[AArch64] Add support for Cortex-A76 and Cortex-A76AE

- Add LLVM backend support for Cortex-A76 and Cortex-A76AE
- Documentation can be found at
  https://developer.arm.com/products/processors/cortex-a/cortex-a76

llvm-svn: 354788

llvm/include/llvm/Support/AArch64TargetParser.def

@@ -93,6 +93,12 @@ 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("cyclone", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false,
                 (AArch64::AEK_NONE))
 AARCH64_CPU_NAME("exynos-m1", ARMV8A, FK_CRYPTO_NEON_FP_ARMV8, false,

llvm/include/llvm/Support/ARMTargetParser.def

@@ -261,6 +261,10 @@ 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("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)

llvm/lib/Target/AArch64/AArch64.td

@@ -482,6 +482,18 @@ def ProcA75     : SubtargetFeature<"a75", "ARMProcFamily", "CortexA75",
                                    FeaturePerfMon
                                    ]>;
 
+def ProcA76     : SubtargetFeature<"a76", "ARMProcFamily", "CortexA76",
+                                   "Cortex-A76 ARM processors", [
+                                    HasV8_2aOps,
+                                    FeatureFPARMv8,
+                                    FeatureNEON,
+                                    FeatureRCPC,
+                                    FeatureCrypto,
+                                    FeatureFullFP16,
+                                    FeatureDotProd,
+                                    FeatureSSBS
+                                    ]>;
+
 // 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",
@@ -693,10 +705,11 @@ def : ProcessorModel<"cortex-a35", CortexA53Model, [ProcA35]>;
 def : ProcessorModel<"cortex-a53", CortexA53Model, [ProcA53]>;
 def : ProcessorModel<"cortex-a55", CortexA53Model, [ProcA55]>;
 def : ProcessorModel<"cortex-a57", CortexA57Model, [ProcA57]>;
-// FIXME: Cortex-A72, Cortex-A73 and Cortex-A75 are currently modeled as a Cortex-A57.
 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<"cyclone", CycloneModel, [ProcCyclone]>;
 def : ProcessorModel<"exynos-m1", ExynosM1Model, [ProcExynosM1]>;
 def : ProcessorModel<"exynos-m2", ExynosM1Model, [ProcExynosM2]>;

llvm/lib/Target/AArch64/AArch64Subtarget.cpp

@@ -82,6 +82,7 @@ void AArch64Subtarget::initializeProperties() {
   case CortexA72:
   case CortexA73:
   case CortexA75:
+  case CortexA76:
     PrefFunctionAlignment = 4;
     break;
   case Cyclone:

llvm/lib/Target/AArch64/AArch64Subtarget.h

@@ -45,6 +45,7 @@ public:
     CortexA72,
     CortexA73,
     CortexA75,
+    CortexA76,
     Cyclone,
     ExynosM1,
     ExynosM3,

llvm/lib/Target/ARM/ARM.td

@@ -494,6 +494,8 @@ def ProcA73     : SubtargetFeature<"a73", "ARMProcFamily", "CortexA73",
                                    "Cortex-A73 ARM processors", []>;
 def ProcA75     : SubtargetFeature<"a75", "ARMProcFamily", "CortexA75",
                                    "Cortex-A75 ARM processors", []>;
+def ProcA76     : SubtargetFeature<"a76", "ARMProcFamily", "CortexA76",
+                                   "Cortex-A76 ARM processors", []>;
 
 def ProcKrait   : SubtargetFeature<"krait", "ARMProcFamily", "Krait",
                                    "Qualcomm Krait processors", []>;
@@ -1059,6 +1061,22 @@ def : ProcNoItin<"cortex-a75",                          [ARMv82a, ProcA75,
                                                          FeatureHWDivARM,
                                                          FeatureDotProd]>;
 
+def : ProcNoItin<"cortex-a76",                          [ARMv82a, ProcA76,
+                                                         FeatureHWDivThumb,
+                                                         FeatureHWDivARM,
+                                                         FeatureCrypto,
+                                                         FeatureCRC,
+                                                         FeatureFullFP16,
+                                                         FeatureDotProd]>;
+
+def : ProcNoItin<"cortex-a76ae",                        [ARMv82a, ProcA76,
+                                                         FeatureHWDivThumb,
+                                                         FeatureHWDivARM,
+                                                         FeatureCrypto,
+                                                         FeatureCRC,
+                                                         FeatureFullFP16,
+                                                         FeatureDotProd]>;
+
 def : ProcessorModel<"cyclone",     SwiftModel,         [ARMv8a, ProcSwift,
                                                          FeatureHasRetAddrStack,
                                                          FeatureNEONForFP,

llvm/lib/Target/ARM/ARMSubtarget.cpp

@@ -284,6 +284,7 @@ void ARMSubtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
   case CortexA72:
   case CortexA73:
   case CortexA75:
+  case CortexA76:
   case CortexR4:
   case CortexR4F:
   case CortexR5:

llvm/lib/Target/ARM/ARMSubtarget.h

@@ -59,6 +59,7 @@ protected:
     CortexA72,
     CortexA73,
     CortexA75,
+    CortexA76,
     CortexA8,
     CortexA9,
     CortexM3,

llvm/test/CodeGen/AArch64/cpus.ll

@@ -9,6 +9,8 @@
 ; 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=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

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

@@ -1,5 +1,6 @@
 // RUN: llvm-mc -triple aarch64 -mattr=+dotprod -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=tsv110 -show-encoding < %s | FileCheck %s --check-prefix=CHECK-DOTPROD
 // RUN: not llvm-mc -triple aarch64 -mattr=+v8.2a -show-encoding < %s 2> %t

llvm/test/MC/AArch64/armv8.5a-ssbs.s

@@ -1,5 +1,7 @@
 // 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: not llvm-mc -triple aarch64 -show-encoding -mattr=-ssbs  < %s 2>&1 | FileCheck %s --check-prefix=NOSPECID
 
 mrs x2, SSBS

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

@@ -1,5 +1,6 @@
 // RUN: llvm-mc -triple arm -mattr=+dotprod -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: not llvm-mc -triple arm -mattr=-dotprod -show-encoding < %s 2> %t

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

@@ -1,5 +1,6 @@
 // RUN: llvm-mc -triple thumb -mattr=+dotprod -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: not llvm-mc -triple thumb -mattr=-dotprod -show-encoding < %s 2> %t

llvm/test/MC/Disassembler/AArch64/armv8.5a-ssbs.txt

@@ -1,5 +1,7 @@
 # RUN: llvm-mc -triple=aarch64 -mattr=+ssbs  -disassemble < %s | FileCheck %s
 # RUN: llvm-mc -triple=aarch64 -mattr=+v8.5a -disassemble < %s | FileCheck %s
+# RUN: llvm-mc -triple=aarch64 -mcpu=cortex-a76 -disassemble < %s | FileCheck %s
+# RUN: llvm-mc -triple=aarch64 -mcpu=cortex-a76ae -disassemble < %s | FileCheck %s
 # RUN: llvm-mc -triple=aarch64 -mattr=-ssbs  -disassemble < %s | FileCheck %s --check-prefix=NOSPECID
 
 [0x3f 0x41 0x03 0xd5]

llvm/unittests/Support/TargetParserTest.cpp

@@ -244,6 +244,18 @@ TEST(TargetParserTest, testARMCPU) {
                          ARM::AEK_HWDIVTHUMB | ARM::AEK_DSP | ARM::AEK_FP16 |
                          ARM::AEK_RAS | ARM::AEK_DOTPROD,
                          "8.2-A"));
+  EXPECT_TRUE(testARMCPU("cortex-a76", "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("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("cyclone", "armv8-a", "crypto-neon-fp-armv8",
                          ARM::AEK_CRC | ARM::AEK_SEC | ARM::AEK_MP |
                              ARM::AEK_VIRT | ARM::AEK_HWDIVARM |
@@ -283,7 +295,7 @@ TEST(TargetParserTest, testARMCPU) {
                          "7-S"));
 }
 
-static constexpr unsigned NumARMCPUArchs = 82;
+static constexpr unsigned NumARMCPUArchs = 84;
 
 TEST(TargetParserTest, testARMCPUArchList) {
   SmallVector<StringRef, NumARMCPUArchs> List;
@@ -743,6 +755,18 @@ TEST(TargetParserTest, 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-a76", "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(
+      "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(
       "cyclone", "armv8-a", "crypto-neon-fp-armv8",
       AArch64::AEK_CRYPTO | AArch64::AEK_FP | AArch64::AEK_SIMD, "8-A"));
@@ -805,7 +829,7 @@ TEST(TargetParserTest, testAArch64CPU) {
       "8.2-A"));
 }
 
-static constexpr unsigned NumAArch64CPUArchs = 21;
+static constexpr unsigned NumAArch64CPUArchs = 23;
 
 TEST(TargetParserTest, testAArch64CPUArchList) {
   SmallVector<StringRef, NumAArch64CPUArchs> List;