[ARM][AArch64] Cortex-A65AE, Neoverse E1 and Neoverse N1 support

[pbarrio]

Summary

Add support for Cortex-A65AE, Neoverse E1 and Neoverse N1.
Neoverse E1 and Cortex-A65AE only implement the AArch64 state of
the Arm architecture.

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

[ostannard]

llvm/include/llvm/Support/AArch64TargetParser.def

95

Why are you just adding cortex-a65ae, and not cortex-a65? Is that coming in a later patch?

96

I think all three of these cores should have AEK_RCPC, AEK_SSBS and AEK_RAS.

llvm/lib/Target/AArch64/AArch64.td

497

I think all three of these should also have FeatureSSBS.

[pbarrio]

Add Cortex-A65 and a few features that were missed in the first patch. I think all the features should be in now.

[ostannard]

llvm/lib/Target/AArch64/AArch64.td

681

These two also need FeatureSSBS.

[pbarrio]

Oooops sorry, not sure how I missed that. I've added SSBS to all the CPUs now.

[ostannard]

LGTM

llvm/include/llvm/Support/AArch64TargetParser.def

 AARCH64_CPU_NAME("cortex-a35", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_CRC))
 AARCH64_CPU_NAME("cortex-a53", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, true,
                  (AArch64::AEK_CRC))
 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-a65ae", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
+                 (AArch64::AEK_FP16 | AArch64::AEK_DOTPROD))
 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,
                  (AArch64::AEK_CRC))
 AARCH64_CPU_NAME("cortex-a75", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_FP16 | AArch64::AEK_DOTPROD | AArch64::AEK_RCPC))
 AARCH64_CPU_NAME("cortex-a76", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_FP16 | AArch64::AEK_DOTPROD | AArch64::AEK_RCPC |
                   AArch64::AEK_SSBS))
 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_FP16 | AArch64::AEK_DOTPROD))
+AARCH64_CPU_NAME("neoverse-n1", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
+                (AArch64::AEK_FP16 | AArch64::AEK_RCPC | AArch64::AEK_PROFILE |
+                 AArch64::AEK_DOTPROD))
 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,
                  (AArch64::AEK_CRC))
 AARCH64_CPU_NAME("exynos-m2", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_CRC))
 AARCH64_CPU_NAME("exynos-m3", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_CRC))

llvm/include/llvm/Support/ARMTargetParser.def

 ARM_CPU_NAME("cortex-a72", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false, ARM::AEK_CRC)
 ARM_CPU_NAME("cortex-a73", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false, ARM::AEK_CRC)
 ARM_CPU_NAME("cortex-a75", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
             (ARM::AEK_FP16 | ARM::AEK_DOTPROD))
 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)
 ARM_CPU_NAME("exynos-m3", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false, ARM::AEK_CRC)
 ARM_CPU_NAME("exynos-m4", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
              (ARM::AEK_FP16 | ARM::AEK_DOTPROD))
 ARM_CPU_NAME("exynos-m5", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
              (ARM::AEK_FP16 | ARM::AEK_DOTPROD))

llvm/lib/Target/AArch64/AArch64.td

def ProcA57     : SubtargetFeature<"a57", "ARMProcFamily", "CortexA57",
                                    FeatureFuseAES,
                                    FeatureFuseLiterals,
                                    FeatureNEON,
                                    FeaturePerfMon,
                                    FeaturePostRAScheduler,
                                    FeaturePredictableSelectIsExpensive
                                    ]>;
 
+def ProcA65     : SubtargetFeature<"a65", "ARMProcFamily", "CortexA65",
+                                   "Cortex-A65 ARM processors", [
+                                   HasV8_2aOps,
+                                   FeatureCrypto,
+                                   FeatureFPARMv8,
+                                   FeatureNEON,
+                                   FeatureCrypto,
+                                   FeatureFullFP16,
+                                   FeatureRCPC,
+                                   FeatureDotProd
+                                   ]>;
+
 def ProcA72     : SubtargetFeature<"a72", "ARMProcFamily", "CortexA72",
                                    "Cortex-A72 ARM processors", [
                                    FeatureCRC,
                                    FeatureCrypto,
                                    FeatureFPARMv8,
                                    FeatureFuseAES,
                                    FeatureNEON,
                                    FeaturePerfMon
def ProcA76     : SubtargetFeature<"a76", "ARMProcFamily", "CortexA76",
                                     FeatureNEON,
                                     FeatureRCPC,
                                     FeatureCrypto,
                                     FeatureFullFP16,
                                     FeatureDotProd,
                                     FeatureSSBS
                                     ]>;
 
+def ProcNeoverseE1 : SubtargetFeature<"neoversee1", "ARMProcFamily",
+                                      "NeoverseE1",
+                                      "Neoverse E1 ARM processors", [
+                                      HasV8_2aOps,
+                                      FeatureFPARMv8,
+                                      FeatureNEON,
+                                      FeatureCrypto,
+                                      FeatureFullFP16,
+                                      FeatureRCPC,
+                                      FeatureDotProd
+                                      ]>;
+
+def ProcNeoverseN1 : SubtargetFeature<"neoversen1", "ARMProcFamily",
+                                      "NeoverseN1",
+                                      "Neoverse N1 ARM processors", [
+                                      HasV8_2aOps,
+                                      FeatureFPARMv8,
+                                      FeatureNEON,
+                                      FeatureRCPC,
+                                      FeatureCrypto,
+                                      FeatureFullFP16,
+                                      FeatureSPE,
+                                      FeatureDotProd
+                                      ]>;
+
 // Note that cyclone does not fuse AES instructions, but newer apple chips do
 // perform the fusion and cyclone is used by default when targetting apple OSes.
 def ProcCyclone : SubtargetFeature<"cyclone", "ARMProcFamily", "Cyclone",
                                    "Cyclone", [
                                    FeatureAlternateSExtLoadCVTF32Pattern,
                                    FeatureArithmeticBccFusion,
                                    FeatureArithmeticCbzFusion,
                                    FeatureCrypto,
def ProcFalkor  : SubtargetFeature<"falkor", "ARMProcFamily", "Falkor",
                                    FeaturePostRAScheduler,
                                    FeaturePredictableSelectIsExpensive,
                                    FeatureRDM,
                                    FeatureZCZeroing,
                                    FeatureLSLFast,
                                    FeatureSlowSTRQro
                                    ]>;
 
 def ProcSaphira  : SubtargetFeature<"saphira", "ARMProcFamily", "Saphira",
                                    "Qualcomm Saphira processors", [
                                    FeatureCrypto,
                                    FeatureCustomCheapAsMoveHandling,
                                    FeatureFPARMv8,
                                    FeatureNEON,
                                    FeatureSPE,
                                    FeaturePerfMon,
                                    FeaturePostRAScheduler,

 def : ProcessorModel<"generic", NoSchedModel, [
                      FeatureFPARMv8,
                      FeatureFuseAES,
                      FeatureNEON,
                      FeaturePerfMon,
                      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-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]>;
 def : ProcessorModel<"exynos-m3", ExynosM3Model, [ProcExynosM3]>;
 def : ProcessorModel<"exynos-m4", ExynosM4Model, [ProcExynosM4]>;
 def : ProcessorModel<"exynos-m5", ExynosM4Model, [ProcExynosM4]>;
 def : ProcessorModel<"falkor", FalkorModel, [ProcFalkor]>;
 def : ProcessorModel<"saphira", FalkorModel, [ProcSaphira]>;

llvm/lib/Target/AArch64/AArch64Subtarget.h

 class AArch64Subtarget final : public AArch64GenSubtargetInfo {
 public:
   enum ARMProcFamilyEnum : uint8_t {
     Others,
     CortexA35,
     CortexA53,
     CortexA55,
     CortexA57,
+    CortexA65,
     CortexA72,
     CortexA73,
     CortexA75,
     CortexA76,
     Cyclone,
     ExynosM1,
     ExynosM3,
     Falkor,
     Kryo,
+    NeoverseE1,
+    NeoverseN1,
     Saphira,
     ThunderX2T99,
     ThunderX,
     ThunderXT81,
     ThunderXT83,
     ThunderXT88,
     TSV110
   };

llvm/lib/Target/ARM/ARM.td

 def : ProcNoItin<"cortex-a76ae",                        [ARMv82a, ProcA76,
                                                          FeatureHWDivThumb,
                                                          FeatureHWDivARM,
                                                          FeatureCrypto,
                                                          FeatureCRC,
                                                          FeatureFullFP16,
                                                          FeatureDotProd]>;
 
+def : ProcNoItin<"neoverse-n1",                         [ARMv82a,
+                                                         FeatureHWDivThumb,
+                                                         FeatureHWDivARM,
+                                                         FeatureCrypto,
+                                                         FeatureCRC,
+                                                         FeatureDotProd]>;
+
 def : ProcessorModel<"cyclone",     SwiftModel,         [ARMv8a, ProcSwift,
                                                          FeatureHasRetAddrStack,
                                                          FeatureNEONForFP,
                                                          FeatureVFP4,
                                                          FeatureMP,
                                                          FeatureHWDivThumb,
                                                          FeatureHWDivARM,
                                                          FeatureAvoidPartialCPSR,

llvm/lib/Target/ARM/ARMSubtarget.h

enum ARMProcFamilyEnum {
     CortexR4,
     CortexR4F,
     CortexR5,
     CortexR52,
     CortexR7,
     Exynos,
     Krait,
     Kryo,
+    NeoverseN1,
     Swift
   };
   enum ARMProcClassEnum {
     None,
 
     AClass,
     MClass,
     RClass

llvm/lib/Target/ARM/ARMSubtarget.cpp

case Exynos:
     if (!isThumb())
       PrefLoopAlignment = 3;
     break;
   case Kryo:
     break;
   case Krait:
     PreISelOperandLatencyAdjustment = 1;
     break;
+  case NeoverseN1:
+    break;
   case Swift:
     MaxInterleaveFactor = 2;
     LdStMultipleTiming = SingleIssuePlusExtras;
     PreISelOperandLatencyAdjustment = 1;
     PartialUpdateClearance = 12;
     break;
   }
 }

llvm/test/CodeGen/AArch64/cpus.ll

 ; This tests that llc accepts all valid AArch64 CPUs
 
 
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=generic 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=cortex-a35 2>&1 | FileCheck %s
 ; 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-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
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=exynos-m4 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=exynos-m5 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=falkor 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=saphira 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=kryo 2>&1 | FileCheck %s

llvm/test/CodeGen/AArch64/remat.ll

 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=cortex-a35 -o - %s | FileCheck %s
 ; 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-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
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=exynos-m4 -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=exynos-m5 -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=falkor -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=saphira -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=kryo -o - %s | FileCheck %s
 ; RUN: llc -mtriple=aarch64-linux-gnuabi -mcpu=thunderx2t99 -o - %s | FileCheck %s
 ; 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
 
 %X = type { i64, i64, i64 }
 declare void @f(%X*)
 define void @t() {
 entry:
   %tmp = alloca %X
   call void @f(%X* %tmp)
 ; 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
 }

llvm/test/MC/AArch64/armv8.2a-dotprod.s

 // 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-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-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
 udot v0.4s, v1.16b, v2.16b
 sdot v0.4s, v1.16b, v2.16b
 udot v0.2s, v1.8b, v2.4b[0]
 sdot v0.2s, v1.8b, v2.4b[1]
 udot v0.4s, v1.16b, v2.4b[2]

llvm/test/MC/AArch64/armv8.3a-rcpc.s

 // 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-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
 
   ldaprb w0, [x0, #0]
   ldaprh w0, [x17, #0]
   ldapr w0, [x1, #0]
   ldapr x0, [x0, #0]

llvm/test/MC/ARM/armv8.2a-dotprod-a32.s

 // 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
 // RUN: not llvm-mc -triple arm -show-encoding < %s 2> %t
 // RUN: FileCheck --check-prefix=CHECK-NO-DOTPROD < %t %s
 // RUN: not llvm-mc -triple arm -mattr=+v8.1a -show-encoding < %s 2> %t
 // RUN: FileCheck --check-prefix=CHECK-NO-DOTPROD < %t %s
 // RUN: not llvm-mc -triple arm -mattr=+v8.2a -show-encoding < %s 2> %t

llvm/test/MC/ARM/armv8.2a-dotprod-t32.s

 // 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
 // RUN: not llvm-mc -triple thumb -show-encoding < %s 2> %t
 // RUN: FileCheck --check-prefix=CHECK-ERROR < %t %s
 // RUN: not llvm-mc -triple thumb -mattr=+v8.1a -show-encoding < %s 2> %t
 // RUN: FileCheck --check-prefix=CHECK-ERROR < %t %s
 // RUN: not llvm-mc -triple thumb -mattr=+v8.2a -show-encoding < %s 2> %t

llvm/test/MC/Disassembler/AArch64/armv8.3a-rcpc.txt

+# 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-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]
 # CHECK: ldapr w0, [x0]
 # CHECK: ldapr x0, [x0]
 [0x00,0xc0,0xbf,0x38]
 [0x00,0xc0,0xbf,0x78]
 [0x00,0xc0,0xbf,0xb8]
 [0x00,0xc0,0xbf,0xf8]
 
 # RUN: not llvm-mc -triple aarch64-none-linux-gnu -mattr=+v8.2a --disassemble < %s 2>&1 | FileCheck --check-prefix=CHECK-V8_2A %s
 
 # CHECK-V8_2A: warning: invalid instruction encoding
 # CHECK-V8_2A: [0x00,0xc0,0xbf,0x38]
 # CHECK-V8_2A:  ^
 # CHECK-V8_2A: warning: invalid instruction encoding
 # CHECK-V8_2A: [0x00,0xc0,0xbf,0x78]
 # CHECK-V8_2A:  ^
 # CHECK-V8_2A: warning: invalid instruction encoding
 # CHECK-V8_2A: [0x00,0xc0,0xbf,0xb8]
 # CHECK-V8_2A:  ^
 # CHECK-V8_2A: warning: invalid instruction encoding
 # CHECK-V8_2A: [0x00,0xc0,0xbf,0xf8]
 # CHECK-V8_2A:  ^
-

llvm/unittests/Support/TargetParserTest.cpp

bool testARMCPU(StringRef CPUName, StringRef ExpectedArch,
   unsigned FPUKind = ARM::getDefaultFPU(CPUName, AK);
   pass &= ARM::getFPUName(FPUKind).equals(ExpectedFPU);
 
   unsigned ExtKind = ARM::getDefaultExtensions(CPUName, AK);
   if (ExtKind > 1 && (ExtKind & ARM::AEK_NONE))
     pass &= ((ExtKind ^ ARM::AEK_NONE) == ExpectedFlags);
   else
     pass &= (ExtKind == ExpectedFlags);
-
   pass &= ARM::getCPUAttr(AK).equals(CPUAttr);
 
   return pass;
 }
 
 TEST(TargetParserTest, testARMCPU) {
   EXPECT_TRUE(testARMCPU("invalid", "invalid", "invalid",
                          ARM::AEK_NONE, ""));
EXPECT_TRUE(testARMCPU("cortex-a76", "armv8.2-a", "crypto-neon-fp-armv8",
                          ARM::AEK_RAS | ARM::AEK_DOTPROD,
                          "8.2-A"));
   EXPECT_TRUE(testARMCPU("cortex-a76ae", "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("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 |
                              ARM::AEK_HWDIVTHUMB | ARM::AEK_DSP,
                          "8-A"));
   EXPECT_TRUE(testARMCPU("exynos-m1", "armv8-a", "crypto-neon-fp-armv8",
                          ARM::AEK_CRC | ARM::AEK_SEC | ARM::AEK_MP |
                          ARM::AEK_VIRT | ARM::AEK_HWDIVARM |
EXPECT_TRUE(testARMCPU("iwmmxt", "iwmmxt", "none",
                          ARM::AEK_NONE, "iwmmxt"));
   EXPECT_TRUE(testARMCPU("xscale", "xscale", "none",
                          ARM::AEK_NONE, "xscale"));
   EXPECT_TRUE(testARMCPU("swift", "armv7s", "neon-vfpv4",
                          ARM::AEK_HWDIVARM | ARM::AEK_HWDIVTHUMB | ARM::AEK_DSP,
                          "7-S"));
 }
 
-static constexpr unsigned NumARMCPUArchs = 86;
+static constexpr unsigned NumARMCPUArchs = 87;
 
 TEST(TargetParserTest, testARMCPUArchList) {
   SmallVector<StringRef, NumARMCPUArchs> List;
   ARM::fillValidCPUArchList(List);
 
   // No list exists for these in this test suite, so ensure all are
   // valid, and match the expected 'magic' count.
   EXPECT_EQ(List.size(), NumARMCPUArchs);
EXPECT_TRUE(testAArch64CPU(
       AArch64::AEK_SIMD | AArch64::AEK_RAS | AArch64::AEK_LSE |
       AArch64::AEK_RDM | AArch64::AEK_FP16 | AArch64::AEK_DOTPROD |
       AArch64::AEK_RCPC, "8.2-A"));
   EXPECT_TRUE(testAArch64CPU(
       "cortex-a57", "armv8-a", "crypto-neon-fp-armv8",
       AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
       AArch64::AEK_SIMD, "8-A"));
   EXPECT_TRUE(testAArch64CPU(
+    "cortex-a65ae", "armv8.2-a", "crypto-neon-fp-armv8",
+    AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
+    AArch64::AEK_RDM | AArch64::AEK_SIMD | AArch64::AEK_RAS | AArch64::AEK_LSE |
+    AArch64::AEK_FP16 | AArch64::AEK_DOTPROD,
+    "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"));
   EXPECT_TRUE(testAArch64CPU(
       "cortex-a73", "armv8-a", "crypto-neon-fp-armv8",
       AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
       AArch64::AEK_SIMD, "8-A"));
   EXPECT_TRUE(testAArch64CPU(
EXPECT_TRUE(testAArch64CPU(
       AArch64::AEK_RCPC| AArch64::AEK_SSBS, "8.2-A"));
   EXPECT_TRUE(testAArch64CPU(
       "cortex-a76ae", "armv8.2-a", "crypto-neon-fp-armv8",
       AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
       AArch64::AEK_RDM | AArch64::AEK_SIMD | AArch64::AEK_RAS |
       AArch64::AEK_LSE | AArch64::AEK_FP16 | AArch64::AEK_DOTPROD |
       AArch64::AEK_RCPC| AArch64::AEK_SSBS, "8.2-A"));
   EXPECT_TRUE(testAArch64CPU(
+     "neoverse-e1", "armv8.2-a", "crypto-neon-fp-armv8",
+     AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
+     AArch64::AEK_RDM | AArch64::AEK_SIMD | AArch64::AEK_RAS |
+     AArch64::AEK_LSE | AArch64::AEK_FP16 | AArch64::AEK_DOTPROD,
+     "8.2-A"));
+  EXPECT_TRUE(testAArch64CPU(
+     "neoverse-n1", "armv8.2-a", "crypto-neon-fp-armv8",
+     AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
+     AArch64::AEK_RDM | AArch64::AEK_SIMD | AArch64::AEK_RAS |
+     AArch64::AEK_LSE | AArch64::AEK_FP16 | AArch64::AEK_DOTPROD |
+     AArch64::AEK_RCPC | AArch64::AEK_PROFILE,
+     "8.2-A"));
+  EXPECT_TRUE(testAArch64CPU(
       "cyclone", "armv8-a", "crypto-neon-fp-armv8",
       AArch64::AEK_CRYPTO | AArch64::AEK_FP | AArch64::AEK_SIMD, "8-A"));
   EXPECT_TRUE(testAArch64CPU(
       "exynos-m1", "armv8-a", "crypto-neon-fp-armv8",
       AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
       AArch64::AEK_SIMD, "8-A"));
   EXPECT_TRUE(testAArch64CPU(
       "exynos-m2", "armv8-a", "crypto-neon-fp-armv8",
EXPECT_TRUE(testAArch64CPU(
       "tsv110", "armv8.2-a", "crypto-neon-fp-armv8",
       AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
       AArch64::AEK_SIMD | AArch64::AEK_RAS | AArch64::AEK_LSE |
       AArch64::AEK_RDM | AArch64::AEK_PROFILE | AArch64::AEK_FP16 |
       AArch64::AEK_FP16FML | AArch64::AEK_DOTPROD,
       "8.2-A"));
 }
 
-static constexpr unsigned NumAArch64CPUArchs = 24;
+static constexpr unsigned NumAArch64CPUArchs = 27;
 
 TEST(TargetParserTest, testAArch64CPUArchList) {
   SmallVector<StringRef, NumAArch64CPUArchs> List;
   AArch64::fillValidCPUArchList(List);
 
   // No list exists for these in this test suite, so ensure all are
   // valid, and match the expected 'magic' count.
   EXPECT_EQ(List.size(), NumAArch64CPUArchs);