Graviton2 versus AMD EPYC 7742 bare metal benchmarks by Michael Larabel.
Graviton2 64c Processor: ARMv8 Neoverse-N1 (64 Cores), Motherboard: Amazon EC2 m6g.metal v1.0, Memory: 252GB, Disk: 137GB Amazon Elastic Block Store, Network: Amazon Elastic
OS: Ubuntu 20.04, Kernel: 5.4.0-1009-aws (aarch64), Compiler: GCC 9.3.0, File-System: ext4
Compiler Notes: --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 -vDisk Notes: NONE / discard,relatime,rwJava Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: 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 Processor: AMD EPYC 7742 64-Core @ 2.25GHz (64 Cores)Motherboard: AMD DAYTONA_X (RDY1006G BIOS)Chipset: AMD Starship/MatisseMemory: 252GBDisk: 3841GB Micron_9300_MTFDHAL3T8TDPGraphics: llvmpipe 252GB, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 20.04, Kernel: 5.4.0-31-generic (x86_64), Desktop: GNOME Shell 3.36.1, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 3.3 Mesa 20.0.4 (LLVM 9.0.1 128 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Compiler Notes: --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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: 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 Changed Processor to AMD EPYC 7742 64-Core @ 2.25GHz (64 Cores / 128 Threads) .
Security Change: 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
Amazon Graviton2 vs. AMD EPYC 7742 Processor Motherboard Memory Disk Network Chipset Graphics Monitor OS Kernel Compiler File-System Desktop Display Server Display Driver OpenGL Screen Resolution Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t ARMv8 Neoverse-N1 (64 Cores) Amazon EC2 m6g.metal v1.0 252GB 137GB Amazon Elastic Block Store Amazon Elastic Ubuntu 20.04 5.4.0-1009-aws (aarch64) GCC 9.3.0 ext4 AMD EPYC 7742 64-Core @ 2.25GHz (64 Cores) AMD DAYTONA_X (RDY1006G BIOS) AMD Starship/Matisse 3841GB Micron_9300_MTFDHAL3T8TDP llvmpipe 252GB VE228 2 x Mellanox MT27710 5.4.0-31-generic (x86_64) GNOME Shell 3.36.1 X Server 1.20.8 modesetting 1.20.8 3.3 Mesa 20.0.4 (LLVM 9.0.1 128 bits) 1920x1080 AMD EPYC 7742 64-Core @ 2.25GHz (64 Cores / 128 Threads) OpenBenchmarking.org Compiler 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,rw Java Details - OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1) Python Details - Python 2.7.18rc1 + Python 3.8.2 Security 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
Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t Logarithmic Result Overview Phoronix Test Suite PostgreSQL pgbench ebizzy rav1e CloverLeaf OpenSSL FLAC Audio Encoding Timed Linux Kernel Compilation BlogBench John The Ripper Timed MrBayes Analysis TTSIOD 3D Renderer NAS Parallel Benchmarks VP9 libvpx Encoding LeelaChessZero MariaDB Swet Crypto++ Parboil Nettle Timed ImageMagick Compilation Stress-NG Coremark Cython benchmark libjpeg-turbo tjbench Optcarrot N-Queens 7-Zip Compression Timed PHP Compilation m-queens Basis Universal GIMP Java Gradle Build Minion C-Blosc asmFish Build2 Primesieve Smallpt Himeno Benchmark Timed LLVM Compilation Node.js Octane Benchmark Rodinia C-Ray Darktable dav1d Apache Cassandra Redis GEGL High Performance Conjugate Gradient GROMACS LAME MP3 Encoding Timed GCC Compilation Perl Benchmarks Node.js Express HTTP Load Test TSCP Renaissance Sockperf x264 Rust Mandelbrot GraphicsMagick RawTherapee Nebular Empirical Analysis Tool Go Benchmarks Timed MAFFT Alignment Zstd Compression XZ Compression
Amazon Graviton2 vs. AMD EPYC 7742 tscp: AI Chess Performance cryptopp: All Algorithms cryptopp: Keyed Algorithms cryptopp: Unkeyed Algorithms cryptopp: Integer + Elliptic Curve Public Key Algorithms nettle: aes256 nettle: chacha nettle: sha512 nettle: poly1305-aes go-benchmark: json go-benchmark: build go-benchmark: garbage compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 java-gradle-perf: Reactor stress-ng: MMAP stress-ng: Atomic stress-ng: Crypto stress-ng: Malloc stress-ng: CPU Cache stress-ng: CPU Stress stress-ng: Semaphores stress-ng: Vector Math stress-ng: Memory Copying stress-ng: Context Switching stress-ng: Glibc C String Functions stress-ng: Glibc Qsort Data Sorting stress-ng: System V Message Passing sockperf: Throughput renaissance: Scala Dotty renaissance: Rand Forest renaissance: Apache Spark ALS renaissance: Apache Spark Bayes renaissance: Savina Reactors.IO renaissance: Apache Spark PageRank renaissance: Akka Unbalanced Cobwebbed Tree renaissance: Genetic Algorithm Using Jenetics + Futures cython-bench: minion: Graceful minion: Solitaire minion: Quasigroup basis: ETC1S basis: UASTC Level 0 basis: UASTC Level 2 basis: UASTC Level 3 basis: UASTC Level 2 + RDO Post-Processing encode-flac: WAV To FLAC encode-mp3: WAV To MP3 darktable: Boat - CPU-only darktable: Masskrug - CPU-only darktable: Server Room - CPU-only tjbench: Decompression Throughput rawtherapee: Total Benchmark Time gegl: Crop gegl: Scale gegl: Cartoon gegl: Reflect gegl: Antialias gegl: Tile Glass gegl: Wavelet Blur gegl: Color Enhance gegl: Rotate 90 Degrees gimp: resize gimp: rotate gimp: auto-levels gimp: unsharp-mask mafft: Multiple Sequence Alignment mrbayes: Primate Phylogeny Analysis himeno: Poisson Pressure Solver lczero: Eigen cloverleaf: Lagrangian-Eulerian Hydrodynamics gromacs: Water Benchmark hpcg: parboil: OpenMP LBM parboil: OpenMP MRI Gridding npb: BT.C npb: EP.C npb: EP.D npb: FT.C npb: IS.D npb: LU.C npb: MG.C npb: SP.B rodinia: OpenMP LavaMD rodinia: OpenMP CFD Solver rodinia: OpenMP Streamcluster neat: coremark: CoreMark Size 666 - Iterations Per Second n-queens: Elapsed Time build-imagemagick: Time To Compile primesieve: 1e12 Prime Number Generation compress-7zip: Compress Speed Test john-the-ripper: Blowfish john-the-ripper: MD5 build-llvm: Time To Compile build-php: Time To Compile compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 rust-mandel: Time To Complete Serial/Parallel Mandelbrot asmfish: 1024 Hash Memory, 26 Depth m-queens: Time To Solve build-gcc: Time To Compile build-linux-kernel: Time To Compile swet: Average vpxenc: Speed 5 graphics-magick: Swirl graphics-magick: Rotate graphics-magick: Sharpen graphics-magick: Enhanced graphics-magick: Noise-Gaussian graphics-magick: HWB Color Space x264: H.264 Video Encoding dav1d: Chimera 1080p dav1d: Summer Nature 4K dav1d: Summer Nature 1080p c-ray: Total Time - 4K, 16 Rays Per Pixel ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping rav1e: 10 smallpt: Global Illumination Renderer; 128 Samples build2: Time To Compile blosc: blosclz blogbench: Write openssl: RSA 4096-bit Performance node-express-loadtest: redis: LPOP redis: SADD redis: LPUSH redis: GET redis: SET cassandra: Writes pgbench: Buffer Test - Normal Load - Read Only pgbench: Buffer Test - Normal Load - Read Write mysqlslap: 1 mysqlslap: 4 mysqlslap: 8 mysqlslap: 16 mysqlslap: 32 mysqlslap: 64 mysqlslap: 128 mysqlslap: 256 mysqlslap: 512 ebizzy: perl-benchmark: Pod2html node-octane: optcarrot: Optimized Benchmark Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 869010 636.516544 310.970923 344.032817 1270.011057 2782.98 449.931 379.99 949.75 1395314 31136250384 772447 21.909 491.393 865.74 231714.32 11364.24 712364028.71 13.37 7220.62 6276772.99 353814.74 10027.87 21475660.36 3519134.35 441.76 10623060.95 386634 9767.832 5806.623 6639.738 2676.428 33873.794 25931.722 26628.122 2374.701 81.590 71.134013 127.633151 165.655664 80.213 19.798 14.958 21.251 878.012 32.664 10.903 3.755 3.566 2.585 108.800089 61.395 12.106 9.597 158.724 45.266 54.334 43.055 85.547 89.185 67.124 13.246 22.087 26.153 31.940 2.246 257.320 2890.311784 2318 1.61 2.747 21.4310 20.609622 40.121080 24463.10 2236.16 2228.04 21669.91 844.58 18641.52 25892.62 9935.40 8.131 8.174 13.999 18.638 1237272.875267 3.67 28.667 6.328 179794 43335 1275000 300.792 64.152 9.407 43.031 105936115 18.743 1014.193 87.912 321026102 9.02 1513 496 717 701 561 1018 140.78 588.39 239.59 648.05 15.545 411.617 0.311 2.912 85.925 9658.2 18017 2628.3 6553 1755471.58 1340494.50 963398.88 1644303.92 1244328.34 266989 176350.406937 2280.175134 3086 1797 1635 1531 1288 965 651 548 550 345427 0.17490547 29340 68.67 1029878 1388.440315 547.790418 303.239346 4206.418142 4794.98 771.233 491.47 2103.68 1411199 28238211426 981570 21.763 341.376 538.85 424049.95 11923.07 1097638087.34 62.25 16311.72 5325535.94 316216.20 14243.42 15203224.41 5116590.96 565.80 22845900.42 454975 6576.560 5005.110 6202.161 3426.461 16569.162 21687.606 18076.818 3206.972 50.960 51.159415 77.439111 132.636762 53.544 7.846 13.207 19.287 726.973 9.871 9.111 3.195 2.864 1.749 172.621813 55.797 9.789 7.080 114.121 36.898 48.624 39.078 77.870 70.242 47.747 9.692 14.923 17.756 22.007 2.160 105.653 3827.226775 4102 0.29 2.501 17.7464 17.899186 93.320796 102257.04 4176.38 4318.05 31351.48 967.61 109034.36 42388.33 18585.84 6.676 7.676 9.151 17.075 1536926.324306 4.007 17.725 4.664 215715 75564 4411667 224.887 44.093 9.003 40.428 94537908 19.039 856.970 29.645 607550474 18.16 1582 556 609 864 582 1241 154.57 456.90 271.32 525.13 12.425 978.007 2.669 2.777 62.960 9296.5 39604 12843.0 7683 1720173.10 1559703.99 1150357.75 1721920.61 1405513.41 211622 611893.068111 42359.001766 11194 7943 7055 5474 2580 1186 534 444 445 2488944 0.14785560 38597 106.94 1022643 1388.273600 547.492068 303.112596 4195.347303 4795.26 771.141 491.16 2102.49 1273253 29667943541 895616 21.896 340.723 934.59 403796.58 12828.13 1248712298.23 46.80 19526.19 9258346.82 424666.61 12405.95 26364845.16 6797662.87 741.19 26968236.93 448694 6532.497 5011.822 6324.940 3529.771 19664.723 21483.402 21717.100 3143.389 51.379 51.443073 77.673532 132.610696 53.661 7.855 12.666 17.828 728.889 9.798 9.115 3.492 3.199 1.995 172.617150 58.835 9.782 7.002 114.389 37.037 48.748 39.045 78.115 70.360 47.926 9.661 14.705 17.638 22.218 2.136 106.972 3912.005207 2041 0.40 2.289 17.5552 22.022019 110.139532 92544.26 4129.25 4271.16 31228.98 971.93 102048.49 38200.26 22447.14 6.319 7.350 8.936 17.277 1988375.158409 2.602 17.074 4.721 269626 74914 4525000 226.620 42.946 9.067 39.004 131314356 12.871 850.033 26.766 605881667 18.18 1764 550 602 884 634 1174 156.16 599.05 331.42 677.59 11.920 881.381 2.324 2.150 64.256 6876.1 48646 12586.6 7771 2168678.10 1683866.41 1307306.84 2047459.14 1493004.17 220011 988939.198432 37417.906497 11293 7447 6593 5155 2481 1133 487 403 394 3075320 0.14684740 38332 107.11 OpenBenchmarking.org
TSCP This is a performance test of TSCP, Tom Kerrigan's Simple Chess Program, which has a built-in performance benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 200K 400K 600K 800K 1000K SE +/- 512.87, N = 5 SE +/- 2923.69, N = 5 SE +/- 720.27, N = 5 869010 1022643 1029878 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Keyed Algorithms Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 120 240 360 480 600 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 SE +/- 0.27, N = 3 310.97 547.49 547.79 1. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Unkeyed Algorithms EPYC 7742 64c 128t EPYC 7742 64c Graviton2 64c 70 140 210 280 350 SE +/- 0.14, N = 3 SE +/- 0.05, N = 3 SE +/- 0.12, N = 3 303.11 303.24 344.03 1. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Integer + Elliptic Curve Public Key Algorithms Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 900 1800 2700 3600 4500 SE +/- 0.65, N = 3 SE +/- 2.27, N = 3 SE +/- 2.97, N = 3 1270.01 4195.35 4206.42 1. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
Nettle GNU Nettle is a low-level cryptographic library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: aes256 Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 1000 2000 3000 4000 5000 SE +/- 0.65, N = 3 SE +/- 0.65, N = 3 SE +/- 0.74, N = 3 2782.98 4794.98 4795.26 MIN: 1656.91 / MAX: 5033.12 MIN: 3477.92 / MAX: 7440.81 MIN: 3477.09 / MAX: 7440.83 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: chacha Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 170 340 510 680 850 SE +/- 0.52, N = 3 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 449.93 771.14 771.23 MIN: 267.62 / MAX: 976 MIN: 393.01 / MAX: 2103.79 MIN: 393.13 / MAX: 2103.79 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: sha512 Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 110 220 330 440 550 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.18, N = 3 379.99 491.16 491.47 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.5.1 Test: poly1305-aes Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 500 1000 1500 2000 2500 SE +/- 1.97, N = 3 SE +/- 0.20, N = 3 SE +/- 0.04, N = 3 949.75 2102.49 2103.68 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
Go Benchmarks Benchmark for monitoring real time performance of the Go implementation for HTTP, JSON and garbage testing per iteration. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: json EPYC 7742 64c Graviton2 64c EPYC 7742 64c 128t 300K 600K 900K 1200K 1500K SE +/- 5729.12, N = 3 SE +/- 5211.56, N = 3 SE +/- 16777.18, N = 4 1411199 1395314 1273253
OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: build Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 7000M 14000M 21000M 28000M 35000M SE +/- 11752689.24, N = 3 SE +/- 53807658.06, N = 3 SE +/- 179022572.52, N = 3 31136250384 29667943541 28238211426
OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: garbage EPYC 7742 64c EPYC 7742 64c 128t Graviton2 64c 200K 400K 600K 800K 1000K SE +/- 11062.32, N = 3 SE +/- 12148.68, N = 3 SE +/- 10663.19, N = 4 981570 895616 772447
XZ Compression This test measures the time needed to compress a sample file (an Ubuntu file-system image) using XZ compression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better XZ Compression 5.2.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 SE +/- 0.05, N = 3 21.91 21.90 21.76 1. (CC) gcc options: -pthread -fvisibility=hidden -O2
Java Gradle Build This test runs Java software project builds using the Gradle build system. It is intended to give developers an idea as to the build performance for development activities and build servers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Java Gradle Build Gradle Build: Reactor Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 110 220 330 440 550 SE +/- 18.56, N = 9 SE +/- 2.96, N = 3 SE +/- 11.27, N = 6 491.39 341.38 340.72
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Atomic Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 90K 180K 270K 360K 450K SE +/- 756.68, N = 3 SE +/- 147.04, N = 3 SE +/- 146.09, N = 3 231714.32 403796.58 424049.95 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Crypto Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 3K 6K 9K 12K 15K SE +/- 25.31, N = 3 SE +/- 18.74, N = 3 SE +/- 29.74, N = 3 11364.24 11923.07 12828.13 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Malloc Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 300M 600M 900M 1200M 1500M SE +/- 603865.65, N = 3 SE +/- 1348531.50, N = 3 SE +/- 2770486.87, N = 3 712364028.71 1097638087.34 1248712298.23 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Cache Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 14 28 42 56 70 SE +/- 0.57, N = 12 SE +/- 1.15, N = 15 SE +/- 0.90, N = 15 13.37 46.80 62.25 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 4K 8K 12K 16K 20K SE +/- 0.34, N = 3 SE +/- 16.32, N = 3 SE +/- 17.20, N = 3 7220.62 16311.72 19526.19 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Semaphores EPYC 7742 64c Graviton2 64c EPYC 7742 64c 128t 2M 4M 6M 8M 10M SE +/- 6529.14, N = 3 SE +/- 9411.48, N = 3 SE +/- 3849.76, N = 3 5325535.94 6276772.99 9258346.82 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Vector Math EPYC 7742 64c Graviton2 64c EPYC 7742 64c 128t 90K 180K 270K 360K 450K SE +/- 25.04, N = 3 SE +/- 2.26, N = 3 SE +/- 22.32, N = 3 316216.20 353814.74 424666.61 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Memory Copying Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 3K 6K 9K 12K 15K SE +/- 1.90, N = 3 SE +/- 33.48, N = 3 SE +/- 386.12, N = 15 10027.87 12405.95 14243.42 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching EPYC 7742 64c Graviton2 64c EPYC 7742 64c 128t 6M 12M 18M 24M 30M SE +/- 205500.78, N = 3 SE +/- 104061.74, N = 3 SE +/- 714410.24, N = 15 15203224.41 21475660.36 26364845.16 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc C String Functions Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 1.5M 3M 4.5M 6M 7.5M SE +/- 3159.35, N = 3 SE +/- 34550.61, N = 3 SE +/- 108910.76, N = 3 3519134.35 5116590.96 6797662.87 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc Qsort Data Sorting Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 160 320 480 640 800 SE +/- 0.98, N = 3 SE +/- 8.12, N = 3 SE +/- 1.48, N = 3 441.76 565.80 741.19 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 6M 12M 18M 24M 30M SE +/- 98960.78, N = 3 SE +/- 174925.99, N = 3 SE +/- 373815.20, N = 15 10623060.95 22845900.42 26968236.93 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Random Forest Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 1200 2400 3600 4800 6000 SE +/- 38.49, N = 5 SE +/- 67.01, N = 5 SE +/- 29.52, N = 5 5806.62 5011.82 5005.11
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark ALS Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 1400 2800 4200 5600 7000 SE +/- 47.97, N = 5 SE +/- 68.32, N = 5 SE +/- 45.99, N = 16 6639.74 6324.94 6202.16
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark Bayes EPYC 7742 64c 128t EPYC 7742 64c Graviton2 64c 800 1600 2400 3200 4000 SE +/- 31.46, N = 25 SE +/- 31.10, N = 5 SE +/- 16.86, N = 5 3529.77 3426.46 2676.43
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Savina Reactors.IO Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 7K 14K 21K 28K 35K SE +/- 446.60, N = 5 SE +/- 297.23, N = 20 SE +/- 184.32, N = 25 33873.79 19664.72 16569.16
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark PageRank Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 6K 12K 18K 24K 30K SE +/- 278.60, N = 5 SE +/- 125.46, N = 5 SE +/- 241.74, N = 5 25931.72 21687.61 21483.40
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Akka Unbalanced Cobwebbed Tree Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 6K 12K 18K 24K 30K SE +/- 327.70, N = 25 SE +/- 223.45, N = 5 SE +/- 200.56, N = 5 26628.12 21717.10 18076.82
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Genetic Algorithm Using Jenetics + Futures EPYC 7742 64c EPYC 7742 64c 128t Graviton2 64c 700 1400 2100 2800 3500 SE +/- 17.98, N = 5 SE +/- 41.69, N = 25 SE +/- 10.21, N = 5 3206.97 3143.39 2374.70
Minion Minion is an open-source constraint solver that is designed to be very scalable. This test profile uses Minion's integrated benchmarking problems to solve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Graceful Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 16 32 48 64 80 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 71.13 51.44 51.16 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Solitaire Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 30 60 90 120 150 SE +/- 0.31, N = 3 SE +/- 0.34, N = 3 SE +/- 0.34, N = 3 127.63 77.67 77.44 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Quasigroup Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 40 80 120 160 200 SE +/- 0.84, N = 3 SE +/- 0.21, N = 3 SE +/- 0.29, N = 3 165.66 132.64 132.61 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
Basis Universal Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: ETC1S Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 20 40 60 80 100 SE +/- 0.43, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 80.21 53.66 53.54 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 0 Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 5 10 15 20 25 SE +/- 0.218, N = 7 SE +/- 0.006, N = 3 SE +/- 0.011, N = 3 19.798 7.855 7.846 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 14.96 13.21 12.67 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 3 Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 21.25 19.29 17.83 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 + RDO Post-Processing Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 200 400 600 800 1000 SE +/- 0.17, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 878.01 728.89 726.97 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
LAME MP3 Encoding LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 3 6 9 12 15 SE +/- 0.002, N = 3 SE +/- 0.007, N = 3 SE +/- 0.001, N = 3 10.903 9.115 9.111 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.0.1 Test: Boat - Acceleration: CPU-only Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 0.8449 1.6898 2.5347 3.3796 4.2245 SE +/- 0.004, N = 3 SE +/- 0.017, N = 3 SE +/- 0.016, N = 3 3.755 3.492 3.195
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.0.1 Test: Masskrug - Acceleration: CPU-only Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 0.8024 1.6048 2.4072 3.2096 4.012 SE +/- 0.015, N = 3 SE +/- 0.005, N = 3 SE +/- 0.001, N = 3 3.566 3.199 2.864
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.0.1 Test: Server Room - Acceleration: CPU-only Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 0.5816 1.1632 1.7448 2.3264 2.908 SE +/- 0.004, N = 3 SE +/- 0.004, N = 3 SE +/- 0.004, N = 3 2.585 1.995 1.749
GEGL GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Crop Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 3 6 9 12 15 SE +/- 0.021, N = 3 SE +/- 0.066, N = 3 SE +/- 0.018, N = 3 12.106 9.789 9.782
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Scale Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 3 6 9 12 15 SE +/- 0.149, N = 3 SE +/- 0.036, N = 3 SE +/- 0.068, N = 3 9.597 7.080 7.002
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Cartoon Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 40 80 120 160 200 SE +/- 0.18, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 158.72 114.39 114.12
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Reflect Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 45.27 37.04 36.90
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Antialias Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 12 24 36 48 60 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 54.33 48.75 48.62
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Tile Glass Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 10 20 30 40 50 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 43.06 39.08 39.05
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Wavelet Blur Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 85.55 78.12 77.87
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Color Enhance Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 89.19 70.36 70.24
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Rotate 90 Degrees Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 15 30 45 60 75 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 SE +/- 0.15, N = 3 67.12 47.93 47.75
GIMP GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: resize Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 3 6 9 12 15 SE +/- 0.082, N = 3 SE +/- 0.067, N = 3 SE +/- 0.030, N = 3 13.246 9.692 9.661
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: rotate Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 22.09 14.92 14.71
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: auto-levels Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 6 12 18 24 30 SE +/- 0.15, N = 3 SE +/- 0.16, N = 3 SE +/- 0.13, N = 3 26.15 17.76 17.64
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: unsharp-mask Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 7 14 21 28 35 SE +/- 0.23, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 31.94 22.22 22.01
Timed MrBayes Analysis This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 60 120 180 240 300 SE +/- 0.26, N = 3 SE +/- 0.84, N = 3 SE +/- 0.12, N = 3 257.32 106.97 105.65 -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 -mabm 1. (CC) gcc options: -O3 -std=c99 -pedantic -lm
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.25 Backend: Eigen EPYC 7742 64c 128t Graviton2 64c EPYC 7742 64c 900 1800 2700 3600 4500 SE +/- 25.11, N = 5 SE +/- 39.54, N = 3 SE +/- 38.67, N = 3 2041 2318 4102 1. (CXX) g++ options: -pthread
CloverLeaf CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm8192.in input file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf Lagrangian-Eulerian Hydrodynamics Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 0.3623 0.7246 1.0869 1.4492 1.8115 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.61 0.40 0.29 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing on the CPU with the water_GMX50 data. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020.1 Water Benchmark EPYC 7742 64c 128t EPYC 7742 64c Graviton2 64c 0.6181 1.2362 1.8543 2.4724 3.0905 SE +/- 0.026, N = 3 SE +/- 0.013, N = 3 SE +/- 0.006, N = 3 2.289 2.501 2.747 1. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
High Performance Conjugate Gradient HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 EPYC 7742 64c 128t EPYC 7742 64c Graviton2 64c 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 17.56 17.75 21.43 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
Parboil The Parboil Benchmarks from the IMPACT Research Group at University of Illinois are a set of throughput computing applications for looking at computing architecture and compilers. Parboil test-cases support OpenMP, OpenCL, and CUDA multi-processing environments. However, at this time the test profile is just making use of the OpenMP and OpenCL test workloads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP LBM EPYC 7742 64c 128t Graviton2 64c EPYC 7742 64c 5 10 15 20 25 SE +/- 0.29, N = 3 SE +/- 0.03, N = 3 SE +/- 0.28, N = 3 22.02 20.61 17.90 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP MRI Gridding EPYC 7742 64c 128t EPYC 7742 64c Graviton2 64c 20 40 60 80 100 SE +/- 0.32, N = 3 SE +/- 0.25, N = 3 SE +/- 0.24, N = 3 110.14 93.32 40.12 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 20K 40K 60K 80K 100K SE +/- 4.67, N = 3 SE +/- 1221.04, N = 5 SE +/- 1483.41, N = 4 24463.10 92544.26 102257.04 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 900 1800 2700 3600 4500 SE +/- 1.31, N = 3 SE +/- 21.28, N = 3 SE +/- 23.64, N = 3 2236.16 4129.25 4176.38 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 900 1800 2700 3600 4500 SE +/- 2.85, N = 3 SE +/- 8.82, N = 3 SE +/- 3.01, N = 3 2228.04 4271.16 4318.05 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 7K 14K 21K 28K 35K SE +/- 4.05, N = 3 SE +/- 108.47, N = 3 SE +/- 128.22, N = 3 21669.91 31228.98 31351.48 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 200 400 600 800 1000 SE +/- 3.48, N = 3 SE +/- 12.97, N = 3 SE +/- 14.61, N = 3 844.58 967.61 971.93 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 20K 40K 60K 80K 100K SE +/- 140.01, N = 3 SE +/- 1012.10, N = 15 SE +/- 113.11, N = 3 18641.52 102048.49 109034.36 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 9K 18K 27K 36K 45K SE +/- 2.41, N = 3 SE +/- 257.15, N = 3 SE +/- 114.33, N = 3 25892.62 38200.26 42388.33 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 5K 10K 15K 20K 25K SE +/- 4.95, N = 3 SE +/- 233.51, N = 3 SE +/- 217.12, N = 3 9935.40 18585.84 22447.14 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP LavaMD Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 2 4 6 8 10 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.006, N = 3 8.131 6.676 6.319 1. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP CFD Solver Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 2 4 6 8 10 SE +/- 0.052, N = 3 SE +/- 0.080, N = 3 SE +/- 0.092, N = 4 8.174 7.676 7.350 1. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP Streamcluster Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 4 8 12 16 20 SE +/- 0.146, N = 14 SE +/- 0.024, N = 3 SE +/- 0.010, N = 3 13.999 9.151 8.936 1. (CXX) g++ options: -O2 -lOpenCL
N-Queens This is a test of the OpenMP version of a test that solves the N-queens problem. The board problem size is 18. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time EPYC 7742 64c Graviton2 64c EPYC 7742 64c 128t 0.9016 1.8032 2.7048 3.6064 4.508 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 4.007 3.670 2.602 1. (CC) gcc options: -static -fopenmp -O3 -march=native
Primesieve Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 7.4 1e12 Prime Number Generation Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 2 4 6 8 10 SE +/- 0.003, N = 3 SE +/- 0.008, N = 3 SE +/- 0.003, N = 3 6.328 4.721 4.664 1. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 1000K 2000K 3000K 4000K 5000K SE +/- 3000.00, N = 3 SE +/- 2666.67, N = 3 SE +/- 4163.33, N = 3 1275000 4411667 4525000 -m64 -m64 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
Zstd Compression This test measures the time needed to compress a sample file (an Ubuntu file-system image) using Zstd compression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 3 6 9 12 15 SE +/- 0.002, N = 3 SE +/- 0.007, N = 3 SE +/- 0.153, N = 3 9.407 9.067 9.003 1. (CC) gcc options: -O3 -pthread -lz -llzma
Rust Mandelbrot This test profile is of the combined time for the serial and parallel Mandelbrot sets written in Rustlang via willi-kappler/mandel-rust. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rust Mandelbrot Time To Complete Serial/Parallel Mandelbrot Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 43.03 40.43 39.00 -m64 -m64 1. (CC) gcc options: -pie -nodefaultlibs -lutil -ldl -lrt -lpthread -lgcc_s -lc -lm
Swet Swet is a synthetic CPU/RAM benchmark, includes multi-processor test cases. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Operations Per Second, More Is Better Swet 1.5.16 Average Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 130M 260M 390M 520M 650M SE +/- 310568.82, N = 3 SE +/- 1731105.92, N = 3 SE +/- 4322060.32, N = 3 321026102 605881667 607550474 1. (CC) gcc options: -lm -lpthread -lcurses -lrt
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9/WebM format using a sample 1080p video. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.2 Speed: Speed 5 Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 9.02 18.16 18.18 -march=armv8-a -m64 -m64 1. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 400 800 1200 1600 2000 SE +/- 3.61, N = 3 SE +/- 1.20, N = 3 SE +/- 5.57, N = 3 1513 1582 1764 -lfreetype 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 120 240 360 480 600 SE +/- 6.23, N = 3 SE +/- 2.67, N = 3 SE +/- 4.41, N = 3 496 550 556 -lfreetype 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen EPYC 7742 64c 128t EPYC 7742 64c Graviton2 64c 150 300 450 600 750 SE +/- 0.33, N = 3 602 609 717 -lfreetype 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 200 400 600 800 1000 SE +/- 0.58, N = 3 701 864 884 -lfreetype 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 140 280 420 560 700 SE +/- 0.67, N = 3 SE +/- 0.88, N = 3 SE +/- 2.40, N = 3 561 582 634 -lfreetype 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 300 600 900 1200 1500 SE +/- 1.76, N = 3 SE +/- 3.51, N = 3 SE +/- 1.76, N = 3 1018 1174 1241 -lfreetype 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
x264 This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x264 2019-12-17 H.264 Video Encoding Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 30 60 90 120 150 SE +/- 0.35, N = 3 SE +/- 2.58, N = 3 SE +/- 0.23, N = 3 140.78 154.57 156.16 -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-vectorize 1. (CC) gcc options: -ldl -lm -lpthread
dav1d Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better dav1d 0.6.0 Video Input: Chimera 1080p EPYC 7742 64c Graviton2 64c EPYC 7742 64c 128t 130 260 390 520 650 SE +/- 1.39, N = 3 SE +/- 0.55, N = 3 SE +/- 0.89, N = 3 456.90 588.39 599.05 MIN: 319.39 / MAX: 559.29 MIN: 427.39 / MAX: 777.07 MIN: 345.23 / MAX: 743.97 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.6.0 Video Input: Summer Nature 4K Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 70 140 210 280 350 SE +/- 0.72, N = 3 SE +/- 0.32, N = 3 SE +/- 1.58, N = 3 239.59 271.32 331.42 MIN: 138.3 / MAX: 258.62 MIN: 149.06 / MAX: 289.04 MIN: 118.03 / MAX: 366.24 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.6.0 Video Input: Summer Nature 1080p EPYC 7742 64c Graviton2 64c EPYC 7742 64c 128t 150 300 450 600 750 SE +/- 2.15, N = 3 SE +/- 1.42, N = 3 SE +/- 1.47, N = 3 525.13 648.05 677.59 MIN: 291.81 / MAX: 581.55 MIN: 367.46 / MAX: 714.91 MIN: 218.5 / MAX: 776.16 1. (CC) gcc options: -pthread
C-Ray This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 15.55 12.43 11.92 1. (CC) gcc options: -lm -lpthread -O3
TTSIOD 3D Renderer A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 200 400 600 800 1000 SE +/- 12.93, N = 12 SE +/- 6.32, N = 3 SE +/- 12.37, N = 5 411.62 881.38 978.01 -msse -mrecip -mfpmath=sse -msse2 -mssse3 -msse -mrecip -mfpmath=sse -msse2 -mssse3 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -lSDL -fopenmp -fwhole-program -lstdc++
Smallpt Smallpt is a C++ global illumination renderer written in less than 100 lines of code. Global illumination is done via unbiased Monte Carlo path tracing and there is multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 128 Samples Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 0.6552 1.3104 1.9656 2.6208 3.276 SE +/- 0.004, N = 3 SE +/- 0.005, N = 3 SE +/- 0.004, N = 3 2.912 2.777 2.150 1. (CXX) g++ options: -fopenmp -O3
Build2 This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.12 Time To Compile Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 85.93 64.26 62.96
BlogBench BlogBench is designed to replicate the load of a real-world busy file server by stressing the file-system with multiple threads of random reads, writes, and rewrites. The behavior is mimicked of that of a blog by creating blogs with content and pictures, modifying blog posts, adding comments to these blogs, and then reading the content of the blogs. All of these blogs generated are created locally with fake content and pictures. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Write Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 10K 20K 30K 40K 50K SE +/- 1359.02, N = 3 SE +/- 561.49, N = 4 SE +/- 692.73, N = 3 18017 39604 48646 1. (CC) gcc options: -O2 -pthread
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 3K 6K 9K 12K 15K SE +/- 0.56, N = 3 SE +/- 0.69, N = 3 SE +/- 12.96, N = 3 2628.3 12586.6 12843.0 -m64 -m64 1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SADD Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 400K 800K 1200K 1600K 2000K SE +/- 20080.65, N = 3 SE +/- 37698.60, N = 15 SE +/- 30991.56, N = 15 1340494.50 1559703.99 1683866.41 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: LPUSH Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 300K 600K 900K 1200K 1500K SE +/- 1934.63, N = 3 SE +/- 5408.33, N = 3 SE +/- 21281.45, N = 3 963398.88 1150357.75 1307306.84 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: GET Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 400K 800K 1200K 1600K 2000K SE +/- 19731.78, N = 3 SE +/- 49844.86, N = 12 SE +/- 46774.40, N = 12 1644303.92 1721920.61 2047459.14 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SET Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 300K 600K 900K 1200K 1500K SE +/- 4424.59, N = 3 SE +/- 23286.40, N = 15 SE +/- 18650.88, N = 3 1244328.34 1405513.41 1493004.17 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 200K 400K 600K 800K 1000K SE +/- 4653.04, N = 6 SE +/- 4724.61, N = 3 SE +/- 4038.72, N = 3 176350.41 611893.07 988939.20 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 9K 18K 27K 36K 45K SE +/- 45.86, N = 9 SE +/- 110.45, N = 3 SE +/- 37.91, N = 3 2280.18 37417.91 42359.00 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
MariaDB This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 1 Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 2K 4K 6K 8K 10K SE +/- 9.56, N = 3 SE +/- 41.61, N = 3 SE +/- 137.28, N = 15 3086 11194 11293 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 4 Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 2K 4K 6K 8K 10K SE +/- 17.47, N = 3 SE +/- 75.43, N = 8 SE +/- 6.35, N = 10 1797 7447 7943 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 8 Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 1500 3000 4500 6000 7500 SE +/- 6.23, N = 3 SE +/- 14.52, N = 3 SE +/- 12.49, N = 4 1635 6593 7055 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 16 Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 1200 2400 3600 4800 6000 SE +/- 9.85, N = 3 SE +/- 26.71, N = 3 SE +/- 10.01, N = 3 1531 5155 5474 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 32 Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 600 1200 1800 2400 3000 SE +/- 7.72, N = 3 SE +/- 6.17, N = 3 SE +/- 4.43, N = 3 1288 2481 2580 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 64 Graviton2 64c EPYC 7742 64c 128t EPYC 7742 64c 300 600 900 1200 1500 SE +/- 6.47, N = 3 SE +/- 1.55, N = 3 SE +/- 0.35, N = 4 965 1133 1186 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 128 EPYC 7742 64c 128t EPYC 7742 64c Graviton2 64c 140 280 420 560 700 SE +/- 0.29, N = 3 SE +/- 0.66, N = 3 SE +/- 3.08, N = 3 487 534 651 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 256 EPYC 7742 64c 128t EPYC 7742 64c Graviton2 64c 120 240 360 480 600 SE +/- 0.64, N = 3 SE +/- 0.24, N = 3 SE +/- 3.38, N = 3 403 444 548 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 512 EPYC 7742 64c 128t EPYC 7742 64c Graviton2 64c 120 240 360 480 600 SE +/- 1.72, N = 3 SE +/- 0.61, N = 3 SE +/- 2.06, N = 3 394 445 550 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
ebizzy This is a test of ebizzy, a program to generate workloads resembling web server workloads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 700K 1400K 2100K 2800K 3500K SE +/- 8227.80, N = 15 SE +/- 8402.66, N = 3 SE +/- 39888.00, N = 3 345427 2488944 3075320 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
Optcarrot Optcarrot is an NES emulator benchmark for the Ruby language. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better Optcarrot Optimized Benchmark Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 20 40 60 80 100 SE +/- 0.35, N = 4 SE +/- 0.34, N = 4 SE +/- 0.45, N = 4 68.67 106.94 107.11 1. 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]
Geometric Mean Of All Test Results OpenBenchmarking.org Geometric Mean, More Is Better Geometric Mean Of All Test Results Result Composite - Amazon Graviton2 vs. AMD EPYC 7742 Graviton2 64c EPYC 7742 64c EPYC 7742 64c 128t 50 100 150 200 250 143.29 210.15 216.00
Hide Result
Number Of First Place Finishes EPYC 7742 64c 128t 65 [45.5%] EPYC 7742 64c 65 [45.5%] Graviton2 64c 13 [9.1%] Number Of First Place Finishes Wins - 143 Tests OpenBenchmarking.org
Hide Result
Number Of Last Place Finishes Graviton2 64c 117 [81.8%] EPYC 7742 64c 14 [9.8%] EPYC 7742 64c 128t 12 [8.4%] Number Of Last Place Finishes Losses - 143 Tests OpenBenchmarking.org
Hide Result
Graviton2 64c Processor: ARMv8 Neoverse-N1 (64 Cores), Motherboard: Amazon EC2 m6g.metal v1.0, Memory: 252GB, Disk: 137GB Amazon Elastic Block Store, Network: Amazon Elastic
OS: Ubuntu 20.04, Kernel: 5.4.0-1009-aws (aarch64), Compiler: GCC 9.3.0, File-System: ext4
Compiler Notes: --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 -vDisk Notes: NONE / discard,relatime,rwJava Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: 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
Testing initiated at 16 May 2020 01:29 by user ubuntu.
EPYC 7742 64c Processor: AMD EPYC 7742 64-Core @ 2.25GHz (64 Cores), Motherboard: AMD DAYTONA_X (RDY1006G BIOS), Chipset: AMD Starship/Matisse, Memory: 252GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: llvmpipe 252GB, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 20.04, Kernel: 5.4.0-31-generic (x86_64), Desktop: GNOME Shell 3.36.1, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 3.3 Mesa 20.0.4 (LLVM 9.0.1 128 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Compiler Notes: --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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: 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
Testing initiated at 21 May 2020 07:33 by user phoronix.
EPYC 7742 64c 128t Processor: AMD EPYC 7742 64-Core @ 2.25GHz (64 Cores / 128 Threads), Motherboard: AMD DAYTONA_X (RDY1006G BIOS), Chipset: AMD Starship/Matisse, Memory: 252GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: llvmpipe 252GB, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 20.04, Kernel: 5.4.0-31-generic (x86_64), Desktop: GNOME Shell 3.36.1, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 3.3 Mesa 20.0.4 (LLVM 9.0.1 128 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Compiler Notes: --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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: 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
Testing initiated at 20 May 2020 08:37 by user phoronix.