| //===-- X86.td - Target definition file for the Intel X86 --*- tablegen -*-===// |
| // |
| // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. |
| // See https://llvm.org/LICENSE.txt for license information. |
| // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception |
| // |
| //===----------------------------------------------------------------------===// |
| // |
| // 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 |
| // |
| // disregarding specific ABI / programming model |
| def Is64Bit : SubtargetFeature<"64bit-mode", "Is64Bit", "true", |
| "64-bit mode (x86_64)">; |
| def Is32Bit : SubtargetFeature<"32bit-mode", "Is32Bit", "true", |
| "32-bit mode (80386)">; |
| def Is16Bit : SubtargetFeature<"16bit-mode", "Is16Bit", "true", |
| "16-bit mode (i8086)">; |
| |
| //===----------------------------------------------------------------------===// |
| // X86 Subtarget ISA features |
| //===----------------------------------------------------------------------===// |
| |
| def FeatureX87 : SubtargetFeature<"x87","HasX87", "true", |
| "Enable X87 float instructions">; |
| |
| def FeatureNOPL : SubtargetFeature<"nopl", "HasNOPL", "true", |
| "Enable NOPL instruction (generally pentium pro+)">; |
| |
| def FeatureCMOV : SubtargetFeature<"cmov","HasCMOV", "true", |
| "Enable conditional move instructions">; |
| |
| def FeatureCX8 : SubtargetFeature<"cx8", "HasCX8", "true", |
| "Support CMPXCHG8B instructions">; |
| |
| def FeatureCRC32 : SubtargetFeature<"crc32", "HasCRC32", "true", |
| "Enable SSE 4.2 CRC32 instruction (used when SSE4.2 is supported but function is GPR only)">; |
| |
| 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", |
| [FeatureXSAVE]>; |
| |
| def FeatureXSAVEC : SubtargetFeature<"xsavec", "HasXSAVEC", "true", |
| "Support xsavec instructions", |
| [FeatureXSAVE]>; |
| |
| def FeatureXSAVES : SubtargetFeature<"xsaves", "HasXSAVES", "true", |
| "Support xsaves instructions", |
| [FeatureXSAVE]>; |
| |
| def FeatureSSE1 : SubtargetFeature<"sse", "X86SSELevel", "SSE1", |
| "Enable SSE instructions">; |
| 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. Nothing should imply this feature bit. It |
| // is used to enforce that only 64-bit capable CPUs are used in 64-bit mode. |
| def FeatureX86_64 : SubtargetFeature<"64bit", "HasX86_64", "true", |
| "Support 64-bit instructions">; |
| def FeatureCX16 : SubtargetFeature<"cx16", "HasCX16", "true", |
| "64-bit with cmpxchg16b (this is true for most x86-64 chips, but not the first AMD chips)", |
| [FeatureCX8]>; |
| 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", "AVX512", |
| "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 FeaturePREFETCHI : SubtargetFeature<"prefetchi", "HasPREFETCHI", |
| "true", |
| "Prefetch instruction with T0 or T1 Hint">; |
| 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 FeatureAVXIFMA : SubtargetFeature<"avxifma", "HasAVXIFMA", "true", |
| "Enable AVX-IFMA", |
| [FeatureAVX2]>; |
| 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 FeatureAVXVNNI : SubtargetFeature<"avxvnni", "HasAVXVNNI", "true", |
| "Support AVX_VNNI encoding", |
| [FeatureAVX2]>; |
| def FeatureBF16 : SubtargetFeature<"avx512bf16", "HasBF16", "true", |
| "Support bfloat16 floating point", |
| [FeatureBWI]>; |
| def FeatureBITALG : SubtargetFeature<"avx512bitalg", "HasBITALG", "true", |
| "Enable AVX-512 Bit Algorithms", |
| [FeatureBWI]>; |
| def FeatureVP2INTERSECT : SubtargetFeature<"avx512vp2intersect", |
| "HasVP2INTERSECT", "true", |
| "Enable AVX-512 vp2intersect", |
| [FeatureAVX512]>; |
| // FIXME: FP16 scalar intrinsics use the type v8f16, which is supposed to be |
| // guarded under condition hasVLX. So we imply it in FeatureFP16 currently. |
| // FIXME: FP16 conversion between f16 and i64 customize type v8i64, which is |
| // supposed to be guarded under condition hasDQI. So we imply it in FeatureFP16 |
| // currently. |
| def FeatureFP16 : SubtargetFeature<"avx512fp16", "HasFP16", "true", |
| "Support 16-bit floating point", |
| [FeatureBWI, FeatureVLX, FeatureDQI]>; |
| def FeatureAVXVNNIINT8 : SubtargetFeature<"avxvnniint8", |
| "HasAVXVNNIINT8", "true", |
| "Enable AVX-VNNI-INT8", |
| [FeatureAVX2]>; |
| 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 (this may require setting a configuration bit in the processor)">; |
| 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]>; |
| // Processor supports CET SHSTK - Control-Flow Enforcement Technology |
| // using Shadow Stack |
| def FeatureSHSTK : SubtargetFeature<"shstk", "HasSHSTK", "true", |
| "Support CET Shadow-Stack instructions">; |
| def FeaturePRFCHW : SubtargetFeature<"prfchw", "HasPRFCHW", "true", |
| "Support PRFCHW instructions">; |
| def FeatureRDSEED : SubtargetFeature<"rdseed", "HasRDSEED", "true", |
| "Support RDSEED instruction">; |
| def FeatureLAHFSAHF64 : SubtargetFeature<"sahf", "HasLAHFSAHF64", "true", |
| "Support LAHF and SAHF instructions in 64-bit mode">; |
| def FeatureMWAITX : SubtargetFeature<"mwaitx", "HasMWAITX", "true", |
| "Enable MONITORX/MWAITX timer functionality">; |
| def FeatureCLZERO : SubtargetFeature<"clzero", "HasCLZERO", "true", |
| "Enable Cache Line Zero">; |
| def FeatureCLDEMOTE : SubtargetFeature<"cldemote", "HasCLDEMOTE", "true", |
| "Enable Cache Line Demote">; |
| def FeaturePTWRITE : SubtargetFeature<"ptwrite", "HasPTWRITE", "true", |
| "Support ptwrite instruction">; |
| def FeatureAMXTILE : SubtargetFeature<"amx-tile", "HasAMXTILE", "true", |
| "Support AMX-TILE instructions">; |
| def FeatureAMXINT8 : SubtargetFeature<"amx-int8", "HasAMXINT8", "true", |
| "Support AMX-INT8 instructions", |
| [FeatureAMXTILE]>; |
| def FeatureAMXBF16 : SubtargetFeature<"amx-bf16", "HasAMXBF16", "true", |
| "Support AMX-BF16 instructions", |
| [FeatureAMXTILE]>; |
| def FeatureAMXFP16 : SubtargetFeature<"amx-fp16", "HasAMXFP16", "true", |
| "Support AMX amx-fp16 instructions", |
| [FeatureAMXTILE]>; |
| def FeatureAMXCOMPLEX : SubtargetFeature<"amx-complex", "HasAMXCOMPLEX", "true", |
| "Support AMX-COMPLEX instructions", |
| [FeatureAMXTILE]>; |
| def FeatureCMPCCXADD : SubtargetFeature<"cmpccxadd", "HasCMPCCXADD", "true", |
| "Support CMPCCXADD instructions">; |
| def FeatureRAOINT : SubtargetFeature<"raoint", "HasRAOINT", "true", |
| "Support RAO-INT instructions", |
| []>; |
| def FeatureAVXNECONVERT : SubtargetFeature<"avxneconvert", "HasAVXNECONVERT", "true", |
| "Support AVX-NE-CONVERT instructions", |
| [FeatureAVX2]>; |
| def FeatureINVPCID : SubtargetFeature<"invpcid", "HasINVPCID", "true", |
| "Invalidate Process-Context Identifier">; |
| 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 FeatureWBNOINVD : SubtargetFeature<"wbnoinvd", "HasWBNOINVD", "true", |
| "Write Back No Invalidate">; |
| def FeatureRDPID : SubtargetFeature<"rdpid", "HasRDPID", "true", |
| "Support RDPID instructions">; |
| def FeatureRDPRU : SubtargetFeature<"rdpru", "HasRDPRU", "true", |
| "Support RDPRU instructions">; |
| def FeatureWAITPKG : SubtargetFeature<"waitpkg", "HasWAITPKG", "true", |
| "Wait and pause enhancements">; |
| def FeatureENQCMD : SubtargetFeature<"enqcmd", "HasENQCMD", "true", |
| "Has ENQCMD instructions">; |
| def FeatureKL : SubtargetFeature<"kl", "HasKL", "true", |
| "Support Key Locker kl Instructions", |
| [FeatureSSE2]>; |
| def FeatureWIDEKL : SubtargetFeature<"widekl", "HasWIDEKL", "true", |
| "Support Key Locker wide Instructions", |
| [FeatureKL]>; |
| def FeatureHRESET : SubtargetFeature<"hreset", "HasHRESET", "true", |
| "Has hreset instruction">; |
| def FeatureSERIALIZE : SubtargetFeature<"serialize", "HasSERIALIZE", "true", |
| "Has serialize instruction">; |
| def FeatureTSXLDTRK : SubtargetFeature<"tsxldtrk", "HasTSXLDTRK", "true", |
| "Support TSXLDTRK instructions">; |
| def FeatureUINTR : SubtargetFeature<"uintr", "HasUINTR", "true", |
| "Has UINTR Instructions">; |
| def FeaturePCONFIG : SubtargetFeature<"pconfig", "HasPCONFIG", "true", |
| "platform configuration instruction">; |
| def FeatureMOVDIRI : SubtargetFeature<"movdiri", "HasMOVDIRI", "true", |
| "Support movdiri instruction (direct store integer)">; |
| def FeatureMOVDIR64B : SubtargetFeature<"movdir64b", "HasMOVDIR64B", "true", |
| "Support movdir64b instruction (direct store 64 bytes)">; |
| |
| // 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">; |
| |
| // Icelake and newer processors have Fast Short REP MOV. |
| def FeatureFSRM |
| : SubtargetFeature< |
| "fsrm", "HasFSRM", "true", |
| "REP MOVSB of short lengths is faster">; |
| |
| def FeatureSoftFloat |
| : SubtargetFeature<"soft-float", "UseSoftFloat", "true", |
| "Use software floating point features">; |
| |
| //===----------------------------------------------------------------------===// |
| // X86 Subtarget Security Mitigation features |
| //===----------------------------------------------------------------------===// |
| |
| // Lower indirect calls using a special construct called a `retpoline` to |
| // mitigate potential Spectre v2 attacks against them. |
| def FeatureRetpolineIndirectCalls |
| : SubtargetFeature< |
| "retpoline-indirect-calls", "UseRetpolineIndirectCalls", "true", |
| "Remove speculation of indirect calls from the generated code">; |
| |
| // Lower indirect branches and switches either using conditional branch trees |
| // or using a special construct called a `retpoline` to mitigate potential |
| // Spectre v2 attacks against them. |
| def FeatureRetpolineIndirectBranches |
| : SubtargetFeature< |
| "retpoline-indirect-branches", "UseRetpolineIndirectBranches", "true", |
| "Remove speculation of indirect branches from the generated code">; |
| |
| // Deprecated umbrella feature for enabling both `retpoline-indirect-calls` and |
| // `retpoline-indirect-branches` above. |
| def FeatureRetpoline |
| : SubtargetFeature<"retpoline", "DeprecatedUseRetpoline", "true", |
| "Remove speculation of indirect branches from the " |
| "generated code, either by avoiding them entirely or " |
| "lowering them with a speculation blocking construct", |
| [FeatureRetpolineIndirectCalls, |
| FeatureRetpolineIndirectBranches]>; |
| |
| // 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", |
| "When lowering an indirect call or branch using a `retpoline`, rely " |
| "on the specified user provided thunk rather than emitting one " |
| "ourselves. Only has effect when combined with some other retpoline " |
| "feature", [FeatureRetpolineIndirectCalls]>; |
| |
| // Mitigate LVI attacks against indirect calls/branches and call returns |
| def FeatureLVIControlFlowIntegrity |
| : SubtargetFeature< |
| "lvi-cfi", "UseLVIControlFlowIntegrity", "true", |
| "Prevent indirect calls/branches from using a memory operand, and " |
| "precede all indirect calls/branches from a register with an " |
| "LFENCE instruction to serialize control flow. Also decompose RET " |
| "instructions into a POP+LFENCE+JMP sequence.">; |
| |
| // Enable SESES to mitigate speculative execution attacks |
| def FeatureSpeculativeExecutionSideEffectSuppression |
| : SubtargetFeature< |
| "seses", "UseSpeculativeExecutionSideEffectSuppression", "true", |
| "Prevent speculative execution side channel timing attacks by " |
| "inserting a speculation barrier before memory reads, memory writes, " |
| "and conditional branches. Implies LVI Control Flow integrity.", |
| [FeatureLVIControlFlowIntegrity]>; |
| |
| // Mitigate LVI attacks against data loads |
| def FeatureLVILoadHardening |
| : SubtargetFeature< |
| "lvi-load-hardening", "UseLVILoadHardening", "true", |
| "Insert LFENCE instructions to prevent data speculatively injected " |
| "into loads from being used maliciously.">; |
| |
| def FeatureTaggedGlobals |
| : SubtargetFeature< |
| "tagged-globals", "AllowTaggedGlobals", "true", |
| "Use an instruction sequence for taking the address of a global " |
| "that allows a memory tag in the upper address bits.">; |
| |
| // Control codegen mitigation against Straight Line Speculation vulnerability. |
| def FeatureHardenSlsRet |
| : SubtargetFeature< |
| "harden-sls-ret", "HardenSlsRet", "true", |
| "Harden against straight line speculation across RET instructions.">; |
| |
| def FeatureHardenSlsIJmp |
| : SubtargetFeature< |
| "harden-sls-ijmp", "HardenSlsIJmp", "true", |
| "Harden against straight line speculation across indirect JMP instructions.">; |
| |
| //===----------------------------------------------------------------------===// |
| // X86 Subtarget Tuning features |
| //===----------------------------------------------------------------------===// |
| |
| def TuningSlowSHLD : SubtargetFeature<"slow-shld", "IsSHLDSlow", "true", |
| "SHLD instruction is slow">; |
| |
| def TuningSlowPMULLD : SubtargetFeature<"slow-pmulld", "IsPMULLDSlow", "true", |
| "PMULLD instruction is slow (compared to PMULLW/PMULHW and PMULUDQ)">; |
| |
| def TuningSlowPMADDWD : SubtargetFeature<"slow-pmaddwd", "IsPMADDWDSlow", |
| "true", |
| "PMADDWD is slower than PMULLD">; |
| |
| // FIXME: This should not apply to CPUs that do not have SSE. |
| def TuningSlowUAMem16 : SubtargetFeature<"slow-unaligned-mem-16", |
| "IsUnalignedMem16Slow", "true", |
| "Slow unaligned 16-byte memory access">; |
| |
| def TuningSlowUAMem32 : SubtargetFeature<"slow-unaligned-mem-32", |
| "IsUnalignedMem32Slow", "true", |
| "Slow unaligned 32-byte memory access">; |
| |
| def TuningLEAForSP : SubtargetFeature<"lea-sp", "UseLeaForSP", "true", |
| "Use LEA for adjusting the stack pointer (this is an optimization for Intel Atom processors)">; |
| |
| // True if 8-bit divisions are significantly faster than |
| // 32-bit divisions and should be used when possible. |
| def TuningSlowDivide32 : SubtargetFeature<"idivl-to-divb", |
| "HasSlowDivide32", "true", |
| "Use 8-bit divide for positive values less than 256">; |
| |
| // True if 32-bit divides are significantly faster than |
| // 64-bit divisions and should be used when possible. |
| def TuningSlowDivide64 : SubtargetFeature<"idivq-to-divl", |
| "HasSlowDivide64", "true", |
| "Use 32-bit divide for positive values less than 2^32">; |
| |
| def TuningPadShortFunctions : SubtargetFeature<"pad-short-functions", |
| "PadShortFunctions", "true", |
| "Pad short functions (to prevent a stall when returning too early)">; |
| |
| // 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 TuningSlowTwoMemOps : SubtargetFeature<"slow-two-mem-ops", |
| "SlowTwoMemOps", "true", |
| "Two memory operand instructions are slow">; |
| |
| // True if the LEA instruction inputs have to be ready at address generation |
| // (AG) time. |
| def TuningLEAUsesAG : SubtargetFeature<"lea-uses-ag", "LeaUsesAG", "true", |
| "LEA instruction needs inputs at AG stage">; |
| |
| def TuningSlowLEA : SubtargetFeature<"slow-lea", "SlowLEA", "true", |
| "LEA instruction with certain arguments is slow">; |
| |
| // True if the LEA instruction has all three source operands: base, index, |
| // and offset or if the LEA instruction uses base and index registers where |
| // the base is EBP, RBP,or R13 |
| def TuningSlow3OpsLEA : SubtargetFeature<"slow-3ops-lea", "Slow3OpsLEA", "true", |
| "LEA instruction with 3 ops or certain registers is slow">; |
| |
| // True if INC and DEC instructions are slow when writing to flags |
| def TuningSlowIncDec : SubtargetFeature<"slow-incdec", "SlowIncDec", "true", |
| "INC and DEC instructions are slower than ADD and SUB">; |
| |
| def TuningPOPCNTFalseDeps : SubtargetFeature<"false-deps-popcnt", |
| "HasPOPCNTFalseDeps", "true", |
| "POPCNT has a false dependency on dest register">; |
| |
| def TuningLZCNTFalseDeps : SubtargetFeature<"false-deps-lzcnt-tzcnt", |
| "HasLZCNTFalseDeps", "true", |
| "LZCNT/TZCNT have a false dependency on dest register">; |
| |
| def TuningMULCFalseDeps : SubtargetFeature<"false-deps-mulc", |
| "HasMULCFalseDeps", "true", |
| "VF[C]MULCPH/SH has a false dependency on dest register">; |
| |
| def TuningPERMFalseDeps : SubtargetFeature<"false-deps-perm", |
| "HasPERMFalseDeps", "true", |
| "VPERMD/Q/PS/PD has a false dependency on dest register">; |
| |
| def TuningRANGEFalseDeps : SubtargetFeature<"false-deps-range", |
| "HasRANGEFalseDeps", "true", |
| "VRANGEPD/PS/SD/SS has a false dependency on dest register">; |
| |
| def TuningGETMANTFalseDeps : SubtargetFeature<"false-deps-getmant", |
| "HasGETMANTFalseDeps", "true", |
| "VGETMANTSS/SD/SH and VGETMANDPS/PD(memory version) has a" |
| " false dependency on dest register">; |
| |
| def TuningMULLQFalseDeps : SubtargetFeature<"false-deps-mullq", |
| "HasMULLQFalseDeps", "true", |
| "VPMULLQ has a false dependency on dest register">; |
| |
| def TuningSBBDepBreaking : SubtargetFeature<"sbb-dep-breaking", |
| "HasSBBDepBreaking", "true", |
| "SBB with same register has no source dependency">; |
| |
| // On recent X86 (port bound) processors, its preferable to combine to a single shuffle |
| // using a variable mask over multiple fixed shuffles. |
| def TuningFastVariableCrossLaneShuffle |
| : SubtargetFeature<"fast-variable-crosslane-shuffle", |
| "HasFastVariableCrossLaneShuffle", |
| "true", "Cross-lane shuffles with variable masks are fast">; |
| def TuningFastVariablePerLaneShuffle |
| : SubtargetFeature<"fast-variable-perlane-shuffle", |
| "HasFastVariablePerLaneShuffle", |
| "true", "Per-lane shuffles with variable masks are fast">; |
| |
| // Goldmont / Tremont (atom in general) has no bypass delay |
| def TuningNoDomainDelay : SubtargetFeature<"no-bypass-delay", |
| "NoDomainDelay","true", |
| "Has no bypass delay when using the 'wrong' domain">; |
| |
| // Many processors (Nehalem+ on Intel) have no bypass delay when |
| // using the wrong mov type. |
| def TuningNoDomainDelayMov : SubtargetFeature<"no-bypass-delay-mov", |
| "NoDomainDelayMov","true", |
| "Has no bypass delay when using the 'wrong' mov type">; |
| |
| // Newer processors (Skylake+ on Intel) have no bypass delay when |
| // using the wrong blend type. |
| def TuningNoDomainDelayBlend : SubtargetFeature<"no-bypass-delay-blend", |
| "NoDomainDelayBlend","true", |
| "Has no bypass delay when using the 'wrong' blend type">; |
| |
| // Newer processors (Haswell+ on Intel) have no bypass delay when |
| // using the wrong shuffle type. |
| def TuningNoDomainDelayShuffle : SubtargetFeature<"no-bypass-delay-shuffle", |
| "NoDomainDelayShuffle","true", |
| "Has no bypass delay when using the 'wrong' shuffle type">; |
| |
| // Prefer lowering shuffles on AVX512 targets (e.g. Skylake Server) to |
| // imm shifts/rotate if they can use more ports than regular shuffles. |
| def TuningPreferShiftShuffle : SubtargetFeature<"faster-shift-than-shuffle", |
| "PreferLowerShuffleAsShift", "true", |
| "Shifts are faster (or as fast) as shuffle">; |
| |
| // On some X86 processors, a vzeroupper instruction should be inserted after |
| // using ymm/zmm registers before executing code that may use SSE instructions. |
| def TuningInsertVZEROUPPER |
| : SubtargetFeature<"vzeroupper", |
| "InsertVZEROUPPER", |
| "true", "Should insert vzeroupper instructions">; |
| |
| // TuningFastScalarFSQRT should be enabled if scalar FSQRT has shorter latency |
| // than the corresponding NR code. TuningFastVectorFSQRT 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. |
| |
| // True if hardware SQRTSS instruction is at least as fast (latency) as |
| // RSQRTSS followed by a Newton-Raphson iteration. |
| def TuningFastScalarFSQRT |
| : SubtargetFeature<"fast-scalar-fsqrt", "HasFastScalarFSQRT", |
| "true", "Scalar SQRT is fast (disable Newton-Raphson)">; |
| // True if hardware SQRTPS/VSQRTPS instructions are at least as fast |
| // (throughput) as RSQRTPS/VRSQRTPS followed by a Newton-Raphson iteration. |
| def TuningFastVectorFSQRT |
| : 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 TuningFastLZCNT |
| : SubtargetFeature< |
| "fast-lzcnt", "HasFastLZCNT", "true", |
| "LZCNT instructions are as fast as most simple integer ops">; |
| |
| // If the target can efficiently decode NOPs upto 7-bytes in length. |
| def TuningFast7ByteNOP |
| : SubtargetFeature< |
| "fast-7bytenop", "HasFast7ByteNOP", "true", |
| "Target can quickly decode up to 7 byte NOPs">; |
| |
| // If the target can efficiently decode NOPs upto 11-bytes in length. |
| def TuningFast11ByteNOP |
| : 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 TuningFast15ByteNOP |
| : 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 TuningFastSHLDRotate |
| : SubtargetFeature< |
| "fast-shld-rotate", "HasFastSHLDRotate", "true", |
| "SHLD can be used as a faster rotate">; |
| |
| // Bulldozer and newer processors can merge CMP/TEST (but not other |
| // instructions) with conditional branches. |
| def TuningBranchFusion |
| : SubtargetFeature<"branchfusion", "HasBranchFusion", "true", |
| "CMP/TEST can be fused with conditional branches">; |
| |
| // 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 TuningMacroFusion |
| : 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 TuningFastGather |
| : SubtargetFeature<"fast-gather", "HasFastGather", "true", |
| "Indicates if gather is reasonably fast (this is true for Skylake client and all AVX-512 CPUs)">; |
| |
| def TuningPrefer128Bit |
| : SubtargetFeature<"prefer-128-bit", "Prefer128Bit", "true", |
| "Prefer 128-bit AVX instructions">; |
| |
| def TuningPrefer256Bit |
| : SubtargetFeature<"prefer-256-bit", "Prefer256Bit", "true", |
| "Prefer 256-bit AVX instructions">; |
| |
| def TuningAllowLight256Bit |
| : SubtargetFeature<"allow-light-256-bit", "AllowLight256Bit", "true", |
| "Enable generation of 256-bit load/stores even if we prefer 128-bit">; |
| |
| def TuningPreferMaskRegisters |
| : SubtargetFeature<"prefer-mask-registers", "PreferMaskRegisters", "true", |
| "Prefer AVX512 mask registers over PTEST/MOVMSK">; |
| |
| def TuningFastBEXTR : SubtargetFeature<"fast-bextr", "HasFastBEXTR", "true", |
| "Indicates that the BEXTR instruction is implemented as a single uop " |
| "with good throughput">; |
| |
| // Combine vector math operations with shuffles into horizontal math |
| // instructions if a CPU implements horizontal operations (introduced with |
| // SSE3) with better latency/throughput than the alternative sequence. |
| def TuningFastHorizontalOps |
| : SubtargetFeature< |
| "fast-hops", "HasFastHorizontalOps", "true", |
| "Prefer horizontal vector math instructions (haddp, phsub, etc.) over " |
| "normal vector instructions with shuffles">; |
| |
| def TuningFastScalarShiftMasks |
| : SubtargetFeature< |
| "fast-scalar-shift-masks", "HasFastScalarShiftMasks", "true", |
| "Prefer a left/right scalar logical shift pair over a shift+and pair">; |
| |
| def TuningFastVectorShiftMasks |
| : SubtargetFeature< |
| "fast-vector-shift-masks", "HasFastVectorShiftMasks", "true", |
| "Prefer a left/right vector logical shift pair over a shift+and pair">; |
| |
| def TuningFastMOVBE |
| : SubtargetFeature<"fast-movbe", "HasFastMOVBE", "true", |
| "Prefer a movbe over a single-use load + bswap / single-use bswap + store">; |
| |
| def TuningUseSLMArithCosts |
| : SubtargetFeature<"use-slm-arith-costs", "UseSLMArithCosts", "true", |
| "Use Silvermont specific arithmetic costs">; |
| |
| def TuningUseGLMDivSqrtCosts |
| : SubtargetFeature<"use-glm-div-sqrt-costs", "UseGLMDivSqrtCosts", "true", |
| "Use Goldmont specific floating point div/sqrt costs">; |
| |
| //===----------------------------------------------------------------------===// |
| // X86 CPU Families |
| // TODO: Remove these - use general tuning features to determine codegen. |
| //===----------------------------------------------------------------------===// |
| |
| // Bonnell |
| def ProcIntelAtom : SubtargetFeature<"", "IsAtom", "true", "Is Intel Atom processor">; |
| |
| //===----------------------------------------------------------------------===// |
| // Register File Description |
| //===----------------------------------------------------------------------===// |
| |
| include "X86RegisterInfo.td" |
| include "X86RegisterBanks.td" |
| |
| //===----------------------------------------------------------------------===// |
| // Instruction Descriptions |
| //===----------------------------------------------------------------------===// |
| |
| include "X86Schedule.td" |
| include "X86InstrInfo.td" |
| include "X86SchedPredicates.td" |
| |
| def X86InstrInfo : InstrInfo; |
| |
| //===----------------------------------------------------------------------===// |
| // X86 Scheduler Models |
| //===----------------------------------------------------------------------===// |
| |
| include "X86ScheduleAtom.td" |
| include "X86SchedSandyBridge.td" |
| include "X86SchedHaswell.td" |
| include "X86SchedBroadwell.td" |
| include "X86ScheduleSLM.td" |
| include "X86ScheduleZnver1.td" |
| include "X86ScheduleZnver2.td" |
| include "X86ScheduleZnver3.td" |
| include "X86ScheduleZnver4.td" |
| include "X86ScheduleBdVer2.td" |
| include "X86ScheduleBtVer2.td" |
| include "X86SchedSkylakeClient.td" |
| include "X86SchedSkylakeServer.td" |
| include "X86SchedIceLake.td" |
| include "X86SchedAlderlakeP.td" |
| include "X86SchedSapphireRapids.td" |
| |
| //===----------------------------------------------------------------------===// |
| // X86 Processor Feature Lists |
| //===----------------------------------------------------------------------===// |
| |
| def ProcessorFeatures { |
| // x86-64 micro-architecture levels: x86-64 and x86-64-v[234] |
| list<SubtargetFeature> X86_64V1Features = [ |
| FeatureX87, FeatureCX8, FeatureCMOV, FeatureMMX, FeatureSSE2, |
| FeatureFXSR, FeatureNOPL, FeatureX86_64, |
| ]; |
| list<SubtargetFeature> X86_64V1Tuning = [ |
| TuningMacroFusion, |
| TuningSlow3OpsLEA, |
| TuningSlowDivide64, |
| TuningSlowIncDec, |
| TuningInsertVZEROUPPER |
| ]; |
| |
| list<SubtargetFeature> X86_64V2Features = !listconcat(X86_64V1Features, [ |
| FeatureCX16, FeatureLAHFSAHF64, FeatureCRC32, FeaturePOPCNT, |
| FeatureSSE42 |
| ]); |
| list<SubtargetFeature> X86_64V2Tuning = [ |
| TuningMacroFusion, |
| TuningSlow3OpsLEA, |
| TuningSlowDivide64, |
| TuningSlowUAMem32, |
| TuningFastScalarFSQRT, |
| TuningFastSHLDRotate, |
| TuningFast15ByteNOP, |
| TuningPOPCNTFalseDeps, |
| TuningInsertVZEROUPPER |
| ]; |
| |
| list<SubtargetFeature> X86_64V3Features = !listconcat(X86_64V2Features, [ |
| FeatureAVX2, FeatureBMI, FeatureBMI2, FeatureF16C, FeatureFMA, FeatureLZCNT, |
| FeatureMOVBE, FeatureXSAVE |
| ]); |
| list<SubtargetFeature> X86_64V3Tuning = [ |
| TuningMacroFusion, |
| TuningSlow3OpsLEA, |
| TuningSlowDivide64, |
| TuningFastScalarFSQRT, |
| TuningFastSHLDRotate, |
| TuningFast15ByteNOP, |
| TuningFastVariableCrossLaneShuffle, |
| TuningFastVariablePerLaneShuffle, |
| TuningPOPCNTFalseDeps, |
| TuningLZCNTFalseDeps, |
| TuningInsertVZEROUPPER, |
| TuningAllowLight256Bit |
| ]; |
| |
| list<SubtargetFeature> X86_64V4Features = !listconcat(X86_64V3Features, [ |
| FeatureBWI, |
| FeatureCDI, |
| FeatureDQI, |
| FeatureVLX, |
| ]); |
| list<SubtargetFeature> X86_64V4Tuning = [ |
| TuningMacroFusion, |
| TuningSlow3OpsLEA, |
| TuningSlowDivide64, |
| TuningFastScalarFSQRT, |
| TuningFastVectorFSQRT, |
| TuningFastSHLDRotate, |
| TuningFast15ByteNOP, |
| TuningFastVariableCrossLaneShuffle, |
| TuningFastVariablePerLaneShuffle, |
| TuningPrefer256Bit, |
| TuningFastGather, |
| TuningPOPCNTFalseDeps, |
| TuningInsertVZEROUPPER, |
| TuningAllowLight256Bit |
| ]; |
| |
| // Nehalem |
| list<SubtargetFeature> NHMFeatures = X86_64V2Features; |
| list<SubtargetFeature> NHMTuning = [TuningMacroFusion, |
| TuningInsertVZEROUPPER, |
| TuningNoDomainDelayMov]; |
| |
| // Westmere |
| list<SubtargetFeature> WSMAdditionalFeatures = [FeaturePCLMUL]; |
| list<SubtargetFeature> WSMTuning = NHMTuning; |
| list<SubtargetFeature> WSMFeatures = |
| !listconcat(NHMFeatures, WSMAdditionalFeatures); |
| |
| // Sandybridge |
| list<SubtargetFeature> SNBAdditionalFeatures = [FeatureAVX, |
| FeatureXSAVE, |
| FeatureXSAVEOPT]; |
| list<SubtargetFeature> SNBTuning = [TuningMacroFusion, |
| TuningSlow3OpsLEA, |
| TuningSlowDivide64, |
| TuningSlowUAMem32, |
| TuningFastScalarFSQRT, |
| TuningFastSHLDRotate, |
| TuningFast15ByteNOP, |
| TuningPOPCNTFalseDeps, |
| TuningInsertVZEROUPPER, |
| TuningNoDomainDelayMov]; |
| list<SubtargetFeature> SNBFeatures = |
| !listconcat(WSMFeatures, SNBAdditionalFeatures); |
| |
| // Ivybridge |
| list<SubtargetFeature> IVBAdditionalFeatures = [FeatureRDRAND, |
| FeatureF16C, |
| FeatureFSGSBase]; |
| list<SubtargetFeature> IVBTuning = SNBTuning; |
| list<SubtargetFeature> IVBFeatures = |
| !listconcat(SNBFeatures, IVBAdditionalFeatures); |
| |
| // Haswell |
| list<SubtargetFeature> HSWAdditionalFeatures = [FeatureAVX2, |
| FeatureBMI, |
| FeatureBMI2, |
| FeatureERMSB, |
| FeatureFMA, |
| FeatureINVPCID, |
| FeatureLZCNT, |
| FeatureMOVBE]; |
| list<SubtargetFeature> HSWTuning = [TuningMacroFusion, |
| TuningSlow3OpsLEA, |
| TuningSlowDivide64, |
| TuningFastScalarFSQRT, |
| TuningFastSHLDRotate, |
| TuningFast15ByteNOP, |
| TuningFastVariableCrossLaneShuffle, |
| TuningFastVariablePerLaneShuffle, |
| TuningPOPCNTFalseDeps, |
| TuningLZCNTFalseDeps, |
| TuningInsertVZEROUPPER, |
| TuningAllowLight256Bit, |
| TuningNoDomainDelayMov, |
| TuningNoDomainDelayShuffle]; |
| list<SubtargetFeature> HSWFeatures = |
| !listconcat(IVBFeatures, HSWAdditionalFeatures); |
| |
| // Broadwell |
| list<SubtargetFeature> BDWAdditionalFeatures = [FeatureADX, |
| FeatureRDSEED, |
| FeaturePRFCHW]; |
| list<SubtargetFeature> BDWTuning = HSWTuning; |
| list<SubtargetFeature> BDWFeatures = |
| !listconcat(HSWFeatures, BDWAdditionalFeatures); |
| |
| // Skylake |
| list<SubtargetFeature> SKLAdditionalFeatures = [FeatureAES, |
| FeatureXSAVEC, |
| FeatureXSAVES, |
| FeatureCLFLUSHOPT]; |
| list<SubtargetFeature> SKLTuning = [TuningFastGather, |
| TuningMacroFusion, |
| TuningSlow3OpsLEA, |
| TuningSlowDivide64, |
| TuningFastScalarFSQRT, |
| TuningFastVectorFSQRT, |
| TuningFastSHLDRotate, |
| TuningFast15ByteNOP, |
| TuningFastVariableCrossLaneShuffle, |
| TuningFastVariablePerLaneShuffle, |
| TuningPOPCNTFalseDeps, |
| TuningInsertVZEROUPPER, |
| TuningAllowLight256Bit, |
| TuningNoDomainDelayMov, |
| TuningNoDomainDelayShuffle, |
| TuningNoDomainDelayBlend]; |
| list<SubtargetFeature> SKLFeatures = |
| !listconcat(BDWFeatures, SKLAdditionalFeatures); |
| |
| // Skylake-AVX512 |
| list<SubtargetFeature> SKXAdditionalFeatures = [FeatureAES, |
| FeatureXSAVEC, |
| FeatureXSAVES, |
| FeatureCLFLUSHOPT, |
| FeatureAVX512, |
| FeatureCDI, |
| FeatureDQI, |
| FeatureBWI, |
| FeatureVLX, |
| FeaturePKU, |
| FeatureCLWB]; |
| list<SubtargetFeature> SKXTuning = [TuningFastGather, |
| TuningMacroFusion, |
| TuningSlow3OpsLEA, |
| TuningSlowDivide64, |
| TuningFastScalarFSQRT, |
| TuningFastVectorFSQRT, |
| TuningFastSHLDRotate, |
| TuningFast15ByteNOP, |
| TuningFastVariableCrossLaneShuffle, |
| TuningFastVariablePerLaneShuffle, |
| TuningPrefer256Bit, |
| TuningPOPCNTFalseDeps, |
| TuningInsertVZEROUPPER, |
| TuningAllowLight256Bit, |
| TuningPreferShiftShuffle, |
| TuningNoDomainDelayMov, |
| TuningNoDomainDelayShuffle, |
| TuningNoDomainDelayBlend]; |
| list<SubtargetFeature> SKXFeatures = |
| !listconcat(BDWFeatures, SKXAdditionalFeatures); |
| |
| // Cascadelake |
| list<SubtargetFeature> CLXAdditionalFeatures = [FeatureVNNI]; |
| list<SubtargetFeature> CLXTuning = SKXTuning; |
| list<SubtargetFeature> CLXFeatures = |
| !listconcat(SKXFeatures, CLXAdditionalFeatures); |
| |
| // Cooperlake |
| list<SubtargetFeature> CPXAdditionalFeatures = [FeatureBF16]; |
| list<SubtargetFeature> CPXTuning = SKXTuning; |
| list<SubtargetFeature> CPXFeatures = |
| !listconcat(CLXFeatures, CPXAdditionalFeatures); |
| |
| // Cannonlake |
| list<SubtargetFeature> CNLAdditionalFeatures = [FeatureAVX512, |
| FeatureCDI, |
| FeatureDQI, |
| FeatureBWI, |
| FeatureVLX, |
| FeaturePKU, |
| FeatureVBMI, |
| FeatureIFMA, |
| FeatureSHA]; |
| list<SubtargetFeature> CNLTuning = [TuningFastGather, |
| TuningMacroFusion, |
| TuningSlow3OpsLEA, |
| TuningSlowDivide64, |
| TuningFastScalarFSQRT, |
| TuningFastVectorFSQRT, |
| TuningFastSHLDRotate, |
| TuningFast15ByteNOP, |
| TuningFastVariableCrossLaneShuffle, |
| TuningFastVariablePerLaneShuffle, |
| TuningPrefer256Bit, |
| TuningInsertVZEROUPPER, |
| TuningAllowLight256Bit, |
| TuningNoDomainDelayMov, |
| TuningNoDomainDelayShuffle, |
| TuningNoDomainDelayBlend]; |
| list<SubtargetFeature> CNLFeatures = |
| !listconcat(SKLFeatures, CNLAdditionalFeatures); |
| |
| // Icelake |
| list<SubtargetFeature> ICLAdditionalFeatures = [FeatureBITALG, |
| FeatureVAES, |
| FeatureVBMI2, |
| FeatureVNNI, |
| FeatureVPCLMULQDQ, |
| FeatureVPOPCNTDQ, |
| FeatureGFNI, |
| FeatureRDPID, |
| FeatureFSRM]; |
| list<SubtargetFeature> ICLTuning = [TuningFastGather, |
| TuningMacroFusion, |
| TuningSlowDivide64, |
| TuningFastScalarFSQRT, |
| TuningFastVectorFSQRT, |
| TuningFastSHLDRotate, |
| TuningFast15ByteNOP, |
| TuningFastVariableCrossLaneShuffle, |
| TuningFastVariablePerLaneShuffle, |
| TuningPrefer256Bit, |
| TuningInsertVZEROUPPER, |
| TuningAllowLight256Bit, |
| TuningNoDomainDelayMov, |
| TuningNoDomainDelayShuffle, |
| TuningNoDomainDelayBlend]; |
| list<SubtargetFeature> ICLFeatures = |
| !listconcat(CNLFeatures, ICLAdditionalFeatures); |
| |
| // Icelake Server |
| list<SubtargetFeature> ICXAdditionalFeatures = [FeaturePCONFIG, |
| FeatureCLWB, |
| FeatureWBNOINVD]; |
| list<SubtargetFeature> ICXTuning = ICLTuning; |
| list<SubtargetFeature> ICXFeatures = |
| !listconcat(ICLFeatures, ICXAdditionalFeatures); |
| |
| // Tigerlake |
| list<SubtargetFeature> TGLAdditionalFeatures = [FeatureVP2INTERSECT, |
| FeatureCLWB, |
| FeatureMOVDIRI, |
| FeatureMOVDIR64B, |
| FeatureSHSTK]; |
| list<SubtargetFeature> TGLTuning = ICLTuning; |
| list<SubtargetFeature> TGLFeatures = |
| !listconcat(ICLFeatures, TGLAdditionalFeatures ); |
| |
| // Sapphirerapids |
| list<SubtargetFeature> SPRAdditionalFeatures = [FeatureAMXTILE, |
| FeatureAMXINT8, |
| FeatureAMXBF16, |
| FeatureBF16, |
| FeatureSERIALIZE, |
| FeatureCLDEMOTE, |
| FeatureWAITPKG, |
| FeaturePTWRITE, |
| FeatureFP16, |
| FeatureAVXVNNI, |
| FeatureTSXLDTRK, |
| FeatureENQCMD, |
| FeatureSHSTK, |
| FeatureMOVDIRI, |
| FeatureMOVDIR64B, |
| FeatureUINTR]; |
| list<SubtargetFeature> SPRAdditionalTuning = [TuningMULCFalseDeps, |
| TuningPERMFalseDeps, |
| TuningRANGEFalseDeps, |
| TuningGETMANTFalseDeps, |
| TuningMULLQFalseDeps]; |
| list<SubtargetFeature> SPRTuning = !listconcat(ICXTuning, SPRAdditionalTuning); |
| list<SubtargetFeature> SPRFeatures = |
| !listconcat(ICXFeatures, SPRAdditionalFeatures); |
| |
| // Graniterapids |
| list<SubtargetFeature> GNRAdditionalFeatures = [FeatureAMXFP16, |
| FeaturePREFETCHI, |
| FeatureAMXCOMPLEX]; |
| list<SubtargetFeature> GNRFeatures = |
| !listconcat(SPRFeatures, GNRAdditionalFeatures); |
| |
| // Atom |
| list<SubtargetFeature> AtomFeatures = [FeatureX87, |
| FeatureCX8, |
| FeatureCMOV, |
| FeatureMMX, |
| FeatureSSSE3, |
| FeatureFXSR, |
| FeatureNOPL, |
| FeatureX86_64, |
| FeatureCX16, |
| FeatureMOVBE, |
| FeatureLAHFSAHF64]; |
| list<SubtargetFeature> AtomTuning = [ProcIntelAtom, |
| TuningSlowUAMem16, |
| TuningLEAForSP, |
| TuningSlowDivide32, |
| TuningSlowDivide64, |
| TuningSlowTwoMemOps, |
| TuningLEAUsesAG, |
| TuningPadShortFunctions, |
| TuningInsertVZEROUPPER, |
| TuningNoDomainDelay]; |
| |
| // Silvermont |
| list<SubtargetFeature> SLMAdditionalFeatures = [FeatureSSE42, |
| FeatureCRC32, |
| FeaturePOPCNT, |
| FeaturePCLMUL, |
| FeaturePRFCHW, |
| FeatureRDRAND]; |
| list<SubtargetFeature> SLMTuning = [TuningUseSLMArithCosts, |
| TuningSlowTwoMemOps, |
| TuningSlowLEA, |
| TuningSlowIncDec, |
| TuningSlowDivide64, |
| TuningSlowPMULLD, |
| TuningFast7ByteNOP, |
| TuningFastMOVBE, |
| TuningPOPCNTFalseDeps, |
| TuningInsertVZEROUPPER, |
| TuningNoDomainDelay]; |
| list<SubtargetFeature> SLMFeatures = |
| !listconcat(AtomFeatures, SLMAdditionalFeatures); |
| |
| // Goldmont |
| list<SubtargetFeature> GLMAdditionalFeatures = [FeatureAES, |
| FeatureSHA, |
| FeatureRDSEED, |
| FeatureXSAVE, |
| FeatureXSAVEOPT, |
| FeatureXSAVEC, |
| FeatureXSAVES, |
| FeatureCLFLUSHOPT, |
| FeatureFSGSBase]; |
| list<SubtargetFeature> GLMTuning = [TuningUseGLMDivSqrtCosts, |
| TuningSlowTwoMemOps, |
| TuningSlowLEA, |
| TuningSlowIncDec, |
| TuningFastMOVBE, |
| TuningPOPCNTFalseDeps, |
| TuningInsertVZEROUPPER, |
| TuningNoDomainDelay]; |
| list<SubtargetFeature> GLMFeatures = |
| !listconcat(SLMFeatures, GLMAdditionalFeatures); |
| |
| // Goldmont Plus |
| list<SubtargetFeature> GLPAdditionalFeatures = [FeaturePTWRITE, |
| FeatureRDPID]; |
| list<SubtargetFeature> GLPTuning = [TuningUseGLMDivSqrtCosts, |
| TuningSlowTwoMemOps, |
| TuningSlowLEA, |
| TuningSlowIncDec, |
| TuningFastMOVBE, |
| TuningInsertVZEROUPPER, |
| TuningNoDomainDelay]; |
| list<SubtargetFeature> GLPFeatures = |
| !listconcat(GLMFeatures, GLPAdditionalFeatures); |
| |
| // Tremont |
| list<SubtargetFeature> TRMAdditionalFeatures = [FeatureCLWB, |
| FeatureGFNI]; |
| list<SubtargetFeature> TRMTuning = GLPTuning; |
| list<SubtargetFeature> TRMFeatures = |
| !listconcat(GLPFeatures, TRMAdditionalFeatures); |
| |
| // Alderlake |
| list<SubtargetFeature> ADLAdditionalFeatures = [FeatureSERIALIZE, |
| FeaturePCONFIG, |
| FeatureSHSTK, |
| FeatureWIDEKL, |
| FeatureINVPCID, |
| FeatureADX, |
| FeatureFMA, |
| FeatureVAES, |
| FeatureVPCLMULQDQ, |
| FeatureF16C, |
| FeatureBMI, |
| FeatureBMI2, |
| FeatureLZCNT, |
| FeatureAVXVNNI, |
| FeaturePKU, |
| FeatureHRESET, |
| FeatureCLDEMOTE, |
| FeatureMOVDIRI, |
| FeatureMOVDIR64B, |
| FeatureWAITPKG]; |
| list<SubtargetFeature> ADLAdditionalTuning = [TuningPERMFalseDeps]; |
| list<SubtargetFeature> ADLTuning = !listconcat(SKLTuning, ADLAdditionalTuning); |
| list<SubtargetFeature> ADLFeatures = |
| !listconcat(TRMFeatures, ADLAdditionalFeatures); |
| |
| // Sierraforest |
| list<SubtargetFeature> SRFAdditionalFeatures = [FeatureCMPCCXADD, |
| FeatureAVXIFMA, |
| FeatureAVXNECONVERT, |
| FeatureAVXVNNIINT8]; |
| list<SubtargetFeature> SRFFeatures = |
| !listconcat(ADLFeatures, SRFAdditionalFeatures); |
| |
| // Grandridge |
| list<SubtargetFeature> GRRAdditionalFeatures = [FeatureRAOINT]; |
| list<SubtargetFeature> GRRFeatures = |
| !listconcat(SRFFeatures, GRRAdditionalFeatures); |
| |
| // Knights Landing |
| list<SubtargetFeature> KNLFeatures = [FeatureX87, |
| FeatureCX8, |
| FeatureCMOV, |
| FeatureMMX, |
| FeatureFXSR, |
| FeatureNOPL, |
| FeatureX86_64, |
| FeatureCX16, |
| FeatureCRC32, |
| FeaturePOPCNT, |
| FeaturePCLMUL, |
| FeatureXSAVE, |
| FeatureXSAVEOPT, |
| FeatureLAHFSAHF64, |
| FeatureAES, |
| FeatureRDRAND, |
| FeatureF16C, |
| FeatureFSGSBase, |
| FeatureAVX512, |
| FeatureERI, |
| FeatureCDI, |
| FeaturePFI, |
| FeaturePREFETCHWT1, |
| FeatureADX, |
| FeatureRDSEED, |
| FeatureMOVBE, |
| FeatureLZCNT, |
| FeatureBMI, |
| FeatureBMI2, |
| FeatureFMA, |
| FeaturePRFCHW]; |
| list<SubtargetFeature> KNLTuning = [TuningSlowDivide64, |
| TuningSlow3OpsLEA, |
| TuningSlowIncDec, |
| TuningSlowTwoMemOps, |
| TuningPreferMaskRegisters, |
| TuningFastGather, |
| TuningFastMOVBE, |
| TuningSlowPMADDWD]; |
| // TODO Add AVX5124FMAPS/AVX5124VNNIW features |
| list<SubtargetFeature> KNMFeatures = |
| !listconcat(KNLFeatures, [FeatureVPOPCNTDQ]); |
| |
| // Barcelona |
| list<SubtargetFeature> BarcelonaFeatures = [FeatureX87, |
| FeatureCX8, |
| FeatureSSE4A, |
| Feature3DNowA, |
| FeatureFXSR, |
| FeatureNOPL, |
| FeatureCX16, |
| FeaturePRFCHW, |
| FeatureLZCNT, |
| FeaturePOPCNT, |
| FeatureLAHFSAHF64, |
| FeatureCMOV, |
| FeatureX86_64]; |
| list<SubtargetFeature> BarcelonaTuning = [TuningFastScalarShiftMasks, |
| TuningSlowSHLD, |
| TuningSBBDepBreaking, |
| TuningInsertVZEROUPPER]; |
| |
| // Bobcat |
| list<SubtargetFeature> BtVer1Features = [FeatureX87, |
| FeatureCX8, |
| FeatureCMOV, |
| FeatureMMX, |
| FeatureSSSE3, |
| FeatureSSE4A, |
| FeatureFXSR, |
| FeatureNOPL, |
| FeatureX86_64, |
| FeatureCX16, |
| FeaturePRFCHW, |
| FeatureLZCNT, |
| FeaturePOPCNT, |
| FeatureLAHFSAHF64]; |
| list<SubtargetFeature> BtVer1Tuning = [TuningFast15ByteNOP, |
| TuningFastScalarShiftMasks, |
| TuningFastVectorShiftMasks, |
| TuningSlowSHLD, |
| TuningSBBDepBreaking, |
| TuningInsertVZEROUPPER]; |
| |
| // Jaguar |
| list<SubtargetFeature> BtVer2AdditionalFeatures = [FeatureAVX, |
| FeatureAES, |
| FeatureCRC32, |
| FeaturePCLMUL, |
| FeatureBMI, |
| FeatureF16C, |
| FeatureMOVBE, |
| FeatureXSAVE, |
| FeatureXSAVEOPT]; |
| list<SubtargetFeature> BtVer2Tuning = [TuningFastLZCNT, |
| TuningFastBEXTR, |
| TuningFastHorizontalOps, |
| TuningFast15ByteNOP, |
| TuningFastScalarShiftMasks, |
| TuningFastVectorShiftMasks, |
| TuningFastMOVBE, |
| TuningSBBDepBreaking, |
| TuningSlowSHLD]; |
| list<SubtargetFeature> BtVer2Features = |
| !listconcat(BtVer1Features, BtVer2AdditionalFeatures); |
| |
| // Bulldozer |
| list<SubtargetFeature> BdVer1Features = [FeatureX87, |
| FeatureCX8, |
| FeatureCMOV, |
| FeatureXOP, |
| FeatureX86_64, |
| FeatureCX16, |
| FeatureAES, |
| FeatureCRC32, |
| FeaturePRFCHW, |
| FeaturePCLMUL, |
| FeatureMMX, |
| FeatureFXSR, |
| FeatureNOPL, |
| FeatureLZCNT, |
| FeaturePOPCNT, |
| FeatureXSAVE, |
| FeatureLWP, |
| FeatureLAHFSAHF64]; |
| list<SubtargetFeature> BdVer1Tuning = [TuningSlowSHLD, |
| TuningFast11ByteNOP, |
| TuningFastScalarShiftMasks, |
| TuningBranchFusion, |
| TuningSBBDepBreaking, |
| TuningInsertVZEROUPPER]; |
| |
| // PileDriver |
| list<SubtargetFeature> BdVer2AdditionalFeatures = [FeatureF16C, |
| FeatureBMI, |
| FeatureTBM, |
| FeatureFMA]; |
| list<SubtargetFeature> BdVer2AdditionalTuning = [TuningFastBEXTR, |
| TuningFastMOVBE]; |
| list<SubtargetFeature> BdVer2Tuning = |
| !listconcat(BdVer1Tuning, BdVer2AdditionalTuning); |
| list<SubtargetFeature> BdVer2Features = |
| !listconcat(BdVer1Features, BdVer2AdditionalFeatures); |
| |
| // Steamroller |
| list<SubtargetFeature> BdVer3AdditionalFeatures = [FeatureXSAVEOPT, |
| FeatureFSGSBase]; |
| list<SubtargetFeature> BdVer3Tuning = BdVer2Tuning; |
| list<SubtargetFeature> BdVer3Features = |
| !listconcat(BdVer2Features, BdVer3AdditionalFeatures); |
| |
| // Excavator |
| list<SubtargetFeature> BdVer4AdditionalFeatures = [FeatureAVX2, |
| FeatureBMI2, |
| FeatureMOVBE, |
| FeatureRDRAND, |
| FeatureMWAITX]; |
| list<SubtargetFeature> BdVer4Tuning = BdVer3Tuning; |
| list<SubtargetFeature> BdVer4Features = |
| !listconcat(BdVer3Features, BdVer4AdditionalFeatures); |
| |
| |
| // AMD Zen Processors common ISAs |
| list<SubtargetFeature> ZNFeatures = [FeatureADX, |
| FeatureAES, |
| FeatureAVX2, |
| FeatureBMI, |
| FeatureBMI2, |
| FeatureCLFLUSHOPT, |
| FeatureCLZERO, |
| FeatureCMOV, |
| FeatureX86_64, |
| FeatureCX16, |
| FeatureCRC32, |
| FeatureF16C, |
| FeatureFMA, |
| FeatureFSGSBase, |
| FeatureFXSR, |
| FeatureNOPL, |
| FeatureLAHFSAHF64, |
| FeatureLZCNT, |
| FeatureMMX, |
| FeatureMOVBE, |
| FeatureMWAITX, |
| FeaturePCLMUL, |
| FeaturePOPCNT, |
| FeaturePRFCHW, |
| FeatureRDRAND, |
| FeatureRDSEED, |
| FeatureSHA, |
| FeatureSSE4A, |
| FeatureX87, |
| FeatureXSAVE, |
| FeatureXSAVEC, |
| FeatureXSAVEOPT, |
| FeatureXSAVES]; |
| list<SubtargetFeature> ZNTuning = [TuningFastLZCNT, |
| TuningFastBEXTR, |
| TuningFast15ByteNOP, |
| TuningBranchFusion, |
| TuningFastScalarFSQRT, |
| TuningFastVectorFSQRT, |
| TuningFastScalarShiftMasks, |
| TuningFastVariablePerLaneShuffle, |
| TuningFastMOVBE, |
| TuningSlowSHLD, |
| TuningSBBDepBreaking, |
| TuningInsertVZEROUPPER, |
| TuningAllowLight256Bit]; |
| list<SubtargetFeature> ZN2AdditionalFeatures = [FeatureCLWB, |
| FeatureRDPID, |
| FeatureRDPRU, |
| FeatureWBNOINVD]; |
| list<SubtargetFeature> ZN2Tuning = ZNTuning; |
| list<SubtargetFeature> ZN2Features = |
| !listconcat(ZNFeatures, ZN2AdditionalFeatures); |
| list<SubtargetFeature> ZN3AdditionalFeatures = [FeatureFSRM, |
| FeatureINVPCID, |
| FeaturePKU, |
| FeatureVAES, |
| FeatureVPCLMULQDQ]; |
| list<SubtargetFeature> ZN3AdditionalTuning = [TuningMacroFusion]; |
| list<SubtargetFeature> ZN3Tuning = |
| !listconcat(ZN2Tuning, ZN3AdditionalTuning); |
| list<SubtargetFeature> ZN3Features = |
| !listconcat(ZN2Features, ZN3AdditionalFeatures); |
| list<SubtargetFeature> ZN4Tuning = ZN3Tuning; |
| list<SubtargetFeature> ZN4AdditionalFeatures = [FeatureAVX512, |
| FeatureCDI, |
| FeatureDQI, |
| FeatureBWI, |
| FeatureVLX, |
| FeatureVBMI, |
| FeatureVBMI2, |
| FeatureIFMA, |
| FeatureVNNI, |
| FeatureBITALG, |
| FeatureGFNI, |
| FeatureBF16, |
| FeatureSHSTK, |
| FeatureVPOPCNTDQ]; |
| list<SubtargetFeature> ZN4Features = |
| !listconcat(ZN3Features, ZN4AdditionalFeatures); |
| } |
| |
| //===----------------------------------------------------------------------===// |
| // X86 processors supported. |
| //===----------------------------------------------------------------------===// |
| |
| class Proc<string Name, list<SubtargetFeature> Features, |
| list<SubtargetFeature> TuneFeatures> |
| : ProcessorModel<Name, GenericModel, Features, TuneFeatures>; |
| |
| class ProcModel<string Name, SchedMachineModel Model, |
| list<SubtargetFeature> Features, |
| list<SubtargetFeature> TuneFeatures> |
| : ProcessorModel<Name, Model, Features, TuneFeatures>; |
| |
| // NOTE: CMPXCHG8B is here for legacy compatibility so that it is only disabled |
| // if i386/i486 is specifically requested. |
| // NOTE: 64Bit is here as "generic" is the default llc CPU. The X86Subtarget |
| // constructor checks that any CPU used in 64-bit mode has FeatureX86_64 |
| // enabled. It has no effect on code generation. |
| // NOTE: As a default tuning, "generic" aims to produce code optimized for the |
| // most common X86 processors. The tunings might be changed over time. It is |
| // recommended to use "tune-cpu"="x86-64" in function attribute for consistency. |
| def : ProcModel<"generic", SandyBridgeModel, |
| [FeatureX87, FeatureCX8, FeatureX86_64], |
| [TuningSlow3OpsLEA, |
| TuningSlowDivide64, |
| TuningMacroFusion, |
| TuningFastScalarFSQRT, |
| TuningFast15ByteNOP, |
| TuningInsertVZEROUPPER]>; |
| |
| def : Proc<"i386", [FeatureX87], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : Proc<"i486", [FeatureX87], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : Proc<"i586", [FeatureX87, FeatureCX8], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : Proc<"pentium", [FeatureX87, FeatureCX8], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : Proc<"pentium-mmx", [FeatureX87, FeatureCX8, FeatureMMX], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| |
| def : Proc<"i686", [FeatureX87, FeatureCX8, FeatureCMOV], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : Proc<"pentiumpro", [FeatureX87, FeatureCX8, FeatureCMOV, |
| FeatureNOPL], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| |
| def : Proc<"pentium2", [FeatureX87, FeatureCX8, FeatureMMX, FeatureCMOV, |
| FeatureFXSR, FeatureNOPL], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| |
| foreach P = ["pentium3", "pentium3m"] in { |
| def : Proc<P, [FeatureX87, FeatureCX8, FeatureMMX, |
| FeatureSSE1, FeatureFXSR, FeatureNOPL, FeatureCMOV], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| } |
| |
| // 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 : ProcModel<"pentium-m", GenericPostRAModel, |
| [FeatureX87, FeatureCX8, FeatureMMX, FeatureSSE2, |
| FeatureFXSR, FeatureNOPL, FeatureCMOV], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| |
| foreach P = ["pentium4", "pentium4m"] in { |
| def : ProcModel<P, GenericPostRAModel, |
| [FeatureX87, FeatureCX8, FeatureMMX, FeatureSSE2, |
| FeatureFXSR, FeatureNOPL, FeatureCMOV], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| } |
| |
| // Intel Quark. |
| def : Proc<"lakemont", [FeatureCX8], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| |
| // Intel Core Duo. |
| def : ProcModel<"yonah", SandyBridgeModel, |
| [FeatureX87, FeatureCX8, FeatureMMX, FeatureSSE3, |
| FeatureFXSR, FeatureNOPL, FeatureCMOV], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| |
| // NetBurst. |
| def : ProcModel<"prescott", GenericPostRAModel, |
| [FeatureX87, FeatureCX8, FeatureMMX, FeatureSSE3, |
| FeatureFXSR, FeatureNOPL, FeatureCMOV], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : ProcModel<"nocona", GenericPostRAModel, [ |
| FeatureX87, |
| FeatureCX8, |
| FeatureCMOV, |
| FeatureMMX, |
| FeatureSSE3, |
| FeatureFXSR, |
| FeatureNOPL, |
| FeatureX86_64, |
| FeatureCX16, |
| ], |
| [ |
| TuningSlowUAMem16, |
| TuningInsertVZEROUPPER |
| ]>; |
| |
| // Intel Core 2 Solo/Duo. |
| def : ProcModel<"core2", SandyBridgeModel, [ |
| FeatureX87, |
| FeatureCX8, |
| FeatureCMOV, |
| FeatureMMX, |
| FeatureSSSE3, |
| FeatureFXSR, |
| FeatureNOPL, |
| FeatureX86_64, |
| FeatureCX16, |
| FeatureLAHFSAHF64 |
| ], |
| [ |
| TuningMacroFusion, |
| TuningSlowUAMem16, |
| TuningInsertVZEROUPPER |
| ]>; |
| def : ProcModel<"penryn", SandyBridgeModel, [ |
| FeatureX87, |
| FeatureCX8, |
| FeatureCMOV, |
| FeatureMMX, |
| FeatureSSE41, |
| FeatureFXSR, |
| FeatureNOPL, |
| FeatureX86_64, |
| FeatureCX16, |
| FeatureLAHFSAHF64 |
| ], |
| [ |
| TuningMacroFusion, |
| TuningSlowUAMem16, |
| TuningInsertVZEROUPPER |
| ]>; |
| |
| // Atom CPUs. |
| foreach P = ["bonnell", "atom"] in { |
| def : ProcModel<P, AtomModel, ProcessorFeatures.AtomFeatures, |
| ProcessorFeatures.AtomTuning>; |
| } |
| |
| foreach P = ["silvermont", "slm"] in { |
| def : ProcModel<P, SLMModel, ProcessorFeatures.SLMFeatures, |
| ProcessorFeatures.SLMTuning>; |
| } |
| |
| def : ProcModel<"goldmont", SLMModel, ProcessorFeatures.GLMFeatures, |
| ProcessorFeatures.GLMTuning>; |
| def : ProcModel<"goldmont-plus", SLMModel, ProcessorFeatures.GLPFeatures, |
| ProcessorFeatures.GLPTuning>; |
| def : ProcModel<"tremont", SLMModel, ProcessorFeatures.TRMFeatures, |
| ProcessorFeatures.TRMTuning>; |
| def : ProcModel<"sierraforest", AlderlakePModel, ProcessorFeatures.SRFFeatures, |
| ProcessorFeatures.TRMTuning>; |
| def : ProcModel<"grandridge", AlderlakePModel, ProcessorFeatures.GRRFeatures, |
| ProcessorFeatures.TRMTuning>; |
| |
| // "Arrandale" along with corei3 and corei5 |
| foreach P = ["nehalem", "corei7"] in { |
| def : ProcModel<P, SandyBridgeModel, ProcessorFeatures.NHMFeatures, |
| ProcessorFeatures.NHMTuning>; |
| } |
| |
| // Westmere is the corei3/i5/i7 path from nehalem to sandybridge |
| def : ProcModel<"westmere", SandyBridgeModel, ProcessorFeatures.WSMFeatures, |
| ProcessorFeatures.WSMTuning>; |
| |
| foreach P = ["sandybridge", "corei7-avx"] in { |
| def : ProcModel<P, SandyBridgeModel, ProcessorFeatures.SNBFeatures, |
| ProcessorFeatures.SNBTuning>; |
| } |
| |
| foreach P = ["ivybridge", "core-avx-i"] in { |
| def : ProcModel<P, SandyBridgeModel, ProcessorFeatures.IVBFeatures, |
| ProcessorFeatures.IVBTuning>; |
| } |
| |
| foreach P = ["haswell", "core-avx2"] in { |
| def : ProcModel<P, HaswellModel, ProcessorFeatures.HSWFeatures, |
| ProcessorFeatures.HSWTuning>; |
| } |
| |
| def : ProcModel<"broadwell", BroadwellModel, ProcessorFeatures.BDWFeatures, |
| ProcessorFeatures.BDWTuning>; |
| |
| def : ProcModel<"skylake", SkylakeClientModel, ProcessorFeatures.SKLFeatures, |
| ProcessorFeatures.SKLTuning>; |
| |
| // FIXME: define KNL scheduler model |
| def : ProcModel<"knl", HaswellModel, ProcessorFeatures.KNLFeatures, |
| ProcessorFeatures.KNLTuning>; |
| def : ProcModel<"knm", HaswellModel, ProcessorFeatures.KNMFeatures, |
| ProcessorFeatures.KNLTuning>; |
| |
| foreach P = ["skylake-avx512", "skx"] in { |
| def : ProcModel<P, SkylakeServerModel, ProcessorFeatures.SKXFeatures, |
| ProcessorFeatures.SKXTuning>; |
| } |
| |
| def : ProcModel<"cascadelake", SkylakeServerModel, |
| ProcessorFeatures.CLXFeatures, ProcessorFeatures.CLXTuning>; |
| def : ProcModel<"cooperlake", SkylakeServerModel, |
| ProcessorFeatures.CPXFeatures, ProcessorFeatures.CPXTuning>; |
| def : ProcModel<"cannonlake", SkylakeServerModel, |
| ProcessorFeatures.CNLFeatures, ProcessorFeatures.CNLTuning>; |
| def : ProcModel<"icelake-client", IceLakeModel, |
| ProcessorFeatures.ICLFeatures, ProcessorFeatures.ICLTuning>; |
| def : ProcModel<"rocketlake", IceLakeModel, |
| ProcessorFeatures.ICLFeatures, ProcessorFeatures.ICLTuning>; |
| def : ProcModel<"icelake-server", IceLakeModel, |
| ProcessorFeatures.ICXFeatures, ProcessorFeatures.ICXTuning>; |
| def : ProcModel<"tigerlake", IceLakeModel, |
| ProcessorFeatures.TGLFeatures, ProcessorFeatures.TGLTuning>; |
| def : ProcModel<"sapphirerapids", SapphireRapidsModel, |
| ProcessorFeatures.SPRFeatures, ProcessorFeatures.SPRTuning>; |
| def : ProcModel<"alderlake", AlderlakePModel, |
| ProcessorFeatures.ADLFeatures, ProcessorFeatures.ADLTuning>; |
| def : ProcModel<"raptorlake", AlderlakePModel, |
| ProcessorFeatures.ADLFeatures, ProcessorFeatures.ADLTuning>; |
| def : ProcModel<"meteorlake", AlderlakePModel, |
| ProcessorFeatures.ADLFeatures, ProcessorFeatures.ADLTuning>; |
| def : ProcModel<"graniterapids", SapphireRapidsModel, |
| ProcessorFeatures.GNRFeatures, ProcessorFeatures.SPRTuning>; |
| def : ProcModel<"emeraldrapids", SapphireRapidsModel, |
| ProcessorFeatures.SPRFeatures, ProcessorFeatures.SPRTuning>; |
| |
| // AMD CPUs. |
| |
| def : Proc<"k6", [FeatureX87, FeatureCX8, FeatureMMX], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : Proc<"k6-2", [FeatureX87, FeatureCX8, Feature3DNow], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : Proc<"k6-3", [FeatureX87, FeatureCX8, Feature3DNow], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| |
| foreach P = ["athlon", "athlon-tbird"] in { |
| def : Proc<P, [FeatureX87, FeatureCX8, FeatureCMOV, Feature3DNowA, |
| FeatureNOPL], |
| [TuningSlowSHLD, TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| } |
| |
| foreach P = ["athlon-4", "athlon-xp", "athlon-mp"] in { |
| def : Proc<P, [FeatureX87, FeatureCX8, FeatureCMOV, |
| FeatureSSE1, Feature3DNowA, FeatureFXSR, FeatureNOPL], |
| [TuningSlowSHLD, TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| } |
| |
| foreach P = ["k8", "opteron", "athlon64", "athlon-fx"] in { |
| def : Proc<P, [FeatureX87, FeatureCX8, FeatureSSE2, Feature3DNowA, |
| FeatureFXSR, FeatureNOPL, FeatureX86_64, FeatureCMOV], |
| [TuningFastScalarShiftMasks, TuningSlowSHLD, TuningSlowUAMem16, |
| TuningSBBDepBreaking, TuningInsertVZEROUPPER]>; |
| } |
| |
| foreach P = ["k8-sse3", "opteron-sse3", "athlon64-sse3"] in { |
| def : Proc<P, [FeatureX87, FeatureCX8, FeatureSSE3, Feature3DNowA, |
| FeatureFXSR, FeatureNOPL, FeatureCX16, FeatureCMOV, |
| FeatureX86_64], |
| [TuningFastScalarShiftMasks, TuningSlowSHLD, TuningSlowUAMem16, |
| TuningSBBDepBreaking, TuningInsertVZEROUPPER]>; |
| } |
| |
| foreach P = ["amdfam10", "barcelona"] in { |
| def : Proc<P, ProcessorFeatures.BarcelonaFeatures, |
| ProcessorFeatures.BarcelonaTuning>; |
| } |
| |
| // Bobcat |
| def : Proc<"btver1", ProcessorFeatures.BtVer1Features, |
| ProcessorFeatures.BtVer1Tuning>; |
| // Jaguar |
| def : ProcModel<"btver2", BtVer2Model, ProcessorFeatures.BtVer2Features, |
| ProcessorFeatures.BtVer2Tuning>; |
| |
| // Bulldozer |
| def : ProcModel<"bdver1", BdVer2Model, ProcessorFeatures.BdVer1Features, |
| ProcessorFeatures.BdVer1Tuning>; |
| // Piledriver |
| def : ProcModel<"bdver2", BdVer2Model, ProcessorFeatures.BdVer2Features, |
| ProcessorFeatures.BdVer2Tuning>; |
| // Steamroller |
| def : Proc<"bdver3", ProcessorFeatures.BdVer3Features, |
| ProcessorFeatures.BdVer3Tuning>; |
| // Excavator |
| def : Proc<"bdver4", ProcessorFeatures.BdVer4Features, |
| ProcessorFeatures.BdVer4Tuning>; |
| |
| def : ProcModel<"znver1", Znver1Model, ProcessorFeatures.ZNFeatures, |
| ProcessorFeatures.ZNTuning>; |
| def : ProcModel<"znver2", Znver2Model, ProcessorFeatures.ZN2Features, |
| ProcessorFeatures.ZN2Tuning>; |
| def : ProcModel<"znver3", Znver3Model, ProcessorFeatures.ZN3Features, |
| ProcessorFeatures.ZN3Tuning>; |
| def : ProcModel<"znver4", Znver4Model, ProcessorFeatures.ZN4Features, |
| ProcessorFeatures.ZN4Tuning>; |
| |
| def : Proc<"geode", [FeatureX87, FeatureCX8, Feature3DNowA], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| |
| def : Proc<"winchip-c6", [FeatureX87, FeatureMMX], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : Proc<"winchip2", [FeatureX87, Feature3DNow], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : Proc<"c3", [FeatureX87, Feature3DNow], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| def : Proc<"c3-2", [FeatureX87, FeatureCX8, FeatureMMX, |
| FeatureSSE1, FeatureFXSR, FeatureCMOV], |
| [TuningSlowUAMem16, TuningInsertVZEROUPPER]>; |
| |
| // 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 : ProcModel<"x86-64", SandyBridgeModel, ProcessorFeatures.X86_64V1Features, |
| ProcessorFeatures.X86_64V1Tuning>; |
| // Close to Sandybridge. |
| def : ProcModel<"x86-64-v2", SandyBridgeModel, ProcessorFeatures.X86_64V2Features, |
| ProcessorFeatures.X86_64V2Tuning>; |
| // Close to Haswell. |
| def : ProcModel<"x86-64-v3", HaswellModel, ProcessorFeatures.X86_64V3Features, |
| ProcessorFeatures.X86_64V3Tuning>; |
| // Close to the AVX-512 level implemented by Xeon Scalable Processors. |
| def : ProcModel<"x86-64-v4", SkylakeServerModel, ProcessorFeatures.X86_64V4Features, |
| ProcessorFeatures.X86_64V4Tuning>; |
| |
| //===----------------------------------------------------------------------===// |
| // 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" |
