Benchmarks by Michael Larabel for a future article.
Linux 6.1 Defaults Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.4.9Java Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security 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 Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
mitigations=off Processor: Intel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0602 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7a70
OS: Ubuntu 22.04, Kernel: 6.1.0-060100rc5daily20221117-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.5 (LLVM 13.0.1 DRM 3.49), Vulkan: 1.3.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.4.9Java Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security 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: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled PBRSB-eIBRS: Vulnerable + srbds: Not affected + tsx_async_abort: Not affected
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 100, Lossless Compression mitigations=off Linux 6.1 Defaults 0.009 0.018 0.027 0.036 0.045 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.04 0.04 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
Apache Spark This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Broadcast Inner Join Test Time mitigations=off Linux 6.1 Defaults 0.1845 0.369 0.5535 0.738 0.9225 SE +/- 0.01, N = 15 SE +/- 0.02, N = 15 0.76 0.82
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Inner Join Test Time mitigations=off Linux 6.1 Defaults 0.2093 0.4186 0.6279 0.8372 1.0465 SE +/- 0.01, N = 15 SE +/- 0.02, N = 15 0.87 0.93
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Repartition Test Time mitigations=off Linux 6.1 Defaults 0.2408 0.4816 0.7224 0.9632 1.204 SE +/- 0.01, N = 15 SE +/- 0.01, N = 15 1.07 1.05
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Group By Test Time mitigations=off Linux 6.1 Defaults 0.5738 1.1476 1.7214 2.2952 2.869 SE +/- 0.01, N = 15 SE +/- 0.02, N = 15 2.55 2.55
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark Using Dataframe mitigations=off Linux 6.1 Defaults 0.7605 1.521 2.2815 3.042 3.8025 SE +/- 0.04, N = 15 SE +/- 0.05, N = 15 3.38 3.34
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - Calculate Pi Benchmark mitigations=off Linux 6.1 Defaults 12 24 36 48 60 SE +/- 0.08, N = 15 SE +/- 0.07, N = 15 51.25 51.21
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 100 - SHA-512 Benchmark Time mitigations=off Linux 6.1 Defaults 0.4478 0.8956 1.3434 1.7912 2.239 SE +/- 0.02, N = 15 SE +/- 0.02, N = 15 1.99 1.99
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 7.32.6 VGR Performance Metric mitigations=off Linux 6.1 Defaults 100K 200K 300K 400K 500K 463365 462945 1. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -ldl -lm
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read While Writing mitigations=off Linux 6.1 Defaults 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 97717.39, N = 15 SE +/- 97089.51, N = 15 4930581 5089887 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Third Run mitigations=off Linux 6.1 Defaults 70 140 210 280 350 SE +/- 2.73, N = 15 SE +/- 1.24, N = 15 304.77 309.00 MIN: 23.27 / MAX: 30000 MIN: 24.35 / MAX: 30000 1. ClickHouse server version 22.5.4.19 (official build).
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Second Run mitigations=off Linux 6.1 Defaults 70 140 210 280 350 SE +/- 1.81, N = 15 SE +/- 2.35, N = 15 306.76 303.65 MIN: 24.29 / MAX: 30000 MIN: 24.32 / MAX: 30000 1. ClickHouse server version 22.5.4.19 (official build).
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, First Run / Cold Cache mitigations=off Linux 6.1 Defaults 70 140 210 280 350 SE +/- 2.21, N = 15 SE +/- 1.97, N = 15 299.11 300.04 MIN: 23.78 / MAX: 30000 MIN: 23.58 / MAX: 30000 1. ClickHouse server version 22.5.4.19 (official build).
Apache CouchDB This is a bulk insertion benchmark of Apache CouchDB. CouchDB is a document-oriented NoSQL database implemented in Erlang. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.2.2 Bulk Size: 300 - Inserts: 3000 - Rounds: 30 mitigations=off Linux 6.1 Defaults 60 120 180 240 300 SE +/- 0.88, N = 3 SE +/- 2.18, N = 3 287.31 287.57 1. (CXX) g++ options: -std=c++17 -lmozjs-91 -lm -lei -fPIC -MMD
OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Async Random Write - Clients: 16 mitigations=off Linux 6.1 Defaults 20K 40K 60K 80K 100K SE +/- 824.47, N = 3 SE +/- 1004.83, N = 3 79629 78783
Apache CouchDB This is a bulk insertion benchmark of Apache CouchDB. CouchDB is a document-oriented NoSQL database implemented in Erlang. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.2.2 Bulk Size: 100 - Inserts: 3000 - Rounds: 30 mitigations=off Linux 6.1 Defaults 40 80 120 160 200 SE +/- 0.35, N = 3 SE +/- 0.13, N = 3 167.47 168.66 1. (CXX) g++ options: -std=c++17 -lmozjs-91 -lm -lei -fPIC -MMD
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency mitigations=off Linux 6.1 Defaults 0.0182 0.0364 0.0546 0.0728 0.091 SE +/- 0.001, N = 4 SE +/- 0.000, N = 3 0.081 0.081 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only mitigations=off Linux 6.1 Defaults 300K 600K 900K 1200K 1500K SE +/- 13433.82, N = 4 SE +/- 3039.24, N = 3 1238265 1230688 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 95, Compression Effort 7 mitigations=off Linux 6.1 Defaults 0.036 0.072 0.108 0.144 0.18 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.16 0.16 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Futex mitigations=off Linux 6.1 Defaults 800K 1600K 2400K 3200K 4000K SE +/- 41423.32, N = 15 SE +/- 41459.49, N = 15 3421101.28 3515710.91 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Cache mitigations=off Linux 6.1 Defaults 20 40 60 80 100 SE +/- 1.99, N = 15 SE +/- 1.56, N = 15 99.42 97.76 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Akka Unbalanced Cobwebbed Tree mitigations=off Linux 6.1 Defaults 1600 3200 4800 6400 8000 SE +/- 34.79, N = 3 SE +/- 19.11, N = 3 7359.2 7188.4 MIN: 5648.82 / MAX: 7428.65 MIN: 5401.58 / MAX: 7219.72
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency mitigations=off Linux 6.1 Defaults 0.009 0.018 0.027 0.036 0.045 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.040 0.040 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 50 - Mode: Read Only mitigations=off Linux 6.1 Defaults 300K 600K 900K 1200K 1500K SE +/- 6479.50, N = 3 SE +/- 10486.93, N = 3 1268657 1260885 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Increment - Clients: 16 mitigations=off Linux 6.1 Defaults 30K 60K 90K 120K 150K SE +/- 1763.01, N = 3 SE +/- 1182.66, N = 3 128264 125208
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Context Switching mitigations=off Linux 6.1 Defaults 3M 6M 9M 12M 15M SE +/- 538579.50, N = 12 SE +/- 457851.80, N = 12 16210513.97 11794492.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
Apache Spark This is a benchmark of Apache Spark with its PySpark interface. Apache Spark is an open-source unified analytics engine for large-scale data processing and dealing with big data. This test profile benchmars the Apache Spark in a single-system configuration using spark-submit. The test makes use of DIYBigData's pyspark-benchmark (https://github.com/DIYBigData/pyspark-benchmark/) for generating of test data and various Apache Spark operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Broadcast Inner Join Test Time mitigations=off Linux 6.1 Defaults 0.1778 0.3556 0.5334 0.7112 0.889 SE +/- 0.02, N = 7 SE +/- 0.03, N = 3 0.78 0.79
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Repartition Test Time mitigations=off Linux 6.1 Defaults 0.243 0.486 0.729 0.972 1.215 SE +/- 0.01, N = 7 SE +/- 0.03, N = 3 1.07 1.08
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Calculate Pi Benchmark Using Dataframe mitigations=off Linux 6.1 Defaults 0.765 1.53 2.295 3.06 3.825 SE +/- 0.06, N = 7 SE +/- 0.10, N = 3 3.40 3.38
OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 1000000 - Partitions: 500 - Calculate Pi Benchmark mitigations=off Linux 6.1 Defaults 12 24 36 48 60 SE +/- 0.11, N = 7 SE +/- 0.24, N = 3 51.42 51.29
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 6.2.0 mitigations=off Linux 6.1 Defaults 300K 600K 900K 1200K 1500K SE +/- 3433.04, N = 3 SE +/- 3644.79, N = 3 1518638.23 1507777.21 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: ALS Movie Lens mitigations=off Linux 6.1 Defaults 900 1800 2700 3600 4500 SE +/- 22.27, N = 3 SE +/- 32.41, N = 3 4371.5 4371.9 MIN: 4345.9 / MAX: 4750.01 MIN: 4308.11 / MAX: 4860.44
nginx This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 1000 mitigations=off Linux 6.1 Defaults 40K 80K 120K 160K 200K SE +/- 586.42, N = 3 SE +/- 221.20, N = 3 187868.73 187512.54 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Socket Activity mitigations=off Linux 6.1 Defaults 6K 12K 18K 24K 30K SE +/- 323.81, N = 15 SE +/- 197.02, N = 3 26073.14 25195.77 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
nginx This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 500 mitigations=off Linux 6.1 Defaults 40K 80K 120K 160K 200K SE +/- 812.38, N = 3 SE +/- 845.21, N = 3 202777.49 203178.40 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 200 mitigations=off Linux 6.1 Defaults 50K 100K 150K 200K 250K SE +/- 702.24, N = 3 SE +/- 806.08, N = 3 211212.37 211451.29 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 100 mitigations=off Linux 6.1 Defaults 40K 80K 120K 160K 200K SE +/- 1384.83, N = 3 SE +/- 1157.09, N = 3 207784.83 207280.77 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Atomic mitigations=off Linux 6.1 Defaults 70K 140K 210K 280K 350K SE +/- 2320.39, N = 3 SE +/- 7379.51, N = 15 331842.59 338549.56 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 200 400 600 800 1000 SE +/- 1.94, N = 3 SE +/- 3.70, N = 3 952.75 947.67
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 12.45 12.51
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 200 400 600 800 1000 SE +/- 1.73, N = 3 SE +/- 3.52, N = 3 937.65 948.18
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 12.67 12.54
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 50 100 150 200 250 SE +/- 0.57, N = 3 SE +/- 0.42, N = 3 223.81 220.95
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 12 24 36 48 60 SE +/- 0.13, N = 3 SE +/- 0.10, N = 3 53.49 54.16
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Mutex mitigations=off Linux 6.1 Defaults 4M 8M 12M 16M 20M SE +/- 153223.16, N = 3 SE +/- 368734.03, N = 12 17479306.27 16677300.35 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 75, Compression Effort 7 mitigations=off Linux 6.1 Defaults 0.0743 0.1486 0.2229 0.2972 0.3715 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.33 0.33 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
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 0.6 Clients: 200 - Set To Get Ratio: 1:5 mitigations=off Linux 6.1 Defaults 1.5M 3M 4.5M 6M 7.5M SE +/- 33271.78, N = 3 SE +/- 41132.46, N = 3 7029304.50 7029354.71 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 5:1 mitigations=off Linux 6.1 Defaults 1.4M 2.8M 4.2M 5.6M 7M SE +/- 46202.73, N = 3 SE +/- 19398.36, N = 3 6436491.37 6440950.32 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 200 - Set To Get Ratio: 1:1 mitigations=off Linux 6.1 Defaults 1.4M 2.8M 4.2M 5.6M 7M SE +/- 49539.07, N = 3 SE +/- 42144.49, N = 3 6650409.60 6696607.28 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 5:1 mitigations=off Linux 6.1 Defaults 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 5261.63, N = 3 SE +/- 22475.30, N = 3 6243118.04 6159328.58 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:5 mitigations=off Linux 6.1 Defaults 1.4M 2.8M 4.2M 5.6M 7M SE +/- 31744.79, N = 3 SE +/- 16253.11, N = 3 6765462.42 6742394.01 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:1 mitigations=off Linux 6.1 Defaults 1.4M 2.8M 4.2M 5.6M 7M SE +/- 36510.22, N = 3 SE +/- 54773.05, N = 3 6423833.88 6335702.64 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Stargate Digital Audio Workstation Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 512 mitigations=off Linux 6.1 Defaults 0.593 1.186 1.779 2.372 2.965 SE +/- 0.006256, N = 3 SE +/- 0.005802, N = 3 2.629225 2.635590 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
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 10.8.2 Clients: 32 mitigations=off Linux 6.1 Defaults 700 1400 2100 2800 3500 SE +/- 9.76, N = 3 SE +/- 28.86, N = 3 3330 3304 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -lpthread -ldl
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 500 1000 1500 2000 2500 SE +/- 2.24, N = 3 SE +/- 1.23, N = 3 2209.76 2212.51 MIN: 1693.41 / MAX: 2903.99 MIN: 1666.75 / MAX: 2938.5 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 0.81 1.62 2.43 3.24 4.05 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.60 3.59 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU mitigations=off Linux 6.1 Defaults 500 1000 1500 2000 2500 SE +/- 6.69, N = 3 SE +/- 4.82, N = 3 2236.03 2223.37 MIN: 1702.71 / MAX: 3129.63 MIN: 1691.82 / MAX: 2995.51 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU mitigations=off Linux 6.1 Defaults 0.8055 1.611 2.4165 3.222 4.0275 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 3.56 3.58 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 300 600 900 1200 1500 SE +/- 9.54, N = 3 SE +/- 8.27, N = 3 1557.36 1556.54 MIN: 1398.63 / MAX: 1895.62 MIN: 1401.44 / MAX: 1905.83 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 1.1543 2.3086 3.4629 4.6172 5.7715 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 5.13 5.13 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
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 mitigations=off Linux 6.1 Defaults 600K 1200K 1800K 2400K 3000K SE +/- 26949.91, N = 6 SE +/- 11434.48, N = 3 2680364.8 2696816.3
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.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 12.05 12.09 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark PageRank mitigations=off Linux 6.1 Defaults 400 800 1200 1600 2000 SE +/- 7.79, N = 3 SE +/- 15.25, N = 3 1877.8 1900.6 MIN: 1729.93 / MAX: 1920.13 MIN: 1751.32 / MAX: 1979.24
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Genetic Algorithm Using Jenetics + Futures mitigations=off Linux 6.1 Defaults 200 400 600 800 1000 SE +/- 7.18, N = 3 SE +/- 12.61, N = 4 1051.3 1033.2 MIN: 988.02 / MAX: 1106.1 MIN: 963.25 / MAX: 1123.84
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 30 60 90 120 150 SE +/- 0.22, N = 3 SE +/- 0.10, N = 3 125.10 125.00 MIN: 90.23 / MAX: 327.3 MIN: 88.24 / MAX: 330.6 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 14 28 42 56 70 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 63.87 63.95 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU mitigations=off Linux 6.1 Defaults 90 180 270 360 450 SE +/- 0.58, N = 3 SE +/- 0.12, N = 3 438.11 437.50 MIN: 270.11 / MAX: 1300.72 MIN: 270.24 / MAX: 992.11 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU mitigations=off Linux 6.1 Defaults 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 18.24 18.26 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Fill Sync mitigations=off Linux 6.1 Defaults 8K 16K 24K 32K 40K SE +/- 248.77, N = 3 SE +/- 8.74, N = 3 38607 38927 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 10.68 10.58 MIN: 7.52 / MAX: 54.71 MIN: 7.56 / MAX: 57.78 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 160 320 480 640 800 SE +/- 0.34, N = 3 SE +/- 3.32, N = 3 748.06 755.36 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 11 22 33 44 55 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 50.67 50.57 MIN: 30.2 / MAX: 197.71 MIN: 22.73 / MAX: 185.96 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 100 200 300 400 500 SE +/- 0.03, N = 3 SE +/- 0.35, N = 3 472.81 473.81 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 21.56 21.45 MIN: 11.75 / MAX: 89.39 MIN: 11.89 / MAX: 88 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 80 160 240 320 400 SE +/- 0.52, N = 3 SE +/- 0.29, N = 3 370.54 372.54 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU mitigations=off Linux 6.1 Defaults 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 8.74 8.70 MIN: 5.93 / MAX: 61 MIN: 5.93 / MAX: 62.71 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU mitigations=off Linux 6.1 Defaults 200 400 600 800 1000 SE +/- 1.18, N = 3 SE +/- 0.49, N = 3 914.62 919.04 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU mitigations=off Linux 6.1 Defaults 0.162 0.324 0.486 0.648 0.81 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.72 0.72 MIN: 0.5 / MAX: 5.06 MIN: 0.5 / MAX: 5.07 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU mitigations=off Linux 6.1 Defaults 7K 14K 21K 28K 35K SE +/- 20.38, N = 3 SE +/- 4.98, N = 3 33193.11 33202.88 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU mitigations=off Linux 6.1 Defaults 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 14.51 14.41 MIN: 7.71 / MAX: 127.13 MIN: 7.04 / MAX: 135.23 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU mitigations=off Linux 6.1 Defaults 400 800 1200 1600 2000 SE +/- 3.13, N = 3 SE +/- 1.49, N = 3 1653.36 1664.64 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 0.3668 0.7336 1.1004 1.4672 1.834 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.63 1.63 MIN: 0.83 / MAX: 10.17 MIN: 1.11 / MAX: 10.18 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU mitigations=off Linux 6.1 Defaults 3K 6K 9K 12K 15K SE +/- 8.91, N = 3 SE +/- 5.29, N = 3 14683.75 14690.90 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Fill mitigations=off Linux 6.1 Defaults 300K 600K 900K 1200K 1500K SE +/- 5444.71, N = 3 SE +/- 6463.89, N = 3 1367267 1356117 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Update Random mitigations=off Linux 6.1 Defaults 160K 320K 480K 640K 800K SE +/- 4236.67, N = 3 SE +/- 7415.12, N = 3 764558 770017 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Read Random Write Random mitigations=off Linux 6.1 Defaults 800K 1600K 2400K 3200K 4000K SE +/- 15106.42, N = 3 SE +/- 3258.62, N = 3 3624644 3641155 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Random Read mitigations=off Linux 6.1 Defaults 40M 80M 120M 160M 200M SE +/- 2519557.52, N = 3 SE +/- 2292531.98, N = 3 177503122 177480853 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Stargate Digital Audio Workstation Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 1024 mitigations=off Linux 6.1 Defaults 0.6855 1.371 2.0565 2.742 3.4275 SE +/- 0.003982, N = 3 SE +/- 0.002663, N = 3 3.046716 3.033533 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Random Read - Clients: 16 mitigations=off Linux 6.1 Defaults 60K 120K 180K 240K 300K SE +/- 984.52, N = 3 SE +/- 2676.47, N = 3 299708 291117
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Savina Reactors.IO mitigations=off Linux 6.1 Defaults 900 1800 2700 3600 4500 SE +/- 3.06, N = 3 SE +/- 45.21, N = 3 4159.1 4188.3 MIN: 4153.01 / MAX: 5832.37 MIN: 4132.82 / MAX: 5963.25
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 4 - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 0.6883 1.3766 2.0649 2.7532 3.4415 SE +/- 0.005, N = 3 SE +/- 0.016, N = 3 3.044 3.059 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 0.0945 0.189 0.2835 0.378 0.4725 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.41 0.42 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 50 100 150 200 250 SE +/- 0.27, N = 3 SE +/- 0.44, N = 3 237.44 236.76
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 11 22 33 44 55 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 50.30 50.53
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 30 60 90 120 150 SE +/- 1.06, N = 3 SE +/- 1.09, N = 3 113.43 112.77
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 20 40 60 80 100 SE +/- 1.02, N = 3 SE +/- 1.00, N = 3 105.73 106.27
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 mitigations=off Linux 6.1 Defaults 600K 1200K 1800K 2400K 3000K SE +/- 3790.37, N = 3 SE +/- 5792.62, N = 3 2976169.8 2980179.4
OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.5.0 Rows: 1000000 - Test: Random Read - Clients: 1 mitigations=off Linux 6.1 Defaults 6K 12K 18K 24K 30K SE +/- 87.43, N = 3 SE +/- 201.55, N = 3 27660 25419
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 40 80 120 160 200 SE +/- 0.78, N = 3 SE +/- 0.69, N = 3 158.91 158.06
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 512b Encryption mitigations=off Linux 6.1 Defaults 150 300 450 600 750 SE +/- 0.21, N = 3 SE +/- 0.15, N = 3 699.8 699.6
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Decryption mitigations=off Linux 6.1 Defaults 200 400 600 800 1000 SE +/- 0.87, N = 3 SE +/- 0.74, N = 3 1043.1 1043.4
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Encryption mitigations=off Linux 6.1 Defaults 200 400 600 800 1000 SE +/- 0.80, N = 2 SE +/- 0.62, N = 3 1010.4 1011.7
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Decryption mitigations=off Linux 6.1 Defaults 1400 2800 4200 5600 7000 SE +/- 21.42, N = 3 SE +/- 16.52, N = 3 6490.6 6503.1
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Encryption mitigations=off Linux 6.1 Defaults 1400 2800 4200 5600 7000 SE +/- 22.60, N = 3 SE +/- 16.24, N = 3 6508.0 6523.5
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Decryption mitigations=off Linux 6.1 Defaults 150 300 450 600 750 SE +/- 0.30, N = 3 SE +/- 0.27, N = 3 704.3 704.6
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Encryption mitigations=off Linux 6.1 Defaults 150 300 450 600 750 SE +/- 1.37, N = 3 SE +/- 1.56, N = 3 698.5 698.4
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Decryption mitigations=off Linux 6.1 Defaults 200 400 600 800 1000 SE +/- 0.95, N = 3 SE +/- 0.74, N = 3 1042.7 1043.6
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Encryption mitigations=off Linux 6.1 Defaults 200 400 600 800 1000 SE +/- 2.16, N = 3 SE +/- 2.59, N = 3 1008.9 1009.0
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Decryption mitigations=off Linux 6.1 Defaults 1500 3000 4500 6000 7500 SE +/- 24.01, N = 3 SE +/- 15.14, N = 3 7083.9 7108.8
OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Encryption mitigations=off Linux 6.1 Defaults 1500 3000 4500 6000 7500 SE +/- 24.85, N = 3 SE +/- 15.48, N = 3 7078.4 7107.7
OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-whirlpool mitigations=off Linux 6.1 Defaults 300K 600K 900K 1200K 1500K SE +/- 568.00, N = 3 SE +/- 1131.33, N = 3 1336901 1334634
OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-sha512 mitigations=off Linux 6.1 Defaults 600K 1200K 1800K 2400K 3000K SE +/- 1281.67, N = 3 SE +/- 2560.00, N = 3 2840387 2839109
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 20 40 60 80 100 SE +/- 0.51, N = 3 SE +/- 0.28, N = 3 77.20 77.19
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream mitigations=off Linux 6.1 Defaults 30 60 90 120 150 SE +/- 1.00, N = 3 SE +/- 0.64, N = 3 155.32 155.27
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.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 21.68 21.70 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive mitigations=off Linux 6.1 Defaults 0.3288 0.6576 0.9864 1.3152 1.644 SE +/- 0.0029, N = 3 SE +/- 0.0062, N = 3 1.4612 1.4516 1. (CXX) g++ options: -O3 -flto -pthread
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: SENDFILE mitigations=off Linux 6.1 Defaults 130K 260K 390K 520K 650K SE +/- 7176.09, N = 4 SE +/- 7415.69, N = 3 602354.79 610692.10 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: In-Memory Database Shootout mitigations=off Linux 6.1 Defaults 400 800 1200 1600 2000 SE +/- 24.16, N = 3 SE +/- 27.32, N = 3 1968.2 1921.4 MIN: 1760.93 / MAX: 2449.66 MIN: 1708.07 / MAX: 2253.56
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: x86_64 RdRand mitigations=off Linux 6.1 Defaults 20K 40K 60K 80K 100K SE +/- 28.05, N = 3 SE +/- 3.35, N = 3 82746.87 82763.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
Aircrack-ng Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.7 mitigations=off Linux 6.1 Defaults 15K 30K 45K 60K 75K SE +/- 47.65, N = 3 SE +/- 164.84, N = 3 69948.19 69682.14 1. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lpcre -lsqlite3 -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -pthread
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: System V Message Passing mitigations=off Linux 6.1 Defaults 7M 14M 21M 28M 35M SE +/- 441148.10, N = 3 SE +/- 12278.20, N = 3 32855914.63 32462582.17 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Semaphores mitigations=off Linux 6.1 Defaults 800K 1600K 2400K 3200K 4000K SE +/- 4974.11, N = 3 SE +/- 6818.46, N = 3 3519548.92 3517936.22 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc C String Functions mitigations=off Linux 6.1 Defaults 800K 1600K 2400K 3200K 4000K SE +/- 29422.94, N = 3 SE +/- 44204.27, N = 3 3778821.91 3741573.78 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: NUMA mitigations=off Linux 6.1 Defaults 150 300 450 600 750 SE +/- 3.21, N = 3 SE +/- 9.66, N = 3 679.66 688.80 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Malloc mitigations=off Linux 6.1 Defaults 7M 14M 21M 28M 35M SE +/- 95450.84, N = 3 SE +/- 145595.11, N = 3 32341790.85 32335069.76 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Crypto mitigations=off Linux 6.1 Defaults 9K 18K 27K 36K 45K SE +/- 226.79, N = 3 SE +/- 251.10, N = 3 42952.32 42801.84 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Memory Copying mitigations=off Linux 6.1 Defaults 1600 3200 4800 6400 8000 SE +/- 24.63, N = 3 SE +/- 42.34, N = 3 7275.14 7302.74 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Forking mitigations=off Linux 6.1 Defaults 30K 60K 90K 120K 150K SE +/- 714.85, N = 3 SE +/- 866.53, N = 3 133593.49 132107.51 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Vector Math mitigations=off Linux 6.1 Defaults 30K 60K 90K 120K 150K SE +/- 179.45, N = 3 SE +/- 174.14, N = 3 134263.01 134428.58 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Matrix Math mitigations=off Linux 6.1 Defaults 20K 40K 60K 80K 100K SE +/- 1306.38, N = 3 SE +/- 692.52, N = 3 101602.63 102476.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MMAP mitigations=off Linux 6.1 Defaults 140 280 420 560 700 SE +/- 7.79, N = 3 SE +/- 6.66, N = 3 649.59 664.95 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Stress mitigations=off Linux 6.1 Defaults 11K 22K 33K 44K 55K SE +/- 646.04, N = 3 SE +/- 433.83, N = 3 51447.48 51499.15 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: IO_uring mitigations=off Linux 6.1 Defaults 6K 12K 18K 24K 30K SE +/- 16.82, N = 3 SE +/- 6.02, N = 3 27589.43 27773.35 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc Qsort Data Sorting mitigations=off Linux 6.1 Defaults 90 180 270 360 450 SE +/- 1.72, N = 3 SE +/- 2.44, N = 3 411.91 414.37 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lsctp -lz -pthread
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM mitigations=off Linux 6.1 Defaults 40 80 120 160 200 SE +/- 0.32, N = 3 SE +/- 0.12, N = 3 201.8 202.0 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM mitigations=off Linux 6.1 Defaults 150 300 450 600 750 SE +/- 2.62, N = 3 SE +/- 2.42, N = 3 712.1 706.4 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
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 MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless, Highest Compression mitigations=off Linux 6.1 Defaults 0.2115 0.423 0.6345 0.846 1.0575 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.94 0.93 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Finagle HTTP Requests mitigations=off Linux 6.1 Defaults 400 800 1200 1600 2000 SE +/- 12.55, N = 3 SE +/- 2.14, N = 3 1963.9 1992.9 MIN: 1798.97 / MAX: 2151.27 MIN: 1809.15 / MAX: 2148.58
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM mitigations=off Linux 6.1 Defaults 40 80 120 160 200 SE +/- 1.23, N = 3 SE +/- 0.17, N = 3 180.4 181.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM mitigations=off Linux 6.1 Defaults 140 280 420 560 700 SE +/- 4.97, N = 3 SE +/- 5.43, N = 3 639.1 643.2 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Samples / Second, More Is Better srsRAN 22.04.1 Test: OFDM_Test mitigations=off Linux 6.1 Defaults 40M 80M 120M 160M 200M SE +/- 642910.05, N = 3 SE +/- 866666.67, N = 3 200600000 199833333 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
Facebook RocksDB OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.5.3 Test: Sequential Fill mitigations=off Linux 6.1 Defaults 300K 600K 900K 1200K 1500K SE +/- 2086.01, N = 3 SE +/- 17853.48, N = 3 1494610 1502431 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough mitigations=off Linux 6.1 Defaults 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 16.06 16.24 1. (CXX) g++ options: -O3 -flto -pthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 20 40 60 80 100 SE +/- 0.72, N = 7 SE +/- 0.86, N = 4 77.34 76.35 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 10 20 30 40 50 SE +/- 0.22, N = 3 SE +/- 0.13, N = 3 44.71 44.19 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM mitigations=off Linux 6.1 Defaults 50 100 150 200 250 SE +/- 1.80, N = 5 SE +/- 0.44, N = 3 224.3 229.1 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM mitigations=off Linux 6.1 Defaults 140 280 420 560 700 SE +/- 6.50, N = 5 SE +/- 2.79, N = 3 631.3 646.2 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM mitigations=off Linux 6.1 Defaults 20 40 60 80 100 SE +/- 0.52, N = 3 SE +/- 0.12, N = 3 103.1 104.3 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM mitigations=off Linux 6.1 Defaults 50 100 150 200 250 SE +/- 1.89, N = 3 SE +/- 1.46, N = 3 225.8 227.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Fast mitigations=off Linux 6.1 Defaults 70 140 210 280 350 SE +/- 0.26, N = 3 SE +/- 0.16, N = 3 344.76 345.11 1. (CXX) g++ options: -O3 -flto -pthread
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM mitigations=off Linux 6.1 Defaults 50 100 150 200 250 SE +/- 0.50, N = 3 SE +/- 1.56, N = 3 245.5 245.1 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM mitigations=off Linux 6.1 Defaults 150 300 450 600 750 SE +/- 1.00, N = 3 SE +/- 7.34, N = 3 713.6 713.6 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
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.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 15 30 45 60 75 SE +/- 0.78, N = 3 SE +/- 0.37, N = 3 66.49 65.78 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 100, Compression Effort 5 mitigations=off Linux 6.1 Defaults 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.16, N = 15 9.46 9.11 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
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.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 20 40 60 80 100 SE +/- 0.19, N = 3 SE +/- 0.19, N = 3 85.91 83.60 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 20 40 60 80 100 SE +/- 0.57, N = 3 SE +/- 0.27, N = 3 86.62 84.71 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Medium mitigations=off Linux 6.1 Defaults 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.19, N = 3 126.26 126.15 1. (CXX) g++ options: -O3 -flto -pthread
OSBench OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files mitigations=off Linux 6.1 Defaults 2 4 6 8 10 SE +/- 0.004001, N = 3 SE +/- 0.010422, N = 3 8.239698 8.312671 1. (CC) gcc options: -lm
OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations mitigations=off Linux 6.1 Defaults 10 20 30 40 50 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 40.83 42.13 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes mitigations=off Linux 6.1 Defaults 4 8 12 16 20 SE +/- 0.17, N = 3 SE +/- 0.06, N = 3 17.47 17.20 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs mitigations=off Linux 6.1 Defaults 6 12 18 24 30 SE +/- 0.16, N = 3 SE +/- 0.07, N = 3 23.89 23.99 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads mitigations=off Linux 6.1 Defaults 3 6 9 12 15 SE +/- 0.101921, N = 3 SE +/- 0.059195, N = 3 9.106795 9.116332 1. (CC) gcc options: -lm
Bork File Encrypter Bork is a small, cross-platform file encryption utility. It is written in Java and designed to be included along with the files it encrypts for long-term storage. This test measures the amount of time it takes to encrypt a sample file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Bork File Encrypter 1.4 File Encryption Time mitigations=off Linux 6.1 Defaults 1.0901 2.1802 3.2703 4.3604 5.4505 SE +/- 0.030, N = 3 SE +/- 0.033, N = 3 4.817 4.845
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 30 60 90 120 150 SE +/- 1.43, N = 3 SE +/- 1.34, N = 3 147.85 146.09 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 4K mitigations=off Linux 6.1 Defaults 50 100 150 200 250 SE +/- 0.64, N = 3 SE +/- 1.49, N = 3 217.73 216.78 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Default mitigations=off Linux 6.1 Defaults 4 8 12 16 20 SE +/- 0.14, N = 7 SE +/- 0.20, N = 3 15.17 14.92 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
Linux 6.1 Defaults Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.4.9Java Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security 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 Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 28 November 2022 12:55 by user phoronix.
mitigations=off Processor: Intel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0602 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: Realtek ALC897, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel Device 7a70
OS: Ubuntu 22.04, Kernel: 6.1.0-060100rc5daily20221117-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.5 (LLVM 13.0.1 DRM 3.49), Vulkan: 1.3.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.4.9Java Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security 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: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled PBRSB-eIBRS: Vulnerable + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 29 November 2022 05:15 by user phoronix.