diff --git a/clang/test/Driver/aarch64-cpus.c b/clang/test/Driver/aarch64-cpus.c --- a/clang/test/Driver/aarch64-cpus.c +++ b/clang/test/Driver/aarch64-cpus.c @@ -173,6 +173,10 @@ // RUN: %clang -target aarch64 -mcpu=cortex-a77 -### -c %s 2>&1 | FileCheck -check-prefix=CORTEX-A77 %s // CORTEX-A77: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "cortex-a77" +// RUN: %clang -target aarch64 -mcpu=cortex-x1 -### -c %s 2>&1 | FileCheck -check-prefix=CORTEXX1 %s +// CORTEXX1: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "cortex-x1" +// RUN: %clang -target aarch64 -mcpu=cortex-a78 -### -c %s 2>&1 | FileCheck -check-prefix=CORTEXA78 %s +// CORTEXA78: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "cortex-a78" // RUN: %clang -target aarch64_be -mcpu=exynos-m3 -### -c %s 2>&1 | FileCheck -check-prefix=M3 %s // RUN: %clang -target aarch64 -mbig-endian -mcpu=exynos-m3 -### -c %s 2>&1 | FileCheck -check-prefix=M3 %s diff --git a/clang/test/Driver/arm-cortex-cpus.c b/clang/test/Driver/arm-cortex-cpus.c --- a/clang/test/Driver/arm-cortex-cpus.c +++ b/clang/test/Driver/arm-cortex-cpus.c @@ -840,6 +840,18 @@ // CHECK-CORTEX-A76AE-SOFT: "-target-feature" "+soft-float" // CHECK-CORTEX-A76AE-SOFT: "-target-feature" "+soft-float-abi" +// RUN: %clang -target armv8a-arm-none-eabi -mcpu=cortex-x1 -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-CORTEX-X1 %s +// RUN: %clang -target armv8a-arm-none-eabi -mcpu=cortex-x1 -mfpu=crypto-neon-fp-armv8 -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-CORTEX-X1-MFPU %s +// CHECK-CORTEX-X1: "-cc1"{{.*}} "-triple" "armv8.2a-{{.*}} "-target-cpu" "cortex-x1" +// CHECK-CORTEX-X1-MFPU: "-cc1"{{.*}} "-target-feature" "+fp-armv8" +// CHECK-CORTEX-X1-MFPU: "-target-feature" "+crypto" + +// RUN: %clang -target armv8a-arm-none-eabi -mcpu=cortex-a78 -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-CORTEX-A78 %s +// RUN: %clang -target armv8a-arm-none-eabi -mcpu=cortex-a78 -mfpu=crypto-neon-fp-armv8 -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-CORTEX-A78-MFPU %s +// CHECK-CORTEX-A78: "-cc1"{{.*}} "-triple" "armv8.2a-{{.*}} "-target-cpu" "cortex-a78" +// CHECK-CORTEX-A78-MFPU: "-cc1"{{.*}} "-target-feature" "+fp-armv8" +// CHECK-CORTEX-A78-MFPU: "-target-feature" "+crypto" + // RUN: %clang -target arm -mcpu=cortex-m23 -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-CPUV8MBASE %s // CHECK-CPUV8MBASE: "-cc1"{{.*}} "-triple" "thumbv8m.base- diff --git a/llvm/include/llvm/Support/AArch64TargetParser.def b/llvm/include/llvm/Support/AArch64TargetParser.def --- a/llvm/include/llvm/Support/AArch64TargetParser.def +++ b/llvm/include/llvm/Support/AArch64TargetParser.def @@ -127,6 +127,10 @@ AARCH64_CPU_NAME("cortex-a77", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false, (AArch64::AEK_FP16 | AArch64::AEK_RCPC | AArch64::AEK_DOTPROD | AArch64::AEK_SSBS)) +AARCH64_CPU_NAME("cortex-a78", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false, + (AArch64::AEK_RAS | AArch64::AEK_DOTPROD | AArch64::AEK_RCPC | AArch64::AEK_SSBS)) +AARCH64_CPU_NAME("cortex-x1", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false, + (AArch64::AEK_RAS | AArch64::AEK_DOTPROD | AArch64::AEK_RCPC | AArch64::AEK_SSBS)) AARCH64_CPU_NAME("neoverse-e1", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false, (AArch64::AEK_DOTPROD | AArch64::AEK_FP16 | AArch64::AEK_RAS | AArch64::AEK_RCPC | AArch64::AEK_SSBS)) diff --git a/llvm/include/llvm/Support/ARMTargetParser.def b/llvm/include/llvm/Support/ARMTargetParser.def --- a/llvm/include/llvm/Support/ARMTargetParser.def +++ b/llvm/include/llvm/Support/ARMTargetParser.def @@ -296,6 +296,10 @@ (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("cortex-x1", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false, + (ARM::AEK_RAS | ARM::AEK_DOTPROD)) +ARM_CPU_NAME("cortex-a78",ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false, + (ARM::AEK_RAS | ARM::AEK_DOTPROD)) ARM_CPU_NAME("cyclone", 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, diff --git a/llvm/lib/Support/Host.cpp b/llvm/lib/Support/Host.cpp --- a/llvm/lib/Support/Host.cpp +++ b/llvm/lib/Support/Host.cpp @@ -205,6 +205,8 @@ .Case("0xd0a", "cortex-a75") .Case("0xd0b", "cortex-a76") .Case("0xd0d", "cortex-a77") + .Case("0xd41", "cortex-a78") + .Case("0xd44", "cortex-x1") .Case("0xd0c", "neoverse-n1") .Default("generic"); } diff --git a/llvm/lib/Target/AArch64/AArch64.td b/llvm/lib/Target/AArch64/AArch64.td --- a/llvm/lib/Target/AArch64/AArch64.td +++ b/llvm/lib/Target/AArch64/AArch64.td @@ -846,6 +846,36 @@ FeatureSSBS, ]>; +def ProcCortexX1 : SubtargetFeature<"cortex-x1", "ARMProcFamily", "CortexX1", + "Cortex-X1 ARM processors", [ + HasV8_2aOps, + FeatureCrypto, + FeatureFPARMv8, + FeatureFuseAES, + FeatureNEON, + FeaturePerfMon, + FeaturePostRAScheduler, + FeatureSPE, + FeatureFullFP16, + FeatureFP16FML, + FeatureDotProd]>; + +def ProcCortexA78 : SubtargetFeature<"cortex-a78", "ARMProcFamily", + "CortexA78", + "Cortex-A78 ARM processors", [ + HasV8_2aOps, + FeatureCrypto, + FeatureFPARMv8, + FeatureFuseAES, + FeatureNEON, + FeaturePerfMon, + FeaturePostRAScheduler, + FeatureSPE, + FeatureFullFP16, + FeatureFP16FML, + FeatureSSBS, + FeatureDotProd]>; + def ProcSaphira : SubtargetFeature<"saphira", "ARMProcFamily", "Saphira", "Qualcomm Saphira processors", [ FeatureCrypto, @@ -978,6 +1008,8 @@ def : ProcessorModel<"cortex-a76", CortexA57Model, [ProcA76]>; def : ProcessorModel<"cortex-a76ae", CortexA57Model, [ProcA76]>; def : ProcessorModel<"cortex-a77", CortexA57Model, [ProcA77]>; +def : ProcessorModel<"cortex-x1", CortexA57Model, [ProcCortexX1]>; +def : ProcessorModel<"cortex-a78", CortexA57Model, [ProcCortexA78]>; def : ProcessorModel<"neoverse-e1", CortexA53Model, [ProcNeoverseE1]>; def : ProcessorModel<"neoverse-n1", CortexA57Model, [ProcNeoverseN1]>; def : ProcessorModel<"exynos-m3", ExynosM3Model, [ProcExynosM3]>; diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h --- a/llvm/lib/Target/AArch64/AArch64Subtarget.h +++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h @@ -68,7 +68,9 @@ ThunderXT83, ThunderXT88, TSV110, - ThunderX3T110 + ThunderX3T110, + CortexX1, + CortexA78 }; protected: diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp --- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp +++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp @@ -192,6 +192,10 @@ // FIXME: remove this to enable 64-bit SLP if performance looks good. MinVectorRegisterBitWidth = 128; break; + case CortexX1: + case CortexA78: + PrefFunctionLogAlignment = 4; + break; } } diff --git a/llvm/lib/Target/ARM/ARM.td b/llvm/lib/Target/ARM/ARM.td --- a/llvm/lib/Target/ARM/ARM.td +++ b/llvm/lib/Target/ARM/ARM.td @@ -596,6 +596,10 @@ "Cortex-A76 ARM processors", []>; def ProcA77 : SubtargetFeature<"a77", "ARMProcFamily", "CortexA77", "Cortex-A77 ARM processors", []>; +def ProcX1 : SubtargetFeature<"cortex-x1", "ARMProcFamily", "CortexX1", + "Cortex-X1 ARM processors", []>; +def ProcA78 : SubtargetFeature<"cortex-a78", "ARMProcFamily", "CortexA78", + "Cortex-A78 ARM processors", []>; def ProcKrait : SubtargetFeature<"krait", "ARMProcFamily", "Krait", "Qualcomm Krait processors", []>; @@ -1234,6 +1238,22 @@ FeatureFullFP16, FeatureDotProd]>; +def : ProcNoItin<"cortex-x1", [ARMv82a, + FeatureHWDivThumb, + FeatureHWDivARM, + FeatureCrypto, + FeatureCRC, + FeatureFullFP16, + FeatureDotProd]>; + +def : ProcNoItin<"cortex-a78", [ARMv82a, + FeatureHWDivThumb, + FeatureHWDivARM, + FeatureCrypto, + FeatureCRC, + FeatureFullFP16, + FeatureDotProd]>; + def : ProcNoItin<"neoverse-n1", [ARMv82a, FeatureHWDivThumb, FeatureHWDivARM, diff --git a/llvm/lib/Target/ARM/ARMSubtarget.h b/llvm/lib/Target/ARM/ARMSubtarget.h --- a/llvm/lib/Target/ARM/ARMSubtarget.h +++ b/llvm/lib/Target/ARM/ARMSubtarget.h @@ -74,7 +74,9 @@ Krait, Kryo, NeoverseN1, - Swift + Swift, + CortexX1, + CortexA78 }; enum ARMProcClassEnum { None, diff --git a/llvm/lib/Target/ARM/ARMSubtarget.cpp b/llvm/lib/Target/ARM/ARMSubtarget.cpp --- a/llvm/lib/Target/ARM/ARMSubtarget.cpp +++ b/llvm/lib/Target/ARM/ARMSubtarget.cpp @@ -319,6 +319,9 @@ PreISelOperandLatencyAdjustment = 1; PartialUpdateClearance = 12; break; + case CortexX1: + case CortexA78: + break; } } diff --git a/llvm/unittests/Support/TargetParserTest.cpp b/llvm/unittests/Support/TargetParserTest.cpp --- a/llvm/unittests/Support/TargetParserTest.cpp +++ b/llvm/unittests/Support/TargetParserTest.cpp @@ -262,6 +262,18 @@ ARM::AEK_HWDIVTHUMB | ARM::AEK_DSP | ARM::AEK_FP16 | ARM::AEK_RAS | ARM::AEK_DOTPROD, "8.2-A")); + EXPECT_TRUE(testARMCPU("cortex-x1", "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")); + EXPECT_TRUE(testARMCPU("cortex-a78", "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")); 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 | @@ -310,7 +322,7 @@ "7-S")); } -static constexpr unsigned NumARMCPUArchs = 87; +static constexpr unsigned NumARMCPUArchs = 89; TEST(TargetParserTest, testARMCPUArchList) { SmallVector List; @@ -865,6 +877,20 @@ AArch64::AEK_LSE | AArch64::AEK_FP16 | AArch64::AEK_DOTPROD | AArch64::AEK_RCPC | AArch64::AEK_SSBS, "8.2-A")); EXPECT_TRUE(testAArch64CPU( + "cortex-a78", "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_DOTPROD | + AArch64::AEK_RCPC | AArch64::AEK_SSBS, + "8.2-A")); + EXPECT_TRUE(testAArch64CPU( + "cortex-x1", "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_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")); EXPECT_TRUE(testAArch64CPU( @@ -1002,7 +1028,7 @@ "8.2-A")); } -static constexpr unsigned NumAArch64CPUArchs = 40; +static constexpr unsigned NumAArch64CPUArchs = 42; TEST(TargetParserTest, testAArch64CPUArchList) { SmallVector List;