benchmarks for a future article.
RESET Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)Python Notes: Python 3.9.16Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
RESET2 Processor: AMD EPYC 9124 16-Core @ 3.00GHz (16 Cores / 32 Threads), Motherboard: Supermicro H13SSW (1.1 BIOS), Memory: 12 x 64 GB DDR5-4800MT/s HMCG94MEBRA123N, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb
OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1024x768
RESET3 Processor: AMD EPYC 9334 32-Core @ 2.70GHz (32 Cores / 64 Threads) , Motherboard: Supermicro H13SSW (1.1 BIOS), Memory: 12 x 64 GB DDR5-4800MT/s HMCG94MEBRA123N, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb, Monitor: DELL E207WFP
OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1680x1050
AOM AV1 This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.
Encoder Mode: Speed 11 Realtime - Input: Bosphorus 1080p
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 11 Realtime - Input: Bosphorus 4K
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
BRL-CAD BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.36 VGR Performance Metric RESET3 RESET 120K 240K 360K 480K 600K 569090 295626 1. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6
Dragonflydb Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:10 RESET3 RESET2 RESET 4M 8M 12M 16M 20M 16927170.48 8584414.13 8302009.42 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:10 RESET3 RESET RESET2 4M 8M 12M 16M 20M 19505101.23 10162330.86 9527420.80 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:10 RESET3 RESET RESET2 5M 10M 15M 20M 25M 22835296.84 12469755.60 11249348.91 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Clients Per Thread: 60 - Set To Get Ratio: 1:10
RESET3: The test run did not produce a result. E: Connection error: Broken pipe
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 10 - Set To Get Ratio: 1:100 RESET3 RESET2 RESET 4M 8M 12M 16M 20M 17116522.17 8951592.94 8637294.18 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 20 - Set To Get Ratio: 1:100 RESET3 RESET RESET2 5M 10M 15M 20M 25M 21025616.30 9932666.12 9367141.20 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 50 - Set To Get Ratio: 1:100 RESET3 RESET2 RESET 5M 10M 15M 20M 25M 23607335.01 12138788.95 11746361.87 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Clients Per Thread: 60 - Set To Get Ratio: 1:100
RESET3: The test run did not produce a result. E: Connection error: Connection reset by peer
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:10 RESET RESET2 3M 6M 9M 12M 15M 12065388.34 10983543.66 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Clients Per Thread: 60 - Set To Get Ratio: 1:10
RESET3: The test run did not produce a result. E: Connection error: Connection reset by peer
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 1.6.2 Clients Per Thread: 60 - Set To Get Ratio: 1:100 RESET2 RESET 3M 6M 9M 12M 15M 13659195.83 11419293.83 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Clients Per Thread: 60 - Set To Get Ratio: 1:100
RESET3: The test run did not produce a result. E: Connection error: Connection reset by peer
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer - Model: Crown RESET3 RESET RESET2 10 20 30 40 50 43.40 21.58 21.43 MIN: 42.87 / MAX: 44.59 MIN: 21.45 / MAX: 21.93 MIN: 21.27 / MAX: 21.76
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer ISPC - Model: Crown RESET3 RESET RESET2 10 20 30 40 50 45.68 22.68 22.67 MIN: 45.1 / MAX: 46.91 MIN: 22.49 / MAX: 22.98 MIN: 22.51 / MAX: 23.04
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer - Model: Asian Dragon RESET3 RESET2 RESET 11 22 33 44 55 48.15 24.82 24.81 MIN: 47.9 / MAX: 48.87 MIN: 24.74 / MAX: 24.99 MIN: 24.73 / MAX: 25.07
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer - Model: Asian Dragon Obj RESET3 RESET RESET2 10 20 30 40 50 43.51 22.25 22.19 MIN: 43.25 / MAX: 44.05 MIN: 22.17 / MAX: 22.47 MIN: 22.12 / MAX: 22.35
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer ISPC - Model: Asian Dragon RESET3 RESET2 RESET 12 24 36 48 60 54.50 28.42 28.29 MIN: 54.24 / MAX: 54.99 MIN: 28.3 / MAX: 28.73 MIN: 28.19 / MAX: 28.56
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj RESET3 RESET2 RESET 11 22 33 44 55 46.46 23.92 23.83 MIN: 46.18 / MAX: 47.04 MIN: 23.83 / MAX: 24.22 MIN: 23.74 / MAX: 24.04
Kripke Kripke is a simple, scalable, 3D Sn deterministic particle transport code. Its primary purpose is to research how data layout, programming paradigms and architectures effect the implementation and performance of Sn transport. Kripke is developed by LLNL. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.6 RESET3 RESET 80M 160M 240M 320M 400M 351062800 237641100 1. (CXX) g++ options: -O3 -fopenmp -ldl
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 RESET3 RESET RESET2 8M 16M 24M 32M 40M 37083000 35186000 35179000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 57 RESET3 RESET RESET2 12M 24M 36M 48M 60M 55677000 52897000 48803000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 32 RESET3 RESET2 RESET 16M 32M 48M 64M 80M 72570000 68905000 68854000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 57 RESET3 RESET RESET2 20M 40M 60M 80M 100M 108010000 105200000 104020000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 32 RESET3 RESET RESET2 30M 60M 90M 120M 150M 145900000 138520000 136520000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 57 RESET3 RESET RESET2 40M 80M 120M 160M 200M 197890000 190540000 188640000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 32 RESET3 RESET2 RESET 60M 120M 180M 240M 300M 292720000 277780000 277560000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 57 RESET3 RESET2 RESET 80M 160M 240M 320M 400M 380280000 343950000 337660000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 RESET3 RESET RESET2 3M 6M 9M 12M 15M 13359000 12685000 12264000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 32 RESET3 RESET RESET2 120M 240M 360M 480M 600M 582930000 545570000 544800000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 57 RESET3 RESET RESET2 150M 300M 450M 600M 750M 716650000 695920000 686540000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 2 - Buffer Length: 256 - Filter Length: 512 RESET3 RESET RESET2 6M 12M 18M 24M 30M 26065000 25206000 25050000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 32 RESET3 RESET RESET2 300M 600M 900M 1200M 1500M 1169700000 1047500000 1046500000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 57 RESET3 RESET RESET2 300M 600M 900M 1200M 1500M 1397500000 1031700000 1013800000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 4 - Buffer Length: 256 - Filter Length: 512 RESET3 RESET2 RESET 11M 22M 33M 44M 55M 52587000 49614000 48886000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 32 RESET3 RESET2 RESET 400M 800M 1200M 1600M 2000M 2053800000 1056700000 1056400000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 57 RESET3 RESET RESET2 400M 800M 1200M 1600M 2000M 1911400000 1100900000 1098600000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 8 - Buffer Length: 256 - Filter Length: 512 RESET3 RESET2 RESET 20M 40M 60M 80M 100M 105480000 99404000 97011000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 16 - Buffer Length: 256 - Filter Length: 512 RESET3 RESET RESET2 40M 80M 120M 160M 200M 208610000 196300000 196070000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 32 - Buffer Length: 256 - Filter Length: 512 RESET3 RESET2 RESET 80M 160M 240M 320M 400M 393800000 274570000 273720000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 512 RESET3 RESET RESET2 110M 220M 330M 440M 550M 510160000 282490000 282060000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 RESET RESET3 2 4 6 8 10 7.36 7.72 MIN: 6.92 / MAX: 8.19 MIN: 7.29 / MAX: 8.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 RESET RESET3 2 4 6 8 10 7.55 8.08 MIN: 7.41 / MAX: 11.7 MIN: 7.94 / MAX: 8.54 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: shufflenet-v2 RESET RESET3 3 6 9 12 15 8.67 9.38 MIN: 8.53 / MAX: 10.83 MIN: 9.25 / MAX: 12.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mnasnet RESET3 RESET 2 4 6 8 10 7.11 7.47 MIN: 7.04 / MAX: 7.35 MIN: 6.42 / MAX: 190.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: efficientnet-b0 RESET RESET3 3 6 9 12 15 9.35 10.56 MIN: 9.25 / MAX: 10.78 MIN: 9.78 / MAX: 160.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: blazeface RESET RESET3 0.8685 1.737 2.6055 3.474 4.3425 3.35 3.86 MIN: 3.27 / MAX: 3.52 MIN: 3.79 / MAX: 4.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: googlenet RESET RESET3 5 10 15 20 25 17.98 19.29 MIN: 17.82 / MAX: 18.6 MIN: 18.99 / MAX: 22.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vgg16 RESET3 RESET 5 10 15 20 25 20.62 22.59 MIN: 20.22 / MAX: 23.98 MIN: 20.48 / MAX: 23.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet18 RESET3 RESET 3 6 9 12 15 8.72 9.13 MIN: 8.48 / MAX: 9.08 MIN: 9 / MAX: 11.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: alexnet RESET3 RESET 2 4 6 8 10 5.23 6.01 MIN: 5.01 / MAX: 5.51 MIN: 5.86 / MAX: 7.74 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet50 RESET RESET3 4 8 12 16 20 16.83 17.19 MIN: 16.57 / MAX: 24.47 MIN: 16.86 / MAX: 35.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: yolov4-tiny RESET RESET3 6 12 18 24 30 25.42 25.96 MIN: 24.66 / MAX: 60.7 MIN: 25.03 / MAX: 29.61 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: squeezenet_ssd RESET RESET3 4 8 12 16 20 15.52 16.20 MIN: 15.22 / MAX: 20.06 MIN: 15.81 / MAX: 54.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: regnety_400m RESET RESET3 5 10 15 20 25 17.13 22.32 MIN: 16.89 / MAX: 19.07 MIN: 22.1 / MAX: 22.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vision_transformer RESET3 RESET 13 26 39 52 65 44.06 55.73 MIN: 43.6 / MAX: 47.6 MIN: 54.17 / MAX: 116.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: FastestDet RESET RESET3 3 6 9 12 15 11.30 11.81 MIN: 11.03 / MAX: 14.81 MIN: 11.65 / MAX: 12.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
nekRS nekRS is an open-source Navier Stokes solver based on the spectral element method. NekRS supports both CPU and GPU/accelerator support though this test profile is currently configured for CPU execution. NekRS is part of Nek5000 of the Mathematics and Computer Science MCS at Argonne National Laboratory. This nekRS benchmark is primarily relevant to large core count HPC servers and otherwise may be very time consuming on smaller systems. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org flops/rank, More Is Better nekRS 23.0 Input: Kershaw RESET RESET2 RESET3 2000M 4000M 6000M 8000M 10000M 10295200000 10068200000 9111820000 1. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi
OpenBenchmarking.org flops/rank, More Is Better nekRS 23.0 Input: TurboPipe Periodic RESET2 RESET RESET3 2000M 4000M 6000M 8000M 10000M 7961240000 7950340000 6776830000 1. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream RESET3 RESET RESET2 6 12 18 24 30 25.70 13.14 13.03
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream RESET3 RESET2 RESET 1.1086 2.2172 3.3258 4.4344 5.543 3.4287 4.9157 4.9273
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/ao/real_time RESET3 RESET2 RESET 3 6 9 12 15 10.79350 5.57113 5.56770
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: particle_volume/pathtracer/real_time RESET3 RESET RESET2 40 80 120 160 200 192.56 151.87 151.79
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/ao/real_time RESET3 RESET RESET2 3 6 9 12 15 10.91530 5.61038 5.60814
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time RESET3 RESET RESET2 3 6 9 12 15 10.59080 5.46527 5.44882
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.12 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time RESET3 RESET RESET2 3 6 9 12 15 12.50750 6.60071 6.58666
Remhos Remhos (REMap High-Order Solver) is a miniapp that solves the pure advection equations that are used to perform monotonic and conservative discontinuous field interpolation (remap) as part of the Eulerian phase in Arbitrary Lagrangian Eulerian (ALE) simulations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Remhos 1.0 Test: Sample Remap Example RESET3 RESET2 RESET 7 14 21 28 35 20.69 30.94 31.02 1. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi
SPECFEM3D simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.0 Model: Mount St. Helens RESET3 RESET2 RESET 6 12 18 24 30 14.86 26.34 27.11 1. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.0 Model: Layered Halfspace RESET3 RESET2 RESET 16 32 48 64 80 39.28 69.18 69.74 1. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.0 Model: Tomographic Model RESET3 RESET RESET2 6 12 18 24 30 15.28 27.09 27.37 1. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.0 Model: Homogeneous Halfspace RESET3 RESET2 RESET 8 16 24 32 40 20.01 35.32 35.68 1. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.0 Model: Water-layered Halfspace RESET3 RESET2 RESET 14 28 42 56 70 37.55 63.20 64.32 1. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi
Test: IO_uring
RESET: The test run did not produce a result.
RESET3: The test run did not produce a result.
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 4 - Input: Bosphorus 4K RESET3 RESET2 RESET 1.2868 2.5736 3.8604 5.1472 6.434 5.719 4.528 4.502 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 8 - Input: Bosphorus 4K RESET3 RESET RESET2 20 40 60 80 100 81.06 59.64 59.06 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 12 - Input: Bosphorus 4K RESET3 RESET RESET2 50 100 150 200 250 231.17 165.65 164.10 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 13 - Input: Bosphorus 4K RESET3 RESET RESET2 50 100 150 200 250 229.12 165.95 164.68 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 4 - Input: Bosphorus 1080p RESET3 RESET RESET2 4 8 12 16 20 16.40 14.21 14.07 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 8 - Input: Bosphorus 1080p RESET3 RESET RESET2 40 80 120 160 200 160.67 128.58 128.47 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 12 - Input: Bosphorus 1080p RESET3 RESET2 RESET 130 260 390 520 650 599.14 469.49 466.98 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.6 Encoder Mode: Preset 13 - Input: Bosphorus 1080p RESET3 RESET RESET2 160 320 480 640 800 721.70 600.20 595.14 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 1080p RESET RESET3 130 260 390 520 650 590.49 558.19 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 4K RESET RESET3 40 80 120 160 200 161.60 161.43 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 1080p RESET3 RESET 120 240 360 480 600 577.73 528.29 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 4K RESET3 RESET 50 100 150 200 250 216.63 162.29 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p RESET3 RESET 30 60 90 120 150 150.63 119.22 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K RESET3 RESET 20 40 60 80 100 97.76 67.60 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 1080p RESET3 RESET 3 6 9 12 15 12.30 10.73 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K RESET3 RESET 1.145 2.29 3.435 4.58 5.725 5.089 4.152 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_read_write - Threads: 64 RESET3 20K 40K 60K 80K 100K 94643
Test: oltp_read_write - Threads: 64
RESET: The test quit with a non-zero exit status. E: FATAL: Thread initialization failed!
OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_read_write - Threads: 128 RESET 13K 26K 39K 52K 65K 59739
Test: oltp_read_write - Threads: 128
RESET3: The test quit with a non-zero exit status. E: FATAL: Thread initialization failed!
OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_point_select - Threads: 16 RESET3 20K 40K 60K 80K 100K 87667
Test: oltp_point_select - Threads: 16
RESET: The test quit with a non-zero exit status. E: FATAL: Thread initialization failed!
OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_point_select - Threads: 32 RESET 20K 40K 60K 80K 100K 97200
Test: oltp_point_select - Threads: 32
RESET3: The test quit with a non-zero exit status. E: FATAL: Thread initialization failed!
OpenBenchmarking.org Queries Per Second, More Is Better TiDB Community Server 7.3 Test: oltp_point_select - Threads: 64 RESET 30K 60K 90K 120K 150K 118850
Test: oltp_point_select - Threads: 64
RESET3: The test quit with a non-zero exit status. E: FATAL: Thread initialization failed!
Build: allmodconfig
RESET: The test quit with a non-zero exit status.
RESET2: The test quit with a non-zero exit status.
RESET3: The test quit with a non-zero exit status.
VVenC VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Fast RESET3 RESET2 RESET 2 4 6 8 10 7.293 6.147 6.126 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Faster RESET3 RESET2 RESET 4 8 12 16 20 13.94 12.23 12.13 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Fast RESET3 RESET2 RESET 5 10 15 20 25 20.68 18.09 18.01 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 1080p - Video Preset: Faster RESET3 RESET RESET2 9 18 27 36 45 38.36 34.70 34.69 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
RESET Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)Python Notes: Python 3.9.16Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 23 October 2023 02:49 by user .
RESET2 Processor: AMD EPYC 9124 16-Core @ 3.00GHz (16 Cores / 32 Threads), Motherboard: Supermicro H13SSW (1.1 BIOS), Memory: 12 x 64 GB DDR5-4800MT/s HMCG94MEBRA123N, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb
OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)Python Notes: Python 3.9.16Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 23 October 2023 12:52 by user .
RESET3 Processor: AMD EPYC 9334 32-Core @ 2.70GHz (32 Cores / 64 Threads), Motherboard: Supermicro H13SSW (1.1 BIOS), Memory: 12 x 64 GB DDR5-4800MT/s HMCG94MEBRA123N, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb, Monitor: DELL E207WFP
OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1680x1050
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101111Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)Python Notes: Python 3.9.16Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 23 October 2023 19:20 by user .