Amazon EC2 c7g.4xlarge AWS Graviton3

Graviton3 benchmarks by Michael Larabel.

HTML result view exported from: https://openbenchmarking.org/result/2205259-NE-2205240NE17&grr&sro.

Amazon EC2 c7g.4xlarge AWS Graviton3ProcessorMotherboardChipsetMemoryDiskNetworkOSKernelCompilerFile-SystemSystem Layerc7g.4xlargec6g.4xlarge Graviton2ARMv8 Neoverse-V1 (16 Cores)Amazon EC2 c7g.4xlarge (1.0 BIOS)Amazon Device 020032GB193GB Amazon Elastic Block StoreAmazon ElasticUbuntu 22.045.15.0-1004-aws (aarch64)GCC 11.2.0ext4amazonARMv8 Neoverse-N1 (16 Cores)Amazon EC2 c6g.4xlarge (1.0 BIOS)OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-bootstrap --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v Java Details- OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)Python Details- Python 3.10.4Security Details- 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: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected

Amazon EC2 c7g.4xlarge AWS Graviton3build-llvm: Ninjabuild-nodejs: Time To Compilenpb: SP.Cbuild-gem5: Time To Compilelczero: BLASngspice: C7552lczero: Eigennpb: BT.Cnpb: LU.Cavifenc: 0mrbayes: Primate Phylogeny Analysistensorflow-lite: NASNet Mobilesecuremark: SecureMark-TLSngspice: C2670npb: EP.Dgromacs: MPI CPU - water_GMX50_bareavifenc: 2gpaw: Carbon Nanotubeopenssl: SHA256rodinia: OpenMP LavaMDasmfish: 1024 Hash Memory, 26 Depthastcenc: Exhaustivestress-ng: CPU Cachebuild2: Time To Compileonnx: fcn-resnet101-11 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: super-resolution-10 - CPU - Standardhpcg: apache: 1000apache: 500nginx: 500nginx: 100nginx: 200nginx: 1000apache: 100apache: 200npb: IS.Dbuild-php: Time To Compilem-queens: Time To Solverodinia: OpenMP Streamclustersimdjson: PartialTweetssimdjson: DistinctUserIDtensorflow-lite: Inception V4tensorflow-lite: Inception ResNet V2tensorflow-lite: Mobilenet Floattensorflow-lite: SqueezeNettensorflow-lite: Mobilenet Quantopenssl: RSA4096openssl: RSA4096simdjson: Kostyawebp: Quality 100, Lossless, Highest Compressionsimdjson: LargeRandcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speednpb: FT.Cc-ray: Total Time - 4K, 16 Rays Per Pixelcompress-zstd: 19 - Decompression Speedcompress-zstd: 19 - Compression Speedpovray: Trace Timemt-dgemm: Sustained Floating-Point Ratequantlib: compress-zstd: 3 - Compression Speedstockfish: Total Timephpbench: PHP Benchmark Suitecompress-zstd: 3 - Decompression Speedincompact3d: input.i3d 193 Cells Per Directionbuild-imagemagick: Time To Compilepybench: Total For Average Test Timesnpb: CG.Cbuild-apache: Time To Compilestress-ng: CPU Stresssynthmark: VoiceMark_100stress-ng: IO_uringstress-ng: Memory Copyingstress-ng: Cryptostress-ng: Vector Mathstress-ng: Matrix Mathwebp: Quality 100, Losslesscompress-7zip: Decompression Ratingcompress-7zip: Compression Ratingn-queens: Elapsed Timeastcenc: Thoroughcoremark: CoreMark Size 666 - Iterations Per Secondliquid-dsp: 16 - 256 - 57npb: MG.Cdacapobench: Tradesoapdacapobench: Tradebeansavifenc: 6, Losslessrodinia: OpenMP CFD Solverdacapobench: H2avifenc: 6webp: Quality 100, Highest Compressionincompact3d: input.i3d 129 Cells Per Directionamg: dacapobench: Jythonavifenc: 10, Losslesslulesh: tscp: AI Chess Performancelammps: Rhodopsin Proteinc7g.4xlargec6g.4xlarge Graviton2544.929497.5794467.19391.1711103191.286118910339.537730.41256.841251.39711591.9183708198.224934.721.128141.698155.18013722045973143.33432134123139.379764.31115.020387990407609281726.305872719.3373546.32346613.34345710.87352380.98346814.7567231.8873676.951041.9069.48366.82213.2962.622.6941855.140051.32156.603257.941502.95178460.42546.41.9448.2080.73240.639.511791.7738.5173050.341.237.8635.8538642512.74639.1276088916664843508.529.125857027.90411856571.9526.9405029.71675.635843015.786693.3223181.8155258.1780088.7422.769730549782421.53613.9248405413.86055438360666713481.613524320311.90810.47829519.3859.3468.01671425125880733339405.76510940.939137009411.291682.981628.4012356.16488.805864255.2058346449.115133.89406.937384.75314985.4120301263.724558.880.781238.205215.52810723184083215.66626540482159.203937.19142.277286948322334207219.721846629.4550077.81310596.58307349.36308938.67308213.1346995.3550059.97372.7688.89775.22415.4841.511.5346793.945955.72500.873969.351980.2453951.5660.61.1966.1470.492196.331.06244.4862.3232051.634.651.0474.7851231742.42878.82167924544985541.024083540.33317413520.8634.2013404.94470.389770521.812903.0017924.1837753.8964084.0831.082594457128523.13616.5222315464.3398002628900006720.684506434416.51817.035396413.04612.24811.573354793265290056268.3116016.16278723137.935OpenBenchmarking.org

Timed LLVM Compilation

Build System: Ninja

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Ninjac6g.4xlarge Graviton2c7g.4xlarge150300450600750SE +/- 0.49, N = 3SE +/- 5.19, N = 3682.98544.93

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 17.3Time To Compilec6g.4xlarge Graviton2c7g.4xlarge140280420560700SE +/- 0.37, N = 3SE +/- 2.06, N = 3628.40497.58

NAS Parallel Benchmarks

Test / Class: SP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.Cc6g.4xlarge Graviton2c7g.4xlarge10002000300040005000SE +/- 0.57, N = 3SE +/- 9.61, N = 32356.164467.191. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Timed Gem5 Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To Compilec6g.4xlarge Graviton2c7g.4xlarge110220330440550SE +/- 0.53, N = 3SE +/- 1.33, N = 3488.81391.17

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASc6g.4xlarge Graviton2c7g.4xlarge2004006008001000SE +/- 10.22, N = 4SE +/- 6.44, N = 386411031. (CXX) g++ options: -flto -pthread

Ngspice

Circuit: C7552

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552c6g.4xlarge Graviton2c7g.4xlarge60120180240300SE +/- 2.40, N = 7SE +/- 1.94, N = 3255.21191.291. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

LeelaChessZero

Backend: Eigen

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: Eigenc6g.4xlarge Graviton2c7g.4xlarge30060090012001500SE +/- 12.00, N = 3SE +/- 9.70, N = 383411891. (CXX) g++ options: -flto -pthread

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.Cc6g.4xlarge Graviton2c7g.4xlarge2K4K6K8K10KSE +/- 3.20, N = 3SE +/- 7.36, N = 36449.1110339.531. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.Cc6g.4xlarge Graviton2c7g.4xlarge17003400510068008500SE +/- 0.90, N = 3SE +/- 1.96, N = 35133.897730.411. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0c6g.4xlarge Graviton2c7g.4xlarge90180270360450SE +/- 0.13, N = 3SE +/- 0.18, N = 3406.94256.841. (CXX) g++ options: -O3 -fPIC -lm

Timed MrBayes Analysis

Primate Phylogeny Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny Analysisc6g.4xlarge Graviton2c7g.4xlarge80160240320400SE +/- 0.11, N = 3SE +/- 0.24, N = 3384.75251.401. (CC) gcc options: -O3 -std=c99 -pedantic -lm

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet Mobilec6g.4xlarge Graviton2c7g.4xlarge3K6K9K12K15KSE +/- 203.15, N = 15SE +/- 121.56, N = 1514985.411591.9

SecureMark

Benchmark: SecureMark-TLS

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSc6g.4xlarge Graviton2c7g.4xlarge40K80K120K160K200KSE +/- 23.07, N = 3SE +/- 773.26, N = 31203011837081. (CC) gcc options: -pedantic -O3

Ngspice

Circuit: C2670

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670c6g.4xlarge Graviton2c7g.4xlarge60120180240300SE +/- 0.91, N = 3SE +/- 0.86, N = 3263.72198.221. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.Dc6g.4xlarge Graviton2c7g.4xlarge2004006008001000SE +/- 0.23, N = 3SE +/- 0.39, N = 3558.88934.721. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2022.1Implementation: MPI CPU - Input: water_GMX50_barec6g.4xlarge Graviton2c7g.4xlarge0.25380.50760.76141.01521.269SE +/- 0.001, N = 3SE +/- 0.002, N = 30.7811.1281. (CXX) g++ options: -O3

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2c6g.4xlarge Graviton2c7g.4xlarge50100150200250SE +/- 0.12, N = 3SE +/- 0.11, N = 3238.21141.701. (CXX) g++ options: -O3 -fPIC -lm

GPAW

Input: Carbon Nanotube

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 22.1Input: Carbon Nanotubec6g.4xlarge Graviton2c7g.4xlarge50100150200250SE +/- 0.13, N = 3SE +/- 0.08, N = 3215.53155.181. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

OpenSSL

Algorithm: SHA256

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256c6g.4xlarge Graviton2c7g.4xlarge3000M6000M9000M12000M15000MSE +/- 47755430.47, N = 3SE +/- 7739237.92, N = 310723184083137220459731. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

Rodinia

Test: OpenMP LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDc6g.4xlarge Graviton2c7g.4xlarge50100150200250SE +/- 0.01, N = 3SE +/- 0.15, N = 3215.67143.331. (CXX) g++ options: -O2 -lOpenCL

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depthc6g.4xlarge Graviton2c7g.4xlarge7M14M21M28M35MSE +/- 359309.26, N = 3SE +/- 104795.40, N = 32654048232134123

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: Exhaustivec6g.4xlarge Graviton2c7g.4xlarge4080120160200SE +/- 0.00, N = 3SE +/- 0.01, N = 3159.20139.381. (CXX) g++ options: -O3 -flto -pthread

Stress-NG

Test: CPU Cache

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: CPU Cachec6g.4xlarge Graviton2c7g.4xlarge1428425670SE +/- 0.97, N = 15SE +/- 3.64, N = 1237.1964.311. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

Build2

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To Compilec6g.4xlarge Graviton2c7g.4xlarge306090120150SE +/- 0.70, N = 3SE +/- 0.64, N = 3142.28115.02

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: Standardc6g.4xlarge Graviton2c7g.4xlarge918273645SE +/- 0.00, N = 3SE +/- 0.00, N = 328381. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: GPT-2 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: Standardc6g.4xlarge Graviton2c7g.4xlarge2K4K6K8K10KSE +/- 3.50, N = 3SE +/- 2.40, N = 3694879901. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: Standardc6g.4xlarge Graviton2c7g.4xlarge90180270360450SE +/- 0.17, N = 3SE +/- 0.17, N = 33224071. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardc6g.4xlarge Graviton2c7g.4xlarge130260390520650SE +/- 0.17, N = 3SE +/- 0.00, N = 33346091. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: Standardc6g.4xlarge Graviton2c7g.4xlarge6001200180024003000SE +/- 1.74, N = 3SE +/- 1.86, N = 3207228171. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1c6g.4xlarge Graviton2c7g.4xlarge612182430SE +/- 0.02, N = 3SE +/- 0.04, N = 319.7226.311. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

Apache HTTP Server

Concurrent Requests: 1000

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000c6g.4xlarge Graviton2c7g.4xlarge16K32K48K64K80KSE +/- 276.10, N = 3SE +/- 83.83, N = 346629.4572719.331. (CC) gcc options: -shared -fPIC -O2

Apache HTTP Server

Concurrent Requests: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 500c6g.4xlarge Graviton2c7g.4xlarge16K32K48K64K80KSE +/- 578.32, N = 3SE +/- 89.82, N = 350077.8173546.321. (CC) gcc options: -shared -fPIC -O2

nginx

Concurrent Requests: 500

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500c6g.4xlarge Graviton2c7g.4xlarge70K140K210K280K350KSE +/- 3783.68, N = 3SE +/- 1017.52, N = 3310596.58346613.341. (CC) gcc options: -lcrypt -lz -O3 -march=native

nginx

Concurrent Requests: 100

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 100c6g.4xlarge Graviton2c7g.4xlarge70K140K210K280K350KSE +/- 3992.58, N = 3SE +/- 2009.97, N = 3307349.36345710.871. (CC) gcc options: -lcrypt -lz -O3 -march=native

nginx

Concurrent Requests: 200

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200c6g.4xlarge Graviton2c7g.4xlarge80K160K240K320K400KSE +/- 1347.28, N = 3SE +/- 3986.77, N = 3308938.67352380.981. (CC) gcc options: -lcrypt -lz -O3 -march=native

nginx

Concurrent Requests: 1000

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000c6g.4xlarge Graviton2c7g.4xlarge70K140K210K280K350KSE +/- 1677.89, N = 3SE +/- 1410.11, N = 3308213.13346814.751. (CC) gcc options: -lcrypt -lz -O3 -march=native

Apache HTTP Server

Concurrent Requests: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 100c6g.4xlarge Graviton2c7g.4xlarge14K28K42K56K70KSE +/- 93.03, N = 3SE +/- 38.09, N = 346995.3567231.881. (CC) gcc options: -shared -fPIC -O2

Apache HTTP Server

Concurrent Requests: 200

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 200c6g.4xlarge Graviton2c7g.4xlarge16K32K48K64K80KSE +/- 112.65, N = 3SE +/- 649.31, N = 350059.9773676.951. (CC) gcc options: -shared -fPIC -O2

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.Dc6g.4xlarge Graviton2c7g.4xlarge2004006008001000SE +/- 0.20, N = 3SE +/- 2.29, N = 3372.761041.901. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To Compilec6g.4xlarge Graviton2c7g.4xlarge20406080100SE +/- 0.31, N = 3SE +/- 0.11, N = 388.9069.48

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solvec6g.4xlarge Graviton2c7g.4xlarge20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 375.2266.821. (CXX) g++ options: -fopenmp -O2 -march=native

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Streamclusterc6g.4xlarge Graviton2c7g.4xlarge48121620SE +/- 0.26, N = 15SE +/- 0.33, N = 1215.4813.301. (CXX) g++ options: -O2 -lOpenCL

simdjson

Throughput Test: PartialTweets

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: PartialTweetsc6g.4xlarge Graviton2c7g.4xlarge0.58951.1791.76852.3582.9475SE +/- 0.00, N = 3SE +/- 0.00, N = 31.512.621. (CXX) g++ options: -O3

simdjson

Throughput Test: DistinctUserID

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: DistinctUserIDc6g.4xlarge Graviton2c7g.4xlarge0.60531.21061.81592.42123.0265SE +/- 0.00, N = 3SE +/- 0.00, N = 31.532.691. (CXX) g++ options: -O3

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4c6g.4xlarge Graviton2c7g.4xlarge10K20K30K40K50KSE +/- 197.89, N = 3SE +/- 210.27, N = 346793.941855.1

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2c6g.4xlarge Graviton2c7g.4xlarge10K20K30K40K50KSE +/- 336.95, N = 3SE +/- 305.31, N = 345955.740051.3

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Floatc6g.4xlarge Graviton2c7g.4xlarge5001000150020002500SE +/- 28.63, N = 3SE +/- 19.61, N = 32500.872156.60

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetc6g.4xlarge Graviton2c7g.4xlarge9001800270036004500SE +/- 37.23, N = 3SE +/- 22.07, N = 33969.353257.94

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Quantc6g.4xlarge Graviton2c7g.4xlarge400800120016002000SE +/- 14.44, N = 3SE +/- 17.76, N = 31980.241502.95

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096c6g.4xlarge Graviton2c7g.4xlarge40K80K120K160K200KSE +/- 3.30, N = 3SE +/- 82.61, N = 353951.5178460.41. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096c6g.4xlarge Graviton2c7g.4xlarge5001000150020002500SE +/- 0.03, N = 3SE +/- 0.23, N = 3660.62546.41. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

simdjson

Throughput Test: Kostya

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: Kostyac6g.4xlarge Graviton2c7g.4xlarge0.43650.8731.30951.7462.1825SE +/- 0.00, N = 3SE +/- 0.00, N = 31.191.941. (CXX) g++ options: -O3

WebP Image Encode

Encode Settings: Quality 100, Lossless, Highest Compression

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest Compressionc6g.4xlarge Graviton2c7g.4xlarge1530456075SE +/- 0.01, N = 3SE +/- 0.01, N = 366.1548.21-ltiff1. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16

simdjson

Throughput Test: LargeRandom

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: LargeRandomc6g.4xlarge Graviton2c7g.4xlarge0.15750.3150.47250.630.7875SE +/- 0.00, N = 3SE +/- 0.00, N = 30.490.701. (CXX) g++ options: -O3

Zstd Compression

Compression Level: 19, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression Speedc6g.4xlarge Graviton2c7g.4xlarge7001400210028003500SE +/- 2.93, N = 3SE +/- 6.93, N = 32196.33240.6-llzma1. (CC) gcc options: -O3 -pthread -lz

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression Speedc6g.4xlarge Graviton2c7g.4xlarge918273645SE +/- 0.03, N = 3SE +/- 0.23, N = 331.039.5-llzma1. (CC) gcc options: -O3 -pthread -lz

NAS Parallel Benchmarks

Test / Class: FT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.Cc6g.4xlarge Graviton2c7g.4xlarge3K6K9K12K15KSE +/- 1.10, N = 3SE +/- 1.17, N = 36244.4811791.771. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixelc6g.4xlarge Graviton2c7g.4xlarge1428425670SE +/- 0.03, N = 3SE +/- 0.02, N = 362.3238.521. (CC) gcc options: -lm -lpthread -O3

Zstd Compression

Compression Level: 19 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression Speedc6g.4xlarge Graviton2c7g.4xlarge7001400210028003500SE +/- 12.10, N = 3SE +/- 7.75, N = 32051.63050.3-llzma1. (CC) gcc options: -O3 -pthread -lz

Zstd Compression

Compression Level: 19 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression Speedc6g.4xlarge Graviton2c7g.4xlarge918273645SE +/- 0.06, N = 3SE +/- 0.00, N = 334.641.2-llzma1. (CC) gcc options: -O3 -pthread -lz

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Timec6g.4xlarge Graviton2c7g.4xlarge1224364860SE +/- 0.00, N = 3SE +/- 0.01, N = 351.0537.861. (CXX) g++ options: -pipe -O3 -ffast-math -R/usr/lib -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Ratec6g.4xlarge Graviton2c7g.4xlarge1.31712.63423.95135.26846.5855SE +/- 0.007139, N = 3SE +/- 0.016350, N = 34.7851235.8538641. (CC) gcc options: -O3 -march=native -fopenmp

QuantLib

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.21c6g.4xlarge Graviton2c7g.4xlarge5001000150020002500SE +/- 5.40, N = 3SE +/- 0.15, N = 31742.42512.71. (CXX) g++ options: -O3 -march=native -rdynamic

Zstd Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Compression Speedc6g.4xlarge Graviton2c7g.4xlarge10002000300040005000SE +/- 3.74, N = 3SE +/- 9.57, N = 32878.84639.1-llzma1. (CC) gcc options: -O3 -pthread -lz

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Timec6g.4xlarge Graviton2c7g.4xlarge6M12M18M24M30MSE +/- 292329.99, N = 3SE +/- 153578.64, N = 321679245276088911. (CXX) g++ options: -lgcov -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -flto -flto=jobserver

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suitec6g.4xlarge Graviton2c7g.4xlarge140K280K420K560K700KSE +/- 743.13, N = 3SE +/- 525.83, N = 3449855666484

Zstd Compression

Compression Level: 3 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Decompression Speedc7g.4xlarge8001600240032004000SE +/- 2.07, N = 33508.51. (CC) gcc options: -O3 -pthread -lz

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Directionc6g.4xlarge Graviton2c7g.4xlarge918273645SE +/- 0.01, N = 3SE +/- 0.03, N = 341.0229.131. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Timed ImageMagick Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compilec6g.4xlarge Graviton2c7g.4xlarge918273645SE +/- 0.22, N = 3SE +/- 0.13, N = 340.3327.90

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Timesc6g.4xlarge Graviton2c7g.4xlarge400800120016002000SE +/- 1.67, N = 3SE +/- 0.33, N = 317411185

NAS Parallel Benchmarks

Test / Class: CG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.Cc6g.4xlarge Graviton2c7g.4xlarge14002800420056007000SE +/- 9.95, N = 3SE +/- 17.12, N = 33520.866571.951. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Timed Apache Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compilec6g.4xlarge Graviton2c7g.4xlarge816243240SE +/- 0.01, N = 3SE +/- 0.05, N = 334.2026.94

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: CPU Stressc6g.4xlarge Graviton2c7g.4xlarge11002200330044005500SE +/- 0.54, N = 3SE +/- 0.41, N = 33404.945029.711. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

Google SynthMark

Test: VoiceMark_100

OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100c6g.4xlarge Graviton2c7g.4xlarge150300450600750SE +/- 0.33, N = 3SE +/- 0.32, N = 3470.39675.641. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast

Stress-NG

Test: IO_uring

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: IO_uringc6g.4xlarge Graviton2c7g.4xlarge200K400K600K800K1000KSE +/- 2395.13, N = 3SE +/- 614.16, N = 3770521.81843015.781. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

Stress-NG

Test: Memory Copying

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: Memory Copyingc6g.4xlarge Graviton2c7g.4xlarge14002800420056007000SE +/- 3.75, N = 3SE +/- 3.52, N = 32903.006693.321. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: Cryptoc6g.4xlarge Graviton2c7g.4xlarge5K10K15K20K25KSE +/- 92.83, N = 3SE +/- 32.01, N = 317924.1823181.811. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: Vector Mathc6g.4xlarge Graviton2c7g.4xlarge12K24K36K48K60KSE +/- 15.72, N = 3SE +/- 17.05, N = 337753.8955258.171. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

Stress-NG

Test: Matrix Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: Matrix Mathc6g.4xlarge Graviton2c7g.4xlarge20K40K60K80K100KSE +/- 2.76, N = 3SE +/- 3.18, N = 364084.0880088.741. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

WebP Image Encode

Encode Settings: Quality 100, Lossless

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Losslessc6g.4xlarge Graviton2c7g.4xlarge714212835SE +/- 0.02, N = 3SE +/- 0.09, N = 331.0822.77-ltiff1. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 21.06Test: Decompression Ratingc6g.4xlarge Graviton2c7g.4xlarge16K32K48K64K80KSE +/- 239.68, N = 3SE +/- 12.88, N = 359445730541. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 21.06Test: Compression Ratingc6g.4xlarge Graviton2c7g.4xlarge20K40K60K80K100KSE +/- 44.77, N = 3SE +/- 159.36, N = 371285978241. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

N-Queens

Elapsed Time

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed Timec6g.4xlarge Graviton2c7g.4xlarge612182430SE +/- 0.00, N = 3SE +/- 0.00, N = 323.1421.541. (CC) gcc options: -static -fopenmp -O3 -march=native

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: Thoroughc6g.4xlarge Graviton2c7g.4xlarge48121620SE +/- 0.01, N = 3SE +/- 0.00, N = 316.5213.921. (CXX) g++ options: -O3 -flto -pthread

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Secondc6g.4xlarge Graviton2c7g.4xlarge90K180K270K360K450KSE +/- 49.84, N = 3SE +/- 3211.91, N = 3315464.34405413.861. (CC) gcc options: -O2 -lrt" -lrt

Liquid-DSP

Threads: 16 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57c6g.4xlarge Graviton2c7g.4xlarge80M160M240M320M400MSE +/- 35118.85, N = 3SE +/- 400097.21, N = 32628900003836066671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

NAS Parallel Benchmarks

Test / Class: MG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.Cc6g.4xlarge Graviton2c7g.4xlarge3K6K9K12K15KSE +/- 1.39, N = 3SE +/- 4.69, N = 36720.6813481.611. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

DaCapo Benchmark

Java Test: Tradesoap

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradesoapc6g.4xlarge Graviton2c7g.4xlarge10002000300040005000SE +/- 27.95, N = 4SE +/- 14.95, N = 445063524

DaCapo Benchmark

Java Test: Tradebeans

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradebeansc6g.4xlarge Graviton2c7g.4xlarge9001800270036004500SE +/- 40.13, N = 4SE +/- 26.73, N = 443443203

libavif avifenc

Encoder Speed: 6, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, Losslessc6g.4xlarge Graviton2c7g.4xlarge48121620SE +/- 0.17, N = 3SE +/- 0.01, N = 316.5211.911. (CXX) g++ options: -O3 -fPIC -lm

Rodinia

Test: OpenMP CFD Solver

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solverc6g.4xlarge Graviton2c7g.4xlarge48121620SE +/- 0.05, N = 3SE +/- 0.02, N = 317.0410.481. (CXX) g++ options: -O2 -lOpenCL

DaCapo Benchmark

Java Test: H2

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2c6g.4xlarge Graviton2c7g.4xlarge9001800270036004500SE +/- 45.89, N = 4SE +/- 32.57, N = 539642951

libavif avifenc

Encoder Speed: 6

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6c6g.4xlarge Graviton2c7g.4xlarge3691215SE +/- 0.006, N = 3SE +/- 0.025, N = 313.0469.3851. (CXX) g++ options: -O3 -fPIC -lm

WebP Image Encode

Encode Settings: Quality 100, Highest Compression

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest Compressionc6g.4xlarge Graviton2c7g.4xlarge3691215SE +/- 0.043, N = 3SE +/- 0.007, N = 312.2489.346-ltiff1. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16

Xcompact3d Incompact3d

Input: input.i3d 129 Cells Per Direction

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Directionc6g.4xlarge Graviton2c7g.4xlarge3691215SE +/- 0.01351889, N = 3SE +/- 0.01401446, N = 311.573354708.016714251. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Algebraic Multi-Grid Benchmark

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2c6g.4xlarge Graviton2c7g.4xlarge300M600M900M1200M1500MSE +/- 3420043.89, N = 3SE +/- 952437.28, N = 393265290012588073331. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

DaCapo Benchmark

Java Test: Jython

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jythonc6g.4xlarge Graviton2c7g.4xlarge12002400360048006000SE +/- 23.29, N = 4SE +/- 6.99, N = 456263940

libavif avifenc

Encoder Speed: 10, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, Losslessc6g.4xlarge Graviton2c7g.4xlarge246810SE +/- 0.026, N = 3SE +/- 0.021, N = 38.3115.7651. (CXX) g++ options: -O3 -fPIC -lm

LULESH

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3c6g.4xlarge Graviton2c7g.4xlarge2K4K6K8K10KSE +/- 4.88, N = 3SE +/- 76.73, N = 36016.1610940.941. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess Performancec6g.4xlarge Graviton2c7g.4xlarge300K600K900K1200K1500KSE +/- 338.27, N = 5SE +/- 0.00, N = 587231313700941. (CC) gcc options: -O3 -march=native

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin Proteinc6g.4xlarge Graviton2c7g.4xlarge3691215SE +/- 0.014, N = 3SE +/- 0.060, N = 37.93511.2911. (CXX) g++ options: -O3 -lm

Phoronix Test Suite v10.8.4