Amazon Graviton2 vs. AMD EPYC 7742

Graviton2 versus AMD EPYC 7742 bare metal benchmarks by Michael Larabel.

HTML result view exported from: https://openbenchmarking.org/result/2005220-NI-GRAVITON200&grr.

Amazon Graviton2 vs. AMD EPYC 7742ProcessorMotherboardMemoryDiskNetworkChipsetGraphicsMonitorOSKernelCompilerFile-SystemDesktopDisplay ServerDisplay DriverOpenGLScreen ResolutionGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128tARMv8 Neoverse-N1 (64 Cores)Amazon EC2 m6g.metal v1.0252GB137GB Amazon Elastic Block StoreAmazon ElasticUbuntu 20.045.4.0-1009-aws (aarch64)GCC 9.3.0ext4AMD EPYC 7742 64-Core @ 2.25GHz (64 Cores)AMD DAYTONA_X (RDY1006G BIOS)AMD Starship/Matisse3841GB Micron_9300_MTFDHAL3T8TDPllvmpipe 252GBVE2282 x Mellanox MT277105.4.0-31-generic (x86_64)GNOME Shell 3.36.1X Server 1.20.8modesetting 1.20.83.3 Mesa 20.0.4 (LLVM 9.0.1 128 bits)1920x1080AMD EPYC 7742 64-Core @ 2.25GHz (64 Cores / 128 Threads)OpenBenchmarking.orgCompiler Details- Graviton2 64c: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v - EPYC 7742 64c: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - EPYC 7742 64c 128t: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details- Graviton2 64c: NONE / discard,relatime,rw- EPYC 7742 64c: NONE / errors=remount-ro,relatime,rw- EPYC 7742 64c 128t: NONE / errors=remount-ro,relatime,rwJava Details- OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Details- Python 2.7.18rc1 + Python 3.8.2Security Details- Graviton2 64c: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + tsx_async_abort: Not affected - EPYC 7742 64c: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: disabled RSB filling + tsx_async_abort: Not affected - EPYC 7742 64c 128t: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected Processor Details- EPYC 7742 64c, EPYC 7742 64c 128t: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301034

Amazon Graviton2 vs. AMD EPYC 7742build-gcc: Time To Compilejava-gradle-perf: Reactorbasis: UASTC Level 2 + RDO Post-Processingcryptopp: All Algorithmsblogbench: Writepgbench: Buffer Test - Normal Load - Read Writemysqlslap: 512mysqlslap: 256lczero: Eigenmysqlslap: 128cryptopp: Keyed Algorithmspgbench: Buffer Test - Normal Load - Read Onlycryptopp: Integer + Elliptic Curve Public Key Algorithmshpcg: build-llvm: Time To Compilemysqlslap: 64blosc: blosclzmrbayes: Primate Phylogeny Analysisasmfish: 1024 Hash Memory, 26 Depthminion: Quasigroupstress-ng: CPU Cachegegl: Cartoonrav1e: 10renaissance: Savina Reactors.IOmysqlslap: 32renaissance: Akka Unbalanced Cobwebbed Treebuild-linux-kernel: Time To Compilemysqlslap: 4minion: Solitairegromacs: Water Benchmarkcassandra: Writesnpb: LU.Cparboil: OpenMP MRI Griddinggegl: Wavelet Blurgegl: Color Enhanceperl-benchmark: Pod2htmlmysqlslap: 16npb: BT.Cbuild2: Time To Compilemysqlslap: 8stress-ng: System V Message Passingstress-ng: Context Switchingstress-ng: Memory Copyingcryptopp: Unkeyed Algorithmsmysqlslap: 1himeno: Poisson Pressure Solverttsiod-renderer: Phong Rendering With Soft-Shadow Mappingbasis: ETC1Scython-bench: john-the-ripper: MD5graphics-magick: Sharpengraphics-magick: Rotategraphics-magick: Noise-Gaussiangraphics-magick: Enhancedgraphics-magick: HWB Color Spacegraphics-magick: Swirlrawtherapee: Total Benchmark Timeminion: Gracefulgegl: Rotate 90 Degreesgegl: Antialiascompress-7zip: Compress Speed Testbuild-php: Time To Compilerenaissance: Apache Spark PageRankebizzy: vpxenc: Speed 5npb: EP.Dnpb: IS.Drust-mandel: Time To Complete Serial/Parallel Mandelbrotgegl: Tile Glassgegl: Reflectswet: Averageredis: SADDnode-express-loadtest: redis: LPOPnode-octane: redis: GETrenaissance: Apache Spark Bayesrenaissance: Apache Spark ALSjohn-the-ripper: Blowfishstress-ng: CPU Stressstress-ng: Mallocstress-ng: Atomicstress-ng: MMAPstress-ng: Vector Mathstress-ng: Cryptostress-ng: Glibc Qsort Data Sortingstress-ng: Glibc C String Functionsstress-ng: Semaphoresgo-benchmark: buildcoremark: CoreMark Size 666 - Iterations Per Secondencode-flac: WAV To FLACrodinia: OpenMP Streamclusternpb: SP.Bgimp: unsharp-masknpb: FT.Credis: SETparboil: OpenMP LBMcompress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9build-imagemagick: Time To Compiledav1d: Chimera 1080pbasis: UASTC Level 0gimp: auto-levelsopenssl: RSA 4096-bit Performancebasis: UASTC Level 3neat: renaissance: Rand Forestgimp: rotatem-queens: Time To Solvego-benchmark: garbagerenaissance: Genetic Algorithm Using Jenetics + Futuresrenaissance: Scala Dottygo-benchmark: jsonc-ray: Total Time - 4K, 16 Rays Per Pixelbasis: UASTC Level 2sockperf: Throughputdav1d: Summer Nature 4Kredis: LPUSHgimp: resizegegl: Cropencode-mp3: WAV To MP3compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19npb: MG.Crodinia: OpenMP CFD Solvermafft: Multiple Sequence Alignmentgegl: Scalerodinia: OpenMP LavaMDtjbench: Decompression Throughputdav1d: Summer Nature 1080pprimesieve: 1e12 Prime Number Generationnpb: EP.Cdarktable: Boat - CPU-onlydarktable: Masskrug - CPU-onlyx264: H.264 Video Encodingnettle: aes256optcarrot: Optimized Benchmarkdarktable: Server Room - CPU-onlyn-queens: Elapsed Timetscp: AI Chess Performancesmallpt: Global Illumination Renderer; 128 Samplesnettle: sha512nettle: chachacloverleaf: Lagrangian-Eulerian Hydrodynamicsnettle: poly1305-aesGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1014.193491.393878.012636.516544180172280.1751345505482318651310.970923176350.4069371270.01105721.4310300.7929659658.2257.320105936115165.65566413.37158.7240.31133873.794128826628.12287.9121797127.6331512.74726698918641.5240.12108085.54789.1850.17490547153124463.1085.925163510623060.9521475660.3610027.87344.03281730862890.311784411.61780.21381.59012750007174965617011018151361.39571.13401367.12454.33417979464.15225931.7223454279.022228.04844.5843.03143.05545.2663210261021340494.5065531755471.58293401644303.922676.4286639.738433357220.62712364028.71231714.32865.74353814.7411364.24441.763519134.356276772.99311362503841237272.87526732.66413.9999935.4031.94021669.911244328.3420.60962221.90928.667588.3919.79826.1532628.321.25118.6385806.62322.08718.7437724472374.7019767.832139531415.54514.958386634239.59963398.8813.24612.10610.9039.40725892.628.1742.2469.5978.131108.800089648.056.3282236.163.7553.566140.782782.9868.672.5853.678690102.912379.99449.9311.61949.75856.970341.376726.9731388.4403153960442359.0017664454444102534547.790418611893.0681114206.41814217.7464224.88711869296.5105.65394537908132.63676262.25114.1212.66916569.162258018076.81829.645794377.4391112.501211622109034.3693.32079677.87070.2420.147855605474102257.0462.960705522845900.4215203224.4114243.42303.239346111943827.226775978.00753.54450.96044116676095565828641241158255.79751.15941547.74748.62421571544.09321687.606248894418.164318.05967.6140.42839.07836.8986075504741559703.9976831720173.10385971721920.613426.4616202.1617556416311.721097638087.34424049.95538.85316216.2011923.07565.805116590.965325535.94282382114261536926.3243069.8719.15118585.8422.00731351.481405513.4117.89918621.76317.725456.907.84617.75612843.019.28717.0755005.11014.92319.0399815703206.9726576.560141119912.42513.207454975271.321150357.759.6929.7899.1119.00342388.337.6762.1607.0806.676172.621813525.134.6644176.383.1952.864154.574794.98106.941.7494.00710298782.777491.47771.2330.292103.68850.033340.723728.8891388.2736004864637417.9064973944032041487547.492068988939.1984324195.34730317.5552226.62011336876.1106.972131314356132.61069646.80114.3892.32419664.723248121717.10026.766744777.6735322.289220011102048.49110.13953278.11570.3600.14684740515592544.2664.256659326968236.9326364845.1612405.95303.112596112933912.005207881.38153.66151.37945250006025506348841174176458.83551.44307347.92648.74826962642.94621483.402307532018.184271.16971.9339.00439.04537.0376058816671683866.4177712168678.10383322047459.143529.7716324.9407491419526.191248712298.23403796.58934.59424666.6112828.13741.196797662.879258346.82296679435411988375.1584099.7988.93622447.1422.21831228.981493004.1722.02201921.89617.074599.057.85517.63812586.617.82817.2775011.82214.70512.8718956163143.3896532.497127325311.92012.666448694331.421307306.849.6619.7829.1159.06738200.267.3502.1367.0026.319172.617150677.594.7214129.253.4923.199156.164795.26107.111.9952.60210226432.150491.16771.1410.402102.49OpenBenchmarking.org

Timed GCC Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 9.3.0Time To CompileGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2004006008001000SE +/- 2.04, N = 3SE +/- 1.11, N = 3SE +/- 0.17, N = 31014.19856.97850.03

Java Gradle Build

Gradle Build: Reactor

OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle BuildGradle Build: ReactorGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t110220330440550SE +/- 18.56, N = 9SE +/- 2.96, N = 3SE +/- 11.27, N = 6491.39341.38340.72

Basis Universal

Settings: UASTC Level 2 + RDO Post-Processing

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2 + RDO Post-ProcessingGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2004006008001000SE +/- 0.17, N = 3SE +/- 0.06, N = 3SE +/- 0.18, N = 3878.01726.97728.891. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Crypto++

Test: All Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: All AlgorithmsGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t30060090012001500SE +/- 0.33, N = 3SE +/- 1.06, N = 3SE +/- 0.31, N = 3636.521388.441388.271. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

BlogBench

Test: Write

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: WriteGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t10K20K30K40K50KSE +/- 1359.02, N = 3SE +/- 561.49, N = 4SE +/- 692.73, N = 31801739604486461. (CC) gcc options: -O2 -pthread

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read WriteGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t9K18K27K36K45KSE +/- 45.86, N = 9SE +/- 37.91, N = 3SE +/- 110.45, N = 32280.1842359.0037417.911. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

MariaDB

Clients: 512

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 512Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t120240360480600SE +/- 2.06, N = 3SE +/- 0.61, N = 3SE +/- 1.72, N = 35504453941. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

MariaDB

Clients: 256

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 256Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t120240360480600SE +/- 3.38, N = 3SE +/- 0.24, N = 3SE +/- 0.64, N = 35484444031. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

LeelaChessZero

Backend: Eigen

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.25Backend: EigenGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t9001800270036004500SE +/- 39.54, N = 3SE +/- 38.67, N = 3SE +/- 25.11, N = 52318410220411. (CXX) g++ options: -pthread

MariaDB

Clients: 128

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 128Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t140280420560700SE +/- 3.08, N = 3SE +/- 0.66, N = 3SE +/- 0.29, N = 36515344871. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

Crypto++

Test: Keyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Keyed AlgorithmsGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t120240360480600SE +/- 0.15, N = 3SE +/- 0.27, N = 3SE +/- 0.08, N = 3310.97547.79547.491. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t200K400K600K800K1000KSE +/- 4653.04, N = 6SE +/- 4724.61, N = 3SE +/- 4038.72, N = 3176350.41611893.07988939.201. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Crypto++

Test: Integer + Elliptic Curve Public Key Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Integer + Elliptic Curve Public Key AlgorithmsGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t9001800270036004500SE +/- 0.65, N = 3SE +/- 2.97, N = 3SE +/- 2.27, N = 31270.014206.424195.351. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t510152025SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 321.4317.7517.561. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To CompileGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t70140210280350SE +/- 4.33, N = 3SE +/- 1.52, N = 3SE +/- 0.27, N = 3300.79224.89226.62

MariaDB

Clients: 64

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 64Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t30060090012001500SE +/- 6.47, N = 3SE +/- 0.35, N = 4SE +/- 1.55, N = 3965118611331. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

C-Blosc

Compressor: blosclz

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.0 Beta 5Compressor: blosclzGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2K4K6K8K10KSE +/- 47.95, N = 3SE +/- 22.77, N = 3SE +/- 4.44, N = 39658.29296.56876.11. (CXX) g++ options: -rdynamic

Timed MrBayes Analysis

Primate Phylogeny Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t60120180240300SE +/- 0.26, N = 3SE +/- 0.12, N = 3SE +/- 0.84, N = 3257.32105.65106.97-mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm-mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm1. (CC) gcc options: -O3 -std=c99 -pedantic -lm

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t30M60M90M120M150MSE +/- 734052.82, N = 3SE +/- 775749.19, N = 3SE +/- 1280575.13, N = 310593611594537908131314356

Minion

Benchmark: Quasigroup

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: QuasigroupGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t4080120160200SE +/- 0.84, N = 3SE +/- 0.21, N = 3SE +/- 0.29, N = 3165.66132.64132.611. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

Stress-NG

Test: CPU Cache

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU CacheGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1428425670SE +/- 0.57, N = 12SE +/- 0.90, N = 15SE +/- 1.15, N = 1513.3762.2546.801. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

GEGL

Operation: Cartoon

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CartoonGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t4080120160200SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3158.72114.12114.39

rav1e

Speed: 10

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.3.0Speed: 10Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t0.60051.2011.80152.4023.0025SE +/- 0.000, N = 3SE +/- 0.005, N = 3SE +/- 0.005, N = 30.3112.6692.324

Renaissance

Test: Savina Reactors.IO

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Savina Reactors.IOGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t7K14K21K28K35KSE +/- 446.60, N = 5SE +/- 184.32, N = 25SE +/- 297.23, N = 2033873.7916569.1619664.72

MariaDB

Clients: 32

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 32Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t6001200180024003000SE +/- 7.72, N = 3SE +/- 4.43, N = 3SE +/- 6.17, N = 31288258024811. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

Renaissance

Test: Akka Unbalanced Cobwebbed Tree

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Akka Unbalanced Cobwebbed TreeGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t6K12K18K24K30KSE +/- 327.70, N = 25SE +/- 200.56, N = 5SE +/- 223.45, N = 526628.1218076.8221717.10

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t20406080100SE +/- 0.99, N = 3SE +/- 0.28, N = 10SE +/- 0.20, N = 1387.9129.6526.77

MariaDB

Clients: 4

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 4Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2K4K6K8K10KSE +/- 17.47, N = 3SE +/- 6.35, N = 10SE +/- 75.43, N = 81797794374471. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

Minion

Benchmark: Solitaire

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: SolitaireGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t306090120150SE +/- 0.31, N = 3SE +/- 0.34, N = 3SE +/- 0.34, N = 3127.6377.4477.671. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.1Water BenchmarkGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t0.61811.23621.85432.47243.0905SE +/- 0.006, N = 3SE +/- 0.013, N = 3SE +/- 0.026, N = 32.7472.5012.2891. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: WritesGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t60K120K180K240K300KSE +/- 4840.50, N = 2SE +/- 2526.79, N = 3SE +/- 2670.22, N = 3266989211622220011

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t20K40K60K80K100KSE +/- 140.01, N = 3SE +/- 113.11, N = 3SE +/- 1012.10, N = 1518641.52109034.36102048.491. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3

Parboil

Test: OpenMP MRI Gridding

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t20406080100SE +/- 0.24, N = 3SE +/- 0.25, N = 3SE +/- 0.32, N = 340.1293.32110.141. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

GEGL

Operation: Wavelet Blur

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Wavelet BlurGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t20406080100SE +/- 0.33, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 385.5577.8778.12

GEGL

Operation: Color Enhance

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Color EnhanceGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t20406080100SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 389.1970.2470.36

Perl Benchmarks

Test: Pod2html

OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: Pod2htmlGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t0.03940.07880.11820.15760.197SE +/- 0.00053055, N = 3SE +/- 0.00100736, N = 3SE +/- 0.00125382, N = 30.174905470.147855600.14684740

MariaDB

Clients: 16

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 16Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t12002400360048006000SE +/- 9.85, N = 3SE +/- 10.01, N = 3SE +/- 26.71, N = 31531547451551. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t20K40K60K80K100KSE +/- 4.67, N = 3SE +/- 1483.41, N = 4SE +/- 1221.04, N = 524463.10102257.0492544.261. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3

Build2

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.12Time To CompileGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t20406080100SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 385.9362.9664.26

MariaDB

Clients: 8

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 8Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t15003000450060007500SE +/- 6.23, N = 3SE +/- 12.49, N = 4SE +/- 14.52, N = 31635705565931. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

Stress-NG

Test: System V Message Passing

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: System V Message PassingGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t6M12M18M24M30MSE +/- 98960.78, N = 3SE +/- 174925.99, N = 3SE +/- 373815.20, N = 1510623060.9522845900.4226968236.931. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context SwitchingGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t6M12M18M24M30MSE +/- 104061.74, N = 3SE +/- 205500.78, N = 3SE +/- 714410.24, N = 1521475660.3615203224.4126364845.161. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Memory Copying

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Memory CopyingGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t3K6K9K12K15KSE +/- 1.90, N = 3SE +/- 386.12, N = 15SE +/- 33.48, N = 310027.8714243.4212405.951. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Crypto++

Test: Unkeyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed AlgorithmsGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t70140210280350SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 3344.03303.24303.111. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

MariaDB

Clients: 1

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.5.2Clients: 1Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2K4K6K8K10KSE +/- 9.56, N = 3SE +/- 41.61, N = 3SE +/- 137.28, N = 15308611194112931. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t8001600240032004000SE +/- 12.32, N = 3SE +/- 28.36, N = 3SE +/- 56.90, N = 42890.313827.233912.01-mavx2-mavx21. (CC) gcc options: -O3

TTSIOD 3D Renderer

Phong Rendering With Soft-Shadow Mapping

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2004006008001000SE +/- 12.93, N = 12SE +/- 12.37, N = 5SE +/- 6.32, N = 3411.62978.01881.38-msse -mrecip -mfpmath=sse -msse2 -mssse3-msse -mrecip -mfpmath=sse -msse2 -mssse31. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -lSDL -fopenmp -fwhole-program -lstdc++

Basis Universal

Settings: ETC1S

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: ETC1SGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t20406080100SE +/- 0.43, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 380.2153.5453.661. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Cython benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterCython benchmark 0.27Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t20406080100SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.65, N = 381.5950.9651.38

John The Ripper

Test: MD5

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD5Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1000K2000K3000K4000K5000KSE +/- 3000.00, N = 3SE +/- 2666.67, N = 3SE +/- 4163.33, N = 3127500044116674525000-m64-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t150300450600750SE +/- 0.33, N = 3717609602-lfreetype1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t120240360480600SE +/- 6.23, N = 3SE +/- 4.41, N = 3SE +/- 2.67, N = 3496556550-lfreetype1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t140280420560700SE +/- 0.67, N = 3SE +/- 0.88, N = 3SE +/- 2.40, N = 3561582634-lfreetype1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2004006008001000SE +/- 0.58, N = 3701864884-lfreetype1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t30060090012001500SE +/- 1.76, N = 3SE +/- 1.76, N = 3SE +/- 3.51, N = 3101812411174-lfreetype1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t400800120016002000SE +/- 3.61, N = 3SE +/- 1.20, N = 3SE +/- 5.57, N = 3151315821764-lfreetype1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

RawTherapee

Total Benchmark Time

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1428425670SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 361.4055.8058.841. RawTherapee, version 5.8, command line.

Minion

Benchmark: Graceful

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: GracefulGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1632486480SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 371.1351.1651.441. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

GEGL

Operation: Rotate 90 Degrees

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Rotate 90 DegreesGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1530456075SE +/- 0.10, N = 3SE +/- 0.15, N = 3SE +/- 0.02, N = 367.1247.7547.93

GEGL

Operation: Antialias

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: AntialiasGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1224364860SE +/- 0.13, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 354.3348.6248.75

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t60K120K180K240K300KSE +/- 597.59, N = 3SE +/- 477.98, N = 3SE +/- 620.36, N = 31797942157152696261. (CXX) g++ options: -pipe -lpthread

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To CompileGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1428425670SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 364.1544.0942.95

Renaissance

Test: Apache Spark PageRank

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark PageRankGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t6K12K18K24K30KSE +/- 278.60, N = 5SE +/- 125.46, N = 5SE +/- 241.74, N = 525931.7221687.6121483.40

ebizzy

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t700K1400K2100K2800K3500KSE +/- 8227.80, N = 15SE +/- 8402.66, N = 3SE +/- 39888.00, N = 3345427248894430753201. (CC) gcc options: -pthread -lpthread -O3 -march=native

VP9 libvpx Encoding

Speed: Speed 5

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 5Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t48121620SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 39.0218.1618.18-march=armv8-a-m64-m641. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t9001800270036004500SE +/- 2.85, N = 3SE +/- 3.01, N = 3SE +/- 8.82, N = 32228.044318.054271.161. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2004006008001000SE +/- 3.48, N = 3SE +/- 12.97, N = 3SE +/- 14.61, N = 3844.58967.61971.931. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3

Rust Mandelbrot

Time To Complete Serial/Parallel Mandelbrot

OpenBenchmarking.orgSeconds, Fewer Is BetterRust MandelbrotTime To Complete Serial/Parallel MandelbrotGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1020304050SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 343.0340.4339.00-m64-m641. (CC) gcc options: -pie -nodefaultlibs -lutil -ldl -lrt -lpthread -lgcc_s -lc -lm

GEGL

Operation: Tile Glass

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Tile GlassGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1020304050SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 343.0639.0839.05

GEGL

Operation: Reflect

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ReflectGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1020304050SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 345.2736.9037.04

Swet

Average

OpenBenchmarking.orgOperations Per Second, More Is BetterSwet 1.5.16AverageGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t130M260M390M520M650MSE +/- 310568.82, N = 3SE +/- 4322060.32, N = 3SE +/- 1731105.92, N = 33210261026075504746058816671. (CC) gcc options: -lm -lpthread -lcurses -lrt

Redis

Test: SADD

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SADDGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t400K800K1200K1600K2000KSE +/- 20080.65, N = 3SE +/- 37698.60, N = 15SE +/- 30991.56, N = 151340494.501559703.991683866.411. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Node.js Express HTTP Load Test

OpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load TestGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t17003400510068008500SE +/- 79.37, N = 15SE +/- 15.62, N = 3SE +/- 90.06, N = 36553768377711. Nodejs v10.19.0

Redis

Test: LPOP

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPOPGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t500K1000K1500K2000K2500KSE +/- 7219.96, N = 3SE +/- 87395.86, N = 12SE +/- 45135.23, N = 151755471.581720173.102168678.101. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Node.js Octane Benchmark

OpenBenchmarking.orgScore, More Is BetterNode.js Octane BenchmarkGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t8K16K24K32K40KSE +/- 82.34, N = 3SE +/- 54.76, N = 3SE +/- 155.81, N = 32934038597383321. Nodejs v10.19.0

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GETGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t400K800K1200K1600K2000KSE +/- 19731.78, N = 3SE +/- 49844.86, N = 12SE +/- 46774.40, N = 121644303.921721920.612047459.141. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Renaissance

Test: Apache Spark Bayes

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark BayesGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t8001600240032004000SE +/- 16.86, N = 5SE +/- 31.10, N = 5SE +/- 31.46, N = 252676.433426.463529.77

Renaissance

Test: Apache Spark ALS

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALSGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t14002800420056007000SE +/- 47.97, N = 5SE +/- 45.99, N = 16SE +/- 68.32, N = 56639.746202.166324.94

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t16K32K48K64K80KSE +/- 11.29, N = 3SE +/- 17.07, N = 3SE +/- 49.17, N = 3433357556474914-m64-m641. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU StressGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t4K8K12K16K20KSE +/- 0.34, N = 3SE +/- 16.32, N = 3SE +/- 17.20, N = 37220.6216311.7219526.191. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Malloc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MallocGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t300M600M900M1200M1500MSE +/- 603865.65, N = 3SE +/- 1348531.50, N = 3SE +/- 2770486.87, N = 3712364028.711097638087.341248712298.231. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Atomic

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: AtomicGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t90K180K270K360K450KSE +/- 756.68, N = 3SE +/- 146.09, N = 3SE +/- 147.04, N = 3231714.32424049.95403796.581. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: MMAP

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: MMAPGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2004006008001000SE +/- 0.63, N = 3SE +/- 0.56, N = 3SE +/- 0.88, N = 3865.74538.85934.591. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector MathGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t90K180K270K360K450KSE +/- 2.26, N = 3SE +/- 25.04, N = 3SE +/- 22.32, N = 3353814.74316216.20424666.611. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CryptoGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t3K6K9K12K15KSE +/- 25.31, N = 3SE +/- 18.74, N = 3SE +/- 29.74, N = 311364.2411923.0712828.131. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Glibc Qsort Data Sorting

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc Qsort Data SortingGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t160320480640800SE +/- 0.98, N = 3SE +/- 8.12, N = 3SE +/- 1.48, N = 3441.76565.80741.191. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Glibc C String Functions

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Glibc C String FunctionsGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t1.5M3M4.5M6M7.5MSE +/- 3159.35, N = 3SE +/- 34550.61, N = 3SE +/- 108910.76, N = 33519134.355116590.966797662.871. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Semaphores

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: SemaphoresGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2M4M6M8M10MSE +/- 9411.48, N = 3SE +/- 6529.14, N = 3SE +/- 3849.76, N = 36276772.995325535.949258346.821. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc

Go Benchmarks

Test: build

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: buildGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t7000M14000M21000M28000M35000MSE +/- 11752689.24, N = 3SE +/- 179022572.52, N = 3SE +/- 53807658.06, N = 3311362503842823821142629667943541

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t400K800K1200K1600K2000KSE +/- 138.10, N = 3SE +/- 7872.26, N = 3SE +/- 5055.38, N = 31237272.881536926.321988375.161. (CC) gcc options: -O2 -lrt" -lrt

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t816243240SE +/- 0.025, N = 5SE +/- 0.006, N = 5SE +/- 0.008, N = 532.6649.8719.7981. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP StreamclusterGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t48121620SE +/- 0.146, N = 14SE +/- 0.024, N = 3SE +/- 0.010, N = 313.9999.1518.9361. (CXX) g++ options: -O2 -lOpenCL

NAS Parallel Benchmarks

Test / Class: SP.B

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t5K10K15K20K25KSE +/- 4.95, N = 3SE +/- 233.51, N = 3SE +/- 217.12, N = 39935.4018585.8422447.141. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3

GIMP

Test: unsharp-mask

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: unsharp-maskGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t714212835SE +/- 0.23, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 331.9422.0122.22

NAS Parallel Benchmarks

Test / Class: FT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t7K14K21K28K35KSE +/- 4.05, N = 3SE +/- 128.22, N = 3SE +/- 108.47, N = 321669.9131351.4831228.981. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t300K600K900K1200K1500KSE +/- 4424.59, N = 3SE +/- 23286.40, N = 15SE +/- 18650.88, N = 31244328.341405513.411493004.171. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Parboil

Test: OpenMP LBM

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBMGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t510152025SE +/- 0.03, N = 3SE +/- 0.28, N = 3SE +/- 0.29, N = 320.6117.9022.021. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

XZ Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9

OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t510152025SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.15, N = 321.9121.7621.901. (CC) gcc options: -pthread -fvisibility=hidden -O2

Timed ImageMagick Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To CompileGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t714212835SE +/- 0.13, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 328.6717.7317.07

dav1d

Video Input: Chimera 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.6.0Video Input: Chimera 1080pGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t130260390520650SE +/- 0.55, N = 3SE +/- 1.39, N = 3SE +/- 0.89, N = 3588.39456.90599.05MIN: 427.39 / MAX: 777.07MIN: 319.39 / MAX: 559.29MIN: 345.23 / MAX: 743.971. (CC) gcc options: -pthread

Basis Universal

Settings: UASTC Level 0

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 0Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t510152025SE +/- 0.218, N = 7SE +/- 0.011, N = 3SE +/- 0.006, N = 319.7987.8467.8551. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

GIMP

Test: auto-levels

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: auto-levelsGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t612182430SE +/- 0.15, N = 3SE +/- 0.16, N = 3SE +/- 0.13, N = 326.1517.7617.64

OpenSSL

RSA 4096-bit Performance

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t3K6K9K12K15KSE +/- 0.56, N = 3SE +/- 12.96, N = 3SE +/- 0.69, N = 32628.312843.012586.6-m64-m641. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

Basis Universal

Settings: UASTC Level 3

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 3Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t510152025SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 321.2519.2917.831. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Nebular Empirical Analysis Tool

OpenBenchmarking.orgSeconds, Fewer Is BetterNebular Empirical Analysis Tool 2020-02-29Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t510152025SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 318.6417.0817.281. (F9X) gfortran options: -cpp -ffree-line-length-0 -Jsource/ -fopenmp -O3 -fno-backtrace

Renaissance

Test: Random Forest

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Random ForestGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t12002400360048006000SE +/- 38.49, N = 5SE +/- 29.52, N = 5SE +/- 67.01, N = 55806.625005.115011.82

GIMP

Test: rotate

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: rotateGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t510152025SE +/- 0.01, N = 3SE +/- 0.15, N = 3SE +/- 0.03, N = 322.0914.9214.71

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t510152025SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 318.7419.0412.871. (CXX) g++ options: -fopenmp -O2 -march=native

Go Benchmarks

Test: garbage

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: garbageGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t200K400K600K800K1000KSE +/- 10663.19, N = 4SE +/- 11062.32, N = 3SE +/- 12148.68, N = 3772447981570895616

Renaissance

Test: Genetic Algorithm Using Jenetics + Futures

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Genetic Algorithm Using Jenetics + FuturesGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t7001400210028003500SE +/- 10.21, N = 5SE +/- 17.98, N = 5SE +/- 41.69, N = 252374.703206.973143.39

Renaissance

Test: Scala Dotty

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Scala DottyGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t2K4K6K8K10KSE +/- 54.25, N = 5SE +/- 16.73, N = 5SE +/- 21.98, N = 59767.836576.566532.50

Go Benchmarks

Test: json

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: jsonGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t300K600K900K1200K1500KSE +/- 5211.56, N = 3SE +/- 5729.12, N = 3SE +/- 16777.18, N = 4139531414111991273253

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t48121620SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 315.5512.4311.921. (CC) gcc options: -lm -lpthread -O3

Basis Universal

Settings: UASTC Level 2

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t48121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 314.9613.2112.671. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Sockperf

Test: Throughput

OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: ThroughputGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t100K200K300K400K500KSE +/- 2029.76, N = 5SE +/- 4138.37, N = 5SE +/- 4022.67, N = 53866344549754486941. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

dav1d

Video Input: Summer Nature 4K

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.6.0Video Input: Summer Nature 4KGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t70140210280350SE +/- 0.72, N = 3SE +/- 0.32, N = 3SE +/- 1.58, N = 3239.59271.32331.42MIN: 138.3 / MAX: 258.62MIN: 149.06 / MAX: 289.04MIN: 118.03 / MAX: 366.241. (CC) gcc options: -pthread

Redis

Test: LPUSH

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPUSHGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t300K600K900K1200K1500KSE +/- 1934.63, N = 3SE +/- 5408.33, N = 3SE +/- 21281.45, N = 3963398.881150357.751307306.841. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

GIMP

Test: resize

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.18Test: resizeGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t3691215SE +/- 0.082, N = 3SE +/- 0.067, N = 3SE +/- 0.030, N = 313.2469.6929.661

GEGL

Operation: Crop

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CropGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t3691215SE +/- 0.021, N = 3SE +/- 0.066, N = 3SE +/- 0.018, N = 312.1069.7899.782

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t3691215SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.007, N = 310.9039.1119.1151. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm

Zstd Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t3691215SE +/- 0.002, N = 3SE +/- 0.153, N = 3SE +/- 0.007, N = 39.4079.0039.0671. (CC) gcc options: -O3 -pthread -lz -llzma

NAS Parallel Benchmarks

Test / Class: MG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t9K18K27K36K45KSE +/- 2.41, N = 3SE +/- 114.33, N = 3SE +/- 257.15, N = 325892.6242388.3338200.261. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3

Rodinia

Test: OpenMP CFD Solver

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t246810SE +/- 0.052, N = 3SE +/- 0.080, N = 3SE +/- 0.092, N = 48.1747.6767.3501. (CXX) g++ options: -O2 -lOpenCL

Timed MAFFT Alignment

Multiple Sequence Alignment

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.392Multiple Sequence AlignmentGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t0.50541.01081.51622.02162.527SE +/- 0.049, N = 15SE +/- 0.013, N = 3SE +/- 0.029, N = 152.2462.1602.1361. (CC) gcc options: -std=c99 -O3 -lm -lpthread

GEGL

Operation: Scale

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ScaleGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t3691215SE +/- 0.149, N = 3SE +/- 0.036, N = 3SE +/- 0.068, N = 39.5977.0807.002

Rodinia

Test: OpenMP LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t246810SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.006, N = 38.1316.6766.3191. (CXX) g++ options: -O2 -lOpenCL

libjpeg-turbo tjbench

Test: Decompression Throughput

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.0.2Test: Decompression ThroughputGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t4080120160200SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3108.80172.62172.621. (CC) gcc options: -O3 -rdynamic

dav1d

Video Input: Summer Nature 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.6.0Video Input: Summer Nature 1080pGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t150300450600750SE +/- 1.42, N = 3SE +/- 2.15, N = 3SE +/- 1.47, N = 3648.05525.13677.59MIN: 367.46 / MAX: 714.91MIN: 291.81 / MAX: 581.55MIN: 218.5 / MAX: 776.161. (CC) gcc options: -pthread

Primesieve

1e12 Prime Number Generation

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number GenerationGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t246810SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.008, N = 36.3284.6644.7211. (CXX) g++ options: -O3 -lpthread

NAS Parallel Benchmarks

Test / Class: EP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t9001800270036004500SE +/- 1.31, N = 3SE +/- 23.64, N = 3SE +/- 21.28, N = 32236.164176.384129.251. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3

Darktable

Test: Boat - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Boat - Acceleration: CPU-onlyGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t0.84491.68982.53473.37964.2245SE +/- 0.004, N = 3SE +/- 0.016, N = 3SE +/- 0.017, N = 33.7553.1953.492

Darktable

Test: Masskrug - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Masskrug - Acceleration: CPU-onlyGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t0.80241.60482.40723.20964.012SE +/- 0.015, N = 3SE +/- 0.001, N = 3SE +/- 0.005, N = 33.5662.8643.199

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video EncodingGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t306090120150SE +/- 0.35, N = 3SE +/- 2.58, N = 3SE +/- 0.23, N = 3140.78154.57156.16-lavformat -lavcodec -lavutil -lswscale-m64 -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize-m64 -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize1. (CC) gcc options: -ldl -lm -lpthread

Nettle

Test: aes256

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: aes256Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t10002000300040005000SE +/- 0.65, N = 3SE +/- 0.65, N = 3SE +/- 0.74, N = 32782.984794.984795.26MIN: 1656.91 / MAX: 5033.12MIN: 3477.92 / MAX: 7440.81MIN: 3477.09 / MAX: 7440.831. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

Optcarrot

Optimized Benchmark

OpenBenchmarking.orgFPS, More Is BetterOptcarrotOptimized BenchmarkGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t20406080100SE +/- 0.35, N = 4SE +/- 0.34, N = 4SE +/- 0.45, N = 468.67106.94107.111. Graviton2 64c: ruby 2.7.0p0 (2019-12-25 revision 647ee6f091) [aarch64-linux-gnu]2. EPYC 7742 64c: ruby 2.7.0p0 (2019-12-25 revision 647ee6f091) [x86_64-linux-gnu]3. EPYC 7742 64c 128t: ruby 2.7.0p0 (2019-12-25 revision 647ee6f091) [x86_64-linux-gnu]

Darktable

Test: Server Room - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 3.0.1Test: Server Room - Acceleration: CPU-onlyGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t0.58161.16321.74482.32642.908SE +/- 0.004, N = 3SE +/- 0.004, N = 3SE +/- 0.004, N = 32.5851.7491.995

N-Queens

Elapsed Time

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed TimeGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t0.90161.80322.70483.60644.508SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 33.6704.0072.6021. (CC) gcc options: -static -fopenmp -O3 -march=native

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t200K400K600K800K1000KSE +/- 512.87, N = 5SE +/- 720.27, N = 5SE +/- 2923.69, N = 5869010102987810226431. (CC) gcc options: -O3 -march=native

Smallpt

Global Illumination Renderer; 128 Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 SamplesGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t0.65521.31041.96562.62083.276SE +/- 0.004, N = 3SE +/- 0.005, N = 3SE +/- 0.004, N = 32.9122.7772.1501. (CXX) g++ options: -fopenmp -O3

Nettle

Test: sha512

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: sha512Graviton2 64cEPYC 7742 64cEPYC 7742 64c 128t110220330440550SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.03, N = 3379.99491.47491.161. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

Nettle

Test: chacha

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: chachaGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t170340510680850SE +/- 0.52, N = 3SE +/- 0.07, N = 3SE +/- 0.13, N = 3449.93771.23771.14MIN: 267.62 / MAX: 976MIN: 393.13 / MAX: 2103.79MIN: 393.01 / MAX: 2103.791. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

CloverLeaf

Lagrangian-Eulerian Hydrodynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t0.36230.72461.08691.44921.8115SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.610.290.401. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

Nettle

Test: poly1305-aes

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: poly1305-aesGraviton2 64cEPYC 7742 64cEPYC 7742 64c 128t5001000150020002500SE +/- 1.97, N = 3SE +/- 0.04, N = 3SE +/- 0.20, N = 3949.752103.682102.491. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto


Phoronix Test Suite v10.8.5