[AArch64] Add pipeline model for HiSilicon's TSV110

This patch adds the scheduling and cost model for TSV110.

Reviewed by: SjoerdMeijer, bryanpkc

Differential Revision: https://reviews.llvm.org/D89972

llvm/lib/Target/AArch64/AArch64.td

@@ -535,6 +535,7 @@ include "AArch64SchedExynosM5.td"
 include "AArch64SchedThunderX.td"
 include "AArch64SchedThunderX2T99.td"
 include "AArch64SchedThunderX3T110.td"
+include "AArch64SchedTSV110.td"
 
 def ProcA35     : SubtargetFeature<"a35", "ARMProcFamily", "CortexA35",
                                    "Cortex-A35 ARM processors", [
@@ -1058,8 +1059,7 @@ def : ProcessorModel<"thunderxt83", ThunderXT8XModel,  [ProcThunderXT83]>;
 def : ProcessorModel<"thunderx2t99", ThunderX2T99Model, [ProcThunderX2T99]>;
 // Marvell ThunderX3T110 Processors.
 def : ProcessorModel<"thunderx3t110", ThunderX3T110Model, [ProcThunderX3T110]>;
-// FIXME: HiSilicon TSV110 is currently modeled as a Cortex-A57.
+def : ProcessorModel<"tsv110", TSV110Model, [ProcTSV110]>;
-def : ProcessorModel<"tsv110", CortexA57Model, [ProcTSV110]>;
 
 // Support cyclone as an alias for apple-a7 so we can still LTO old bitcode.
 def : ProcessorModel<"cyclone", CycloneModel, [ProcAppleA7]>;

llvm/lib/Target/AArch64/AArch64SchedTSV110.td

@@ -0,0 +1,745 @@
+//==- AArch64SchedTSV110.td - Huawei TSV110 Scheduling Definitions -*- 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 file defines the machine model for Huawei TSV110 to support
+// instruction scheduling and other instruction cost heuristics.
+//
+//===----------------------------------------------------------------------===//
+
+// ===---------------------------------------------------------------------===//
+// The following definitions describe the simpler per-operand machine model.
+// This works with MachineScheduler. See llvm/MC/MCSchedule.h for details.
+
+// Huawei TSV110 scheduling machine model.
+def TSV110Model : SchedMachineModel {
+  let IssueWidth            =   4; // 4 micro-ops dispatched  per cycle. 
+  let MicroOpBufferSize     = 128; // 128 micro-op re-order buffer
+  let LoopMicroOpBufferSize =  16; 
+  let LoadLatency           =   4; // Optimistic load latency.
+  let MispredictPenalty     =  14; // Fetch + Decode/Rename/Dispatch + Branch
+  let CompleteModel         =   1;
+
+  list<Predicate> UnsupportedFeatures = !listconcat(SVEUnsupported.F,
+                                                    PAUnsupported.F);
+}
+
+// Define each kind of processor resource and number available on the TSV110,
+// which has 8 pipelines, each with its own queue where micro-ops wait for
+// their operands and issue out-of-order to one of eight execution pipelines.
+let SchedModel = TSV110Model in {
+  def TSV110UnitALU  : ProcResource<1>; // Int ALU
+  def TSV110UnitAB   : ProcResource<2>; // Int ALU/BRU
+  def TSV110UnitMDU  : ProcResource<1>; // Multi-Cycle
+  def TSV110UnitFSU1 : ProcResource<1>; // FP/ASIMD
+  def TSV110UnitFSU2 : ProcResource<1>; // FP/ASIMD
+  def TSV110UnitLdSt : ProcResource<2>; // Load/Store
+
+  def TSV110UnitF     : ProcResGroup<[TSV110UnitFSU1, TSV110UnitFSU2]>;
+  def TSV110UnitALUAB : ProcResGroup<[TSV110UnitALU, TSV110UnitAB]>;
+  def TSV110UnitFLdSt : ProcResGroup<[TSV110UnitFSU1, TSV110UnitFSU2, TSV110UnitLdSt]>;
+}
+
+let SchedModel = TSV110Model in {
+
+//===----------------------------------------------------------------------===//
+// Map the target-defined scheduler read/write resources and latency for 
+// TSV110
+
+// Integer ALU
+def : WriteRes<WriteImm,   [TSV110UnitALUAB]> { let Latency = 1; }
+def : WriteRes<WriteI,     [TSV110UnitALUAB]> { let Latency = 1; }
+def : WriteRes<WriteISReg, [TSV110UnitMDU]>   { let Latency = 2; } 
+def : WriteRes<WriteIEReg, [TSV110UnitMDU]>   { let Latency = 2; } 
+def : WriteRes<WriteExtr,  [TSV110UnitALUAB]> { let Latency = 1; }
+def : WriteRes<WriteIS,    [TSV110UnitALUAB]> { let Latency = 1; }
+
+// Integer Mul/MAC/Div
+def : WriteRes<WriteID32,  [TSV110UnitMDU]> { let Latency = 12;
+                                              let ResourceCycles = [12]; } 
+def : WriteRes<WriteID64,  [TSV110UnitMDU]> { let Latency = 20;
+                                              let ResourceCycles = [20]; }
+def : WriteRes<WriteIM32,  [TSV110UnitMDU]> { let Latency = 3; }
+def : WriteRes<WriteIM64,  [TSV110UnitMDU]> { let Latency = 4; }
+
+// Load
+def : WriteRes<WriteLD,    [TSV110UnitLdSt]> { let Latency = 4; }
+def : WriteRes<WriteLDIdx, [TSV110UnitLdSt]> { let Latency = 4; }
+def : WriteRes<WriteLDHi,  []> { let Latency = 4; }
+
+// Pre/Post Indexing
+def : WriteRes<WriteAdr,   [TSV110UnitALUAB]> { let Latency = 1; } 
+
+// Store
+def : WriteRes<WriteST,    [TSV110UnitLdSt]> { let Latency = 1; }
+def : WriteRes<WriteSTP,   [TSV110UnitLdSt]> { let Latency = 1; }
+def : WriteRes<WriteSTIdx, [TSV110UnitLdSt]> { let Latency = 1; }
+
+// FP
+def : WriteRes<WriteF,     [TSV110UnitF]> { let Latency = 2; }
+def : WriteRes<WriteFCmp,  [TSV110UnitF]> { let Latency = 3; }
+def : WriteRes<WriteFCvt,  [TSV110UnitF]> { let Latency = 3; } 
+def : WriteRes<WriteFCopy, [TSV110UnitF]> { let Latency = 2; }
+def : WriteRes<WriteFImm,  [TSV110UnitF]> { let Latency = 2; } 
+def : WriteRes<WriteFMul,  [TSV110UnitF]> { let Latency = 5; }
+
+// FP Div, Sqrt
+def : WriteRes<WriteFDiv,  [TSV110UnitFSU1]> { let Latency = 18; } 
+
+def : WriteRes<WriteV,     [TSV110UnitF]>     { let Latency = 4; }
+def : WriteRes<WriteVLD,   [TSV110UnitFLdSt]> { let Latency = 5; }
+def : WriteRes<WriteVST,   [TSV110UnitF]>     { let Latency = 1; }
+
+// Branch
+def : WriteRes<WriteBr,    [TSV110UnitAB]> { let Latency = 1; }
+def : WriteRes<WriteBrReg, [TSV110UnitAB]> { let Latency = 1; }
+def : WriteRes<WriteSys,     []> { let Latency = 1; }
+def : WriteRes<WriteBarrier, []> { let Latency = 1; }
+def : WriteRes<WriteHint,    []> { let Latency = 1; }
+
+def : WriteRes<WriteAtomic, []> { let Unsupported = 1; } 
+
+// Forwarding logic is modeled only for multiply and accumulate.
+def : ReadAdvance<ReadI,       0>;
+def : ReadAdvance<ReadISReg,   0>;
+def : ReadAdvance<ReadIEReg,   0>;
+def : ReadAdvance<ReadIM,      0>;
+def : ReadAdvance<ReadIMA,     2, [WriteIM32, WriteIM64]>;
+def : ReadAdvance<ReadID,      0>;
+def : ReadAdvance<ReadExtrHi,  0>;
+def : ReadAdvance<ReadAdrBase, 0>;
+def : ReadAdvance<ReadVLD,     0>;
+
+def : InstRW<[WriteI], (instrs COPY)>;
+
+// Detailed Refinements
+//===----------------------------------------------------------------------===//
+
+// Contains all of the TSV110 specific SchedWriteRes types. The approach
+// below is to define a generic SchedWriteRes for every combination of
+// latency and microOps. The naming conventions is to use a prefix, one field
+// for latency, and one or more microOp count/type designators.
+//   Prefix: TSV110Wr
+//       Latency: #cyc
+//   MicroOp Count/Types: #(ALU|AB|MDU|FSU1|FSU2|LdSt|ALUAB|F|FLdSt)
+//
+// e.g. TSV110Wr_6cyc_1ALU_6MDU_4LdSt means the total latency is 6 and there are
+//      1 micro-ops to be issued down one ALU pipe, six MDU pipes and four LdSt pipes.
+//
+
+//===----------------------------------------------------------------------===//
+// Define Generic 1 micro-op types
+
+def TSV110Wr_1cyc_1AB    : SchedWriteRes<[TSV110UnitAB]>    { let Latency = 1; }
+def TSV110Wr_1cyc_1ALU   : SchedWriteRes<[TSV110UnitALU]>   { let Latency = 1; }
+def TSV110Wr_1cyc_1ALUAB : SchedWriteRes<[TSV110UnitALUAB]> { let Latency = 1; }
+def TSV110Wr_1cyc_1LdSt  : SchedWriteRes<[TSV110UnitLdSt]>  { let Latency = 1; }
+
+def TSV110Wr_2cyc_1AB    : SchedWriteRes<[TSV110UnitAB]>    { let Latency = 2; }
+def TSV110Wr_2cyc_1ALU   : SchedWriteRes<[TSV110UnitALU]>   { let Latency = 2; }
+def TSV110Wr_2cyc_1LdSt  : SchedWriteRes<[TSV110UnitLdSt]>  { let Latency = 2; }
+def TSV110Wr_2cyc_1MDU   : SchedWriteRes<[TSV110UnitMDU]>   { let Latency = 2; }
+def TSV110Wr_2cyc_1FSU1  : SchedWriteRes<[TSV110UnitFSU1]>  { let Latency = 2; }
+def TSV110Wr_2cyc_1F     : SchedWriteRes<[TSV110UnitF]>     { let Latency = 2; }
+
+def TSV110Wr_3cyc_1F     : SchedWriteRes<[TSV110UnitF]>     { let Latency = 3; }
+def TSV110Wr_3cyc_1FSU1  : SchedWriteRes<[TSV110UnitFSU1]>  { let Latency = 3; }
+def TSV110Wr_3cyc_1MDU   : SchedWriteRes<[TSV110UnitMDU]>   { let Latency = 3; }
+
+def TSV110Wr_4cyc_1FSU1  : SchedWriteRes<[TSV110UnitFSU1]>  { let Latency = 4; }
+def TSV110Wr_4cyc_1F     : SchedWriteRes<[TSV110UnitF]>     { let Latency = 4; }
+def TSV110Wr_4cyc_1LdSt  : SchedWriteRes<[TSV110UnitLdSt]>  { let Latency = 4; }
+def TSV110Wr_4cyc_1MDU   : SchedWriteRes<[TSV110UnitMDU]>   { let Latency = 4; }
+
+def TSV110Wr_5cyc_1F     : SchedWriteRes<[TSV110UnitF]>     { let Latency = 5; }
+def TSV110Wr_5cyc_1FSU1  : SchedWriteRes<[TSV110UnitFSU1]>  { let Latency = 5; }
+def TSV110Wr_5cyc_1FSU2  : SchedWriteRes<[TSV110UnitFSU2]>  { let Latency = 5; }
+def TSV110Wr_5cyc_1LdSt  : SchedWriteRes<[TSV110UnitLdSt]>  { let Latency = 5; }
+
+def TSV110Wr_6cyc_1F     : SchedWriteRes<[TSV110UnitF]>     { let Latency = 6; }
+
+def TSV110Wr_7cyc_1F     : SchedWriteRes<[TSV110UnitF]>     { let Latency = 7; }
+
+def TSV110Wr_8cyc_1F     : SchedWriteRes<[TSV110UnitF]>     { let Latency = 8; }
+
+def TSV110Wr_11cyc_1FSU1 : SchedWriteRes<[TSV110UnitFSU1]>  { let Latency = 11; }
+
+def TSV110Wr_12cyc_1MDU  : SchedWriteRes<[TSV110UnitMDU]>   { let Latency = 12; }
+
+def TSV110Wr_17cyc_1FSU2 : SchedWriteRes<[TSV110UnitFSU2]>  { let Latency = 17; }
+
+def TSV110Wr_18cyc_1FSU1 : SchedWriteRes<[TSV110UnitFSU1]>  { let Latency = 18; }
+
+def TSV110Wr_20cyc_1MDU  : SchedWriteRes<[TSV110UnitMDU]>   { let Latency = 20; }
+
+def TSV110Wr_24cyc_1FSU1 : SchedWriteRes<[TSV110UnitFSU1]>  { let Latency = 24; }
+
+def TSV110Wr_31cyc_1FSU2 : SchedWriteRes<[TSV110UnitFSU2]>  { let Latency = 31; }
+
+def TSV110Wr_36cyc_1FSU2 : SchedWriteRes<[TSV110UnitFSU2]>  { let Latency = 36; }
+
+def TSV110Wr_38cyc_1FSU1 : SchedWriteRes<[TSV110UnitFSU1]>  { let Latency = 38; }
+
+def TSV110Wr_64cyc_1FSU2 : SchedWriteRes<[TSV110UnitFSU2]>  { let Latency = 64; }
+
+//===----------------------------------------------------------------------===//
+// Define Generic 2 micro-op types
+
+def TSV110Wr_1cyc_1LdSt_1ALUAB : SchedWriteRes<[TSV110UnitLdSt,
+                                                TSV110UnitALUAB]> {
+  let Latency = 1;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_2cyc_1LdSt_1ALUAB :  SchedWriteRes<[TSV110UnitLdSt,
+                                                 TSV110UnitALUAB]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_2cyc_2LdSt        : SchedWriteRes<[TSV110UnitLdSt,
+                                                TSV110UnitLdSt]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_2cyc_2F           : SchedWriteRes<[TSV110UnitF,
+                                                TSV110UnitF]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_2cyc_1FSU1_1FSU2  : SchedWriteRes<[TSV110UnitFSU1,
+                                                TSV110UnitFSU2]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_4cyc_2F           : SchedWriteRes<[TSV110UnitF,
+                                                TSV110UnitF]> {
+  let Latency = 4;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_4cyc_1FSU1_1FSU2  : SchedWriteRes<[TSV110UnitFSU1,
+                                                TSV110UnitFSU2]> {
+  let Latency = 4;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_4cyc_1LdSt_1ALUAB : SchedWriteRes<[TSV110UnitLdSt,
+                                                TSV110UnitALUAB]> {
+  let Latency = 4;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_5cyc_1ALU_1F      : SchedWriteRes<[TSV110UnitALU,
+                                                TSV110UnitF]> {
+  let Latency     = 5;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_6cyc_2LdSt        : SchedWriteRes<[TSV110UnitLdSt,
+                                                TSV110UnitLdSt]> {
+  let Latency = 6;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_6cyc_1LdSt_1ALUAB : SchedWriteRes<[TSV110UnitLdSt,
+                                                TSV110UnitALUAB]> {
+  let Latency = 6;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_7cyc_1F_1LdSt     : SchedWriteRes<[TSV110UnitF,
+                                                TSV110UnitLdSt]> {
+  let Latency = 7;
+  let NumMicroOps = 2;
+}
+
+def TSV110Wr_8cyc_2FSU1        : SchedWriteRes<[TSV110UnitFSU1,
+                                                TSV110UnitFSU1]> {
+  let Latency = 8;
+  let NumMicroOps = 2;
+}
+
+
+def TSV110Wr_8cyc_1FSU1_1FSU2  : SchedWriteRes<[TSV110UnitFSU1,
+                                                TSV110UnitFSU2]> {
+  let Latency = 8;
+  let NumMicroOps = 2;
+}
+
+//===----------------------------------------------------------------------===//
+// Define Generic 3 micro-op types
+
+def TSV110Wr_6cyc_3F       : SchedWriteRes<[TSV110UnitF, TSV110UnitF,
+                                            TSV110UnitF]> {
+  let Latency     = 6;
+  let NumMicroOps = 3;
+}
+
+def TSV110Wr_6cyc_3LdSt    : SchedWriteRes<[TSV110UnitLdSt, TSV110UnitLdSt,
+                                            TSV110UnitLdSt]> {
+  let Latency = 6;
+  let NumMicroOps = 3;
+}
+
+def TSV110Wr_7cyc_2F_1LdSt : SchedWriteRes<[TSV110UnitF, TSV110UnitF,
+                                                         TSV110UnitLdSt]> {
+  let Latency = 7;
+  let NumMicroOps = 3;
+}
+
+//===----------------------------------------------------------------------===//
+// Define Generic 4 micro-op types
+
+def TSV110Wr_8cyc_4F          : SchedWriteRes<[TSV110UnitF, TSV110UnitF,
+                                               TSV110UnitF, TSV110UnitF]> {
+  let Latency = 8;
+  let NumMicroOps = 4;
+}
+
+def TSV110Wr_8cyc_3F_1LdSt    : SchedWriteRes<[TSV110UnitF, TSV110UnitF,
+                                               TSV110UnitF, TSV110UnitLdSt]> {
+  let Latency = 8;
+  let NumMicroOps = 4;
+}
+
+//===----------------------------------------------------------------------===//
+// Define Generic 5 micro-op types
+
+def TSV110Wr_8cyc_3F_2LdSt : SchedWriteRes<[TSV110UnitF, TSV110UnitF, TSV110UnitF,
+                                            TSV110UnitLdSt, TSV110UnitLdSt]> {
+  let Latency = 8;
+  let NumMicroOps = 5;
+}
+
+//===----------------------------------------------------------------------===//
+// Define Generic 8 micro-op types
+
+def TSV110Wr_10cyc_4F_4LdSt : SchedWriteRes<[TSV110UnitF, TSV110UnitF,
+                                             TSV110UnitF, TSV110UnitF,
+                                             TSV110UnitLdSt, TSV110UnitLdSt,
+                                             TSV110UnitLdSt, TSV110UnitLdSt]> {
+  let Latency = 10;
+  let NumMicroOps = 8;
+}
+
+
+// Branch Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_1cyc_1AB], (instrs B)>;
+def : InstRW<[TSV110Wr_1cyc_1AB], (instrs BL)>;
+def : InstRW<[TSV110Wr_1cyc_1AB], (instrs BLR)>;
+def : InstRW<[TSV110Wr_1cyc_1AB], (instregex "^(BR|RET|(CBZ|CBNZ|TBZ|TBNZ))$")>;
+
+
+// Cryptography Extensions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_3cyc_1FSU1], (instregex "^AES[DE]")>;
+def : InstRW<[TSV110Wr_3cyc_1FSU1], (instregex "^AESI?MC")>;
+def : InstRW<[TSV110Wr_2cyc_1FSU1], (instregex "^SHA1SU1")>;
+def : InstRW<[TSV110Wr_2cyc_2F],    (instregex "^SHA1(H|SU0)")>;
+def : InstRW<[TSV110Wr_5cyc_1FSU1], (instregex "^SHA1[CMP]")>;
+def : InstRW<[TSV110Wr_2cyc_1FSU1], (instregex "^SHA256SU0")>;
+def : InstRW<[TSV110Wr_3cyc_1FSU1], (instregex "^SHA256SU1")>;
+def : InstRW<[TSV110Wr_5cyc_1FSU1], (instregex "^SHA256(H|H2)")>;
+def TSV110ReadCRC: SchedReadAdvance<1, [TSV110Wr_2cyc_1MDU]>;
+def : InstRW<[TSV110Wr_2cyc_1MDU, TSV110ReadCRC],  (instregex "^CRC32.*$")>;
+
+
+// Arithmetic and Logical Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_1cyc_1ALUAB], (instregex "(BIC|EON|ORN)[WX]rr")>;
+def : InstRW<[TSV110Wr_1cyc_1AB],    (instregex "(BIC)S[WX]rr")>;
+
+def : InstRW<[TSV110Wr_1cyc_1ALUAB], (instregex "(ADD|AND|EOR|ORR|SUB)[WX]r(r|i)")>;
+def : InstRW<[TSV110Wr_1cyc_1AB],    (instregex "(ADD|AND|EOR|ORR|SUB)S[WX]r(r|i)")>;
+
+def : InstRW<[TSV110Wr_1cyc_1ALUAB], (instregex "^(ADC|SBC|BIC)[WX]r$")>;
+def : InstRW<[TSV110Wr_1cyc_1AB],    (instregex "^(ADC|SBC)S[WX]r$")>;
+
+def : InstRW<[TSV110Wr_2cyc_1MDU],   (instregex "^(AND|BIC|EON|EOR|ORN|ORR)[WX]rs$")>;
+def : InstRW<[TSV110Wr_2cyc_1AB],    (instregex "^(AND|BIC|EON|EOR|ORN|ORR)S[WX]rs$")>;
+def : InstRW<[TSV110Wr_2cyc_1MDU],   (instregex "^(ADD|SUB)[WX]r(s|x|x64)$")>;
+def : InstRW<[TSV110Wr_2cyc_1AB],    (instregex "^(ADD|SUB)S[WX]r(s|x|x64)$")>;
+
+def : InstRW<[TSV110Wr_1cyc_1AB],    (instregex "^(CCMN|CCMP)(W|X)(r|i)$")>;
+def : InstRW<[TSV110Wr_1cyc_1ALUAB], (instregex "^(CSEL|CSINC|CSINV|CSNEG)(W|X)r$")>;
+
+
+// Move and Shift Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_1cyc_1ALUAB], (instrs ADR, ADRP)>;
+def : InstRW<[TSV110Wr_1cyc_1ALUAB], (instregex "^MOV[NZK][WX]i")>;
+def : InstRW<[TSV110Wr_1cyc_1ALUAB], (instregex "(LSLV|LSRV|ASRV|RORV)(W|X)r")>;
+
+
+// Divide and Multiply Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_12cyc_1MDU],  (instregex "^(S|U)DIVWr$")>;
+def : InstRW<[TSV110Wr_20cyc_1MDU],  (instregex "^(S|U)DIVXr$")>;
+
+def TSV110ReadMAW : SchedReadAdvance<2, [TSV110Wr_3cyc_1MDU]>;
+def : InstRW<[TSV110Wr_3cyc_1MDU, TSV110ReadMAW], (instrs MADDWrrr, MSUBWrrr)>;
+def TSV110ReadMAQ : SchedReadAdvance<3, [TSV110Wr_4cyc_1MDU]>;
+def : InstRW<[TSV110Wr_4cyc_1MDU, TSV110ReadMAQ], (instrs MADDXrrr, MSUBXrrr)>;
+def : InstRW<[TSV110Wr_3cyc_1MDU, TSV110ReadMAW], (instregex "(S|U)(MADDL|MSUBL)rrr")>;
+def : InstRW<[TSV110Wr_4cyc_1MDU], (instregex "^(S|U)MULHrr$")>;
+
+
+// Miscellaneous Data-Processing Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_1cyc_1ALUAB],    (instregex "^EXTR(W|X)rri$")>;
+def : InstRW<[TSV110Wr_1cyc_1ALUAB],    (instregex "^(S|U)?BFM(W|X)ri$")>;
+def : InstRW<[TSV110Wr_1cyc_1ALUAB],    (instregex "^(CLS|CLZ|RBIT|REV(16|32)?)(W|X)r$")>;
+
+
+// Load Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instregex "^LDR(W|X)l$")>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instrs LDRSWl)>;
+
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instregex "^LDR(BB|HH|W|X)ui$")>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instregex "^LDRS(BW|BX|HW|HX|W)ui$")>;
+
+def : InstRW<[TSV110Wr_4cyc_1LdSt, WriteAdr],     (instregex "^LDR(BB|HH|W|X)(post|pre)$")>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt, WriteAdr],     (instregex "^LDRS(BW|BX|HW|HX|W)(post|pre)$")>;
+
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instregex "^LDTR(B|H|W|X)i$")>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instregex "^LDUR(BB|HH|W|X)i$")>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instregex "^LDTRS(BW|BX|HW|HX|W)i$")>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instregex "^LDURS(BW|BX|HW|HX|W)i$")>;
+
+def : InstRW<[TSV110Wr_4cyc_1LdSt, WriteLDHi],     (instregex "^LDNP(W|X)i$")>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt, WriteLDHi],     (instregex "^LDP(W|X)i$")>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt_1ALUAB, WriteLDHi, WriteAdr],(instregex "^LDP(W|X)(post|pre)$")>;
+
+def : InstRW<[TSV110Wr_4cyc_1LdSt, WriteLDHi],           (instrs LDPSWi)>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt, WriteLDHi, WriteAdr], (instrs LDPSWpost)>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt, WriteLDHi, WriteAdr], (instrs LDPSWpre)>;
+
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instrs PRFMl)>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instrs PRFUMi)>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instregex "^PRFMui$")>;
+def : InstRW<[TSV110Wr_4cyc_1LdSt],     (instregex "^PRFMro(W|X)$")>;
+
+
+// Store Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_1cyc_1LdSt],            (instregex "^STN?P(W|X)i$")>;
+def : InstRW<[TSV110Wr_1cyc_1LdSt, WriteAdr],  (instregex "^STP(W|X)(post|pre)$")>;
+def : InstRW<[TSV110Wr_1cyc_1LdSt],            (instregex "^STUR(BB|HH|W|X)i$")>;
+def : InstRW<[TSV110Wr_1cyc_1LdSt],            (instregex "^STTR(B|H|W|X)i$")>;
+def : InstRW<[TSV110Wr_1cyc_1LdSt],            (instregex "^STR(BB|HH|W|X)ui$")>;
+
+def : InstRW<[TSV110Wr_1cyc_1LdSt, WriteAdr],  (instregex "^STR(BB|HH|W|X)(post|pre)$")>;
+def : InstRW<[TSV110Wr_1cyc_1LdSt, WriteAdr],  (instregex "^STR(BB|HH|W|X)ro(W|X)$")>;
+
+
+// FP Data Processing Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_2cyc_1F], (instregex "F(ABS|NEG)(D|S)r")>;
+def : InstRW<[TSV110Wr_3cyc_1F], (instregex "^FCCMP(E)?(S|D)rr$")>;
+def : InstRW<[TSV110Wr_3cyc_1F], (instregex "^FCMP(E)?(S|D)r(r|i)$")>;
+def : InstRW<[TSV110Wr_3cyc_1F], (instregex "^FCSEL(S|D)rrr$")>;
+
+def : InstRW<[TSV110Wr_11cyc_1FSU1], (instrs FDIVSrr)>;
+def : InstRW<[TSV110Wr_18cyc_1FSU1], (instrs FDIVDrr)>;
+def : InstRW<[TSV110Wr_17cyc_1FSU2], (instrs FSQRTSr)>;
+def : InstRW<[TSV110Wr_31cyc_1FSU2], (instrs FSQRTDr)>;
+
+def : InstRW<[TSV110Wr_2cyc_1F], (instregex "^F(MAX|MIN).+rr")>;
+
+def : InstRW<[TSV110Wr_4cyc_1F], (instregex "^FN?M(ADD|SUB)Hrrr")>;
+def : InstRW<[TSV110Wr_5cyc_1F], (instregex "^FN?M(ADD|SUB)Srrr")>;
+def : InstRW<[TSV110Wr_7cyc_1F], (instregex "^FN?M(ADD|SUB)Drrr")>;
+
+def : InstRW<[TSV110Wr_4cyc_1F], (instregex "^F(ADD|SUB)Hrr")>;
+def : InstRW<[TSV110Wr_5cyc_1F], (instregex "^F(ADD|SUB)Srr")>;
+def : InstRW<[TSV110Wr_4cyc_1F], (instregex "^F(ADD|SUB)Drr")>;
+
+def : InstRW<[TSV110Wr_4cyc_1F], (instregex "^F(N)?MULHrr$")>;
+def : InstRW<[TSV110Wr_5cyc_1F], (instregex "^F(N)?MULSrr$")>;
+def : InstRW<[TSV110Wr_5cyc_1F], (instregex "^F(N)?MULDrr$")>;
+
+def : InstRW<[TSV110Wr_3cyc_1F], (instregex "^FRINT.+r")>;
+
+
+// FP Miscellaneous Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_5cyc_1ALU_1F], (instregex "^[SU]CVTF[SU][WX][SD]ri")>;
+def : InstRW<[TSV110Wr_4cyc_1FSU1],   (instregex "^FCVT(A|M|N|P|Z)(S|U)U(W|X)(S|D)r$")>;
+def : InstRW<[TSV110Wr_3cyc_1F],      (instregex "^FCVT[HSD][HSD]r")>;
+
+def : InstRW<[TSV110Wr_2cyc_1FSU1],   (instregex "^FMOV(DX|WS|XD|SW|DXHigh|XDHigh)r$")>;
+def : InstRW<[TSV110Wr_2cyc_1F],      (instregex "^FMOV[SD][ir]$")>;
+
+
+// FP Load Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_5cyc_1LdSt],                      (instregex "^LDR[DSQ]l")>;
+def : InstRW<[TSV110Wr_5cyc_1LdSt],                      (instregex "^LDUR[BDHSQ]i")>;
+def : InstRW<[TSV110Wr_5cyc_1LdSt, WriteAdr],            (instregex "^LDR[BDHSQ](post|pre)")>;
+def : InstRW<[TSV110Wr_5cyc_1LdSt],                      (instregex "^LDR[BDHSQ]ui")>;
+def : InstRW<[TSV110Wr_6cyc_1LdSt_1ALUAB, ReadAdrBase],  (instregex "^LDR(Q|D|H|S|B)ro(W|X)$")>;
+def : InstRW<[TSV110Wr_5cyc_1LdSt, WriteLDHi],           (instregex "^LDN?P[DQS]i")>;
+def : InstRW<[TSV110Wr_5cyc_1LdSt, WriteLDHi, WriteAdr], (instregex "^LDP[DQS](post|pre)")>;
+
+
+// FP Store Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_1cyc_1LdSt],                     (instregex "^STUR[BHSDQ]i")>;
+def : InstRW<[TSV110Wr_1cyc_1LdSt_1ALUAB, ReadAdrBase], (instregex "^STR[BHSDQ](post|pre)")>;
+def : InstRW<[TSV110Wr_1cyc_1LdSt],                     (instregex "^STR[BHSDQ]ui")>;
+def : InstRW<[TSV110Wr_2cyc_1LdSt_1ALUAB, ReadAdrBase], (instregex "^STR[BHSDQ]ro[WX]")>;
+def : InstRW<[TSV110Wr_2cyc_2LdSt],                     (instregex "^STN?P[SDQ]i")>;
+def : InstRW<[TSV110Wr_2cyc_2LdSt, WriteAdr],           (instregex "^STP[SDQ](post|pre)")>;
+
+
+// ASIMD Integer Instructions
+// -----------------------------------------------------------------------------
+
+// Reference for forms in this group
+//   D form - v8i8, v4i16, v2i32
+//   Q form - v16i8, v8i16, v4i32
+//   D form - v1i8, v1i16, v1i32, v1i64
+//   Q form - v16i8, v8i16, v4i32, v2i64
+//   D form - v8i8_v8i16, v4i16_v4i32, v2i32_v2i64
+//   Q form - v16i8_v8i16, v8i16_v4i32, v4i32_v2i64
+
+// ASIMD simple arithmetic
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^(ABS|ADD(P)?|NEG|SUB)v")>;
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^[SU](ADD(L|LP|W)|SUB(L|W))v")>;
+
+// ASIMD complex arithmetic
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^[SU]H(ADD|SUB)v")>;
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^R?(ADD|SUB)HN2?v")>;
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^[SU]Q(ADD|SUB)v")>;
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^(SU|US)QADDv")>;
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^[SU]RHADDv")>;
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^[SU]ABAL?v")>;
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^[SU]ABDL?v")>;
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^[SU]ADALPv")>;
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^((SQ)(ABS|NEG))v")>;
+
+// ASIMD compare
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^CM(EQ|GE|GT|HI|HS|LE|LT|TST)v")>;
+
+// ASIMD max/min
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^[SU](MIN|MAX)P?v")>;
+
+// ASIMD logical
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^(AND|BIC|BIF|BIT|BSL|EOR|MVN|NOT|ORN|ORR)v")>;
+
+// ASIMD multiply accumulate, D-form
+def : InstRW<[TSV110Wr_4cyc_1FSU1], (instregex "^(MUL|ML[AS]|SQR?D(MULH))(v8i8|v4i16|v2i32|v1i8|v1i16|v1i32|v1i64)")>;
+// ASIMD multiply accumulate, Q-form
+def : InstRW<[TSV110Wr_8cyc_2FSU1], (instregex "^(MUL|ML[AS]|SQR?D(MULH))(v16i8|v8i16|v4i32)")>;
+
+// ASIMD multiply accumulate long
+def : InstRW<[TSV110Wr_4cyc_1FSU1], (instregex "(S|U|SQD)(MLAL|MLSL|MULL)v.*")>;
+def : InstRW<[TSV110Wr_2cyc_1FSU1], (instregex "^PMULL(v8i8|v16i8)")>;
+def : InstRW<[TSV110Wr_2cyc_1FSU1], (instregex "^PMULL(v1i64|v2i64)")>;
+
+// ASIMD shift
+// ASIMD shift accumulate
+def : InstRW<[TSV110Wr_4cyc_1FSU1], (instregex "^(S|SR|U|UR)SRA")>;
+// ASIMD shift by immed, basic
+def : InstRW<[TSV110Wr_4cyc_1FSU1],
+            (instregex "SHLv","SLIv","SRIv","SHRNv","SQXTNv","SQXTUNv","UQXTNv")>;
+// ASIMD shift by immed, complex
+def : InstRW<[TSV110Wr_4cyc_1FSU1], (instregex "^[SU]?(Q|R){1,2}SHR")>;
+def : InstRW<[TSV110Wr_4cyc_1FSU1], (instregex "^SQSHLU")>;
+// ASIMD shift by register, basic, Q-form
+def : InstRW<[TSV110Wr_4cyc_1FSU1], (instregex "^[SU]SHL(v16i8|v8i16|v4i32|v2i64)")>;
+// ASIMD shift by register, complex, D-form
+def : InstRW<[TSV110Wr_4cyc_1FSU1], (instregex "^[SU][QR]{1,2}SHL(v1i8|v1i16|v1i32|v1i64|v8i8|v4i16|v2i32|b|d|h|s)")>;
+// ASIMD shift by register, complex, Q-form
+def : InstRW<[TSV110Wr_4cyc_1FSU1], (instregex "^[SU][QR]{1,2}SHL(v16i8|v8i16|v4i32|v2i64)")>;
+
+// ASIMD reduction
+// ASIMD arith, reduce, 4H/4S
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^[SU]?ADDL?V(v8i8|v4i16|v2i32)v$")>;
+// ASIMD arith, reduce, 8B/8H
+def : InstRW<[TSV110Wr_8cyc_1FSU1_1FSU2], (instregex "^[SU]?ADDL?V(v8i16|v4i32)v$")>;
+// ASIMD arith, reduce, 16B
+def : InstRW<[TSV110Wr_8cyc_1FSU1_1FSU2], (instregex "^[SU]?ADDL?Vv16i8v$")>;
+
+// ASIMD max/min, reduce, 4H/4S
+def : InstRW<[TSV110Wr_4cyc_1FSU1_1FSU2], (instregex "^[SU](MIN|MAX)V(v4i16|v4i32)v$")>;
+// ASIMD max/min, reduce, 8B/8H
+def : InstRW<[TSV110Wr_8cyc_1FSU1_1FSU2], (instregex "^[SU](MIN|MAX)V(v8i8|v8i16)v$")>;
+// ASIMD max/min, reduce, 16B
+def : InstRW<[TSV110Wr_8cyc_1FSU1_1FSU2], (instregex "^[SU](MIN|MAX)Vv16i8v$")>;
+
+
+// Vector - Floating Point
+// -----------------------------------------------------------------------------
+
+// Reference for forms in this group
+//   D form - v2f32
+//   Q form - v4f32, v2f64
+//   D form - 32, 64
+//   D form - v1i32, v1i64
+//   D form - v2i32
+//   Q form - v4i32, v2i64
+
+// ASIMD FP sign manipulation
+def : InstRW<[TSV110Wr_2cyc_1F],  (instregex "^FABSv")>;
+def : InstRW<[TSV110Wr_2cyc_1F],  (instregex "^FNEGv")>;
+
+// ASIMD FP compare
+def : InstRW<[TSV110Wr_2cyc_1F],  (instregex "^F(AC|CM)(EQ|GE|GT|LE|LT)v")>;
+
+// ASIMD FP convert
+def : InstRW<[TSV110Wr_2cyc_1F],  (instregex "^FCVT[AMNPZ][SU]v")>;
+def : InstRW<[TSV110Wr_3cyc_1F],  (instregex "^FCVT(L)v")>;
+def : InstRW<[TSV110Wr_5cyc_1F],  (instregex "^FCVT(N|XN)v")>;
+
+// ASIMD FP divide, D-form, F32
+def : InstRW<[TSV110Wr_11cyc_1FSU1], (instregex "FDIVv2f32")>;
+// ASIMD FP divide, Q-form, F32
+def : InstRW<[TSV110Wr_24cyc_1FSU1], (instregex "FDIVv4f32")>;
+// ASIMD FP divide, Q-form, F64
+def : InstRW<[TSV110Wr_38cyc_1FSU1], (instregex "FDIVv2f64")>;
+
+// ASIMD FP SQRT
+def : InstRW<[TSV110Wr_17cyc_1FSU2], (instrs FSQRTv2f32)>;
+def : InstRW<[TSV110Wr_36cyc_1FSU2], (instrs FSQRTv4f32)>;
+def : InstRW<[TSV110Wr_64cyc_1FSU2], (instrs FSQRTv2f64)>;
+
+// ASIMD FP max,min
+def : InstRW<[TSV110Wr_2cyc_1F],  (instregex "^F(MAX|MIN)(NM)?v")>;
+def : InstRW<[TSV110Wr_2cyc_1F],  (instregex "^F(MAX|MIN)(NM)?Pv")>;
+def : InstRW<[TSV110Wr_4cyc_1F],  (instregex "^F(MAX|MIN)(NM)?Vv")>;
+
+// ASIMD FP add
+def : InstRW<[TSV110Wr_5cyc_1F],  (instregex "^F(ADD|ADDP|SUB)v")>;
+
+// ASIMD FP multiply
+def : InstRW<[TSV110Wr_5cyc_1F],  (instregex "^FMULX?v")>;
+
+
+// ASIMD Miscellaneous Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^(CLS|CLZ|CNT)v")>;
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^(DUP|INS)v.+lane")>;
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^REV(16|32|64)v")>;
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^(UZP|ZIP)[12]v")>;
+
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^EXTv")>;
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^XTNv")>;
+def : InstRW<[TSV110Wr_2cyc_1FSU1_1FSU2], (instregex "^RBITv")>;
+
+def : InstRW<[TSV110Wr_4cyc_1F], (instregex "^(INS|DUP)v.+gpr")>;
+
+def : InstRW<[TSV110Wr_3cyc_1FSU1], (instregex "^[SU]MOVv")>;
+
+// ASIMD table lookup, D-form
+def : InstRW<[TSV110Wr_2cyc_1F], (instregex "^TB[LX]v8i8One")>;
+def : InstRW<[TSV110Wr_4cyc_2F], (instregex "^TB[LX]v8i8Two")>;
+def : InstRW<[TSV110Wr_6cyc_3F], (instregex "^TB[LX]v8i8Three")>;
+def : InstRW<[TSV110Wr_8cyc_4F], (instregex "^TB[LX]v8i8Four")>;
+// ASIMD table lookup, Q-form
+def : InstRW<[TSV110Wr_2cyc_1F], (instregex "^TB[LX]v16i8One")>;
+def : InstRW<[TSV110Wr_4cyc_2F], (instregex "^TB[LX]v16i8Two")>;
+def : InstRW<[TSV110Wr_6cyc_3F], (instregex "^TB[LX]v16i8Three")>;
+def : InstRW<[TSV110Wr_8cyc_4F], (instregex "^TB[LX]v16i8Four")>;
+
+def : InstRW<[TSV110Wr_2cyc_1F], (instregex "^FMOVv")>;
+
+def : InstRW<[TSV110Wr_3cyc_1F], (instregex "^FRINT[AIMNPXZ]v")>;
+def : InstRW<[TSV110Wr_3cyc_1F], (instregex "^[SU]CVTFv")>;
+def : InstRW<[TSV110Wr_3cyc_1F], (instregex "^[FU](RECP|RSQRT)(E|X)v")>;
+
+
+// ASIMD Load Instructions
+// -----------------------------------------------------------------------------
+
+def : InstRW<[TSV110Wr_7cyc_1F_1LdSt],            (instregex "^LD1Rv(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_7cyc_1F_1LdSt, WriteAdr],  (instregex "^LD1Rv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+def : InstRW<[TSV110Wr_7cyc_2F_1LdSt],            (instregex "^LD2Rv(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_7cyc_2F_1LdSt, WriteAdr],  (instregex "^LD2Rv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+def : InstRW<[TSV110Wr_8cyc_3F_1LdSt],            (instregex "^LD3Rv(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_8cyc_3F_1LdSt, WriteAdr],  (instregex "^LD3Rv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+def : InstRW<[TSV110Wr_8cyc_3F_2LdSt],            (instregex "^LD4Rv(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_8cyc_3F_2LdSt, WriteAdr],  (instregex "^LD4Rv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+
+def  : InstRW<[TSV110Wr_7cyc_1F_1LdSt],           (instregex "LD1i(8|16|32|64)$")>;
+def  : InstRW<[TSV110Wr_7cyc_1F_1LdSt, WriteAdr], (instregex "LD1i(8|16|32|64)_POST$")>;
+def  : InstRW<[TSV110Wr_7cyc_2F_1LdSt],           (instregex "LD2i(8|16|32|64)$")>;
+def  : InstRW<[TSV110Wr_7cyc_2F_1LdSt, WriteAdr], (instregex "LD2i(8|16|32|64)_POST$")>;
+def  : InstRW<[TSV110Wr_8cyc_3F_1LdSt],           (instregex "LD3i(8|16|32|64)$")>;
+def  : InstRW<[TSV110Wr_8cyc_3F_1LdSt, WriteAdr], (instregex "LD3i(8|16|32|64)_POST$")>;
+def  : InstRW<[TSV110Wr_8cyc_3F_2LdSt],           (instregex "LD4i(8|16|32|64)$")>;
+def  : InstRW<[TSV110Wr_8cyc_3F_2LdSt, WriteAdr], (instregex "LD4i(8|16|32|64)_POST$")>;
+
+def : InstRW<[TSV110Wr_5cyc_1LdSt],               (instregex "^LD1Onev(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_5cyc_1LdSt, WriteAdr],     (instregex "^LD1Onev(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+def : InstRW<[TSV110Wr_5cyc_1LdSt],               (instregex "^LD1Twov(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_5cyc_1LdSt, WriteAdr],     (instregex "^LD1Twov(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+def : InstRW<[TSV110Wr_6cyc_3LdSt],               (instregex "^LD1Threev(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_6cyc_3LdSt, WriteAdr],     (instregex "^LD1Threev(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+def : InstRW<[TSV110Wr_6cyc_2LdSt],               (instregex "^LD1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_6cyc_2LdSt, WriteAdr],     (instregex "^LD1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+
+def : InstRW<[TSV110Wr_7cyc_2F_1LdSt],            (instregex "^LD2Twov(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_7cyc_2F_1LdSt, WriteAdr],  (instregex "^LD2Twov(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+
+def : InstRW<[TSV110Wr_8cyc_3F_1LdSt],            (instregex "^LD3Threev(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_8cyc_3F_1LdSt, WriteAdr],  (instregex "^LD3Threev(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+
+def : InstRW<[TSV110Wr_10cyc_4F_4LdSt],           (instregex "^LD4Fourv(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_10cyc_4F_4LdSt, WriteAdr], (instregex "^LD4Fourv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+
+
+// ASIMD Store Instructions
+// -----------------------------------------------------------------------------
+
+def  : InstRW<[TSV110Wr_3cyc_1F],             (instregex "ST1i(8|16|32|64)$")>;
+def  : InstRW<[TSV110Wr_3cyc_1F, WriteAdr],   (instregex "ST1i(8|16|32|64)_POST$")>;
+def  : InstRW<[TSV110Wr_4cyc_1F],             (instregex "ST2i(8|16|32|64)$")>;
+def  : InstRW<[TSV110Wr_4cyc_1F, WriteAdr],   (instregex "ST2i(8|16|32|64)_POST$")>;
+def  : InstRW<[TSV110Wr_5cyc_1F],             (instregex "ST3i(8|16|32|64)$")>;
+def  : InstRW<[TSV110Wr_5cyc_1F, WriteAdr],   (instregex "ST3i(8|16|32|64)_POST$")>;
+def  : InstRW<[TSV110Wr_6cyc_1F],             (instregex "ST4i(8|16|32|64)$")>;
+def  : InstRW<[TSV110Wr_6cyc_1F, WriteAdr],   (instregex "ST4i(8|16|32|64)_POST$")>;
+
+def : InstRW<[TSV110Wr_3cyc_1F],              (instregex "^ST1Onev(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_3cyc_1F, WriteAdr],    (instregex "^ST1Onev(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+def : InstRW<[TSV110Wr_4cyc_1F],              (instregex "^ST1Twov(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_4cyc_1F, WriteAdr],    (instregex "^ST1Twov(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+def : InstRW<[TSV110Wr_5cyc_1F],              (instregex "^ST1Threev(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_5cyc_1F, WriteAdr],    (instregex "^ST1Threev(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+def : InstRW<[TSV110Wr_6cyc_1F],              (instregex "^ST1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_6cyc_1F, WriteAdr],    (instregex "^ST1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+
+def : InstRW<[TSV110Wr_4cyc_1F],              (instregex "^ST2Twov(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_4cyc_1F, WriteAdr],    (instregex "^ST2Twov(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+
+def : InstRW<[TSV110Wr_5cyc_1F],              (instregex "^ST3Threev(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_5cyc_1F, WriteAdr],    (instregex "^ST3Threev(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+
+def : InstRW<[TSV110Wr_8cyc_1F],              (instregex "^ST4Fourv(8b|4h|2s|1d|16b|8h|4s|2d)$")>;
+def : InstRW<[TSV110Wr_8cyc_1F, WriteAdr],    (instregex "^ST4Fourv(8b|4h|2s|1d|16b|8h|4s|2d)_POST$")>;
+
+} // SchedModel = TSV110Model

llvm/test/CodeGen/AArch64/machine-combiner-madd.ll

@@ -7,6 +7,7 @@
 ; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=kryo       < %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=thunderx2t99 < %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=thunderx3t110 < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=tsv110 < %s | FileCheck %s
 
 ; Make sure that inst-combine fuses the multiply add in the addressing mode of
 ; the load.

llvm/test/CodeGen/AArch64/preferred-function-alignment.ll

@@ -20,6 +20,7 @@
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=thunderxt88 < %s | FileCheck --check-prefixes=ALIGN3,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=thunderx2t99 < %s | FileCheck --check-prefixes=ALIGN3,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=thunderx3t110 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
+; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=tsv110 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=exynos-m3 < %s | FileCheck --check-prefixes=ALIGN5,CHECK %s
 
 define void @test() {