[Driver][AArch64]Add driver support for neoverse-512tvb target

The support for  neoverse-512tvb mirrors the same option available in GCC[1].
There is no functional effect for this option yet.
This patch ensures the driver accepts "-mcpu=neoverse-512tvb", and enough
plumbing is in place to allow the new option to be used in the future.

[1]https://gcc.gnu.org/onlinedocs/gcc/AArch64-Options.html

Differential Revision: https://reviews.llvm.org/D112406

diff --git a/clang/test/Driver/aarch64-cpus.c b/clang/test/Driver/aarch64-cpus.c
index 55cef73..4f049c7 100644 (file)
--- a/clang/test/Driver/aarch64-cpus.c
+++ b/clang/test/Driver/aarch64-cpus.c
@@ -192,6 +192,9 @@
 // RUN: %clang -target aarch64 -mcpu=neoverse-n2 -### -c %s 2>&1 | FileCheck -check-prefix=NEOVERSE-N2 %s
 // NEOVERSE-N2: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "neoverse-n2"
 
+// RUN: %clang -target aarch64 -mcpu=neoverse-512tvb -### -c %s 2>&1 | FileCheck -check-prefix=NEOVERSE-512TVB %s
+// NEOVERSE-512TVB: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "neoverse-512tvb"
+
 // RUN: %clang -target aarch64 -mcpu=cortex-r82  -### -c %s 2>&1 | FileCheck -check-prefix=CORTEXR82 %s
 // CORTEXR82: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "cortex-r82"
 

diff --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c
index 800910b..efdc922 100644 (file)
--- 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-r82, cortex-x1, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-v1, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-m1, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel{{$}}
+// AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-r82, cortex-x1, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-m1, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel{{$}}
 
 // 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-r82, cortex-x1, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-v1, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-m1, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel{{$}}
+// TUNE_AARCH64-NEXT: note: valid target CPU values are: cortex-a34, cortex-a35, cortex-a53, cortex-a55, cortex-a510, cortex-a57, cortex-a65, cortex-a65ae, cortex-a72, cortex-a73, cortex-a75, cortex-a76, cortex-a76ae, cortex-a77, cortex-a78, cortex-a78c, cortex-r82, cortex-x1, neoverse-e1, neoverse-n1, neoverse-n2, neoverse-512tvb, neoverse-v1, cyclone, apple-a7, apple-a8, apple-a9, apple-a10, apple-a11, apple-a12, apple-a13, apple-a14, apple-m1, apple-s4, apple-s5, exynos-m3, exynos-m4, exynos-m5, falkor, saphira, kryo, thunderx2t99, thunderx3t110, thunderx, thunderxt88, thunderxt81, thunderxt83, tsv110, a64fx, carmel{{$}}
 
 // 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/include/llvm/Support/AArch64TargetParser.def b/llvm/include/llvm/Support/AArch64TargetParser.def
index a87d7e8..a281109 100644 (file)
--- a/llvm/include/llvm/Support/AArch64TargetParser.def
+++ b/llvm/include/llvm/Support/AArch64TargetParser.def
@@ -194,6 +194,10 @@ AARCH64_CPU_NAME("neoverse-n2", ARMV8_5A, FK_CRYPTO_NEON_FP_ARMV8, false,
                   AArch64::AEK_I8MM | AArch64::AEK_MTE | AArch64::AEK_RAS |
                   AArch64::AEK_RCPC | AArch64::AEK_SB | AArch64::AEK_SSBS |
                   AArch64::AEK_SVE | AArch64::AEK_SVE2 | AArch64::AEK_SVE2BITPERM))
+AARCH64_CPU_NAME("neoverse-512tvb", ARMV8_4A, FK_CRYPTO_NEON_FP_ARMV8, false,
+                 (AArch64::AEK_RAS | AArch64::AEK_SVE | AArch64::AEK_SSBS |
+                  AArch64::AEK_RCPC | AArch64::AEK_FP16 | AArch64::AEK_BF16 |
+                  AArch64::AEK_DOTPROD ))
 AARCH64_CPU_NAME("neoverse-v1", ARMV8_4A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_RAS | AArch64::AEK_SVE | AArch64::AEK_SSBS |
                   AArch64::AEK_RCPC | AArch64::AEK_FP16 | AArch64::AEK_BF16 |

diff --git a/llvm/lib/Target/AArch64/AArch64.td b/llvm/lib/Target/AArch64/AArch64.td
index 10637fd..9224f84 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64.td
+++ b/llvm/lib/Target/AArch64/AArch64.td
@@ -843,6 +843,11 @@ def TuneNeoverseN2 : SubtargetFeature<"neoversen2", "ARMProcFamily", "NeoverseN2
                                       FeaturePostRAScheduler,
                                       FeatureFuseAES
                                       ]>;
+def TuneNeoverse512TVB : SubtargetFeature<"neoverse512tvb", "ARMProcFamily", "Neoverse512TVB",
+                                      "Neoverse 512-TVB ARM processors", [
+                                      FeaturePostRAScheduler,
+                                      FeatureFuseAES
+                                      ]>;
 
 def TuneNeoverseV1 : SubtargetFeature<"neoversev1", "ARMProcFamily", "NeoverseV1",
                                       "Neoverse V1 ARM processors", [
@@ -975,6 +980,11 @@ def ProcessorFeatures {
   list<SubtargetFeature> NeoverseN2 = [HasV8_5aOps, FeatureBF16, FeatureETE,
                                        FeatureMatMulInt8, FeatureMTE, FeatureSVE2,
                                        FeatureSVE2BitPerm, FeatureTRBE, FeatureCrypto];
+  list<SubtargetFeature> Neoverse512TVB = [HasV8_4aOps, FeatureBF16, FeatureCacheDeepPersist,
+                                           FeatureCrypto, FeatureFPARMv8, FeatureFP16FML,
+                                           FeatureFullFP16, FeatureMatMulInt8, FeatureNEON,
+                                           FeaturePerfMon, FeatureRandGen, FeatureSPE,
+                                           FeatureSSBS, FeatureSVE];
   list<SubtargetFeature> NeoverseV1 = [HasV8_4aOps, FeatureBF16, FeatureCacheDeepPersist,
                                        FeatureCrypto, FeatureFPARMv8, FeatureFP16FML,
                                        FeatureFullFP16, FeatureMatMulInt8, FeatureNEON,
@@ -1045,6 +1055,8 @@ def : ProcessorModel<"neoverse-n1", CortexA57Model,
                      ProcessorFeatures.NeoverseN1, [TuneNeoverseN1]>;
 def : ProcessorModel<"neoverse-n2", CortexA57Model,
                      ProcessorFeatures.NeoverseN2, [TuneNeoverseN2]>;
+def : ProcessorModel<"neoverse-512tvb", CortexA57Model,
+                     ProcessorFeatures.Neoverse512TVB, [TuneNeoverse512TVB]>;
 def : ProcessorModel<"neoverse-v1", CortexA57Model,
                      ProcessorFeatures.NeoverseV1, [TuneNeoverseV1]>;
 def : ProcessorModel<"exynos-m3", ExynosM3Model, ProcessorFeatures.ExynosM3,

diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
index 7955ede..3072b5a 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -164,6 +164,11 @@ void AArch64Subtarget::initializeProperties() {
     PrefFunctionLogAlignment = 4;
     VScaleForTuning = 2;
     break;
+  case Neoverse512TVB:
+    PrefFunctionLogAlignment = 4;
+    VScaleForTuning = 1;
+    MaxInterleaveFactor = 4;
+    break;
   case Saphira:
     MaxInterleaveFactor = 4;
     // FIXME: remove this to enable 64-bit SLP if performance looks good.

diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h
index 1fffb20..a34e148 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.h
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -68,6 +68,7 @@ public:
     NeoverseE1,
     NeoverseN1,
     NeoverseN2,
+    Neoverse512TVB,
     NeoverseV1,
     Saphira,
     ThunderX2T99,

diff --git a/llvm/test/CodeGen/AArch64/cpus.ll b/llvm/test/CodeGen/AArch64/cpus.ll
index 1c63186..88330b6 100644 (file)
--- a/llvm/test/CodeGen/AArch64/cpus.ll
+++ b/llvm/test/CodeGen/AArch64/cpus.ll
@@ -21,6 +21,7 @@
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=neoverse-e1 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=neoverse-n1 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=neoverse-n2 2>&1 | FileCheck %s
+; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=neoverse-512tvb 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=neoverse-v1 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=exynos-m3 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=exynos-m4 2>&1 | FileCheck %s

diff --git a/llvm/test/CodeGen/AArch64/misched-fusion-aes.ll b/llvm/test/CodeGen/AArch64/misched-fusion-aes.ll
index 2e6139a..111f173 100644 (file)
--- a/llvm/test/CodeGen/AArch64/misched-fusion-aes.ll
+++ b/llvm/test/CodeGen/AArch64/misched-fusion-aes.ll
@@ -14,6 +14,7 @@
 ; RUN: llc %s -o - -mtriple=aarch64-unknown -mcpu=neoverse-n1 | FileCheck %s
 ; RUN: llc %s -o - -mtriple=aarch64-unknown -mcpu=neoverse-n2 | FileCheck %s
 ; RUN: llc %s -o - -mtriple=aarch64-unknown -mcpu=neoverse-v1 | FileCheck %s
+; RUN: llc %s -o - -mtriple=aarch64-unknown -mcpu=neoverse-512tvb | FileCheck %s
 ; RUN: llc %s -o - -mtriple=aarch64-unknown -mcpu=exynos-m3  | FileCheck %s
 ; RUN: llc %s -o - -mtriple=aarch64-unknown -mcpu=exynos-m4  | FileCheck %s
 ; RUN: llc %s -o - -mtriple=aarch64-unknown -mcpu=exynos-m5  | FileCheck %s

diff --git a/llvm/unittests/Support/TargetParserTest.cpp b/llvm/unittests/Support/TargetParserTest.cpp
index b8b84ca..ba0e7dc 100644 (file)
--- a/llvm/unittests/Support/TargetParserTest.cpp
+++ b/llvm/unittests/Support/TargetParserTest.cpp
@@ -1134,6 +1134,14 @@ INSTANTIATE_TEST_SUITE_P(
                              AArch64::AEK_SVE2 | AArch64::AEK_SVE2BITPERM |
                              AArch64::AEK_BF16 | AArch64::AEK_I8MM,
                          "8.5-A"),
+        ARMCPUTestParams(
+            "neoverse-512tvb", "armv8.4-a", "crypto-neon-fp-armv8",
+            AArch64::AEK_RAS | AArch64::AEK_SVE | AArch64::AEK_SSBS |
+                AArch64::AEK_RCPC | AArch64::AEK_CRC | AArch64::AEK_FP |
+                AArch64::AEK_SIMD | AArch64::AEK_RAS | AArch64::AEK_LSE |
+                AArch64::AEK_RDM | AArch64::AEK_RCPC | AArch64::AEK_DOTPROD |
+                AArch64::AEK_CRYPTO | AArch64::AEK_FP16 | AArch64::AEK_BF16,
+            "8.4-A"),
         ARMCPUTestParams("thunderx2t99", "armv8.1-a", "crypto-neon-fp-armv8",
                          AArch64::AEK_NONE | AArch64::AEK_CRC |
                              AArch64::AEK_CRYPTO | AArch64::AEK_LSE |
@@ -1189,7 +1197,7 @@ INSTANTIATE_TEST_SUITE_P(
                              AArch64::AEK_LSE | AArch64::AEK_RDM,
                          "8.2-A")));
 
-static constexpr unsigned NumAArch64CPUArchs = 49;
+static constexpr unsigned NumAArch64CPUArchs = 50;
 
 TEST(TargetParserTest, testAArch64CPUArchList) {
   SmallVector<StringRef, NumAArch64CPUArchs> List;