSr:
- case X86::RCPSSr_Int:
- case X86::ROUNDSDr:
- case X86::ROUNDSSr:
- case X86::RSQRTSSr:
- case X86::RSQRTSSr_Int:
- case X86::SQRTSSr:
- case X86::SQRTSSr_Int:
- return 0;
- }
+ // Unless optimizing for size, don't fold to avoid partial
+ // register update stalls
+ if (!MF.getFunction()->hasFnAttr(Attribute::OptimizeForSize) &&
+ hasPartialRegUpdate(MI->getOpcode()))
+ return 0;
const MachineFrameInfo *MFI = MF.getFrameInfo();
unsigned Size = MFI->getObjectSize(FrameIndex);
MachineInstr *MI,
const SmallVectorImpl<unsigned> &Ops,
MachineInstr *LoadMI) const {
- // Check switch flag
+ // Check switch flag
if (NoFusing) return NULL;
- if (!MF.getFunction()->hasFnAttr(Attribute::OptimizeForSize))
- switch (MI->getOpcode()) {
- case X86::CVTSD2SSrr:
- case X86::Int_CVTSD2SSrr:
- case X86::CVTSS2SDrr:
- case X86::Int_CVTSS2SDrr:
- case X86::RCPSSr:
- case X86::RCPSSr_Int:
- case X86::ROUNDSDr:
- case X86::ROUNDSSr:
- case X86::RSQRTSSr:
- case X86::RSQRTSSr_Int:
- case X86::SQRTSSr:
- case X86::SQRTSSr_Int:
- return 0;
- }
+ // Unless optimizing for size, don't fold to avoid partial
+ // register update stalls
+ if (!MF.getFunction()->hasFnAttr(Attribute::OptimizeForSize) &&
+ hasPartialRegUpdate(MI->getOpcode()))
+ return 0;
// Determine the alignment of the load.
unsigned Alignment = 0;
switch (LoadMI->getOpcode()) {
case X86::AVX_SET0PSY:
case X86::AVX_SET0PDY:
+ case X86::AVX2_SETALLONES:
+ case X86::AVX2_SET0:
Alignment = 32;
break;
- case X86::V_SET0PS:
- case X86::V_SET0PD:
- case X86::V_SET0PI:
+ case X86::V_SET0:
case X86::V_SETALLONES:
- case X86::AVX_SET0PS:
- case X86::AVX_SET0PD:
- case X86::AVX_SET0PI:
+ case X86::AVX_SETALLONES:
Alignment = 16;
break;
case X86::FsFLD0SD:
Alignment = 4;
break;
default:
- llvm_unreachable("Don't know how to fold this instruction!");
+ return 0;
}
if (Ops.size() == 2 && Ops[0] == 0 && Ops[1] == 1) {
unsigned NewOpc = 0;
SmallVector<MachineOperand,X86::AddrNumOperands> MOs;
switch (LoadMI->getOpcode()) {
- case X86::V_SET0PS:
- case X86::V_SET0PD:
- case X86::V_SET0PI:
+ case X86::V_SET0:
case X86::V_SETALLONES:
- case X86::AVX_SET0PS:
- case X86::AVX_SET0PD:
- case X86::AVX_SET0PI:
case X86::AVX_SET0PSY:
case X86::AVX_SET0PDY:
+ case X86::AVX_SETALLONES:
+ case X86::AVX2_SETALLONES:
+ case X86::AVX2_SET0:
case X86::FsFLD0SD:
case X86::FsFLD0SS: {
- // Folding a V_SET0P? or V_SETALLONES as a load, to ease register pressure.
+ // Folding a V_SET0 or V_SETALLONES as a load, to ease register pressure.
// Create a constant-pool entry and operands to load from it.
// Medium and large mode can't fold loads this way.
// Create a constant-pool entry.
MachineConstantPool &MCP = *MF.getConstantPool();
- const Type *Ty;
+ Type *Ty;
unsigned Opc = LoadMI->getOpcode();
if (Opc == X86::FsFLD0SS)
Ty = Type::getFloatTy(MF.getFunction()->getContext());
Ty = Type::getDoubleTy(MF.getFunction()->getContext());
else if (Opc == X86::AVX_SET0PSY || Opc == X86::AVX_SET0PDY)
Ty = VectorType::get(Type::getFloatTy(MF.getFunction()->getContext()), 8);
+ else if (Opc == X86::AVX2_SETALLONES || Opc == X86::AVX2_SET0)
+ Ty = VectorType::get(Type::getInt32Ty(MF.getFunction()->getContext()), 8);
else
Ty = VectorType::get(Type::getInt32Ty(MF.getFunction()->getContext()), 4);
- const Constant *C = LoadMI->getOpcode() == X86::V_SETALLONES ?
- Constant::getAllOnesValue(Ty) :
- Constant::getNullValue(Ty);
+
+ bool IsAllOnes = (Opc == X86::V_SETALLONES || Opc == X86::AVX_SETALLONES ||
+ Opc == X86::AVX2_SETALLONES);
+ const Constant *C = IsAllOnes ? Constant::getAllOnesValue(Ty) :
+ Constant::getNullValue(Ty);
unsigned CPI = MCP.getConstantPoolIndex(C, Alignment);
// Create operands to load from the constant pool entry.
bool X86InstrInfo::canFoldMemoryOperand(const MachineInstr *MI,
const SmallVectorImpl<unsigned> &Ops) const {
- // Check switch flag
+ // Check switch flag
if (NoFusing) return 0;
if (Ops.size() == 2 && Ops[0] == 0 && Ops[1] == 1) {
switch (MI->getOpcode()) {
default: return false;
- case X86::TEST8rr:
+ case X86::TEST8rr:
case X86::TEST16rr:
case X86::TEST32rr:
case X86::TEST64rr:
return true;
+ case X86::ADD32ri:
+ // FIXME: AsmPrinter doesn't know how to handle
+ // X86II::MO_GOT_ABSOLUTE_ADDRESS after folding.
+ if (MI->getOperand(2).getTargetFlags() == X86II::MO_GOT_ABSOLUTE_ADDRESS)
+ return false;
+ break;
}
}
unsigned Opc = MI->getOpcode();
unsigned NumOps = MI->getDesc().getNumOperands();
bool isTwoAddr = NumOps > 1 &&
- MI->getDesc().getOperandConstraint(1, TOI::TIED_TO) != -1;
+ MI->getDesc().getOperandConstraint(1, MCOI::TIED_TO) != -1;
// Folding a memory location into the two-address part of a two-address
// instruction is different than folding it other places. It requires
// replacing the *two* registers with the memory location.
const DenseMap<unsigned, std::pair<unsigned,unsigned> > *OpcodeTablePtr = 0;
- if (isTwoAddr && NumOps >= 2 && OpNum < 2) {
+ if (isTwoAddr && NumOps >= 2 && OpNum < 2) {
OpcodeTablePtr = &RegOp2MemOpTable2Addr;
} else if (OpNum == 0) { // If operand 0
switch (Opc) {
} else if (OpNum == 2) {
OpcodeTablePtr = &RegOp2MemOpTable2;
}
-
+
if (OpcodeTablePtr && OpcodeTablePtr->count(Opc))
return true;
return TargetInstrInfoImpl::canFoldMemoryOperand(MI, Ops);
if (I == MemOp2RegOpTable.end())
return false;
unsigned Opc = I->second.first;
- unsigned Index = I->second.second & 0xf;
- bool FoldedLoad = I->second.second & (1 << 4);
- bool FoldedStore = I->second.second & (1 << 5);
+ unsigned Index = I->second.second & TB_INDEX_MASK;
+ bool FoldedLoad = I->second.second & TB_FOLDED_LOAD;
+ bool FoldedStore = I->second.second & TB_FOLDED_STORE;
if (UnfoldLoad && !FoldedLoad)
return false;
UnfoldLoad &= FoldedLoad;
return false;
UnfoldStore &= FoldedStore;
- const TargetInstrDesc &TID = get(Opc);
- const TargetOperandInfo &TOI = TID.OpInfo[Index];
- const TargetRegisterClass *RC = TOI.getRegClass(&RI);
+ const MCInstrDesc &MCID = get(Opc);
+ const TargetRegisterClass *RC = getRegClass(MCID, Index, &RI, MF);
if (!MI->hasOneMemOperand() &&
RC == &X86::VR128RegClass &&
!TM.getSubtarget<X86Subtarget>().isUnalignedMemAccessFast())
}
// Emit the data processing instruction.
- MachineInstr *DataMI = MF.CreateMachineInstr(TID, MI->getDebugLoc(), true);
+ MachineInstr *DataMI = MF.CreateMachineInstr(MCID, MI->getDebugLoc(), true);
MachineInstrBuilder MIB(DataMI);
-
+
if (FoldedStore)
MIB.addReg(Reg, RegState::Define);
for (unsigned i = 0, e = BeforeOps.size(); i != e; ++i)
// Emit the store instruction.
if (UnfoldStore) {
- const TargetRegisterClass *DstRC = TID.OpInfo[0].getRegClass(&RI);
+ const TargetRegisterClass *DstRC = getRegClass(MCID, 0, &RI, MF);
std::pair<MachineInstr::mmo_iterator,
MachineInstr::mmo_iterator> MMOs =
MF.extractStoreMemRefs(MI->memoperands_begin(),
if (I == MemOp2RegOpTable.end())
return false;
unsigned Opc = I->second.first;
- unsigned Index = I->second.second & 0xf;
- bool FoldedLoad = I->second.second & (1 << 4);
- bool FoldedStore = I->second.second & (1 << 5);
- const TargetInstrDesc &TID = get(Opc);
- const TargetRegisterClass *RC = TID.OpInfo[Index].getRegClass(&RI);
- unsigned NumDefs = TID.NumDefs;
+ unsigned Index = I->second.second & TB_INDEX_MASK;
+ bool FoldedLoad = I->second.second & TB_FOLDED_LOAD;
+ bool FoldedStore = I->second.second & TB_FOLDED_STORE;
+ const MCInstrDesc &MCID = get(Opc);
+ MachineFunction &MF = DAG.getMachineFunction();
+ const TargetRegisterClass *RC = getRegClass(MCID, Index, &RI, MF);
+ unsigned NumDefs = MCID.NumDefs;
std::vector<SDValue> AddrOps;
std::vector<SDValue> BeforeOps;
std::vector<SDValue> AfterOps;
// Emit the load instruction.
SDNode *Load = 0;
- MachineFunction &MF = DAG.getMachineFunction();
if (FoldedLoad) {
EVT VT = *RC->vt_begin();
std::pair<MachineInstr::mmo_iterator,
!TM.getSubtarget<X86Subtarget>().isUnalignedMemAccessFast())
// Do not introduce a slow unaligned load.
return false;
- bool isAligned = (*MMOs.first) && (*MMOs.first)->getAlignment() >= 16;
+ unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
+ bool isAligned = (*MMOs.first) &&
+ (*MMOs.first)->getAlignment() >= Alignment;
Load = DAG.getMachineNode(getLoadRegOpcode(0, RC, isAligned, TM), dl,
VT, MVT::Other, &AddrOps[0], AddrOps.size());
NewNodes.push_back(Load);
// Emit the data processing instruction.
std::vector<EVT> VTs;
const TargetRegisterClass *DstRC = 0;
- if (TID.getNumDefs() > 0) {
- DstRC = TID.OpInfo[0].getRegClass(&RI);
+ if (MCID.getNumDefs() > 0) {
+ DstRC = getRegClass(MCID, 0, &RI, MF);
VTs.push_back(*DstRC->vt_begin());
}
for (unsigned i = 0, e = N->getNumValues(); i != e; ++i) {
EVT VT = N->getValueType(i);
- if (VT != MVT::Other && i >= (unsigned)TID.getNumDefs())
+ if (VT != MVT::Other && i >= (unsigned)MCID.getNumDefs())
VTs.push_back(VT);
}
if (Load)
!TM.getSubtarget<X86Subtarget>().isUnalignedMemAccessFast())
// Do not introduce a slow unaligned store.
return false;
- bool isAligned = (*MMOs.first) && (*MMOs.first)->getAlignment() >= 16;
+ unsigned Alignment = RC->getSize() == 32 ? 32 : 16;
+ bool isAligned = (*MMOs.first) &&
+ (*MMOs.first)->getAlignment() >= Alignment;
SDNode *Store = DAG.getMachineNode(getStoreRegOpcode(0, DstRC,
isAligned, TM),
dl, MVT::Other,
MemOp2RegOpTable.find(Opc);
if (I == MemOp2RegOpTable.end())
return 0;
- bool FoldedLoad = I->second.second & (1 << 4);
- bool FoldedStore = I->second.second & (1 << 5);
+ bool FoldedLoad = I->second.second & TB_FOLDED_LOAD;
+ bool FoldedStore = I->second.second & TB_FOLDED_STORE;
if (UnfoldLoad && !FoldedLoad)
return 0;
if (UnfoldStore && !FoldedStore)
return 0;
if (LoadRegIndex)
- *LoadRegIndex = I->second.second & 0xf;
+ *LoadRegIndex = I->second.second & TB_INDEX_MASK;
return I->second.first;
}
case X86::FsMOVAPDrm:
case X86::MOVAPSrm:
case X86::MOVUPSrm:
- case X86::MOVUPSrm_Int:
case X86::MOVAPDrm:
case X86::MOVDQArm:
case X86::MOVDQUrm:
- case X86::MOVDQUrm_Int:
+ // AVX load instructions
+ case X86::VMOVSSrm:
+ case X86::VMOVSDrm:
+ case X86::FsVMOVAPSrm:
+ case X86::FsVMOVAPDrm:
+ case X86::VMOVAPSrm:
+ case X86::VMOVUPSrm:
+ case X86::VMOVAPDrm:
+ case X86::VMOVDQArm:
+ case X86::VMOVDQUrm:
+ case X86::VMOVAPSYrm:
+ case X86::VMOVUPSYrm:
+ case X86::VMOVAPDYrm:
+ case X86::VMOVDQAYrm:
+ case X86::VMOVDQUYrm:
break;
}
switch (Opc2) {
case X86::FsMOVAPDrm:
case X86::MOVAPSrm:
case X86::MOVUPSrm:
- case X86::MOVUPSrm_Int:
case X86::MOVAPDrm:
case X86::MOVDQArm:
case X86::MOVDQUrm:
- case X86::MOVDQUrm_Int:
+ // AVX load instructions
+ case X86::VMOVSSrm:
+ case X86::VMOVSDrm:
+ case X86::FsVMOVAPSrm:
+ case X86::FsVMOVAPDrm:
+ case X86::VMOVAPSrm:
+ case X86::VMOVUPSrm:
+ case X86::VMOVAPDrm:
+ case X86::VMOVDQArm:
+ case X86::VMOVDQUrm:
+ case X86::VMOVAPSYrm:
+ case X86::VMOVUPSYrm:
+ case X86::VMOVAPDYrm:
+ case X86::VMOVDQAYrm:
+ case X86::VMOVDQUYrm:
break;
}
RC == &X86::RFP64RegClass || RC == &X86::RFP80RegClass);
}
-
-/// isX86_64ExtendedReg - Is the MachineOperand a x86-64 extended (r8 or higher)
-/// register? e.g. r8, xmm8, xmm13, etc.
-bool X86InstrInfo::isX86_64ExtendedReg(unsigned RegNo) {
- switch (RegNo) {
- default: break;
- case X86::R8: case X86::R9: case X86::R10: case X86::R11:
- case X86::R12: case X86::R13: case X86::R14: case X86::R15:
- case X86::R8D: case X86::R9D: case X86::R10D: case X86::R11D:
- case X86::R12D: case X86::R13D: case X86::R14D: case X86::R15D:
- case X86::R8W: case X86::R9W: case X86::R10W: case X86::R11W:
- case X86::R12W: case X86::R13W: case X86::R14W: case X86::R15W:
- case X86::R8B: case X86::R9B: case X86::R10B: case X86::R11B:
- case X86::R12B: case X86::R13B: case X86::R14B: case X86::R15B:
- case X86::XMM8: case X86::XMM9: case X86::XMM10: case X86::XMM11:
- case X86::XMM12: case X86::XMM13: case X86::XMM14: case X86::XMM15:
- case X86::YMM8: case X86::YMM9: case X86::YMM10: case X86::YMM11:
- case X86::YMM12: case X86::YMM13: case X86::YMM14: case X86::YMM15:
- case X86::CR8: case X86::CR9: case X86::CR10: case X86::CR11:
- case X86::CR12: case X86::CR13: case X86::CR14: case X86::CR15:
- return true;
- }
- return false;
-}
-
/// getGlobalBaseReg - Return a virtual register initialized with the
/// the global base register value. Output instructions required to
/// initialize the register in the function entry block, if necessary.
// Create the register. The code to initialize it is inserted
// later, by the CGBR pass (below).
MachineRegisterInfo &RegInfo = MF->getRegInfo();
- GlobalBaseReg = RegInfo.createVirtualRegister(X86::GR32RegisterClass);
+ GlobalBaseReg = RegInfo.createVirtualRegister(&X86::GR32_NOSPRegClass);
X86FI->setGlobalBaseReg(GlobalBaseReg);
return GlobalBaseReg;
}
// These are the replaceable SSE instructions. Some of these have Int variants
// that we don't include here. We don't want to replace instructions selected
// by intrinsics.
-static const unsigned ReplaceableInstrs[][3] = {
+static const uint16_t ReplaceableInstrs[][3] = {
//PackedSingle PackedDouble PackedInt
{ X86::MOVAPSmr, X86::MOVAPDmr, X86::MOVDQAmr },
{ X86::MOVAPSrm, X86::MOVAPDrm, X86::MOVDQArm },
{ X86::ANDPSrr, X86::ANDPDrr, X86::PANDrr },
{ X86::ORPSrm, X86::ORPDrm, X86::PORrm },
{ X86::ORPSrr, X86::ORPDrr, X86::PORrr },
- { X86::V_SET0PS, X86::V_SET0PD, X86::V_SET0PI },
{ X86::XORPSrm, X86::XORPDrm, X86::PXORrm },
{ X86::XORPSrr, X86::XORPDrr, X86::PXORrr },
// AVX 128-bit support
{ X86::VANDPSrr, X86::VANDPDrr, X86::VPANDrr },
{ X86::VORPSrm, X86::VORPDrm, X86::VPORrm },
{ X86::VORPSrr, X86::VORPDrr, X86::VPORrr },
- { X86::AVX_SET0PS, X86::AVX_SET0PD, X86::AVX_SET0PI },
{ X86::VXORPSrm, X86::VXORPDrm, X86::VPXORrm },
{ X86::VXORPSrr, X86::VXORPDrr, X86::VPXORrr },
+ // AVX 256-bit support
+ { X86::VMOVAPSYmr, X86::VMOVAPDYmr, X86::VMOVDQAYmr },
+ { X86::VMOVAPSYrm, X86::VMOVAPDYrm, X86::VMOVDQAYrm },
+ { X86::VMOVAPSYrr, X86::VMOVAPDYrr, X86::VMOVDQAYrr },
+ { X86::VMOVUPSYmr, X86::VMOVUPDYmr, X86::VMOVDQUYmr },
+ { X86::VMOVUPSYrm, X86::VMOVUPDYrm, X86::VMOVDQUYrm },
+ { X86::VMOVNTPSYmr, X86::VMOVNTPDYmr, X86::VMOVNTDQYmr }
+};
+
+static const uint16_t ReplaceableInstrsAVX2[][3] = {
+ //PackedSingle PackedDouble PackedInt
+ { X86::VANDNPSYrm, X86::VANDNPDYrm, X86::VPANDNYrm },
+ { X86::VANDNPSYrr, X86::VANDNPDYrr, X86::VPANDNYrr },
+ { X86::VANDPSYrm, X86::VANDPDYrm, X86::VPANDYrm },
+ { X86::VANDPSYrr, X86::VANDPDYrr, X86::VPANDYrr },
+ { X86::VORPSYrm, X86::VORPDYrm, X86::VPORYrm },
+ { X86::VORPSYrr, X86::VORPDYrr, X86::VPORYrr },
+ { X86::VXORPSYrm, X86::VXORPDYrm, X86::VPXORYrm },
+ { X86::VXORPSYrr, X86::VXORPDYrr, X86::VPXORYrr },
+ { X86::VEXTRACTF128mr, X86::VEXTRACTF128mr, X86::VEXTRACTI128mr },
+ { X86::VEXTRACTF128rr, X86::VEXTRACTF128rr, X86::VEXTRACTI128rr },
+ { X86::VINSERTF128rm, X86::VINSERTF128rm, X86::VINSERTI128rm },
+ { X86::VINSERTF128rr, X86::VINSERTF128rr, X86::VINSERTI128rr },
+ { X86::VPERM2F128rm, X86::VPERM2F128rm, X86::VPERM2I128rm },
+ { X86::VPERM2F128rr, X86::VPERM2F128rr, X86::VPERM2I128rr }
};
// FIXME: Some shuffle and unpack instructions have equivalents in different
// domains, but they require a bit more work than just switching opcodes.
-static const unsigned *lookup(unsigned opcode, unsigned domain) {
+static const uint16_t *lookup(unsigned opcode, unsigned domain) {
for (unsigned i = 0, e = array_lengthof(ReplaceableInstrs); i != e; ++i)
if (ReplaceableInstrs[i][domain-1] == opcode)
return ReplaceableInstrs[i];
return 0;
}
+static const uint16_t *lookupAVX2(unsigned opcode, unsigned domain) {
+ for (unsigned i = 0, e = array_lengthof(ReplaceableInstrsAVX2); i != e; ++i)
+ if (ReplaceableInstrsAVX2[i][domain-1] == opcode)
+ return ReplaceableInstrsAVX2[i];
+ return 0;
+}
+
std::pair<uint16_t, uint16_t>
-X86InstrInfo::GetSSEDomain(const MachineInstr *MI) const {
+X86InstrInfo::getExecutionDomain(const MachineInstr *MI) const {
uint16_t domain = (MI->getDesc().TSFlags >> X86II::SSEDomainShift) & 3;
- return std::make_pair(domain,
- domain && lookup(MI->getOpcode(), domain) ? 0xe : 0);
+ bool hasAVX2 = TM.getSubtarget<X86Subtarget>().hasAVX2();
+ uint16_t validDomains = 0;
+ if (domain && lookup(MI->getOpcode(), domain))
+ validDomains = 0xe;
+ else if (domain && lookupAVX2(MI->getOpcode(), domain))
+ validDomains = hasAVX2 ? 0xe : 0x6;
+ return std::make_pair(domain, validDomains);
}
-void X86InstrInfo::SetSSEDomain(MachineInstr *MI, unsigned Domain) const {
+void X86InstrInfo::setExecutionDomain(MachineInstr *MI, unsigned Domain) const {
assert(Domain>0 && Domain<4 && "Invalid execution domain");
uint16_t dom = (MI->getDesc().TSFlags >> X86II::SSEDomainShift) & 3;
assert(dom && "Not an SSE instruction");
- const unsigned *table = lookup(MI->getOpcode(), dom);
+ const uint16_t *table = lookup(MI->getOpcode(), dom);
+ if (!table) { // try the other table
+ assert((TM.getSubtarget<X86Subtarget>().hasAVX2() || Domain < 3) &&
+ "256-bit vector operations only available in AVX2");
+ table = lookupAVX2(MI->getOpcode(), dom);
+ }
assert(table && "Cannot change domain");
MI->setDesc(get(table[Domain-1]));
}
NopInst.setOpcode(X86::NOOP);
}
-bool X86InstrInfo::
-hasHighOperandLatency(const InstrItineraryData *ItinData,
- const MachineRegisterInfo *MRI,
- const MachineInstr *DefMI, unsigned DefIdx,
- const MachineInstr *UseMI, unsigned UseIdx) const {
- switch (DefMI->getOpcode()) {
+bool X86InstrInfo::isHighLatencyDef(int opc) const {
+ switch (opc) {
default: return false;
case X86::DIVSDrm:
case X86::DIVSDrm_Int:
case X86::SQRTSSm_Int:
case X86::SQRTSSr:
case X86::SQRTSSr_Int:
+ // AVX instructions with high latency
+ case X86::VDIVSDrm:
+ case X86::VDIVSDrm_Int:
+ case X86::VDIVSDrr:
+ case X86::VDIVSDrr_Int:
+ case X86::VDIVSSrm:
+ case X86::VDIVSSrm_Int:
+ case X86::VDIVSSrr:
+ case X86::VDIVSSrr_Int:
+ case X86::VSQRTPDm:
+ case X86::VSQRTPDm_Int:
+ case X86::VSQRTPDr:
+ case X86::VSQRTPDr_Int:
+ case X86::VSQRTPSm:
+ case X86::VSQRTPSm_Int:
+ case X86::VSQRTPSr:
+ case X86::VSQRTPSr_Int:
+ case X86::VSQRTSDm:
+ case X86::VSQRTSDm_Int:
+ case X86::VSQRTSDr:
+ case X86::VSQRTSSm:
+ case X86::VSQRTSSm_Int:
+ case X86::VSQRTSSr:
return true;
}
}
+bool X86InstrInfo::
+hasHighOperandLatency(const InstrItineraryData *ItinData,
+ const MachineRegisterInfo *MRI,
+ const MachineInstr *DefMI, unsigned DefIdx,
+ const MachineInstr *UseMI, unsigned UseIdx) const {
+ return isHighLatencyDef(DefMI->getOpcode());
+}
+
namespace {
/// CGBR - Create Global Base Reg pass. This initializes the PIC
/// global base register for x86-32.
unsigned PC;
if (TM->getSubtarget<X86Subtarget>().isPICStyleGOT())
- PC = RegInfo.createVirtualRegister(X86::GR32RegisterClass);
+ PC = RegInfo.createVirtualRegister(&X86::GR32RegClass);
else
PC = GlobalBaseReg;
-
+
// Operand of MovePCtoStack is completely ignored by asm printer. It's
// only used in JIT code emission as displacement to pc.
BuildMI(FirstMBB, MBBI, DL, TII->get(X86::MOVPC32r), PC).addImm(0);
-
+
// If we're using vanilla 'GOT' PIC style, we should use relative addressing
// not to pc, but to _GLOBAL_OFFSET_TABLE_ external.
if (TM->getSubtarget<X86Subtarget>().isPICStyleGOT()) {
char CGBR::ID = 0;
FunctionPass*
llvm::createGlobalBaseRegPass() { return new CGBR(); }
+
+namespace {
+ struct LDTLSCleanup : public MachineFunctionPass {
+ static char ID;
+ LDTLSCleanup() : MachineFunctionPass(ID) {}
+
+ virtual bool runOnMachineFunction(MachineFunction &MF) {
+ X86MachineFunctionInfo* MFI = MF.getInfo<X86MachineFunctionInfo>();
+ if (MFI->getNumLocalDynamicTLSAccesses() < 2) {
+ // No point folding accesses if there isn't at least two.
+ return false;
+ }
+
+ MachineDominatorTree *DT = &getAnalysis<MachineDominatorTree>();
+ return VisitNode(DT->getRootNode(), 0);
+ }
+
+ // Visit the dominator subtree rooted at Node in pre-order.
+ // If TLSBaseAddrReg is non-null, then use that to replace any
+ // TLS_base_addr instructions. Otherwise, create the register
+ // when the first such instruction is seen, and then use it
+ // as we encounter more instructions.
+ bool VisitNode(MachineDomTreeNode *Node, unsigned TLSBaseAddrReg) {
+ MachineBasicBlock *BB = Node->getBlock();
+ bool Changed = false;
+
+ // Traverse the current block.
+ for (MachineBasicBlock::iterator I = BB->begin(), E = BB->end(); I != E;
+ ++I) {
+ switch (I->getOpcode()) {
+ case X86::TLS_base_addr32:
+ case X86::TLS_base_addr64:
+ if (TLSBaseAddrReg)
+ I = ReplaceTLSBaseAddrCall(I, TLSBaseAddrReg);
+ else
+ I = SetRegister(I, &TLSBaseAddrReg);
+ Changed = true;
+ break;
+ default:
+ break;
+ }
+ }
+
+ // Visit the children of this block in the dominator tree.
+ for (MachineDomTreeNode::iterator I = Node->begin(), E = Node->end();
+ I != E; ++I) {
+ Changed |= VisitNode(*I, TLSBaseAddrReg);
+ }
+
+ return Changed;
+ }
+
+ // Replace the TLS_base_addr instruction I with a copy from
+ // TLSBaseAddrReg, returning the new instruction.
+ MachineInstr *ReplaceTLSBaseAddrCall(MachineInstr *I,
+ unsigned TLSBaseAddrReg) {
+ MachineFunction *MF = I->getParent()->getParent();
+ const X86TargetMachine *TM =
+ static_cast<const X86TargetMachine *>(&MF->getTarget());
+ const bool is64Bit = TM->getSubtarget<X86Subtarget>().is64Bit();
+ const X86InstrInfo *TII = TM->getInstrInfo();
+
+ // Insert a Copy from TLSBaseAddrReg to RAX/EAX.
+ MachineInstr *Copy = BuildMI(*I->getParent(), I, I->getDebugLoc(),
+ TII->get(TargetOpcode::COPY),
+ is64Bit ? X86::RAX : X86::EAX)
+ .addReg(TLSBaseAddrReg);
+
+ // Erase the TLS_base_addr instruction.
+ I->eraseFromParent();
+
+ return Copy;
+ }
+
+ // Create a virtal register in *TLSBaseAddrReg, and populate it by
+ // inserting a copy instruction after I. Returns the new instruction.
+ MachineInstr *SetRegister(MachineInstr *I, unsigned *TLSBaseAddrReg) {
+ MachineFunction *MF = I->getParent()->getParent();
+ const X86TargetMachine *TM =
+ static_cast<const X86TargetMachine *>(&MF->getTarget());
+ const bool is64Bit = TM->getSubtarget<X86Subtarget>().is64Bit();
+ const X86InstrInfo *TII = TM->getInstrInfo();
+
+ // Create a virtual register for the TLS base address.
+ MachineRegisterInfo &RegInfo = MF->getRegInfo();
+ *TLSBaseAddrReg = RegInfo.createVirtualRegister(is64Bit
+ ? &X86::GR64RegClass
+ : &X86::GR32RegClass);
+
+ // Insert a copy from RAX/EAX to TLSBaseAddrReg.
+ MachineInstr *Next = I->getNextNode();
+ MachineInstr *Copy = BuildMI(*I->getParent(), Next, I->getDebugLoc(),
+ TII->get(TargetOpcode::COPY),
+ *TLSBaseAddrReg)
+ .addReg(is64Bit ? X86::RAX : X86::EAX);
+
+ return Copy;
+ }
+
+ virtual const char *getPassName() const {
+ return "Local Dynamic TLS Access Clean-up";
+ }
+
+ virtual void getAnalysisUsage(AnalysisUsage &AU) const {
+ AU.setPreservesCFG();
+ AU.addRequired<MachineDominatorTree>();
+ MachineFunctionPass::getAnalysisUsage(AU);
+ }
+ };
+}
+
+char LDTLSCleanup::ID = 0;
+FunctionPass*
+llvm::createCleanupLocalDynamicTLSPass() { return new LDTLSCleanup(); }