[AArch64] Add support for Fujitsu A64FX

A64FX is an Armv8.2-A CPU used in FUJITSU Supercomputer
PRIMEHPC FX1000, PRIMEHPC FX700, and supercomputer Fugaku.

https://www.fujitsu.com/global/products/computing/servers/supercomputer/specifications/

Differential Revision: https://reviews.llvm.org/D75594

diff --git a/clang/test/Driver/aarch64-cpus.c b/clang/test/Driver/aarch64-cpus.c
index f1b53d9..36444f0 100644 (file)
--- a/clang/test/Driver/aarch64-cpus.c
+++ b/clang/test/Driver/aarch64-cpus.c
@@ -269,6 +269,20 @@
 // ARM64-THUNDERX2T99-TUNE: "-cc1"{{.*}} "-triple" "arm64{{.*}}" "-target-cpu" "generic"
 // ARM64-THUNDERX2T99-TUNE-NOT: +v8.1a
 
+// RUN: %clang -target aarch64 -mcpu=a64fx -### -c %s 2>&1 | FileCheck -check-prefix=A64FX %s
+// RUN: %clang -target aarch64 -mlittle-endian -mcpu=a64fx -### -c %s 2>&1 | FileCheck -check-prefix=A64FX %s
+// RUN: %clang -target aarch64 -mtune=a64fx -### -c %s 2>&1 | FileCheck -check-prefix=A64FX-TUNE %s
+// RUN: %clang -target aarch64 -mlittle-endian -mtune=a64fx -### -c %s 2>&1 | FileCheck -check-prefix=A64FX-TUNE %s
+// A64FX: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "a64fx"
+// A64FX-TUNE: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "generic"
+
+// RUN: %clang -target arm64 -mcpu=a64fx -### -c %s 2>&1 | FileCheck -check-prefix=ARM64-A64FX %s
+// RUN: %clang -target arm64 -mlittle-endian -mcpu=a64fx -### -c %s 2>&1 | FileCheck -check-prefix=ARM64-A64FX %s
+// RUN: %clang -target arm64 -mtune=a64fx -### -c %s 2>&1 | FileCheck -check-prefix=ARM64-A64FX-TUNE %s
+// RUN: %clang -target arm64 -mlittle-endian -mtune=a64fx -### -c %s 2>&1 | FileCheck -check-prefix=ARM64-A64FX-TUNE %s
+// ARM64-A64FX: "-cc1"{{.*}} "-triple" "arm64{{.*}}" "-target-cpu" "a64fx"
+// ARM64-A64FX-TUNE: "-cc1"{{.*}} "-triple" "arm64{{.*}}" "-target-cpu" "generic"
+
 // RUN: %clang -target aarch64_be -### -c %s 2>&1 | FileCheck -check-prefix=GENERIC-BE %s
 // RUN: %clang -target aarch64 -mbig-endian -### -c %s 2>&1 | FileCheck -check-prefix=GENERIC-BE %s
 // RUN: %clang -target aarch64_be -mbig-endian -### -c %s 2>&1 | FileCheck -check-prefix=GENERIC-BE %s

diff --git a/clang/test/Preprocessor/aarch64-target-features.c b/clang/test/Preprocessor/aarch64-target-features.c
index 9fb8dce..c62c82a 100644 (file)
--- a/clang/test/Preprocessor/aarch64-target-features.c
+++ b/clang/test/Preprocessor/aarch64-target-features.c
@@ -160,6 +160,7 @@
 // RUN: %clang -target aarch64 -mcpu=exynos-m5 -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-MCPU-M4 %s
 // RUN: %clang -target aarch64 -mcpu=kryo -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-MCPU-KRYO %s
 // RUN: %clang -target aarch64 -mcpu=thunderx2t99 -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-MCPU-THUNDERX2T99 %s
+// RUN: %clang -target aarch64 -mcpu=a64fx -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-MCPU-A64FX %s
 // CHECK-MCPU-APPLE-A7: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+fp-armv8" "-target-feature" "+neon" "-target-feature" "+crypto" "-target-feature" "+zcm" "-target-feature" "+zcz" "-target-feature" "+sha2" "-target-feature" "+aes"
 // CHECK-MCPU-APPLE-A10: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+fp-armv8" "-target-feature" "+neon" "-target-feature" "+crc" "-target-feature" "+crypto" "-target-feature" "+rdm" "-target-feature" "+zcm" "-target-feature" "+zcz" "-target-feature" "+sha2" "-target-feature" "+aes"
 // CHECK-MCPU-APPLE-A11: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+v8.2a" "-target-feature" "+fp-armv8" "-target-feature" "+neon" "-target-feature" "+crc" "-target-feature" "+crypto" "-target-feature" "+ras" "-target-feature" "+lse" "-target-feature" "+rdm" "-target-feature" "+zcm" "-target-feature" "+zcz" "-target-feature" "+sha2" "-target-feature" "+aes"
@@ -175,6 +176,7 @@
 // CHECK-MCPU-M4: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+neon" "-target-feature" "+crc" "-target-feature" "+crypto" "-target-feature" "+dotprod" "-target-feature" "+fullfp16"
 // CHECK-MCPU-KRYO: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+neon" "-target-feature" "+crc" "-target-feature" "+crypto"
 // CHECK-MCPU-THUNDERX2T99: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+neon" "-target-feature" "+crc" "-target-feature" "+crypto"
+// CHECK-MCPU-A64FX: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+v8.2a" "-target-feature" "+fp-armv8" "-target-feature" "+neon" "-target-feature" "+crc" "-target-feature" "+crypto" "-target-feature" "+fullfp16" "-target-feature" "+ras" "-target-feature" "+lse" "-target-feature" "+rdm" "-target-feature" "+sve" "-target-feature" "+sha2"
 
 // RUN: %clang -target x86_64-apple-macosx -arch arm64 -### -c %s 2>&1 | FileCheck --check-prefix=CHECK-ARCH-ARM64 %s
 // CHECK-ARCH-ARM64: "-target-cpu" "apple-a7" "-target-feature" "+fp-armv8" "-target-feature" "+neon" "-target-feature" "+crypto" "-target-feature" "+zcm" "-target-feature" "+zcz"

diff --git a/llvm/include/llvm/Support/AArch64TargetParser.def b/llvm/include/llvm/Support/AArch64TargetParser.def
index 1394cf7..0fd4117 100644 (file)
--- a/llvm/include/llvm/Support/AArch64TargetParser.def
+++ b/llvm/include/llvm/Support/AArch64TargetParser.def
@@ -166,6 +166,8 @@ AARCH64_CPU_NAME("tsv110", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
                  (AArch64::AEK_DOTPROD |
                   AArch64::AEK_FP16 | AArch64::AEK_FP16FML |
                   AArch64::AEK_PROFILE))
+AARCH64_CPU_NAME("a64fx", ARMV8_2A, FK_CRYPTO_NEON_FP_ARMV8, false,
+                 (AArch64::AEK_FP16 | AArch64::AEK_SVE))
 // Invalid CPU
 AARCH64_CPU_NAME("invalid", INVALID, FK_INVALID, true, AArch64::AEK_INVALID)
 #undef AARCH64_CPU_NAME

diff --git a/llvm/lib/Support/Host.cpp b/llvm/lib/Support/Host.cpp
index 9b9d60e..2fb0c25 100644 (file)
--- a/llvm/lib/Support/Host.cpp
+++ b/llvm/lib/Support/Host.cpp
@@ -219,6 +219,16 @@ StringRef sys::detail::getHostCPUNameForARM(StringRef ProcCpuinfoContent) {
     }
   }
 
+  if (Implementer == "0x46") { // Fujitsu Ltd.
+    for (unsigned I = 0, E = Lines.size(); I != E; ++I) {
+      if (Lines[I].startswith("CPU part")) {
+        return StringSwitch<const char *>(Lines[I].substr(8).ltrim("\t :"))
+          .Case("0x001", "a64fx")
+          .Default("generic");
+      }
+    }
+  }
+
   if (Implementer == "0x48") // HiSilicon Technologies, Inc.
     // Look for the CPU part line.
     for (unsigned I = 0, E = Lines.size(); I != E; ++I)

diff --git a/llvm/lib/Target/AArch64/AArch64.td b/llvm/lib/Target/AArch64/AArch64.td
index df35bb4..a6af2a1 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64.td
+++ b/llvm/lib/Target/AArch64/AArch64.td
@@ -563,6 +563,19 @@ def ProcA76     : SubtargetFeature<"a76", "ARMProcFamily", "CortexA76",
                                     FeatureSSBS
                                     ]>;
 
+def ProcA64FX : SubtargetFeature<"a64fx", "ARMProcFamily", "A64FX",
+                                 "Fujitsu A64FX processors", [
+                                  HasV8_2aOps,
+                                  FeatureFPARMv8,
+                                  FeatureNEON,
+                                  FeatureSHA2,
+                                  FeaturePerfMon,
+                                  FeatureFullFP16,
+                                  FeatureSVE,
+                                  FeaturePostRAScheduler,
+                                  FeatureComplxNum
+                                  ]>;
+
 // 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 ProcAppleA7 : SubtargetFeature<"apple-a7", "ARMProcFamily", "AppleA7",
@@ -901,6 +914,10 @@ def : ProcessorModel<"apple-s5", CycloneModel, [ProcAppleA12]>;
 // Alias for the latest Apple processor model supported by LLVM.
 def : ProcessorModel<"apple-latest", CycloneModel, [ProcAppleA13]>;
 
+// Fujitsu A64FX
+// FIXME: Scheduling model is not implemented yet.
+def : ProcessorModel<"a64fx", NoSchedModel, [ProcA64FX]>;
+
 //===----------------------------------------------------------------------===//
 // Assembly parser
 //===----------------------------------------------------------------------===//

diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
index 3636d8d..dc744f5 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -88,6 +88,11 @@ void AArch64Subtarget::initializeProperties() {
   case CortexA76:
     PrefFunctionLogAlignment = 4;
     break;
+  case A64FX:
+    CacheLineSize = 256;
+    PrefFunctionLogAlignment = 5;
+    PrefLoopLogAlignment = 5;
+    break;
   case AppleA7:
   case AppleA10:
   case AppleA11:

diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h
index 79c2c16..dca2b8b 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.h
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -38,6 +38,7 @@ class AArch64Subtarget final : public AArch64GenSubtargetInfo {
 public:
   enum ARMProcFamilyEnum : uint8_t {
     Others,
+    A64FX,
     AppleA7,
     AppleA10,
     AppleA11,

diff --git a/llvm/test/CodeGen/AArch64/cpus.ll b/llvm/test/CodeGen/AArch64/cpus.ll
index a8a82b7..2d84003 100644 (file)
--- a/llvm/test/CodeGen/AArch64/cpus.ll
+++ b/llvm/test/CodeGen/AArch64/cpus.ll
@@ -25,6 +25,7 @@
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=thunderx2t99 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=tsv110 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=apple-latest 2>&1 | FileCheck %s
+; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=a64fx 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=invalidcpu 2>&1 | FileCheck %s --check-prefix=INVALID
 
 ; CHECK-NOT: {{.*}}  is not a recognized processor for this target

diff --git a/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll b/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll
index 012fe4f..f3e6935 100644 (file)
--- a/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll
+++ b/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll
@@ -8,6 +8,7 @@
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a73 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a75 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a76 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
+; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=a64fx < %s | FileCheck --check-prefixes=ALIGN5,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cyclone < %s | FileCheck --check-prefixes=ALIGN2,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=falkor < %s | FileCheck --check-prefixes=ALIGN2,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=kryo < %s | FileCheck --check-prefixes=ALIGN2,CHECK %s

diff --git a/llvm/unittests/Support/Host.cpp b/llvm/unittests/Support/Host.cpp
index e5c2816..36ca70a 100644 (file)
--- a/llvm/unittests/Support/Host.cpp
+++ b/llvm/unittests/Support/Host.cpp
@@ -249,6 +249,19 @@ CPU part   : 0x0a1
   EXPECT_EQ(sys::detail::getHostCPUNameForARM("CPU implementer : 0x48\n"
                                               "CPU part        : 0xd01"),
             "tsv110");
+
+  // Verify A64FX.
+  const std::string A64FXProcCpuInfo = R"(
+processor       : 0
+BogoMIPS        : 200.00
+Features        : fp asimd evtstrm sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm fcma dcpop sve
+CPU implementer : 0x46
+CPU architecture: 8
+CPU variant     : 0x1
+CPU part        : 0x001
+)";
+
+  EXPECT_EQ(sys::detail::getHostCPUNameForARM(A64FXProcCpuInfo), "a64fx");
 }
 
 #if defined(__APPLE__) || defined(_AIX)

diff --git a/llvm/unittests/Support/TargetParserTest.cpp b/llvm/unittests/Support/TargetParserTest.cpp
index 881dd4b..2d68b4c 100644 (file)
--- a/llvm/unittests/Support/TargetParserTest.cpp
+++ b/llvm/unittests/Support/TargetParserTest.cpp
@@ -964,9 +964,15 @@ TEST(TargetParserTest, testAArch64CPU) {
       AArch64::AEK_RDM | AArch64::AEK_PROFILE | AArch64::AEK_FP16 |
       AArch64::AEK_FP16FML | AArch64::AEK_DOTPROD,
       "8.2-A"));
+  EXPECT_TRUE(testAArch64CPU(
+      "a64fx", "armv8.2-a", "crypto-neon-fp-armv8",
+      AArch64::AEK_CRC | AArch64::AEK_CRYPTO | AArch64::AEK_FP |
+      AArch64::AEK_SIMD | AArch64::AEK_FP16 | AArch64::AEK_RAS |
+      AArch64::AEK_LSE | AArch64::AEK_SVE | AArch64::AEK_RDM,
+      "8.2-A"));
 }
 
-static constexpr unsigned NumAArch64CPUArchs = 36;
+static constexpr unsigned NumAArch64CPUArchs = 37;
 
 TEST(TargetParserTest, testAArch64CPUArchList) {
   SmallVector<StringRef, NumAArch64CPUArchs> List;
@@ -1107,6 +1113,12 @@ TEST(TargetParserTest, testAArch64Extension) {
                                    AArch64::ArchKind::INVALID, "fp16fml"));
   EXPECT_TRUE(testAArch64Extension("tsv110",
                                    AArch64::ArchKind::INVALID, "dotprod"));
+  EXPECT_TRUE(testAArch64Extension("a64fx",
+                                   AArch64::ArchKind::INVALID, "fp16"));
+  EXPECT_TRUE(testAArch64Extension("a64fx",
+                                   AArch64::ArchKind::INVALID, "sve"));
+  EXPECT_FALSE(testAArch64Extension("a64fx",
+                                   AArch64::ArchKind::INVALID, "sve2"));
 
   EXPECT_FALSE(testAArch64Extension(
       "generic", AArch64::ArchKind::ARMV8A, "ras"));