[AArch64] Support for Ampere1 core

Add support for the Ampere Computing Ampere1 core.
Ampere1 implements the AArch64 state and is compatible with ARMv8.6-A.

Differential Revision: https://reviews.llvm.org/D117112

(cherry picked from commit 64816e68f4419a9e14c23be8aa96fa412bed7e12)

15 files changed, 1209 insertions, 4 deletions

diff --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c
index 9b3cb45f8e23..15d7aebe35cb 100644
--- a/clang/test/Misc/target-invalid-cpu-note.c
+++ b/clang/test/Misc/target-invalid-cpu-note.c
@@ -5,11 +5,11 @@
 
 // RUN: not %clang_cc1 -triple arm64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AARCH64
 // AARCH64: error: unknown target CPU 'not-a-cpu'
-// AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-m1, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel{{$}}
+// AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-m1, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1{{$}}
 
 // RUN: not %clang_cc1 -triple arm64--- -tune-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix TUNE_AARCH64
 // TUNE_AARCH64: error: unknown target CPU 'not-a-cpu'
-// TUNE_AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-m1, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel{{$}}
+// TUNE_AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-m1, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1{{$}}
 
 // RUN: not %clang_cc1 -triple i386--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix X86
 // X86: error: unknown target CPU 'not-a-cpu'
diff --git a/llvm/include/llvm/Support/AArch64TargetParser.def b/llvm/include/llvm/Support/AArch64TargetParser.def
index a953e9439db4..199dba08e465 100644
--- a/llvm/include/llvm/Support/AArch64TargetParser.def
+++ b/llvm/include/llvm/Support/AArch64TargetParser.def
@@ -290,6 +290,9 @@ AARCH64_CPU_NAME("a64fx", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_FP16 | AArch64::AEK_SVE))
 AARCH64_CPU_NAME("carmel", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  AArch64::AEK_FP16)
+AARCH64_CPU_NAME("ampere1", ARMV8_6A, FK_CRYPTO_NEON_FP_ARMV8, false,
+                 (AArch64::AEK_FP16 | AArch64::AEK_MTE | AArch64::AEK_SB |
+                  AArch64::AEK_SSBS))
 // Invalid CPU
 AARCH64_CPU_NAME("invalid", INVALID, FK_INVALID, true, AArch64::AEK_INVALID)
 #undef AARCH64_CPU_NAME
diff --git a/llvm/lib/Target/AArch64/AArch64.td b/llvm/lib/Target/AArch64/AArch64.td
index 70c7b7b3f5dc..80e574b7b886 100644
--- a/llvm/lib/Target/AArch64/AArch64.td
+++ b/llvm/lib/Target/AArch64/AArch64.td
@@ -557,6 +557,7 @@ include "AArch64Schedule.td"
 include "AArch64InstrInfo.td"
 include "AArch64SchedPredicates.td"
 include "AArch64SchedPredExynos.td"
+include "AArch64SchedPredAmpere.td"
 include "AArch64Combine.td"
 
 def AArch64InstrInfo : InstrInfo;
@@ -626,6 +627,7 @@ include "AArch64SchedThunderX2T99.td"
 include "AArch64SchedA64FX.td"
 include "AArch64SchedThunderX3T110.td"
 include "AArch64SchedTSV110.td"
+include "AArch64SchedAmpere1.td"
 
 def TuneA35     : SubtargetFeature<"a35", "ARMProcFamily", "CortexA35",
                                 "Cortex-A35 ARM processors">;
@@ -939,6 +941,16 @@ def TuneTSV110 : SubtargetFeature<"tsv110", "ARMProcFamily", "TSV110",
                                   FeatureFuseAES,
                                   FeaturePostRAScheduler]>;
 
+def TuneAmpere1 : SubtargetFeature<"ampere1", "ARMProcFamily", "Ampere1",
+                                   "Ampere Computing Ampere-1 processors", [
+                                   FeaturePostRAScheduler,
+                                   FeatureFuseAES,
+                                   FeatureLSLFast,
+                                   FeatureAggressiveFMA,
+                                   FeatureArithmeticBccFusion,
+                                   FeatureCmpBccFusion,
+                                   FeatureFuseAddress,
+                                   FeatureFuseLiterals]>;
 
 def ProcessorFeatures {
   list<SubtargetFeature> A53  = [HasV8_0aOps, FeatureCRC, FeatureCrypto,
@@ -1047,6 +1059,8 @@ def ProcessorFeatures {
   list<SubtargetFeature> TSV110 = [HasV8_2aOps, FeatureCrypto, FeatureFPARMv8,
                                    FeatureNEON, FeaturePerfMon, FeatureSPE,
                                    FeatureFullFP16, FeatureFP16FML, FeatureDotProd];
+  list<SubtargetFeature> Ampere1 = [HasV8_6aOps, FeatureNEON, FeaturePerfMon,
+                                    FeatureMTE, FeatureSSBS];
 
   // ETE and TRBE are future architecture extensions. We temporarily enable them
   // by default for users targeting generic AArch64. The extensions do not
@@ -1184,6 +1198,10 @@ def : ProcessorModel<"a64fx", A64FXModel, ProcessorFeatures.A64FX,
 def : ProcessorModel<"carmel", NoSchedModel, ProcessorFeatures.Carmel,
                      [TuneCarmel]>;
 
+// Ampere Computing
+def : ProcessorModel<"ampere1", Ampere1Model, ProcessorFeatures.Ampere1,
+                     [TuneAmpere1]>;
+
 //===----------------------------------------------------------------------===//
 // Assembly parser
 //===----------------------------------------------------------------------===//
diff --git a/llvm/lib/Target/AArch64/AArch64SchedAmpere1.td b/llvm/lib/Target/AArch64/AArch64SchedAmpere1.td
new file mode 100644
index 000000000000..32f7299fbf87
--- /dev/null
+++ b/llvm/lib/Target/AArch64/AArch64SchedAmpere1.td
@@ -0,0 +1,1136 @@
+//=- AArch64SchedAmpere1.td - Ampere-1 scheduling def -----*- 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 the Ampere Computing Ampere-1 to
+// support instruction scheduling and other instruction cost heuristics.
+//
+//===----------------------------------------------------------------------===//
+
+// The Ampere-1 core is an out-of-order micro-architecture.  The front
+// end has branch prediction, with a 10-cycle recovery time from a
+// mispredicted branch.  Instructions coming out of the front end are
+// decoded into internal micro-ops (uops).
+
+def Ampere1Model : SchedMachineModel {
+  let IssueWidth            =   4;  // 4-way decode and dispatch
+  let MicroOpBufferSize     = 174;  // micro-op re-order buffer size
+  let LoadLatency           =   4;  // Optimistic load latency
+  let MispredictPenalty     =  10;  // Branch mispredict penalty
+  let LoopMicroOpBufferSize =  32;  // Instruction queue size
+  let CompleteModel = 1;
+
+  list<Predicate> UnsupportedFeatures = !listconcat(SVEUnsupported.F,
+                                                    SMEUnsupported.F);
+}
+
+let SchedModel = Ampere1Model in {
+
+//===----------------------------------------------------------------------===//
+// Define each kind of processor resource and number available on Ampere-1.
+// Ampere-1 has 12 pipelines that 8 independent scheduler (4 integer, 2 FP,
+// and 2 memory) issue into.  The integer and FP schedulers can each issue
+// one uop per cycle, while the memory schedulers can each issue one load
+// and one store address calculation per cycle.
+
+def Ampere1UnitA  : ProcResource<2>;  // integer single-cycle, branch, and flags r/w
+def Ampere1UnitB  : ProcResource<2>;  // integer single-cycle, and complex shifts
+def Ampere1UnitBS : ProcResource<1>;  // integer multi-cycle
+def Ampere1UnitL  : ProcResource<2>;  // load
+def Ampere1UnitS  : ProcResource<2>;  // store address calculation
+def Ampere1UnitX  : ProcResource<1>;  // FP and vector operations, and flag write
+def Ampere1UnitY  : ProcResource<1>;  // FP and vector operations, and crypto
+def Ampere1UnitZ  : ProcResource<1>;  // FP store data and FP-to-integer moves
+
+def Ampere1UnitAB : ProcResGroup<[Ampere1UnitA, Ampere1UnitB]>;
+def Ampere1UnitXY : ProcResGroup<[Ampere1UnitX, Ampere1UnitY]>;
+
+//===----------------------------------------------------------------------===//
+// Define customized scheduler read/write types specific to the Ampere-1.
+
+def Ampere1Write_1cyc_1A : SchedWriteRes<[Ampere1UnitA]> {
+  let Latency = 1;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_1cyc_2A : SchedWriteRes<[Ampere1UnitA, Ampere1UnitA]> {
+  let Latency = 1;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_1cyc_1B : SchedWriteRes<[Ampere1UnitB]> {
+  let Latency = 1;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_1cyc_1AB : SchedWriteRes<[Ampere1UnitAB]> {
+  let Latency = 1;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_1cyc_1L : SchedWriteRes<[Ampere1UnitL]> {
+  let Latency = 1;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_1cyc_1S : SchedWriteRes<[Ampere1UnitS]> {
+  let Latency = 1;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_1cyc_2S : SchedWriteRes<[Ampere1UnitS, Ampere1UnitS]> {
+  let Latency = 1;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_2cyc_1Y : SchedWriteRes<[Ampere1UnitY]> {
+  let Latency = 2;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_2cyc_2AB : SchedWriteRes<[Ampere1UnitAB, Ampere1UnitAB]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_2cyc_1B_1AB : SchedWriteRes<[Ampere1UnitB, Ampere1UnitAB]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_2cyc_1B_1A : SchedWriteRes<[Ampere1UnitB, Ampere1UnitA]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_2cyc_1AB_1A : SchedWriteRes<[Ampere1UnitAB, Ampere1UnitA]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_2cyc_1AB_1L : SchedWriteRes<[Ampere1UnitAB, Ampere1UnitL]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_2cyc_1AB_2S : SchedWriteRes<[Ampere1UnitAB, Ampere1UnitS,
+                                                             Ampere1UnitS]> {
+  let Latency = 2;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_2cyc_1AB_1S_1Z : SchedWriteRes<[Ampere1UnitAB, Ampere1UnitS,
+                                                                Ampere1UnitZ]> {
+  let Latency = 2;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_2cyc_1B_1S : SchedWriteRes<[Ampere1UnitB, Ampere1UnitS]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_2cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 2;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_2cyc_1S_1Z : SchedWriteRes<[Ampere1UnitS, Ampere1UnitZ]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_3cyc_1BS : SchedWriteRes<[Ampere1UnitBS]> {
+  let Latency = 3;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_3cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 3;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_3cyc_1B_1S_1AB : SchedWriteRes<[Ampere1UnitB, Ampere1UnitS,
+                                                               Ampere1UnitAB]> {
+  let Latency = 2;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_3cyc_1S_2Z : SchedWriteRes<[Ampere1UnitS, Ampere1UnitZ, Ampere1UnitZ]> {
+  let Latency = 2;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_3cyc_2S_2Z : SchedWriteRes<[Ampere1UnitS, Ampere1UnitS,
+                                             Ampere1UnitZ, Ampere1UnitZ]> {
+  let Latency = 2;
+  let NumMicroOps = 4;
+}
+
+def Ampere1Write_4cyc_1BS : SchedWriteRes<[Ampere1UnitBS]> {
+  let Latency = 4;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_4cyc_1L : SchedWriteRes<[Ampere1UnitL]> {
+  let Latency = 4;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_4cyc_1X : SchedWriteRes<[Ampere1UnitX]> {
+  let Latency = 4;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_4cyc_1Y : SchedWriteRes<[Ampere1UnitY]> {
+  let Latency = 4;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_4cyc_1Z : SchedWriteRes<[Ampere1UnitZ]> {
+  let Latency = 4;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_4cyc_2L : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL]> {
+  let Latency = 4;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_4cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 4;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_4cyc_2XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 4;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_4cyc_1XY_1S_1Z : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitS, Ampere1UnitZ]> {
+  let Latency = 4;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_4cyc_3S_3Z : SchedWriteRes<[Ampere1UnitS, Ampere1UnitS, Ampere1UnitS,
+                                             Ampere1UnitZ, Ampere1UnitZ, Ampere1UnitZ]> {
+  let Latency = 4;
+  let NumMicroOps = 6;
+}
+
+def Ampere1Write_5cyc_1AB_1L : SchedWriteRes<[Ampere1UnitAB, Ampere1UnitL]> {
+  let Latency = 5;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_5cyc_1BS : SchedWriteRes<[Ampere1UnitBS]> {
+  let Latency = 5;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_5cyc_1X : SchedWriteRes<[Ampere1UnitX]> {
+  let Latency = 5;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_5cyc_1L : SchedWriteRes<[Ampere1UnitL]> {
+  let Latency = 5;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_5cyc_2L : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL]> {
+  let Latency = 5;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_5cyc_1L_1BS : SchedWriteRes<[Ampere1UnitL, Ampere1UnitBS]> {
+  let Latency = 5;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_5cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 5;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_5cyc_2XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 5;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_5cyc_4S_4Z : SchedWriteRes<[Ampere1UnitS, Ampere1UnitS,
+                                             Ampere1UnitS, Ampere1UnitS,
+                                             Ampere1UnitZ, Ampere1UnitZ,
+                                             Ampere1UnitZ, Ampere1UnitZ]> {
+  let Latency = 5;
+  let NumMicroOps = 8;
+}
+
+def Ampere1Write_5cyc_2XY_2S_2Z : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitS, Ampere1UnitS,
+                                                 Ampere1UnitZ, Ampere1UnitZ]> {
+  let Latency = 5;
+  let NumMicroOps = 6;
+}
+
+def Ampere1Write_6cyc_2XY_2S_2Z : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitS, Ampere1UnitS,
+                                                 Ampere1UnitZ, Ampere1UnitZ]> {
+  let Latency = 6;
+  let NumMicroOps = 6;
+}
+
+def Ampere1Write_6cyc_3XY_3S_3Z : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitS, Ampere1UnitS, Ampere1UnitS,
+                                                 Ampere1UnitZ, Ampere1UnitZ, Ampere1UnitZ]> {
+  let Latency = 6;
+  let NumMicroOps = 9;
+}
+
+def Ampere1Write_6cyc_1AB_1L : SchedWriteRes<[Ampere1UnitAB, Ampere1UnitL]> {
+  let Latency = 6;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_6cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 6;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_6cyc_2XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 6;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_6cyc_3XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 6;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_6cyc_3L : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL, Ampere1UnitL]> {
+  let Latency = 6;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_6cyc_4L : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL,
+                                          Ampere1UnitL, Ampere1UnitL]> {
+  let Latency = 6;
+  let NumMicroOps = 4;
+}
+
+def Ampere1Write_6cyc_1XY_1Z : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitZ]> {
+  let Latency = 6;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_7cyc_1BS : SchedWriteRes<[Ampere1UnitBS]> {
+  let Latency = 7;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_7cyc_1BS_1XY : SchedWriteRes<[Ampere1UnitBS, Ampere1UnitXY]> {
+  let Latency = 7;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_7cyc_1L_1XY : SchedWriteRes<[Ampere1UnitL, Ampere1UnitXY]> {
+  let Latency = 7;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_7cyc_2L_2XY : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL,
+                                              Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 7;
+  let NumMicroOps = 4;
+}
+
+def Ampere1Write_7cyc_2XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 7;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_7cyc_4XY_4S_4Z : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitS, Ampere1UnitS,
+                                                 Ampere1UnitS, Ampere1UnitS,
+                                                 Ampere1UnitZ, Ampere1UnitZ,
+                                                 Ampere1UnitZ, Ampere1UnitZ]> {
+  let Latency = 7;
+  let NumMicroOps = 12;
+}
+
+def Ampere1Write_8cyc_1BS_1A : SchedWriteRes<[Ampere1UnitBS, Ampere1UnitA]> {
+  let Latency = 8;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_8cyc_1BS_2A : SchedWriteRes<[Ampere1UnitBS, Ampere1UnitA,
+                                                             Ampere1UnitA]> {
+  let Latency = 8;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_8cyc_2XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 8;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_8cyc_4XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY,
+                                           Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 8;
+  let NumMicroOps = 4;
+}
+
+def Ampere1Write_8cyc_3L_3XY : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL, Ampere1UnitL,
+                                              Ampere1UnitXY, Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 8;
+  let NumMicroOps = 6;
+}
+
+def Ampere1Write_8cyc_4L_4XY : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL,
+                                              Ampere1UnitL, Ampere1UnitL,
+                                              Ampere1UnitXY, Ampere1UnitXY,
+                                              Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 8;
+  let NumMicroOps = 8;
+}
+
+def Ampere1Write_9cyc_3L_3XY : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL, Ampere1UnitL,
+                                              Ampere1UnitXY, Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 9;
+  let NumMicroOps = 6;
+}
+
+def Ampere1Write_9cyc_4L_4XY : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL,
+                                              Ampere1UnitL, Ampere1UnitL,
+                                              Ampere1UnitXY, Ampere1UnitXY,
+                                              Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 9;
+  let NumMicroOps = 8;
+}
+
+def Ampere1Write_9cyc_3XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 9;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_9cyc_2L_3XY : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL,
+                                              Ampere1UnitXY, Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 9;
+  let NumMicroOps = 5;
+}
+
+def Ampere1Write_9cyc_6XY_4S_4Z : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitS, Ampere1UnitS,
+                                                 Ampere1UnitS, Ampere1UnitS,
+                                                 Ampere1UnitZ, Ampere1UnitZ,
+                                                 Ampere1UnitZ, Ampere1UnitZ]> {
+  let Latency = 9;
+  let NumMicroOps = 14;
+}
+
+def Ampere1Write_9cyc_8XY_4S_4Z : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitXY, Ampere1UnitXY,
+                                                 Ampere1UnitS, Ampere1UnitS,
+                                                 Ampere1UnitS, Ampere1UnitS,
+                                                 Ampere1UnitZ, Ampere1UnitZ,
+                                                 Ampere1UnitZ, Ampere1UnitZ]> {
+  let Latency = 9;
+  let NumMicroOps = 16;
+}
+
+def Ampere1Write_10cyc_2XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 10;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_10cyc_1XY_1Z : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitZ]> {
+  let Latency = 10;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_10cyc_1X_1Z : SchedWriteRes<[Ampere1UnitX, Ampere1UnitZ]> {
+  let Latency = 10;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_10cyc_3L_3XY : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL, Ampere1UnitL,
+                                               Ampere1UnitXY, Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 10;
+  let NumMicroOps = 6;
+}
+
+def Ampere1Write_10cyc_1A_1BS_1X : SchedWriteRes<[Ampere1UnitA, Ampere1UnitBS, Ampere1UnitX]> {
+  let Latency = 10;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_10cyc_1A_1BS_1XY : SchedWriteRes<[Ampere1UnitA, Ampere1UnitBS, Ampere1UnitXY]> {
+  let Latency = 10;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_11cyc_1BS_1L : SchedWriteRes<[Ampere1UnitBS, Ampere1UnitL]> {
+  let Latency = 11;
+  let NumMicroOps = 2;
+}
+
+def Ampere1Write_11cyc_1A_1BS_1X : SchedWriteRes<[Ampere1UnitA, Ampere1UnitBS, Ampere1UnitX]> {
+  let Latency = 11;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_11cyc_1A_1BS_1XY : SchedWriteRes<[Ampere1UnitA, Ampere1UnitBS, Ampere1UnitXY]> {
+  let Latency = 11;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_11cyc_4L_8XY : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL,
+                                               Ampere1UnitL, Ampere1UnitL,
+                                               Ampere1UnitXY, Ampere1UnitXY,
+                                               Ampere1UnitXY, Ampere1UnitXY,
+                                               Ampere1UnitXY, Ampere1UnitXY,
+                                               Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 11;
+  let NumMicroOps = 12;
+}
+
+def Ampere1Write_12cyc_4L_8XY : SchedWriteRes<[Ampere1UnitL, Ampere1UnitL,
+                                               Ampere1UnitL, Ampere1UnitL,
+                                               Ampere1UnitXY, Ampere1UnitXY,
+                                               Ampere1UnitXY, Ampere1UnitXY,
+                                               Ampere1UnitXY, Ampere1UnitXY,
+                                               Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 12;
+  let NumMicroOps = 12;
+}
+
+def Ampere1Write_12cyc_3XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 12;
+  let NumMicroOps = 3;
+}
+
+def Ampere1Write_12cyc_4XY : SchedWriteRes<[Ampere1UnitXY, Ampere1UnitXY,
+                                            Ampere1UnitXY, Ampere1UnitXY]> {
+  let Latency = 12;
+  let NumMicroOps = 4;
+}
+
+def Ampere1Write_18cyc_1BS : SchedWriteRes<[Ampere1UnitBS]> {
+  let Latency = 18;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_19cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 19;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_25cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 25;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_32cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 32;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_34cyc_1BS : SchedWriteRes<[Ampere1UnitBS]> {
+  let Latency = 34;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_34cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 34;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_39cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 39;
+  let NumMicroOps = 1;
+}
+
+def Ampere1Write_62cyc_1XY : SchedWriteRes<[Ampere1UnitXY]> {
+  let Latency = 62;
+  let NumMicroOps = 1;
+}
+
+// For basic arithmetic, we have more flexibility for short shifts (LSL shift <= 4),
+// which are a single uop, and for extended registers, which have full flexibility
+// across Unit A or B for both uops.
+def Ampere1Write_Arith : SchedWriteVariant<[
+                                SchedVar<RegExtendedPred, [Ampere1Write_2cyc_2AB]>,
+                                SchedVar<AmpereCheapLSL,  [Ampere1Write_1cyc_1AB]>,
+                                SchedVar<NoSchedPred,     [Ampere1Write_2cyc_1B_1AB]>]>;
+
+def Ampere1Write_ArithFlagsetting : SchedWriteVariant<[
+                                SchedVar<RegExtendedPred, [Ampere1Write_2cyc_1AB_1A]>,
+                                SchedVar<AmpereCheapLSL,  [Ampere1Write_1cyc_1A]>,
+                                SchedVar<NoSchedPred,     [Ampere1Write_2cyc_1B_1A]>]>;
+
+//===----------------------------------------------------------------------===//
+// Map the target-defined scheduler read/write resources and latencies for Ampere-1.
+// This provides a coarse model, which is then specialised below.
+
+def : WriteRes<WriteImm,   [Ampere1UnitAB]>;  // MOVN, MOVZ
+def : WriteRes<WriteI,     [Ampere1UnitAB]>;  // ALU
+def : WriteRes<WriteISReg, [Ampere1UnitB, Ampere1UnitA]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}  // ALU of Shifted-Reg
+def : WriteRes<WriteIEReg, [Ampere1UnitAB, Ampere1UnitA]> {
+  let Latency = 2;
+  let NumMicroOps = 2;
+}  // ALU of Extended-Reg
+def : WriteRes<WriteExtr,  [Ampere1UnitB]>;  // EXTR shifts a reg pair
+def : WriteRes<WriteIS,    [Ampere1UnitB]>;  // Shift/Scale
+def : WriteRes<WriteID32,  [Ampere1UnitBS]> {
+  let Latency = 18;
+}  // 32-bit Divide
+def : WriteRes<WriteID64,  [Ampere1UnitBS]> {
+  let Latency = 34;
+}  // 64-bit Divide
+def : WriteRes<WriteIM32,  [Ampere1UnitBS]> {
+  let Latency = 3;
+}  // 32-bit Multiply
+def : WriteRes<WriteIM64,  [Ampere1UnitBS]> {
+  let Latency = 3;
+}  // 32-bit Multiply
+def : WriteRes<WriteBr,    [Ampere1UnitA]>;
+def : WriteRes<WriteBrReg, [Ampere1UnitA, Ampere1UnitA]>;
+def : WriteRes<WriteLD,    [Ampere1UnitL]> {
+  let Latency = 4;
+}  // Load from base addr plus immediate offset
+def : WriteRes<WriteST,    [Ampere1UnitS]> {
+  let Latency = 1;
+}  // Store to base addr plus immediate offset
+def : WriteRes<WriteSTP,   [Ampere1UnitS, Ampere1UnitS]> {
+  let Latency = 1;
+  let NumMicroOps = 2;
+}  // Store a register pair.
+def : WriteRes<WriteAdr,   [Ampere1UnitAB]>;
+def : WriteRes<WriteLDIdx, [Ampere1UnitAB, Ampere1UnitS]> {
+  let Latency = 5;
+  let NumMicroOps = 2;
+}  // Load from a register index (maybe scaled).
+def : WriteRes<WriteSTIdx, [Ampere1UnitS, Ampere1UnitS]> {
+  let Latency = 1;
+  let NumMicroOps = 2;
+}  // Store to a register index (maybe scaled).
+def : WriteRes<WriteF,  [Ampere1UnitXY]> {
+  let Latency = 2;
+}  // General floating-point ops.
+def : WriteRes<WriteFCmp,  [Ampere1UnitX]> {
+  let Latency = 5;
+}  // Floating-point compare.
+def : WriteRes<WriteFCvt,  [Ampere1UnitXY]> {
+  let Latency = 6;
+}  // Float conversion.
+def : WriteRes<WriteFCopy, [Ampere1UnitXY]> {
+}  // Float-int register copy.
+def : WriteRes<WriteFImm,  [Ampere1UnitXY]> {
+  let Latency = 2;
+}  // Float-int register copy.
+def : WriteRes<WriteFMul,  [Ampere1UnitXY]> {
+  let Latency = 5;
+}  // Floating-point multiply.
+def : WriteRes<WriteFDiv,  [Ampere1UnitXY]> {
+  let Latency = 34;
+}  // Floating-point division.
+def : WriteRes<WriteVd,    [Ampere1UnitXY]> {
+  let Latency = 3;
+}  // 64bit Vector D ops.
+def : WriteRes<WriteVq,    [Ampere1UnitXY]> {
+  let Latency = 3;
+}  // 128bit Vector Q ops.
+def : WriteRes<WriteVLD,   [Ampere1UnitL, Ampere1UnitL]> {
+  let Latency = 5;
+}  // Vector loads.
+def : WriteRes<WriteVST,   [Ampere1UnitS, Ampere1UnitZ]> {
+  let Latency = 2;
+}  // Vector stores.
+
+def : WriteRes<WriteAtomic,  []> { let Unsupported = 1; }
+
+def : WriteRes<WriteSys,     []> { let Latency = 1; }
+def : WriteRes<WriteBarrier, []> { let Latency = 1; }
+def : WriteRes<WriteHint,    []> { let Latency = 1; }
+
+def : WriteRes<WriteLDHi,    []> {
+  let Latency = 4;
+}  // The second register of a load-pair: LDP,LDPSW,LDNP,LDXP,LDAXP
+
+// Forwarding logic.
+def : ReadAdvance<ReadI,       0>;
+def : ReadAdvance<ReadISReg,   0>;
+def : ReadAdvance<ReadIEReg,   0>;
+def : ReadAdvance<ReadIM,      0>;
+def : ReadAdvance<ReadIMA,     1, [WriteIM32, WriteIM64]>;
+def : ReadAdvance<ReadID,      0>;
+def : ReadAdvance<ReadExtrHi,  0>;
+def : ReadAdvance<ReadST,      0>;
+def : ReadAdvance<ReadAdrBase, 0>;
+def : ReadAdvance<ReadVLD,     0>;
+
+//===----------------------------------------------------------------------===//
+// Specialising the scheduling model further for Ampere-1.
+
+def : InstRW<[Ampere1Write_1cyc_1AB], (instrs COPY)>;
+
+// Branch instructions
+def : InstRW<[Ampere1Write_1cyc_1A], (instrs Bcc, BL, RET)>;
+def : InstRW<[Ampere1Write_1cyc_1A],
+        (instrs CBZW, CBZX, CBNZW, CBNZX, TBZW, TBZX, TBNZW, TBNZX)>;
+def : InstRW<[Ampere1Write_1cyc_2A], (instrs BLR)>;
+
+// Cryptography instructions
+// -- AES encryption/decryption
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^AES[DE]")>;
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^AESI?MC")>;
+// -- Polynomial multiplication
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^PMUL", "^PMULL")>;
+// -- SHA-256 hash
+def : InstRW<[Ampere1Write_4cyc_1X], (instregex "^SHA256(H|H2)")>;
+// -- SHA-256 schedule update
+def : InstRW<[Ampere1Write_4cyc_1Y], (instregex "^SHA256SU[01]")>;
+// -- SHA-3 instructions
+def : InstRW<[Ampere1Write_2cyc_1XY],
+        (instregex "^BCAX", "^EOR3", "^RAX1", "^XAR")>;
+// -- SHA-512 hash
+def : InstRW<[Ampere1Write_4cyc_1X], (instregex "^SHA512(H|H2)")>;
+// -- SHA-512 schedule update
+def : InstRW<[Ampere1Write_4cyc_1Y], (instregex "^SHA512SU[01]")>;
+// -- SHA1 choose/majority/parity
+def : InstRW<[Ampere1Write_4cyc_1X], (instregex "^SHA1[CMP]")>;
+// -- SHA1 hash/schedule update
+def : InstRW<[Ampere1Write_2cyc_1Y], (instregex "^SHA1SU[01]")>;
+def : InstRW<[Ampere1Write_2cyc_1Y], (instregex "^SHA1H")>;
+
+// FP and vector load instructions
+// -- Load 1-element structure to one/all lanes
+// ---- all lanes
+def : InstRW<[Ampere1Write_7cyc_1L_1XY],
+        (instregex "^LD1Rv(8b|4h|2s|16b|8h|4s|2d)")>;
+// ---- one lane
+def : InstRW<[Ampere1Write_7cyc_1L_1XY],
+        (instregex "^LD1i(8|16|32|64)")>;
+// -- Load 1-element structure to one/all lanes, 1D size
+def : InstRW<[Ampere1Write_5cyc_1L],
+        (instregex "^LD1Rv1d")>;
+// -- Load 1-element structures to 1 register
+def : InstRW<[Ampere1Write_5cyc_1L],
+        (instregex "^LD1Onev(8b|4h|2s|1d|16b|8h|4s|2d)")>;
+// -- Load 1-element structures to 2 registers
+def : InstRW<[Ampere1Write_5cyc_2L],
+        (instregex "^LD1Twov(8b|4h|2s|1d|16b|8h|4s|2d)")>;
+// -- Load 1-element structures to 3 registers
+def : InstRW<[Ampere1Write_6cyc_3L],
+        (instregex "^LD1Threev(8b|4h|2s|1d|16b|8h|4s|2d)")>;
+// -- Load 1-element structures to 4 registers
+def : InstRW<[Ampere1Write_6cyc_4L],
+        (instregex "^LD1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)")>;
+// -- Load 2-element structure to all lanes of 2 registers, 1D size
+def : InstRW<[Ampere1Write_5cyc_2L],
+        (instregex "^LD2Rv1d")>;
+// -- Load 2-element structure to all lanes of 2 registers, other sizes
+def : InstRW<[Ampere1Write_7cyc_2L_2XY],
+        (instregex "^LD2Rv(8b|4h|2s|16b|8h|4s|2d)")>;
+// -- Load 2-element structure to one lane of 2 registers
+def : InstRW<[Ampere1Write_7cyc_2L_2XY],
+        (instregex "^LD2i(8|16|32|64)")>;
+// -- Load 2-element structures to 2 registers, 16B/8H/4S/2D size
+def : InstRW<[Ampere1Write_7cyc_2L_2XY],
+        (instregex "^LD2Twov(16b|8h|4s|2d)")>;
+// -- Load 2-element structures to 2 registers, 8B/4H/2S size
+def : InstRW<[Ampere1Write_9cyc_2L_3XY],
+        (instregex "^LD2Twov(8b|4h|2s)")>;
+// -- Load 3-element structure to all lanes of 3 registers, 1D size
+def : InstRW<[Ampere1Write_6cyc_3L],
+        (instregex "^LD3Rv1d")>;
+// -- Load 3-element structure to all lanes of 3 registers, other sizes
+def : InstRW<[Ampere1Write_8cyc_3L_3XY],
+        (instregex "^LD3Rv(8b|4h|2s|16b|8h|4s|2d)")>;
+// -- Load 3-element structure to one lane of 3 registers
+def : InstRW<[Ampere1Write_8cyc_3L_3XY],
+        (instregex "^LD3i(8|16|32|64)")>;
+// -- Load 3-element structures to 3 registers, 16B/8H/4S sizes
+def : InstRW<[Ampere1Write_9cyc_3L_3XY],
+        (instregex "^LD3Threev(16b|8h|4s)")>;
+// -- Load 3-element structures to 3 registers, 2D size
+def : InstRW<[Ampere1Write_8cyc_3L_3XY],
+        (instregex "^LD3Threev2d")>;
+// -- Load 3-element structures to 3 registers, 8B/4H/2S sizes
+def : InstRW<[Ampere1Write_10cyc_3L_3XY],
+        (instregex "^LD3Threev(8b|4h|2s)")>;
+// -- Load 4-element structure to all lanes of 4 registers, 1D size
+def : InstRW<[Ampere1Write_6cyc_4L],
+        (instregex "^LD4Rv1d")>;
+// -- Load 4-element structure to all lanes of 4 registers, other sizes
+def : InstRW<[Ampere1Write_8cyc_4L_4XY],
+        (instregex "^LD4Rv(8b|4h|2s|16b|8h|4s|2d)")>;
+// -- Load 4-element structure to one lane of 4 registers
+def : InstRW<[Ampere1Write_6cyc_4L],
+        (instregex "^LD4i(8|16|32|64)")>;
+// -- Load 4-element structures to 4 registers, 2D size
+def : InstRW<[Ampere1Write_9cyc_4L_4XY],
+        (instregex "^LD4Fourv2d")>;
+// -- Load 4-element structures to 4 registers, 2S size
+def : InstRW<[Ampere1Write_12cyc_4L_8XY],
+        (instregex "^LD4Fourv2s")>;
+// -- Load 4-element structures to 4 registers, other sizes
+def : InstRW<[Ampere1Write_11cyc_4L_8XY],
+        (instregex "^LD4Fourv(8b|4h|16b|8h|4s)")>;
+// -- Load pair, Q-form
+def : InstRW<[Ampere1Write_5cyc_2L], (instregex "LDN?PQ")>;
+// -- Load pair, S/D-form
+def : InstRW<[Ampere1Write_5cyc_1L_1BS], (instregex "LDN?P(S|D)")>;
+// -- Load register
+def : InstRW<[Ampere1Write_5cyc_1L], (instregex "LDU?R[BHSDQ]i")>;
+// -- Load register, sign-extended register
+def : InstRW<[Ampere1Write_6cyc_1AB_1L], (instregex "LDR[BHSDQ]ro(W|X)")>;
+
+// FP and vector store instructions
+// -- Store 1-element structure from one lane of 1 register
+def : InstRW<[Ampere1Write_4cyc_1XY_1S_1Z],
+        (instregex "^ST1i(8|16|32|64)")>;
+// -- Store 1-element structures from 1 register
+def : InstRW<[Ampere1Write_2cyc_1S_1Z],
+        (instregex "^ST1Onev(8b|4h|2s|1d|16b|8h|4s|2d)")>;
+// -- Store 1-element structures from 2 registers
+def : InstRW<[Ampere1Write_3cyc_2S_2Z],
+        (instregex "^ST1Twov(8b|4h|2s|1d|16b|8h|4s|2d)")>;
+// -- Store 1-element structures from 3 registers
+def : InstRW<[Ampere1Write_4cyc_3S_3Z],
+        (instregex "^ST1Threev(8b|4h|2s|1d|16b|8h|4s|2d)")>;
+// -- Store 1-element structures from 4 registers
+def : InstRW<[Ampere1Write_5cyc_4S_4Z],
+        (instregex "^ST1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)")>;
+// -- Store 2-element structure from one lane of 2 registers
+def : InstRW<[Ampere1Write_5cyc_2XY_2S_2Z],
+        (instregex "^ST2i(8|16|32|64)")>;
+// -- Store 2-element structures from 2 registers, 16B/8H/4S/2D sizes
+def : InstRW<[Ampere1Write_5cyc_2XY_2S_2Z],
+        (instregex "^ST2Twov(16b|8h|4s|2d)")>;
+// -- Store 2-element structures from 2 registers, 8B/4H/2S sizes
+def : InstRW<[Ampere1Write_6cyc_2XY_2S_2Z],
+        (instregex "^ST2Twov(8b|4h|2s)")>;
+// -- Store 3-element structure from one lane of 3 registers
+def : InstRW<[Ampere1Write_6cyc_3XY_3S_3Z],
+        (instregex "^ST3i(8|16|32|64)")>;
+// -- Store 3-element structures from 3 registers
+def : InstRW<[Ampere1Write_6cyc_3XY_3S_3Z],
+        (instregex "^ST3Threev(8b|4h|2s|1d|16b|8h|4s|2d)")>;
+// -- Store 4-element structure from one lane of 4 registers
+def : InstRW<[Ampere1Write_7cyc_4XY_4S_4Z],
+        (instregex "^ST4i(8|16|32|64)")>;
+// -- Store 4-element structures from 4 registers, 16B/8H/4S sizes
+def : InstRW<[Ampere1Write_9cyc_8XY_4S_4Z],
+        (instregex "^ST4Fourv(16b|8h|4s)")>;
+// -- Store 4-element structures from 4 registers, 2D sizes
+def : InstRW<[Ampere1Write_7cyc_4XY_4S_4Z],
+        (instregex "^ST4Fourv2d")>;
+// -- Store 4-element structures from 4 registers, 8B/4H/2S sizes
+def : InstRW<[Ampere1Write_9cyc_6XY_4S_4Z],
+        (instregex "^ST4Fourv(8b|4h|2s)")>;
+// -- Store pair, Q-form
+def : InstRW<[Ampere1Write_3cyc_2S_2Z], (instregex "^STN?PQ")>;
+// -- Store pair, S/D-form
+def : InstRW<[Ampere1Write_3cyc_1S_2Z],	(instregex "^STN?P[SD]")>;
+// -- Store register
+def : InstRW<[Ampere1Write_2cyc_1S_1Z],	(instregex "^STU?R[BHSDQ](ui|i)")>;
+// -- Store register, sign-extended register offset
+def : InstRW<[Ampere1Write_2cyc_1AB_1S_1Z], (instregex "^STR[BHSDQ]ro[XW]")>;
+
+// FP data processing, bfloat16 format
+def : InstRW<[Ampere1Write_5cyc_1XY], (instrs BFCVT)>;
+def : InstRW<[Ampere1Write_7cyc_2XY], (instrs BFCVTN, BFCVTN2)>;
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^BFDOTv", "^BF16DOT")>;
+def : InstRW<[Ampere1Write_4cyc_2XY], (instrs BFMMLA)>;
+def : InstRW<[Ampere1Write_5cyc_1XY], (instregex "^BFMLAL")>;
+
+// FP data processing, scalar/vector, half precision
+def : InstRW<[Ampere1Write_4cyc_1XY], (instregex "^F(ABD|ABS)v.[fi]16")>;
+def : InstRW<[Ampere1Write_4cyc_1XY],
+        (instregex "^F(ADD|ADDP|CADD|NEG|NMUL|SUB)v.[fi]16")>;
+def : InstRW<[Ampere1Write_4cyc_1XY],
+        (instregex "^F(AC|CM)(EQ|GE|GT|LE|LT)v.[fi]16")>;
+def : InstRW<[Ampere1Write_4cyc_1XY],
+        (instregex "^F(AC|CM)(EQ|GE|GT|LE|LT)16")>;
+def : InstRW<[Ampere1Write_4cyc_1X],
+        (instregex "^FCMPE?H")>;
+def : InstRW<[Ampere1Write_10cyc_1A_1BS_1X],
+        (instregex "^FCCMPE?H")>;
+def : InstRW<[Ampere1Write_10cyc_1A_1BS_1XY],
+        (instregex "^FCSELH")>;
+def : InstRW<[Ampere1Write_4cyc_1XY], (instregex "^FCVT[AMNPZ][SU]v.[if]16")>;
+def : InstRW<[Ampere1Write_4cyc_1XY], (instregex "^[SU]CVTFv.[fi]16")>;
+def : InstRW<[Ampere1Write_25cyc_1XY], (instregex "^FDIVv.[if]16", "FDIVH")>;
+def : InstRW<[Ampere1Write_4cyc_1XY], (instregex "^F(MAX|MIN)(NM)?P?v.[if]16")>;
+def : InstRW<[Ampere1Write_8cyc_2XY], (instregex "^F(MAX|MIN)(NM)?Vv4[if]16")>;
+def : InstRW<[Ampere1Write_12cyc_3XY], (instregex "^F(MAX|MIN)(NM)?Vv8[if]16")>;
+def : InstRW<[Ampere1Write_4cyc_1XY], (instregex "^FMULX?v.[if]16")>;
+def : InstRW<[Ampere1Write_4cyc_1XY], (instrs FMULX16)>;
+def : InstRW<[Ampere1Write_4cyc_1XY], (instregex "^FN?M(ADD|SUB)[H]rrr")>;
+def : InstRW<[Ampere1Write_4cyc_1XY], (instregex "^FML[AS]v.[if]16")>;
+def : InstRW<[Ampere1Write_4cyc_1XY], (instregex "^FRECPXv.[if]16")>;
+def : InstRW<[Ampere1Write_4cyc_1XY], (instregex "^F(RECP|RSQRT)S16")>;
+def : InstRW<[Ampere1Write_4cyc_1XY], (instregex "^FRINT[AIMNPXZ]v.[if]16")>;
+def : InstRW<[Ampere1Write_39cyc_1XY], (instregex "^FSQRTv.f16", "^FSQRTHr")>;
+
+// FP data processing, scalar/vector, single/double precision
+def : InstRW<[Ampere1Write_5cyc_1XY], (instregex "^F(ABD|ABS)v.[fi](32|64)")>;
+def : InstRW<[Ampere1Write_5cyc_1XY],
+        (instregex "^F(ADD|ADDP|CADD|NEG|NMUL|SUB)v.[fi](32|64)")>;
+def : InstRW<[Ampere1Write_5cyc_1XY],
+        (instregex "^F(AC|CM)(EQ|GE|GT|LE|LT)v.[fi](32|64)")>;
+def : InstRW<[Ampere1Write_5cyc_1XY],
+        (instregex "^F(AC|CM)(EQ|GE|GT|LE|LT)(32|64)")>;
+def : InstRW<[Ampere1Write_5cyc_1X],
+        (instregex "^FCMPE?(S|D)")>;
+def : InstRW<[Ampere1Write_11cyc_1A_1BS_1X],
+        (instregex "^FCCMPE?(S|D)")>;
+def : InstRW<[Ampere1Write_11cyc_1A_1BS_1XY],
+        (instregex "^FCSEL(S|D)")>;
+def : InstRW<[Ampere1Write_6cyc_1XY], (instregex "^FCVT[AMNPZ][SU]v.[if](32|64)")>;
+def : InstRW<[Ampere1Write_6cyc_1XY], (instregex "^[SU]CVTFv.[fi](32|64)")>;
+def : InstRW<[Ampere1Write_34cyc_1XY], (instregex "^FDIVv.[if](64)", "FDIVD")>;
+def : InstRW<[Ampere1Write_19cyc_1XY], (instregex "^FDIVv.[if](32)", "FDIVS")>;
+def : InstRW<[Ampere1Write_5cyc_1XY], (instregex "^F(MAX|MIN)(NM)?P?v.[if](32|64)")>;
+def : InstRW<[Ampere1Write_10cyc_2XY], (instregex "^F(MAX|MIN)(NM)?Vv.[if](32|64)")>;
+def : InstRW<[Ampere1Write_6cyc_1XY], (instregex "^FMULX?v.[if](32|64)")>;
+def : InstRW<[Ampere1Write_6cyc_1XY], (instrs FMULX32, FMULX64)>;
+def : InstRW<[Ampere1Write_5cyc_1XY], (instregex "^FN?M(ADD|SUB)[SD]rrr")>;
+def : InstRW<[Ampere1Write_5cyc_1XY], (instregex "^FML[AS]v.[if](32|64)")>;
+def : InstRW<[Ampere1Write_5cyc_1XY], (instregex "^FRECPXv.[if](32|64)")>;
+def : InstRW<[Ampere1Write_6cyc_1XY], (instregex "^F(RECP|RSQRT)S(32|64)")>;
+def : InstRW<[Ampere1Write_6cyc_1XY], (instregex "^FRINT[AIMNPXZ]v.[if](32|64)")>;
+def : InstRW<[Ampere1Write_6cyc_1XY], (instregex "^FRINT(32|64)")>;
+def : InstRW<[Ampere1Write_62cyc_1XY], (instregex "^FSQRTv.f64", "^FSQRTDr")>;
+def : InstRW<[Ampere1Write_32cyc_1XY], (instregex "^FSQRTv.f32", "^FSQRTSr")>;
+
+// FP miscellaneous instructions
+def : InstRW<[Ampere1Write_10cyc_1XY_1Z], (instregex "^FCVT[AMNPZ][SU][SU][XW][HSD]r")>;
+def : InstRW<[Ampere1Write_5cyc_1XY], (instregex "^FCVT[HSD]Hr")>;
+def : InstRW<[Ampere1Write_6cyc_1XY], (instregex "^FCVT[HSD][SD]r")>;
+def : InstRW<[Ampere1Write_6cyc_1XY], (instregex "^FCVTLv")>;
+def : InstRW<[Ampere1Write_8cyc_2XY], (instregex "^FCVT(N|XN)v")>;
+def : InstRW<[Ampere1Write_10cyc_1X_1Z], (instrs FJCVTZS)>;
+def : InstRW<[Ampere1Write_5cyc_1BS], (instregex "^FMOV[HSD][WX]r")>;
+def : InstRW<[Ampere1Write_7cyc_1BS_1XY], (instregex "^FMOVDXHighr")>;
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^FMOV[HSD][ri]")>;
+def : InstRW<[Ampere1Write_6cyc_1XY_1Z], (instregex "^FMOVXDHighr")>;
+def : InstRW<[Ampere1Write_4cyc_1Z], (instregex "^FMOV[WX][HSD]r")>;
+
+// Integer arithmetic and logical instructions
+def : InstRW<[Ampere1Write_1cyc_1A],
+        (instregex "ADC(W|X)r", "SBC(W|X)r")>;
+def : InstRW<[Ampere1Write_Arith],
+        (instregex "(ADD|AND|BIC|EON|EOR|ORN|ORR|SUB)(W|X)r")>;
+def : InstRW<[Ampere1Write_ArithFlagsetting],
+        (instregex "(ADD|AND|BIC|SUB)S(W|X)r")>;
+def : InstRW<[Ampere1Write_1cyc_1A],
+        (instregex "(ADC|SBC)S(W|X)r")>;
+def : InstRW<[Ampere1Write_1cyc_1A], (instrs RMIF)>;
+def : InstRW<[Ampere1Write_1cyc_1A],
+        (instregex "(CCMN|CCMP)(X|W)")>;
+def : InstRW<[Ampere1Write_1cyc_1A],
+        (instregex "(CSEL|CSINC|CSINV|CSNEG)(X|W)")>;
+def : InstRW<[Ampere1Write_18cyc_1BS], (instrs SDIVWr, UDIVWr)>;
+def : InstRW<[Ampere1Write_34cyc_1BS], (instrs SDIVXr, UDIVXr)>;
+def : InstRW<[Ampere1Write_3cyc_1BS],
+        (instregex "(S|U)MULHr")>;
+def : InstRW<[Ampere1Write_4cyc_1BS],
+        (instregex "(S|U)?M(ADD|SUB)L?r")>;
+
+// Integer load instructions
+def : InstRW<[Ampere1Write_4cyc_2L],
+        (instregex "(LDNP|LDP|LDPSW)(X|W)")>;
+def : InstRW<[Ampere1Write_4cyc_1L],
+        (instregex "LDR(B|D|H|Q|S)ui")>;
+def : InstRW<[Ampere1Write_4cyc_1L],
+        (instregex "LDR(D|Q|W|X)l")>;
+def : InstRW<[Ampere1Write_4cyc_1L],
+        (instregex "LDTR(B|H|W|X)i")>;
+def : InstRW<[Ampere1Write_4cyc_1L],
+        (instregex "LDTRS(BW|BX|HW|HX|W)i")>;
+def : InstRW<[Ampere1Write_4cyc_1L],
+        (instregex "LDUR(BB|HH|X|W)i")>;
+def : InstRW<[Ampere1Write_4cyc_1L],
+        (instregex "LDURS(BW|BX|HW|HX|W)i")>;
+def : InstRW<[Ampere1Write_5cyc_1AB_1L],
+        (instregex "LDR(HH|SHW|SHX|W|X)ro(W|X)")>;
+def : InstRW<[Ampere1Write_1cyc_1L],
+        (instrs PRFMl, PRFUMi, PRFUMi)>;
+def : InstRW<[Ampere1Write_2cyc_1AB_1L],
+        (instrs PRFMroW, PRFMroX)>;
+
+// Integer miscellaneous instructions
+def : InstRW<[Ampere1Write_1cyc_1A],  (instrs ADR, ADRP)>;
+def : InstRW<[Ampere1Write_1cyc_1B],  (instregex "EXTR(W|X)")>;
+def : InstRW<[Ampere1Write_1cyc_1B],  (instregex "(S|U)?BFM(W|X)")>;
+def : InstRW<[Ampere1Write_3cyc_1BS], (instregex "^CRC32C?[BHWX]")>;
+def : InstRW<[Ampere1Write_1cyc_1B],  (instregex "CLS(W|X)")>;
+def : InstRW<[Ampere1Write_1cyc_1A],  (instrs SETF8, SETF16)>;
+def : InstRW<[Ampere1Write_1cyc_1AB],
+        (instrs MOVKWi, MOVKXi, MOVNWi, MOVNXi, MOVZWi, MOVZXi)>;
+def : InstRW<[Ampere1Write_1cyc_1B],
+        (instregex "(RBIT|REV|REV16)(W|X)r", "REV32Xr")>;
+def : InstRW<[Ampere1Write_1cyc_1B],
+        (instregex "(ASR|LSL|LSR|ROR)V(W|X)r")>;
+
+// Integer store instructions
+def : InstRW<[Ampere1Write_1cyc_2S],  (instregex "STNP(X|W)i")>;
+def : InstRW<[Ampere1Write_2cyc_1B_1S],
+        (instrs STPWi, STPXi)>;
+def : InstRW<[Ampere1Write_3cyc_1B_1S_1AB],
+        (instregex "STP(W|X)(pre|post)")>;
+def : InstRW<[Ampere1Write_1cyc_1S],
+        (instrs STTRBi, STTRHi, STTRWi, STTRXi)>;
+def : InstRW<[Ampere1Write_1cyc_1S],
+        (instregex "STUR(BB|HH|X|W)i",
+                   "STR(X|W)ui",
+                   "STUR(BB|HH|X|W)i")>;
+def : InstRW<[Ampere1Write_1cyc_2S], (instrs STRWroX, STRXroX)>;
+def : InstRW<[Ampere1Write_2cyc_1AB_2S], (instrs STRWroW, STRXroW)>;
+
+// Pointer authentication
+//def : InstRW<[Ampere1Write_7cyc_1BS],
+//	(instrs AUTIAZ, AUTIBZ, AUTIASP, AUTIBSP, AUTIA1716, AUTIB1716)>;
+def : InstRW<[Ampere1Write_8cyc_1BS_1A],
+        (instregex "BRA(A|AZ|B|BZ)", "RETA(A|B)", "ERETA(A|B)")>;
+def : InstRW<[Ampere1Write_8cyc_1BS_2A],
+        (instrs BLRAA, BLRAAZ, BLRAB, BLRABZ)>;
+//def : InstRW<[Ampere1Write_7cyc_1BS],
+//	(instrs PACIAZ, PACIBZ, PACIASP, PACIBSP, PACIA1716, PACIB1716)>;
+def : InstRW<[Ampere1Write_11cyc_1BS_1L], (instregex "^LDRA(A|B)")>;
+def : InstRW<[Ampere1Write_7cyc_1BS], (instrs XPACD, XPACI)>;
+
+// Vector integer instructions
+// -- absolute difference
+def : InstRW<[Ampere1Write_3cyc_1XY],
+             (instregex "^SABAv", "^SABALv", "^SABDv", "^SABDLv",
+                        "^UABAv", "^UABALv", "^UABDv", "^UABDLv")>;
+// -- arithmetic
+def : InstRW<[Ampere1Write_3cyc_1XY],
+        (instregex "^ABSv", "^(ADD|SUB)v", "^SADDLv", "^SADDW", "SHADD",
+                   "SHSUB", "^SRHADD", "^URHADD", "SSUBL", "SSUBW",
+                   "^UADDLv", "^UADDW", "UHADD", "UHSUB", "USUBL", "USUBW")>;
+// -- arithmetic, horizontal, 16B
+def : InstRW<[Ampere1Write_12cyc_4XY],
+            (instregex "^ADDVv16i8v", "^SADDLVv16i8v", "^UADDLVv16i8v")>;
+def : InstRW<[Ampere1Write_12cyc_4XY],
+            (instregex "^[SU](MIN|MAX)Vv16i8v")>;
+// -- arithmetic, horizontal, 4H/4S
+def : InstRW<[Ampere1Write_6cyc_2XY],
+            (instregex "^[SU]?ADDL?V(v8i8|v4i16|v2i32)v")>;
+def : InstRW<[Ampere1Write_6cyc_2XY],
+            (instregex "^[SU](MIN|MAX)V(v4i16|v4i32)v")>;
+// -- arithmetic, horizontal, 8B/8H
+def : InstRW<[Ampere1Write_9cyc_3XY],
+            (instregex "^[SU]?ADDL?V(v8i16|v4i32)v")>;
+def : InstRW<[Ampere1Write_9cyc_3XY],
+            (instregex "^[SU](MIN|MAX)V(v8i8|v8i16)v")>;
+// -- arithmetic, narrowing
+def : InstRW<[Ampere1Write_5cyc_2XY], (instregex "(ADD|SUB)HNv.*")>;
+def : InstRW<[Ampere1Write_5cyc_2XY], (instregex "(RADD|RSUB)HNv.*")>;
+// -- arithmetic, pairwise
+def : InstRW<[Ampere1Write_3cyc_1XY],
+        (instregex "^ADDPv", "^SADALP", "^UADALP", "^SADDLPv", "^UADDLPv")>;
+// -- arithmetic, saturating
+def : InstRW<[Ampere1Write_3cyc_1XY],
+        (instregex "^SQADD", "^SQSUB", "^SUQADD", "^UQADD", "^UQSUB", "^USQADD")>;
+// -- bit count
+def : InstRW<[Ampere1Write_2cyc_1XY],
+        (instregex "^(CLS|CLZ|CNT)v")>;
+// -- compare
+def : InstRW<[Ampere1Write_3cyc_1XY],
+        (instregex "^CMEQv", "^CMGEv", "^CMGTv", "^CMLEv", "^CMLTv",
+                   "^CMHIv", "^CMHSv")>;
+// -- compare non-zero
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^CMTSTv")>;
+// -- dot product
+def : InstRW<[Ampere1Write_3cyc_1XY], (instregex "^(S|SU|U|US)DOTv")>;
+// -- fp reciprocal estimate
+def : InstRW<[Ampere1Write_5cyc_1XY], (instregex "^FRECPEv", "^FRSQRTEv")>;
+// -- integer reciprocal estimate
+def : InstRW<[Ampere1Write_5cyc_1XY], (instregex "^URECPEv", "^URSQRTEv")>;
+// -- logical
+def : InstRW<[Ampere1Write_2cyc_1XY],
+        (instregex "^ANDv", "^BICv", "^EORv", "^ORRv", "^ORNv", "^NOTv")>;
+// -- logical, narrowing
+def : InstRW<[Ampere1Write_5cyc_2XY],
+        (instregex "RSHRNv",
+                   "SHRNv", "SQSHRNv", "SQSHRUNv",
+                   "UQXTNv")>;
+// -- matrix multiply
+def : InstRW<[Ampere1Write_6cyc_2XY],
+        (instrs SMMLA, UMMLA, USMMLA)>;
+// -- max/min
+def : InstRW<[Ampere1Write_3cyc_1XY],
+        (instregex "^SMAXv", "^SMINv", "^UMAXv", "^UMINv")>;
+def : InstRW<[Ampere1Write_3cyc_1XY],
+        (instregex "^SMAXPv", "^SMINPv", "^UMAXPv", "^UMINPv")>;
+// -- move immediate
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^MOVIv", "^MVNIv")>;
+// -- multiply
+def : InstRW<[Ampere1Write_3cyc_1XY],
+        (instregex "MULv", "SMULLv", "UMULLv", "SQDMUL(H|L)v", "SQRDMULHv")>;
+// -- multiply accumulate
+def : InstRW<[Ampere1Write_3cyc_1XY],
+        (instregex "MLAv", "MLSv", "(S|U|SQD)(MLAL|MLSL)v", "SQRDML(A|S)Hv")>;
+// -- negation, saturating
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^SQABS", "^SQNEG")>;
+// -- reverse bits/bytes
+def : InstRW<[Ampere1Write_2cyc_1XY],
+        (instregex "^RBITv", "^REV16v", "^REV32v", "^REV64v")>;
+// -- shift
+def : InstRW<[Ampere1Write_3cyc_1XY], (instregex "^[SU]SHL(v16i8|v8i16|v4i32|v2i64)")>;
+// -- shift and accumulate
+def : InstRW<[Ampere1Write_3cyc_1XY],
+        (instregex "SRSRAv", "SSRAv", "URSRAv", "USRAv")>;
+// -- shift, saturating
+def : InstRW<[Ampere1Write_3cyc_1XY],
+        (instregex "^SQRSHLv", "^SQRSHRNv", "^SQRSHRUNv", "^SQSHL", "^SQSHLU",
+                   "^SQXTNv", "^SQXTUNv", "^UQSHRNv", "UQRSHRNv", "^UQRSHL",
+                   "^UQSHL")>;
+
+// Vector miscellaneous instructions
+// -- duplicate element
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^DUPv.+lane")>;
+// -- duplicate from GPR
+def : InstRW<[Ampere1Write_5cyc_1BS], (instregex "^DUPv.+gpr")>;
+// -- extract narrow
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^XTNv")>;
+// -- insert/extract element
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^EXTv", "^INSv.+lane")>;
+// -- move FP immediate
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^FMOVv")>;
+// -- move element to GPR
+def : InstRW<[Ampere1Write_6cyc_1XY_1Z], (instregex "(S|U)MOVv")>;
+// -- move from GPR to any element
+def : InstRW<[Ampere1Write_7cyc_1BS_1XY], (instregex "^INSv.+gpr")>;
+// -- table lookup
+def : InstRW<[Ampere1Write_2cyc_1XY],
+            (instrs TBLv8i8One, TBLv16i8One, TBXv8i8One, TBXv16i8One)>;
+def : InstRW<[Ampere1Write_4cyc_2XY],
+            (instrs TBLv8i8Two, TBLv16i8Two, TBXv8i8Two, TBXv16i8Two)>;
+def : InstRW<[Ampere1Write_6cyc_3XY],
+            (instrs TBLv8i8Three, TBLv16i8Three, TBXv8i8Three, TBXv16i8Three)>;
+def : InstRW<[Ampere1Write_8cyc_4XY],
+            (instrs TBLv8i8Four, TBLv16i8Four, TBXv8i8Four, TBXv16i8Four)>;
+// -- transpose
+def : InstRW<[Ampere1Write_2cyc_1XY],
+              (instregex "^TRN1v", "^TRN2v", "^UZP1v", "^UZP2v")>;
+// -- zip/unzip
+def : InstRW<[Ampere1Write_2cyc_1XY], (instregex "^ZIP1v", "^ZIP2v")>;
+
+} // SchedModel = Ampere1Model
diff --git a/llvm/lib/Target/AArch64/AArch64SchedPredAmpere.td b/llvm/lib/Target/AArch64/AArch64SchedPredAmpere.td
new file mode 100644
index 000000000000..8552c07bda56
--- /dev/null
+++ b/llvm/lib/Target/AArch64/AArch64SchedPredAmpere.td
@@ -0,0 +1,25 @@
+//===- AArch64SchedPredAmpere.td - AArch64 Sched Preds -----*- 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 scheduling predicate definitions that are used by the
+// AArch64 Ampere Computing processors.
+//
+//===----------------------------------------------------------------------===//
+
+// Auxiliary predicates.
+
+// Check for a LSL shift <= 4
+def AmpereCheapLSL : MCSchedPredicate<
+                                CheckAny<[CheckShiftBy0,
+                                 CheckAll<
+                                   [CheckShiftLSL,
+                                    CheckAny<
+                                      [CheckShiftBy1,
+                                       CheckShiftBy2,
+                                       CheckShiftBy3,
+                                       CheckShiftBy4]>]>]>>;
diff --git a/llvm/lib/Target/AArch64/AArch64SchedPredicates.td b/llvm/lib/Target/AArch64/AArch64SchedPredicates.td
index fc13b23b4cf8..19a3780c7381 100644
--- a/llvm/lib/Target/AArch64/AArch64SchedPredicates.td
+++ b/llvm/lib/Target/AArch64/AArch64SchedPredicates.td
@@ -53,7 +53,7 @@ let FunctionMapper = "AArch64_AM::getShiftType" in {
 }
 
 // Check for shifting in arithmetic and logic instructions.
-foreach I = {0-3, 8} in {
+foreach I = {0-4, 8} in {
   let FunctionMapper = "AArch64_AM::getShiftValue" in
   def CheckShiftBy#I        : CheckImmOperand<3, I>;
 }
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
index 8a7e20237271..9f2753584db8 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -221,6 +221,12 @@ void AArch64Subtarget::initializeProperties() {
     // FIXME: remove this to enable 64-bit SLP if performance looks good.
     MinVectorRegisterBitWidth = 128;
     break;
+  case Ampere1:
+    CacheLineSize = 64;
+    PrefFunctionLogAlignment = 6;
+    PrefLoopLogAlignment = 6;
+    MaxInterleaveFactor = 4;
+    break;
   }
 }
 
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h
index 061db926ee2b..1c14e0a55049 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.h
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -40,6 +40,7 @@ public:
   enum ARMProcFamilyEnum : uint8_t {
     Others,
     A64FX,
+    Ampere1,
     AppleA7,
     AppleA10,
     AppleA11,
diff --git a/llvm/test/CodeGen/AArch64/cpus.ll b/llvm/test/CodeGen/AArch64/cpus.ll
index 88330b6461ec..9167f12a97ed 100644
--- a/llvm/test/CodeGen/AArch64/cpus.ll
+++ b/llvm/test/CodeGen/AArch64/cpus.ll
@@ -34,6 +34,7 @@
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=tsv110 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=apple-latest 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=a64fx 2>&1 | FileCheck %s
+; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=ampere1 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=invalidcpu 2>&1 | FileCheck %s --check-prefix=INVALID
 
 ; CHECK-NOT: {{.*}}  is not a recognized processor for this target
diff --git a/llvm/test/CodeGen/AArch64/neon-dot-product.ll b/llvm/test/CodeGen/AArch64/neon-dot-product.ll
index 6c76d4e90e2d..f71546c66a5c 100644
--- a/llvm/test/CodeGen/AArch64/neon-dot-product.ll
+++ b/llvm/test/CodeGen/AArch64/neon-dot-product.ll
@@ -5,6 +5,7 @@
 ; RUN: llc -mtriple aarch64-none-linux-gnu -mcpu=neoverse-e1  < %s | FileCheck %s
 ; RUN: llc -mtriple aarch64-none-linux-gnu -mcpu=neoverse-n1  < %s | FileCheck %s
 ; RUN: llc -mtriple aarch64-none-linux-gnu -mcpu=neoverse-n2  < %s | FileCheck %s
+; RUN: llc -mtriple aarch64-none-linux-gnu -mcpu=ampere1      < %s | FileCheck %s
 
 declare <2 x i32> @llvm.aarch64.neon.udot.v2i32.v8i8(<2 x i32>, <8 x i8>, <8 x i8>)
 declare <4 x i32> @llvm.aarch64.neon.udot.v4i32.v16i8(<4 x i32>, <16 x i8>, <16 x i8>)
diff --git a/llvm/test/CodeGen/AArch64/remat.ll b/llvm/test/CodeGen/AArch64/remat.ll
index bd2786f66e41..062aa47b2578 100644
--- a/llvm/test/CodeGen/AArch64/remat.ll
+++ b/llvm/test/CodeGen/AArch64/remat.ll
@@ -24,6 +24,7 @@
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=tsv110 -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mattr=+custom-cheap-as-move -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=thunderx3t110 -o - %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=ampere1 -o - %s | FileCheck %s
 
 %X = type { i64, i64, i64 }
 declare void @f(%X*)
diff --git a/llvm/test/MC/AArch64/armv8.2a-dotprod.s b/llvm/test/MC/AArch64/armv8.2a-dotprod.s
index c561fbc4bab4..45dc8d0737ef 100644
--- a/llvm/test/MC/AArch64/armv8.2a-dotprod.s
+++ b/llvm/test/MC/AArch64/armv8.2a-dotprod.s
@@ -13,6 +13,7 @@
 // RUN: llvm-mc -triple aarch64 -mcpu=tsv110 -show-encoding < %s | FileCheck %s --check-prefix=CHECK-DOTPROD
 // RUN: llvm-mc -triple aarch64 -mcpu=cortex-r82 -show-encoding < %s | FileCheck %s --check-prefix=CHECK-DOTPROD
 // RUN: llvm-mc -triple aarch64 -mattr=+v8r -show-encoding < %s | FileCheck %s --check-prefix=CHECK-DOTPROD
+// RUN: llvm-mc -triple aarch64 -mcpu=ampere1 -show-encoding < %s | FileCheck %s --check-prefix=CHECK-DOTPROD
 
 // RUN: not llvm-mc -triple aarch64 -mattr=+v8.2a -show-encoding < %s 2> %t
 // RUN: FileCheck --check-prefix=CHECK-NO-DOTPROD < %t %s
@@ -36,6 +37,8 @@
 // RUN: FileCheck --check-prefix=CHECK-NO-DOTPROD < %t %s
 // RUN: not llvm-mc -triple aarch64 -mcpu=neoverse-n2 -mattr=-dotprod -show-encoding < %s 2> %t
 // RUN: FileCheck --check-prefix=CHECK-NO-DOTPROD < %t %s
+// RUN: not llvm-mc -triple aarch64 -mcpu=ampere1 -mattr=-dotprod -show-encoding < %s 2> %t
+// RUN: FileCheck --check-prefix=CHECK-NO-DOTPROD < %t %s
 
 udot v0.2s, v1.8b, v2.8b
 sdot v0.2s, v1.8b, v2.8b
diff --git a/llvm/test/MC/AArch64/armv8.3a-rcpc.s b/llvm/test/MC/AArch64/armv8.3a-rcpc.s
index 1660cc4c7504..271eea5dddd2 100644
--- a/llvm/test/MC/AArch64/armv8.3a-rcpc.s
+++ b/llvm/test/MC/AArch64/armv8.3a-rcpc.s
@@ -6,6 +6,7 @@
 // RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mcpu=neoverse-e1 < %s 2>&1 | FileCheck %s
 // RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mcpu=neoverse-n1 < %s 2>&1 | FileCheck %s
 // RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mcpu=neoverse-n2 < %s 2>&1 | FileCheck %s
+// RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mcpu=ampere1 < %s 2>&1 | FileCheck %s
 // RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mattr=+v8.2a -mattr=+rcpc < %s 2>&1 | FileCheck %s
 // RUN: not llvm-mc -triple aarch64-none-linux-gnu -mattr=+v8.2a < %s 2> %t
 // RUN: FileCheck --check-prefix=CHECK-REQ %s < %t
diff --git a/llvm/test/MC/Disassembler/AArch64/armv8.3a-rcpc.txt b/llvm/test/MC/Disassembler/AArch64/armv8.3a-rcpc.txt
index c6d7c79a3d0f..d7d246b0afb7 100644
--- a/llvm/test/MC/Disassembler/AArch64/armv8.3a-rcpc.txt
+++ b/llvm/test/MC/Disassembler/AArch64/armv8.3a-rcpc.txt
@@ -12,6 +12,7 @@
 # RUN: llvm-mc -triple aarch64-none-linux-gnu -mcpu=neoverse-e1 --disassemble < %s | FileCheck %s
 # RUN: llvm-mc -triple aarch64-none-linux-gnu -mcpu=neoverse-n1 --disassemble < %s | FileCheck %s
 # RUN: llvm-mc -triple aarch64-none-linux-gnu -mcpu=neoverse-n2 --disassemble < %s | FileCheck %s
+# RUN: llvm-mc -triple aarch64-none-linux-gnu -mcpu=ampere1 --disassemble < %s | FileCheck %s
 
 # CHECK: ldaprb w0, [x0]
 # CHECK: ldaprh w0, [x0]
diff --git a/llvm/unittests/Support/TargetParserTest.cpp b/llvm/unittests/Support/TargetParserTest.cpp
index de750ac1be96..bba51e8c43e6 100644
--- a/llvm/unittests/Support/TargetParserTest.cpp
+++ b/llvm/unittests/Support/TargetParserTest.cpp
@@ -1186,6 +1186,14 @@ INSTANTIATE_TEST_SUITE_P(
                              AArch64::AEK_SVE2 | AArch64::AEK_SVE2BITPERM |
                              AArch64::AEK_BF16 | AArch64::AEK_I8MM,
                          "8.5-A"),
+        ARMCPUTestParams("ampere1", "armv8.6-a", "crypto-neon-fp-armv8",
+                         AArch64::AEK_CRC  | AArch64::AEK_FP   | AArch64::AEK_FP16   |
+                             AArch64::AEK_SIMD | AArch64::AEK_RAS  | AArch64::AEK_LSE     |
+                             AArch64::AEK_RDM  | AArch64::AEK_RCPC | AArch64::AEK_DOTPROD |
+                             AArch64::AEK_SM4  | AArch64::AEK_SHA3 | AArch64::AEK_BF16    |
+                             AArch64::AEK_SHA2 | AArch64::AEK_AES  | AArch64::AEK_I8MM    |
+                             AArch64::AEK_MTE  | AArch64::AEK_SSBS | AArch64::AEK_SB,
+                         "8.6-A"),
         ARMCPUTestParams(
             "neoverse-512tvb", "armv8.4-a", "crypto-neon-fp-armv8",
             AArch64::AEK_RAS | AArch64::AEK_SVE | AArch64::AEK_SSBS |
@@ -1249,7 +1257,7 @@ INSTANTIATE_TEST_SUITE_P(
                              AArch64::AEK_LSE | AArch64::AEK_RDM,
                          "8.2-A")));
 
-static constexpr unsigned NumAArch64CPUArchs = 53;
+static constexpr unsigned NumAArch64CPUArchs = 54;
 
 TEST(TargetParserTest, testAArch64CPUArchList) {
   SmallVector<StringRef, NumAArch64CPUArchs> List;