llvm/lib/Target/X86/X86.td

//===-- X86.td - Target definition file for the Intel X86 --*- tablegen -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This is a target description file for the Intel i386 architecture, referred
// to here as the "X86" architecture.
//
//===----------------------------------------------------------------------===//

// Get the target-independent interfaces which we are implementing...
//
include "llvm/Target/Target.td"

//===----------------------------------------------------------------------===//
// X86 Subtarget state
//

def Mode64Bit : SubtargetFeature<"64bit-mode", "In64BitMode", "true",
                                  "64-bit mode (x86_64)">;
def Mode32Bit : SubtargetFeature<"32bit-mode", "In32BitMode", "true",
                                  "32-bit mode (80386)">;
def Mode16Bit : SubtargetFeature<"16bit-mode", "In16BitMode", "true",
                                  "16-bit mode (i8086)">;

//===----------------------------------------------------------------------===//
// X86 Subtarget features
//===----------------------------------------------------------------------===//

def FeatureX87     : SubtargetFeature<"x87","HasX87", "true",
                                      "Enable X87 float instructions">;

def FeatureNOPL    : SubtargetFeature<"nopl", "HasNOPL", "true",
                                      "Enable NOPL instruction">;

def FeatureCMOV    : SubtargetFeature<"cmov","HasCMov", "true",
                                      "Enable conditional move instructions">;

def FeaturePOPCNT   : SubtargetFeature<"popcnt", "HasPOPCNT", "true",
                                       "Support POPCNT instruction">;

def FeatureFXSR    : SubtargetFeature<"fxsr", "HasFXSR", "true",
                                      "Support fxsave/fxrestore instructions">;

def FeatureXSAVE   : SubtargetFeature<"xsave", "HasXSAVE", "true",
                                       "Support xsave instructions">;

def FeatureXSAVEOPT: SubtargetFeature<"xsaveopt", "HasXSAVEOPT", "true",
                                       "Support xsaveopt instructions">;

def FeatureXSAVEC  : SubtargetFeature<"xsavec", "HasXSAVEC", "true",
                                       "Support xsavec instructions">;

def FeatureXSAVES  : SubtargetFeature<"xsaves", "HasXSAVES", "true",
                                       "Support xsaves instructions">;

def FeatureSSE1    : SubtargetFeature<"sse", "X86SSELevel", "SSE1",
                                      "Enable SSE instructions",
                                      // SSE codegen depends on cmovs, and all
                                      // SSE1+ processors support them.
                                      [FeatureCMOV]>;
def FeatureSSE2    : SubtargetFeature<"sse2", "X86SSELevel", "SSE2",
                                      "Enable SSE2 instructions",
                                      [FeatureSSE1]>;
def FeatureSSE3    : SubtargetFeature<"sse3", "X86SSELevel", "SSE3",
                                      "Enable SSE3 instructions",
                                      [FeatureSSE2]>;
def FeatureSSSE3   : SubtargetFeature<"ssse3", "X86SSELevel", "SSSE3",
                                      "Enable SSSE3 instructions",
                                      [FeatureSSE3]>;
def FeatureSSE41   : SubtargetFeature<"sse4.1", "X86SSELevel", "SSE41",
                                      "Enable SSE 4.1 instructions",
                                      [FeatureSSSE3]>;
def FeatureSSE42   : SubtargetFeature<"sse4.2", "X86SSELevel", "SSE42",
                                      "Enable SSE 4.2 instructions",
                                      [FeatureSSE41]>;
// The MMX subtarget feature is separate from the rest of the SSE features
// because it's important (for odd compatibility reasons) to be able to
// turn it off explicitly while allowing SSE+ to be on.
def FeatureMMX     : SubtargetFeature<"mmx","X863DNowLevel", "MMX",
                                      "Enable MMX instructions">;
def Feature3DNow   : SubtargetFeature<"3dnow", "X863DNowLevel", "ThreeDNow",
                                      "Enable 3DNow! instructions",
                                      [FeatureMMX]>;
def Feature3DNowA  : SubtargetFeature<"3dnowa", "X863DNowLevel", "ThreeDNowA",
                                      "Enable 3DNow! Athlon instructions",
                                      [Feature3DNow]>;
// All x86-64 hardware has SSE2, but we don't mark SSE2 as an implied
// feature, because SSE2 can be disabled (e.g. for compiling OS kernels)
// without disabling 64-bit mode.
def Feature64Bit   : SubtargetFeature<"64bit", "HasX86_64", "true",
                                      "Support 64-bit instructions",
                                      [FeatureCMOV]>;
def FeatureCMPXCHG16B : SubtargetFeature<"cx16", "HasCmpxchg16b", "true",
                                      "64-bit with cmpxchg16b",
                                      [Feature64Bit]>;
def FeatureSlowSHLD : SubtargetFeature<"slow-shld", "IsSHLDSlow", "true",
                                       "SHLD instruction is slow">;
def FeatureSlowPMULLD : SubtargetFeature<"slow-pmulld", "IsPMULLDSlow", "true",
                                        "PMULLD instruction is slow">;
// FIXME: This should not apply to CPUs that do not have SSE.
def FeatureSlowUAMem16 : SubtargetFeature<"slow-unaligned-mem-16",
                                "IsUAMem16Slow", "true",
                                "Slow unaligned 16-byte memory access">;
def FeatureSlowUAMem32 : SubtargetFeature<"slow-unaligned-mem-32",
                                "IsUAMem32Slow", "true",
                                "Slow unaligned 32-byte memory access">;
def FeatureSSE4A   : SubtargetFeature<"sse4a", "HasSSE4A", "true",
                                      "Support SSE 4a instructions",
                                      [FeatureSSE3]>;

def FeatureAVX     : SubtargetFeature<"avx", "X86SSELevel", "AVX",
                                      "Enable AVX instructions",
                                      [FeatureSSE42]>;
def FeatureAVX2    : SubtargetFeature<"avx2", "X86SSELevel", "AVX2",
                                      "Enable AVX2 instructions",
                                      [FeatureAVX]>;
def FeatureFMA     : SubtargetFeature<"fma", "HasFMA", "true",
                                      "Enable three-operand fused multiple-add",
                                      [FeatureAVX]>;
def FeatureF16C    : SubtargetFeature<"f16c", "HasF16C", "true",
                       "Support 16-bit floating point conversion instructions",
                       [FeatureAVX]>;
def FeatureAVX512   : SubtargetFeature<"avx512f", "X86SSELevel", "AVX512F",
                                      "Enable AVX-512 instructions",
                                      [FeatureAVX2, FeatureFMA, FeatureF16C]>;
def FeatureERI      : SubtargetFeature<"avx512er", "HasERI", "true",
                      "Enable AVX-512 Exponential and Reciprocal Instructions",
                                      [FeatureAVX512]>;
def FeatureCDI      : SubtargetFeature<"avx512cd", "HasCDI", "true",
                      "Enable AVX-512 Conflict Detection Instructions",
                                      [FeatureAVX512]>;
def FeatureVPOPCNTDQ : SubtargetFeature<"avx512vpopcntdq", "HasVPOPCNTDQ",
                       "true", "Enable AVX-512 Population Count Instructions",
                                      [FeatureAVX512]>;
def FeaturePFI      : SubtargetFeature<"avx512pf", "HasPFI", "true",
                      "Enable AVX-512 PreFetch Instructions",
                                      [FeatureAVX512]>;
def FeaturePREFETCHWT1  : SubtargetFeature<"prefetchwt1", "HasPREFETCHWT1",
                                   "true",
                                   "Prefetch with Intent to Write and T1 Hint">;
def FeatureDQI     : SubtargetFeature<"avx512dq", "HasDQI", "true",
                      "Enable AVX-512 Doubleword and Quadword Instructions",
                                      [FeatureAVX512]>;
def FeatureBWI     : SubtargetFeature<"avx512bw", "HasBWI", "true",
                      "Enable AVX-512 Byte and Word Instructions",
                                      [FeatureAVX512]>;
def FeatureVLX     : SubtargetFeature<"avx512vl", "HasVLX", "true",
                      "Enable AVX-512 Vector Length eXtensions",
                                      [FeatureAVX512]>;
def FeatureVBMI     : SubtargetFeature<"avx512vbmi", "HasVBMI", "true",
                      "Enable AVX-512 Vector Byte Manipulation Instructions",
                                      [FeatureBWI]>;
def FeatureVBMI2    : SubtargetFeature<"avx512vbmi2", "HasVBMI2", "true",
                      "Enable AVX-512 further Vector Byte Manipulation Instructions",
                                      [FeatureBWI]>;
def FeatureIFMA     : SubtargetFeature<"avx512ifma", "HasIFMA", "true",
                      "Enable AVX-512 Integer Fused Multiple-Add",
                                      [FeatureAVX512]>;
def FeaturePKU   : SubtargetFeature<"pku", "HasPKU", "true",
                      "Enable protection keys">;
def FeatureVNNI    : SubtargetFeature<"avx512vnni", "HasVNNI", "true",
                          "Enable AVX-512 Vector Neural Network Instructions",
                                      [FeatureAVX512]>;
def FeatureBITALG  : SubtargetFeature<"avx512bitalg", "HasBITALG", "true",
                       "Enable AVX-512 Bit Algorithms",
                        [FeatureBWI]>;
def FeaturePCLMUL  : SubtargetFeature<"pclmul", "HasPCLMUL", "true",
                         "Enable packed carry-less multiplication instructions",
                               [FeatureSSE2]>;
def FeatureGFNI    : SubtargetFeature<"gfni", "HasGFNI", "true",
                         "Enable Galois Field Arithmetic Instructions",
                               [FeatureSSE2]>;
def FeatureVPCLMULQDQ : SubtargetFeature<"vpclmulqdq", "HasVPCLMULQDQ", "true",
                                         "Enable vpclmulqdq instructions",
                                         [FeatureAVX, FeaturePCLMUL]>;
def FeatureFMA4    : SubtargetFeature<"fma4", "HasFMA4", "true",
                                      "Enable four-operand fused multiple-add",
                                      [FeatureAVX, FeatureSSE4A]>;
def FeatureXOP     : SubtargetFeature<"xop", "HasXOP", "true",
                                      "Enable XOP instructions",
                                      [FeatureFMA4]>;
def FeatureSSEUnalignedMem : SubtargetFeature<"sse-unaligned-mem",
                                          "HasSSEUnalignedMem", "true",
                      "Allow unaligned memory operands with SSE instructions">;
def FeatureAES     : SubtargetFeature<"aes", "HasAES", "true",
                                      "Enable AES instructions",
                                      [FeatureSSE2]>;
def FeatureVAES    : SubtargetFeature<"vaes", "HasVAES", "true",
                       "Promote selected AES instructions to AVX512/AVX registers",
                        [FeatureAVX, FeatureAES]>;
def FeatureTBM     : SubtargetFeature<"tbm", "HasTBM", "true",
                                      "Enable TBM instructions">;
def FeatureLWP     : SubtargetFeature<"lwp", "HasLWP", "true",
                                      "Enable LWP instructions">;
def FeatureMOVBE   : SubtargetFeature<"movbe", "HasMOVBE", "true",
                                      "Support MOVBE instruction">;
def FeatureRDRAND  : SubtargetFeature<"rdrnd", "HasRDRAND", "true",
                                      "Support RDRAND instruction">;
def FeatureFSGSBase : SubtargetFeature<"fsgsbase", "HasFSGSBase", "true",
                                       "Support FS/GS Base instructions">;
def FeatureLZCNT   : SubtargetFeature<"lzcnt", "HasLZCNT", "true",
                                      "Support LZCNT instruction">;
def FeatureBMI     : SubtargetFeature<"bmi", "HasBMI", "true",
                                      "Support BMI instructions">;
def FeatureBMI2    : SubtargetFeature<"bmi2", "HasBMI2", "true",
                                      "Support BMI2 instructions">;
def FeatureRTM     : SubtargetFeature<"rtm", "HasRTM", "true",
                                      "Support RTM instructions">;
def FeatureADX     : SubtargetFeature<"adx", "HasADX", "true",
                                      "Support ADX instructions">;
def FeatureSHA     : SubtargetFeature<"sha", "HasSHA", "true",
                                      "Enable SHA instructions",
                                      [FeatureSSE2]>;
def FeatureSHSTK   : SubtargetFeature<"shstk", "HasSHSTK", "true",
                       "Support CET Shadow-Stack instructions">;
def FeatureIBT     : SubtargetFeature<"ibt", "HasIBT", "true",
                       "Support CET Indirect-Branch-Tracking instructions">;
def FeaturePRFCHW  : SubtargetFeature<"prfchw", "HasPRFCHW", "true",
                                      "Support PRFCHW instructions">;
def FeatureRDSEED  : SubtargetFeature<"rdseed", "HasRDSEED", "true",
                                      "Support RDSEED instruction">;
def FeatureLAHFSAHF : SubtargetFeature<"sahf", "HasLAHFSAHF", "true",
                                       "Support LAHF and SAHF instructions">;
def FeatureMWAITX  : SubtargetFeature<"mwaitx", "HasMWAITX", "true",
                                      "Enable MONITORX/MWAITX timer functionality">;
def FeatureCLZERO  : SubtargetFeature<"clzero", "HasCLZERO", "true",
                                      "Enable Cache Line Zero">;
def FeatureMPX     : SubtargetFeature<"mpx", "HasMPX", "true",
                                      "Support MPX instructions">;
def FeatureLEAForSP : SubtargetFeature<"lea-sp", "UseLeaForSP", "true",
                                     "Use LEA for adjusting the stack pointer">;
def FeatureSlowDivide32 : SubtargetFeature<"idivl-to-divb",
                                     "HasSlowDivide32", "true",
                                     "Use 8-bit divide for positive values less than 256">;
def FeatureSlowDivide64 : SubtargetFeature<"idivq-to-divl",
                                     "HasSlowDivide64", "true",
                                     "Use 32-bit divide for positive values less than 2^32">;
def FeaturePadShortFunctions : SubtargetFeature<"pad-short-functions",
                                     "PadShortFunctions", "true",
                                     "Pad short functions">;
def FeatureSGX     : SubtargetFeature<"sgx", "HasSGX", "true",
                                      "Enable Software Guard Extensions">;
def FeatureCLFLUSHOPT : SubtargetFeature<"clflushopt", "HasCLFLUSHOPT", "true",
                                      "Flush A Cache Line Optimized">;
def FeatureCLWB    : SubtargetFeature<"clwb", "HasCLWB", "true",
                                      "Cache Line Write Back">;
def FeatureRDPID : SubtargetFeature<"rdpid", "HasRDPID", "true",
                                    "Support RDPID instructions">;
// On some processors, instructions that implicitly take two memory operands are
// slow. In practice, this means that CALL, PUSH, and POP with memory operands
// should be avoided in favor of a MOV + register CALL/PUSH/POP.
def FeatureSlowTwoMemOps : SubtargetFeature<"slow-two-mem-ops",
                                     "SlowTwoMemOps", "true",
                                     "Two memory operand instructions are slow">;
def FeatureLEAUsesAG : SubtargetFeature<"lea-uses-ag", "LEAUsesAG", "true",
                                   "LEA instruction needs inputs at AG stage">;
def FeatureSlowLEA : SubtargetFeature<"slow-lea", "SlowLEA", "true",
                                   "LEA instruction with certain arguments is slow">;
def FeatureSlow3OpsLEA : SubtargetFeature<"slow-3ops-lea", "Slow3OpsLEA", "true",
                                   "LEA instruction with 3 ops or certain registers is slow">;
def FeatureSlowIncDec : SubtargetFeature<"slow-incdec", "SlowIncDec", "true",
                                   "INC and DEC instructions are slower than ADD and SUB">;
def FeatureSoftFloat
    : SubtargetFeature<"soft-float", "UseSoftFloat", "true",
                       "Use software floating point features.">;
def FeaturePOPCNTFalseDeps : SubtargetFeature<"false-deps-popcnt",
                                     "HasPOPCNTFalseDeps", "true",
                                     "POPCNT has a false dependency on dest register">;
def FeatureLZCNTFalseDeps : SubtargetFeature<"false-deps-lzcnt-tzcnt",
                                     "HasLZCNTFalseDeps", "true",
                                     "LZCNT/TZCNT have a false dependency on dest register">;
// On recent X86 (port bound) processors, its preferable to combine to a single shuffle
// using a variable mask over multiple fixed shuffles.
def FeatureFastVariableShuffle
    : SubtargetFeature<"fast-variable-shuffle",
                       "HasFastVariableShuffle",
                       "true", "Shuffles with variable masks are fast">;
// On some X86 processors, there is no performance hazard to writing only the
// lower parts of a YMM or ZMM register without clearing the upper part.
def FeatureFastPartialYMMorZMMWrite
    : SubtargetFeature<"fast-partial-ymm-or-zmm-write",
                       "HasFastPartialYMMorZMMWrite",
                       "true", "Partial writes to YMM/ZMM registers are fast">;
// FeatureFastScalarFSQRT should be enabled if scalar FSQRT has shorter latency
// than the corresponding NR code. FeatureFastVectorFSQRT should be enabled if
// vector FSQRT has higher throughput than the corresponding NR code.
// The idea is that throughput bound code is likely to be vectorized, so for
// vectorized code we should care about the throughput of SQRT operations.
// But if the code is scalar that probably means that the code has some kind of
// dependency and we should care more about reducing the latency.
def FeatureFastScalarFSQRT
    : SubtargetFeature<"fast-scalar-fsqrt", "HasFastScalarFSQRT",
                       "true", "Scalar SQRT is fast (disable Newton-Raphson)">;
def FeatureFastVectorFSQRT
    : SubtargetFeature<"fast-vector-fsqrt", "HasFastVectorFSQRT",
                       "true", "Vector SQRT is fast (disable Newton-Raphson)">;
// If lzcnt has equivalent latency/throughput to most simple integer ops, it can
// be used to replace test/set sequences.
def FeatureFastLZCNT
    : SubtargetFeature<
          "fast-lzcnt", "HasFastLZCNT", "true",
          "LZCNT instructions are as fast as most simple integer ops">;
// If the target can efficiently decode NOPs upto 11-bytes in length.
def FeatureFast11ByteNOP
    : SubtargetFeature<
          "fast-11bytenop", "HasFast11ByteNOP", "true",
          "Target can quickly decode up to 11 byte NOPs">;
// If the target can efficiently decode NOPs upto 15-bytes in length.
def FeatureFast15ByteNOP
    : SubtargetFeature<
          "fast-15bytenop", "HasFast15ByteNOP", "true",
          "Target can quickly decode up to 15 byte NOPs">;
// Sandy Bridge and newer processors can use SHLD with the same source on both
// inputs to implement rotate to avoid the partial flag update of the normal
// rotate instructions.
def FeatureFastSHLDRotate
    : SubtargetFeature<
          "fast-shld-rotate", "HasFastSHLDRotate", "true",
          "SHLD can be used as a faster rotate">;

// Ivy Bridge and newer processors have enhanced REP MOVSB and STOSB (aka
// "string operations"). See "REP String Enhancement" in the Intel Software
// Development Manual. This feature essentially means that REP MOVSB will copy
// using the largest available size instead of copying bytes one by one, making
// it at least as fast as REPMOVS{W,D,Q}.
def FeatureERMSB
    : SubtargetFeature<
          "ermsb", "HasERMSB", "true",
          "REP MOVS/STOS are fast">;

// Sandy Bridge and newer processors have many instructions that can be
// fused with conditional branches and pass through the CPU as a single
// operation.
def FeatureMacroFusion
    : SubtargetFeature<"macrofusion", "HasMacroFusion", "true",
                 "Various instructions can be fused with conditional branches">;

// Gather is available since Haswell (AVX2 set). So technically, we can
// generate Gathers on all AVX2 processors. But the overhead on HSW is high.
// Skylake Client processor has faster Gathers than HSW and performance is
// similar to Skylake Server (AVX-512).
def FeatureHasFastGather
    : SubtargetFeature<"fast-gather", "HasFastGather", "true",
                       "Indicates if gather is reasonably fast.">;

def FeaturePrefer256Bit
    : SubtargetFeature<"prefer-256-bit", "Prefer256Bit", "true",
                       "Prefer 256-bit AVX instructions">;

// Enable mitigation of some aspects of speculative execution related
// vulnerabilities by removing speculatable indirect branches. This disables
// jump-table formation, rewrites explicit `indirectbr` instructions into
// `switch` instructions, and uses a special construct called a "retpoline" to
// prevent speculation of the remaining indirect branches (indirect calls and
// tail calls).
def FeatureRetpoline
    : SubtargetFeature<"retpoline", "UseRetpoline", "true",
                       "Remove speculation of indirect branches from the "
                       "generated code, either by avoiding them entirely or "
                       "lowering them with a speculation blocking construct.">;

// Rely on external thunks for the emitted retpoline calls. This allows users
// to provide their own custom thunk definitions in highly specialized
// environments such as a kernel that does boot-time hot patching.
def FeatureRetpolineExternalThunk
    : SubtargetFeature<
          "retpoline-external-thunk", "UseRetpolineExternalThunk", "true",
          "Enable retpoline, but with an externally provided thunk.",
          [FeatureRetpoline]>;

//===----------------------------------------------------------------------===//
// Register File Description
//===----------------------------------------------------------------------===//

include "X86RegisterInfo.td"
include "X86RegisterBanks.td"

//===----------------------------------------------------------------------===//
// Instruction Descriptions
//===----------------------------------------------------------------------===//

include "X86Schedule.td"
include "X86InstrInfo.td"

def X86InstrInfo : InstrInfo;

//===----------------------------------------------------------------------===//
// X86 processors supported.
//===----------------------------------------------------------------------===//

include "X86ScheduleAtom.td"
include "X86SchedSandyBridge.td"
include "X86SchedHaswell.td"
include "X86SchedBroadwell.td"
include "X86ScheduleSLM.td"
include "X86ScheduleZnver1.td"
include "X86ScheduleBtVer2.td"
include "X86SchedSkylakeClient.td"
include "X86SchedSkylakeServer.td"

def ProcIntelAtom : SubtargetFeature<"atom", "X86ProcFamily", "IntelAtom",
                    "Intel Atom processors">;
def ProcIntelSLM  : SubtargetFeature<"slm", "X86ProcFamily", "IntelSLM",
                    "Intel Silvermont processors">;
def ProcIntelGLM  : SubtargetFeature<"glm", "X86ProcFamily", "IntelGLM",
                    "Intel Goldmont processors">;
def ProcIntelHSW  : SubtargetFeature<"haswell", "X86ProcFamily",
                    "IntelHaswell", "Intel Haswell processors">;
def ProcIntelBDW  : SubtargetFeature<"broadwell", "X86ProcFamily",
                    "IntelBroadwell", "Intel Broadwell processors">;
def ProcIntelSKL  : SubtargetFeature<"skylake", "X86ProcFamily",
                    "IntelSkylake", "Intel Skylake processors">;
def ProcIntelKNL  : SubtargetFeature<"knl", "X86ProcFamily",
                    "IntelKNL", "Intel Knights Landing processors">;
def ProcIntelSKX  : SubtargetFeature<"skx", "X86ProcFamily",
                    "IntelSKX", "Intel Skylake Server processors">;
def ProcIntelCNL  : SubtargetFeature<"cannonlake", "X86ProcFamily",
                    "IntelCannonlake", "Intel Cannonlake processors">;
def ProcIntelICL  : SubtargetFeature<"icelake", "X86ProcFamily",
                    "IntelIcelake", "Intel Icelake processors">;

class Proc<string Name, list<SubtargetFeature> Features>
 : ProcessorModel<Name, GenericModel, Features>;

def : Proc<"generic",         [FeatureX87, FeatureSlowUAMem16]>;
def : Proc<"i386",            [FeatureX87, FeatureSlowUAMem16]>;
def : Proc<"i486",            [FeatureX87, FeatureSlowUAMem16]>;
def : Proc<"i586",            [FeatureX87, FeatureSlowUAMem16]>;
def : Proc<"pentium",         [FeatureX87, FeatureSlowUAMem16]>;
def : Proc<"pentium-mmx",     [FeatureX87, FeatureSlowUAMem16, FeatureMMX]>;

def : Proc<"i686", [FeatureX87, FeatureSlowUAMem16, FeatureCMOV]>;
def : Proc<"pentiumpro", [FeatureX87, FeatureSlowUAMem16, FeatureCMOV,
                          FeatureNOPL]>;

def : Proc<"pentium2",        [FeatureX87, FeatureSlowUAMem16, FeatureMMX,
                               FeatureCMOV, FeatureFXSR, FeatureNOPL]>;

foreach P = ["pentium3", "pentium3m"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, FeatureMMX, FeatureSSE1,
                 FeatureFXSR, FeatureNOPL]>;
}

// Enable the PostRAScheduler for SSE2 and SSE3 class cpus.
// The intent is to enable it for pentium4 which is the current default
// processor in a vanilla 32-bit clang compilation when no specific
// architecture is specified.  This generally gives a nice performance
// increase on silvermont, with largely neutral behavior on other
// contemporary large core processors.
// pentium-m, pentium4m, prescott and nocona are included as a preventative
// measure to avoid performance surprises, in case clang's default cpu
// changes slightly.

def : ProcessorModel<"pentium-m", GenericPostRAModel,
                     [FeatureX87, FeatureSlowUAMem16, FeatureMMX,
                      FeatureSSE2, FeatureFXSR, FeatureNOPL]>;

foreach P = ["pentium4", "pentium4m"] in {
  def : ProcessorModel<P, GenericPostRAModel,
                       [FeatureX87, FeatureSlowUAMem16, FeatureMMX,
                        FeatureSSE2, FeatureFXSR, FeatureNOPL]>;
}

// Intel Quark.
def : Proc<"lakemont",        []>;

// Intel Core Duo.
def : ProcessorModel<"yonah", SandyBridgeModel,
                     [FeatureX87, FeatureSlowUAMem16, FeatureMMX, FeatureSSE3,
                      FeatureFXSR, FeatureNOPL]>;

// NetBurst.
def : ProcessorModel<"prescott", GenericPostRAModel,
                     [FeatureX87, FeatureSlowUAMem16, FeatureMMX, FeatureSSE3,
                      FeatureFXSR, FeatureNOPL]>;
def : ProcessorModel<"nocona", GenericPostRAModel, [
  FeatureX87,
  FeatureSlowUAMem16,
  FeatureMMX,
  FeatureSSE3,
  FeatureFXSR,
  FeatureNOPL,
  FeatureCMPXCHG16B
]>;

// Intel Core 2 Solo/Duo.
def : ProcessorModel<"core2", SandyBridgeModel, [
  FeatureX87,
  FeatureSlowUAMem16,
  FeatureMMX,
  FeatureSSSE3,
  FeatureFXSR,
  FeatureNOPL,
  FeatureCMPXCHG16B,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;
def : ProcessorModel<"penryn", SandyBridgeModel, [
  FeatureX87,
  FeatureSlowUAMem16,
  FeatureMMX,
  FeatureSSE41,
  FeatureFXSR,
  FeatureNOPL,
  FeatureCMPXCHG16B,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;

// Atom CPUs.
class BonnellProc<string Name> : ProcessorModel<Name, AtomModel, [
  ProcIntelAtom,
  FeatureX87,
  FeatureSlowUAMem16,
  FeatureMMX,
  FeatureSSSE3,
  FeatureFXSR,
  FeatureNOPL,
  FeatureCMPXCHG16B,
  FeatureMOVBE,
  FeatureLEAForSP,
  FeatureSlowDivide32,
  FeatureSlowDivide64,
  FeatureSlowTwoMemOps,
  FeatureLEAUsesAG,
  FeaturePadShortFunctions,
  FeatureLAHFSAHF
]>;
def : BonnellProc<"bonnell">;
def : BonnellProc<"atom">; // Pin the generic name to the baseline.

class SilvermontProc<string Name> : ProcessorModel<Name, SLMModel, [
  ProcIntelSLM,
  FeatureX87,
  FeatureMMX,
  FeatureSSE42,
  FeatureFXSR,
  FeatureNOPL,
  FeatureCMPXCHG16B,
  FeatureMOVBE,
  FeaturePOPCNT,
  FeaturePCLMUL,
  FeatureAES,
  FeatureSlowDivide64,
  FeatureSlowTwoMemOps,
  FeaturePRFCHW,
  FeatureSlowLEA,
  FeatureSlowIncDec,
  FeatureSlowPMULLD,
  FeatureRDRAND,
  FeatureLAHFSAHF
]>;
def : SilvermontProc<"silvermont">;
def : SilvermontProc<"slm">; // Legacy alias.

class GoldmontProc<string Name> : ProcessorModel<Name, SLMModel, [
  ProcIntelGLM,
  FeatureX87,
  FeatureMMX,
  FeatureSSE42,
  FeatureFXSR,
  FeatureNOPL,
  FeatureCMPXCHG16B,
  FeatureMOVBE,
  FeaturePOPCNT,
  FeaturePCLMUL,
  FeatureAES,
  FeaturePRFCHW,
  FeatureSlowTwoMemOps,
  FeatureSlowLEA,
  FeatureSlowIncDec,
  FeatureLAHFSAHF,
  FeatureMPX,
  FeatureSHA,
  FeatureRDRAND,
  FeatureRDSEED,
  FeatureXSAVE,
  FeatureXSAVEOPT,
  FeatureXSAVEC,
  FeatureXSAVES,
  FeatureCLFLUSHOPT,
  FeatureFSGSBase
]>;
def : GoldmontProc<"goldmont">;

// "Arrandale" along with corei3 and corei5
class NehalemProc<string Name> : ProcessorModel<Name, SandyBridgeModel, [
  FeatureX87,
  FeatureMMX,
  FeatureSSE42,
  FeatureFXSR,
  FeatureNOPL,
  FeatureCMPXCHG16B,
  FeaturePOPCNT,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;
def : NehalemProc<"nehalem">;
def : NehalemProc<"corei7">;

// Westmere is a similar machine to nehalem with some additional features.
// Westmere is the corei3/i5/i7 path from nehalem to sandybridge
class WestmereProc<string Name> : ProcessorModel<Name, SandyBridgeModel, [
  FeatureX87,
  FeatureMMX,
  FeatureSSE42,
  FeatureFXSR,
  FeatureNOPL,
  FeatureCMPXCHG16B,
  FeaturePOPCNT,
  FeatureAES,
  FeaturePCLMUL,
  FeatureLAHFSAHF,
  FeatureMacroFusion
]>;
def : WestmereProc<"westmere">;

class ProcessorFeatures<list<SubtargetFeature> Inherited,
                        list<SubtargetFeature> NewFeatures> {
  list<SubtargetFeature> Value = !listconcat(Inherited, NewFeatures);
}

class ProcModel<string Name, SchedMachineModel Model,
                list<SubtargetFeature> ProcFeatures,
                list<SubtargetFeature> OtherFeatures> :
  ProcessorModel<Name, Model, !listconcat(ProcFeatures, OtherFeatures)>;

// SSE is not listed here since llvm treats AVX as a reimplementation of SSE,
// rather than a superset.
def SNBFeatures : ProcessorFeatures<[], [
  FeatureX87,
  FeatureMMX,
  FeatureAVX,
  FeatureFXSR,
  FeatureNOPL,
  FeatureCMPXCHG16B,
  FeaturePOPCNT,
  FeatureAES,
  FeatureSlowDivide64,
  FeaturePCLMUL,
  FeatureXSAVE,
  FeatureXSAVEOPT,
  FeatureLAHFSAHF,
  FeatureSlow3OpsLEA,
  FeatureFastScalarFSQRT,
  FeatureFastSHLDRotate,
  FeatureSlowIncDec,
  FeatureMacroFusion
]>;

class SandyBridgeProc<string Name> : ProcModel<Name, SandyBridgeModel,
                                               SNBFeatures.Value, [
  FeatureSlowUAMem32,
  FeaturePOPCNTFalseDeps
]>;
def : SandyBridgeProc<"sandybridge">;
def : SandyBridgeProc<"corei7-avx">; // Legacy alias.

def IVBFeatures : ProcessorFeatures<SNBFeatures.Value, [
  FeatureRDRAND,
  FeatureF16C,
  FeatureFSGSBase
]>;

class IvyBridgeProc<string Name> : ProcModel<Name, SandyBridgeModel,
                                             IVBFeatures.Value, [
  FeatureSlowUAMem32,
  FeaturePOPCNTFalseDeps
]>;
def : IvyBridgeProc<"ivybridge">;
def : IvyBridgeProc<"core-avx-i">; // Legacy alias.

def HSWFeatures : ProcessorFeatures<IVBFeatures.Value, [
  FeatureAVX2,
  FeatureBMI,
  FeatureBMI2,
  FeatureERMSB,
  FeatureFMA,
  FeatureLZCNT,
  FeatureMOVBE,
  FeatureFastVariableShuffle
]>;

class HaswellProc<string Name> : ProcModel<Name, HaswellModel,
                                           HSWFeatures.Value, [
  ProcIntelHSW,
  FeaturePOPCNTFalseDeps,
  FeatureLZCNTFalseDeps
]>;
def : HaswellProc<"haswell">;
def : HaswellProc<"core-avx2">; // Legacy alias.

def BDWFeatures : ProcessorFeatures<HSWFeatures.Value, [
  FeatureADX,
  FeatureRDSEED,
  FeaturePRFCHW
]>;
class BroadwellProc<string Name> : ProcModel<Name, BroadwellModel,
                                             BDWFeatures.Value, [
  ProcIntelBDW,
  FeaturePOPCNTFalseDeps,
  FeatureLZCNTFalseDeps
]>;
def : BroadwellProc<"broadwell">;

def SKLFeatures : ProcessorFeatures<BDWFeatures.Value, [
  FeatureMPX,
  FeatureRTM,
  FeatureXSAVEC,
  FeatureXSAVES,
  FeatureSGX,
  FeatureCLFLUSHOPT,
  FeatureFastVectorFSQRT
]>;

class SkylakeClientProc<string Name> : ProcModel<Name, SkylakeClientModel,
                                                 SKLFeatures.Value, [
  ProcIntelSKL,
  FeatureHasFastGather,
  FeaturePOPCNTFalseDeps
]>;
def : SkylakeClientProc<"skylake">;

def KNLFeatures : ProcessorFeatures<IVBFeatures.Value, [
  FeatureAVX512,
  FeatureERI,
  FeatureCDI,
  FeaturePFI,
  FeaturePREFETCHWT1,
  FeatureADX,
  FeatureRDSEED,
  FeatureMOVBE,
  FeatureLZCNT,
  FeatureBMI,
  FeatureBMI2,
  FeatureFMA,
  FeaturePRFCHW
]>;

// FIXME: define KNL model
class KnightsLandingProc<string Name> : ProcModel<Name, HaswellModel,
                                                  KNLFeatures.Value, [
  ProcIntelKNL,
  FeatureSlowTwoMemOps,
  FeatureFastPartialYMMorZMMWrite,
  FeatureHasFastGather
]>;
def : KnightsLandingProc<"knl">;

class KnightsMillProc<string Name> : ProcModel<Name, HaswellModel,
                                               KNLFeatures.Value, [
  ProcIntelKNL,
  FeatureSlowTwoMemOps,
  FeatureFastPartialYMMorZMMWrite,
  FeatureHasFastGather,
  FeatureVPOPCNTDQ
]>;
def : KnightsMillProc<"knm">; // TODO Add AVX5124FMAPS/AVX5124VNNIW features

def SKXFeatures : ProcessorFeatures<SKLFeatures.Value, [
  FeatureAVX512,
  FeatureCDI,
  FeatureDQI,
  FeatureBWI,
  FeatureVLX,
  FeaturePKU,
  FeatureCLWB
]>;

class SkylakeServerProc<string Name> : ProcModel<Name, SkylakeServerModel,
                                                 SKXFeatures.Value, [
  ProcIntelSKX,
  FeatureHasFastGather,
  FeaturePOPCNTFalseDeps
]>;
def : SkylakeServerProc<"skylake-avx512">;
def : SkylakeServerProc<"skx">; // Legacy alias.

def CNLFeatures : ProcessorFeatures<SKLFeatures.Value, [
  FeatureAVX512,
  FeatureCDI,
  FeatureDQI,
  FeatureBWI,
  FeatureVLX,
  FeaturePKU,
  FeatureVBMI,
  FeatureIFMA,
  FeatureSHA
]>;

class CannonlakeProc<string Name> : ProcModel<Name, SkylakeServerModel,
                                              CNLFeatures.Value, [
  ProcIntelCNL,
  FeatureHasFastGather
]>;
def : CannonlakeProc<"cannonlake">;

def ICLFeatures : ProcessorFeatures<CNLFeatures.Value, [
  FeatureBITALG,
  FeatureVAES,
  FeatureVBMI2,
  FeatureVNNI,
  FeatureVPCLMULQDQ,
  FeatureVPOPCNTDQ,
  FeatureGFNI,
  FeatureCLWB,
  FeatureRDPID
]>;

class IcelakeProc<string Name> : ProcModel<Name, SkylakeServerModel,
                                           ICLFeatures.Value, [
  ProcIntelICL,
  FeatureHasFastGather
]>;
def : IcelakeProc<"icelake">;

// AMD CPUs.

def : Proc<"k6",              [FeatureX87, FeatureSlowUAMem16, FeatureMMX]>;
def : Proc<"k6-2",            [FeatureX87, FeatureSlowUAMem16, Feature3DNow]>;
def : Proc<"k6-3",            [FeatureX87, FeatureSlowUAMem16, Feature3DNow]>;

foreach P = ["athlon", "athlon-tbird"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, Feature3DNowA,
                 FeatureNOPL, FeatureSlowSHLD]>;
}

foreach P = ["athlon-4", "athlon-xp", "athlon-mp"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, FeatureSSE1,
                 Feature3DNowA, FeatureFXSR, FeatureNOPL, FeatureSlowSHLD]>;
}

foreach P = ["k8", "opteron", "athlon64", "athlon-fx"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, FeatureSSE2, Feature3DNowA,
                 FeatureFXSR, FeatureNOPL, Feature64Bit, FeatureSlowSHLD]>;
}

foreach P = ["k8-sse3", "opteron-sse3", "athlon64-sse3"] in {
  def : Proc<P, [FeatureX87, FeatureSlowUAMem16, FeatureSSE3, Feature3DNowA,
                 FeatureFXSR, FeatureNOPL, FeatureCMPXCHG16B, FeatureSlowSHLD]>;
}

foreach P = ["amdfam10", "barcelona"] in {
  def : Proc<P, [FeatureX87, FeatureSSE4A, Feature3DNowA, FeatureFXSR,
                 FeatureNOPL, FeatureCMPXCHG16B, FeatureLZCNT, FeaturePOPCNT,
                 FeatureSlowSHLD, FeatureLAHFSAHF]>;
}

// Bobcat
def : Proc<"btver1", [
  FeatureX87,
  FeatureMMX,
  FeatureSSSE3,
  FeatureSSE4A,
  FeatureFXSR,
  FeatureNOPL,
  FeatureCMPXCHG16B,
  FeaturePRFCHW,
  FeatureLZCNT,
  FeaturePOPCNT,
  FeatureSlowSHLD,
  FeatureLAHFSAHF,
  FeatureFast15ByteNOP
]>;

// Jaguar
def : ProcessorModel<"btver2", BtVer2Model, [
  FeatureX87,
  FeatureMMX,
  FeatureAVX,
  FeatureFXSR,
  FeatureNOPL,
  FeatureSSE4A,
  FeatureCMPXCHG16B,
  FeaturePRFCHW,
  FeatureAES,
  FeaturePCLMUL,
  FeatureBMI,
  FeatureF16C,
  FeatureMOVBE,
  FeatureLZCNT,
  FeatureFastLZCNT,
  FeaturePOPCNT,
  FeatureXSAVE,
  FeatureXSAVEOPT,
  FeatureSlowSHLD,
  FeatureLAHFSAHF,
  FeatureFast15ByteNOP,
  FeatureFastPartialYMMorZMMWrite
]>;

// Bulldozer
def : Proc<"bdver1", [
  FeatureX87,
  FeatureXOP,
  FeatureFMA4,
  FeatureCMPXCHG16B,
  FeatureAES,
  FeaturePRFCHW,
  FeaturePCLMUL,
  FeatureMMX,
  FeatureAVX,
  FeatureFXSR,
  FeatureNOPL,
  FeatureSSE4A,
  FeatureLZCNT,
  FeaturePOPCNT,
  FeatureXSAVE,
  FeatureLWP,
  FeatureSlowSHLD,
  FeatureLAHFSAHF,
  FeatureFast11ByteNOP,
  FeatureMacroFusion
]>;
// Piledriver
def : Proc<"bdver2", [
  FeatureX87,
  FeatureXOP,
  FeatureFMA4,
  FeatureCMPXCHG16B,
  FeatureAES,
  FeaturePRFCHW,
  FeaturePCLMUL,
  FeatureMMX,
  FeatureAVX,
  FeatureFXSR,
  FeatureNOPL,
  FeatureSSE4A,
  FeatureF16C,
  FeatureLZCNT,
  FeaturePOPCNT,
  FeatureXSAVE,
  FeatureBMI,
  FeatureTBM,
  FeatureLWP,
  FeatureFMA,
  FeatureSlowSHLD,
  FeatureLAHFSAHF,
  FeatureFast11ByteNOP,
  FeatureMacroFusion
]>;

// Steamroller
def : Proc<"bdver3", [
  FeatureX87,
  FeatureXOP,
  FeatureFMA4,
  FeatureCMPXCHG16B,
  FeatureAES,
  FeaturePRFCHW,
  FeaturePCLMUL,
  FeatureMMX,
  FeatureAVX,
  FeatureFXSR,
  FeatureNOPL,
  FeatureSSE4A,
  FeatureF16C,
  FeatureLZCNT,
  FeaturePOPCNT,
  FeatureXSAVE,
  FeatureBMI,
  FeatureTBM,
  FeatureLWP,
  FeatureFMA,
  FeatureXSAVEOPT,
  FeatureSlowSHLD,
  FeatureFSGSBase,
  FeatureLAHFSAHF,
  FeatureFast11ByteNOP,
  FeatureMacroFusion
]>;

// Excavator
def : Proc<"bdver4", [
  FeatureX87,
  FeatureMMX,
  FeatureAVX2,
  FeatureFXSR,
  FeatureNOPL,
  FeatureXOP,
  FeatureFMA4,
  FeatureCMPXCHG16B,
  FeatureAES,
  FeaturePRFCHW,
  FeaturePCLMUL,
  FeatureF16C,
  FeatureLZCNT,
  FeaturePOPCNT,
  FeatureXSAVE,
  FeatureBMI,
  FeatureBMI2,
  FeatureTBM,
  FeatureLWP,
  FeatureFMA,
  FeatureXSAVEOPT,
  FeatureSlowSHLD,
  FeatureFSGSBase,
  FeatureLAHFSAHF,
  FeatureFast11ByteNOP,
  FeatureMWAITX,
  FeatureMacroFusion
]>;

// Znver1
def: ProcessorModel<"znver1", Znver1Model, [
  FeatureADX,
  FeatureAES,
  FeatureAVX2,
  FeatureBMI,
  FeatureBMI2,
  FeatureCLFLUSHOPT,
  FeatureCLZERO,
  FeatureCMPXCHG16B,
  FeatureF16C,
  FeatureFMA,
  FeatureFSGSBase,
  FeatureFXSR,
  FeatureNOPL,
  FeatureFastLZCNT,
  FeatureLAHFSAHF,
  FeatureLZCNT,
  FeatureFast15ByteNOP,
  FeatureMacroFusion,
  FeatureMMX,
  FeatureMOVBE,
  FeatureMWAITX,
  FeaturePCLMUL,
  FeaturePOPCNT,
  FeaturePRFCHW,
  FeatureRDRAND,
  FeatureRDSEED,
  FeatureSHA,
  FeatureSSE4A,
  FeatureSlowSHLD,
  FeatureX87,
  FeatureXSAVE,
  FeatureXSAVEC,
  FeatureXSAVEOPT,
  FeatureXSAVES]>;

def : Proc<"geode",           [FeatureX87, FeatureSlowUAMem16, Feature3DNowA]>;

def : Proc<"winchip-c6",      [FeatureX87, FeatureSlowUAMem16, FeatureMMX]>;
def : Proc<"winchip2",        [FeatureX87, FeatureSlowUAMem16, Feature3DNow]>;
def : Proc<"c3",              [FeatureX87, FeatureSlowUAMem16, Feature3DNow]>;
def : Proc<"c3-2",            [FeatureX87, FeatureSlowUAMem16, FeatureMMX,
                               FeatureSSE1, FeatureFXSR]>;

// We also provide a generic 64-bit specific x86 processor model which tries to
// be good for modern chips without enabling instruction set encodings past the
// basic SSE2 and 64-bit ones. It disables slow things from any mainstream and
// modern 64-bit x86 chip, and enables features that are generally beneficial.
//
// We currently use the Sandy Bridge model as the default scheduling model as
// we use it across Nehalem, Westmere, Sandy Bridge, and Ivy Bridge which
// covers a huge swath of x86 processors. If there are specific scheduling
// knobs which need to be tuned differently for AMD chips, we might consider
// forming a common base for them.
def : ProcessorModel<"x86-64", SandyBridgeModel, [
  FeatureX87,
  FeatureMMX,
  FeatureSSE2,
  FeatureFXSR,
  FeatureNOPL,
  Feature64Bit,
  FeatureSlow3OpsLEA,
  FeatureSlowIncDec,
  FeatureMacroFusion
]>;

//===----------------------------------------------------------------------===//
// Calling Conventions
//===----------------------------------------------------------------------===//

include "X86CallingConv.td"


//===----------------------------------------------------------------------===//
// Assembly Parser
//===----------------------------------------------------------------------===//

def ATTAsmParserVariant : AsmParserVariant {
  int Variant = 0;

  // Variant name.
  string Name = "att";

  // Discard comments in assembly strings.
  string CommentDelimiter = "#";

  // Recognize hard coded registers.
  string RegisterPrefix = "%";
}

def IntelAsmParserVariant : AsmParserVariant {
  int Variant = 1;

  // Variant name.
  string Name = "intel";

  // Discard comments in assembly strings.
  string CommentDelimiter = ";";

  // Recognize hard coded registers.
  string RegisterPrefix = "";
}

//===----------------------------------------------------------------------===//
// Assembly Printers
//===----------------------------------------------------------------------===//

// The X86 target supports two different syntaxes for emitting machine code.
// This is controlled by the -x86-asm-syntax={att|intel}
def ATTAsmWriter : AsmWriter {
  string AsmWriterClassName  = "ATTInstPrinter";
  int Variant = 0;
}
def IntelAsmWriter : AsmWriter {
  string AsmWriterClassName  = "IntelInstPrinter";
  int Variant = 1;
}

def X86 : Target {
  // Information about the instructions...
  let InstructionSet = X86InstrInfo;
  let AssemblyParserVariants = [ATTAsmParserVariant, IntelAsmParserVariant];
  let AssemblyWriters = [ATTAsmWriter, IntelAsmWriter];
  let AllowRegisterRenaming = 1;
}

//===----------------------------------------------------------------------===//
// Pfm Counters
//===----------------------------------------------------------------------===//

include "X86PfmCounters.td"