diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst --- a/clang/docs/ReleaseNotes.rst +++ b/clang/docs/ReleaseNotes.rst @@ -733,6 +733,9 @@ them, which it cannot. - Add driver and tuning support for Neoverse V2 via the flag ``-mcpu=neoverse-v2``. Native detection is also supported via ``-mcpu=native``. +- Support has been added for the following processors (-mcpu identifiers in parenthesis): + + * Arm Cortex-A715 (cortex-a715). Floating Point Support in Clang ------------------------------- diff --git a/clang/test/Driver/aarch64-mcpu.c b/clang/test/Driver/aarch64-mcpu.c --- a/clang/test/Driver/aarch64-mcpu.c +++ b/clang/test/Driver/aarch64-mcpu.c @@ -45,6 +45,8 @@ // 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-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=neoverse-e1 -### -c %s 2>&1 | FileCheck -check-prefix=NEOVERSE-E1 %s // NEOVERSE-E1: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "neoverse-e1" // RUN: %clang -target aarch64 -mcpu=neoverse-v1 -### -c %s 2>&1 | FileCheck -check-prefix=NEOVERSE-V1 %s diff --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c --- 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-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, 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-m1, apple-m2, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, grace{{$}} +// AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-a715, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, neoverse-v2, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-m1, apple-m2, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, grace{{$}} // 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-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, 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-m1, apple-m2, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, grace{{$}} +// TUNE_AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-a710, cortex-a715, cortex-r82, cortex-x1, cortex-x1c, cortex-x2, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, neoverse-v2, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-a15, apple-a16, apple-m1, apple-m2, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel, ampere1, grace{{$}} // 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/llvm/docs/ReleaseNotes.rst b/llvm/docs/ReleaseNotes.rst --- a/llvm/docs/ReleaseNotes.rst +++ b/llvm/docs/ReleaseNotes.rst @@ -81,6 +81,8 @@ Changes to the AArch64 Backend ------------------------------ +* Added support for the Cortex-A715 CPU. + Changes to the AMDGPU Backend ----------------------------- 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 @@ -204,6 +204,12 @@ AArch64::AEK_SB | AArch64::AEK_I8MM | AArch64::AEK_FP16FML | AArch64::AEK_SVE | AArch64::AEK_SVE2 | AArch64::AEK_SVE2BITPERM | AArch64::AEK_BF16)) +AARCH64_CPU_NAME("cortex-a715", ARMV9A, FK_NEON_FP_ARMV8, false, + (AArch64::AEK_SB | AArch64::AEK_SSBS | AArch64::AEK_MTE | + AArch64::AEK_FP16 | AArch64::AEK_FP16FML | AArch64::AEK_PAUTH | + AArch64::AEK_I8MM | AArch64::AEK_PREDRES | AArch64::AEK_PERFMON | + AArch64::AEK_PROFILE | AArch64::AEK_SVE | AArch64::AEK_SVE2BITPERM | + AArch64::AEK_BF16 | AArch64::AEK_FLAGM)) AARCH64_CPU_NAME("cortex-r82", ARMV8R, FK_CRYPTO_NEON_FP_ARMV8, false, (AArch64::AEK_LSE)) AARCH64_CPU_NAME("cortex-x1", 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 @@ -213,6 +213,7 @@ .Case("0xd0b", "cortex-a76") .Case("0xd0d", "cortex-a77") .Case("0xd41", "cortex-a78") + .Case("0xd4d", "cortex-a715") .Case("0xd44", "cortex-x1") .Case("0xd4c", "cortex-x1c") .Case("0xd0c", "neoverse-n1") 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 @@ -764,6 +764,14 @@ FeatureLSLFast, FeaturePostRAScheduler]>; +def TuneA715 : SubtargetFeature<"a715", "ARMProcFamily", "CortexA715", + "Cortex-A715 ARM processors", [ + FeatureFuseAES, + FeaturePostRAScheduler, + FeatureCmpBccFusion, + FeatureLSLFast, + FeatureFuseAdrpAdd]>; + def TuneR82 : SubtargetFeature<"cortex-r82", "ARMProcFamily", "CortexR82", "Cortex-R82 ARM processors", [ @@ -1093,6 +1101,10 @@ list A710 = [HasV9_0aOps, FeatureNEON, FeaturePerfMon, FeatureETE, FeatureMTE, FeatureFP16FML, FeatureSVE2BitPerm, FeatureBF16, FeatureMatMulInt8]; + list A715 = [HasV9_0aOps, FeatureNEON, FeatureMTE, + FeatureFP16FML, FeatureSVE, FeatureTRBE, + FeatureSVE2BitPerm, FeatureBF16, FeatureETE, + FeaturePerfMon, FeatureMatMulInt8, FeatureSPE]; list R82 = [HasV8_0rOps, FeaturePerfMon, FeatureFullFP16, FeatureFP16FML, FeatureSSBS, FeaturePredRes, FeatureSB]; @@ -1231,6 +1243,8 @@ [TuneA78C]>; def : ProcessorModel<"cortex-a710", NeoverseN2Model, ProcessorFeatures.A710, [TuneA710]>; +def : ProcessorModel<"cortex-a715", NeoverseN2Model, ProcessorFeatures.A715, + [TuneA715]>; def : ProcessorModel<"cortex-r82", CortexA55Model, ProcessorFeatures.R82, [TuneR82]>; def : ProcessorModel<"cortex-x1", CortexA57Model, ProcessorFeatures.X1, 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 @@ -64,6 +64,7 @@ CortexA78, CortexA78C, CortexA710, + CortexA715, CortexR82, CortexX1, CortexX1C, 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 @@ -142,6 +142,7 @@ MaxBytesForLoopAlignment = 8; break; case CortexA710: + case CortexA715: case CortexX2: PrefFunctionLogAlignment = 4; VScaleForTuning = 1; 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 @@ -1016,6 +1016,19 @@ AArch64::AEK_FLAGM | AArch64::AEK_SB | AArch64::AEK_I8MM | AArch64::AEK_BF16, "9-A"), + ARMCPUTestParams("cortex-a715", "armv9-a", "neon-fp-armv8", + AArch64::AEK_CRC | AArch64::AEK_FP | AArch64::AEK_BF16 | + AArch64::AEK_SIMD | AArch64::AEK_RAS | + AArch64::AEK_LSE | AArch64::AEK_RDM | + AArch64::AEK_RCPC | AArch64::AEK_DOTPROD | + AArch64::AEK_MTE | AArch64::AEK_PAUTH | + AArch64::AEK_SVE | AArch64::AEK_SVE2 | + AArch64::AEK_SVE2BITPERM | AArch64::AEK_SSBS | + AArch64::AEK_SB | AArch64::AEK_I8MM | + AArch64::AEK_PERFMON | AArch64::AEK_PREDRES | + AArch64::AEK_PROFILE | AArch64::AEK_FP16FML | + AArch64::AEK_FP16 | AArch64::AEK_FLAGM, + "9-A"), ARMCPUTestParams( "neoverse-v1", "armv8.4-a", "crypto-neon-fp-armv8", AArch64::AEK_RAS | AArch64::AEK_SVE | AArch64::AEK_SSBS | @@ -1296,7 +1309,7 @@ "8.2-A"))); // Note: number of CPUs includes aliases. -static constexpr unsigned NumAArch64CPUArchs = 59; +static constexpr unsigned NumAArch64CPUArchs = 60; TEST(TargetParserTest, testAArch64CPUArchList) { SmallVector List;