#include "X86InstrInfo.h"
#include "X86.h"
-#include "X86GenInstrInfo.inc"
#include "X86InstrBuilder.h"
#include "X86MachineFunctionInfo.h"
#include "X86Subtarget.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 - 7)
+ TB_INDEX_0 = 0,
+ TB_INDEX_1 = 1,
+ TB_INDEX_2 = 2,
+ TB_INDEX_MASK = 0xff,
+
+ // 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,
+
+ // 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 << 16,
+
+ // 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 << 17,
+
+ TB_FOLDED_LOAD = 1 << 18,
+ TB_FOLDED_STORE = 1 << 19
+};
+
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) {
- SmallVector<unsigned,16> AmbEntries;
- 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::ADD16rr, X86::ADD16mr },
- { X86::ADD32ri, X86::ADD32mi },
- { X86::ADD32ri8, X86::ADD32mi8 },
- { X86::ADD32rr, X86::ADD32mr },
- { X86::ADD64ri32, X86::ADD64mi32 },
- { X86::ADD64ri8, X86::ADD64mi8 },
- { X86::ADD64rr, X86::ADD64mr },
- { 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 unsigned OpTbl2Addr[][3] = {
+ { 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];
- if (!RegOp2MemOpTable2Addr.insert(std::make_pair((unsigned*)RegOp,
- std::make_pair(MemOp,0))).second)
- assert(false && "Duplicated entries?");
- // Index 0, folded load and store, no alignment requirement.
- unsigned AuxInfo = 0 | (1 << 4) | (1 << 5);
- if (!MemOp2RegOpTable.insert(std::make_pair((unsigned*)MemOp,
- std::make_pair(RegOp,
- AuxInfo))).second)
- AmbEntries.push_back(MemOp);
- }
-
- // 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::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, 0, 0 },
- { X86::FsMOVAPSrr, X86::MOVSSmr, 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::MOV32rr_TC, X86::MOV32mr_TC, 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 Flags = OpTbl2Addr[i][2];
+ 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 unsigned OpTbl0[][3] = {
+ { 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::WINCALL64r, X86::WINCALL64m, 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::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::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];
- unsigned Align = OpTbl0[i][3];
- if (!RegOp2MemOpTable0.insert(std::make_pair((unsigned*)RegOp,
- std::make_pair(MemOp,Align))).second)
- assert(false && "Duplicated entries?");
- unsigned FoldedLoad = OpTbl0[i][2];
- // Index 0, folded load or store.
- unsigned AuxInfo = 0 | (FoldedLoad << 4) | ((FoldedLoad^1) << 5);
- if (RegOp != X86::FsMOVAPDrr && RegOp != X86::FsMOVAPSrr)
- if (!MemOp2RegOpTable.insert(std::make_pair((unsigned*)MemOp,
- std::make_pair(RegOp, AuxInfo))).second)
- AmbEntries.push_back(MemOp);
+ unsigned RegOp = OpTbl0[i][0];
+ unsigned MemOp = OpTbl0[i][1];
+ unsigned Flags = OpTbl0[i][2];
+ AddTableEntry(RegOp2MemOpTable0, MemOp2RegOpTable,
+ RegOp, MemOp, TB_INDEX_0 | Flags);
}
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, 0 },
- { X86::FsMOVAPSrr, X86::MOVSSrm, 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::Int_CVTSD2SI64rr,X86::Int_CVTSD2SI64rm, 0 },
- { X86::Int_CVTSD2SIrr, X86::Int_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::Int_CVTTPD2DQrr, X86::Int_CVTTPD2DQrm, 16 },
- { X86::Int_CVTTPS2DQrr, X86::Int_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::MOV32rr_TC, X86::MOV32rm_TC, 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 },
+ { 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::Int_CVTDQ2PDrr, X86::Int_CVTDQ2PDrm, TB_ALIGN_16 },
+ { X86::Int_CVTDQ2PSrr, X86::Int_CVTDQ2PSrm, TB_ALIGN_16 },
+ { X86::Int_CVTPD2DQrr, X86::Int_CVTPD2DQrm, TB_ALIGN_16 },
+ { X86::Int_CVTPD2PSrr, X86::Int_CVTPD2PSrm, TB_ALIGN_16 },
+ { X86::Int_CVTPS2DQrr, X86::Int_CVTPS2DQrm, TB_ALIGN_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::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::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_VCVTDQ2PDrr, X86::Int_VCVTDQ2PDrm, TB_ALIGN_16 },
+ { X86::Int_VCVTDQ2PSrr, X86::Int_VCVTDQ2PSrm, TB_ALIGN_16 },
+ { X86::Int_VCVTPD2DQrr, X86::Int_VCVTPD2DQrm, TB_ALIGN_16 },
+ { X86::Int_VCVTPD2PSrr, X86::Int_VCVTPD2PSrm, TB_ALIGN_16 },
+ { X86::Int_VCVTPS2DQrr, X86::Int_VCVTPS2DQrm, TB_ALIGN_16 },
+ { X86::Int_VCVTPS2PDrr, X86::Int_VCVTPS2PDrm, 0 },
+ { X86::Int_VUCOMISDrr, X86::Int_VUCOMISDrm, 0 },
+ { X86::Int_VUCOMISSrr, X86::Int_VUCOMISSrm, 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::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_16 },
+ { X86::VMOVUPDYrr, X86::VMOVUPDYrm, 0 },
+ { X86::VMOVUPSYrr, X86::VMOVUPSYrm, 0 }
};
for (unsigned i = 0, e = array_lengthof(OpTbl1); i != e; ++i) {
unsigned RegOp = OpTbl1[i][0];
unsigned MemOp = OpTbl1[i][1];
- unsigned Align = OpTbl1[i][2];
- if (!RegOp2MemOpTable1.insert(std::make_pair((unsigned*)RegOp,
- std::make_pair(MemOp,Align))).second)
- assert(false && "Duplicated entries?");
- // Index 1, folded load
- unsigned AuxInfo = 1 | (1 << 4);
- if (RegOp != X86::FsMOVAPDrr && RegOp != X86::FsMOVAPSrr)
- if (!MemOp2RegOpTable.insert(std::make_pair((unsigned*)MemOp,
- std::make_pair(RegOp, AuxInfo))).second)
- AmbEntries.push_back(MemOp);
+ unsigned Flags = OpTbl1[i][2];
+ AddTableEntry(RegOp2MemOpTable1, MemOp2RegOpTable,
+ RegOp, MemOp,
+ // Index 1, folded load
+ Flags | TB_INDEX_1 | TB_FOLDED_LOAD);
}
static const unsigned OpTbl2[][3] = {
- { X86::ADC32rr, X86::ADC32rm, 0 },
- { X86::ADC64rr, X86::ADC64rm, 0 },
- { X86::ADD16rr, X86::ADD16rm, 0 },
- { X86::ADD32rr, X86::ADD32rm, 0 },
- { X86::ADD64rr, X86::ADD64rm, 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 },
+ { 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::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::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::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::PADDWrr, X86::PADDWrm, 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::PCMPEQBrr, X86::PCMPEQBrm, TB_ALIGN_16 },
+ { X86::PCMPEQDrr, X86::PCMPEQDrm, 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::PCMPGTWrr, X86::PCMPGTWrm, TB_ALIGN_16 },
+ { X86::PINSRWrri, X86::PINSRWrmi, 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::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::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::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::VCVTTPD2DQrr, X86::VCVTTPD2DQrm, 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::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::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::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::VPADDWrr, X86::VPADDWrm, TB_ALIGN_16 },
+ { X86::VPANDNrr, X86::VPANDNrm, TB_ALIGN_16 },
+ { X86::VPANDrr, X86::VPANDrm, TB_ALIGN_16 },
+ { X86::VPCMPEQBrr, X86::VPCMPEQBrm, TB_ALIGN_16 },
+ { X86::VPCMPEQDrr, X86::VPCMPEQDrm, 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::VPCMPGTWrr, X86::VPCMPGTWrm, TB_ALIGN_16 },
+ { X86::VPINSRWrri, X86::VPINSRWrmi, 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::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::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 }
+ // 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];
- unsigned Align = OpTbl2[i][2];
- if (!RegOp2MemOpTable2.insert(std::make_pair((unsigned*)RegOp,
- std::make_pair(MemOp,Align))).second)
- assert(false && "Duplicated entries?");
- // Index 2, folded load
- unsigned AuxInfo = 2 | (1 << 4);
- if (!MemOp2RegOpTable.insert(std::make_pair((unsigned*)MemOp,
- std::make_pair(RegOp, AuxInfo))).second)
- AmbEntries.push_back(MemOp);
- }
-
- // Remove ambiguous entries.
- assert(AmbEntries.empty() && "Duplicated entries in unfolding maps?");
+ unsigned Flags = OpTbl2[i][2];
+ AddTableEntry(RegOp2MemOpTable2, MemOp2RegOpTable,
+ RegOp, MemOp,
+ // Index 2, folded load
+ Flags | TB_INDEX_2 | TB_FOLDED_LOAD);
+ }
}
-bool X86InstrInfo::isMoveInstr(const MachineInstr& MI,
- unsigned &SrcReg, unsigned &DstReg,
- unsigned &SrcSubIdx, unsigned &DstSubIdx) const {
- switch (MI.getOpcode()) {
- default:
- return false;
- case X86::MOV8rr:
- case X86::MOV8rr_NOREX:
- case X86::MOV16rr:
- case X86::MOV32rr:
- case X86::MOV64rr:
- case X86::MOV32rr_TC:
- case X86::MOV64rr_TC:
-
- // FP Stack register class copies
- case X86::MOV_Fp3232: case X86::MOV_Fp6464: case X86::MOV_Fp8080:
- case X86::MOV_Fp3264: case X86::MOV_Fp3280:
- case X86::MOV_Fp6432: case X86::MOV_Fp8032:
-
- // Note that MOVSSrr and MOVSDrr are not considered copies. FR32 and FR64
- // copies are done with FsMOVAPSrr and FsMOVAPDrr.
-
- case X86::FsMOVAPSrr:
- case X86::FsMOVAPDrr:
- case X86::MOVAPSrr:
- case X86::MOVAPDrr:
- case X86::MOVDQArr:
- case X86::MMX_MOVQ64rr:
- assert(MI.getNumOperands() >= 2 &&
- MI.getOperand(0).isReg() &&
- MI.getOperand(1).isReg() &&
- "invalid register-register move instruction");
- SrcReg = MI.getOperand(1).getReg();
- DstReg = MI.getOperand(0).getReg();
- SrcSubIdx = MI.getOperand(1).getSubReg();
- DstSubIdx = MI.getOperand(0).getSubReg();
- return true;
- }
+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
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;
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 (isFrameOperand(MI, 1, FrameIndex))
+ if (MI->getOperand(0).getSubReg() == 0 && isFrameOperand(MI, 1, FrameIndex))
return MI->getOperand(0).getReg();
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()))
- if (isFrameOperand(MI, 0, FrameIndex))
- return MI->getOperand(X86AddrNumOperands).getReg();
+ if (MI->getOperand(X86::AddrNumOperands).getSubReg() == 0 &&
+ isFrameOperand(MI, 0, FrameIndex))
+ return MI->getOperand(X86::AddrNumOperands).getReg();
return 0;
}
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);
// 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();
unsigned Opc = TM.getSubtarget<X86Subtarget>().is64Bit()
? X86::LEA64_32r : X86::LEA32r;
MachineRegisterInfo &RegInfo = MFI->getParent()->getRegInfo();
- unsigned leaInReg = RegInfo.createVirtualRegister(&X86::GR32RegClass);
+ 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
case X86::SHL16ri: {
unsigned ShAmt = MI->getOperand(2).getImm();
MIB.addReg(0).addImm(1 << ShAmt)
- .addReg(leaInReg, RegState::Kill).addImm(0);
+ .addReg(leaInReg, RegState::Kill).addImm(0).addReg(0);
break;
}
case X86::INC16r:
case X86::INC64_16r:
- addLeaRegOffset(MIB, leaInReg, true, 1);
+ addRegOffset(MIB, leaInReg, true, 1);
break;
case X86::DEC16r:
case X86::DEC64_16r:
- addLeaRegOffset(MIB, leaInReg, true, -1);
+ addRegOffset(MIB, leaInReg, true, -1);
break;
case X86::ADD16ri:
case X86::ADD16ri8:
- addLeaRegOffset(MIB, leaInReg, true, MI->getOperand(2).getImm());
+ case X86::ADD16ri_DB:
+ case X86::ADD16ri8_DB:
+ addRegOffset(MIB, leaInReg, true, MI->getOperand(2).getImm());
break;
- case X86::ADD16rr: {
+ case X86::ADD16rr:
+ case X86::ADD16rr_DB: {
unsigned Src2 = MI->getOperand(2).getReg();
bool isKill2 = MI->getOperand(2).isKill();
unsigned leaInReg2 = 0;
// just a single insert_subreg.
addRegReg(MIB, leaInReg, true, leaInReg, false);
} else {
- leaInReg2 = RegInfo.createVirtualRegister(&X86::GR32RegClass);
+ 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.
+ // 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))
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;
unsigned ShAmt = MI->getOperand(2).getImm();
if (ShAmt == 0 || ShAmt >= 4) return 0;
+ // LEA can't handle RSP.
+ if (TargetRegisterInfo::isVirtualRegister(Src) &&
+ !MF.getRegInfo().constrainRegClass(Src, &X86::GR64_NOSPRegClass))
+ return 0;
+
NewMI = BuildMI(MF, MI->getDebugLoc(), get(X86::LEA64r))
.addReg(Dest, RegState::Define | getDeadRegState(isDead))
.addReg(0).addImm(1 << ShAmt)
.addReg(Src, getKillRegState(isKill))
- .addImm(0);
+ .addImm(0).addReg(0);
break;
}
case X86::SHL32ri: {
unsigned ShAmt = MI->getOperand(2).getImm();
if (ShAmt == 0 || ShAmt >= 4) return 0;
+ // LEA can't handle ESP.
+ if (TargetRegisterInfo::isVirtualRegister(Src) &&
+ !MF.getRegInfo().constrainRegClass(Src, &X86::GR32_NOSPRegClass))
+ return 0;
+
unsigned Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
NewMI = BuildMI(MF, MI->getDebugLoc(), get(Opc))
.addReg(Dest, RegState::Define | getDeadRegState(isDead))
.addReg(0).addImm(1 << ShAmt)
- .addReg(Src, getKillRegState(isKill)).addImm(0);
+ .addReg(Src, getKillRegState(isKill)).addImm(0).addReg(0);
break;
}
case X86::SHL16ri: {
.addReg(Dest, RegState::Define | getDeadRegState(isDead))
.addReg(0).addImm(1 << ShAmt)
.addReg(Src, getKillRegState(isKill))
- .addImm(0);
+ .addImm(0).addReg(0);
break;
}
default: {
assert(MI->getNumOperands() >= 2 && "Unknown inc instruction!");
unsigned Opc = MIOpc == X86::INC64r ? X86::LEA64r
: (is64Bit ? X86::LEA64_32r : X86::LEA32r);
- NewMI = addLeaRegOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
+
+ // LEA can't handle RSP.
+ if (TargetRegisterInfo::isVirtualRegister(Src) &&
+ !MF.getRegInfo().constrainRegClass(Src,
+ MIOpc == X86::INC64r ? X86::GR64_NOSPRegisterClass :
+ X86::GR32_NOSPRegisterClass))
+ return 0;
+
+ NewMI = addRegOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
.addReg(Dest, RegState::Define |
getDeadRegState(isDead)),
Src, isKill, 1);
assert(MI->getNumOperands() >= 2 && "Unknown dec instruction!");
unsigned Opc = MIOpc == X86::DEC64r ? X86::LEA64r
: (is64Bit ? X86::LEA64_32r : X86::LEA32r);
- NewMI = addLeaRegOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
+ // LEA can't handle RSP.
+ if (TargetRegisterInfo::isVirtualRegister(Src) &&
+ !MF.getRegInfo().constrainRegClass(Src,
+ MIOpc == X86::DEC64r ? X86::GR64_NOSPRegisterClass :
+ X86::GR32_NOSPRegisterClass))
+ return 0;
+
+ NewMI = addRegOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
.addReg(Dest, RegState::Define |
getDeadRegState(isDead)),
Src, isKill, -1);
Src, isKill, -1);
break;
case X86::ADD64rr:
- case X86::ADD32rr: {
+ case X86::ADD64rr_DB:
+ case X86::ADD32rr:
+ case X86::ADD32rr_DB: {
assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
- unsigned Opc = MIOpc == X86::ADD64rr ? X86::LEA64r
- : (is64Bit ? X86::LEA64_32r : X86::LEA32r);
+ unsigned Opc;
+ TargetRegisterClass *RC;
+ if (MIOpc == X86::ADD64rr || MIOpc == X86::ADD64rr_DB) {
+ Opc = X86::LEA64r;
+ RC = X86::GR64_NOSPRegisterClass;
+ } else {
+ Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
+ RC = X86::GR32_NOSPRegisterClass;
+ }
+
+
unsigned Src2 = MI->getOperand(2).getReg();
bool isKill2 = MI->getOperand(2).isKill();
+
+ // LEA can't handle RSP.
+ if (TargetRegisterInfo::isVirtualRegister(Src2) &&
+ !MF.getRegInfo().constrainRegClass(Src2, RC))
+ return 0;
+
NewMI = addRegReg(BuildMI(MF, MI->getDebugLoc(), get(Opc))
.addReg(Dest, RegState::Define |
getDeadRegState(isDead)),
LV->replaceKillInstruction(Src2, MI, NewMI);
break;
}
- case X86::ADD16rr: {
+ case X86::ADD16rr:
+ case X86::ADD16rr_DB: {
if (DisableLEA16)
return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV) : 0;
assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
}
case X86::ADD64ri32:
case X86::ADD64ri8:
+ case X86::ADD64ri32_DB:
+ case X86::ADD64ri8_DB:
assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
- NewMI = addLeaRegOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA64r))
+ NewMI = addRegOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA64r))
.addReg(Dest, RegState::Define |
getDeadRegState(isDead)),
Src, isKill, MI->getOperand(2).getImm());
break;
case X86::ADD32ri:
- case X86::ADD32ri8: {
+ case X86::ADD32ri8:
+ case X86::ADD32ri_DB:
+ case X86::ADD32ri8_DB: {
assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
unsigned Opc = is64Bit ? X86::LEA64_32r : X86::LEA32r;
- NewMI = addLeaRegOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
+ NewMI = addRegOffset(BuildMI(MF, MI->getDebugLoc(), get(Opc))
.addReg(Dest, RegState::Define |
getDeadRegState(isDead)),
Src, isKill, MI->getOperand(2).getImm());
}
case X86::ADD16ri:
case X86::ADD16ri8:
+ case X86::ADD16ri_DB:
+ case X86::ADD16ri8_DB:
if (DisableLEA16)
return is64Bit ? convertToThreeAddressWithLEA(MIOpc, MFI, MBBI, LV) : 0;
assert(MI->getNumOperands() >= 3 && "Unknown add instruction!");
- NewMI = addLeaRegOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
+ NewMI = addRegOffset(BuildMI(MF, MI->getDebugLoc(), get(X86::LEA16r))
.addReg(Dest, RegState::Define |
getDeadRegState(isDead)),
Src, isKill, MI->getOperand(2).getImm());
LV->replaceKillInstruction(Dest, MI, NewMI);
}
- MFI->insert(MBBI, NewMI); // Insert the new inst
+ MFI->insert(MBBI, NewMI); // Insert the new inst
return NewMI;
}
}
bool X86InstrInfo::isUnpredicatedTerminator(const MachineInstr *MI) const {
- const TargetInstrDesc &TID = MI->getDesc();
- if (!TID.isTerminator()) return false;
-
+ const MCInstrDesc &MCID = MI->getDesc();
+ if (!MCID.isTerminator()) return false;
+
// Conditional branch is a special case.
- if (TID.isBranch() && !TID.isBarrier())
+ if (MCID.isBranch() && !MCID.isBarrier())
return true;
- if (!TID.isPredicable())
+ if (!MCID.isPredicable())
return true;
return !isPredicated(MI);
}
-// For purposes of branch analysis do not count FP_REG_KILL as a terminator.
-static bool isBrAnalysisUnpredicatedTerminator(const MachineInstr *MI,
- const X86InstrInfo &TII) {
- if (MI->getOpcode() == X86::FP_REG_KILL)
- return false;
- return TII.isUnpredicatedTerminator(MI);
-}
-
-bool X86InstrInfo::AnalyzeBranch(MachineBasicBlock &MBB,
+bool X86InstrInfo::AnalyzeBranch(MachineBasicBlock &MBB,
MachineBasicBlock *&TBB,
MachineBasicBlock *&FBB,
SmallVectorImpl<MachineOperand> &Cond,
// Working from the bottom, when we see a non-terminator instruction, we're
// done.
- if (!isBrAnalysisUnpredicatedTerminator(I, *this))
+ if (!isUnpredicatedTerminator(I))
break;
// A terminator that isn't a branch can't easily be handled by this
.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 X86::GR8_ABCD_HRegClass.contains(Reg);
}
-bool X86InstrInfo::copyRegToReg(MachineBasicBlock &MBB,
- MachineBasicBlock::iterator MI,
- unsigned DestReg, unsigned SrcReg,
- const TargetRegisterClass *DestRC,
- const TargetRegisterClass *SrcRC,
- DebugLoc DL) const {
-
- // Determine if DstRC and SrcRC have a common superclass in common.
- const TargetRegisterClass *CommonRC = DestRC;
- if (DestRC == SrcRC)
- /* Source and destination have the same register class. */;
- else if (CommonRC->hasSuperClass(SrcRC))
- CommonRC = SrcRC;
- else if (!DestRC->hasSubClass(SrcRC)) {
- // Neither of GR64_NOREX or GR64_NOSP is a superclass of the other,
- // but we want to copy them as GR64. Similarly, for GR32_NOREX and
- // GR32_NOSP, copy as GR32.
- if (SrcRC->hasSuperClass(&X86::GR64RegClass) &&
- DestRC->hasSuperClass(&X86::GR64RegClass))
- CommonRC = &X86::GR64RegClass;
- else if (SrcRC->hasSuperClass(&X86::GR32RegClass) &&
- DestRC->hasSuperClass(&X86::GR32RegClass))
- CommonRC = &X86::GR32RegClass;
- else if (SrcRC->hasSuperClass(&X86::GR8RegClass) &&
- DestRC->hasSuperClass(&X86::GR8RegClass))
- CommonRC = &X86::GR8RegClass;
- else
- CommonRC = 0;
- }
+// Try and copy between VR128/VR64 and GR64 registers.
+static unsigned CopyToFromAsymmetricReg(unsigned DestReg, unsigned SrcReg,
+ bool HasAVX) {
+ // SrcReg(VR128) -> DestReg(GR64)
+ // SrcReg(VR64) -> DestReg(GR64)
+ // SrcReg(GR64) -> DestReg(VR128)
+ // SrcReg(GR64) -> DestReg(VR64)
- if (CommonRC) {
- unsigned Opc;
- if (CommonRC == &X86::GR64RegClass || CommonRC == &X86::GR64_NOSPRegClass) {
- Opc = X86::MOV64rr;
- } else if (CommonRC == &X86::GR32RegClass ||
- CommonRC == &X86::GR32_NOSPRegClass) {
- Opc = X86::MOV32rr;
- } else if (CommonRC == &X86::GR16RegClass) {
- Opc = X86::MOV16rr;
- } else if (CommonRC == &X86::GR8RegClass) {
- // 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) ||
- SrcRC == &X86::GR8_ABCD_HRegClass ||
- DestRC == &X86::GR8_ABCD_HRegClass) &&
- TM.getSubtarget<X86Subtarget>().is64Bit())
- Opc = X86::MOV8rr_NOREX;
- else
- Opc = X86::MOV8rr;
- } else if (CommonRC == &X86::GR64_ABCDRegClass) {
- Opc = X86::MOV64rr;
- } else if (CommonRC == &X86::GR32_ABCDRegClass) {
- Opc = X86::MOV32rr;
- } else if (CommonRC == &X86::GR16_ABCDRegClass) {
- Opc = X86::MOV16rr;
- } else if (CommonRC == &X86::GR8_ABCD_LRegClass) {
- Opc = X86::MOV8rr;
- } else if (CommonRC == &X86::GR8_ABCD_HRegClass) {
- if (TM.getSubtarget<X86Subtarget>().is64Bit())
- Opc = X86::MOV8rr_NOREX;
- else
- Opc = X86::MOV8rr;
- } else if (CommonRC == &X86::GR64_NOREXRegClass ||
- CommonRC == &X86::GR64_NOREX_NOSPRegClass) {
- Opc = X86::MOV64rr;
- } else if (CommonRC == &X86::GR32_NOREXRegClass) {
- Opc = X86::MOV32rr;
- } else if (CommonRC == &X86::GR16_NOREXRegClass) {
- Opc = X86::MOV16rr;
- } else if (CommonRC == &X86::GR8_NOREXRegClass) {
- Opc = X86::MOV8rr;
- } else if (CommonRC == &X86::GR64_TCRegClass) {
- Opc = X86::MOV64rr_TC;
- } else if (CommonRC == &X86::GR32_TCRegClass) {
- Opc = X86::MOV32rr_TC;
- } else if (CommonRC == &X86::RFP32RegClass) {
- Opc = X86::MOV_Fp3232;
- } else if (CommonRC == &X86::RFP64RegClass || CommonRC == &X86::RSTRegClass) {
- Opc = X86::MOV_Fp6464;
- } else if (CommonRC == &X86::RFP80RegClass) {
- Opc = X86::MOV_Fp8080;
- } else if (CommonRC == &X86::FR32RegClass) {
- Opc = X86::FsMOVAPSrr;
- } else if (CommonRC == &X86::FR64RegClass) {
- Opc = X86::FsMOVAPDrr;
- } else if (CommonRC == &X86::VR128RegClass) {
- Opc = X86::MOVAPSrr;
- } else if (CommonRC == &X86::VR64RegClass) {
- Opc = X86::MMX_MOVQ64rr;
- } else {
- return false;
+ if (X86::GR64RegClass.contains(DestReg)) {
+ if (X86::VR128RegClass.contains(SrcReg)) {
+ // Copy from a VR128 register to a GR64 register.
+ return HasAVX ? X86::VMOVPQIto64rr : X86::MOVPQIto64rr;
+ } else if (X86::VR64RegClass.contains(SrcReg)) {
+ // Copy from a VR64 register to a GR64 register.
+ return X86::MOVSDto64rr;
}
- BuildMI(MBB, MI, DL, get(Opc), DestReg).addReg(SrcReg);
- return true;
+ } else if (X86::GR64RegClass.contains(SrcReg)) {
+ // Copy from a GR64 register to a VR128 register.
+ if (X86::VR128RegClass.contains(DestReg))
+ return HasAVX ? X86::VMOV64toPQIrr : X86::MOV64toPQIrr;
+ // Copy from a GR64 register to a VR64 register.
+ else if (X86::VR64RegClass.contains(DestReg))
+ return X86::MOV64toSDrr;
}
- // Moving EFLAGS to / from another register requires a push and a pop.
- if (SrcRC == &X86::CCRRegClass) {
- if (SrcReg != X86::EFLAGS)
- return false;
- if (DestRC == &X86::GR64RegClass || DestRC == &X86::GR64_NOSPRegClass) {
- BuildMI(MBB, MI, DL, get(X86::PUSHF64));
- BuildMI(MBB, MI, DL, get(X86::POP64r), DestReg);
- return true;
- } else if (DestRC == &X86::GR32RegClass ||
- DestRC == &X86::GR32_NOSPRegClass) {
- BuildMI(MBB, MI, DL, get(X86::PUSHF32));
- BuildMI(MBB, MI, DL, get(X86::POP32r), DestReg);
- return true;
- }
- } else if (DestRC == &X86::CCRRegClass) {
- if (DestReg != X86::EFLAGS)
- return false;
- if (SrcRC == &X86::GR64RegClass || DestRC == &X86::GR64_NOSPRegClass) {
- BuildMI(MBB, MI, DL, get(X86::PUSH64r)).addReg(SrcReg);
- BuildMI(MBB, MI, DL, get(X86::POPF64));
- return true;
- } else if (SrcRC == &X86::GR32RegClass ||
- DestRC == &X86::GR32_NOSPRegClass) {
- BuildMI(MBB, MI, DL, get(X86::PUSH32r)).addReg(SrcReg);
- BuildMI(MBB, MI, DL, get(X86::POPF32));
- return true;
- }
- }
-
- // Moving from ST(0) turns into FpGET_ST0_32 etc.
- if (SrcRC == &X86::RSTRegClass) {
- // Copying from ST(0)/ST(1).
- if (SrcReg != X86::ST0 && SrcReg != X86::ST1)
- // Can only copy from ST(0)/ST(1) right now
- return false;
- bool isST0 = SrcReg == X86::ST0;
- unsigned Opc;
- if (DestRC == &X86::RFP32RegClass)
- Opc = isST0 ? X86::FpGET_ST0_32 : X86::FpGET_ST1_32;
- else if (DestRC == &X86::RFP64RegClass)
- Opc = isST0 ? X86::FpGET_ST0_64 : X86::FpGET_ST1_64;
- else {
- if (DestRC != &X86::RFP80RegClass)
- return false;
- Opc = isST0 ? X86::FpGET_ST0_80 : X86::FpGET_ST1_80;
- }
- BuildMI(MBB, MI, DL, get(Opc), DestReg);
- return true;
- }
-
- // Moving to ST(0) turns into FpSET_ST0_32 etc.
- if (DestRC == &X86::RSTRegClass) {
- // Copying to ST(0) / ST(1).
- if (DestReg != X86::ST0 && DestReg != X86::ST1)
- // Can only copy to TOS right now
- return false;
- bool isST0 = DestReg == X86::ST0;
- unsigned Opc;
- if (SrcRC == &X86::RFP32RegClass)
- Opc = isST0 ? X86::FpSET_ST0_32 : X86::FpSET_ST1_32;
- else if (SrcRC == &X86::RFP64RegClass)
- Opc = isST0 ? X86::FpSET_ST0_64 : X86::FpSET_ST1_64;
- else {
- if (SrcRC != &X86::RFP80RegClass)
- return false;
- Opc = isST0 ? X86::FpSET_ST0_80 : X86::FpSET_ST1_80;
- }
- BuildMI(MBB, MI, DL, get(Opc)).addReg(SrcReg);
- return true;
- }
-
- // Not yet supported!
- return false;
+ return 0;
}
void X86InstrInfo::copyPhysReg(MachineBasicBlock &MBB,
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;
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, HasAVX);
if (Opc) {
BuildMI(MBB, MI, DL, get(Opc), DestReg)
bool isStackAligned,
const TargetMachine &TM,
bool load) {
- if (RC == &X86::GR64RegClass || RC == &X86::GR64_NOSPRegClass) {
- return load ? X86::MOV64rm : X86::MOV64mr;
- } else if (RC == &X86::GR32RegClass || RC == &X86::GR32_NOSPRegClass) {
- return load ? X86::MOV32rm : X86::MOV32mr;
- } else if (RC == &X86::GR16RegClass) {
- return load ? X86::MOV16rm : X86::MOV16mr;
- } else if (RC == &X86::GR8RegClass) {
- // 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;
- } else if (RC == &X86::GR64_ABCDRegClass) {
- return load ? X86::MOV64rm : X86::MOV64mr;
- } else if (RC == &X86::GR32_ABCDRegClass) {
- return load ? X86::MOV32rm : X86::MOV32mr;
- } else if (RC == &X86::GR16_ABCDRegClass) {
- return load ? X86::MOV16rm : X86::MOV16mr;
- } else if (RC == &X86::GR8_ABCD_LRegClass) {
- return load ? X86::MOV8rm :X86::MOV8mr;
- } else if (RC == &X86::GR8_ABCD_HRegClass) {
+ bool HasAVX = TM.getSubtarget<X86Subtarget>().hasAVX();
+ switch (RC->getSize()) {
+ default:
+ 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;
- } else if (RC == &X86::GR64_NOREXRegClass ||
- RC == &X86::GR64_NOREX_NOSPRegClass) {
- return load ? X86::MOV64rm : X86::MOV64mr;
- } else if (RC == &X86::GR32_NOREXRegClass) {
- return load ? X86::MOV32rm : X86::MOV32mr;
- } else if (RC == &X86::GR16_NOREXRegClass) {
- return load ? X86::MOV16rm : X86::MOV16mr;
- } else if (RC == &X86::GR8_NOREXRegClass) {
+ // 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;
- } else if (RC == &X86::GR64_TCRegClass) {
- return load ? X86::MOV64rm_TC : X86::MOV64mr_TC;
- } else if (RC == &X86::GR32_TCRegClass) {
- return load ? X86::MOV32rm_TC : X86::MOV32mr_TC;
- } else if (RC == &X86::RFP80RegClass) {
+ 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;
- } else if (RC == &X86::RFP64RegClass) {
- return load ? X86::LD_Fp64m : X86::ST_Fp64m;
- } else if (RC == &X86::RFP32RegClass) {
- return load ? X86::LD_Fp32m : X86::ST_Fp32m;
- } else if (RC == &X86::FR32RegClass) {
- return load ? X86::MOVSSrm : X86::MOVSSmr;
- } else if (RC == &X86::FR64RegClass) {
- return load ? X86::MOVSDrm : X86::MOVSDmr;
- } else if (RC == &X86::VR128RegClass) {
+ case 16: {
+ assert(X86::VR128RegClass.hasSubClassEq(RC) && "Unknown 16-byte regclass");
// If stack is realigned we can use aligned stores.
if (isStackAligned)
- return load ? X86::MOVAPSrm : X86::MOVAPSmr;
+ return load ?
+ (HasAVX ? X86::VMOVAPSrm : X86::MOVAPSrm) :
+ (HasAVX ? X86::VMOVAPSmr : X86::MOVAPSmr);
else
- return load ? X86::MOVUPSrm : X86::MOVUPSmr;
- } else if (RC == &X86::VR64RegClass) {
- return load ? X86::MMX_MOVQ64rm : X86::MMX_MOVQ64mr;
- } else {
- llvm_unreachable("Unknown regclass");
+ 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::VMOVAPSYrm : X86::VMOVAPSYmr;
+ else
+ return load ? X86::VMOVUPSYrm : X86::VMOVUPSYmr;
}
}
const TargetRegisterClass *RC,
const TargetRegisterInfo *TRI) const {
const MachineFunction &MF = *MBB.getParent();
- bool isAligned = (RI.getStackAlignment() >= 16) || RI.canRealignStack(MF);
+ assert(MF.getFrameInfo()->getObjectSize(FrameIdx) >= RC->getSize() &&
+ "Stack slot too small for store");
+ 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 && (*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 && (*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;
-
- DebugLoc DL = MBB.findDebugLoc(MI);
-
- bool is64Bit = TM.getSubtarget<X86Subtarget>().is64Bit();
- bool isWin64 = TM.getSubtarget<X86Subtarget>().isTargetWin64();
- unsigned SlotSize = is64Bit ? 8 : 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 {
- storeRegToStackSlot(MBB, MI, Reg, true, CSI[i-1].getFrameIdx(),
- &X86::VR128RegClass, &RI);
- }
- }
-
- X86FI->setCalleeSavedFrameSize(CalleeFrameSize);
- return true;
-}
-
-bool X86InstrInfo::restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
- MachineBasicBlock::iterator MI,
- const std::vector<CalleeSavedInfo> &CSI,
- const TargetRegisterInfo *TRI) const {
- if (CSI.empty())
- return false;
-
- DebugLoc DL = MBB.findDebugLoc(MI);
-
- 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.
- continue;
- if (!X86::VR128RegClass.contains(Reg) && !isWin64) {
- BuildMI(MBB, MI, DL, get(Opc), Reg);
- } else {
- loadRegFromStackSlot(MBB, MI, Reg, CSI[i].getFrameIdx(),
- &X86::VR128RegClass, &RI);
- }
- }
- return true;
-}
-
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) {
MachineInstr *MI, unsigned i,
const SmallVectorImpl<MachineOperand> &MOs,
unsigned Size, unsigned Align) const {
- const DenseMap<unsigned*, std::pair<unsigned,unsigned> > *OpcodeTablePtr=NULL;
+ const DenseMap<unsigned, std::pair<unsigned,unsigned> > *OpcodeTablePtr = 0;
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
- DenseMap<unsigned*, std::pair<unsigned,unsigned> >::const_iterator I =
- OpcodeTablePtr->find((unsigned*)MI->getOpcode());
+ DenseMap<unsigned, std::pair<unsigned,unsigned> >::const_iterator I =
+ 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)->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
- if (PrintFailedFusing)
+
+ // 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::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:
+ // 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::VROUNDSSr:
+ case X86::VRSQRTSSr:
+ case X86::VSQRTSSr:
+ return true;
+ }
+
+ return false;
+}
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_Int:
- case X86::ROUNDSSr_Int:
- 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_Int:
- case X86::ROUNDSSr_Int:
- 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;
Alignment = (*LoadMI->memoperands_begin())->getAlignment();
else
switch (LoadMI->getOpcode()) {
+ case X86::AVX_SET0PSY:
+ case X86::AVX_SET0PDY:
+ Alignment = 32;
+ break;
case X86::V_SET0PS:
case X86::V_SET0PD:
case X86::V_SET0PI:
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:
+ case X86::VFsFLD0SD:
Alignment = 8;
break;
case X86::FsFLD0SS:
+ case X86::VFsFLD0SS:
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;
} else if (Ops.size() != 1)
return NULL;
- SmallVector<MachineOperand,X86AddrNumOperands> MOs;
+ // Make sure the subregisters match.
+ // Otherwise we risk changing the size of the load.
+ if (LoadMI->getOperand(0).getSubReg() != MI->getOperand(Ops[0]).getSubReg())
+ return NULL;
+
+ SmallVector<MachineOperand,X86::AddrNumOperands> MOs;
switch (LoadMI->getOpcode()) {
case X86::V_SET0PS:
case X86::V_SET0PD:
case X86::V_SET0PI:
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::FsFLD0SD:
- case X86::FsFLD0SS: {
+ case X86::FsFLD0SS:
+ case X86::VFsFLD0SD:
+ case X86::VFsFLD0SS: {
// Folding a V_SET0P? or V_SETALLONES as a load, to ease register pressure.
// Create a constant-pool entry and operands to load from it.
if (TM.getSubtarget<X86Subtarget>().is64Bit())
PICBase = X86::RIP;
else
- // FIXME: PICBase = TM.getInstrInfo()->getGlobalBaseReg(&MF);
+ // FIXME: PICBase = getGlobalBaseReg(&MF);
// This doesn't work for several reasons.
// 1. GlobalBaseReg may have been spilled.
// 2. It may not be live at MI.
// Create a constant-pool entry.
MachineConstantPool &MCP = *MF.getConstantPool();
- const Type *Ty;
- if (LoadMI->getOpcode() == X86::FsFLD0SS)
+ Type *Ty;
+ unsigned Opc = LoadMI->getOpcode();
+ if (Opc == X86::FsFLD0SS || Opc == X86::VFsFLD0SS)
Ty = Type::getFloatTy(MF.getFunction()->getContext());
- else if (LoadMI->getOpcode() == X86::FsFLD0SD)
+ else if (Opc == X86::FsFLD0SD || Opc == X86::VFsFLD0SD)
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
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);
+ 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.
default: {
// Folding a normal load. Just copy the load's address operands.
unsigned NumOps = LoadMI->getDesc().getNumOperands();
- for (unsigned i = NumOps - X86AddrNumOperands; i != NumOps; ++i)
+ for (unsigned i = NumOps - X86::AddrNumOperands; i != NumOps; ++i)
MOs.push_back(LoadMI->getOperand(i));
break;
}
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=NULL;
- if (isTwoAddr && NumOps >= 2 && OpNum < 2) {
+ const DenseMap<unsigned, std::pair<unsigned,unsigned> > *OpcodeTablePtr = 0;
+ if (isTwoAddr && NumOps >= 2 && OpNum < 2) {
OpcodeTablePtr = &RegOp2MemOpTable2Addr;
} else if (OpNum == 0) { // If operand 0
switch (Opc) {
case X86::MOV8r0:
case X86::MOV16r0:
case X86::MOV32r0:
- case X86::MOV64r0:
- return true;
+ case X86::MOV64r0: return true;
default: break;
}
OpcodeTablePtr = &RegOp2MemOpTable0;
} else if (OpNum == 2) {
OpcodeTablePtr = &RegOp2MemOpTable2;
}
-
- if (OpcodeTablePtr) {
- // Find the Opcode to fuse
- DenseMap<unsigned*, std::pair<unsigned,unsigned> >::const_iterator I =
- OpcodeTablePtr->find((unsigned*)Opc);
- if (I != OpcodeTablePtr->end())
- return true;
- }
- return false;
+
+ if (OpcodeTablePtr && OpcodeTablePtr->count(Opc))
+ return true;
+ return TargetInstrInfoImpl::canFoldMemoryOperand(MI, Ops);
}
bool X86InstrInfo::unfoldMemoryOperand(MachineFunction &MF, MachineInstr *MI,
unsigned Reg, bool UnfoldLoad, bool UnfoldStore,
SmallVectorImpl<MachineInstr*> &NewMIs) const {
- DenseMap<unsigned*, std::pair<unsigned,unsigned> >::const_iterator I =
- MemOp2RegOpTable.find((unsigned*)MI->getOpcode());
+ DenseMap<unsigned, std::pair<unsigned,unsigned> >::const_iterator I =
+ MemOp2RegOpTable.find(MI->getOpcode());
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);
if (!MI->hasOneMemOperand() &&
RC == &X86::VR128RegClass &&
!TM.getSubtarget<X86Subtarget>().isUnalignedMemAccessFast())
// conservatively assume the address is unaligned. That's bad for
// performance.
return false;
- SmallVector<MachineOperand, X86AddrNumOperands> AddrOps;
+ SmallVector<MachineOperand, X86::AddrNumOperands> AddrOps;
SmallVector<MachineOperand,2> BeforeOps;
SmallVector<MachineOperand,2> AfterOps;
SmallVector<MachineOperand,4> ImpOps;
for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
MachineOperand &Op = MI->getOperand(i);
- if (i >= Index && i < Index + X86AddrNumOperands)
+ if (i >= Index && i < Index + X86::AddrNumOperands)
AddrOps.push_back(Op);
else if (Op.isReg() && Op.isImplicit())
ImpOps.push_back(Op);
loadRegFromAddr(MF, Reg, AddrOps, RC, MMOs.first, MMOs.second, NewMIs);
if (UnfoldStore) {
// Address operands cannot be marked isKill.
- for (unsigned i = 1; i != 1 + X86AddrNumOperands; ++i) {
+ for (unsigned i = 1; i != 1 + X86::AddrNumOperands; ++i) {
MachineOperand &MO = NewMIs[0]->getOperand(i);
if (MO.isReg())
MO.setIsKill(false);
}
// 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);
std::pair<MachineInstr::mmo_iterator,
MachineInstr::mmo_iterator> MMOs =
MF.extractStoreMemRefs(MI->memoperands_begin(),
if (!N->isMachineOpcode())
return false;
- DenseMap<unsigned*, std::pair<unsigned,unsigned> >::const_iterator I =
- MemOp2RegOpTable.find((unsigned*)N->getMachineOpcode());
+ DenseMap<unsigned, std::pair<unsigned,unsigned> >::const_iterator I =
+ MemOp2RegOpTable.find(N->getMachineOpcode());
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);
+ const TargetRegisterClass *RC = getRegClass(MCID, Index, &RI);
+ unsigned NumDefs = MCID.NumDefs;
std::vector<SDValue> AddrOps;
std::vector<SDValue> BeforeOps;
std::vector<SDValue> AfterOps;
unsigned NumOps = N->getNumOperands();
for (unsigned i = 0; i != NumOps-1; ++i) {
SDValue Op = N->getOperand(i);
- if (i >= Index-NumDefs && i < Index-NumDefs + X86AddrNumOperands)
+ if (i >= Index-NumDefs && i < Index-NumDefs + X86::AddrNumOperands)
AddrOps.push_back(Op);
else if (i < Index-NumDefs)
BeforeOps.push_back(Op);
!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);
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,
unsigned X86InstrInfo::getOpcodeAfterMemoryUnfold(unsigned Opc,
bool UnfoldLoad, bool UnfoldStore,
unsigned *LoadRegIndex) const {
- DenseMap<unsigned*, std::pair<unsigned,unsigned> >::const_iterator I =
- MemOp2RegOpTable.find((unsigned*)Opc);
+ DenseMap<unsigned, std::pair<unsigned,unsigned> >::const_iterator I =
+ 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:
- return true;
- }
- return false;
-}
-
-
-/// determineREX - Determine if the MachineInstr has to be encoded with a X86-64
-/// REX prefix which specifies 1) 64-bit instructions, 2) non-default operand
-/// size, and 3) use of X86-64 extended registers.
-unsigned X86InstrInfo::determineREX(const MachineInstr &MI) {
- unsigned REX = 0;
- const TargetInstrDesc &Desc = MI.getDesc();
-
- // Pseudo instructions do not need REX prefix byte.
- if ((Desc.TSFlags & X86II::FormMask) == X86II::Pseudo)
- return 0;
- if (Desc.TSFlags & X86II::REX_W)
- REX |= 1 << 3;
-
- unsigned NumOps = Desc.getNumOperands();
- if (NumOps) {
- bool isTwoAddr = NumOps > 1 &&
- Desc.getOperandConstraint(1, TOI::TIED_TO) != -1;
-
- // If it accesses SPL, BPL, SIL, or DIL, then it requires a 0x40 REX prefix.
- unsigned i = isTwoAddr ? 1 : 0;
- for (unsigned e = NumOps; i != e; ++i) {
- const MachineOperand& MO = MI.getOperand(i);
- if (MO.isReg()) {
- unsigned Reg = MO.getReg();
- if (isX86_64NonExtLowByteReg(Reg))
- REX |= 0x40;
- }
- }
-
- switch (Desc.TSFlags & X86II::FormMask) {
- case X86II::MRMInitReg:
- if (isX86_64ExtendedReg(MI.getOperand(0)))
- REX |= (1 << 0) | (1 << 2);
- break;
- case X86II::MRMSrcReg: {
- if (isX86_64ExtendedReg(MI.getOperand(0)))
- REX |= 1 << 2;
- i = isTwoAddr ? 2 : 1;
- for (unsigned e = NumOps; i != e; ++i) {
- const MachineOperand& MO = MI.getOperand(i);
- if (isX86_64ExtendedReg(MO))
- REX |= 1 << 0;
- }
- break;
- }
- case X86II::MRMSrcMem: {
- if (isX86_64ExtendedReg(MI.getOperand(0)))
- REX |= 1 << 2;
- unsigned Bit = 0;
- i = isTwoAddr ? 2 : 1;
- for (; i != NumOps; ++i) {
- const MachineOperand& MO = MI.getOperand(i);
- if (MO.isReg()) {
- if (isX86_64ExtendedReg(MO))
- REX |= 1 << Bit;
- Bit++;
- }
- }
- break;
- }
- case X86II::MRM0m: case X86II::MRM1m:
- case X86II::MRM2m: case X86II::MRM3m:
- case X86II::MRM4m: case X86II::MRM5m:
- case X86II::MRM6m: case X86II::MRM7m:
- case X86II::MRMDestMem: {
- unsigned e = (isTwoAddr ? X86AddrNumOperands+1 : X86AddrNumOperands);
- i = isTwoAddr ? 1 : 0;
- if (NumOps > e && isX86_64ExtendedReg(MI.getOperand(e)))
- REX |= 1 << 2;
- unsigned Bit = 0;
- for (; i != e; ++i) {
- const MachineOperand& MO = MI.getOperand(i);
- if (MO.isReg()) {
- if (isX86_64ExtendedReg(MO))
- REX |= 1 << Bit;
- Bit++;
- }
- }
- break;
- }
- default: {
- if (isX86_64ExtendedReg(MI.getOperand(0)))
- REX |= 1 << 0;
- i = isTwoAddr ? 2 : 1;
- for (unsigned e = NumOps; i != e; ++i) {
- const MachineOperand& MO = MI.getOperand(i);
- if (isX86_64ExtendedReg(MO))
- REX |= 1 << 2;
- }
- break;
- }
- }
- }
- return REX;
-}
-
-/// sizePCRelativeBlockAddress - This method returns the size of a PC
-/// relative block address instruction
-///
-static unsigned sizePCRelativeBlockAddress() {
- return 4;
-}
-
-/// sizeGlobalAddress - Give the size of the emission of this global address
-///
-static unsigned sizeGlobalAddress(bool dword) {
- return dword ? 8 : 4;
-}
-
-/// sizeConstPoolAddress - Give the size of the emission of this constant
-/// pool address
-///
-static unsigned sizeConstPoolAddress(bool dword) {
- return dword ? 8 : 4;
-}
-
-/// sizeExternalSymbolAddress - Give the size of the emission of this external
-/// symbol
-///
-static unsigned sizeExternalSymbolAddress(bool dword) {
- return dword ? 8 : 4;
-}
-
-/// sizeJumpTableAddress - Give the size of the emission of this jump
-/// table address
-///
-static unsigned sizeJumpTableAddress(bool dword) {
- return dword ? 8 : 4;
-}
-
-static unsigned sizeConstant(unsigned Size) {
- return Size;
-}
-
-static unsigned sizeRegModRMByte(){
- return 1;
-}
-
-static unsigned sizeSIBByte(){
- return 1;
-}
-
-static unsigned getDisplacementFieldSize(const MachineOperand *RelocOp) {
- unsigned FinalSize = 0;
- // If this is a simple integer displacement that doesn't require a relocation.
- if (!RelocOp) {
- FinalSize += sizeConstant(4);
- return FinalSize;
- }
-
- // Otherwise, this is something that requires a relocation.
- if (RelocOp->isGlobal()) {
- FinalSize += sizeGlobalAddress(false);
- } else if (RelocOp->isCPI()) {
- FinalSize += sizeConstPoolAddress(false);
- } else if (RelocOp->isJTI()) {
- FinalSize += sizeJumpTableAddress(false);
- } else {
- llvm_unreachable("Unknown value to relocate!");
- }
- return FinalSize;
-}
-
-static unsigned getMemModRMByteSize(const MachineInstr &MI, unsigned Op,
- bool IsPIC, bool Is64BitMode) {
- const MachineOperand &Op3 = MI.getOperand(Op+3);
- int DispVal = 0;
- const MachineOperand *DispForReloc = 0;
- unsigned FinalSize = 0;
-
- // Figure out what sort of displacement we have to handle here.
- if (Op3.isGlobal()) {
- DispForReloc = &Op3;
- } else if (Op3.isCPI()) {
- if (Is64BitMode || IsPIC) {
- DispForReloc = &Op3;
- } else {
- DispVal = 1;
- }
- } else if (Op3.isJTI()) {
- if (Is64BitMode || IsPIC) {
- DispForReloc = &Op3;
- } else {
- DispVal = 1;
- }
- } else {
- DispVal = 1;
- }
-
- const MachineOperand &Base = MI.getOperand(Op);
- const MachineOperand &IndexReg = MI.getOperand(Op+2);
-
- unsigned BaseReg = Base.getReg();
-
- // Is a SIB byte needed?
- if ((!Is64BitMode || DispForReloc || BaseReg != 0) &&
- IndexReg.getReg() == 0 &&
- (BaseReg == 0 || X86RegisterInfo::getX86RegNum(BaseReg) != N86::ESP)) {
- if (BaseReg == 0) { // Just a displacement?
- // Emit special case [disp32] encoding
- ++FinalSize;
- FinalSize += getDisplacementFieldSize(DispForReloc);
- } else {
- unsigned BaseRegNo = X86RegisterInfo::getX86RegNum(BaseReg);
- if (!DispForReloc && DispVal == 0 && BaseRegNo != N86::EBP) {
- // Emit simple indirect register encoding... [EAX] f.e.
- ++FinalSize;
- // Be pessimistic and assume it's a disp32, not a disp8
- } else {
- // Emit the most general non-SIB encoding: [REG+disp32]
- ++FinalSize;
- FinalSize += getDisplacementFieldSize(DispForReloc);
- }
- }
-
- } else { // We need a SIB byte, so start by outputting the ModR/M byte first
- assert(IndexReg.getReg() != X86::ESP &&
- IndexReg.getReg() != X86::RSP && "Cannot use ESP as index reg!");
-
- bool ForceDisp32 = false;
- if (BaseReg == 0 || DispForReloc) {
- // Emit the normal disp32 encoding.
- ++FinalSize;
- ForceDisp32 = true;
- } else {
- ++FinalSize;
- }
-
- FinalSize += sizeSIBByte();
-
- // Do we need to output a displacement?
- if (DispVal != 0 || ForceDisp32) {
- FinalSize += getDisplacementFieldSize(DispForReloc);
- }
- }
- return FinalSize;
-}
-
-
-static unsigned GetInstSizeWithDesc(const MachineInstr &MI,
- const TargetInstrDesc *Desc,
- bool IsPIC, bool Is64BitMode) {
-
- unsigned Opcode = Desc->Opcode;
- unsigned FinalSize = 0;
-
- // Emit the lock opcode prefix as needed.
- if (Desc->TSFlags & X86II::LOCK) ++FinalSize;
-
- // Emit segment override opcode prefix as needed.
- switch (Desc->TSFlags & X86II::SegOvrMask) {
- case X86II::FS:
- case X86II::GS:
- ++FinalSize;
- break;
- default: llvm_unreachable("Invalid segment!");
- case 0: break; // No segment override!
- }
-
- // Emit the repeat opcode prefix as needed.
- if ((Desc->TSFlags & X86II::Op0Mask) == X86II::REP) ++FinalSize;
-
- // Emit the operand size opcode prefix as needed.
- if (Desc->TSFlags & X86II::OpSize) ++FinalSize;
-
- // Emit the address size opcode prefix as needed.
- if (Desc->TSFlags & X86II::AdSize) ++FinalSize;
-
- bool Need0FPrefix = false;
- switch (Desc->TSFlags & X86II::Op0Mask) {
- case X86II::TB: // Two-byte opcode prefix
- case X86II::T8: // 0F 38
- case X86II::TA: // 0F 3A
- Need0FPrefix = true;
- break;
- case X86II::TF: // F2 0F 38
- ++FinalSize;
- Need0FPrefix = true;
- break;
- case X86II::REP: break; // already handled.
- case X86II::XS: // F3 0F
- ++FinalSize;
- Need0FPrefix = true;
- break;
- case X86II::XD: // F2 0F
- ++FinalSize;
- Need0FPrefix = true;
- break;
- case X86II::D8: case X86II::D9: case X86II::DA: case X86II::DB:
- case X86II::DC: case X86II::DD: case X86II::DE: case X86II::DF:
- ++FinalSize;
- break; // Two-byte opcode prefix
- default: llvm_unreachable("Invalid prefix!");
- case 0: break; // No prefix!
- }
-
- if (Is64BitMode) {
- // REX prefix
- unsigned REX = X86InstrInfo::determineREX(MI);
- if (REX)
- ++FinalSize;
- }
-
- // 0x0F escape code must be emitted just before the opcode.
- if (Need0FPrefix)
- ++FinalSize;
-
- switch (Desc->TSFlags & X86II::Op0Mask) {
- case X86II::T8: // 0F 38
- ++FinalSize;
- break;
- case X86II::TA: // 0F 3A
- ++FinalSize;
- break;
- case X86II::TF: // F2 0F 38
- ++FinalSize;
- break;
- }
-
- // If this is a two-address instruction, skip one of the register operands.
- unsigned NumOps = Desc->getNumOperands();
- unsigned CurOp = 0;
- if (NumOps > 1 && Desc->getOperandConstraint(1, TOI::TIED_TO) != -1)
- CurOp++;
- else if (NumOps > 2 && Desc->getOperandConstraint(NumOps-1, TOI::TIED_TO)== 0)
- // Skip the last source operand that is tied_to the dest reg. e.g. LXADD32
- --NumOps;
-
- switch (Desc->TSFlags & X86II::FormMask) {
- default: llvm_unreachable("Unknown FormMask value in X86 MachineCodeEmitter!");
- case X86II::Pseudo:
- // Remember the current PC offset, this is the PIC relocation
- // base address.
- switch (Opcode) {
- default:
- break;
- case TargetOpcode::INLINEASM: {
- const MachineFunction *MF = MI.getParent()->getParent();
- const TargetInstrInfo &TII = *MF->getTarget().getInstrInfo();
- FinalSize += TII.getInlineAsmLength(MI.getOperand(0).getSymbolName(),
- *MF->getTarget().getMCAsmInfo());
- break;
- }
- case TargetOpcode::DBG_LABEL:
- case TargetOpcode::EH_LABEL:
- case TargetOpcode::DBG_VALUE:
- break;
- case TargetOpcode::IMPLICIT_DEF:
- case TargetOpcode::KILL:
- case X86::FP_REG_KILL:
- break;
- case X86::MOVPC32r: {
- // This emits the "call" portion of this pseudo instruction.
- ++FinalSize;
- FinalSize += sizeConstant(X86II::getSizeOfImm(Desc->TSFlags));
- break;
- }
- }
- CurOp = NumOps;
- break;
- case X86II::RawFrm:
- ++FinalSize;
-
- if (CurOp != NumOps) {
- const MachineOperand &MO = MI.getOperand(CurOp++);
- if (MO.isMBB()) {
- FinalSize += sizePCRelativeBlockAddress();
- } else if (MO.isGlobal()) {
- FinalSize += sizeGlobalAddress(false);
- } else if (MO.isSymbol()) {
- FinalSize += sizeExternalSymbolAddress(false);
- } else if (MO.isImm()) {
- FinalSize += sizeConstant(X86II::getSizeOfImm(Desc->TSFlags));
- } else {
- llvm_unreachable("Unknown RawFrm operand!");
- }
- }
- break;
-
- case X86II::AddRegFrm:
- ++FinalSize;
- ++CurOp;
-
- if (CurOp != NumOps) {
- const MachineOperand &MO1 = MI.getOperand(CurOp++);
- unsigned Size = X86II::getSizeOfImm(Desc->TSFlags);
- if (MO1.isImm())
- FinalSize += sizeConstant(Size);
- else {
- bool dword = false;
- if (Opcode == X86::MOV64ri)
- dword = true;
- if (MO1.isGlobal()) {
- FinalSize += sizeGlobalAddress(dword);
- } else if (MO1.isSymbol())
- FinalSize += sizeExternalSymbolAddress(dword);
- else if (MO1.isCPI())
- FinalSize += sizeConstPoolAddress(dword);
- else if (MO1.isJTI())
- FinalSize += sizeJumpTableAddress(dword);
- }
- }
- break;
-
- case X86II::MRMDestReg: {
- ++FinalSize;
- FinalSize += sizeRegModRMByte();
- CurOp += 2;
- if (CurOp != NumOps) {
- ++CurOp;
- FinalSize += sizeConstant(X86II::getSizeOfImm(Desc->TSFlags));
- }
- break;
- }
- case X86II::MRMDestMem: {
- ++FinalSize;
- FinalSize += getMemModRMByteSize(MI, CurOp, IsPIC, Is64BitMode);
- CurOp += X86AddrNumOperands + 1;
- if (CurOp != NumOps) {
- ++CurOp;
- FinalSize += sizeConstant(X86II::getSizeOfImm(Desc->TSFlags));
- }
- break;
- }
-
- case X86II::MRMSrcReg:
- ++FinalSize;
- FinalSize += sizeRegModRMByte();
- CurOp += 2;
- if (CurOp != NumOps) {
- ++CurOp;
- FinalSize += sizeConstant(X86II::getSizeOfImm(Desc->TSFlags));
- }
- break;
-
- case X86II::MRMSrcMem: {
- int AddrOperands;
- if (Opcode == X86::LEA64r || Opcode == X86::LEA64_32r ||
- Opcode == X86::LEA16r || Opcode == X86::LEA32r)
- AddrOperands = X86AddrNumOperands - 1; // No segment register
- else
- AddrOperands = X86AddrNumOperands;
-
- ++FinalSize;
- FinalSize += getMemModRMByteSize(MI, CurOp+1, IsPIC, Is64BitMode);
- CurOp += AddrOperands + 1;
- if (CurOp != NumOps) {
- ++CurOp;
- FinalSize += sizeConstant(X86II::getSizeOfImm(Desc->TSFlags));
- }
- break;
- }
-
- case X86II::MRM0r: case X86II::MRM1r:
- case X86II::MRM2r: case X86II::MRM3r:
- case X86II::MRM4r: case X86II::MRM5r:
- case X86II::MRM6r: case X86II::MRM7r:
- ++FinalSize;
- if (Desc->getOpcode() == X86::LFENCE ||
- Desc->getOpcode() == X86::MFENCE) {
- // Special handling of lfence and mfence;
- FinalSize += sizeRegModRMByte();
- } else if (Desc->getOpcode() == X86::MONITOR ||
- Desc->getOpcode() == X86::MWAIT) {
- // Special handling of monitor and mwait.
- FinalSize += sizeRegModRMByte() + 1; // +1 for the opcode.
- } else {
- ++CurOp;
- FinalSize += sizeRegModRMByte();
- }
-
- if (CurOp != NumOps) {
- const MachineOperand &MO1 = MI.getOperand(CurOp++);
- unsigned Size = X86II::getSizeOfImm(Desc->TSFlags);
- if (MO1.isImm())
- FinalSize += sizeConstant(Size);
- else {
- bool dword = false;
- if (Opcode == X86::MOV64ri32)
- dword = true;
- if (MO1.isGlobal()) {
- FinalSize += sizeGlobalAddress(dword);
- } else if (MO1.isSymbol())
- FinalSize += sizeExternalSymbolAddress(dword);
- else if (MO1.isCPI())
- FinalSize += sizeConstPoolAddress(dword);
- else if (MO1.isJTI())
- FinalSize += sizeJumpTableAddress(dword);
- }
- }
- break;
-
- case X86II::MRM0m: case X86II::MRM1m:
- case X86II::MRM2m: case X86II::MRM3m:
- case X86II::MRM4m: case X86II::MRM5m:
- case X86II::MRM6m: case X86II::MRM7m: {
-
- ++FinalSize;
- FinalSize += getMemModRMByteSize(MI, CurOp, IsPIC, Is64BitMode);
- CurOp += X86AddrNumOperands;
-
- if (CurOp != NumOps) {
- const MachineOperand &MO = MI.getOperand(CurOp++);
- unsigned Size = X86II::getSizeOfImm(Desc->TSFlags);
- if (MO.isImm())
- FinalSize += sizeConstant(Size);
- else {
- bool dword = false;
- if (Opcode == X86::MOV64mi32)
- dword = true;
- if (MO.isGlobal()) {
- FinalSize += sizeGlobalAddress(dword);
- } else if (MO.isSymbol())
- FinalSize += sizeExternalSymbolAddress(dword);
- else if (MO.isCPI())
- FinalSize += sizeConstPoolAddress(dword);
- else if (MO.isJTI())
- FinalSize += sizeJumpTableAddress(dword);
- }
- }
- break;
-
- case X86II::MRM_C1:
- case X86II::MRM_C8:
- case X86II::MRM_C9:
- case X86II::MRM_E8:
- case X86II::MRM_F0:
- FinalSize += 2;
- break;
- }
-
- case X86II::MRMInitReg:
- ++FinalSize;
- // Duplicate register, used by things like MOV8r0 (aka xor reg,reg).
- FinalSize += sizeRegModRMByte();
- ++CurOp;
- break;
- }
-
- if (!Desc->isVariadic() && CurOp != NumOps) {
- std::string msg;
- raw_string_ostream Msg(msg);
- Msg << "Cannot determine size: " << MI;
- report_fatal_error(Msg.str());
- }
-
-
- return FinalSize;
-}
-
-
-unsigned X86InstrInfo::GetInstSizeInBytes(const MachineInstr *MI) const {
- const TargetInstrDesc &Desc = MI->getDesc();
- bool IsPIC = TM.getRelocationModel() == Reloc::PIC_;
- bool Is64BitMode = TM.getSubtargetImpl()->is64Bit();
- unsigned Size = GetInstSizeWithDesc(*MI, &Desc, IsPIC, Is64BitMode);
- if (Desc.getOpcode() == X86::MOVPC32r)
- Size += GetInstSizeWithDesc(*MI, &get(X86::POP32r), IsPIC, Is64BitMode);
- return Size;
-}
-
/// 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.
///
+/// TODO: Eliminate this and move the code to X86MachineFunctionInfo.
+///
unsigned X86InstrInfo::getGlobalBaseReg(MachineFunction *MF) const {
assert(!TM.getSubtarget<X86Subtarget>().is64Bit() &&
"X86-64 PIC uses RIP relative addressing");
if (GlobalBaseReg != 0)
return GlobalBaseReg;
- // Insert the set of GlobalBaseReg into the first MBB of the function
- MachineBasicBlock &FirstMBB = MF->front();
- MachineBasicBlock::iterator MBBI = FirstMBB.begin();
- DebugLoc DL = FirstMBB.findDebugLoc(MBBI);
+ // Create the register. The code to initialize it is inserted
+ // later, by the CGBR pass (below).
MachineRegisterInfo &RegInfo = MF->getRegInfo();
- unsigned PC = RegInfo.createVirtualRegister(X86::GR32RegisterClass);
-
- const TargetInstrInfo *TII = TM.getInstrInfo();
- // 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()) {
- GlobalBaseReg = RegInfo.createVirtualRegister(X86::GR32RegisterClass);
- // Generate addl $__GLOBAL_OFFSET_TABLE_ + [.-piclabel], %some_register
- BuildMI(FirstMBB, MBBI, DL, TII->get(X86::ADD32ri), GlobalBaseReg)
- .addReg(PC).addExternalSymbol("_GLOBAL_OFFSET_TABLE_",
- X86II::MO_GOT_ABSOLUTE_ADDRESS);
- } else {
- GlobalBaseReg = PC;
- }
-
+ GlobalBaseReg = RegInfo.createVirtualRegister(X86::GR32RegisterClass);
X86FI->setGlobalBaseReg(GlobalBaseReg);
return GlobalBaseReg;
}
// that we don't include here. We don't want to replace instructions selected
// by intrinsics.
static const unsigned ReplaceableInstrs[][3] = {
- //PackedInt PackedSingle PackedDouble
+ //PackedSingle PackedDouble PackedInt
{ X86::MOVAPSmr, X86::MOVAPDmr, X86::MOVDQAmr },
{ X86::MOVAPSrm, X86::MOVAPDrm, X86::MOVDQArm },
{ X86::MOVAPSrr, X86::MOVAPDrr, X86::MOVDQArr },
{ 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::VMOVAPSmr, X86::VMOVAPDmr, X86::VMOVDQAmr },
+ { X86::VMOVAPSrm, X86::VMOVAPDrm, X86::VMOVDQArm },
+ { X86::VMOVAPSrr, X86::VMOVAPDrr, X86::VMOVDQArr },
+ { X86::VMOVUPSmr, X86::VMOVUPDmr, X86::VMOVDQUmr },
+ { X86::VMOVUPSrm, X86::VMOVUPDrm, X86::VMOVDQUrm },
+ { X86::VMOVNTPSmr, X86::VMOVNTPDmr, X86::VMOVNTDQmr },
+ { X86::VANDNPSrm, X86::VANDNPDrm, X86::VPANDNrm },
+ { X86::VANDNPSrr, X86::VANDNPDrr, X86::VPANDNrr },
+ { X86::VANDPSrm, X86::VANDPDrm, X86::VPANDrm },
+ { 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 },
};
// FIXME: Some shuffle and unpack instructions have equivalents in different
void X86InstrInfo::getNoopForMachoTarget(MCInst &NopInst) const {
NopInst.setOpcode(X86::NOOP);
}
+
+bool X86InstrInfo::isHighLatencyDef(int opc) const {
+ switch (opc) {
+ default: return false;
+ case X86::DIVSDrm:
+ case X86::DIVSDrm_Int:
+ case X86::DIVSDrr:
+ case X86::DIVSDrr_Int:
+ case X86::DIVSSrm:
+ case X86::DIVSSrm_Int:
+ case X86::DIVSSrr:
+ case X86::DIVSSrr_Int:
+ case X86::SQRTPDm:
+ case X86::SQRTPDm_Int:
+ case X86::SQRTPDr:
+ case X86::SQRTPDr_Int:
+ case X86::SQRTPSm:
+ case X86::SQRTPSm_Int:
+ case X86::SQRTPSr:
+ case X86::SQRTPSr_Int:
+ case X86::SQRTSDm:
+ case X86::SQRTSDm_Int:
+ case X86::SQRTSDr:
+ case X86::SQRTSDr_Int:
+ case X86::SQRTSSm:
+ 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.
+ struct CGBR : public MachineFunctionPass {
+ static char ID;
+ CGBR() : MachineFunctionPass(ID) {}
+
+ virtual bool runOnMachineFunction(MachineFunction &MF) {
+ const X86TargetMachine *TM =
+ static_cast<const X86TargetMachine *>(&MF.getTarget());
+
+ assert(!TM->getSubtarget<X86Subtarget>().is64Bit() &&
+ "X86-64 PIC uses RIP relative addressing");
+
+ // Only emit a global base reg in PIC mode.
+ if (TM->getRelocationModel() != Reloc::PIC_)
+ return false;
+
+ X86MachineFunctionInfo *X86FI = MF.getInfo<X86MachineFunctionInfo>();
+ unsigned GlobalBaseReg = X86FI->getGlobalBaseReg();
+
+ // If we didn't need a GlobalBaseReg, don't insert code.
+ if (GlobalBaseReg == 0)
+ return false;
+
+ // Insert the set of GlobalBaseReg into the first MBB of the function
+ MachineBasicBlock &FirstMBB = MF.front();
+ MachineBasicBlock::iterator MBBI = FirstMBB.begin();
+ DebugLoc DL = FirstMBB.findDebugLoc(MBBI);
+ MachineRegisterInfo &RegInfo = MF.getRegInfo();
+ const X86InstrInfo *TII = TM->getInstrInfo();
+
+ unsigned PC;
+ if (TM->getSubtarget<X86Subtarget>().isPICStyleGOT())
+ PC = RegInfo.createVirtualRegister(X86::GR32RegisterClass);
+ 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()) {
+ // Generate addl $__GLOBAL_OFFSET_TABLE_ + [.-piclabel], %some_register
+ BuildMI(FirstMBB, MBBI, DL, TII->get(X86::ADD32ri), GlobalBaseReg)
+ .addReg(PC).addExternalSymbol("_GLOBAL_OFFSET_TABLE_",
+ X86II::MO_GOT_ABSOLUTE_ADDRESS);
+ }
+
+ return true;
+ }
+
+ virtual const char *getPassName() const {
+ return "X86 PIC Global Base Reg Initialization";
+ }
+
+ virtual void getAnalysisUsage(AnalysisUsage &AU) const {
+ AU.setPreservesCFG();
+ MachineFunctionPass::getAnalysisUsage(AU);
+ }
+ };
+}
+
+char CGBR::ID = 0;
+FunctionPass*
+llvm::createGlobalBaseRegPass() { return new CGBR(); }
projects / oota-llvm.git / blobdiff