Amazon EC2 Graviton3 Benchmark Comparison

Amazon AWS Graviton3 benchmarks by Michael Larabel.

HTML result view exported from: https://openbenchmarking.org/result/2205260-PTS-GRAVITON42&grs&rdt.

Amazon EC2 Graviton3 Benchmark ComparisonProcessorMotherboardChipsetMemoryDiskNetworkOSKernelCompilerFile-SystemSystem Layerc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge XeonARMv8 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 Cortex-A72 (16 Cores)Amazon EC2 a1.4xlarge (1.0 BIOS)ARMv8 Neoverse-N1 (16 Cores)Amazon EC2 c6g.4xlarge (1.0 BIOS)AMD EPYC 7R13 (8 Cores / 16 Threads)Amazon EC2 c6a.4xlarge (1.0 BIOS)Intel 440FX 82441FX PMC5.15.0-1004-aws (x86_64)Intel Xeon Platinum 8375C (8 Cores / 16 Threads)Amazon EC2 c6i.4xlarge (1.0 BIOS)OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- c7g.4xlarge Graviton3: --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 - a1.4xlarge Graviton: --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 - c6g.4xlarge Graviton2: --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 - c6a.4xlarge EPYC: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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 - c6i.4xlarge Xeon: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --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-build-config=bootstrap-lto-lean --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 Java Details- OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)Python Details- Python 3.10.4Security Details- c7g.4xlarge Graviton3: 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 - a1.4xlarge Graviton: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Not affected + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Branch predictor hardening BHB + srbds: Not affected + tsx_async_abort: Not affected - c6g.4xlarge Graviton2: 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 - c6a.4xlarge EPYC: 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 Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - c6i.4xlarge Xeon: 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected Processor Details- c6a.4xlarge EPYC: CPU Microcode: 0xa001144- c6i.4xlarge Xeon: CPU Microcode: 0xd000331

Amazon EC2 Graviton3 Benchmark Comparisonstress-ng: Memory Copyingnpb: MG.Cnpb: CG.Cnpb: SP.Ccompress-zstd: 3 - Compression Speednpb: FT.Chpcg: amg: incompact3d: input.i3d 129 Cells Per Directionmt-dgemm: Sustained Floating-Point Rateincompact3d: input.i3d 193 Cells Per Directionstress-ng: CPU Stresssimdjson: DistinctUserIDmrbayes: Primate Phylogeny Analysisnpb: IS.Dtensorflow-lite: Mobilenet Floatgpaw: Carbon Nanotubeavifenc: 2simdjson: PartialTweetslulesh: apache: 100astcenc: Thoroughgromacs: MPI CPU - water_GMX50_baretensorflow-lite: Inception V4apache: 500apache: 200simdjson: Kostyanpb: BT.Copenssl: RSA4096tensorflow-lite: Inception ResNet V2apache: 1000tensorflow-lite: SqueezeNetastcenc: Exhaustiverodinia: OpenMP CFD Solveropenssl: RSA4096avifenc: 0build-nodejs: Time To Compilelammps: Rhodopsin Proteinpybench: Total For Average Test Timesphpbench: PHP Benchmark Suitebuild-imagemagick: Time To Compiletensorflow-lite: NASNet Mobilebuild-apache: Time To Compiledacapobench: Jythonbuild-llvm: Ninjanpb: EP.Dngspice: C2670dacapobench: Tradesoapsimdjson: LargeRandsecuremark: SecureMark-TLSdacapobench: Tradebeansliquid-dsp: 16 - 256 - 57build2: Time To Compilebuild-php: Time To Compilecompress-7zip: Compression Ratingngspice: C7552webp: Quality 100, Lossless, Highest Compressionbuild-gem5: Time To Compilewebp: Quality 100, Losslessavifenc: 6, Losslessnginx: 1000nginx: 500nginx: 200compress-zstd: 19 - Decompression Speednginx: 100tscp: AI Chess Performancecompress-zstd: 19, Long Mode - Decompression Speedstockfish: Total Timerodinia: OpenMP LavaMDpovray: Trace Timecompress-zstd: 19, Long Mode - Compression Speedcompress-zstd: 19 - Compression Speeddacapobench: H2stress-ng: Cryptoasmfish: 1024 Hash Memory, 26 Depthsynthmark: VoiceMark_100openssl: SHA256stress-ng: Vector Mathnpb: LU.Clczero: Eigenlczero: BLAScoremark: CoreMark Size 666 - Iterations Per Secondn-queens: Elapsed Timecompress-7zip: Decompression Ratingm-queens: Time To Solvestress-ng: IO_uringonnx: super-resolution-10 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: GPT-2 - CPU - Standardtensorflow-lite: Mobilenet Quantc-ray: Total Time - 4K, 16 Rays Per Pixelrodinia: OpenMP Streamclusterc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon6693.3213481.616571.954467.194639.111791.7726.305812588073338.016714255.85386429.12585705029.712.69251.3971041.902156.60155.180141.6982.6210940.93967231.8813.92481.12841855.173546.3273676.951.9410339.532546.440051.372719.333257.94139.379710.478178460.4256.841497.57911.291118566648427.90411591.926.9403940544.929934.72198.22435240.71837083203383606667115.02069.48397824191.28648.208391.17122.76911.908346814.75346613.34352380.983050.3345710.8713700943240.627608891143.33437.86339.541.2295123181.8132134123675.6351372204597355258.177730.4111891103405413.86055421.5367305466.822843015.7828176093840779901502.9538.51713.296798.243266.361213.151293.80633.92927.163.7783418671693353.77062740.891391182.5839392366.000.8644.788197.579990.15769.346449.0220.782328.272418636.4333.51980.31618891020133.4920887.580.633148.18588.317116919278.6812014.7277.766941.45045328.6768.3021765.9103.245345224125993.63230986.774.742129971784.600339.20473.901111820.3743569045165513333353.912196.02932498480.793124.7081155.61561.80133.991138205.11139414.84141436.201121.7143155.485385001213.910980430360.30493.8011616.9674011985.3815331550331.070678568951727341.472558.12128135203869.40201732.28540891110.368918172.377571651011523125724.66104.76147.4302903.006720.683520.862356.162878.86244.4819.721893265290011.57335474.78512341.02408353404.941.53384.753372.762500.87215.528238.2051.516016.162746995.3516.52220.78146793.950077.8150059.971.196449.11660.645955.746629.453969.35159.203917.03553951.5406.937628.4017.935174144985540.33314985.434.2015626682.981558.88263.72445060.491203014344262890000142.27788.89771285255.20566.147488.80531.08216.518308213.13310596.58308938.672051.6307349.368723132196.321679245215.66651.04731.034.6396417924.1826540482470.3891072318408337753.895133.89834864315464.33980023.1365944575.224770521.8120723342832269481980.2462.32315.4843551.8016826.436169.228094.792768.718299.965.0604226767070028.27976612.432432110.77002713304.504.30120.636541.352159.72302.95693.9463.645452.105177567.697.98181.00444920.681995.6483070.002.8013134.462088.941366.671537.113103.1272.390821.789136784.2195.532664.3475.067196148074132.6269266.8623.5324616760.344466.21245.88640520.952132883167509746667150.99467.08462562180.35648.677515.20126.70816.394388657.76389030.11390932.792907.5388010.7614426312826.023857623224.33149.43525.930.0301913556.0626187688663.0731169140335353787.6125140.5510011091345133.44054116.3785731872.330768723.46369611926548856173847.9669.34918.3833150.4926298.819522.829563.223440.620423.578.6603166136476717.86827722.23054569.216997812527.164.30134.924861.571965.07202.10697.7353.718112.371586545.577.26251.45241185.791746.5794458.222.4613888.402161.341179.779830.962983.9369.638720.446140964.4204.994604.6206.22099782818629.73710900.622.5274013685.7041103.22147.89338150.862305492928373100000136.80164.33766631161.08141.805469.94021.12217.529347345.49351672.92356829.932582.0356302.8412725962666.122081961281.38952.78433.838.1292110210.3423746200565.690709699393740140.3038136.7714661397285378.84166118.8394565391.2311037943.373450137413977379443967.3992.54523.512OpenBenchmarking.org

Stress-NG

Test: Memory Copying

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: Memory Copyingc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon14002800420056007000SE +/- 3.52, N = 3SE +/- 0.91, N = 3SE +/- 3.75, N = 3SE +/- 11.57, N = 3SE +/- 0.94, N = 36693.32798.242903.003551.803150.491. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

NAS Parallel Benchmarks

Test / Class: MG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.Cc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon6K12K18K24K30KSE +/- 4.69, N = 3SE +/- 1.64, N = 3SE +/- 1.39, N = 3SE +/- 30.62, N = 3SE +/- 184.24, N = 313481.613266.366720.6816826.4326298.811. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

NAS Parallel Benchmarks

Test / Class: CG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.Cc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon2K4K6K8K10KSE +/- 17.12, N = 3SE +/- 11.79, N = 6SE +/- 9.95, N = 3SE +/- 81.25, N = 3SE +/- 66.44, N = 36571.951213.153520.866169.229522.821. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

NAS Parallel Benchmarks

Test / Class: SP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.Cc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon2K4K6K8K10KSE +/- 9.61, N = 3SE +/- 2.51, N = 3SE +/- 0.57, N = 3SE +/- 24.63, N = 3SE +/- 73.65, N = 34467.191293.802356.168094.799563.221. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

Zstd Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Compression Speedc6g.4xlarge Graviton2c6a.4xlarge EPYCc7g.4xlarge Graviton3a1.4xlarge Gravitonc6i.4xlarge Xeon10002000300040005000SE +/- 6.37, N = 3SE +/- 2.65, N = 3SE +/- 9.57, N = 3SE +/- 4.47, N = 3SE +/- 29.53, N = 32888.32784.04639.1633.93440.6-llzma-llzma-llzma-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.Cc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon4K8K12K16K20KSE +/- 1.17, N = 3SE +/- 1.73, N = 3SE +/- 1.10, N = 3SE +/- 45.90, N = 3SE +/- 40.24, N = 311791.772927.166244.4818299.9620423.571. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon612182430SE +/- 0.03738, N = 3SE +/- 0.00065, N = 3SE +/- 0.01639, N = 3SE +/- 0.00225, N = 3SE +/- 0.04033, N = 326.305803.7783419.721805.060428.660311. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

Algebraic Multi-Grid Benchmark

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon300M600M900M1200M1500MSE +/- 952437.28, N = 3SE +/- 176548.39, N = 3SE +/- 3420043.89, N = 3SE +/- 103921.81, N = 3SE +/- 5114517.12, N = 312588073331867169339326529002676707006613647671. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

Xcompact3d Incompact3d

Input: input.i3d 129 Cells Per Direction

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Directionc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon1224364860SE +/- 0.01401446, N = 3SE +/- 0.02862870, N = 3SE +/- 0.01351889, N = 3SE +/- 0.03718674, N = 3SE +/- 0.09619197, N = 38.0167142553.7706274011.5733547028.2797661017.868277201. (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

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Ratec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon1.31712.63423.95135.26846.5855SE +/- 0.016350, N = 3SE +/- 0.002370, N = 3SE +/- 0.007139, N = 3SE +/- 0.023324, N = 6SE +/- 0.003819, N = 35.8538640.8913914.7851232.4324322.2305451. (CC) gcc options: -O3 -march=native -fopenmp

Xcompact3d Incompact3d

Input: input.i3d 193 Cells Per Direction

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Directionc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon4080120160200SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.14, N = 329.13182.5841.02110.7769.221. (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

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: CPU Stressc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon3K6K9K12K15KSE +/- 0.41, N = 3SE +/- 0.16, N = 3SE +/- 0.54, N = 3SE +/- 37.60, N = 3SE +/- 155.66, N = 35029.712366.003404.9413304.5012527.161. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

simdjson

Throughput Test: DistinctUserID

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: DistinctUserIDc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon0.96751.9352.90253.874.8375SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.690.801.534.304.301. (CXX) g++ options: -O3

Timed MrBayes Analysis

Primate Phylogeny Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny Analysisc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon140280420560700SE +/- 0.24, N = 3SE +/- 0.49, N = 3SE +/- 0.11, N = 3SE +/- 0.35, N = 3SE +/- 1.43, N = 3251.40644.79384.75120.64134.92-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 -msha -maes -mavx -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mrdrnd -mbmi -mbmi2 -madx -mabm1. (CC) gcc options: -O3 -std=c99 -pedantic -lm

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.Dc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon2004006008001000SE +/- 2.29, N = 3SE +/- 0.31, N = 3SE +/- 0.20, N = 3SE +/- 0.47, N = 3SE +/- 2.14, N = 31041.90197.57372.76541.35861.571. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

TensorFlow Lite

Model: Mobilenet Float

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Floatc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon2K4K6K8K10KSE +/- 19.61, N = 3SE +/- 113.94, N = 3SE +/- 28.63, N = 3SE +/- 1.03, N = 3SE +/- 1.81, N = 32156.609990.152500.872159.721965.07

GPAW

Input: Carbon Nanotube

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 22.1Input: Carbon Nanotubec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon170340510680850SE +/- 0.08, N = 3SE +/- 5.37, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.24, N = 3155.18769.35215.53302.96202.111. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon100200300400500SE +/- 0.11, N = 3SE +/- 0.29, N = 3SE +/- 0.12, N = 3SE +/- 0.44, N = 3SE +/- 0.26, N = 3141.70449.02238.2193.9597.741. (CXX) g++ options: -O3 -fPIC -lm

simdjson

Throughput Test: PartialTweets

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: PartialTweetsc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon0.83481.66962.50443.33924.174SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.620.781.513.643.711. (CXX) g++ options: -O3

LULESH

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon2K4K6K8K10KSE +/- 76.73, N = 3SE +/- 6.27, N = 3SE +/- 4.88, N = 3SE +/- 5.52, N = 3SE +/- 14.20, N = 310940.942328.276016.165452.118112.371. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

Apache HTTP Server

Concurrent Requests: 100

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 100c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon20K40K60K80K100KSE +/- 38.09, N = 3SE +/- 28.97, N = 3SE +/- 93.03, N = 3SE +/- 211.56, N = 3SE +/- 389.13, N = 367231.8818636.4346995.3577567.6986545.571. (CC) gcc options: -shared -fPIC -O2

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: Thoroughc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon816243240SE +/- 0.0011, N = 3SE +/- 0.0061, N = 3SE +/- 0.0064, N = 3SE +/- 0.0154, N = 3SE +/- 0.0001, N = 313.924833.519816.52227.98187.26251. (CXX) g++ options: -O3 -flto -pthread

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2022.1Implementation: MPI CPU - Input: water_GMX50_barec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon0.32670.65340.98011.30681.6335SE +/- 0.002, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 31.1280.3160.7811.0041.4521. (CXX) g++ options: -O3

TensorFlow Lite

Model: Inception V4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon40K80K120K160K200KSE +/- 210.27, N = 3SE +/- 1746.17, N = 3SE +/- 197.89, N = 3SE +/- 53.95, N = 3SE +/- 75.14, N = 341855.1188910.046793.944920.641185.7

Apache HTTP Server

Concurrent Requests: 500

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 500c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon20K40K60K80K100KSE +/- 89.82, N = 3SE +/- 93.64, N = 3SE +/- 578.32, N = 3SE +/- 636.46, N = 13SE +/- 833.50, N = 773546.3220133.4950077.8181995.6491746.571. (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: 200c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon20K40K60K80K100KSE +/- 649.31, N = 3SE +/- 59.55, N = 3SE +/- 112.65, N = 3SE +/- 644.29, N = 3SE +/- 615.05, N = 373676.9520887.5850059.9783070.0094458.221. (CC) gcc options: -shared -fPIC -O2

simdjson

Throughput Test: Kostya

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: Kostyac7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon0.631.261.892.523.15SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.940.631.192.802.461. (CXX) g++ options: -O3

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.Cc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon3K6K9K12K15KSE +/- 7.36, N = 3SE +/- 3.44, N = 3SE +/- 3.20, N = 3SE +/- 98.45, N = 3SE +/- 22.04, N = 310339.533148.186449.1113134.4613888.401. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon5001000150020002500SE +/- 0.23, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 1.40, N = 3SE +/- 4.47, N = 32546.4588.3660.62088.92161.3-m64-m641. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

TensorFlow Lite

Model: Inception ResNet V2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon40K80K120K160K200KSE +/- 305.31, N = 3SE +/- 825.35, N = 3SE +/- 336.95, N = 3SE +/- 27.66, N = 3SE +/- 110.01, N = 340051.3171169.045955.741366.641179.7

Apache HTTP Server

Concurrent Requests: 1000

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon20K40K60K80K100KSE +/- 83.83, N = 3SE +/- 98.61, N = 3SE +/- 276.10, N = 3SE +/- 397.88, N = 3SE +/- 335.63, N = 372719.3319278.6846629.4571537.1179830.961. (CC) gcc options: -shared -fPIC -O2

TensorFlow Lite

Model: SqueezeNet

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon3K6K9K12K15KSE +/- 22.07, N = 3SE +/- 46.48, N = 3SE +/- 37.23, N = 3SE +/- 1.37, N = 3SE +/- 3.54, N = 33257.9412014.703969.353103.122983.93

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: Exhaustivec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon60120180240300SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3139.38277.77159.2072.3969.641. (CXX) g++ options: -O3 -flto -pthread

Rodinia

Test: OpenMP CFD Solver

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solverc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon918273645SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 310.4841.4517.0421.7920.451. (CXX) g++ options: -O2 -lOpenCL

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon40K80K120K160K200KSE +/- 82.61, N = 3SE +/- 63.75, N = 3SE +/- 3.30, N = 3SE +/- 74.60, N = 3SE +/- 47.94, N = 3178460.445328.653951.5136784.2140964.4-m64-m641. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon170340510680850SE +/- 0.18, N = 3SE +/- 0.58, N = 3SE +/- 0.13, N = 3SE +/- 0.62, N = 3SE +/- 0.33, N = 3256.84768.30406.94195.53204.991. (CXX) g++ options: -O3 -fPIC -lm

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 17.3Time To Compilec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon400800120016002000SE +/- 2.06, N = 3SE +/- 1.80, N = 3SE +/- 0.37, N = 3SE +/- 0.26, N = 3SE +/- 0.42, N = 3497.581765.91628.40664.35604.62

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin Proteinc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon3691215SE +/- 0.060, N = 3SE +/- 0.040, N = 3SE +/- 0.014, N = 3SE +/- 0.039, N = 12SE +/- 0.009, N = 311.2913.2457.9355.0676.2201. (CXX) g++ options: -O3 -lm

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Timesc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon7001400210028003500SE +/- 0.33, N = 3SE +/- 18.15, N = 3SE +/- 1.67, N = 3SE +/- 1.53, N = 3SE +/- 3.84, N = 31185345217411961997

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suitec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon200K400K600K800K1000KSE +/- 525.83, N = 3SE +/- 816.27, N = 3SE +/- 743.13, N = 3SE +/- 2681.41, N = 3SE +/- 983.65, N = 3666484241259449855480741828186

Timed ImageMagick Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compilec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon20406080100SE +/- 0.13, N = 3SE +/- 0.27, N = 3SE +/- 0.22, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 327.9093.6340.3332.6329.74

TensorFlow Lite

Model: NASNet Mobile

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet Mobilec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon7K14K21K28K35KSE +/- 121.56, N = 15SE +/- 49.84, N = 3SE +/- 203.15, N = 15SE +/- 23.44, N = 3SE +/- 166.62, N = 1411591.9030986.7014985.409266.8610900.60

Timed Apache Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compilec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon20406080100SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 326.9474.7434.2023.5322.53

DaCapo Benchmark

Java Test: Jython

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jythonc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon3K6K9K12K15KSE +/- 6.99, N = 4SE +/- 48.38, N = 4SE +/- 23.29, N = 4SE +/- 23.33, N = 4SE +/- 24.07, N = 4394012997562646164013

Timed LLVM Compilation

Build System: Ninja

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Ninjac7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon400800120016002000SE +/- 5.19, N = 3SE +/- 0.34, N = 3SE +/- 0.49, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3544.931784.60682.98760.34685.70

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.Dc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon2004006008001000SE +/- 0.39, N = 3SE +/- 0.24, N = 3SE +/- 0.23, N = 3SE +/- 0.06, N = 3SE +/- 19.93, N = 9934.72339.20558.88466.211103.221. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

Ngspice

Circuit: C2670

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon100200300400500SE +/- 0.86, N = 3SE +/- 3.48, N = 3SE +/- 0.91, N = 3SE +/- 1.17, N = 3SE +/- 1.80, N = 4198.22473.90263.72245.89147.891. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

DaCapo Benchmark

Java Test: Tradesoap

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradesoapc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon2K4K6K8K10KSE +/- 14.95, N = 4SE +/- 71.92, N = 4SE +/- 27.95, N = 4SE +/- 16.15, N = 4SE +/- 24.39, N = 4352411182450640523815

simdjson

Throughput Test: LargeRandom

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 1.0Throughput Test: LargeRandomc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon0.21380.42760.64140.85521.069SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.700.300.490.950.861. (CXX) g++ options: -O3

SecureMark

Benchmark: SecureMark-TLS

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon50K100K150K200K250KSE +/- 773.26, N = 3SE +/- 59.40, N = 3SE +/- 23.07, N = 3SE +/- 3310.19, N = 9SE +/- 864.34, N = 3183708743561203012132882305491. (CC) gcc options: -pedantic -O3

DaCapo Benchmark

Java Test: Tradebeans

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradebeansc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon2K4K6K8K10KSE +/- 26.73, N = 4SE +/- 44.35, N = 4SE +/- 40.13, N = 4SE +/- 23.53, N = 11SE +/- 19.24, N = 2032039045434431672928

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: 57c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon110M220M330M440M550MSE +/- 400097.21, N = 3SE +/- 8819.17, N = 3SE +/- 35118.85, N = 3SE +/- 489364.67, N = 3SE +/- 41633.32, N = 33836066671655133332628900005097466673731000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Build2

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To Compilec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon80160240320400SE +/- 0.64, N = 3SE +/- 1.89, N = 3SE +/- 0.70, N = 3SE +/- 0.87, N = 3SE +/- 0.69, N = 3115.02353.91142.28150.99136.80

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To Compilec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon4080120160200SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.31, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 369.48196.0388.9067.0864.34

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 21.06Test: Compression Ratingc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon20K40K60K80K100KSE +/- 159.36, N = 3SE +/- 91.00, N = 3SE +/- 44.77, N = 3SE +/- 16.02, N = 3SE +/- 174.34, N = 397824324987128562562666311. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Ngspice

Circuit: C7552

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon100200300400500SE +/- 1.94, N = 3SE +/- 1.19, N = 3SE +/- 2.40, N = 7SE +/- 0.66, N = 3SE +/- 0.33, N = 3191.29480.79255.21180.36161.081. (CC) gcc options: -O0 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

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 Compressionc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon306090120150SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.34, N = 348.21124.7166.1548.6841.81-ltiff-ltiff-ltiff-ltiff1. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16

Timed Gem5 Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To Compilec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon2004006008001000SE +/- 1.33, N = 3SE +/- 0.78, N = 3SE +/- 0.53, N = 3SE +/- 0.79, N = 3SE +/- 0.59, N = 3391.171155.62488.81515.20469.94

WebP Image Encode

Encode Settings: Quality 100, Lossless

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Losslessc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon1428425670SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 15SE +/- 0.03, N = 322.7761.8031.0826.7121.12-ltiff-ltiff-ltiff-ltiff1. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16

libavif avifenc

Encoder Speed: 6, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, Losslessc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon816243240SE +/- 0.01, N = 3SE +/- 0.31, N = 3SE +/- 0.17, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 311.9133.9916.5216.3917.531. (CXX) g++ options: -O3 -fPIC -lm

nginx

Concurrent Requests: 1000

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon80K160K240K320K400KSE +/- 1410.11, N = 3SE +/- 66.96, N = 3SE +/- 1677.89, N = 3SE +/- 781.49, N = 3SE +/- 2637.25, N = 3346814.75138205.11308213.13388657.76347345.491. (CC) gcc options: -lcrypt -lz -O3 -march=native

nginx

Concurrent Requests: 500

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon80K160K240K320K400KSE +/- 1017.52, N = 3SE +/- 141.15, N = 3SE +/- 3783.68, N = 3SE +/- 771.95, N = 3SE +/- 1620.39, N = 3346613.34139414.84310596.58389030.11351672.921. (CC) gcc options: -lcrypt -lz -O3 -march=native

nginx

Concurrent Requests: 200

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon80K160K240K320K400KSE +/- 3986.77, N = 3SE +/- 133.96, N = 3SE +/- 1347.28, N = 3SE +/- 1242.81, N = 3SE +/- 1582.66, N = 3352380.98141436.20308938.67390932.79356829.931. (CC) gcc options: -lcrypt -lz -O3 -march=native

Zstd Compression

Compression Level: 19 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression Speedc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon7001400210028003500SE +/- 7.75, N = 3SE +/- 4.74, N = 3SE +/- 12.10, N = 3SE +/- 3.25, N = 3SE +/- 24.18, N = 33050.31121.72051.62907.52582.0-llzma-llzma-llzma-llzma1. (CC) gcc options: -O3 -pthread -lz

nginx

Concurrent Requests: 100

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 100c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon80K160K240K320K400KSE +/- 2009.97, N = 3SE +/- 22.67, N = 3SE +/- 3992.58, N = 3SE +/- 436.72, N = 3SE +/- 1727.81, N = 3345710.87143155.48307349.36388010.76356302.841. (CC) gcc options: -lcrypt -lz -O3 -march=native

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess Performancec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon300K600K900K1200K1500KSE +/- 0.00, N = 5SE +/- 196.86, N = 5SE +/- 338.27, N = 5SE +/- 4180.17, N = 5SE +/- 1099.67, N = 51370094538500872313144263112725961. (CC) gcc options: -O3 -march=native

Zstd Compression

Compression Level: 19, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression Speedc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon7001400210028003500SE +/- 6.93, N = 3SE +/- 15.28, N = 3SE +/- 2.93, N = 3SE +/- 6.53, N = 3SE +/- 7.82, N = 33240.61213.92196.32826.02666.1-llzma-llzma-llzma-llzma1. (CC) gcc options: -O3 -pthread -lz

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Timec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon6M12M18M24M30MSE +/- 153578.64, N = 3SE +/- 123749.22, N = 3SE +/- 292329.99, N = 3SE +/- 149731.77, N = 3SE +/- 242448.39, N = 32760889110980430216792452385762322081961-m64 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2-m64 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi21. (CXX) g++ options: -lgcov -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -flto -flto=jobserver

Rodinia

Test: OpenMP LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon80160240320400SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.14, N = 3143.33360.30215.67224.33281.391. (CXX) g++ options: -O2 -lOpenCL

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Timec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon20406080100SE +/- 0.01, N = 3SE +/- 0.94, N = 15SE +/- 0.00, N = 3SE +/- 0.18, N = 3SE +/- 0.12, N = 337.8693.8051.0549.4452.78-march=native-march=native1. (CXX) g++ options: -pipe -O3 -ffast-math -R/usr/lib -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression Speedc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon918273645SE +/- 0.23, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.27, N = 3SE +/- 0.10, N = 339.516.031.025.933.8-llzma-llzma-llzma-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 Speedc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon918273645SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.21, N = 3SE +/- 0.40, N = 341.216.934.630.038.1-llzma-llzma-llzma-llzma1. (CC) gcc options: -O3 -pthread -lz

DaCapo Benchmark

Java Test: H2

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon14002800420056007000SE +/- 32.57, N = 5SE +/- 63.66, N = 4SE +/- 45.89, N = 4SE +/- 27.42, N = 4SE +/- 32.93, N = 429516740396430192921

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: Cryptoc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon5K10K15K20K25KSE +/- 32.01, N = 3SE +/- 6.29, N = 3SE +/- 92.83, N = 3SE +/- 3.93, N = 3SE +/- 5.89, N = 323181.8111985.3817924.1813556.0610210.341. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depthc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon7M14M21M28M35MSE +/- 104795.40, N = 3SE +/- 106812.26, N = 3SE +/- 359309.26, N = 3SE +/- 303648.79, N = 3SE +/- 325631.00, N = 33213412315331550265404822618768823746200

Google SynthMark

Test: VoiceMark_100

OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon150300450600750SE +/- 0.32, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 7.09, N = 3SE +/- 2.00, N = 3675.64331.07470.39663.07565.691. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast

OpenSSL

Algorithm: SHA256

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256c7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon3000M6000M9000M12000M15000MSE +/- 7739237.92, N = 3SE +/- 12563225.46, N = 3SE +/- 47755430.47, N = 3SE +/- 8616254.20, N = 3SE +/- 606684.16, N = 313722045973678568951710723184083116914033537096993937-m64-m641. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: Vector Mathc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon12K24K36K48K60KSE +/- 17.05, N = 3SE +/- 0.49, N = 3SE +/- 15.72, N = 3SE +/- 2.46, N = 3SE +/- 28.50, N = 355258.1727341.4737753.8953787.6140140.301. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.Cc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon8K16K24K32K40KSE +/- 1.96, N = 3SE +/- 0.15, N = 3SE +/- 0.90, N = 3SE +/- 18.06, N = 3SE +/- 160.86, N = 37730.412558.125133.8925140.5538136.771. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

LeelaChessZero

Backend: Eigen

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: Eigenc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon30060090012001500SE +/- 9.70, N = 3SE +/- 0.67, N = 3SE +/- 12.00, N = 3SE +/- 11.74, N = 9SE +/- 13.37, N = 31189128834100114661. (CXX) g++ options: -flto -pthread

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon30060090012001500SE +/- 6.44, N = 3SE +/- 0.88, N = 3SE +/- 10.22, N = 4SE +/- 12.82, N = 9SE +/- 12.41, N = 91103135864109113971. (CXX) g++ options: -flto -pthread

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Secondc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon90K180K270K360K450KSE +/- 3211.91, N = 3SE +/- 116.54, N = 3SE +/- 49.84, N = 3SE +/- 2163.00, N = 3SE +/- 80.93, N = 3405413.86203869.40315464.34345133.44285378.841. (CC) gcc options: -O2 -lrt" -lrt

N-Queens

Elapsed Time

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed Timec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon714212835SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 321.5432.2923.1416.3818.841. (CC) gcc options: -static -fopenmp -O3 -march=native

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 21.06Test: Decompression Ratingc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon16K32K48K64K80KSE +/- 12.88, N = 3SE +/- 31.21, N = 3SE +/- 239.68, N = 3SE +/- 142.56, N = 3SE +/- 35.00, N = 373054408915944557318456531. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solvec7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon20406080100SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 366.82110.3775.2272.3391.231. (CXX) g++ options: -fopenmp -O2 -march=native

Stress-NG

Test: IO_uring

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14Test: IO_uringc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon200K400K600K800K1000KSE +/- 614.16, N = 3SE +/- 3840.04, N = 3SE +/- 2395.13, N = 3SE +/- 713.03, N = 3SE +/- 405.56, N = 3843015.78918172.37770521.81768723.461037943.371. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread

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: Standardc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon8001600240032004000SE +/- 1.86, N = 3SE +/- 0.50, N = 3SE +/- 1.74, N = 3SE +/- 234.97, N = 12SE +/- 1.61, N = 328177572072369634501. (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: Standardc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon30060090012001500SE +/- 0.00, N = 3SE +/- 0.50, N = 3SE +/- 0.17, N = 3SE +/- 82.60, N = 12SE +/- 91.51, N = 12609165334119213741. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

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: Standardc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon306090120150SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 5.55, N = 12SE +/- 0.60, N = 3381028651391. (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: Standardc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon170340510680850SE +/- 0.17, N = 3SE +/- 0.88, N = 3SE +/- 0.17, N = 3SE +/- 0.58, N = 3SE +/- 50.92, N = 124071153224887731. (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: Standardc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon2K4K6K8K10KSE +/- 2.40, N = 3SE +/- 2.20, N = 3SE +/- 3.50, N = 3SE +/- 75.29, N = 12SE +/- 322.41, N = 12799023126948561779441. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

TensorFlow Lite

Model: Mobilenet Quant

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Quantc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon12002400360048006000SE +/- 17.76, N = 3SE +/- 20.90, N = 3SE +/- 14.44, N = 3SE +/- 53.31, N = 15SE +/- 80.05, N = 121502.955724.661980.243847.963967.39

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixelc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon20406080100SE +/- 0.02, N = 3SE +/- 2.00, N = 15SE +/- 0.03, N = 3SE +/- 0.77, N = 5SE +/- 0.04, N = 338.52104.7662.3269.3592.551. (CC) gcc options: -lm -lpthread -O3

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Streamclusterc7g.4xlarge Graviton3a1.4xlarge Gravitonc6g.4xlarge Graviton2c6a.4xlarge EPYCc6i.4xlarge Xeon1122334455SE +/- 0.33, N = 12SE +/- 0.02, N = 3SE +/- 0.26, N = 15SE +/- 0.05, N = 3SE +/- 0.07, N = 313.3047.4315.4818.3823.511. (CXX) g++ options: -O2 -lOpenCL

Phoronix Test Suite v10.8.5