[ARM] Introduce the v9.5-A architecture version to Arm targets (#78994)

This introduces the Armv9.5-A architecture version to the Arm backend,
following on from the existing implementation for AArch64 targets.

Mode details about the Armv9.5-A architecture version can be found at:
* https://community.arm.com/arm-community-blogs/b/architectures-and-processors-blog/posts/arm-a-profile-architecture-developments-2023
* https://developer.arm.com/documentation/ddi0602/2023-09/

Author: pratlucas

clang/lib/Basic/Targets/ARM.cpp

@@ -227,6 +227,8 @@ StringRef ARMTargetInfo::getCPUAttr() const {
     return "9_3A";
   case llvm::ARM::ArchKind::ARMV9_4A:
     return "9_4A";
+  case llvm::ARM::ArchKind::ARMV9_5A:
+    return "9_5A";
   case llvm::ARM::ArchKind::ARMV8MBaseline:
     return "8M_BASE";
   case llvm::ARM::ArchKind::ARMV8MMainline:
@@ -889,6 +891,7 @@ void ARMTargetInfo::getTargetDefines(const LangOptions &Opts,
   case llvm::ARM::ArchKind::ARMV9_2A:
   case llvm::ARM::ArchKind::ARMV9_3A:
   case llvm::ARM::ArchKind::ARMV9_4A:
+  case llvm::ARM::ArchKind::ARMV9_5A:
     // Filter __arm_cdp, __arm_ldcl, __arm_stcl in arm_acle.h
     FeatureCoprocBF = FEATURE_COPROC_B1 | FEATURE_COPROC_B3;
     break;
@@ -1057,6 +1060,7 @@ void ARMTargetInfo::getTargetDefines(const LangOptions &Opts,
   case llvm::ARM::ArchKind::ARMV9_2A:
   case llvm::ARM::ArchKind::ARMV9_3A:
   case llvm::ARM::ArchKind::ARMV9_4A:
+  case llvm::ARM::ArchKind::ARMV9_5A:
     getTargetDefinesARMV83A(Opts, Builder);
     break;
   }

clang/test/CodeGen/arm-acle-coproc.c

@@ -24,6 +24,7 @@
 // RUN: %clang_cc1 -triple armv9.2a %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8 %s
 // RUN: %clang_cc1 -triple armv9.3a %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8 %s
 // RUN: %clang_cc1 -triple armv9.4a %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8 %s
+// RUN: %clang_cc1 -triple armv9.5a %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8 %s
 // RUN: %clang_cc1 -triple thumbv4 %s -E -dD -o - | FileCheck --check-prefix=CHECK-V4-THUMB %s
 // RUN: %clang_cc1 -triple thumbv4t %s -E -dD -o - | FileCheck --check-prefix=CHECK-V4-THUMB %s
 // RUN: %clang_cc1 -triple thumbv5 %s -E -dD -o - | FileCheck --check-prefix=CHECK-V5-THUMB %s
@@ -52,6 +53,7 @@
 // RUN: %clang_cc1 -triple thumbv9.2a %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8 %s
 // RUN: %clang_cc1 -triple thumbv9.3a %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8 %s
 // RUN: %clang_cc1 -triple thumbv9.4a %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8 %s
+// RUN: %clang_cc1 -triple thumbv9.5a %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8 %s
 // RUN: %clang_cc1 -triple thumbv8m.base %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8-BASE %s
 // RUN: %clang_cc1 -triple thumbv8m.main %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8-MAIN %s
 // RUN: %clang_cc1 -triple thumbv8.1m.main %s -E -dD -o - | FileCheck --check-prefix=CHECK-V8-MAIN %s

clang/test/Driver/arm-cortex-cpus-1.c

@@ -478,3 +478,20 @@
 // RUN: %clang -target arm -march=armebv9.4a -mbig-endian -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-BE-V94A %s
 // RUN: %clang -target arm -march=armebv9.4-a -mbig-endian -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-BE-V94A %s
 // CHECK-BE-V94A: "-cc1"{{.*}} "-triple" "armebv9.4{{.*}}" "-target-cpu" "generic"
+
+// RUN: %clang -target armv9.5a -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-V95A %s
+// RUN: %clang -target arm -march=armv9.5a -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-V95A %s
+// RUN: %clang -target arm -march=armv9.5-a -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-V95A %s
+// RUN: %clang -target arm -march=armv9.5a -mlittle-endian -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-V95A %s
+// RUN: %clang -target armv9.5a -mlittle-endian -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-V95A %s
+// RUN: %clang -target arm -march=armv9.5a -mlittle-endian -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-V95A %s
+// RUN: %clang -target arm -mlittle-endian -march=armv9.5-a -mlittle-endian -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-V95A %s
+// CHECK-V95A: "-cc1"{{.*}} "-triple" "armv9.5{{.*}}" "-target-cpu" "generic"
+
+// RUN: %clang -target armebv9.5a -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-BE-V95A %s
+// RUN: %clang -target armv9.5a -mbig-endian -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-BE-V95A %s
+// RUN: %clang -target armeb -march=armebv9.5a -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-BE-V95A %s
+// RUN: %clang -target armeb -march=armebv9.5-a -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-BE-V95A %s
+// RUN: %clang -target arm -march=armebv9.5a -mbig-endian -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-BE-V95A %s
+// RUN: %clang -target arm -march=armebv9.5-a -mbig-endian -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-BE-V95A %s
+// CHECK-BE-V95A: "-cc1"{{.*}} "-triple" "armebv9.5{{.*}}" "-target-cpu" "generic"

clang/test/Preprocessor/arm-target-features.c

@@ -897,6 +897,11 @@
 // CHECK-V94A: #define __ARM_ARCH_9_4A__ 1
 // CHECK-V94A: #define __ARM_ARCH_PROFILE 'A'
 
+// RUN: %clang -target armv9.5a-none-none-eabi -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-V95A %s
+// CHECK-V95A: #define __ARM_ARCH 9
+// CHECK-V95A: #define __ARM_ARCH_9_5A__ 1
+// CHECK-V95A: #define __ARM_ARCH_PROFILE 'A'
+
 // RUN: %clang -target arm-none-none-eabi -march=armv7-m -mfpu=softvfp -x c -E -dM %s -o - | FileCheck --check-prefix=CHECK-SOFTVFP %s
 // CHECK-SOFTVFP-NOT: #define __ARM_FP 0x
 

llvm/include/llvm/TargetParser/ARMTargetParser.def

@@ -151,6 +151,11 @@ ARM_ARCH("armv9.4-a", ARMV9_4A, "9.4-A", "+v9.4a",
          (ARM::AEK_SEC | ARM::AEK_MP | ARM::AEK_VIRT | ARM::AEK_HWDIVARM |
           ARM::AEK_HWDIVTHUMB | ARM::AEK_DSP | ARM::AEK_CRC | ARM::AEK_RAS |
           ARM::AEK_DOTPROD | ARM::AEK_BF16 | ARM::AEK_I8MM))
+ARM_ARCH("armv9.5-a", ARMV9_5A, "9.5-A", "+v9.5a",
+         ARMBuildAttrs::CPUArch::v9_A, FK_NEON_FP_ARMV8,
+         (ARM::AEK_SEC | ARM::AEK_MP | ARM::AEK_VIRT | ARM::AEK_HWDIVARM |
+          ARM::AEK_HWDIVTHUMB | ARM::AEK_DSP | ARM::AEK_CRC | ARM::AEK_RAS |
+          ARM::AEK_DOTPROD | ARM::AEK_BF16 | ARM::AEK_I8MM))
 ARM_ARCH("armv8-r", ARMV8R, "8-R", "+v8r", ARMBuildAttrs::CPUArch::v8_R,
           FK_NEON_FP_ARMV8,
           (ARM::AEK_MP | ARM::AEK_VIRT | ARM::AEK_HWDIVARM | ARM::AEK_HWDIVTHUMB |

llvm/lib/Target/ARM/ARM.td

@@ -704,6 +704,12 @@ def HasV9_4aOps   : SubtargetFeature<"v9.4a", "HasV9_4aOps", "true",
                                    "Support ARM v9.4a instructions",
                                    [HasV8_9aOps, HasV9_3aOps]>;
 
+// Armv9.5-A is a v9-only architecture. From v9.5-A onwards there's no mapping
+// to an equivalent v8.x version.
+def HasV9_5aOps   : SubtargetFeature<"v9.5a", "HasV9_5aOps", "true",
+                                   "Support ARM v9.5a instructions",
+                                   [HasV9_4aOps]>;
+
 def HasV8_1MMainlineOps : SubtargetFeature<
                "v8.1m.main", "HasV8_1MMainlineOps", "true",
                "Support ARM v8-1M Mainline instructions",
@@ -1139,6 +1145,18 @@ def ARMv94a   : Architecture<"armv9.4-a", "ARMv94a",  [HasV9_4aOps,
                                                        FeatureCRC,
                                                        FeatureRAS,
                                                        FeatureDotProd]>;
+def ARMv95a   : Architecture<"armv9.5-a", "ARMv95a",  [HasV9_5aOps,
+                                                       FeatureAClass,
+                                                       FeatureDB,
+                                                       FeatureFPARMv8,
+                                                       FeatureNEON,
+                                                       FeatureDSP,
+                                                       FeatureTrustZone,
+                                                       FeatureMP,
+                                                       FeatureVirtualization,
+                                                       FeatureCRC,
+                                                       FeatureRAS,
+                                                       FeatureDotProd]>;
 
 def ARMv8r    : Architecture<"armv8-r",   "ARMv8r",   [HasV8Ops,
                                                        FeatureRClass,

llvm/lib/Target/ARM/ARMSubtarget.h

@@ -132,6 +132,7 @@ class ARMSubtarget : public ARMGenSubtargetInfo {
     ARMv92a,
     ARMv93a,
     ARMv94a,
+    ARMv95a,
   };
 
 public:

llvm/lib/Target/ARM/MCTargetDesc/ARMELFStreamer.cpp

@@ -898,6 +898,7 @@ void ARMTargetELFStreamer::emitArchDefaultAttributes() {
   case ARM::ArchKind::ARMV9_2A:
   case ARM::ArchKind::ARMV9_3A:
   case ARM::ArchKind::ARMV9_4A:
+  case ARM::ArchKind::ARMV9_5A:
     S.setAttributeItem(CPU_arch_profile, ApplicationProfile, false);
     S.setAttributeItem(ARM_ISA_use, Allowed, false);
     S.setAttributeItem(THUMB_ISA_use, AllowThumb32, false);

llvm/lib/TargetParser/ARMTargetParser.cpp

@@ -86,6 +86,7 @@ unsigned ARM::parseArchVersion(StringRef Arch) {
   case ArchKind::ARMV9_2A:
   case ArchKind::ARMV9_3A:
   case ArchKind::ARMV9_4A:
+  case ArchKind::ARMV9_5A:
     return 9;
   case ArchKind::INVALID:
     return 0;
@@ -123,6 +124,7 @@ static ARM::ProfileKind getProfileKind(ARM::ArchKind AK) {
   case ARM::ArchKind::ARMV9_2A:
   case ARM::ArchKind::ARMV9_3A:
   case ARM::ArchKind::ARMV9_4A:
+  case ARM::ArchKind::ARMV9_5A:
     return ARM::ProfileKind::A;
   case ARM::ArchKind::ARMV4:
   case ARM::ArchKind::ARMV4T:

llvm/lib/TargetParser/Triple.cpp

@@ -811,6 +811,8 @@ static Triple::SubArchType parseSubArch(StringRef SubArchName) {
     return Triple::ARMSubArch_v9_3a;
   case ARM::ArchKind::ARMV9_4A:
     return Triple::ARMSubArch_v9_4a;
+  case ARM::ArchKind::ARMV9_5A:
+    return Triple::ARMSubArch_v9_5a;
   case ARM::ArchKind::ARMV8R:
     return Triple::ARMSubArch_v8r;
   case ARM::ArchKind::ARMV8MBaseline:

llvm/unittests/TargetParser/TargetParserTest.cpp

@@ -45,7 +45,7 @@ const char *ARMArch[] = {
     "armv8m.main",  "iwmmxt",      "iwmmxt2",        "xscale",      "armv8.1-m.main",
     "armv9-a",      "armv9",       "armv9a",         "armv9.1-a",   "armv9.1a",
     "armv9.2-a",    "armv9.2a",    "armv9.3-a",      "armv9.3a",    "armv9.4-a",
-    "armv9.4a",
+    "armv9.4a",     "armv9.5-a",   "armv9.5a",
 };
 
 std::string FormatExtensionFlags(int64_t Flags) {
@@ -605,6 +605,9 @@ TEST(TargetParserTest, testARMArch) {
   EXPECT_TRUE(
       testARMArch("armv9.4-a", "generic", "v9.4a",
                           ARMBuildAttrs::CPUArch::v9_A));
+  EXPECT_TRUE(
+      testARMArch("armv9.5-a", "generic", "v9.5a",
+                          ARMBuildAttrs::CPUArch::v9_A));
   EXPECT_TRUE(
       testARMArch("armv8-r", "cortex-r52", "v8r",
                           ARMBuildAttrs::CPUArch::v8_R));
@@ -940,6 +943,7 @@ TEST(TargetParserTest, ARMparseArchProfile) {
     case ARM::ArchKind::ARMV9_2A:
     case ARM::ArchKind::ARMV9_3A:
     case ARM::ArchKind::ARMV9_4A:
+    case ARM::ArchKind::ARMV9_5A:
       EXPECT_EQ(ARM::ProfileKind::A, ARM::parseArchProfile(ARMArch[i]));
       break;
     default: