Benchmarks by Michael Larabel.
5.10.1 Processor: 2 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads), Motherboard: Supermicro H11DSi-NT v2.00 (2.1 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Intel 10G X550T
OS: Ubuntu 20.10, Kernel: 5.10.1-051001-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, OpenGL: 4.5 Mesa 20.2.1 (LLVM 11.0.0 256 bits), Compiler: GCC 10.2.0, 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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,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,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10)Python Notes: Python 3.8.6Security 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 + srbds: Not affected + tsx_async_abort: Not affected
Linux 5.11 GIt OS: Ubuntu 20.10, Kernel: 5.10.0-051000daily20201219-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, OpenGL: 4.5 Mesa 20.2.1 (LLVM 11.0.0 256 bits), Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080
EPYC 7F72 2P Linux 5.11 OpenBenchmarking.org Phoronix Test Suite 2 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads) Supermicro H11DSi-NT v2.00 (2.1 BIOS) AMD Starship/Matisse 126GB 1000GB Western Digital WD_BLACK SN850 1TB llvmpipe VE228 2 x Intel 10G X550T Ubuntu 20.10 5.10.1-051001-generic (x86_64) 5.10.0-051000daily20201219-generic (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 modesetting 1.20.9 4.5 Mesa 20.2.1 (LLVM 11.0.0 256 bits) GCC 10.2.0 ext4 1920x1080 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernels Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution EPYC 7F72 2P Linux 5.11 Benchmarks System Logs - --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,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 - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034 - OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10) - Python 3.8.6 - 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 + srbds: Not affected + tsx_async_abort: Not affected
5.10.1 vs. Linux 5.11 GIt Comparison Phoronix Test Suite Baseline +9.5% +9.5% +19% +19% +28.5% +28.5% +38% +38% 38.1% 38.1% 21.6% 21.2% 20.5% 20.5% 18.6% 17.9% 17.8% 17.6% 16.7% 8.9% 8.9% 8.4% 8.3% 8.2% 7.6% 7.5% 7.4% 6.4% 6% 5.6% 5.6% 5.3% 5.2% 4.6% 4.5% 4.4% 3.4% 2.7% 2.6% 2.4% 2.4% 2.3% 2.2% 100 - 50 - Read Write - Average Latency 100 - 50 - Read Write 100 - 100 - Read Only - Average Latency CPU - alexnet 21.2% 100 - 100 - Read Only 100 - 100 - Read Write 100 - 100 - Read Write - Average Latency CPU - googlenet 19.2% 100 - 50 - Read Only - Average Latency 100 - 50 - Read Only 100 - 250 - Read Only - Average Latency 100 - 250 - Read Only NASNet Mobile CPU - resnet18 14.5% CPU - shufflenet-v2 12.9% CPU - squeezenet_ssd 12.7% 1 - 250 - Read Write 1 - 250 - Read Write - Average Latency CPU - mobilenet 1 - 100 - Read Write 1 - 100 - Read Write - Average Latency P.D.S 8.2% Rand Read - IO_uring - No - Yes - 4KB Rand Read - IO_uring - No - Yes - 4KB 1 - 50 - Read Only - Average Latency 512 7.1% CPU-v3-v3 - mobilenet-v3 7.1% CPU - regnety_400m 6.6% CPU - efficientnet-b0 Mobilenet Quant M.S.A - LSU RNA 1 - 50 - Read Only CPU - resnet50 5.4% Seq Write - IO_uring - No - Yes - 4KB Seq Write - IO_uring - No - Yes - 4KB Inception V4 Q.1.H.C 100 - 250 - Read Write - Average Latency 3.4% 100 - 250 - Read Write 3.4% Mobilenet Float Dhrystone 2 3.2% Rand Write - IO_uring - No - Yes - 4KB 3.2% Rand Write - IO_uring - No - Yes - 4KB 3.1% Rhodopsin Protein 3% CPU - mnasnet 1 - 250 - Read Only 128 Writes P.P.B PostgreSQL pgbench PostgreSQL pgbench PostgreSQL pgbench NCNN PostgreSQL pgbench PostgreSQL pgbench PostgreSQL pgbench NCNN PostgreSQL pgbench PostgreSQL pgbench PostgreSQL pgbench PostgreSQL pgbench TensorFlow Lite NCNN NCNN NCNN PostgreSQL pgbench PostgreSQL pgbench NCNN PostgreSQL pgbench PostgreSQL pgbench Timed HMMer Search Flexible IO Tester Flexible IO Tester PostgreSQL pgbench MariaDB NCNN NCNN NCNN TensorFlow Lite Timed MAFFT Alignment PostgreSQL pgbench NCNN Flexible IO Tester Flexible IO Tester TensorFlow Lite KeyDB WebP Image Encode PostgreSQL pgbench PostgreSQL pgbench TensorFlow Lite BYTE Unix Benchmark Flexible IO Tester Flexible IO Tester LAMMPS Molecular Dynamics Simulator NCNN PostgreSQL pgbench MariaDB Numpy Benchmark Apache Cassandra LibRaw 5.10.1 Linux 5.11 GIt
EPYC 7F72 2P Linux 5.11 pgbench: 100 - 50 - Read Write - Average Latency pgbench: 100 - 50 - Read Write pgbench: 100 - 100 - Read Only - Average Latency pgbench: 100 - 100 - Read Only pgbench: 100 - 100 - Read Write pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 50 - Read Only - Average Latency pgbench: 100 - 50 - Read Only pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 250 - Read Only pgbench: 1 - 250 - Read Write pgbench: 1 - 250 - Read Write - Average Latency pgbench: 1 - 100 - Read Write pgbench: 1 - 100 - Read Write - Average Latency hmmer: Pfam Database Search pgbench: 1 - 50 - Read Only - Average Latency mysqlslap: 512 tensorflow-lite: Mobilenet Quant mafft: Multiple Sequence Alignment - LSU RNA pgbench: 1 - 50 - Read Only tensorflow-lite: Inception V4 keydb: webp: Quality 100, Highest Compression pgbench: 100 - 250 - Read Write - Average Latency pgbench: 100 - 250 - Read Write tensorflow-lite: Mobilenet Float byte: Dhrystone 2 lammps: Rhodopsin Protein pgbench: 1 - 250 - Read Only mysqlslap: 128 numpy: libraw: Post-Processing Benchmark pgbench: 1 - 50 - Read Write - Average Latency pgbench: 1 - 50 - Read Write influxdb: 4 - 10000 - 2,5000,1 - 10000 pgbench: 1 - 250 - Read Only - Average Latency ffte: N=256, 3D Complex FFT Routine pgbench: 1 - 100 - Read Only - Average Latency build-llvm: Time To Compile tensorflow-lite: Inception ResNet V2 mysqlslap: 256 fio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directory fio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directory sqlite-speedtest: Timed Time - Size 1,000 hpcg: gpaw: Carbon Nanotube influxdb: 1024 - 10000 - 2,5000,1 - 10000 build-linux-kernel: Time To Compile pgbench: 1 - 100 - Read Only lammps: 20k Atoms namd: ATPase Simulation - 327,506 Atoms tensorflow-lite: SqueezeNet fio: Seq Write - IO_uring - No - Yes - 2MB - Default Test Directory webp: Quality 100, Lossless fio: Seq Read - IO_uring - No - Yes - 2MB - Default Test Directory gromacs: Water Benchmark fio: Seq Write - IO_uring - No - Yes - 2MB - Default Test Directory fio: Rand Write - IO_uring - No - Yes - 2MB - Default Test Directory fio: Rand Write - IO_uring - No - Yes - 2MB - Default Test Directory influxdb: 64 - 10000 - 2,5000,1 - 10000 fio: Rand Read - IO_uring - No - Yes - 2MB - Default Test Directory fio: Seq Read - IO_uring - No - Yes - 2MB - Default Test Directory fio: Rand Read - IO_uring - No - Yes - 2MB - Default Test Directory webp: Quality 100, Lossless, Highest Compression dolfyn: Computational Fluid Dynamics cassandra: Writes ncnn: CPU - regnety_400m ncnn: CPU - squeezenet_ssd ncnn: CPU - yolov4-tiny ncnn: CPU - resnet50 ncnn: CPU - alexnet ncnn: CPU - resnet18 ncnn: CPU - googlenet ncnn: CPU - blazeface ncnn: CPU - efficientnet-b0 ncnn: CPU - mnasnet ncnn: CPU - shufflenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU - mobilenet tensorflow-lite: NASNet Mobile fio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directory fio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directory fio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directory fio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directory fio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directory fio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directory 5.10.1 Linux 5.11 GIt 2.322 21541 0.141 711666 28715 3.487 0.083 606873 0.390 642667 1677 149.521 2076 48.235 167.422 0.058 346 44630.9 10.571 870106 865300 281673.09 8.882 8.250 30364 42127.1 38425404.3 24.477 1115680 413 316.84 32.19 20.741 2412 819301.6 0.231 186025.61593571 0.072 210.074 744333 346 1447 370467 70.362 30.9913 59.759 1352829.7 25.891 1403975 24.975 0.44723 61073.2 1608 19.022 1704 5.279 800 800 1607 1232963.7 848 849 1703 39.196 18.665 182904 150.24 39.14 43.57 45.26 9.67 20.79 39.25 11.98 38.22 29.69 22.48 26.65 31.31 48.31 159950 352167 1376 378833 1480 358600 1400 1.681 29754 0.116 862491 34603 2.894 0.070 715622 0.331 755951 1827 137.247 2248 44.561 181.192 0.054 323 42091.2 10.012 918476 827173 294322.97 8.504 8.533 29362 40759.1 37244826.2 23.755 1145021 423 324.35 32.90 20.368 2456 805008.9 0.227 183298.97574590 0.071 207.636 737620 343 1437 367933 70.020 30.8412 59.941 1349149.0 25.956 1407456 25.036 0.44620 61194.2 1605 18.987 1707 5.271 799 799 1605 1231469.8 849 850 1705 39.234 18.677 187097 160.20 44.11 43.86 47.72 11.72 23.81 46.78 12.02 35.91 28.90 25.38 28.53 31.09 44.56 137101 370800 1448 367200 1435 385667 1506 OpenBenchmarking.org
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency 5.10.1 Linux 5.11 GIt 0.5225 1.045 1.5675 2.09 2.6125 SE +/- 0.010, N = 3 SE +/- 0.005, N = 3 2.322 1.681 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write 5.10.1 Linux 5.11 GIt 6K 12K 18K 24K 30K SE +/- 89.03, N = 3 SE +/- 93.74, N = 3 21541 29754 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency 5.10.1 Linux 5.11 GIt 0.0317 0.0634 0.0951 0.1268 0.1585 SE +/- 0.002, N = 4 SE +/- 0.001, N = 3 0.141 0.116 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only 5.10.1 Linux 5.11 GIt 200K 400K 600K 800K 1000K SE +/- 8541.80, N = 4 SE +/- 2856.26, N = 3 711666 862491 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write 5.10.1 Linux 5.11 GIt 7K 14K 21K 28K 35K SE +/- 129.02, N = 3 SE +/- 27.44, N = 3 28715 34603 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency 5.10.1 Linux 5.11 GIt 0.7846 1.5692 2.3538 3.1384 3.923 SE +/- 0.016, N = 3 SE +/- 0.002, N = 3 3.487 2.894 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency 5.10.1 Linux 5.11 GIt 0.0187 0.0374 0.0561 0.0748 0.0935 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.083 0.070 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only 5.10.1 Linux 5.11 GIt 150K 300K 450K 600K 750K SE +/- 6943.34, N = 3 SE +/- 6188.41, N = 3 606873 715622 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency 5.10.1 Linux 5.11 GIt 0.0878 0.1756 0.2634 0.3512 0.439 SE +/- 0.004, N = 3 SE +/- 0.001, N = 3 0.390 0.331 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only 5.10.1 Linux 5.11 GIt 160K 320K 480K 640K 800K SE +/- 5575.53, N = 3 SE +/- 3509.72, N = 3 642667 755951 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Write 5.10.1 Linux 5.11 GIt 400 800 1200 1600 2000 SE +/- 12.76, N = 15 SE +/- 16.43, N = 15 1677 1827 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency 5.10.1 Linux 5.11 GIt 30 60 90 120 150 SE +/- 1.16, N = 15 SE +/- 1.27, N = 15 149.52 137.25 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write 5.10.1 Linux 5.11 GIt 500 1000 1500 2000 2500 SE +/- 8.57, N = 3 SE +/- 24.68, N = 4 2076 2248 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency 5.10.1 Linux 5.11 GIt 11 22 33 44 55 SE +/- 0.20, N = 3 SE +/- 0.47, N = 4 48.24 44.56 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency 5.10.1 Linux 5.11 GIt 0.0131 0.0262 0.0393 0.0524 0.0655 SE +/- 0.001, N = 15 SE +/- 0.001, N = 3 0.058 0.054 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -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: 512 5.10.1 Linux 5.11 GIt 80 160 240 320 400 SE +/- 1.13, N = 3 SE +/- 1.84, N = 3 346 323 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Only 5.10.1 Linux 5.11 GIt 200K 400K 600K 800K 1000K SE +/- 12003.05, N = 15 SE +/- 10147.31, N = 3 870106 918476 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
KeyDB A benchmark of KeyDB as a multi-threaded fork of the Redis server. The KeyDB benchmark is conducted using memtier-benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.0.16 5.10.1 Linux 5.11 GIt 60K 120K 180K 240K 300K SE +/- 3029.38, N = 15 SE +/- 3709.77, N = 15 281673.09 294322.97 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
WebP Image Encode This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression 5.10.1 Linux 5.11 GIt 2 4 6 8 10 SE +/- 0.004, N = 3 SE +/- 0.004, N = 3 8.882 8.504 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency 5.10.1 Linux 5.11 GIt 2 4 6 8 10 SE +/- 0.008, N = 3 SE +/- 0.071, N = 3 8.250 8.533 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write 5.10.1 Linux 5.11 GIt 7K 14K 21K 28K 35K SE +/- 24.08, N = 3 SE +/- 247.15, N = 3 30364 29362 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Only 5.10.1 Linux 5.11 GIt 200K 400K 600K 800K 1000K SE +/- 13323.28, N = 3 SE +/- 7697.94, N = 3 1115680 1145021 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -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: 128 5.10.1 Linux 5.11 GIt 90 180 270 360 450 SE +/- 1.65, N = 3 SE +/- 0.72, N = 3 413 423 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency 5.10.1 Linux 5.11 GIt 5 10 15 20 25 SE +/- 0.27, N = 3 SE +/- 0.19, N = 3 20.74 20.37 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Write 5.10.1 Linux 5.11 GIt 500 1000 1500 2000 2500 SE +/- 31.68, N = 3 SE +/- 22.83, N = 3 2412 2456 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
InfluxDB This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 5.10.1 Linux 5.11 GIt 200K 400K 600K 800K 1000K SE +/- 512.32, N = 3 SE +/- 590.36, N = 3 819301.6 805008.9
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency 5.10.1 Linux 5.11 GIt 0.052 0.104 0.156 0.208 0.26 SE +/- 0.005, N = 3 SE +/- 0.004, N = 3 0.231 0.227 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
FFTE FFTE is a package by Daisuke Takahashi to compute Discrete Fourier Transforms of 1-, 2- and 3- dimensional sequences of length (2^p)*(3^q)*(5^r). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MFLOPS, More Is Better FFTE 7.0 N=256, 3D Complex FFT Routine 5.10.1 Linux 5.11 GIt 40K 80K 120K 160K 200K SE +/- 1930.68, N = 15 SE +/- 2289.08, N = 3 186025.62 183298.98 1. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency 5.10.1 Linux 5.11 GIt 0.0162 0.0324 0.0486 0.0648 0.081 SE +/- 0.001, N = 3 SE +/- 0.001, N = 5 0.072 0.071 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -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: 256 5.10.1 Linux 5.11 GIt 80 160 240 320 400 SE +/- 1.34, N = 3 SE +/- 3.70, N = 3 346 343 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
Flexible IO Tester FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 300 600 900 1200 1500 SE +/- 21.82, N = 15 SE +/- 17.44, N = 15 1447 1437 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 80K 160K 240K 320K 400K SE +/- 5556.52, N = 15 SE +/- 4467.31, N = 15 370467 367933 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
GPAW GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GPAW 20.1 Input: Carbon Nanotube 5.10.1 Linux 5.11 GIt 13 26 39 52 65 SE +/- 0.25, N = 3 SE +/- 0.35, N = 3 59.76 59.94 1. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi
InfluxDB This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 5.10.1 Linux 5.11 GIt 300K 600K 900K 1200K 1500K SE +/- 1142.84, N = 3 SE +/- 6930.92, N = 3 1352829.7 1349149.0
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only 5.10.1 Linux 5.11 GIt 300K 600K 900K 1200K 1500K SE +/- 14464.08, N = 3 SE +/- 14001.39, N = 5 1403975 1407456 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
NAMD NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms 5.10.1 Linux 5.11 GIt 0.1006 0.2012 0.3018 0.4024 0.503 SE +/- 0.00013, N = 3 SE +/- 0.00045, N = 3 0.44723 0.44620
Flexible IO Tester FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 300 600 900 1200 1500 SE +/- 0.58, N = 3 1608 1605 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
WebP Image Encode This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless 5.10.1 Linux 5.11 GIt 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.23, N = 3 19.02 18.99 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Flexible IO Tester FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 400 800 1200 1600 2000 SE +/- 1.33, N = 3 1704 1707 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
Flexible IO Tester FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 200 400 600 800 1000 800 799 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 200 400 600 800 1000 800 799 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 300 600 900 1200 1500 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 1607 1605 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
InfluxDB This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 5.10.1 Linux 5.11 GIt 300K 600K 900K 1200K 1500K SE +/- 8165.96, N = 3 SE +/- 4664.91, N = 3 1232963.7 1231469.8
Flexible IO Tester FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 200 400 600 800 1000 SE +/- 0.88, N = 3 SE +/- 1.00, N = 3 848 849 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 200 400 600 800 1000 SE +/- 0.67, N = 3 849 850 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 400 800 1200 1600 2000 SE +/- 1.86, N = 3 SE +/- 1.67, N = 3 1703 1705 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
WebP Image Encode This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression 5.10.1 Linux 5.11 GIt 9 18 27 36 45 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 39.20 39.23 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Dolfyn Dolfyn is a Computational Fluid Dynamics (CFD) code of modern numerical simulation techniques. The Dolfyn test profile measures the execution time of the bundled computational fluid dynamics demos that are bundled with Dolfyn. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Dolfyn 0.527 Computational Fluid Dynamics 5.10.1 Linux 5.11 GIt 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 18.67 18.68
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m 5.10.1 Linux 5.11 GIt 40 80 120 160 200 SE +/- 2.81, N = 9 SE +/- 3.32, N = 12 150.24 160.20 MIN: 133.84 / MAX: 328.96 MIN: 135.86 / MAX: 4176.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd 5.10.1 Linux 5.11 GIt 10 20 30 40 50 SE +/- 1.01, N = 9 SE +/- 4.28, N = 12 39.14 44.11 MIN: 34.06 / MAX: 146.53 MIN: 34.69 / MAX: 3186.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny 5.10.1 Linux 5.11 GIt 10 20 30 40 50 SE +/- 2.39, N = 9 SE +/- 1.19, N = 12 43.57 43.86 MIN: 33.92 / MAX: 1781.14 MIN: 37.57 / MAX: 425.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 5.10.1 Linux 5.11 GIt 11 22 33 44 55 SE +/- 1.26, N = 9 SE +/- 2.53, N = 12 45.26 47.72 MIN: 37.04 / MAX: 328.01 MIN: 35.7 / MAX: 1101.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet 5.10.1 Linux 5.11 GIt 3 6 9 12 15 SE +/- 0.28, N = 9 SE +/- 2.04, N = 12 9.67 11.72 MIN: 7.95 / MAX: 119.19 MIN: 7.98 / MAX: 635.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 5.10.1 Linux 5.11 GIt 6 12 18 24 30 SE +/- 1.15, N = 9 SE +/- 1.57, N = 12 20.79 23.81 MIN: 16.54 / MAX: 111.61 MIN: 17.21 / MAX: 145.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet 5.10.1 Linux 5.11 GIt 11 22 33 44 55 SE +/- 4.70, N = 9 SE +/- 4.02, N = 12 39.25 46.78 MIN: 28.99 / MAX: 103.89 MIN: 30.29 / MAX: 586.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface 5.10.1 Linux 5.11 GIt 3 6 9 12 15 SE +/- 0.64, N = 9 SE +/- 0.43, N = 12 11.98 12.02 MIN: 7.86 / MAX: 70.46 MIN: 9.05 / MAX: 75.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 5.10.1 Linux 5.11 GIt 9 18 27 36 45 SE +/- 1.93, N = 9 SE +/- 1.40, N = 12 38.22 35.91 MIN: 23.89 / MAX: 112.32 MIN: 23.08 / MAX: 388.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mnasnet 5.10.1 Linux 5.11 GIt 7 14 21 28 35 SE +/- 1.79, N = 9 SE +/- 1.80, N = 12 29.69 28.90 MIN: 17.42 / MAX: 205.67 MIN: 16.82 / MAX: 1285.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: shufflenet-v2 5.10.1 Linux 5.11 GIt 6 12 18 24 30 SE +/- 1.00, N = 9 SE +/- 1.10, N = 12 22.48 25.38 MIN: 15.91 / MAX: 81.66 MIN: 16.9 / MAX: 1187.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 5.10.1 Linux 5.11 GIt 7 14 21 28 35 SE +/- 1.32, N = 9 SE +/- 1.21, N = 12 26.65 28.53 MIN: 17.37 / MAX: 367.94 MIN: 17.34 / MAX: 871.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 5.10.1 Linux 5.11 GIt 7 14 21 28 35 SE +/- 2.64, N = 9 SE +/- 2.03, N = 12 31.31 31.09 MIN: 16.55 / MAX: 2070.1 MIN: 17.07 / MAX: 1004.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet 5.10.1 Linux 5.11 GIt 11 22 33 44 55 SE +/- 4.01, N = 9 SE +/- 2.70, N = 12 48.31 44.56 MIN: 31.79 / MAX: 164.57 MIN: 32.81 / MAX: 140.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Flexible IO Tester FIO, the Flexible I/O Tester, is an advanced Linux disk benchmark supporting multiple I/O engines and a wealth of options. FIO was written by Jens Axboe for testing of the Linux I/O subsystem and schedulers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 80K 160K 240K 320K 400K SE +/- 8848.76, N = 12 SE +/- 5951.55, N = 15 352167 370800 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 300 600 900 1200 1500 SE +/- 34.58, N = 12 SE +/- 23.21, N = 15 1376 1448 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 80K 160K 240K 320K 400K SE +/- 3815.90, N = 6 SE +/- 6020.76, N = 15 378833 367200 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 300 600 900 1200 1500 SE +/- 15.00, N = 6 SE +/- 23.61, N = 15 1480 1435 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.25 Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 80K 160K 240K 320K 400K SE +/- 7578.04, N = 15 SE +/- 1763.83, N = 3 358600 385667 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.25 Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory 5.10.1 Linux 5.11 GIt 300 600 900 1200 1500 SE +/- 29.71, N = 15 SE +/- 6.69, N = 3 1400 1506 1. (CC) gcc options: -rdynamic -ll -lnuma -lrt -lz -lpthread -lm -ldl -laio -lcurl -lssl -lcrypto -std=gnu99 -ffast-math -include -O3 -fcommon -U_FORTIFY_SOURCE -march=native
5.10.1 Processor: 2 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads), Motherboard: Supermicro H11DSi-NT v2.00 (2.1 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Intel 10G X550T
OS: Ubuntu 20.10, Kernel: 5.10.1-051001-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, OpenGL: 4.5 Mesa 20.2.1 (LLVM 11.0.0 256 bits), Compiler: GCC 10.2.0, 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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,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,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10)Python Notes: Python 3.8.6Security 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 + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 19 December 2020 09:52 by user phoronix.
Linux 5.11 GIt Processor: 2 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads), Motherboard: Supermicro H11DSi-NT v2.00 (2.1 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 1000GB Western Digital WD_BLACK SN850 1TB, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Intel 10G X550T
OS: Ubuntu 20.10, Kernel: 5.10.0-051000daily20201219-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, OpenGL: 4.5 Mesa 20.2.1 (LLVM 11.0.0 256 bits), Compiler: GCC 10.2.0, 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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,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,rw / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034Java Notes: OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10)Python Notes: Python 3.8.6Security 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 + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 19 December 2020 18:19 by user phoronix.