[ARM][AArch64] Add support for Arm Cortex A78AE CPU

clang/docs/ReleaseNotes.rst

@@ -384,6 +384,8 @@ Arm and AArch64 Support
   instructions (rdm). The identifier is available on the command line as
   a feature modifier for -march and -mcpu as well as via target attributes
   like ``target_version`` or ``target_clones``.
+- Support has been added for the following processors (-mcpu identifiers in parenthesis):
+    * Arm Cortex-A78AE (cortex-a78ae).
 
 Android Support
 ^^^^^^^^^^^^^^^

clang/test/Driver/aarch64-mcpu.c

@@ -50,6 +50,8 @@
 // CORTEXA78: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "cortex-a78"
 // RUN: %clang --target=aarch64 -mcpu=cortex-a78c  -### -c %s 2>&1 | FileCheck -check-prefix=CORTEX-A78C %s
 // CORTEX-A78C: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "cortex-a78c"
+// RUN: %clang --target=aarch64 -mcpu=cortex-a78ae  -### -c %s 2>&1 | FileCheck -check-prefix=CORTEX-A78AE %s
+// CORTEX-A78AE: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "cortex-a78ae"
 // RUN: %clang --target=aarch64 -mcpu=cortex-a715  -### -c %s 2>&1 | FileCheck -check-prefix=CORTEX-A715 %s
 // CORTEX-A715: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "cortex-a715"
 // RUN: %clang --target=aarch64 -mcpu=cortex-a720  -### -c %s 2>&1 | FileCheck -check-prefix=CORTEX-A720 %s

clang/test/Driver/arm-cortex-cpus-2.c

@@ -537,6 +537,13 @@
 // CHECK-CORTEX-A78C-MFPU: "-target-feature" "+sha2"
 // CHECK-CORTEX-A78C-MFPU: "-target-feature" "+aes"
 
+// RUN: %clang -target armv8a-arm-none-eabi -mcpu=cortex-a78ae -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-CORTEX-A78AE %s
+// RUN: %clang -target armv8a-arm-none-eabi -mcpu=cortex-a78ae -mfpu=crypto-neon-fp-armv8 -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-CORTEX-A78AE-MFPU %s
+// CHECK-CORTEX-A78AE: "-cc1"{{.*}} "-triple" "armv8.2a-{{.*}} "-target-cpu" "cortex-a78ae"
+// CHECK-CORTEX-A78AE-MFPU: "-cc1"{{.*}} "-target-feature" "+fp-armv8"
+// CHECK-CORTEX-A78AE-MFPU: "-target-feature" "+sha2"
+// CHECK-CORTEX-A78AE-MFPU: "-target-feature" "+aes"
+
 // RUN: %clang -target armv8a-arm-none-eabi -mcpu=cortex-a710 -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-CORTEX-A710 %s
 // RUN: %clang -target armv8a-arm-none-eabi -mcpu=cortex-a710 -mfpu=crypto-neon-fp-armv8 -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-CORTEX-A710-MFPU %s
 // CHECK-CORTEX-A710: "-cc1"{{.*}} "-triple" "armv9a-{{.*}} "-target-cpu" "cortex-a710"

clang/test/Misc/target-invalid-cpu-note.c

@@ -1,15 +1,15 @@
 // Use CHECK-NEXT instead of multiple CHECK-SAME to ensure we will fail if there is anything extra in the output.
 // RUN: not %clang_cc1 -triple armv5--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix ARM
 // ARM: error: unknown target CPU 'not-a-cpu'
-// ARM-NEXT: note: valid target CPU values are: arm8, arm810, strongarm, strongarm110, strongarm1100, strongarm1110, arm7tdmi, arm7tdmi-s, arm710t, arm720t, arm9, arm9tdmi, arm920, arm920t, arm922t, arm940t, ep9312, arm10tdmi, arm1020t, arm9e, arm946e-s, arm966e-s, arm968e-s, arm10e, arm1020e, arm1022e, arm926ej-s, arm1136j-s, arm1136jf-s, mpcore, mpcorenovfp, arm1176jz-s, arm1176jzf-s, arm1156t2-s, arm1156t2f-s, cortex-m0, cortex-m0plus, cortex-m1, sc000, cortex-a5, cortex-a7, cortex-a8, cortex-a9, cortex-a12, cortex-a15, cortex-a17, krait, cortex-r4, cortex-r4f, cortex-r5, cortex-r7, cortex-r8, cortex-r52, sc300, cortex-m3, cortex-m4, cortex-m7, cortex-m23, cortex-m33, cortex-m35p, cortex-m55, cortex-m85, cortex-m52, cortex-a32, cortex-a35, cortex-a53, cortex-a55, cortex-a57, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-x1, cortex-x1c, neoverse-n1, neoverse-n2, neoverse-v1, cyclone, exynos-m3, exynos-m4, exynos-m5, kryo, iwmmxt, xscale, swift{{$}}
+// ARM-NEXT: note: valid target CPU values are: arm8, arm810, strongarm, strongarm110, strongarm1100, strongarm1110, arm7tdmi, arm7tdmi-s, arm710t, arm720t, arm9, arm9tdmi, arm920, arm920t, arm922t, arm940t, ep9312, arm10tdmi, arm1020t, arm9e, arm946e-s, arm966e-s, arm968e-s, arm10e, arm1020e, arm1022e, arm926ej-s, arm1136j-s, arm1136jf-s, mpcore, mpcorenovfp, arm1176jz-s, arm1176jzf-s, arm1156t2-s, arm1156t2f-s, cortex-m0, cortex-m0plus, cortex-m1, sc000, cortex-a5, cortex-a7, cortex-a8, cortex-a9, cortex-a12, cortex-a15, cortex-a17, krait, cortex-r4, cortex-r4f, cortex-r5, cortex-r7, cortex-r8, cortex-r52, sc300, cortex-m3, cortex-m4, cortex-m7, cortex-m23, cortex-m33, cortex-m35p, cortex-m55, cortex-m85, cortex-m52, cortex-a32, cortex-a35, cortex-a53, cortex-a55, cortex-a57, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-a710, cortex-x1, cortex-x1c, neoverse-n1, neoverse-n2, neoverse-v1, cyclone, exynos-m3, exynos-m4, exynos-m5, kryo, iwmmxt, xscale, swift{{$}}
 
 // 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-a520, 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-a715, cortex-a720, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, neoverse-v2, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-a17, apple-m1, apple-m2, apple-m3, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, ampere1a, ampere1b, cobalt-100, grace{{$}}
+// AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a520, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-a710, cortex-a715, cortex-a720, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, neoverse-v2, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-a17, apple-m1, apple-m2, apple-m3, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, ampere1a, ampere1b, cobalt-100, grace{{$}}
 
 // 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-a520, 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-a715, cortex-a720, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, neoverse-v2, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-a17, apple-m1, apple-m2, apple-m3, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, ampere1a, ampere1b, cobalt-100, grace{{$}}
+// TUNE_AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a520, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-a710, cortex-a715, cortex-a720, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, neoverse-v2, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-a17, apple-m1, apple-m2, apple-m3, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, ampere1a, ampere1b, cobalt-100, grace{{$}}
 
 // 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'

llvm/include/llvm/TargetParser/AArch64TargetParser.h

@@ -592,6 +592,11 @@ inline constexpr CpuInfo CpuInfos[] = {
                                AArch64::AEK_FP16, AArch64::AEK_DOTPROD,
                                AArch64::AEK_RCPC, AArch64::AEK_SSBS,
                                AArch64::AEK_PROFILE})},
+    {"cortex-a78ae", ARMV8_2A,
+     AArch64::ExtensionBitset({AArch64::AEK_AES, AArch64::AEK_SHA2,
+                               AArch64::AEK_FP16, AArch64::AEK_DOTPROD,
+                               AArch64::AEK_RCPC, AArch64::AEK_SSBS,
+                               AArch64::AEK_PROFILE})},
     {"cortex-a78c", ARMV8_2A,
      AArch64::ExtensionBitset(
          {AArch64::AEK_AES, AArch64::AEK_SHA2, AArch64::AEK_FP16,

llvm/include/llvm/TargetParser/ARMTargetParser.def

@@ -363,6 +363,8 @@ ARM_CPU_NAME("cortex-a77", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
              (ARM::AEK_FP16 | ARM::AEK_DOTPROD))
 ARM_CPU_NAME("cortex-a78", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
              (ARM::AEK_FP16 | ARM::AEK_DOTPROD))
+ARM_CPU_NAME("cortex-a78ae", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
+             (ARM::AEK_RAS | ARM::AEK_DOTPROD))
 ARM_CPU_NAME("cortex-a78c", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
              ARM::AEK_FP16 | ARM::AEK_DOTPROD)
 ARM_CPU_NAME("cortex-a710", ARMV9A, FK_NEON_FP_ARMV8, false,

llvm/lib/Target/AArch64/AArch64.td

@@ -944,6 +944,18 @@ def TuneA78 : SubtargetFeature<"a78", "ARMProcFamily", "CortexA78",
                                FeatureEnableSelectOptimize,
                                FeaturePredictableSelectIsExpensive]>;
 
+def TuneA78AE : SubtargetFeature<"a78ae", "ARMProcFamily",
+                                 "CortexA78AE",
+                                 "Cortex-A78AE ARM processors", [
+                                 FeatureCmpBccFusion,
+                                 FeatureFuseAES,
+                                 FeatureFuseAdrpAdd,
+                                 FeatureAddrLSLFast,
+                                 FeatureALULSLFast,
+                                 FeaturePostRAScheduler,
+                                 FeatureEnableSelectOptimize,
+                                 FeaturePredictableSelectIsExpensive]>;
+
 def TuneA78C : SubtargetFeature<"a78c", "ARMProcFamily",
                                 "CortexA78C",
                                 "Cortex-A78C ARM processors", [
@@ -1425,6 +1437,10 @@ def ProcessorFeatures {
                                  FeatureNEON, FeatureFullFP16, FeatureDotProd,
                                  FeatureRCPC, FeaturePerfMon, FeatureSPE,
                                  FeatureSSBS];
+  list<SubtargetFeature> A78AE = [HasV8_2aOps, FeatureCrypto, FeatureFPARMv8,
+                                  FeatureNEON, FeatureFullFP16, FeatureDotProd,
+                                  FeatureRCPC, FeaturePerfMon, FeatureSPE,
+                                  FeatureSSBS];
   list<SubtargetFeature> A78C = [HasV8_2aOps, FeatureCrypto, FeatureFPARMv8,
                                  FeatureNEON, FeatureFullFP16, FeatureDotProd,
                                  FeatureFlagM, FeaturePAuth,
@@ -1602,6 +1618,8 @@ def : ProcessorModel<"cortex-a77", CortexA57Model, ProcessorFeatures.A77,
                      [TuneA77]>;
 def : ProcessorModel<"cortex-a78", CortexA57Model, ProcessorFeatures.A78,
                      [TuneA78]>;
+def : ProcessorModel<"cortex-a78ae", CortexA57Model, ProcessorFeatures.A78AE,
+                     [TuneA78AE]>;
 def : ProcessorModel<"cortex-a78c", CortexA57Model, ProcessorFeatures.A78C,
                      [TuneA78C]>;
 def : ProcessorModel<"cortex-a710", NeoverseN2Model, ProcessorFeatures.A710,

llvm/lib/Target/AArch64/AArch64Subtarget.cpp

@@ -140,6 +140,7 @@ void AArch64Subtarget::initializeProperties(bool HasMinSize) {
   case CortexA76:
   case CortexA77:
   case CortexA78:
+  case CortexA78AE:
   case CortexA78C:
   case CortexR82:
   case CortexX1:

llvm/lib/Target/AArch64/AArch64Subtarget.h

@@ -66,6 +66,7 @@ class AArch64Subtarget final : public AArch64GenSubtargetInfo {
     CortexA76,
     CortexA77,
     CortexA78,
+    CortexA78AE,
     CortexA78C,
     CortexA710,
     CortexA715,

llvm/lib/Target/ARM/ARM.td

@@ -809,6 +809,8 @@ def ProcA77     : SubtargetFeature<"a77", "ARMProcFamily", "CortexA77",
                                    "Cortex-A77 ARM processors", []>;
 def ProcA78     : SubtargetFeature<"cortex-a78", "ARMProcFamily", "CortexA78",
                                    "Cortex-A78 ARM processors", []>;
+def ProcA78AE   : SubtargetFeature<"cortex-a78ae", "ARMProcFamily", "CortexA78AE",
+                                   "Cortex-A78AE ARM processors", []>;
 def ProcA78C    : SubtargetFeature<"a78c", "ARMProcFamily", "CortexA78C",
                                    "Cortex-A78C ARM processors", []>;
 def ProcA710    : SubtargetFeature<"cortex-a710", "ARMProcFamily",
@@ -1632,6 +1634,14 @@ def : ProcNoItin<"cortex-a78",                          [ARMv82a, ProcA78,
                                                          FeatureFullFP16,
                                                          FeatureDotProd]>;
 
+def : ProcNoItin<"cortex-a78ae",                        [ARMv82a, ProcA78AE,
+                                                         FeatureHWDivThumb,
+                                                         FeatureHWDivARM,
+                                                         FeatureCrypto,
+                                                         FeatureCRC,
+                                                         FeatureFullFP16,
+                                                         FeatureDotProd]>;
+
 def : ProcNoItin<"cortex-a78c",                         [ARMv82a, ProcA78C,
                                                          FeatureHWDivThumb,
                                                          FeatureHWDivARM,

llvm/lib/Target/ARM/ARMSubtarget.cpp

@@ -289,6 +289,7 @@ void ARMSubtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
   case CortexA76:
   case CortexA77:
   case CortexA78:
+  case CortexA78AE:
   case CortexA78C:
   case CortexA710:
   case CortexR4:

llvm/lib/Target/ARM/ARMSubtarget.h

@@ -66,6 +66,7 @@ class ARMSubtarget : public ARMGenSubtargetInfo {
     CortexA76,
     CortexA77,
     CortexA78,
+    CortexA78AE,
     CortexA78C,
     CortexA710,
     CortexA8,

llvm/lib/TargetParser/Host.cpp

@@ -217,6 +217,7 @@ StringRef sys::detail::getHostCPUNameForARM(StringRef ProcCpuinfoContent) {
         .Case("0xd0b", "cortex-a76")
         .Case("0xd0d", "cortex-a77")
         .Case("0xd41", "cortex-a78")
+        .Case("0xd42", "cortex-a78ae")
         .Case("0xd47", "cortex-a710")
         .Case("0xd4d", "cortex-a715")
         .Case("0xd81", "cortex-a720")

llvm/unittests/TargetParser/TargetParserTest.cpp

@@ -454,6 +454,12 @@ INSTANTIATE_TEST_SUITE_P(
                 ARM::AEK_VIRT | ARM::AEK_HWDIVARM | ARM::AEK_HWDIVTHUMB |
                 ARM::AEK_DSP | ARM::AEK_CRC | ARM::AEK_RAS,
             "8.2-A"),
+        ARMCPUTestParams<uint64_t>(
+            "cortex-a78ae", "armv8.2-a", "crypto-neon-fp-armv8",
+            ARM::AEK_RAS | ARM::AEK_DOTPROD | ARM::AEK_SEC | ARM::AEK_MP |
+                ARM::AEK_VIRT | ARM::AEK_HWDIVARM | ARM::AEK_HWDIVTHUMB |
+                ARM::AEK_DSP | ARM::AEK_CRC | ARM::AEK_RAS,
+            "8.2-A"),
         ARMCPUTestParams<uint64_t>(
             "cortex-x1", "armv8.2-a", "crypto-neon-fp-armv8",
             ARM::AEK_RAS | ARM::AEK_FP16 | ARM::AEK_DOTPROD | ARM::AEK_SEC |
@@ -542,7 +548,7 @@ INSTANTIATE_TEST_SUITE_P(
                                    "7-S")),
     ARMCPUTestParams<uint64_t>::PrintToStringParamName);
 
-static constexpr unsigned NumARMCPUArchs = 90;
+static constexpr unsigned NumARMCPUArchs = 91;
 
 TEST(TargetParserTest, testARMCPUArchList) {
   SmallVector<StringRef, NumARMCPUArchs> List;
@@ -1209,6 +1215,15 @@ INSTANTIATE_TEST_SUITE_P(
                  AArch64::AEK_DOTPROD, AArch64::AEK_RCPC, AArch64::AEK_SSBS,
                  AArch64::AEK_PROFILE}),
             "8.2-A"),
+        ARMCPUTestParams<AArch64::ExtensionBitset>(
+            "cortex-a78ae", "armv8.2-a", "crypto-neon-fp-armv8",
+            AArch64::ExtensionBitset(
+                {AArch64::AEK_CRC, AArch64::AEK_AES, AArch64::AEK_SHA2,
+                 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,
+                 AArch64::AEK_PROFILE}),
+            "8.2-A"),
         ARMCPUTestParams<AArch64::ExtensionBitset>(
             "cortex-a78c", "armv8.2-a", "crypto-neon-fp-armv8",
             AArch64::ExtensionBitset(
@@ -1702,7 +1717,7 @@ INSTANTIATE_TEST_SUITE_P(
     ARMCPUTestParams<AArch64::ExtensionBitset>::PrintToStringParamName);
 
 // Note: number of CPUs includes aliases.
-static constexpr unsigned NumAArch64CPUArchs = 69;
+static constexpr unsigned NumAArch64CPUArchs = 70;
 
 TEST(TargetParserTest, testAArch64CPUArchList) {
   SmallVector<StringRef, NumAArch64CPUArchs> List;