mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 20:29:48 +00:00
a9d7398280
This is a first pass at a scheduling model for Jaguar. It's structured largely on the existing SandyBridge and SLM sched models. Using this model, in addition to turning on the PostRA scheduler, results in some perf wins on internal and 3rd party benchmarks. There's not much difference in LLVM's test-suite benchmarking subset of tests. Differential Revision: http://reviews.llvm.org/D5229 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217457 91177308-0d34-0410-b5e6-96231b3b80d8
645 lines
22 KiB
TableGen
645 lines
22 KiB
TableGen
//===-- X86Schedule.td - X86 Scheduling Definitions --------*- tablegen -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// InstrSchedModel annotations for out-of-order CPUs.
|
|
//
|
|
// These annotations are independent of the itinerary classes defined below.
|
|
|
|
// Instructions with folded loads need to read the memory operand immediately,
|
|
// but other register operands don't have to be read until the load is ready.
|
|
// These operands are marked with ReadAfterLd.
|
|
def ReadAfterLd : SchedRead;
|
|
|
|
// Instructions with both a load and a store folded are modeled as a folded
|
|
// load + WriteRMW.
|
|
def WriteRMW : SchedWrite;
|
|
|
|
// Most instructions can fold loads, so almost every SchedWrite comes in two
|
|
// variants: With and without a folded load.
|
|
// An X86FoldableSchedWrite holds a reference to the corresponding SchedWrite
|
|
// with a folded load.
|
|
class X86FoldableSchedWrite : SchedWrite {
|
|
// The SchedWrite to use when a load is folded into the instruction.
|
|
SchedWrite Folded;
|
|
}
|
|
|
|
// Multiclass that produces a linked pair of SchedWrites.
|
|
multiclass X86SchedWritePair {
|
|
// Register-Memory operation.
|
|
def Ld : SchedWrite;
|
|
// Register-Register operation.
|
|
def NAME : X86FoldableSchedWrite {
|
|
let Folded = !cast<SchedWrite>(NAME#"Ld");
|
|
}
|
|
}
|
|
|
|
// Arithmetic.
|
|
defm WriteALU : X86SchedWritePair; // Simple integer ALU op.
|
|
defm WriteIMul : X86SchedWritePair; // Integer multiplication.
|
|
def WriteIMulH : SchedWrite; // Integer multiplication, high part.
|
|
defm WriteIDiv : X86SchedWritePair; // Integer division.
|
|
def WriteLEA : SchedWrite; // LEA instructions can't fold loads.
|
|
|
|
// Integer shifts and rotates.
|
|
defm WriteShift : X86SchedWritePair;
|
|
|
|
// Loads, stores, and moves, not folded with other operations.
|
|
def WriteLoad : SchedWrite;
|
|
def WriteStore : SchedWrite;
|
|
def WriteMove : SchedWrite;
|
|
|
|
// Idioms that clear a register, like xorps %xmm0, %xmm0.
|
|
// These can often bypass execution ports completely.
|
|
def WriteZero : SchedWrite;
|
|
|
|
// Branches don't produce values, so they have no latency, but they still
|
|
// consume resources. Indirect branches can fold loads.
|
|
defm WriteJump : X86SchedWritePair;
|
|
|
|
// Floating point. This covers both scalar and vector operations.
|
|
defm WriteFAdd : X86SchedWritePair; // Floating point add/sub/compare.
|
|
defm WriteFMul : X86SchedWritePair; // Floating point multiplication.
|
|
defm WriteFDiv : X86SchedWritePair; // Floating point division.
|
|
defm WriteFSqrt : X86SchedWritePair; // Floating point square root.
|
|
defm WriteFRcp : X86SchedWritePair; // Floating point reciprocal.
|
|
defm WriteFMA : X86SchedWritePair; // Fused Multiply Add.
|
|
defm WriteFShuffle : X86SchedWritePair; // Floating point vector shuffles.
|
|
defm WriteFBlend : X86SchedWritePair; // Floating point vector blends.
|
|
defm WriteFVarBlend : X86SchedWritePair; // Fp vector variable blends.
|
|
|
|
// FMA Scheduling helper class.
|
|
class FMASC { X86FoldableSchedWrite Sched = WriteFAdd; }
|
|
|
|
// Vector integer operations.
|
|
defm WriteVecALU : X86SchedWritePair; // Vector integer ALU op, no logicals.
|
|
defm WriteVecShift : X86SchedWritePair; // Vector integer shifts.
|
|
defm WriteVecIMul : X86SchedWritePair; // Vector integer multiply.
|
|
defm WriteShuffle : X86SchedWritePair; // Vector shuffles.
|
|
defm WriteBlend : X86SchedWritePair; // Vector blends.
|
|
defm WriteVarBlend : X86SchedWritePair; // Vector variable blends.
|
|
defm WriteMPSAD : X86SchedWritePair; // Vector MPSAD.
|
|
|
|
// Vector bitwise operations.
|
|
// These are often used on both floating point and integer vectors.
|
|
defm WriteVecLogic : X86SchedWritePair; // Vector and/or/xor.
|
|
|
|
// Conversion between integer and float.
|
|
defm WriteCvtF2I : X86SchedWritePair; // Float -> Integer.
|
|
defm WriteCvtI2F : X86SchedWritePair; // Integer -> Float.
|
|
defm WriteCvtF2F : X86SchedWritePair; // Float -> Float size conversion.
|
|
|
|
// Strings instructions.
|
|
// Packed Compare Implicit Length Strings, Return Mask
|
|
defm WritePCmpIStrM : X86SchedWritePair;
|
|
// Packed Compare Explicit Length Strings, Return Mask
|
|
defm WritePCmpEStrM : X86SchedWritePair;
|
|
// Packed Compare Implicit Length Strings, Return Index
|
|
defm WritePCmpIStrI : X86SchedWritePair;
|
|
// Packed Compare Explicit Length Strings, Return Index
|
|
defm WritePCmpEStrI : X86SchedWritePair;
|
|
|
|
// AES instructions.
|
|
defm WriteAESDecEnc : X86SchedWritePair; // Decryption, encryption.
|
|
defm WriteAESIMC : X86SchedWritePair; // InvMixColumn.
|
|
defm WriteAESKeyGen : X86SchedWritePair; // Key Generation.
|
|
|
|
// Carry-less multiplication instructions.
|
|
defm WriteCLMul : X86SchedWritePair;
|
|
|
|
// Catch-all for expensive system instructions.
|
|
def WriteSystem : SchedWrite;
|
|
|
|
// AVX2.
|
|
defm WriteFShuffle256 : X86SchedWritePair; // Fp 256-bit width vector shuffles.
|
|
defm WriteShuffle256 : X86SchedWritePair; // 256-bit width vector shuffles.
|
|
defm WriteVarVecShift : X86SchedWritePair; // Variable vector shifts.
|
|
|
|
// Old microcoded instructions that nobody use.
|
|
def WriteMicrocoded : SchedWrite;
|
|
|
|
// Fence instructions.
|
|
def WriteFence : SchedWrite;
|
|
|
|
// Nop, not very useful expect it provides a model for nops!
|
|
def WriteNop : SchedWrite;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Instruction Itinerary classes used for X86
|
|
def IIC_ALU_MEM : InstrItinClass;
|
|
def IIC_ALU_NONMEM : InstrItinClass;
|
|
def IIC_LEA : InstrItinClass;
|
|
def IIC_LEA_16 : InstrItinClass;
|
|
def IIC_MUL8 : InstrItinClass;
|
|
def IIC_MUL16_MEM : InstrItinClass;
|
|
def IIC_MUL16_REG : InstrItinClass;
|
|
def IIC_MUL32_MEM : InstrItinClass;
|
|
def IIC_MUL32_REG : InstrItinClass;
|
|
def IIC_MUL64 : InstrItinClass;
|
|
// imul by al, ax, eax, tax
|
|
def IIC_IMUL8 : InstrItinClass;
|
|
def IIC_IMUL16_MEM : InstrItinClass;
|
|
def IIC_IMUL16_REG : InstrItinClass;
|
|
def IIC_IMUL32_MEM : InstrItinClass;
|
|
def IIC_IMUL32_REG : InstrItinClass;
|
|
def IIC_IMUL64 : InstrItinClass;
|
|
// imul reg by reg|mem
|
|
def IIC_IMUL16_RM : InstrItinClass;
|
|
def IIC_IMUL16_RR : InstrItinClass;
|
|
def IIC_IMUL32_RM : InstrItinClass;
|
|
def IIC_IMUL32_RR : InstrItinClass;
|
|
def IIC_IMUL64_RM : InstrItinClass;
|
|
def IIC_IMUL64_RR : InstrItinClass;
|
|
// imul reg = reg/mem * imm
|
|
def IIC_IMUL16_RMI : InstrItinClass;
|
|
def IIC_IMUL16_RRI : InstrItinClass;
|
|
def IIC_IMUL32_RMI : InstrItinClass;
|
|
def IIC_IMUL32_RRI : InstrItinClass;
|
|
def IIC_IMUL64_RMI : InstrItinClass;
|
|
def IIC_IMUL64_RRI : InstrItinClass;
|
|
// div
|
|
def IIC_DIV8_MEM : InstrItinClass;
|
|
def IIC_DIV8_REG : InstrItinClass;
|
|
def IIC_DIV16 : InstrItinClass;
|
|
def IIC_DIV32 : InstrItinClass;
|
|
def IIC_DIV64 : InstrItinClass;
|
|
// idiv
|
|
def IIC_IDIV8 : InstrItinClass;
|
|
def IIC_IDIV16 : InstrItinClass;
|
|
def IIC_IDIV32 : InstrItinClass;
|
|
def IIC_IDIV64 : InstrItinClass;
|
|
// neg/not/inc/dec
|
|
def IIC_UNARY_REG : InstrItinClass;
|
|
def IIC_UNARY_MEM : InstrItinClass;
|
|
// add/sub/and/or/xor/sbc/cmp/test
|
|
def IIC_BIN_MEM : InstrItinClass;
|
|
def IIC_BIN_NONMEM : InstrItinClass;
|
|
// adc/sbc
|
|
def IIC_BIN_CARRY_MEM : InstrItinClass;
|
|
def IIC_BIN_CARRY_NONMEM : InstrItinClass;
|
|
// shift/rotate
|
|
def IIC_SR : InstrItinClass;
|
|
// shift double
|
|
def IIC_SHD16_REG_IM : InstrItinClass;
|
|
def IIC_SHD16_REG_CL : InstrItinClass;
|
|
def IIC_SHD16_MEM_IM : InstrItinClass;
|
|
def IIC_SHD16_MEM_CL : InstrItinClass;
|
|
def IIC_SHD32_REG_IM : InstrItinClass;
|
|
def IIC_SHD32_REG_CL : InstrItinClass;
|
|
def IIC_SHD32_MEM_IM : InstrItinClass;
|
|
def IIC_SHD32_MEM_CL : InstrItinClass;
|
|
def IIC_SHD64_REG_IM : InstrItinClass;
|
|
def IIC_SHD64_REG_CL : InstrItinClass;
|
|
def IIC_SHD64_MEM_IM : InstrItinClass;
|
|
def IIC_SHD64_MEM_CL : InstrItinClass;
|
|
// cmov
|
|
def IIC_CMOV16_RM : InstrItinClass;
|
|
def IIC_CMOV16_RR : InstrItinClass;
|
|
def IIC_CMOV32_RM : InstrItinClass;
|
|
def IIC_CMOV32_RR : InstrItinClass;
|
|
def IIC_CMOV64_RM : InstrItinClass;
|
|
def IIC_CMOV64_RR : InstrItinClass;
|
|
// set
|
|
def IIC_SET_R : InstrItinClass;
|
|
def IIC_SET_M : InstrItinClass;
|
|
// jmp/jcc/jcxz
|
|
def IIC_Jcc : InstrItinClass;
|
|
def IIC_JCXZ : InstrItinClass;
|
|
def IIC_JMP_REL : InstrItinClass;
|
|
def IIC_JMP_REG : InstrItinClass;
|
|
def IIC_JMP_MEM : InstrItinClass;
|
|
def IIC_JMP_FAR_MEM : InstrItinClass;
|
|
def IIC_JMP_FAR_PTR : InstrItinClass;
|
|
// loop
|
|
def IIC_LOOP : InstrItinClass;
|
|
def IIC_LOOPE : InstrItinClass;
|
|
def IIC_LOOPNE : InstrItinClass;
|
|
// call
|
|
def IIC_CALL_RI : InstrItinClass;
|
|
def IIC_CALL_MEM : InstrItinClass;
|
|
def IIC_CALL_FAR_MEM : InstrItinClass;
|
|
def IIC_CALL_FAR_PTR : InstrItinClass;
|
|
// ret
|
|
def IIC_RET : InstrItinClass;
|
|
def IIC_RET_IMM : InstrItinClass;
|
|
//sign extension movs
|
|
def IIC_MOVSX : InstrItinClass;
|
|
def IIC_MOVSX_R16_R8 : InstrItinClass;
|
|
def IIC_MOVSX_R16_M8 : InstrItinClass;
|
|
def IIC_MOVSX_R16_R16 : InstrItinClass;
|
|
def IIC_MOVSX_R32_R32 : InstrItinClass;
|
|
//zero extension movs
|
|
def IIC_MOVZX : InstrItinClass;
|
|
def IIC_MOVZX_R16_R8 : InstrItinClass;
|
|
def IIC_MOVZX_R16_M8 : InstrItinClass;
|
|
|
|
def IIC_REP_MOVS : InstrItinClass;
|
|
def IIC_REP_STOS : InstrItinClass;
|
|
|
|
// SSE scalar/parallel binary operations
|
|
def IIC_SSE_ALU_F32S_RR : InstrItinClass;
|
|
def IIC_SSE_ALU_F32S_RM : InstrItinClass;
|
|
def IIC_SSE_ALU_F64S_RR : InstrItinClass;
|
|
def IIC_SSE_ALU_F64S_RM : InstrItinClass;
|
|
def IIC_SSE_MUL_F32S_RR : InstrItinClass;
|
|
def IIC_SSE_MUL_F32S_RM : InstrItinClass;
|
|
def IIC_SSE_MUL_F64S_RR : InstrItinClass;
|
|
def IIC_SSE_MUL_F64S_RM : InstrItinClass;
|
|
def IIC_SSE_DIV_F32S_RR : InstrItinClass;
|
|
def IIC_SSE_DIV_F32S_RM : InstrItinClass;
|
|
def IIC_SSE_DIV_F64S_RR : InstrItinClass;
|
|
def IIC_SSE_DIV_F64S_RM : InstrItinClass;
|
|
def IIC_SSE_ALU_F32P_RR : InstrItinClass;
|
|
def IIC_SSE_ALU_F32P_RM : InstrItinClass;
|
|
def IIC_SSE_ALU_F64P_RR : InstrItinClass;
|
|
def IIC_SSE_ALU_F64P_RM : InstrItinClass;
|
|
def IIC_SSE_MUL_F32P_RR : InstrItinClass;
|
|
def IIC_SSE_MUL_F32P_RM : InstrItinClass;
|
|
def IIC_SSE_MUL_F64P_RR : InstrItinClass;
|
|
def IIC_SSE_MUL_F64P_RM : InstrItinClass;
|
|
def IIC_SSE_DIV_F32P_RR : InstrItinClass;
|
|
def IIC_SSE_DIV_F32P_RM : InstrItinClass;
|
|
def IIC_SSE_DIV_F64P_RR : InstrItinClass;
|
|
def IIC_SSE_DIV_F64P_RM : InstrItinClass;
|
|
|
|
def IIC_SSE_COMIS_RR : InstrItinClass;
|
|
def IIC_SSE_COMIS_RM : InstrItinClass;
|
|
|
|
def IIC_SSE_HADDSUB_RR : InstrItinClass;
|
|
def IIC_SSE_HADDSUB_RM : InstrItinClass;
|
|
|
|
def IIC_SSE_BIT_P_RR : InstrItinClass;
|
|
def IIC_SSE_BIT_P_RM : InstrItinClass;
|
|
|
|
def IIC_SSE_INTALU_P_RR : InstrItinClass;
|
|
def IIC_SSE_INTALU_P_RM : InstrItinClass;
|
|
def IIC_SSE_INTALUQ_P_RR : InstrItinClass;
|
|
def IIC_SSE_INTALUQ_P_RM : InstrItinClass;
|
|
|
|
def IIC_SSE_INTMUL_P_RR : InstrItinClass;
|
|
def IIC_SSE_INTMUL_P_RM : InstrItinClass;
|
|
|
|
def IIC_SSE_INTSH_P_RR : InstrItinClass;
|
|
def IIC_SSE_INTSH_P_RM : InstrItinClass;
|
|
def IIC_SSE_INTSH_P_RI : InstrItinClass;
|
|
|
|
def IIC_SSE_INTSHDQ_P_RI : InstrItinClass;
|
|
|
|
def IIC_SSE_SHUFP : InstrItinClass;
|
|
def IIC_SSE_PSHUF_RI : InstrItinClass;
|
|
def IIC_SSE_PSHUF_MI : InstrItinClass;
|
|
|
|
def IIC_SSE_UNPCK : InstrItinClass;
|
|
|
|
def IIC_SSE_MOVMSK : InstrItinClass;
|
|
def IIC_SSE_MASKMOV : InstrItinClass;
|
|
|
|
def IIC_SSE_PEXTRW : InstrItinClass;
|
|
def IIC_SSE_PINSRW : InstrItinClass;
|
|
|
|
def IIC_SSE_PABS_RR : InstrItinClass;
|
|
def IIC_SSE_PABS_RM : InstrItinClass;
|
|
|
|
def IIC_SSE_SQRTPS_RR : InstrItinClass;
|
|
def IIC_SSE_SQRTPS_RM : InstrItinClass;
|
|
def IIC_SSE_SQRTSS_RR : InstrItinClass;
|
|
def IIC_SSE_SQRTSS_RM : InstrItinClass;
|
|
def IIC_SSE_SQRTPD_RR : InstrItinClass;
|
|
def IIC_SSE_SQRTPD_RM : InstrItinClass;
|
|
def IIC_SSE_SQRTSD_RR : InstrItinClass;
|
|
def IIC_SSE_SQRTSD_RM : InstrItinClass;
|
|
|
|
def IIC_SSE_RCPP_RR : InstrItinClass;
|
|
def IIC_SSE_RCPP_RM : InstrItinClass;
|
|
def IIC_SSE_RCPS_RR : InstrItinClass;
|
|
def IIC_SSE_RCPS_RM : InstrItinClass;
|
|
|
|
def IIC_SSE_MOV_S_RR : InstrItinClass;
|
|
def IIC_SSE_MOV_S_RM : InstrItinClass;
|
|
def IIC_SSE_MOV_S_MR : InstrItinClass;
|
|
|
|
def IIC_SSE_MOVA_P_RR : InstrItinClass;
|
|
def IIC_SSE_MOVA_P_RM : InstrItinClass;
|
|
def IIC_SSE_MOVA_P_MR : InstrItinClass;
|
|
|
|
def IIC_SSE_MOVU_P_RR : InstrItinClass;
|
|
def IIC_SSE_MOVU_P_RM : InstrItinClass;
|
|
def IIC_SSE_MOVU_P_MR : InstrItinClass;
|
|
|
|
def IIC_SSE_MOVDQ : InstrItinClass;
|
|
def IIC_SSE_MOVD_ToGP : InstrItinClass;
|
|
def IIC_SSE_MOVQ_RR : InstrItinClass;
|
|
|
|
def IIC_SSE_MOV_LH : InstrItinClass;
|
|
|
|
def IIC_SSE_LDDQU : InstrItinClass;
|
|
|
|
def IIC_SSE_MOVNT : InstrItinClass;
|
|
|
|
def IIC_SSE_PHADDSUBD_RR : InstrItinClass;
|
|
def IIC_SSE_PHADDSUBD_RM : InstrItinClass;
|
|
def IIC_SSE_PHADDSUBSW_RR : InstrItinClass;
|
|
def IIC_SSE_PHADDSUBSW_RM : InstrItinClass;
|
|
def IIC_SSE_PHADDSUBW_RR : InstrItinClass;
|
|
def IIC_SSE_PHADDSUBW_RM : InstrItinClass;
|
|
def IIC_SSE_PSHUFB_RR : InstrItinClass;
|
|
def IIC_SSE_PSHUFB_RM : InstrItinClass;
|
|
def IIC_SSE_PSIGN_RR : InstrItinClass;
|
|
def IIC_SSE_PSIGN_RM : InstrItinClass;
|
|
|
|
def IIC_SSE_PMADD : InstrItinClass;
|
|
def IIC_SSE_PMULHRSW : InstrItinClass;
|
|
def IIC_SSE_PALIGNRR : InstrItinClass;
|
|
def IIC_SSE_PALIGNRM : InstrItinClass;
|
|
def IIC_SSE_MWAIT : InstrItinClass;
|
|
def IIC_SSE_MONITOR : InstrItinClass;
|
|
|
|
def IIC_SSE_PREFETCH : InstrItinClass;
|
|
def IIC_SSE_PAUSE : InstrItinClass;
|
|
def IIC_SSE_LFENCE : InstrItinClass;
|
|
def IIC_SSE_MFENCE : InstrItinClass;
|
|
def IIC_SSE_SFENCE : InstrItinClass;
|
|
def IIC_SSE_LDMXCSR : InstrItinClass;
|
|
def IIC_SSE_STMXCSR : InstrItinClass;
|
|
|
|
def IIC_SSE_CVT_PD_RR : InstrItinClass;
|
|
def IIC_SSE_CVT_PD_RM : InstrItinClass;
|
|
def IIC_SSE_CVT_PS_RR : InstrItinClass;
|
|
def IIC_SSE_CVT_PS_RM : InstrItinClass;
|
|
def IIC_SSE_CVT_PI2PS_RR : InstrItinClass;
|
|
def IIC_SSE_CVT_PI2PS_RM : InstrItinClass;
|
|
def IIC_SSE_CVT_Scalar_RR : InstrItinClass;
|
|
def IIC_SSE_CVT_Scalar_RM : InstrItinClass;
|
|
def IIC_SSE_CVT_SS2SI32_RM : InstrItinClass;
|
|
def IIC_SSE_CVT_SS2SI32_RR : InstrItinClass;
|
|
def IIC_SSE_CVT_SS2SI64_RM : InstrItinClass;
|
|
def IIC_SSE_CVT_SS2SI64_RR : InstrItinClass;
|
|
def IIC_SSE_CVT_SD2SI_RM : InstrItinClass;
|
|
def IIC_SSE_CVT_SD2SI_RR : InstrItinClass;
|
|
|
|
// MMX
|
|
def IIC_MMX_MOV_MM_RM : InstrItinClass;
|
|
def IIC_MMX_MOV_REG_MM : InstrItinClass;
|
|
def IIC_MMX_MOVQ_RM : InstrItinClass;
|
|
def IIC_MMX_MOVQ_RR : InstrItinClass;
|
|
|
|
def IIC_MMX_ALU_RM : InstrItinClass;
|
|
def IIC_MMX_ALU_RR : InstrItinClass;
|
|
def IIC_MMX_ALUQ_RM : InstrItinClass;
|
|
def IIC_MMX_ALUQ_RR : InstrItinClass;
|
|
def IIC_MMX_PHADDSUBW_RM : InstrItinClass;
|
|
def IIC_MMX_PHADDSUBW_RR : InstrItinClass;
|
|
def IIC_MMX_PHADDSUBD_RM : InstrItinClass;
|
|
def IIC_MMX_PHADDSUBD_RR : InstrItinClass;
|
|
def IIC_MMX_PMUL : InstrItinClass;
|
|
def IIC_MMX_MISC_FUNC_MEM : InstrItinClass;
|
|
def IIC_MMX_MISC_FUNC_REG : InstrItinClass;
|
|
def IIC_MMX_PSADBW : InstrItinClass;
|
|
def IIC_MMX_SHIFT_RI : InstrItinClass;
|
|
def IIC_MMX_SHIFT_RM : InstrItinClass;
|
|
def IIC_MMX_SHIFT_RR : InstrItinClass;
|
|
def IIC_MMX_UNPCK_H_RM : InstrItinClass;
|
|
def IIC_MMX_UNPCK_H_RR : InstrItinClass;
|
|
def IIC_MMX_UNPCK_L : InstrItinClass;
|
|
def IIC_MMX_PCK_RM : InstrItinClass;
|
|
def IIC_MMX_PCK_RR : InstrItinClass;
|
|
def IIC_MMX_PSHUF : InstrItinClass;
|
|
def IIC_MMX_PEXTR : InstrItinClass;
|
|
def IIC_MMX_PINSRW : InstrItinClass;
|
|
def IIC_MMX_MASKMOV : InstrItinClass;
|
|
|
|
def IIC_MMX_CVT_PD_RR : InstrItinClass;
|
|
def IIC_MMX_CVT_PD_RM : InstrItinClass;
|
|
def IIC_MMX_CVT_PS_RR : InstrItinClass;
|
|
def IIC_MMX_CVT_PS_RM : InstrItinClass;
|
|
|
|
def IIC_CMPX_LOCK : InstrItinClass;
|
|
def IIC_CMPX_LOCK_8 : InstrItinClass;
|
|
def IIC_CMPX_LOCK_8B : InstrItinClass;
|
|
def IIC_CMPX_LOCK_16B : InstrItinClass;
|
|
|
|
def IIC_XADD_LOCK_MEM : InstrItinClass;
|
|
def IIC_XADD_LOCK_MEM8 : InstrItinClass;
|
|
|
|
def IIC_FILD : InstrItinClass;
|
|
def IIC_FLD : InstrItinClass;
|
|
def IIC_FLD80 : InstrItinClass;
|
|
def IIC_FST : InstrItinClass;
|
|
def IIC_FST80 : InstrItinClass;
|
|
def IIC_FIST : InstrItinClass;
|
|
def IIC_FLDZ : InstrItinClass;
|
|
def IIC_FUCOM : InstrItinClass;
|
|
def IIC_FUCOMI : InstrItinClass;
|
|
def IIC_FCOMI : InstrItinClass;
|
|
def IIC_FNSTSW : InstrItinClass;
|
|
def IIC_FNSTCW : InstrItinClass;
|
|
def IIC_FLDCW : InstrItinClass;
|
|
def IIC_FNINIT : InstrItinClass;
|
|
def IIC_FFREE : InstrItinClass;
|
|
def IIC_FNCLEX : InstrItinClass;
|
|
def IIC_WAIT : InstrItinClass;
|
|
def IIC_FXAM : InstrItinClass;
|
|
def IIC_FNOP : InstrItinClass;
|
|
def IIC_FLDL : InstrItinClass;
|
|
def IIC_F2XM1 : InstrItinClass;
|
|
def IIC_FYL2X : InstrItinClass;
|
|
def IIC_FPTAN : InstrItinClass;
|
|
def IIC_FPATAN : InstrItinClass;
|
|
def IIC_FXTRACT : InstrItinClass;
|
|
def IIC_FPREM1 : InstrItinClass;
|
|
def IIC_FPSTP : InstrItinClass;
|
|
def IIC_FPREM : InstrItinClass;
|
|
def IIC_FYL2XP1 : InstrItinClass;
|
|
def IIC_FSINCOS : InstrItinClass;
|
|
def IIC_FRNDINT : InstrItinClass;
|
|
def IIC_FSCALE : InstrItinClass;
|
|
def IIC_FCOMPP : InstrItinClass;
|
|
def IIC_FXSAVE : InstrItinClass;
|
|
def IIC_FXRSTOR : InstrItinClass;
|
|
|
|
def IIC_FXCH : InstrItinClass;
|
|
|
|
// System instructions
|
|
def IIC_CPUID : InstrItinClass;
|
|
def IIC_INT : InstrItinClass;
|
|
def IIC_INT3 : InstrItinClass;
|
|
def IIC_INVD : InstrItinClass;
|
|
def IIC_INVLPG : InstrItinClass;
|
|
def IIC_IRET : InstrItinClass;
|
|
def IIC_HLT : InstrItinClass;
|
|
def IIC_LXS : InstrItinClass;
|
|
def IIC_LTR : InstrItinClass;
|
|
def IIC_RDTSC : InstrItinClass;
|
|
def IIC_RSM : InstrItinClass;
|
|
def IIC_SIDT : InstrItinClass;
|
|
def IIC_SGDT : InstrItinClass;
|
|
def IIC_SLDT : InstrItinClass;
|
|
def IIC_STR : InstrItinClass;
|
|
def IIC_SWAPGS : InstrItinClass;
|
|
def IIC_SYSCALL : InstrItinClass;
|
|
def IIC_SYS_ENTER_EXIT : InstrItinClass;
|
|
def IIC_IN_RR : InstrItinClass;
|
|
def IIC_IN_RI : InstrItinClass;
|
|
def IIC_OUT_RR : InstrItinClass;
|
|
def IIC_OUT_IR : InstrItinClass;
|
|
def IIC_INS : InstrItinClass;
|
|
def IIC_MOV_REG_DR : InstrItinClass;
|
|
def IIC_MOV_DR_REG : InstrItinClass;
|
|
def IIC_MOV_REG_CR : InstrItinClass;
|
|
def IIC_MOV_CR_REG : InstrItinClass;
|
|
def IIC_MOV_REG_SR : InstrItinClass;
|
|
def IIC_MOV_MEM_SR : InstrItinClass;
|
|
def IIC_MOV_SR_REG : InstrItinClass;
|
|
def IIC_MOV_SR_MEM : InstrItinClass;
|
|
def IIC_LAR_RM : InstrItinClass;
|
|
def IIC_LAR_RR : InstrItinClass;
|
|
def IIC_LSL_RM : InstrItinClass;
|
|
def IIC_LSL_RR : InstrItinClass;
|
|
def IIC_LGDT : InstrItinClass;
|
|
def IIC_LIDT : InstrItinClass;
|
|
def IIC_LLDT_REG : InstrItinClass;
|
|
def IIC_LLDT_MEM : InstrItinClass;
|
|
def IIC_PUSH_CS : InstrItinClass;
|
|
def IIC_PUSH_SR : InstrItinClass;
|
|
def IIC_POP_SR : InstrItinClass;
|
|
def IIC_POP_SR_SS : InstrItinClass;
|
|
def IIC_VERR : InstrItinClass;
|
|
def IIC_VERW_REG : InstrItinClass;
|
|
def IIC_VERW_MEM : InstrItinClass;
|
|
def IIC_WRMSR : InstrItinClass;
|
|
def IIC_RDMSR : InstrItinClass;
|
|
def IIC_RDPMC : InstrItinClass;
|
|
def IIC_SMSW : InstrItinClass;
|
|
def IIC_LMSW_REG : InstrItinClass;
|
|
def IIC_LMSW_MEM : InstrItinClass;
|
|
def IIC_ENTER : InstrItinClass;
|
|
def IIC_LEAVE : InstrItinClass;
|
|
def IIC_POP_MEM : InstrItinClass;
|
|
def IIC_POP_REG16 : InstrItinClass;
|
|
def IIC_POP_REG : InstrItinClass;
|
|
def IIC_POP_F : InstrItinClass;
|
|
def IIC_POP_FD : InstrItinClass;
|
|
def IIC_POP_A : InstrItinClass;
|
|
def IIC_PUSH_IMM : InstrItinClass;
|
|
def IIC_PUSH_MEM : InstrItinClass;
|
|
def IIC_PUSH_REG : InstrItinClass;
|
|
def IIC_PUSH_F : InstrItinClass;
|
|
def IIC_PUSH_A : InstrItinClass;
|
|
def IIC_BSWAP : InstrItinClass;
|
|
def IIC_BIT_SCAN_MEM : InstrItinClass;
|
|
def IIC_BIT_SCAN_REG : InstrItinClass;
|
|
def IIC_MOVS : InstrItinClass;
|
|
def IIC_STOS : InstrItinClass;
|
|
def IIC_SCAS : InstrItinClass;
|
|
def IIC_CMPS : InstrItinClass;
|
|
def IIC_MOV : InstrItinClass;
|
|
def IIC_MOV_MEM : InstrItinClass;
|
|
def IIC_AHF : InstrItinClass;
|
|
def IIC_BT_MI : InstrItinClass;
|
|
def IIC_BT_MR : InstrItinClass;
|
|
def IIC_BT_RI : InstrItinClass;
|
|
def IIC_BT_RR : InstrItinClass;
|
|
def IIC_BTX_MI : InstrItinClass;
|
|
def IIC_BTX_MR : InstrItinClass;
|
|
def IIC_BTX_RI : InstrItinClass;
|
|
def IIC_BTX_RR : InstrItinClass;
|
|
def IIC_XCHG_REG : InstrItinClass;
|
|
def IIC_XCHG_MEM : InstrItinClass;
|
|
def IIC_XADD_REG : InstrItinClass;
|
|
def IIC_XADD_MEM : InstrItinClass;
|
|
def IIC_CMPXCHG_MEM : InstrItinClass;
|
|
def IIC_CMPXCHG_REG : InstrItinClass;
|
|
def IIC_CMPXCHG_MEM8 : InstrItinClass;
|
|
def IIC_CMPXCHG_REG8 : InstrItinClass;
|
|
def IIC_CMPXCHG_8B : InstrItinClass;
|
|
def IIC_CMPXCHG_16B : InstrItinClass;
|
|
def IIC_LODS : InstrItinClass;
|
|
def IIC_OUTS : InstrItinClass;
|
|
def IIC_CLC : InstrItinClass;
|
|
def IIC_CLD : InstrItinClass;
|
|
def IIC_CLI : InstrItinClass;
|
|
def IIC_CMC : InstrItinClass;
|
|
def IIC_CLTS : InstrItinClass;
|
|
def IIC_STC : InstrItinClass;
|
|
def IIC_STI : InstrItinClass;
|
|
def IIC_STD : InstrItinClass;
|
|
def IIC_XLAT : InstrItinClass;
|
|
def IIC_AAA : InstrItinClass;
|
|
def IIC_AAD : InstrItinClass;
|
|
def IIC_AAM : InstrItinClass;
|
|
def IIC_AAS : InstrItinClass;
|
|
def IIC_DAA : InstrItinClass;
|
|
def IIC_DAS : InstrItinClass;
|
|
def IIC_BOUND : InstrItinClass;
|
|
def IIC_ARPL_REG : InstrItinClass;
|
|
def IIC_ARPL_MEM : InstrItinClass;
|
|
def IIC_MOVBE : InstrItinClass;
|
|
def IIC_AES : InstrItinClass;
|
|
def IIC_BLEND_MEM : InstrItinClass;
|
|
def IIC_BLEND_NOMEM : InstrItinClass;
|
|
def IIC_CBW : InstrItinClass;
|
|
def IIC_CRC32_REG : InstrItinClass;
|
|
def IIC_CRC32_MEM : InstrItinClass;
|
|
def IIC_SSE_DPPD_RR : InstrItinClass;
|
|
def IIC_SSE_DPPD_RM : InstrItinClass;
|
|
def IIC_SSE_DPPS_RR : InstrItinClass;
|
|
def IIC_SSE_DPPS_RM : InstrItinClass;
|
|
def IIC_MMX_EMMS : InstrItinClass;
|
|
def IIC_SSE_EXTRACTPS_RR : InstrItinClass;
|
|
def IIC_SSE_EXTRACTPS_RM : InstrItinClass;
|
|
def IIC_SSE_INSERTPS_RR : InstrItinClass;
|
|
def IIC_SSE_INSERTPS_RM : InstrItinClass;
|
|
def IIC_SSE_MPSADBW_RR : InstrItinClass;
|
|
def IIC_SSE_MPSADBW_RM : InstrItinClass;
|
|
def IIC_SSE_PMULLD_RR : InstrItinClass;
|
|
def IIC_SSE_PMULLD_RM : InstrItinClass;
|
|
def IIC_SSE_ROUNDPS_REG : InstrItinClass;
|
|
def IIC_SSE_ROUNDPS_MEM : InstrItinClass;
|
|
def IIC_SSE_ROUNDPD_REG : InstrItinClass;
|
|
def IIC_SSE_ROUNDPD_MEM : InstrItinClass;
|
|
def IIC_SSE_POPCNT_RR : InstrItinClass;
|
|
def IIC_SSE_POPCNT_RM : InstrItinClass;
|
|
def IIC_SSE_PCLMULQDQ_RR : InstrItinClass;
|
|
def IIC_SSE_PCLMULQDQ_RM : InstrItinClass;
|
|
|
|
def IIC_NOP : InstrItinClass;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Processor instruction itineraries.
|
|
|
|
// IssueWidth is analogous to the number of decode units. Core and its
|
|
// descendents, including Nehalem and SandyBridge have 4 decoders.
|
|
// Resources beyond the decoder operate on micro-ops and are bufferred
|
|
// so adjacent micro-ops don't directly compete.
|
|
//
|
|
// MicroOpBufferSize > 1 indicates that RAW dependencies can be
|
|
// decoded in the same cycle. The value 32 is a reasonably arbitrary
|
|
// number of in-flight instructions.
|
|
//
|
|
// HighLatency=10 is optimistic. X86InstrInfo::isHighLatencyDef
|
|
// indicates high latency opcodes. Alternatively, InstrItinData
|
|
// entries may be included here to define specific operand
|
|
// latencies. Since these latencies are not used for pipeline hazards,
|
|
// they do not need to be exact.
|
|
//
|
|
// The GenericModel contains no instruction itineraries.
|
|
def GenericModel : SchedMachineModel {
|
|
let IssueWidth = 4;
|
|
let MicroOpBufferSize = 32;
|
|
let LoadLatency = 4;
|
|
let HighLatency = 10;
|
|
let PostRAScheduler = 0;
|
|
}
|
|
|
|
include "X86ScheduleAtom.td"
|
|
include "X86SchedSandyBridge.td"
|
|
include "X86SchedHaswell.td"
|
|
include "X86ScheduleSLM.td"
|
|
include "X86ScheduleBtVer2.td"
|
|
|