[AArch64] Add support for Cortex-R82AE and improve Cortex-R82 (#90440)

jthackray · web-flow · commit e50a857fb16b · 2024-04-30T14:15:01.000+01:00
diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst
@@ -666,6 +666,7 @@ Arm and AArch64 Support
     * Arm Cortex-A78AE (cortex-a78ae).
     * Arm Cortex-A520AE (cortex-a520ae).
     * Arm Cortex-A720AE (cortex-a720ae).
+    * Arm Cortex-R82AE (cortex-r82ae).
     * Arm Neoverse-N3 (neoverse-n3).
     * Arm Neoverse-V3 (neoverse-v3).
     * Arm Neoverse-V3AE (neoverse-v3ae).
diff --git 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-a520, cortex-a520ae, 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-a720ae, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-n3, neoverse-512tvb, neoverse-v1, neoverse-v2, neoverse-v3, neoverse-v3ae, 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{{$}}
+// AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a520, cortex-a520ae, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-a710, cortex-a715, cortex-a720, cortex-a720ae, cortex-r82, cortex-r82ae, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-n3, neoverse-512tvb, neoverse-v1, neoverse-v2, neoverse-v3, neoverse-v3ae, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-a17, apple-m1, apple-m2, apple-m3, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, ampere1a, ampere1b, cobalt-100, grace{{$}}
 
 // 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-a520ae, 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-a720ae, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-n3, neoverse-512tvb, neoverse-v1, neoverse-v2, neoverse-v3, neoverse-v3ae, 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{{$}}
+// TUNE_AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a520, cortex-a520ae, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78ae, cortex-a78c, cortex-a710, cortex-a715, cortex-a720, cortex-a720ae, cortex-r82, cortex-r82ae, cortex-x1, cortex-x1c, cortex-x2, cortex-x3, cortex-x4, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-n3, neoverse-512tvb, neoverse-v1, neoverse-v2, neoverse-v3, neoverse-v3ae, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-a17, apple-m1, apple-m2, apple-m3, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, ampere1a, ampere1b, cobalt-100, grace{{$}}
 
 // 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'
diff --git a/clang/test/Preprocessor/aarch64-target-features.c b/clang/test/Preprocessor/aarch64-target-features.c
@@ -326,7 +326,7 @@
 // CHECK-MCPU-A57: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+v8a" "-target-feature" "+aes" "-target-feature" "+crc" "-target-feature" "+fp-armv8" "-target-feature" "+sha2" "-target-feature" "+neon"
 // CHECK-MCPU-A72: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+v8a" "-target-feature" "+aes" "-target-feature" "+crc" "-target-feature" "+fp-armv8" "-target-feature" "+sha2" "-target-feature" "+neon"
 // CHECK-MCPU-CORTEX-A73: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+v8a" "-target-feature" "+aes" "-target-feature" "+crc" "-target-feature" "+fp-armv8" "-target-feature" "+sha2" "-target-feature" "+neon"
-// CHECK-MCPU-CORTEX-R82: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+v8r" "-target-feature" "+crc" "-target-feature" "+dotprod" "-target-feature" "+complxnum" "-target-feature" "+fp-armv8" "-target-feature" "+fullfp16" "-target-feature" "+fp16fml" "-target-feature" "+jsconv" "-target-feature" "+lse" "-target-feature" "+pauth" "-target-feature" "+ras" "-target-feature" "+rcpc" "-target-feature" "+rdm" "-target-feature" "+sb" "-target-feature" "+neon" "-target-feature" "+ssbs"
+// CHECK-MCPU-CORTEX-R82: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+v8r" "-target-feature" "+crc" "-target-feature" "+dotprod" "-target-feature" "+complxnum" "-target-feature" "+flagm" "-target-feature" "+fp-armv8" "-target-feature" "+fullfp16" "-target-feature" "+fp16fml" "-target-feature" "+jsconv" "-target-feature" "+lse" "-target-feature" "+pauth" "-target-feature" "+perfmon" "-target-feature" "+predres" "-target-feature" "+ras" "-target-feature" "+rcpc" "-target-feature" "+rdm" "-target-feature" "+sb" "-target-feature" "+neon" "-target-feature" "+ssbs"
 // CHECK-MCPU-M3: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+v8a" "-target-feature" "+aes" "-target-feature" "+crc" "-target-feature" "+fp-armv8" "-target-feature" "+sha2" "-target-feature" "+neon"
 // CHECK-MCPU-M4: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+v8.2a" "-target-feature" "+aes" "-target-feature" "+crc" "-target-feature" "+dotprod" "-target-feature" "+fp-armv8" "-target-feature" "+fullfp16" "-target-feature" "+lse" "-target-feature" "+ras" "-target-feature" "+rdm" "-target-feature" "+sha2" "-target-feature" "+neon"
 // CHECK-MCPU-KRYO: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+v8a" "-target-feature" "+aes" "-target-feature" "+crc" "-target-feature" "+fp-armv8" "-target-feature" "+sha2" "-target-feature" "+neon"
diff --git a/llvm/docs/ReleaseNotes.rst b/llvm/docs/ReleaseNotes.rst
@@ -74,7 +74,7 @@ Changes to the AArch64 Backend
 ------------------------------
 
 * Added support for Cortex-A78AE, Cortex-A520AE, Cortex-A720AE,
-  Neoverse-N3, Neoverse-V3 and Neoverse-V3AE CPUs.
+  Cortex-R82AE, Neoverse-N3, Neoverse-V3 and Neoverse-V3AE CPUs.
 
 Changes to the AMDGPU Backend
 -----------------------------
diff --git a/llvm/include/llvm/TargetParser/AArch64TargetParser.h b/llvm/include/llvm/TargetParser/AArch64TargetParser.h
@@ -573,7 +573,12 @@ inline constexpr CpuInfo CpuInfos[] = {
                                AArch64::AEK_PAUTH, AArch64::AEK_SVE2BITPERM,
                                AArch64::AEK_FLAGM, AArch64::AEK_PERFMON,
                                AArch64::AEK_PREDRES, AArch64::AEK_PROFILE})},
-    {"cortex-r82", ARMV8R, AArch64::ExtensionBitset({AArch64::AEK_LSE})},
+    {"cortex-r82", ARMV8R,
+     AArch64::ExtensionBitset({AArch64::AEK_LSE, AArch64::AEK_FLAGM,
+                               AArch64::AEK_PERFMON, AArch64::AEK_PREDRES})},
+    {"cortex-r82ae", ARMV8R,
+     AArch64::ExtensionBitset({AArch64::AEK_LSE, AArch64::AEK_FLAGM,
+                               AArch64::AEK_PERFMON, AArch64::AEK_PREDRES})},
     {"cortex-x1", ARMV8_2A,
      AArch64::ExtensionBitset({AArch64::AEK_AES, AArch64::AEK_SHA2,
                                AArch64::AEK_FP16, AArch64::AEK_DOTPROD,
diff --git a/llvm/lib/Target/AArch64/AArch64Processors.td b/llvm/lib/Target/AArch64/AArch64Processors.td
@@ -194,6 +194,11 @@ def TuneR82 : SubtargetFeature<"cortex-r82", "ARMProcFamily",
                                "Cortex-R82 ARM processors", [
                                FeaturePostRAScheduler]>;
 
+def TuneR82AE : SubtargetFeature<"cortex-r82ae", "ARMProcFamily",
+                                 "CortexR82AE",
+                                 "Cortex-R82-AE ARM processors",
+                                 [FeaturePostRAScheduler]>;
+
 def TuneX1 : SubtargetFeature<"cortex-x1", "ARMProcFamily", "CortexX1",
                                   "Cortex-X1 ARM processors", [
                                   FeatureCmpBccFusion,
@@ -667,7 +672,13 @@ def ProcessorFeatures {
   list<SubtargetFeature> R82  = [HasV8_0rOps, FeaturePerfMon, FeatureFullFP16,
                                  FeatureFP16FML, FeatureSSBS, FeaturePredRes,
                                  FeatureSB, FeatureRDM, FeatureDotProd,
-                                 FeatureComplxNum, FeatureJS];
+                                 FeatureComplxNum, FeatureJS,
+                                 FeatureCacheDeepPersist];
+  list<SubtargetFeature> R82AE = [HasV8_0rOps, FeaturePerfMon, FeatureFullFP16,
+                                  FeatureFP16FML, FeatureSSBS, FeaturePredRes,
+                                  FeatureSB, FeatureRDM, FeatureDotProd,
+                                  FeatureComplxNum, FeatureJS,
+                                  FeatureCacheDeepPersist];
   list<SubtargetFeature> X1   = [HasV8_2aOps, FeatureCrypto, FeatureFPARMv8,
                                  FeatureNEON, FeatureRCPC, FeaturePerfMon,
                                  FeatureSPE, FeatureFullFP16, FeatureDotProd,
@@ -854,6 +865,8 @@ def : ProcessorModel<"cortex-a720ae", NeoverseN2Model, ProcessorFeatures.A720AE,
                      [TuneA720AE]>;
 def : ProcessorModel<"cortex-r82", CortexA55Model, ProcessorFeatures.R82,
                      [TuneR82]>;
+def : ProcessorModel<"cortex-r82ae", CortexA55Model, ProcessorFeatures.R82AE,
+                     [TuneR82AE]>;
 def : ProcessorModel<"cortex-x1", CortexA57Model, ProcessorFeatures.X1,
                      [TuneX1]>;
 def : ProcessorModel<"cortex-x1c", CortexA57Model, ProcessorFeatures.X1C,
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -117,6 +117,8 @@ void AArch64Subtarget::initializeProperties(bool HasMinSize) {
   case CortexA35:
   case CortexA53:
   case CortexA55:
+  case CortexR82:
+  case CortexR82AE:
     PrefFunctionAlignment = Align(16);
     PrefLoopAlignment = Align(16);
     MaxBytesForLoopAlignment = 8;
@@ -142,7 +144,6 @@ void AArch64Subtarget::initializeProperties(bool HasMinSize) {
   case CortexA78:
   case CortexA78AE:
   case CortexA78C:
-  case CortexR82:
   case CortexX1:
     PrefFunctionAlignment = Align(16);
     PrefLoopAlignment = Align(32);
diff --git a/llvm/lib/TargetParser/Host.cpp b/llvm/lib/TargetParser/Host.cpp
@@ -214,6 +214,7 @@ StringRef sys::detail::getHostCPUNameForARM(StringRef ProcCpuinfoContent) {
         .Case("0xc18", "cortex-r8")
         .Case("0xd13", "cortex-r52")
         .Case("0xd15", "cortex-r82")
+        .Case("0xd14", "cortex-r82ae")
         .Case("0xd02", "cortex-a34")
         .Case("0xd04", "cortex-a35")
         .Case("0xd03", "cortex-a53")
diff --git a/llvm/unittests/TargetParser/TargetParserTest.cpp b/llvm/unittests/TargetParser/TargetParserTest.cpp
@@ -1390,7 +1390,20 @@ INSTANTIATE_TEST_SUITE_P(
                  AArch64::AEK_DOTPROD, AArch64::AEK_FP, AArch64::AEK_SIMD,
                  AArch64::AEK_FP16, AArch64::AEK_FP16FML, AArch64::AEK_RAS,
                  AArch64::AEK_RCPC, AArch64::AEK_LSE, AArch64::AEK_SB,
-                 AArch64::AEK_JSCVT, AArch64::AEK_FCMA, AArch64::AEK_PAUTH}),
+                 AArch64::AEK_JSCVT, AArch64::AEK_FCMA, AArch64::AEK_PAUTH,
+                 AArch64::AEK_FLAGM, AArch64::AEK_PERFMON,
+                 AArch64::AEK_PREDRES}),
+            "8-R"),
+        ARMCPUTestParams<AArch64::ExtensionBitset>(
+            "cortex-r82ae", "armv8-r", "crypto-neon-fp-armv8",
+            AArch64::ExtensionBitset(
+                {AArch64::AEK_CRC, AArch64::AEK_RDM, AArch64::AEK_SSBS,
+                 AArch64::AEK_DOTPROD, AArch64::AEK_FP, AArch64::AEK_SIMD,
+                 AArch64::AEK_FP16, AArch64::AEK_FP16FML, AArch64::AEK_RAS,
+                 AArch64::AEK_RCPC, AArch64::AEK_LSE, AArch64::AEK_SB,
+                 AArch64::AEK_JSCVT, AArch64::AEK_FCMA, AArch64::AEK_PAUTH,
+                 AArch64::AEK_FLAGM, AArch64::AEK_PERFMON,
+                 AArch64::AEK_PREDRES}),
             "8-R"),
         ARMCPUTestParams<AArch64::ExtensionBitset>(
             "cortex-x1", "armv8.2-a", "crypto-neon-fp-armv8",
@@ -1806,7 +1819,7 @@ INSTANTIATE_TEST_SUITE_P(
     ARMCPUTestParams<AArch64::ExtensionBitset>::PrintToStringParamName);
 
 // Note: number of CPUs includes aliases.
-static constexpr unsigned NumAArch64CPUArchs = 75;
+static constexpr unsigned NumAArch64CPUArchs = 76;
 
 TEST(TargetParserTest, testAArch64CPUArchList) {
   SmallVector<StringRef, NumAArch64CPUArchs> List;
