Linux 6.4.14 Processor: Intel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0812 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 7700S/7600S/7600M XT 8GB (1940/1124MHz), Audio: Realtek ALC897, Monitor: ASUS VP28U
OS: Ubuntu 22.04, Kernel: 6.4.14-060414-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.3~git2308070600.777734~oibaf~j (git-7777349 2023-08-07 jammy-oibaf-ppa) (LLVM 15.0.7 DRM 3.52), OpenCL: OpenCL 1.1 Mesa 23.3~git2308020600.4de7e0~oibaf~j (git-4de7e00 2023-08-02 jammy-oibaf-ppa) + OpenCL 3.0, Vulkan: 1.3.258, Compiler: GCC 11.4.0 + Clang 16.0.6 + LLVM 16.0.6, 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-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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: 0x119 - Thermald 2.4.9Python Notes: Python 3.10.12Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Linux 6.5.1 OS: Ubuntu 22.04, Kernel: 6.5.1-060501-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.3~git2308070600.777734~oibaf~j (git-7777349 2023-08-07 jammy-oibaf-ppa) (LLVM 15.0.7 DRM 3.54), OpenCL: OpenCL 1.1 Mesa 23.3~git2308020600.4de7e0~oibaf~j (git-4de7e00 2023-08-02 jammy-oibaf-ppa) + OpenCL 3.0, Vulkan: 1.3.258, Compiler: GCC 11.4.0 + Clang 16.0.6 + LLVM 16.0.6, File-System: ext4, Screen Resolution: 3840x2160
Linux 6.6-rc1 OS: Ubuntu 22.04, Kernel: 6.6.0-060600rc1-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.3~git2308070600.777734~oibaf~j (git-7777349 2023-08-07 jammy-oibaf-ppa) (LLVM 15.0.7 DRM 3.54), OpenCL: OpenCL 1.1 Mesa 23.3~git2308020600.4de7e0~oibaf~j (git-4de7e00 2023-08-02 jammy-oibaf-ppa) + OpenCL 3.0, Vulkan: 1.3.258, Compiler: GCC 11.4.0 + Clang 16.0.6 + LLVM 16.0.6, File-System: ext4, Screen Resolution: 3840x2160
Redis Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPOP - Parallel Connections: 50 Linux 6.4.14 Linux 6.5.1 Linux 6.6-rc1 1.4M 2.8M 4.2M 5.6M 7M SE +/- 61180.11, N = 14 SE +/- 26986.45, N = 3 SE +/- 24192.95, N = 3 6527019.80 3608927.58 3574286.00 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 4K Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 30 60 90 120 150 SE +/- 0.72, N = 3 SE +/- 0.97, N = 3 SE +/- 1.14, N = 15 120.36 102.07 99.15 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 5 10 15 20 25 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 21.09 20.88 17.88
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 140 280 420 560 700 SE +/- 0.68, N = 3 SE +/- 0.69, N = 3 SE +/- 1.80, N = 3 564.13 571.45 664.90
Redis Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 50 Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 1.4M 2.8M 4.2M 5.6M 7M SE +/- 21190.91, N = 3 SE +/- 32399.38, N = 3 SE +/- 59708.19, N = 4 6372860.8 5432508.7 5409166.1 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 20 40 60 80 100 SE +/- 0.55, N = 3 SE +/- 0.93, N = 3 SE +/- 0.32, N = 3 74.36 73.42 63.28 1. (CXX) g++ options: -fPIE -mavx512vl -std=gnu++11
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: Faster Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 15.40 14.84 13.26 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
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 3.7 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Linux 6.4.14 Linux 6.5.1 Linux 6.6-rc1 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 1.05, N = 6 SE +/- 0.68, N = 15 115.95 105.82 99.98 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 40 80 120 160 200 SE +/- 1.04, N = 3 SE +/- 0.79, N = 3 SE +/- 0.30, N = 3 178.57 177.51 155.07
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 20 40 60 80 100 SE +/- 0.39, N = 3 SE +/- 0.29, N = 3 SE +/- 0.16, N = 3 67.14 67.53 77.30
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 FPS, More Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 80 160 240 320 400 SE +/- 1.67, N = 3 SE +/- 0.45, N = 3 SE +/- 0.37, N = 3 363.88 359.56 317.31 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 6 12 18 24 30 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 21.96 22.17 25.18 MIN: 12.48 / MAX: 92.92 MIN: 12.18 / MAX: 92.23 MIN: 12.04 / MAX: 268.7 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -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 3.7 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Linux 6.4.14 Linux 6.5.1 Linux 6.6-rc1 20 40 60 80 100 SE +/- 0.93, N = 5 SE +/- 1.29, N = 14 SE +/- 0.71, N = 15 90.94 83.39 79.37 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
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 FPS, More Is Better OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 1.1745 2.349 3.5235 4.698 5.8725 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 5.22 5.21 4.56 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
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 1080p - Video Preset: Faster Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 10 20 30 40 50 SE +/- 0.40, N = 3 SE +/- 0.26, N = 3 SE +/- 0.41, N = 15 43.06 40.93 37.67 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 50 100 150 200 250 SE +/- 0.47, N = 3 SE +/- 0.93, N = 3 SE +/- 1.56, N = 3 215.12 218.70 244.95
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 Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 40K 80K 120K 160K 200K SE +/- 405.81, N = 3 SE +/- 206.63, N = 3 SE +/- 193.59, N = 3 181548.67 178781.88 159455.41 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 12 24 36 48 60 SE +/- 0.12, N = 3 SE +/- 0.19, N = 3 SE +/- 0.33, N = 3 55.56 54.67 48.83
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 2022.3 Model: Face Detection FP16-INT8 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 120 240 360 480 600 SE +/- 0.44, N = 3 SE +/- 2.53, N = 3 SE +/- 1.24, N = 3 472.84 480.58 537.88 MIN: 277.17 / MAX: 1075.52 MIN: 281.91 / MAX: 1819.21 MIN: 283.72 / MAX: 1567.74 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 16.84 16.54 14.82 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
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 1080p - Video Preset: Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 5 10 15 20 25 SE +/- 0.19, N = 3 SE +/- 0.24, N = 3 SE +/- 0.23, N = 4 21.39 21.03 18.82 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
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 2022.3 Model: Face Detection FP16 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 400 800 1200 1600 2000 SE +/- 4.26, N = 3 SE +/- 2.73, N = 3 SE +/- 3.95, N = 3 1527.69 1530.67 1732.57 MIN: 1245.52 / MAX: 2434.1 MIN: 1261.48 / MAX: 2153.42 MIN: 1219.45 / MAX: 2642.28 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 50 100 150 200 250 SE +/- 0.39, N = 3 SE +/- 0.35, N = 3 SE +/- 1.57, N = 3 183.50 184.57 207.79
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 16 32 48 64 80 SE +/- 0.58, N = 9 SE +/- 1.13, N = 12 SE +/- 0.23, N = 3 70.21 69.36 62.04 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 15 30 45 60 75 SE +/- 0.15, N = 3 SE +/- 0.14, N = 3 SE +/- 0.47, N = 3 65.20 64.91 57.67
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 5 10 15 20 25 SE +/- 0.20, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 18.98 18.73 16.80
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 11 22 33 44 55 SE +/- 0.13, N = 3 SE +/- 0.31, N = 15 SE +/- 0.34, N = 15 48.98 47.18 43.40
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 2022.3 Model: Person Detection FP32 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 600 1200 1800 2400 3000 SE +/- 1.81, N = 3 SE +/- 2.59, N = 3 SE +/- 7.80, N = 3 2358.66 2376.85 2659.28 MIN: 1633.33 / MAX: 3064.46 MIN: 1653.87 / MAX: 3128.88 MIN: 1744.63 / MAX: 3523.32 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 150 300 450 600 750 SE +/- 5.83, N = 3 SE +/- 0.52, N = 3 SE +/- 1.88, N = 3 627.09 635.34 706.21
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.16, N = 15 14.95 14.42 13.28 1. (CXX) g++ options: -fPIE -mavx512vl -std=gnu++11
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 FPS, More Is Better OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 0.747 1.494 2.241 2.988 3.735 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.32 3.30 2.95 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 9 18 27 36 45 SE +/- 0.07, N = 3 SE +/- 0.49, N = 3 SE +/- 0.38, N = 4 37.05 35.89 32.96
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: 100 Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 40K 80K 120K 160K 200K SE +/- 863.45, N = 3 SE +/- 662.36, N = 3 SE +/- 909.81, N = 3 194643.92 191219.52 173181.72 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: nbody Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 14 28 42 56 70 SE +/- 0.13, N = 3 SE +/- 0.51, N = 3 SE +/- 0.70, N = 3 57.3 57.4 64.3
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 2022.3 Model: Person Detection FP16 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 600 1200 1800 2400 3000 SE +/- 7.60, N = 3 SE +/- 6.89, N = 3 SE +/- 5.22, N = 3 2354.17 2356.13 2638.93 MIN: 1820.77 / MAX: 3381.57 MIN: 1722.27 / MAX: 3041.75 MIN: 1728.66 / MAX: 3518.83 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 300 600 900 1200 1500 SE +/- 1.43, N = 3 SE +/- 0.91, N = 3 SE +/- 2.42, N = 3 1497.35 1490.03 1335.97 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 5 10 15 20 25 SE +/- 0.15, N = 3 SE +/- 0.14, N = 12 SE +/- 0.04, N = 3 18.31 17.96 16.34 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 16.02 16.10 17.95 MIN: 9.1 / MAX: 136.77 MIN: 9.11 / MAX: 137.77 MIN: 9.65 / MAX: 145.04 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 9 18 27 36 45 SE +/- 0.53, N = 3 SE +/- 0.49, N = 4 SE +/- 0.34, N = 15 40.58 40.48 36.23 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 1.1516 2.3032 3.4548 4.6064 5.758 SE +/- 0.029, N = 3 SE +/- 0.018, N = 3 SE +/- 0.032, N = 15 5.118 5.079 4.570 1. (CXX) g++ options: -fPIE -mavx512vl -std=gnu++11
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 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 14 28 42 56 70 SE +/- 0.16, N = 3 SE +/- 0.21, N = 3 SE +/- 0.12, N = 3 55.47 56.34 62.12 MIN: 23.14 / MAX: 211.78 MIN: 29.26 / MAX: 335.02 MIN: 31.33 / MAX: 333.99 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 90 180 270 360 450 SE +/- 1.22, N = 3 SE +/- 1.55, N = 3 SE +/- 0.80, N = 3 431.89 425.19 385.73 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 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-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 5 10 15 20 25 SE +/- 0.19, N = 3 SE +/- 0.09, N = 3 SE +/- 0.18, N = 3 21.37 21.09 19.09 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
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 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 9.15 9.22 10.23 MIN: 5.63 / MAX: 63.19 MIN: 5.62 / MAX: 64.74 MIN: 5.61 / MAX: 80.94 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 0.7515 1.503 2.2545 3.006 3.7575 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.34 3.33 2.99 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 200 400 600 800 1000 SE +/- 1.97, N = 3 SE +/- 1.32, N = 3 SE +/- 4.97, N = 3 872.96 854.42 781.75 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 14 28 42 56 70 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.16, N = 3 56.07 56.54 62.58
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 50 100 150 200 250 SE +/- 0.35, N = 3 SE +/- 0.26, N = 3 SE +/- 0.48, N = 3 213.65 211.92 191.44
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 30 60 90 120 150 SE +/- 0.28, N = 3 SE +/- 0.30, N = 3 SE +/- 0.12, N = 3 131.06 130.79 117.44
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.20, N = 3 SE +/- 0.11, N = 3 91.50 91.70 102.09
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 20 40 60 80 100 SE +/- 0.60, N = 3 SE +/- 0.18, N = 3 SE +/- 0.35, N = 3 98.02 98.01 87.93
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 Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 40K 80K 120K 160K 200K SE +/- 444.27, N = 3 SE +/- 355.54, N = 3 SE +/- 255.25, N = 3 191326.52 191291.62 171679.65 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 9 18 27 36 45 SE +/- 0.09, N = 3 SE +/- 0.25, N = 3 SE +/- 0.26, N = 15 39.78 38.69 35.72
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.15, N = 3 SE +/- 0.02, N = 3 13.28 13.18 11.93
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 12 24 36 48 60 SE +/- 0.43, N = 15 SE +/- 0.70, N = 3 SE +/- 0.37, N = 15 51.10 50.28 45.91 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 300 600 900 1200 1500 SE +/- 3.04, N = 3 SE +/- 0.47, N = 3 SE +/- 3.12, N = 3 1390.03 1380.05 1248.94
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 3 6 9 12 15 SE +/- 0.0179, N = 3 SE +/- 0.0024, N = 3 SE +/- 0.0246, N = 3 8.6225 8.6853 9.5956
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Very Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 30 60 90 120 150 SE +/- 1.43, N = 7 SE +/- 1.58, N = 3 SE +/- 1.35, N = 3 155.33 139.94 139.82 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 28.52 28.61 31.68
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 FPS, More Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 3K 6K 9K 12K 15K SE +/- 12.91, N = 3 SE +/- 10.06, N = 3 SE +/- 6.22, N = 3 15347.17 15213.23 13817.99 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 30 60 90 120 150 SE +/- 0.22, N = 3 SE +/- 0.75, N = 3 SE +/- 0.56, N = 3 122.33 122.38 135.85
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 90 180 270 360 450 SE +/- 0.24, N = 3 SE +/- 0.82, N = 3 SE +/- 0.34, N = 3 420.33 418.88 378.53
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Medium Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 16 32 48 64 80 SE +/- 0.74, N = 3 SE +/- 0.64, N = 3 SE +/- 0.72, N = 15 70.72 66.27 63.70 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 0.3893 0.7786 1.1679 1.5572 1.9465 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.56 1.57 1.73 MIN: 0.92 / MAX: 9.52 MIN: 0.75 / MAX: 9.53 MIN: 0.88 / MAX: 18.06 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 30 60 90 120 150 SE +/- 0.52, N = 3 SE +/- 1.12, N = 3 SE +/- 0.19, N = 3 124.20 124.27 137.66
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 20 40 60 80 100 SE +/- 0.86, N = 3 SE +/- 0.44, N = 3 SE +/- 0.10, N = 3 96.41 96.33 87.00
Blender OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: Fishy Cat - Compute: CPU-Only Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 20 40 60 80 100 SE +/- 0.28, N = 3 SE +/- 0.09, N = 3 SE +/- 0.14, N = 3 81.12 81.66 89.90
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 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-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 4K Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 1.224 2.448 3.672 4.896 6.12 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 5.44 5.41 4.91 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
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 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 30 60 90 120 150 SE +/- 0.25, N = 3 SE +/- 0.17, N = 3 SE +/- 0.54, N = 3 133.02 134.10 147.34 MIN: 85.74 / MAX: 349.01 MIN: 95.56 / MAX: 396.86 MIN: 90.36 / MAX: 765.94 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 13 26 39 52 65 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.20, N = 3 60.06 59.60 54.23 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 3K 6K 9K 12K 15K SE +/- 20.15, N = 3 SE +/- 15.31, N = 3 SE +/- 18.74, N = 3 14053.46 13875.03 12689.87 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 0.423 0.846 1.269 1.692 2.115 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.70 1.72 1.88 MIN: 1.05 / MAX: 10.31 MIN: 0.82 / MAX: 10.33 MIN: 1.01 / MAX: 11.34 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 14 28 42 56 70 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 54.84 54.86 60.63
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 50 100 150 200 250 SE +/- 0.31, N = 3 SE +/- 0.35, N = 3 SE +/- 0.23, N = 3 218.69 218.53 197.83
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 50 100 150 200 250 SE +/- 0.44, N = 3 SE +/- 0.14, N = 3 SE +/- 0.13, N = 3 218.50 217.01 197.83
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 14 28 42 56 70 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 54.89 55.28 60.62
x265 This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.33, N = 5 SE +/- 0.31, N = 3 32.45 32.24 29.39 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
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: 200 Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 40K 80K 120K 160K 200K SE +/- 2169.07, N = 4 SE +/- 628.65, N = 3 SE +/- 308.61, N = 3 195256.70 192417.90 176902.95 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Blender OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.6 Blend File: BMW27 - Compute: CPU-Only Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 14 28 42 56 70 SE +/- 0.29, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 58.80 59.09 64.84
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 Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 0.306 0.612 0.918 1.224 1.53 SE +/- 0.0061, N = 3 SE +/- 0.0067, N = 3 SE +/- 0.0158, N = 3 1.3600 1.3386 1.2359 1. (CXX) g++ options: -O3 -flto -pthread
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 15.62 15.52 14.25
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 FPS, More Is Better OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 150 300 450 600 750 SE +/- 2.95, N = 3 SE +/- 2.64, N = 3 SE +/- 2.43, N = 3 690.48 666.94 630.92 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 11.57 11.91 12.66 MIN: 7.62 / MAX: 58.68 MIN: 7.82 / MAX: 60.4 MIN: 7.52 / MAX: 102.87 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
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 Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 15.75 15.59 14.39
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 Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 2 4 6 8 10 SE +/- 0.100, N = 3 SE +/- 0.033, N = 3 SE +/- 0.077, N = 4 7.607 7.594 6.958 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 200 400 600 800 1000 SE +/- 1.66, N = 3 SE +/- 1.81, N = 3 SE +/- 3.87, N = 3 759.10 763.82 824.97
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 200 400 600 800 1000 SE +/- 2.06, N = 3 SE +/- 0.98, N = 3 SE +/- 0.81, N = 3 765.24 769.87 828.76
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 3.7 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 4K Linux 6.4.14 Linux 6.5.1 Linux 6.6-rc1 20 40 60 80 100 SE +/- 1.04, N = 15 SE +/- 1.42, N = 15 SE +/- 1.05, N = 15 111.35 108.21 103.07 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Medium Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 12 24 36 48 60 SE +/- 0.27, N = 3 SE +/- 0.57, N = 4 SE +/- 0.40, N = 8 51.37 50.42 48.34
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 60 120 180 240 300 SE +/- 1.44, N = 3 SE +/- 2.08, N = 3 SE +/- 2.57, N = 5 260.80 246.36 246.33 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Selenium OpenBenchmarking.org Geometric Mean, More Is Better Selenium Benchmark: Octane - Browser: Google Chrome Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 20K 40K 60K 80K 100K SE +/- 738.74, N = 3 SE +/- 682.73, N = 3 SE +/- 1444.69, N = 15 114315 113361 108124 1. chrome 116.0.5845.179
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 Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 0.2093 0.4186 0.6279 0.8372 1.0465 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 6 0.93 0.93 0.88 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
Selenium OpenBenchmarking.org Geometric Mean, More Is Better Selenium Benchmark: Octane - Browser: Firefox Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 12K 24K 36K 48K 60K SE +/- 67.84, N = 3 SE +/- 45.39, N = 3 SE +/- 732.21, N = 3 58047 57866 55011 1. firefox 117.0
OCRMyPDF OCRMyPDF is an optical character recognition (OCR) text layer to scanned PDF files, producing new PDFs with the text now selectable/searchable/copy-paste capable. OCRMyPDF leverages the Tesseract OCR engine and is written in Python. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 13.4.0+dfsg Processing 60 Page PDF Document Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 3 6 9 12 15 SE +/- 0.130, N = 3 SE +/- 0.118, N = 15 SE +/- 0.091, N = 3 9.179 9.244 9.652
Redis Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: LPUSH - Parallel Connections: 50 Linux 6.6-rc1 Linux 6.5.1 Linux 6.4.14 800K 1600K 2400K 3200K 4000K SE +/- 36644.94, N = 6 SE +/- 8153.44, N = 3 SE +/- 26791.23, N = 3 3842480.21 3712129.75 3673940.00 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Selenium OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Firefox Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 50 100 150 200 250 SE +/- 3.14, N = 3 SE +/- 0.78, N = 3 SE +/- 1.94, N = 3 243.41 241.30 233.77 1. firefox 117.0
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.8.1 Test: Masskrug - Acceleration: CPU-only Linux 6.5.1 Linux 6.6-rc1 Linux 6.4.14 0.4689 0.9378 1.4067 1.8756 2.3445 SE +/- 0.012, N = 3 SE +/- 0.027, N = 15 SE +/- 0.011, N = 3 2.002 2.070 2.084
Selenium OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Google Chrome Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 80 160 240 320 400 SE +/- 0.69, N = 3 SE +/- 1.73, N = 3 SE +/- 5.21, N = 3 382.75 377.06 367.90 1. chrome 116.0.5845.179
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 Linux 6.5.1 Linux 6.6-rc1 Linux 6.4.14 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 15.02 14.82 14.49 1. (CXX) g++ options: -O3 -flto -pthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 4K Linux 6.4.14 Linux 6.5.1 Linux 6.6-rc1 40 80 120 160 200 SE +/- 0.07, N = 3 SE +/- 1.93, N = 3 SE +/- 1.97, N = 5 186.33 180.88 179.80 1. (CXX) g++ options: -fPIE -mavx512vl -std=gnu++11
GIMP GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.30 Test: rotate Linux 6.5.1 Linux 6.6-rc1 Linux 6.4.14 3 6 9 12 15 SE +/- 0.021, N = 3 SE +/- 0.031, N = 3 SE +/- 0.005, N = 3 9.467 9.696 9.806
GIMP GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.30 Test: auto-levels Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 10.27 10.56 10.61
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 130 260 390 520 650 SE +/- 4.68, N = 3 SE +/- 6.10, N = 3 SE +/- 6.61, N = 3 582.35 582.21 564.99 1. (CXX) g++ options: -fPIE -mavx512vl -std=gnu++11
Selenium OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM collisionDetection - Browser: Google Chrome Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 2.35, N = 3 SE +/- 2.03, N = 15 176.38 179.61 181.58 1. chrome 116.0.5845.179
GIMP GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.30 Test: unsharp-mask Linux 6.5.1 Linux 6.6-rc1 Linux 6.4.14 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 11.91 12.22 12.25
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.30 Test: resize Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 3 6 9 12 15 SE +/- 0.12, N = 7 SE +/- 0.07, N = 3 SE +/- 0.13, N = 6 12.84 12.94 13.19
x265 This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 20 40 60 80 100 SE +/- 0.42, N = 3 SE +/- 0.12, N = 3 SE +/- 0.72, N = 13 86.16 85.24 84.27 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
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 3.7 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 20 40 60 80 100 SE +/- 1.44, N = 3 SE +/- 0.78, N = 3 SE +/- 0.57, N = 3 103.95 101.78 101.69 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Selenium OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Firefox Linux 6.5.1 Linux 6.6-rc1 Linux 6.4.14 110 220 330 440 550 SE +/- 3.30, N = 3 SE +/- 4.44, N = 3 SE +/- 1.33, N = 3 505.1 508.1 513.9 1. firefox 117.0
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 110 220 330 440 550 SE +/- 4.35, N = 3 SE +/- 2.62, N = 3 SE +/- 5.03, N = 6 518.13 511.30 509.36 1. (CXX) g++ options: -fPIE -mavx512vl -std=gnu++11
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 Linux 6.5.1 Linux 6.6-rc1 Linux 6.4.14 30 60 90 120 150 SE +/- 0.40, N = 3 SE +/- 0.56, N = 3 SE +/- 0.19, N = 3 122.12 120.49 120.09 1. (CXX) g++ options: -O3 -flto -pthread
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.8.1 Test: Server Room - Acceleration: CPU-only Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 0.3506 0.7012 1.0518 1.4024 1.753 SE +/- 0.010, N = 3 SE +/- 0.001, N = 3 SE +/- 0.008, N = 3 1.535 1.548 1.558
Selenium OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Google Chrome Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 80 160 240 320 400 SE +/- 0.84, N = 3 SE +/- 1.85, N = 3 SE +/- 1.50, N = 3 351.0 354.2 355.3 1. chrome 116.0.5845.179
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: Kostya Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 1.2083 2.4166 3.6249 4.8332 6.0415 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 5.37 5.31 5.31 1. (CXX) g++ options: -O3
Selenium OpenBenchmarking.org Runs Per Minute, More Is Better Selenium Benchmark: Speedometer - Browser: Google Chrome Linux 6.4.14 Linux 6.5.1 Linux 6.6-rc1 100 200 300 400 500 SE +/- 2.60, N = 3 SE +/- 1.20, N = 3 SE +/- 0.58, N = 3 441 440 437 1. chrome 116.0.5845.179
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 Linux 6.5.1 Linux 6.6-rc1 Linux 6.4.14 70 140 210 280 350 SE +/- 0.33, N = 3 SE +/- 1.41, N = 3 SE +/- 1.06, N = 3 339.55 337.76 336.83 1. (CXX) g++ options: -O3 -flto -pthread
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Linux 6.6-rc1 Linux 6.5.1 Linux 6.4.14 100 200 300 400 500 SE +/- 0.58, N = 3 SE +/- 1.00, N = 3 SE +/- 1.67, N = 3 453 454 456
Selenium OpenBenchmarking.org Runs Per Minute, More Is Better Selenium Benchmark: Speedometer - Browser: Firefox Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 90 180 270 360 450 SE +/- 1.76, N = 3 SE +/- 2.08, N = 3 SE +/- 3.06, N = 3 400 399 398 1. firefox 117.0
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 Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 0.5288 1.0576 1.5864 2.1152 2.644 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.35 2.34 2.34 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
Selenium OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Firefox Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 500 1000 1500 2000 2500 SE +/- 2.03, N = 3 SE +/- 2.33, N = 3 SE +/- 4.16, N = 3 2158 2161 2164 1. firefox 117.0
OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM collisionDetection - Browser: Firefox Linux 6.4.14 Linux 6.5.1 Linux 6.6-rc1 50 100 150 200 250 SE +/- 0.19, N = 3 SE +/- 0.42, N = 3 SE +/- 0.57, N = 3 222.0 222.3 222.6 1. firefox 117.0
Git This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 31.99 32.05 32.06 1. git version 2.34.1
libjpeg-turbo tjbench tjbench is a JPEG decompression/compression benchmark that is part of libjpeg-turbo, a JPEG image codec library optimized for SIMD instructions on modern CPU architectures. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 2.1.0 Test: Decompression Throughput Linux 6.6-rc1 Linux 6.5.1 Linux 6.4.14 70 140 210 280 350 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.49, N = 3 309.55 309.22 308.83 1. (CC) gcc options: -O3 -rdynamic
Selenium OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM imageConvolute - Browser: Google Chrome Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 14.60 14.61 14.63 1. chrome 116.0.5845.179
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, Highest Compression Linux 6.5.1 Linux 6.6-rc1 Linux 6.4.14 1.1633 2.3266 3.4899 4.6532 5.8165 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 5.17 5.16 5.16 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 6.84 6.84 6.83 1. (CXX) g++ options: -O3
Selenium OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Google Chrome Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 500 1000 1500 2000 2500 SE +/- 5.21, N = 3 SE +/- 5.51, N = 3 SE +/- 3.28, N = 3 2354 2355 2357 1. chrome 116.0.5845.179
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet Linux 6.6-rc1 Linux 6.5.1 Linux 6.4.14 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 7.88 7.88 7.87 1. (CXX) g++ options: -O3
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: DistinctUserID Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 8.10 8.10 8.09 1. (CXX) g++ options: -O3
Selenium OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM imageConvolute - Browser: Firefox Linux 6.4.14 Linux 6.5.1 Linux 6.6-rc1 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 14.9 14.9 14.9 1. firefox 117.0
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom Linux 6.6-rc1 Linux 6.5.1 Linux 6.4.14 0.4298 0.8596 1.2894 1.7192 2.149 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.91 1.91 1.91 1. (CXX) g++ options: -O3
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 400K 800K 1200K 1600K 2000K SE +/- 4409.66, N = 3 SE +/- 14714.08, N = 7 SE +/- 25349.46, N = 15 1641215 1608855 1473031
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.8.1 Test: Server Rack - Acceleration: CPU-only Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 0.0239 0.0478 0.0717 0.0956 0.1195 SE +/- 0.001, N = 15 SE +/- 0.005, N = 12 SE +/- 0.006, N = 15 0.094 0.102 0.106
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.8.1 Test: Boat - Acceleration: CPU-only Linux 6.5.1 Linux 6.6-rc1 Linux 6.4.14 0.4671 0.9342 1.4013 1.8684 2.3355 SE +/- 0.005, N = 3 SE +/- 0.060, N = 15 SE +/- 0.067, N = 12 1.944 2.057 2.076
Redis Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SADD - Parallel Connections: 50 Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 1000K 2000K 3000K 4000K 5000K SE +/- 52928.01, N = 5 SE +/- 43633.94, N = 15 SE +/- 107778.44, N = 12 4825673.10 4814183.70 4320145.38 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 50 Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 900K 1800K 2700K 3600K 4500K SE +/- 12864.15, N = 3 SE +/- 76521.21, N = 12 SE +/- 89650.69, N = 15 4341185.00 4207756.96 4091086.13 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6, Lossless Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 2 4 6 8 10 SE +/- 0.032, N = 3 SE +/- 0.010, N = 3 SE +/- 0.109, N = 15 5.336 5.378 6.081 1. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6 Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 0.8478 1.6956 2.5434 3.3912 4.239 SE +/- 0.099, N = 15 SE +/- 0.137, N = 15 SE +/- 0.106, N = 15 3.617 3.768 3.768 1. (CXX) g++ options: -O3 -fPIC -lm
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 40 80 120 160 200 SE +/- 1.55, N = 3 SE +/- 4.35, N = 12 SE +/- 4.92, N = 15 188.74 173.19 162.10
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 30 60 90 120 150 SE +/- 2.26, N = 15 SE +/- 3.44, N = 12 SE +/- 3.52, N = 15 152.80 150.17 141.05
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 30 60 90 120 150 SE +/- 0.29, N = 3 SE +/- 2.36, N = 15 SE +/- 0.46, N = 3 151.72 138.54 123.50
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 90 180 270 360 450 SE +/- 17.13, N = 15 SE +/- 16.35, N = 15 SE +/- 21.18, N = 15 400.14 398.57 368.11 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.5.1 Linux 6.4.14 110 220 330 440 550 SE +/- 16.81, N = 15 SE +/- 28.01, N = 12 SE +/- 29.38, N = 15 494.53 460.39 453.70 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 30 60 90 120 150 SE +/- 0.52, N = 3 SE +/- 0.87, N = 3 SE +/- 2.01, N = 15 149.07 106.17 100.67 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 110 220 330 440 550 SE +/- 17.31, N = 15 SE +/- 22.20, N = 14 SE +/- 25.02, N = 15 486.87 457.51 456.32 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 4K Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 30 60 90 120 150 SE +/- 2.09, N = 15 SE +/- 0.14, N = 3 SE +/- 1.68, N = 15 135.00 105.29 96.35 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 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-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 140 280 420 560 700 SE +/- 1.32, N = 3 SE +/- 20.19, N = 12 SE +/- 35.17, N = 15 669.40 635.86 583.51 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 70 140 210 280 350 SE +/- 10.18, N = 15 SE +/- 12.48, N = 15 SE +/- 13.20, N = 15 301.06 284.70 284.51 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 4K Linux 6.4.14 Linux 6.5.1 Linux 6.6-rc1 40 80 120 160 200 SE +/- 0.53, N = 3 SE +/- 2.38, N = 15 SE +/- 0.74, N = 15 195.12 127.68 123.90 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 4K Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 20 40 60 80 100 SE +/- 1.81, N = 15 SE +/- 1.38, N = 15 SE +/- 1.12, N = 3 96.82 96.09 89.44 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 30 60 90 120 150 SE +/- 1.08, N = 15 SE +/- 0.36, N = 3 SE +/- 2.44, N = 15 132.92 132.89 128.52 1. (CXX) g++ options: -fPIE -mavx512vl -std=gnu++11
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.7 Encoder Mode: Preset 12 - Input: Bosphorus 4K Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 40 80 120 160 200 SE +/- 0.90, N = 3 SE +/- 4.24, N = 12 SE +/- 4.12, N = 15 178.67 176.67 171.52 1. (CXX) g++ options: -fPIE -mavx512vl -std=gnu++11
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Super Fast Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 50 100 150 200 250 SE +/- 1.49, N = 3 SE +/- 4.79, N = 12 SE +/- 5.50, N = 15 209.30 194.68 186.74 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 3.7 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 1080p Linux 6.5.1 Linux 6.6-rc1 Linux 6.4.14 70 140 210 280 350 SE +/- 2.99, N = 15 SE +/- 2.88, N = 6 SE +/- 4.63, N = 15 305.18 300.50 295.92 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 60 120 180 240 300 SE +/- 4.90, N = 15 SE +/- 4.34, N = 15 SE +/- 4.09, N = 15 296.42 295.13 285.01 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.5.1 Linux 6.4.14 60 120 180 240 300 SE +/- 3.05, N = 15 SE +/- 5.48, N = 15 SE +/- 4.34, N = 15 296.54 290.39 282.35 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.4.14 Linux 6.5.1 60 120 180 240 300 SE +/- 2.62, N = 3 SE +/- 4.17, N = 15 SE +/- 3.79, N = 15 283.47 267.56 263.42 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p Linux 6.6-rc1 Linux 6.5.1 Linux 6.4.14 50 100 150 200 250 SE +/- 3.81, N = 15 SE +/- 3.60, N = 15 SE +/- 3.83, N = 15 247.18 242.99 229.52 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.7 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Linux 6.4.14 Linux 6.5.1 Linux 6.6-rc1 20 40 60 80 100 SE +/- 2.01, N = 14 SE +/- 1.63, N = 14 SE +/- 1.29, N = 15 96.89 88.81 82.99 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: HMAC-SHA512 Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 15M 30M 45M 60M 75M SE +/- 444919.97, N = 3 SE +/- 4941602.26, N = 12 SE +/- 2837291.02, N = 12 69673333 63281250 57671917 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: Blowfish Linux 6.4.14 Linux 6.6-rc1 Linux 6.5.1 9K 18K 27K 36K 45K SE +/- 14.62, N = 3 SE +/- 809.89, N = 12 SE +/- 463.35, N = 15 39743 37496 31828 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
WireGuard + Linux Networking Stack Stress Test This is a benchmark of the WireGuard secure VPN tunnel and Linux networking stack stress test. The test runs on the local host but does require root permissions to run. The way it works is it creates three namespaces. ns0 has a loopback device. ns1 and ns2 each have wireguard devices. Those two wireguard devices send traffic through the loopback device of ns0. The end result of this is that tests wind up testing encryption and decryption at the same time -- a pretty CPU and scheduler-heavy workflow. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better WireGuard + Linux Networking Stack Stress Test Linux 6.5.1 Linux 6.4.14 Linux 6.6-rc1 30 60 90 120 150 SE +/- 1.02, N = 3 SE +/- 0.27, N = 3 SE +/- 4.06, N = 12 95.08 95.21 112.56
Linux 6.4.14 Processor: Intel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0812 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 7700S/7600S/7600M XT 8GB (1940/1124MHz), Audio: Realtek ALC897, Monitor: ASUS VP28U
OS: Ubuntu 22.04, Kernel: 6.4.14-060414-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.3~git2308070600.777734~oibaf~j (git-7777349 2023-08-07 jammy-oibaf-ppa) (LLVM 15.0.7 DRM 3.52), OpenCL: OpenCL 1.1 Mesa 23.3~git2308020600.4de7e0~oibaf~j (git-4de7e00 2023-08-02 jammy-oibaf-ppa) + OpenCL 3.0, Vulkan: 1.3.258, Compiler: GCC 11.4.0 + Clang 16.0.6 + LLVM 16.0.6, 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-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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: 0x119 - Thermald 2.4.9Python Notes: Python 3.10.12Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 September 2023 11:34 by user pts.
Linux 6.5.1 Processor: Intel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0812 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 7700S/7600S/7600M XT 8GB (1940/1124MHz), Audio: Realtek ALC897, Monitor: ASUS VP28U
OS: Ubuntu 22.04, Kernel: 6.5.1-060501-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.3~git2308070600.777734~oibaf~j (git-7777349 2023-08-07 jammy-oibaf-ppa) (LLVM 15.0.7 DRM 3.54), OpenCL: OpenCL 1.1 Mesa 23.3~git2308020600.4de7e0~oibaf~j (git-4de7e00 2023-08-02 jammy-oibaf-ppa) + OpenCL 3.0, Vulkan: 1.3.258, Compiler: GCC 11.4.0 + Clang 16.0.6 + LLVM 16.0.6, 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-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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: 0x119 - Thermald 2.4.9Python Notes: Python 3.10.12Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 September 2023 17:45 by user pts.
Linux 6.6-rc1 Processor: Intel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads), Motherboard: ASUS PRIME Z790-P WIFI (0812 BIOS), Chipset: Intel Device 7a27, Memory: 32GB, Disk: 1000GB Western Digital WDS100T1X0E-00AFY0, Graphics: AMD Radeon RX 7700S/7600S/7600M XT 8GB (1940/1124MHz), Audio: Realtek ALC897, Monitor: ASUS VP28U
OS: Ubuntu 22.04, Kernel: 6.6.0-060600rc1-generic (x86_64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.4 + Wayland, OpenGL: 4.6 Mesa 23.3~git2308070600.777734~oibaf~j (git-7777349 2023-08-07 jammy-oibaf-ppa) (LLVM 15.0.7 DRM 3.54), OpenCL: OpenCL 1.1 Mesa 23.3~git2308020600.4de7e0~oibaf~j (git-4de7e00 2023-08-02 jammy-oibaf-ppa) + OpenCL 3.0, Vulkan: 1.3.258, Compiler: GCC 11.4.0 + Clang 16.0.6 + LLVM 16.0.6, 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-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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: 0x119 - Thermald 2.4.9Python Notes: Python 3.10.12Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 11 September 2023 10:15 by user pts.