[clang] [llvm] [AArch64] Add initial support for FUJITSU-MONAKA (PR #118432)

Kinoshita Kotaro via cfe-commits cfe-commits at lists.llvm.org
Mon Dec 2 22:02:45 PST 2024


https://github.com/kinoshita-fj created https://github.com/llvm/llvm-project/pull/118432

FUJITSU-MONAKA is a CPU we are currently developing.

This is the slides for the CPU: https://www.fujitsu.com/downloads/SUPER/topics/isc24/next-arm-based-processor-fujitsu-monaka-and-its-software-ecosystem.pdf


>From bd4c80f2c16e1380be077b586cd13e4bf39f762b Mon Sep 17 00:00:00 2001
From: Kinoshita Kotaro <k.kotaro at fujitsu.com>
Date: Tue, 3 Dec 2024 05:30:33 +0000
Subject: [PATCH] [AArch64]  Add initial support for FUJITSU-MONAKA

This patch adds initial support for FUJITSU-MONAKA CPU (-mcpu=fujitsu-monaka).

The scheduling model will be corrected in the future.
---
 clang/test/Driver/aarch64-fujitsu-monaka.c    | 13 +++
 .../aarch64-fujitsu-monaka.c                  | 82 +++++++++++++++++++
 .../Misc/target-invalid-cpu-note/aarch64.c    |  1 +
 llvm/lib/Target/AArch64/AArch64Processors.td  | 18 ++++
 llvm/lib/Target/AArch64/AArch64Subtarget.cpp  |  3 +
 llvm/lib/TargetParser/Host.cpp                |  5 +-
 llvm/test/CodeGen/AArch64/cpus.ll             |  1 +
 llvm/unittests/TargetParser/Host.cpp          |  3 +
 .../TargetParser/TargetParserTest.cpp         |  3 +-
 9 files changed, 126 insertions(+), 3 deletions(-)
 create mode 100644 clang/test/Driver/aarch64-fujitsu-monaka.c
 create mode 100644 clang/test/Driver/print-enabled-extensions/aarch64-fujitsu-monaka.c

diff --git a/clang/test/Driver/aarch64-fujitsu-monaka.c b/clang/test/Driver/aarch64-fujitsu-monaka.c
new file mode 100644
index 00000000000000..df96b36bace681
--- /dev/null
+++ b/clang/test/Driver/aarch64-fujitsu-monaka.c
@@ -0,0 +1,13 @@
+// RUN: %clang --target=aarch64 -mcpu=fujitsu-monaka -### -c %s 2>&1 | FileCheck -check-prefix=fujitsu-monaka %s
+// RUN: %clang --target=aarch64 -mlittle-endian -mcpu=fujitsu-monaka -### -c %s 2>&1 | FileCheck -check-prefix=fujitsu-monaka %s
+// RUN: %clang --target=aarch64 -mtune=fujitsu-monaka -### -c %s 2>&1 | FileCheck -check-prefix=fujitsu-monaka-TUNE %s
+// RUN: %clang --target=aarch64 -mlittle-endian -mtune=fujitsu-monaka -### -c %s 2>&1 | FileCheck -check-prefix=fujitsu-monaka-TUNE %s
+// fujitsu-monaka: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "fujitsu-monaka"
+// fujitsu-monaka-TUNE: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-cpu" "generic"
+
+// RUN: %clang --target=arm64 -mcpu=fujitsu-monaka -### -c %s 2>&1 | FileCheck -check-prefix=ARM64-fujitsu-monaka %s
+// RUN: %clang --target=arm64 -mlittle-endian -mcpu=fujitsu-monaka -### -c %s 2>&1 | FileCheck -check-prefix=ARM64-fujitsu-monaka %s
+// RUN: %clang --target=arm64 -mtune=fujitsu-monaka -### -c %s 2>&1 | FileCheck -check-prefix=ARM64-fujitsu-monaka-TUNE %s
+// RUN: %clang --target=arm64 -mlittle-endian -mtune=fujitsu-monaka -### -c %s 2>&1 | FileCheck -check-prefix=ARM64-fujitsu-monaka-TUNE %s
+// ARM64-fujitsu-monaka: "-cc1"{{.*}} "-triple" "arm64{{.*}}" "-target-cpu" "fujitsu-monaka"
+// ARM64-fujitsu-monaka-TUNE: "-cc1"{{.*}} "-triple" "arm64{{.*}}" "-target-cpu" "generic"
diff --git a/clang/test/Driver/print-enabled-extensions/aarch64-fujitsu-monaka.c b/clang/test/Driver/print-enabled-extensions/aarch64-fujitsu-monaka.c
new file mode 100644
index 00000000000000..fce76a49c07d38
--- /dev/null
+++ b/clang/test/Driver/print-enabled-extensions/aarch64-fujitsu-monaka.c
@@ -0,0 +1,82 @@
+// REQUIRES: aarch64-registered-target
+// RUN: %clang --target=aarch64 --print-enabled-extensions -mcpu=fujitsu-monaka | FileCheck --strict-whitespace --implicit-check-not=FEAT_ %s
+
+// CHECK: Extensions enabled for the given AArch64 target
+// CHECK-EMPTY:
+// CHECK-NEXT:     Architecture Feature(s)                                Description
+// CHECK-NEXT:     FEAT_AES, FEAT_PMULL                                   Enable AES support
+// CHECK-NEXT:     FEAT_AMUv1                                             Enable Armv8.4-A Activity Monitors extension
+// CHECK-NEXT:     FEAT_AMUv1p1                                           Enable Armv8.6-A Activity Monitors Virtualization support
+// CHECK-NEXT:     FEAT_AdvSIMD                                           Enable Advanced SIMD instructions
+// CHECK-NEXT:     FEAT_BF16                                              Enable BFloat16 Extension
+// CHECK-NEXT:     FEAT_BTI                                               Enable Branch Target Identification
+// CHECK-NEXT:     FEAT_CCIDX                                             Enable Armv8.3-A Extend of the CCSIDR number of sets
+// CHECK-NEXT:     FEAT_CLRBHB                                            Enable Clear BHB instruction
+// CHECK-NEXT:     FEAT_CRC32                                             Enable Armv8.0-A CRC-32 checksum instructions
+// CHECK-NEXT:     FEAT_CSV2_2                                            Enable architectural speculation restriction
+// CHECK-NEXT:     FEAT_DIT                                               Enable Armv8.4-A Data Independent Timing instructions
+// CHECK-NEXT:     FEAT_DPB                                               Enable Armv8.2-A data Cache Clean to Point of Persistence
+// CHECK-NEXT:     FEAT_DPB2                                              Enable Armv8.5-A Cache Clean to Point of Deep Persistence
+// CHECK-NEXT:     FEAT_DotProd                                           Enable dot product support
+// CHECK-NEXT:     FEAT_ECV                                               Enable enhanced counter virtualization extension
+// CHECK-NEXT:     FEAT_ETE                                               Enable Embedded Trace Extension
+// CHECK-NEXT:     FEAT_FAMINMAX                                          Enable FAMIN and FAMAX instructions
+// CHECK-NEXT:     FEAT_FCMA                                              Enable Armv8.3-A Floating-point complex number support
+// CHECK-NEXT:     FEAT_FGT                                               Enable fine grained virtualization traps extension
+// CHECK-NEXT:     FEAT_FHM                                               Enable FP16 FML instructions
+// CHECK-NEXT:     FEAT_FP                                                Enable Armv8.0-A Floating Point Extensions
+// CHECK-NEXT:     FEAT_FP16                                              Enable half-precision floating-point data processing
+// CHECK-NEXT:     FEAT_FP8                                               Enable FP8 instructions
+// CHECK-NEXT:     FEAT_FP8DOT2                                           Enable FP8 2-way dot instructions
+// CHECK-NEXT:     FEAT_FP8DOT4                                           Enable FP8 4-way dot instructions
+// CHECK-NEXT:     FEAT_FP8FMA                                            Enable Armv9.5-A FP8 multiply-add instructions
+// CHECK-NEXT:     FEAT_FPAC                                              Enable Armv8.3-A Pointer Authentication Faulting enhancement
+// CHECK-NEXT:     FEAT_FRINTTS                                           Enable FRInt[32|64][Z|X] instructions that round a floating-point number to an integer (in FP format) forcing it to fit into a 32- or 64-bit int
+// CHECK-NEXT:     FEAT_FlagM                                             Enable Armv8.4-A Flag Manipulation instructions
+// CHECK-NEXT:     FEAT_FlagM2                                            Enable alternative NZCV format for floating point comparisons
+// CHECK-NEXT:     FEAT_HBC                                               Enable Armv8.8-A Hinted Conditional Branches Extension
+// CHECK-NEXT:     FEAT_HCX                                               Enable Armv8.7-A HCRX_EL2 system register
+// CHECK-NEXT:     FEAT_I8MM                                              Enable Matrix Multiply Int8 Extension
+// CHECK-NEXT:     FEAT_JSCVT                                             Enable Armv8.3-A JavaScript FP conversion instructions
+// CHECK-NEXT:     FEAT_LOR                                               Enable Armv8.1-A Limited Ordering Regions extension
+// CHECK-NEXT:     FEAT_LRCPC                                             Enable support for RCPC extension
+// CHECK-NEXT:     FEAT_LRCPC2                                            Enable Armv8.4-A RCPC instructions with Immediate Offsets
+// CHECK-NEXT:     FEAT_LS64, FEAT_LS64_V, FEAT_LS64_ACCDATA              Enable Armv8.7-A LD64B/ST64B Accelerator Extension
+// CHECK-NEXT:     FEAT_LSE                                               Enable Armv8.1-A Large System Extension (LSE) atomic instructions
+// CHECK-NEXT:     FEAT_LSE2                                              Enable Armv8.4-A Large System Extension 2 (LSE2) atomicity rules
+// CHECK-NEXT:     FEAT_LUT                                               Enable Lookup Table instructions
+// CHECK-NEXT:     FEAT_MEC                                               Enable Memory Encryption Contexts Extension
+// CHECK-NEXT:     FEAT_MOPS                                              Enable Armv8.8-A memcpy and memset acceleration instructions
+// CHECK-NEXT:     FEAT_MPAM                                              Enable Armv8.4-A Memory system Partitioning and Monitoring extension
+// CHECK-NEXT:     FEAT_NMI, FEAT_GICv3_NMI                               Enable Armv8.8-A Non-maskable Interrupts
+// CHECK-NEXT:     FEAT_NV, FEAT_NV2                                      Enable Armv8.4-A Nested Virtualization Enchancement
+// CHECK-NEXT:     FEAT_PAN                                               Enable Armv8.1-A Privileged Access-Never extension
+// CHECK-NEXT:     FEAT_PAN2                                              Enable Armv8.2-A PAN s1e1R and s1e1W Variants
+// CHECK-NEXT:     FEAT_PAuth                                             Enable Armv8.3-A Pointer Authentication extension
+// CHECK-NEXT:     FEAT_PMUv3                                             Enable Armv8.0-A PMUv3 Performance Monitors extension
+// CHECK-NEXT:     FEAT_RAS, FEAT_RASv1p1                                 Enable Armv8.0-A Reliability, Availability and Serviceability Extensions
+// CHECK-NEXT:     FEAT_RDM                                               Enable Armv8.1-A Rounding Double Multiply Add/Subtract instructions
+// CHECK-NEXT:     FEAT_RME                                               Enable Realm Management Extension
+// CHECK-NEXT:     FEAT_RNG                                               Enable Random Number generation instructions
+// CHECK-NEXT:     FEAT_SB                                                Enable Armv8.5-A Speculation Barrier
+// CHECK-NEXT:     FEAT_SEL2                                              Enable Armv8.4-A Secure Exception Level 2 extension
+// CHECK-NEXT:     FEAT_SHA1, FEAT_SHA256                                 Enable SHA1 and SHA256 support
+// CHECK-NEXT:     FEAT_SHA3, FEAT_SHA512                                 Enable SHA512 and SHA3 support
+// CHECK-NEXT:     FEAT_SM4, FEAT_SM3                                     Enable SM3 and SM4 support
+// CHECK-NEXT:     FEAT_SPECRES                                           Enable Armv8.5-A execution and data prediction invalidation instructions
+// CHECK-NEXT:     FEAT_SPECRES2                                          Enable Speculation Restriction Instruction
+// CHECK-NEXT:     FEAT_SPEv1p2                                           Enable extra register in the Statistical Profiling Extension
+// CHECK-NEXT:     FEAT_SSBS, FEAT_SSBS2                                  Enable Speculative Store Bypass Safe bit
+// CHECK-NEXT:     FEAT_SVE                                               Enable Scalable Vector Extension (SVE) instructions
+// CHECK-NEXT:     FEAT_SVE2                                              Enable Scalable Vector Extension 2 (SVE2) instructions
+// CHECK-NEXT:     FEAT_SVE_AES, FEAT_SVE_PMULL128                        Enable AES SVE2 instructions
+// CHECK-NEXT:     FEAT_SVE_BitPerm                                       Enable bit permutation SVE2 instructions
+// CHECK-NEXT:     FEAT_SVE_SHA3                                          Enable SHA3 SVE2 instructions
+// CHECK-NEXT:     FEAT_SVE_SM4                                           Enable SM4 SVE2 instructions
+// CHECK-NEXT:     FEAT_TLBIOS, FEAT_TLBIRANGE                            Enable Armv8.4-A TLB Range and Maintenance instructions
+// CHECK-NEXT:     FEAT_TRBE                                              Enable Trace Buffer Extension
+// CHECK-NEXT:     FEAT_TRF                                               Enable Armv8.4-A Trace extension
+// CHECK-NEXT:     FEAT_UAO                                               Enable Armv8.2-A UAO PState
+// CHECK-NEXT:     FEAT_VHE                                               Enable Armv8.1-A Virtual Host extension
+// CHECK-NEXT:     FEAT_WFxT                                              Enable Armv8.7-A WFET and WFIT instruction
+// CHECK-NEXT:     FEAT_XS                                                Enable Armv8.7-A limited-TLB-maintenance instruction
\ No newline at end of file
diff --git a/clang/test/Misc/target-invalid-cpu-note/aarch64.c b/clang/test/Misc/target-invalid-cpu-note/aarch64.c
index ab83f299ac5997..e6ff09557fe070 100644
--- a/clang/test/Misc/target-invalid-cpu-note/aarch64.c
+++ b/clang/test/Misc/target-invalid-cpu-note/aarch64.c
@@ -67,6 +67,7 @@
 // CHECK-SAME: {{^}}, exynos-m4
 // CHECK-SAME: {{^}}, exynos-m5
 // CHECK-SAME: {{^}}, falkor
+// CHECK-SAME: {{^}}, fujitsu-monaka
 // CHECK-SAME: {{^}}, generic
 // CHECK-SAME: {{^}}, grace
 // CHECK-SAME: {{^}}, kryo
diff --git a/llvm/lib/Target/AArch64/AArch64Processors.td b/llvm/lib/Target/AArch64/AArch64Processors.td
index 6886df5392565d..83fdb85c50f6bf 100644
--- a/llvm/lib/Target/AArch64/AArch64Processors.td
+++ b/llvm/lib/Target/AArch64/AArch64Processors.td
@@ -266,6 +266,14 @@ def TuneA64FX : SubtargetFeature<"a64fx", "ARMProcFamily", "A64FX",
                                  FeatureStorePairSuppress,
                                  FeaturePredictableSelectIsExpensive]>;
 
+def TuneMONAKA : SubtargetFeature<"fujitsu-monaka", "ARMProcFamily", "MONAKA",
+                                 "Fujitsu FUJITSU-MONAKA processors", [
+                                 FeaturePredictableSelectIsExpensive,
+                                 FeatureEnableSelectOptimize,
+                                 FeaturePostRAScheduler,
+                                 FeatureArithmeticBccFusion,
+                                 ]>;
+
 def TuneCarmel : SubtargetFeature<"carmel", "ARMProcFamily", "Carmel",
                                   "Nvidia Carmel processors">;
 
@@ -843,6 +851,12 @@ def ProcessorFeatures {
                                      FeatureSHA2, FeaturePerfMon, FeatureFullFP16,
                                      FeatureSVE, FeatureComplxNum,
                                      FeatureAES, FeatureCRC, FeatureLSE, FeatureRAS, FeatureRDM];
+  list<SubtargetFeature> MONAKA = [HasV9_3aOps, FeaturePerfMon, FeatureCCIDX,
+                                   FeatureFPAC, FeatureFP16FML, FeatureRandGen,
+                                   FeatureSSBS, FeatureLS64, FeatureCLRBHB,
+                                   FeatureSPECRES2, FeatureSVE2AES, FeatureSVE2SM4,
+                                   FeatureSVE2SHA3, FeatureSVE2BitPerm, FeatureETE,
+                                   FeatureMEC, FeatureFP8DOT2];
   list<SubtargetFeature> Carmel   = [HasV8_2aOps, FeatureNEON, FeatureSHA2, FeatureAES,
                                      FeatureFullFP16, FeatureCRC, FeatureLSE, FeatureRAS, FeatureRDM,
                                      FeatureFPARMv8];
@@ -1225,6 +1239,10 @@ def : ProcessorAlias<"apple-latest", "apple-m4">;
 def : ProcessorModel<"a64fx", A64FXModel, ProcessorFeatures.A64FX,
                      [TuneA64FX]>;
 
+// Fujitsu FUJITSU-MONAKA
+def : ProcessorModel<"fujitsu-monaka", A64FXModel, ProcessorFeatures.MONAKA,
+                     [TuneMONAKA]>;
+
 // Nvidia Carmel
 def : ProcessorModel<"carmel", NoSchedModel, ProcessorFeatures.Carmel,
                      [TuneCarmel]>;
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
index e37e2cacc7852e..3767b34bd5b0c5 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -195,6 +195,9 @@ void AArch64Subtarget::initializeProperties(bool HasMinSize) {
     MaxPrefetchIterationsAhead = 4;
     VScaleForTuning = 4;
     break;
+  case MONAKA:
+    VScaleForTuning = 2;
+    break;
   case AppleA7:
   case AppleA10:
   case AppleA11:
diff --git a/llvm/lib/TargetParser/Host.cpp b/llvm/lib/TargetParser/Host.cpp
index 4457e481def10a..7c28f12d6b6811 100644
--- a/llvm/lib/TargetParser/Host.cpp
+++ b/llvm/lib/TargetParser/Host.cpp
@@ -280,8 +280,9 @@ StringRef sys::detail::getHostCPUNameForARM(StringRef ProcCpuinfoContent) {
 
   if (Implementer == "0x46") { // Fujitsu Ltd.
     return StringSwitch<const char *>(Part)
-      .Case("0x001", "a64fx")
-      .Default("generic");
+        .Case("0x001", "a64fx")
+        .Case("0x003", "fujitsu-monaka")
+        .Default("generic");
   }
 
   if (Implementer == "0x4e") { // NVIDIA Corporation
diff --git a/llvm/test/CodeGen/AArch64/cpus.ll b/llvm/test/CodeGen/AArch64/cpus.ll
index 3e593a82fdf288..e9722f348f4113 100644
--- a/llvm/test/CodeGen/AArch64/cpus.ll
+++ b/llvm/test/CodeGen/AArch64/cpus.ll
@@ -36,6 +36,7 @@
 ; 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=fujitsu-monaka 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=ampere1 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=ampere1a 2>&1 | FileCheck %s
 ; RUN: llc < %s -mtriple=arm64-unknown-unknown -mcpu=ampere1b 2>&1 | FileCheck %s
diff --git a/llvm/unittests/TargetParser/Host.cpp b/llvm/unittests/TargetParser/Host.cpp
index 5e2edcef09bf8c..67c727a6c1c5df 100644
--- a/llvm/unittests/TargetParser/Host.cpp
+++ b/llvm/unittests/TargetParser/Host.cpp
@@ -140,6 +140,9 @@ TEST(getLinuxHostCPUName, AArch64) {
   EXPECT_EQ(sys::detail::getHostCPUNameForARM("CPU implementer : 0x51\n"
                                               "CPU part        : 0x001"),
             "oryon-1");
+  EXPECT_EQ(sys::detail::getHostCPUNameForARM("CPU implementer : 0x46\n"
+                                              "CPU part        : 0x003"),
+            "fujitsu-monaka");
 
   // MSM8992/4 weirdness
   StringRef MSM8992ProcCpuInfo = R"(
diff --git a/llvm/unittests/TargetParser/TargetParserTest.cpp b/llvm/unittests/TargetParser/TargetParserTest.cpp
index d281c2cbd55d35..6b07e848def37f 100644
--- a/llvm/unittests/TargetParser/TargetParserTest.cpp
+++ b/llvm/unittests/TargetParser/TargetParserTest.cpp
@@ -1150,13 +1150,14 @@ INSTANTIATE_TEST_SUITE_P(
                       AArch64CPUTestParams("thunderxt88", "armv8-a"),
                       AArch64CPUTestParams("tsv110", "armv8.2-a"),
                       AArch64CPUTestParams("a64fx", "armv8.2-a"),
+                      AArch64CPUTestParams("fujitsu-monaka", "armv9.3-a"),
                       AArch64CPUTestParams("carmel", "armv8.2-a"),
                       AArch64CPUTestParams("saphira", "armv8.4-a"),
                       AArch64CPUTestParams("oryon-1", "armv8.6-a")),
     AArch64CPUTestParams::PrintToStringParamName);
 
 // Note: number of CPUs includes aliases.
-static constexpr unsigned NumAArch64CPUArchs = 81;
+static constexpr unsigned NumAArch64CPUArchs = 82;
 
 TEST(TargetParserTest, testAArch64CPUArchList) {
   SmallVector<StringRef, NumAArch64CPUArchs> List;



More information about the cfe-commits mailing list