Initial Google Tau VM AMD EPYC Milan benchmarking compared to Amazon EC2 M6g instances for a future article on Phoronix.com by Michael Larabel.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2110131-TJ-TAUVMEC2833 Google TauVM AMD EPYC vs. M6g Graviton2 Benchmarks - Phoronix Test Suite Google TauVM AMD EPYC vs. M6g Graviton2 Benchmarks Initial Google Tau VM AMD EPYC Milan benchmarking compared to Amazon EC2 M6g instances for a future article on Phoronix.com by Michael Larabel.
HTML result view exported from: https://openbenchmarking.org/result/2110131-TJ-TAUVMEC2833&sro&grw .
Google TauVM AMD EPYC vs. M6g Graviton2 Benchmarks Processor Motherboard Memory Disk Chipset Network OS Kernel Compiler File-System System Layer t2d-standard-8 t2d-standard-32 m6g.2xlarge m6g.8xlarge AMD EPYC 7B13 (8 Cores) Google Compute Engine t2d-standard-8 2 x 16384 MB RAM 11GB PersistentDisk + 107GB PersistentDisk Debian 10 4.19.0-17-cloud-amd64 (x86_64) GCC 8.3.0 ext4 KVM AMD EPYC 7B13 (32 Cores) Google Compute Engine t2d-standard-32 8 x 16384 MB RAM ARMv8 Neoverse-N1 (8 Cores) Amazon EC2 m6g.2xlarge (1.0 BIOS) Amazon Device 0200 32GB 107GB Amazon Elastic Block Store Amazon Elastic 4.19.0-14-arm64 (aarch64) ARMv8 Neoverse-N1 (32 Cores) Amazon EC2 m6g.8xlarge (1.0 BIOS) 124GB OpenBenchmarking.org Kernel Details - t2d-standard-8: scsi_mod.use_blk_mq=Y - Transparent Huge Pages: always - t2d-standard-32: scsi_mod.use_blk_mq=Y - Transparent Huge Pages: always - m6g.2xlarge: Transparent Huge Pages: always - m6g.8xlarge: Transparent Huge Pages: always Compiler Details - t2d-standard-8: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - t2d-standard-32: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - m6g.2xlarge: --build=aarch64-linux-gnu --disable-libphobos --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++ --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 -v - m6g.8xlarge: --build=aarch64-linux-gnu --disable-libphobos --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++ --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 -v Processor Details - t2d-standard-8, t2d-standard-32: CPU Microcode: 0x1000065 Java Details - t2d-standard-8, t2d-standard-32: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2deb10u1) Python Details - t2d-standard-8: Python 3.7.3 - t2d-standard-32: Python 3.7.3 - m6g.2xlarge: Python 2.7.16 + Python 3.7.3 - m6g.8xlarge: Python 2.7.16 + Python 3.7.3 Security Details - t2d-standard-8: 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 + srbds: Not affected + tsx_async_abort: Not affected - t2d-standard-32: 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 + srbds: Not affected + tsx_async_abort: Not affected - m6g.2xlarge: 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 + srbds: Not affected + tsx_async_abort: Not affected - m6g.8xlarge: 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 + srbds: Not affected + tsx_async_abort: Not affected
Google TauVM AMD EPYC vs. M6g Graviton2 Benchmarks stress-ng: Crypto stress-ng: Vector Math basis: UASTC Level 2 basis: UASTC Level 3 build-ffmpeg: Time To Compile build-gdb: Time To Compile compress-7zip: Compress Speed Test john-the-ripper: Blowfish john-the-ripper: MD5 graphics-magick: Swirl graphics-magick: Sharpen graphics-magick: Enhanced dav1d: Summer Nature 4K build2: Time To Compile build-nodejs: Time To Compile openssl: SHA256 pgbench: 100 - 250 - Read Only pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 500 - Read Only pgbench: 100 - 500 - Read Only - Average Latency t2d-standard-8 t2d-standard-32 m6g.2xlarge m6g.8xlarge 1650.02 20807.29 37.681 74.771 71.044 71.620 38830 10796 812530 340 89 149 136.96 139.925 554.723 6659560627 152289 1.642 143763 3.488 6218.86 78739.94 14.965 24.761 30.708 43.817 133228 42732 3210333 1248 346 573 326.48 57.698 165.283 25739835653 617961 0.405 605373 0.826 1257.57 17255.17 50.229 99.644 84.158 100.206 27799 5183 185258 269 74 103 78.21 183.076 761.417 5527759170 87873 2.845 82474 6.073 5030.58 69034.73 19.177 31.592 32.671 63.432 109417 20648 721783 1006 267 401 198.26 78.061 234.102 22078459950 406665 0.615 347544 1.439 OpenBenchmarking.org
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Crypto m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 1300 2600 3900 5200 6500 SE +/- 0.71, N = 3 SE +/- 2.69, N = 3 SE +/- 2.08, N = 3 SE +/- 5.68, N = 3 1257.57 5030.58 6218.86 1650.02 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc -latomic
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Vector Math m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 20K 40K 60K 80K 100K SE +/- 7.25, N = 3 SE +/- 28.36, N = 3 SE +/- 12.58, N = 3 SE +/- 58.31, N = 3 17255.17 69034.73 78739.94 20807.29 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc -latomic
Basis Universal Settings: UASTC Level 2 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 2 m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 11 22 33 44 55 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 50.23 19.18 14.97 37.68 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Basis Universal Settings: UASTC Level 3 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 3 m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.24, N = 3 99.64 31.59 24.76 74.77 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.4 Time To Compile m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.03, N = 3 SE +/- 0.24, N = 3 SE +/- 0.62, N = 15 84.16 32.67 30.71 71.04
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 10.2 Time To Compile m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.43, N = 3 100.21 63.43 43.82 71.62
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 30K 60K 90K 120K 150K SE +/- 77.93, N = 3 SE +/- 186.53, N = 3 SE +/- 1357.41, N = 3 SE +/- 581.53, N = 15 27799 109417 133228 38830 1. (CXX) g++ options: -pipe -lpthread
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 9K 18K 27K 36K 45K SE +/- 0.67, N = 3 SE +/- 2.19, N = 3 SE +/- 31.94, N = 3 SE +/- 5.36, N = 3 5183 20648 42732 10796 -m64 -m64 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 700K 1400K 2100K 2800K 3500K SE +/- 37.20, N = 3 SE +/- 670.59, N = 3 SE +/- 1201.85, N = 3 SE +/- 1883.13, N = 3 185258 721783 3210333 812530 -m64 -m64 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 300 600 900 1200 1500 SE +/- 2.33, N = 3 SE +/- 2.67, N = 3 SE +/- 1.53, N = 3 269 1006 1248 340 -lxml2 -lSM -lICE -lX11 -lxml2 -lSM -lICE -lX11 -lxml2 1. (CC) gcc options: -fopenmp -O2 -pthread -ljpeg -lz -lm -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 80 160 240 320 400 74 267 346 89 -lxml2 -lSM -lICE -lX11 -lxml2 -lSM -lICE -lX11 -lxml2 1. (CC) gcc options: -fopenmp -O2 -pthread -ljpeg -lz -lm -lpthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 120 240 360 480 600 SE +/- 0.33, N = 3 103 401 573 149 -lxml2 -lSM -lICE -lX11 -lxml2 -lSM -lICE -lX11 -lxml2 1. (CC) gcc options: -fopenmp -O2 -pthread -ljpeg -lz -lm -lpthread
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.9.2 Video Input: Summer Nature 4K m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 70 140 210 280 350 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 1.06, N = 3 SE +/- 0.15, N = 3 78.21 198.26 326.48 136.96 MIN: 72.84 / MAX: 84.32 MIN: 135.94 / MAX: 210.43 MIN: 254.49 / MAX: 365.12 MIN: 128.38 / MAX: 155.91 1. (CC) gcc options: -lm -pthread
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 40 80 120 160 200 SE +/- 1.20, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.54, N = 3 183.08 78.06 57.70 139.93
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 160 320 480 640 800 SE +/- 3.14, N = 3 SE +/- 0.29, N = 3 SE +/- 0.89, N = 3 SE +/- 1.86, N = 3 761.42 234.10 165.28 554.72
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.0 Algorithm: SHA256 m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 6000M 12000M 18000M 24000M 30000M SE +/- 13414421.31, N = 3 SE +/- 55812357.58, N = 3 SE +/- 4017105.90, N = 3 SE +/- 51724089.12, N = 3 5527759170 22078459950 25739835653 6659560627 -m64 -m64 1. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 130K 260K 390K 520K 650K SE +/- 593.35, N = 3 SE +/- 1401.95, N = 3 SE +/- 3588.30, N = 3 SE +/- 453.87, N = 3 87873 406665 617961 152289 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 0.6401 1.2802 1.9203 2.5604 3.2005 SE +/- 0.019, N = 3 SE +/- 0.002, N = 3 SE +/- 0.002, N = 3 SE +/- 0.005, N = 3 2.845 0.615 0.405 1.642 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Only m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 130K 260K 390K 520K 650K SE +/- 997.61, N = 12 SE +/- 2376.63, N = 3 SE +/- 3614.22, N = 3 SE +/- 2355.50, N = 11 82474 347544 605373 143763 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency m6g.2xlarge m6g.8xlarge t2d-standard-32 t2d-standard-8 2 4 6 8 10 SE +/- 0.075, N = 12 SE +/- 0.010, N = 3 SE +/- 0.005, N = 3 SE +/- 0.061, N = 11 6.073 1.439 0.826 3.488 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Phoronix Test Suite v10.8.4