[ARM][AArch64] Support for Cortex-A65 & A65AE, Neoverse E1 & N1

Summary:
Add support for Cortex-A65, Cortex-A65AE, Neoverse E1 and Neoverse N1.
Neoverse E1 and Cortex-A65(&AE) only implement the AArch64 state of the
Arm architecture. Neoverse N1 implements both AArch32 and AArch64.

Cortex-A65:
https://developer.arm.com/ip-products/processors/cortex-a/cortex-a65

Cortex-A65AE:
https://developer.arm.com/ip-products/processors/cortex-a/cortex-a65ae

Neoverse E1:
https://developer.arm.com/ip-products/processors/neoverse/neoverse-e1

Neoverse N1:
https://developer.arm.com/ip-products/processors/neoverse/neoverse-n1

Patch by Diogo Sampaio and Pablo Barrio

Reviewers: samparker, LukeCheeseman, sbaranga, ostannard

Reviewed By: ostannard

Subscribers: ostannard, javed.absar, kristof.beyls, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D64406

llvm-svn: 367007

19 files changed, 164 insertions, 16 deletions

diff --git a/llvm/include/llvm/Support/AArch64TargetParser.def b/llvm/include/llvm/Support/AArch64TargetParser.def
index e152f383b3e..9ee9cbf281f 100644
--- a/llvm/include/llvm/Support/AArch64TargetParser.def
+++ b/llvm/include/llvm/Support/AArch64TargetParser.def
@@ -92,6 +92,12 @@ AARCH64_CPU_NAME("cortex-a55", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_FP16 | AArch64::AEK_DOTPROD | AArch64::AEK_RCPC))
 AARCH64_CPU_NAME("cortex-a57", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_CRC))
+AARCH64_CPU_NAME("cortex-a65", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
+                 (AArch64::AEK_DOTPROD | AArch64::AEK_FP16 | AArch64::AEK_RAS |
+                  AArch64::AEK_RCPC | AArch64::AEK_SSBS))
+AARCH64_CPU_NAME("cortex-a65ae", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
+                 (AArch64::AEK_DOTPROD | AArch64::AEK_FP16 | AArch64::AEK_RAS |
+                  AArch64::AEK_RCPC | AArch64::AEK_SSBS))
 AARCH64_CPU_NAME("cortex-a72", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_CRC))
 AARCH64_CPU_NAME("cortex-a73", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false,
@@ -104,6 +110,13 @@ AARCH64_CPU_NAME("cortex-a76", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
 AARCH64_CPU_NAME("cortex-a76ae", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_FP16 | AArch64::AEK_DOTPROD | AArch64::AEK_RCPC |
                   AArch64::AEK_SSBS))
+AARCH64_CPU_NAME("neoverse-e1", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
+                 (AArch64::AEK_DOTPROD | AArch64::AEK_FP16 | AArch64::AEK_RAS |
+                  AArch64::AEK_RCPC | AArch64::AEK_SSBS))
+AARCH64_CPU_NAME("neoverse-n1", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
+                 (AArch64::AEK_DOTPROD | AArch64::AEK_FP16 |
+                  AArch64::AEK_PROFILE | AArch64::AEK_RAS | AArch64::AEK_RCPC |
+                  AArch64::AEK_SSBS))
 AARCH64_CPU_NAME("cyclone", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_NONE))
 AARCH64_CPU_NAME("exynos-m1", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false,
diff --git a/llvm/include/llvm/Support/ARMTargetParser.def b/llvm/include/llvm/Support/ARMTargetParser.def
index f466b325274..3e77e20762c 100644
--- a/llvm/include/llvm/Support/ARMTargetParser.def
+++ b/llvm/include/llvm/Support/ARMTargetParser.def
@@ -274,6 +274,8 @@ ARM_CPU_NAME("cortex-a76", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
             (ARM::AEK_FP16 | ARM::AEK_DOTPROD))
 ARM_CPU_NAME("cortex-a76ae", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
             (ARM::AEK_FP16 | ARM::AEK_DOTPROD))
+ARM_CPU_NAME("neoverse-n1", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
+             (ARM::AEK_FP16 | ARM::AEK_DOTPROD))
 ARM_CPU_NAME("cyclone", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false, ARM::AEK_CRC)
 ARM_CPU_NAME("exynos-m1", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false, ARM::AEK_CRC)
 ARM_CPU_NAME("exynos-m2", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false, ARM::AEK_CRC)
diff --git a/llvm/lib/Target/AArch64/AArch64.td b/llvm/lib/Target/AArch64/AArch64.td
index e39c6995e36..a0d334ebb3f 100644
--- a/llvm/lib/Target/AArch64/AArch64.td
+++ b/llvm/lib/Target/AArch64/AArch64.td
@@ -354,7 +354,7 @@ def HasV8_1aOps : SubtargetFeature<"v8.1a", "HasV8_1aOps", "true",
   FeaturePAN, FeatureLOR, FeatureVH]>;
 
 def HasV8_2aOps : SubtargetFeature<"v8.2a", "HasV8_2aOps", "true",
-  "Support ARM v8.2a instructions", [HasV8_1aOps, FeaturePsUAO, 
+  "Support ARM v8.2a instructions", [HasV8_1aOps, FeaturePsUAO,
   FeaturePAN_RWV, FeatureRAS, FeatureCCPP]>;
 
 def HasV8_3aOps : SubtargetFeature<"v8.3a", "HasV8_3aOps", "true",
@@ -484,6 +484,19 @@ def ProcA57     : SubtargetFeature<"a57", "ARMProcFamily", "CortexA57",
                                    FeaturePredictableSelectIsExpensive
                                    ]>;
 
+def ProcA65     : SubtargetFeature<"a65", "ARMProcFamily", "CortexA65",
+                                   "Cortex-A65 ARM processors", [
+                                   HasV8_2aOps,
+                                   FeatureCrypto,
+                                   FeatureDotProd,
+                                   FeatureFPARMv8,
+                                   FeatureFullFP16,
+                                   FeatureNEON,
+                                   FeatureRAS,
+                                   FeatureRCPC,
+                                   FeatureSSBS,
+                                   ]>;
+
 def ProcA72     : SubtargetFeature<"a72", "ARMProcFamily", "CortexA72",
                                    "Cortex-A72 ARM processors", [
                                    FeatureCRC,
@@ -641,6 +654,33 @@ def ProcFalkor  : SubtargetFeature<"falkor", "ARMProcFamily", "Falkor",
                                    FeatureSlowSTRQro
                                    ]>;
 
+def ProcNeoverseE1 : SubtargetFeature<"neoversee1", "ARMProcFamily",
+                                      "NeoverseE1",
+                                      "Neoverse E1 ARM processors", [
+                                      HasV8_2aOps,
+                                      FeatureCrypto,
+                                      FeatureDotProd,
+                                      FeatureFPARMv8,
+                                      FeatureFullFP16,
+                                      FeatureNEON,
+                                      FeatureRCPC,
+                                      FeatureSSBS,
+                                      ]>;
+
+def ProcNeoverseN1 : SubtargetFeature<"neoversen1", "ARMProcFamily",
+                                      "NeoverseN1",
+                                      "Neoverse N1 ARM processors", [
+                                      HasV8_2aOps,
+                                      FeatureCrypto,
+                                      FeatureDotProd,
+                                      FeatureFPARMv8,
+                                      FeatureFullFP16,
+                                      FeatureNEON,
+                                      FeatureRCPC,
+                                      FeatureSPE,
+                                      FeatureSSBS,
+                                      ]>;
+
 def ProcSaphira  : SubtargetFeature<"saphira", "ARMProcFamily", "Saphira",
                                    "Qualcomm Saphira processors", [
                                    FeatureCrypto,
@@ -735,16 +775,19 @@ def : ProcessorModel<"generic", NoSchedModel, [
                      FeaturePostRAScheduler
                      ]>;
 
-// FIXME: Cortex-A35 and Cortex-A55 are currently modeled as a Cortex-A53.
 def : ProcessorModel<"cortex-a35", CortexA53Model, [ProcA35]>;
 def : ProcessorModel<"cortex-a53", CortexA53Model, [ProcA53]>;
 def : ProcessorModel<"cortex-a55", CortexA53Model, [ProcA55]>;
 def : ProcessorModel<"cortex-a57", CortexA57Model, [ProcA57]>;
+def : ProcessorModel<"cortex-a65", CortexA53Model, [ProcA65]>;
+def : ProcessorModel<"cortex-a65ae", CortexA53Model, [ProcA65]>;
 def : ProcessorModel<"cortex-a72", CortexA57Model, [ProcA72]>;
 def : ProcessorModel<"cortex-a73", CortexA57Model, [ProcA73]>;
 def : ProcessorModel<"cortex-a75", CortexA57Model, [ProcA75]>;
 def : ProcessorModel<"cortex-a76", CortexA57Model, [ProcA76]>;
 def : ProcessorModel<"cortex-a76ae", CortexA57Model, [ProcA76]>;
+def : ProcessorModel<"neoverse-e1", CortexA53Model, [ProcNeoverseE1]>;
+def : ProcessorModel<"neoverse-n1", CortexA57Model, [ProcNeoverseN1]>;
 def : ProcessorModel<"cyclone", CycloneModel, [ProcCyclone]>;
 def : ProcessorModel<"exynos-m1", ExynosM1Model, [ProcExynosM1]>;
 def : ProcessorModel<"exynos-m2", ExynosM1Model, [ProcExynosM2]>;
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
index 3bc89b91c3f..aa6e233e28a 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -79,6 +79,8 @@ void AArch64Subtarget::initializeProperties() {
     MaxInterleaveFactor = 4;
     PrefFunctionAlignment = 4;
     break;
+  case CortexA65:
+    break;
   case CortexA72:
   case CortexA73:
   case CortexA75:
@@ -122,6 +124,9 @@ void AArch64Subtarget::initializeProperties() {
     // FIXME: remove this to enable 64-bit SLP if performance looks good.
     MinVectorRegisterBitWidth = 128;
     break;
+  case NeoverseE1:
+  case NeoverseN1:
+    break;
   case Saphira:
     MaxInterleaveFactor = 4;
     // FIXME: remove this to enable 64-bit SLP if performance looks good.
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h
index 0c84cfb8329..ff51a22240e 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.h
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -42,6 +42,7 @@ public:
     CortexA53,
     CortexA55,
     CortexA57,
+    CortexA65,
     CortexA72,
     CortexA73,
     CortexA75,
@@ -51,6 +52,8 @@ public:
     ExynosM3,
     Falkor,
     Kryo,
+    NeoverseE1,
+    NeoverseN1,
     Saphira,
     ThunderX2T99,
     ThunderX,
diff --git a/llvm/lib/Target/ARM/ARM.td b/llvm/lib/Target/ARM/ARM.td
index b687db12eaf..cac14dbaa59 100644
--- a/llvm/lib/Target/ARM/ARM.td
+++ b/llvm/lib/Target/ARM/ARM.td
@@ -1156,6 +1156,13 @@ def : ProcNoItin<"cortex-a76ae",                        [ARMv82a, ProcA76,
                                                          FeatureFullFP16,
                                                          FeatureDotProd]>;
 
+def : ProcNoItin<"neoverse-n1",                         [ARMv82a,
+                                                         FeatureHWDivThumb,
+                                                         FeatureHWDivARM,
+                                                         FeatureCrypto,
+                                                         FeatureCRC,
+                                                         FeatureDotProd]>;
+
 def : ProcessorModel<"cyclone",     SwiftModel,         [ARMv8a, ProcSwift,
                                                          FeatureHasRetAddrStack,
                                                          FeatureNEONForFP,
diff --git a/llvm/lib/Target/ARM/ARMSubtarget.cpp b/llvm/lib/Target/ARM/ARMSubtarget.cpp
index 978faed776b..383c913fb6a 100644
--- a/llvm/lib/Target/ARM/ARMSubtarget.cpp
+++ b/llvm/lib/Target/ARM/ARMSubtarget.cpp
@@ -303,6 +303,8 @@ void ARMSubtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
   case Krait:
     PreISelOperandLatencyAdjustment = 1;
     break;
+  case NeoverseN1:
+    break;
   case Swift:
     MaxInterleaveFactor = 2;
     LdStMultipleTiming = SingleIssuePlusExtras;
diff --git a/llvm/lib/Target/ARM/ARMSubtarget.h b/llvm/lib/Target/ARM/ARMSubtarget.h
index c2b0f052b84..f167fa71959 100644
--- a/llvm/lib/Target/ARM/ARMSubtarget.h
+++ b/llvm/lib/Target/ARM/ARMSubtarget.h
@@ -71,6 +71,7 @@ protected:
     Exynos,
     Krait,
     Kryo,
+    NeoverseN1,
     Swift
   };
   enum ARMProcClassEnum {
diff --git a/llvm/test/CodeGen/AArch64/cpus.ll b/llvm/test/CodeGen/AArch64/cpus.ll
index d0ca70694fe..1e08e504b5c 100644
--- a/llvm/test/CodeGen/AArch64/cpus.ll
+++ b/llvm/test/CodeGen/AArch64/cpus.ll
@@ -6,11 +6,15 @@
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a53 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a55 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a57 2>&1 | FileCheck %s
+; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a65 2>&1 | FileCheck %s
+; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a65ae 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a72 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a73 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a75 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a76ae 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a76 2>&1 | FileCheck %s
+; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=neoverse-e1 2>&1 | FileCheck %s
+; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=neoverse-n1 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=exynos-m1 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=exynos-m2 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=exynos-m3 2>&1 | FileCheck %s
diff --git a/llvm/test/CodeGen/AArch64/neon-dot-product.ll b/llvm/test/CodeGen/AArch64/neon-dot-product.ll
index 5ad75a7d24c..4b3c7cf4a65 100644
--- a/llvm/test/CodeGen/AArch64/neon-dot-product.ll
+++ b/llvm/test/CodeGen/AArch64/neon-dot-product.ll
@@ -1,4 +1,8 @@
-; RUN: llc -mtriple aarch64-none-linux-gnu -mattr=+dotprod < %s | FileCheck %s
+; RUN: llc -mtriple aarch64-none-linux-gnu -mattr=+dotprod    < %s | FileCheck %s
+; RUN: llc -mtriple aarch64-none-linux-gnu -mcpu=cortex-a65   < %s | FileCheck %s
+; RUN: llc -mtriple aarch64-none-linux-gnu -mcpu=cortex-a65ae < %s | FileCheck %s
+; 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
 
 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 f110c38f9e5..193b41b66d5 100644
--- a/llvm/test/CodeGen/AArch64/remat.ll
+++ b/llvm/test/CodeGen/AArch64/remat.ll
@@ -2,9 +2,13 @@
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=cortex-a53 -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=cortex-a55 -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=cortex-a57 -o - %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=cortex-a65 -o - %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=cortex-a65ae -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=cortex-a72 -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=cortex-a73 -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=cortex-a75 -o - %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=neoverse-e1 -o - %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=neoverse-n1 -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=exynos-m1 -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=exynos-m2 -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=exynos-m3 -o - %s | FileCheck %s
@@ -26,9 +30,9 @@ entry:
 ; CHECK: add x0, sp, #8
 ; CHECK-NOT: mov
 ; CHECK-NEXT: bl f
-  call void @f(%X* %tmp)               
+  call void @f(%X* %tmp)
 ; CHECK: add x0, sp, #8
 ; CHECK-NOT: mov
 ; CHECK-NEXT: bl f
-  ret void 
+  ret void
 }
diff --git a/llvm/test/MC/AArch64/armv8.2a-dotprod.s b/llvm/test/MC/AArch64/armv8.2a-dotprod.s
index 6a462fa55b3..b8aafbe8857 100644
--- a/llvm/test/MC/AArch64/armv8.2a-dotprod.s
+++ b/llvm/test/MC/AArch64/armv8.2a-dotprod.s
@@ -1,10 +1,23 @@
 // RUN: llvm-mc -triple aarch64 -mattr=+dotprod -show-encoding < %s | FileCheck %s  --check-prefix=CHECK-DOTPROD
+// RUN: llvm-mc -triple aarch64 -mcpu=cortex-a55 -show-encoding < %s | FileCheck %s --check-prefix=CHECK-DOTPROD
+// RUN: llvm-mc -triple aarch64 -mcpu=cortex-a65 -show-encoding < %s| FileCheck %s --check-prefix=CHECK-DOTPROD
+// RUN: llvm-mc -triple aarch64 -mcpu=cortex-a65ae -show-encoding < %s| FileCheck %s --check-prefix=CHECK-DOTPROD
 // RUN: llvm-mc -triple aarch64 -mcpu=cortex-a75 -show-encoding < %s | FileCheck %s --check-prefix=CHECK-DOTPROD
 // RUN: llvm-mc -triple aarch64 -mcpu=cortex-a76 -show-encoding < %s | FileCheck %s --check-prefix=CHECK-DOTPROD
-// RUN: llvm-mc -triple aarch64 -mcpu=cortex-a55 -show-encoding < %s | FileCheck %s --check-prefix=CHECK-DOTPROD
+// RUN: llvm-mc -triple aarch64 -mcpu=neoverse-e1 -show-encoding < %s| FileCheck %s --check-prefix=CHECK-DOTPROD
+// RUN: llvm-mc -triple aarch64 -mcpu=neoverse-n1 -show-encoding < %s| FileCheck %s --check-prefix=CHECK-DOTPROD
 // RUN: llvm-mc -triple aarch64 -mcpu=tsv110 -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
+// RUN: not llvm-mc -triple aarch64 -mcpu=cortex-a65 -mattr=-dotprod -show-encoding < %s 2> %t
+// RUN: FileCheck --check-prefix=CHECK-NO-DOTPROD < %t %s
+// RUN: not llvm-mc -triple aarch64 -mcpu=cortex-a65ae -mattr=-dotprod -show-encoding < %s 2> %t
+// RUN: FileCheck --check-prefix=CHECK-NO-DOTPROD < %t %s
+// RUN: not llvm-mc -triple aarch64 -mcpu=neoverse-e1 -mattr=-dotprod -show-encoding < %s 2> %t
+// RUN: FileCheck --check-prefix=CHECK-NO-DOTPROD < %t %s
+// RUN: not llvm-mc -triple aarch64 -mcpu=neoverse-n1 -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/armv8.2a-statistical-profiling.s b/llvm/test/MC/AArch64/armv8.2a-statistical-profiling.s
index a11a4b227ac..c1dbc22ef5d 100644
--- a/llvm/test/MC/AArch64/armv8.2a-statistical-profiling.s
+++ b/llvm/test/MC/AArch64/armv8.2a-statistical-profiling.s
@@ -1,4 +1,5 @@
 // RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mattr=+spe < %s | FileCheck %s
+// RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mcpu=neoverse-n1 < %s | FileCheck %s
 // RUN: not llvm-mc -triple aarch64-none-linux-gnu -show-encoding < %s 2>&1 | FileCheck --check-prefix=NO_SPE %s
 
   psb csync
diff --git a/llvm/test/MC/AArch64/armv8.3a-rcpc.s b/llvm/test/MC/AArch64/armv8.3a-rcpc.s
index cd254acdf96..f38161ee21e 100644
--- a/llvm/test/MC/AArch64/armv8.3a-rcpc.s
+++ b/llvm/test/MC/AArch64/armv8.3a-rcpc.s
@@ -1,6 +1,10 @@
 // RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mattr=+v8.3a < %s 2>&1 | FileCheck %s
+// RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mcpu=cortex-a65 < %s 2>&1 | FileCheck %s
+// RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mcpu=cortex-a65ae < %s 2>&1 | FileCheck %s
 // RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mcpu=cortex-a75 < %s 2>&1 | FileCheck %s
 // RUN: llvm-mc -triple aarch64-none-linux-gnu -show-encoding -mcpu=cortex-a55 < %s 2>&1 | FileCheck %s
+// 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 -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/AArch64/armv8.5a-ssbs.s b/llvm/test/MC/AArch64/armv8.5a-ssbs.s
index 4903253be21..81f1a48a1a4 100644
--- a/llvm/test/MC/AArch64/armv8.5a-ssbs.s
+++ b/llvm/test/MC/AArch64/armv8.5a-ssbs.s
@@ -1,7 +1,11 @@
 // RUN:     llvm-mc -triple aarch64 -show-encoding -mattr=+ssbs  < %s      | FileCheck %s
 // RUN:     llvm-mc -triple aarch64 -show-encoding -mattr=+v8.5a < %s      | FileCheck %s
-// RUN:     llvm-mc -triple aarch64 -show-encoding -mcpu=cortex-a76 < %s      | FileCheck %s
-// RUN:     llvm-mc -triple aarch64 -show-encoding -mcpu=cortex-a76ae < %s      | FileCheck %s
+// RUN:     llvm-mc -triple aarch64 -show-encoding -mcpu=cortex-a65 < %s   | FileCheck %s
+// RUN:     llvm-mc -triple aarch64 -show-encoding -mcpu=cortex-a65ae < %s | FileCheck %s
+// RUN:     llvm-mc -triple aarch64 -show-encoding -mcpu=cortex-a76 < %s   | FileCheck %s
+// RUN:     llvm-mc -triple aarch64 -show-encoding -mcpu=cortex-a76ae < %s | FileCheck %s
+// RUN:     llvm-mc -triple aarch64 -show-encoding -mcpu=neoverse-e1 < %s  | FileCheck %s
+// RUN:     llvm-mc -triple aarch64 -show-encoding -mcpu=neoverse-n1 < %s  | FileCheck %s
 // RUN: not llvm-mc -triple aarch64 -show-encoding -mattr=-ssbs  < %s 2>&1 | FileCheck %s --check-prefix=NOSPECID
 
 mrs x2, SSBS
diff --git a/llvm/test/MC/ARM/armv8.2a-dotprod-a32.s b/llvm/test/MC/ARM/armv8.2a-dotprod-a32.s
index 7ef489607dd..366f85c5cb4 100644
--- a/llvm/test/MC/ARM/armv8.2a-dotprod-a32.s
+++ b/llvm/test/MC/ARM/armv8.2a-dotprod-a32.s
@@ -1,7 +1,8 @@
 // RUN: llvm-mc -triple arm -mattr=+dotprod -show-encoding < %s | FileCheck %s  --check-prefix=CHECK
+// RUN: llvm-mc -triple arm -mcpu=cortex-a55 -show-encoding < %s | FileCheck %s  --check-prefix=CHECK
 // RUN: llvm-mc -triple arm -mcpu=cortex-a75 -show-encoding < %s | FileCheck %s  --check-prefix=CHECK
 // RUN: llvm-mc -triple arm -mcpu=cortex-a76 -show-encoding < %s | FileCheck %s  --check-prefix=CHECK
-// RUN: llvm-mc -triple arm -mcpu=cortex-a55 -show-encoding < %s | FileCheck %s  --check-prefix=CHECK
+// RUN: llvm-mc -triple arm -mcpu=neoverse-n1 -show-encoding < %s | FileCheck %s --check-prefix=CHECK
 
 // RUN: not llvm-mc -triple arm -mattr=-dotprod -show-encoding < %s 2> %t
 // RUN: FileCheck --check-prefix=CHECK-NO-DOTPROD < %t %s
diff --git a/llvm/test/MC/ARM/armv8.2a-dotprod-t32.s b/llvm/test/MC/ARM/armv8.2a-dotprod-t32.s
index 77d81a25217..3964fddaedd 100644
--- a/llvm/test/MC/ARM/armv8.2a-dotprod-t32.s
+++ b/llvm/test/MC/ARM/armv8.2a-dotprod-t32.s
@@ -1,7 +1,8 @@
 // RUN: llvm-mc -triple thumb -mattr=+dotprod -show-encoding < %s | FileCheck %s  --check-prefix=CHECK
+// RUN: llvm-mc -triple thumb -mcpu=cortex-a55 -show-encoding < %s | FileCheck %s  --check-prefix=CHECK
 // RUN: llvm-mc -triple thumb -mcpu=cortex-a75 -show-encoding < %s | FileCheck %s  --check-prefix=CHECK
 // RUN: llvm-mc -triple thumb -mcpu=cortex-a76 -show-encoding < %s | FileCheck %s  --check-prefix=CHECK
-// RUN: llvm-mc -triple thumb -mcpu=cortex-a55 -show-encoding < %s | FileCheck %s  --check-prefix=CHECK
+// RUN: llvm-mc -triple thumb -mcpu=neoverse-n1 -show-encoding < %s | FileCheck %s --check-prefix=CHECK
 
 // RUN: not llvm-mc -triple thumb -mattr=-dotprod -show-encoding < %s 2> %t
 // RUN: FileCheck --check-prefix=CHECK-ERROR < %t %s
diff --git a/llvm/test/MC/Disassembler/AArch64/armv8.3a-rcpc.txt b/llvm/test/MC/Disassembler/AArch64/armv8.3a-rcpc.txt
index cc3649de097..3bd935b3f79 100644
--- a/llvm/test/MC/Disassembler/AArch64/armv8.3a-rcpc.txt
+++ b/llvm/test/MC/Disassembler/AArch64/armv8.3a-rcpc.txt
@@ -1,7 +1,11 @@
+# RUN: llvm-mc -triple aarch64-none-linux-gnu -mattr=+v8.2a -mattr=+rcpc --disassemble < %s | FileCheck %s
 # RUN: llvm-mc -triple aarch64-none-linux-gnu -mattr=+v8.3a --disassemble < %s | FileCheck %s
-# RUN: llvm-mc -triple aarch64-none-linux-gnu -mcpu=cortex-a75 --disassemble < %s | FileCheck %s
 # RUN: llvm-mc -triple aarch64-none-linux-gnu -mcpu=cortex-a55 --disassemble < %s | FileCheck %s
-# RUN: llvm-mc -triple aarch64-none-linux-gnu -mattr=+v8.2a -mattr=+rcpc --disassemble < %s | FileCheck %s
+# RUN: llvm-mc -triple aarch64-none-linux-gnu -mcpu=cortex-a65 --disassemble < %s | FileCheck %s
+# RUN: llvm-mc -triple aarch64-none-linux-gnu -mcpu=cortex-a65ae --disassemble < %s | FileCheck %s
+# RUN: llvm-mc -triple aarch64-none-linux-gnu -mcpu=cortex-a75 --disassemble < %s | FileCheck %s
+# 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
 
 # CHECK: ldaprb w0, [x0]
 # CHECK: ldaprh w0, [x0]
@@ -26,4 +30,3 @@
 # CHECK-V8_2A: warning: invalid instruction encoding
 # CHECK-V8_2A: [0x00,0xc0,0xbf,0xf8]
 # CHECK-V8_2A:  ^
-
diff --git a/llvm/unittests/Support/TargetParserTest.cpp b/llvm/unittests/Support/TargetParserTest.cpp
index 34c7a8a4fd1..d1b82952828 100644
--- a/llvm/unittests/Support/TargetParserTest.cpp
+++ b/llvm/unittests/Support/TargetParserTest.cpp
@@ -44,7 +44,6 @@ bool testARMCPU(StringRef CPUName, StringRef ExpectedArch,
     pass &= ((ExtKind ^ ARM::AEK_NONE) == ExpectedFlags);
   else
     pass &= (ExtKind == ExpectedFlags);
-
   pass &= ARM::getCPUAttr(AK).equals(CPUAttr);
 
   return pass;
@@ -257,6 +256,12 @@ TEST(TargetParserTest, testARMCPU) {
                          ARM::AEK_HWDIVTHUMB | ARM::AEK_DSP | ARM::AEK_FP16 |
                          ARM::AEK_RAS | ARM::AEK_DOTPROD,
                          "8.2-A"));
+  EXPECT_TRUE(testARMCPU("neoverse-n1", "armv8.2-a", "crypto-neon-fp-armv8",
+                        ARM::AEK_CRC | ARM::AEK_SEC | ARM::AEK_MP |
+                        ARM::AEK_VIRT | ARM::AEK_HWDIVARM |
+                        ARM::AEK_HWDIVTHUMB | ARM::AEK_DSP | ARM::AEK_FP16 |
+                        ARM::AEK_RAS | ARM::AEK_DOTPROD,
+                        "8.2-A"));
   EXPECT_TRUE(testARMCPU("cyclone", "armv8-a", "crypto-neon-fp-armv8",
                          ARM::AEK_CRC | ARM::AEK_SEC | ARM::AEK_MP |
                              ARM::AEK_VIRT | ARM::AEK_HWDIVARM |
@@ -304,7 +309,7 @@ TEST(TargetParserTest, testARMCPU) {
                          "7-S"));
 }
 
-static constexpr unsigned NumARMCPUArchs = 86;
+static constexpr unsigned NumARMCPUArchs = 87;
 
 TEST(TargetParserTest, testARMCPUArchList) {
   SmallVector<StringRef, NumARMCPUArchs> List;
@@ -782,6 +787,20 @@ TEST(TargetParserTest, testAArch64CPU) {
       AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
       AArch64::AEK_SIMD, "8-A"));
   EXPECT_TRUE(testAArch64CPU(
+      "cortex-a65", "armv8.2-a", "crypto-neon-fp-armv8",
+      AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_DOTPROD |
+      AArch64::AEK_FP | AArch64::AEK_FP16 | AArch64::AEK_LSE |
+      AArch64::AEK_RAS | AArch64::AEK_RCPC | AArch64::AEK_RDM |
+      AArch64::AEK_SIMD | AArch64::AEK_SSBS,
+      "8.2-A"));
+  EXPECT_TRUE(testAArch64CPU(
+      "cortex-a65ae", "armv8.2-a", "crypto-neon-fp-armv8",
+      AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_DOTPROD |
+      AArch64::AEK_FP | AArch64::AEK_FP16 | AArch64::AEK_LSE |
+      AArch64::AEK_RAS | AArch64::AEK_RCPC | AArch64::AEK_RDM |
+      AArch64::AEK_SIMD | AArch64::AEK_SSBS,
+      "8.2-A"));
+  EXPECT_TRUE(testAArch64CPU(
       "cortex-a72", "armv8-a", "crypto-neon-fp-armv8",
       AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
       AArch64::AEK_SIMD, "8-A"));
@@ -843,6 +862,20 @@ TEST(TargetParserTest, testAArch64CPU) {
       AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
       AArch64::AEK_SIMD, "8-A"));
   EXPECT_TRUE(testAArch64CPU(
+     "neoverse-e1", "armv8.2-a", "crypto-neon-fp-armv8",
+      AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_DOTPROD |
+      AArch64::AEK_FP | AArch64::AEK_FP16 | AArch64::AEK_LSE |
+      AArch64::AEK_RAS | AArch64::AEK_RCPC | AArch64::AEK_RDM |
+      AArch64::AEK_SIMD | AArch64::AEK_SSBS,
+     "8.2-A"));
+  EXPECT_TRUE(testAArch64CPU(
+     "neoverse-n1", "armv8.2-a", "crypto-neon-fp-armv8",
+      AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_DOTPROD |
+      AArch64::AEK_FP | AArch64::AEK_FP16 | AArch64::AEK_LSE |
+      AArch64::AEK_PROFILE | AArch64::AEK_RAS | AArch64::AEK_RCPC |
+      AArch64::AEK_RDM | AArch64::AEK_SIMD | AArch64::AEK_SSBS,
+     "8.2-A"));
+  EXPECT_TRUE(testAArch64CPU(
       "thunderx2t99", "armv8.1-a", "crypto-neon-fp-armv8",
       AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_LSE |
       AArch64::AEK_RDM | AArch64::AEK_FP | AArch64::AEK_SIMD, "8.1-A"));
@@ -875,7 +908,7 @@ TEST(TargetParserTest, testAArch64CPU) {
       "8.2-A"));
 }
 
-static constexpr unsigned NumAArch64CPUArchs = 24;
+static constexpr unsigned NumAArch64CPUArchs = 28;
 
 TEST(TargetParserTest, testAArch64CPUArchList) {
   SmallVector<StringRef, NumAArch64CPUArchs> List;