Benchmarks by Michael Larabel for a future article.
Linux 6.6 Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS), Chipset: AMD Starship/Matisse, Memory: 4 x 32GB DDR4-3000MT/s CMK64GX4M2D3000C16, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200
OS: Pop 22.04, Kernel: 6.6.6-76060606-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 23.3.2-1pop0~1704238321~22.04~36f1d0e (LLVM 15.0.7 DRM 3.54), Vulkan: 1.3.267, Compiler: GCC 11.4.0, 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-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: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x830107aPython 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: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Linux 6.8 Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS), Chipset: AMD Starship/Matisse, Memory: 4 x 32GB DDR4-3000MT/s CMK64GX4M2D3000C16, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GBAudio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200
OS: Pop 22.04, Kernel: 6.8.0-76060800daily20240311-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 24.0.3-1pop1~1711635559~22.04~7a9f319 (LLVM 15.0.7 DRM 3.57), Vulkan: 1.3.274, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3840x2160
Graph500 This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org bfs max_TEPS, More Is Better Graph500 3.0 Scale: 26 Linux 6.6 Linux 6.8 120M 240M 360M 480M 600M 539379000 541789000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org bfs median_TEPS, More Is Better Graph500 3.0 Scale: 26 Linux 6.6 Linux 6.8 110M 220M 330M 440M 550M 533558000 535202000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA256 Linux 6.8 Linux 6.6 13000M 26000M 39000M 52000M 65000M SE +/- 119311058.77, N = 3 SE +/- 85875563.68, N = 3 62255778377 62279387347 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA512 Linux 6.8 Linux 6.6 5000M 10000M 15000M 20000M 25000M SE +/- 35361661.51, N = 3 SE +/- 10966945.92, N = 3 22401412077 22766572557 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20 Linux 6.8 Linux 6.6 40000M 80000M 120000M 160000M 200000M SE +/- 59010640.14, N = 3 SE +/- 40917174.40, N = 3 196096058490 199904856290 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-128-GCM Linux 6.8 Linux 6.6 50000M 100000M 150000M 200000M 250000M SE +/- 184834186.21, N = 3 SE +/- 69181218.89, N = 3 221088305973 226180667070 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-256-GCM Linux 6.8 Linux 6.6 40000M 80000M 120000M 160000M 200000M SE +/- 98406556.77, N = 3 SE +/- 284249597.90, N = 3 202616674350 207429799297 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20-Poly1305 Linux 6.8 Linux 6.6 30000M 60000M 90000M 120000M 150000M SE +/- 143226146.09, N = 3 SE +/- 175506084.92, N = 3 126331970173 128107845040 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
FFmpeg This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx264 - Scenario: Live Linux 6.6 Linux 6.8 40 80 120 160 200 SE +/- 0.31, N = 3 SE +/- 0.36, N = 3 179.69 182.30 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Live Linux 6.6 Linux 6.8 16 32 48 64 80 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 66.35 72.59 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx264 - Scenario: Upload Linux 6.6 Linux 6.8 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 11.78 11.78 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Upload Linux 6.6 Linux 6.8 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 13.03 14.82 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx264 - Scenario: Platform Linux 6.6 Linux 6.8 10 20 30 40 50 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 44.08 44.08 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Platform Linux 6.6 Linux 6.8 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 27.28 30.85 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx264 - Scenario: Video On Demand Linux 6.6 Linux 6.8 10 20 30 40 50 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 43.90 43.97 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Video On Demand Linux 6.6 Linux 6.8 7 14 21 28 35 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 27.21 30.94 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
dav1d Dav1d is an open-source, speedy AV1 video decoder supporting modern SIMD CPU features. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better dav1d 1.4 Video Input: Chimera 1080p Linux 6.6 Linux 6.8 80 160 240 320 400 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 375.32 375.76 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 1.4 Video Input: Summer Nature 4K Linux 6.8 Linux 6.6 50 100 150 200 250 SE +/- 0.83, N = 3 SE +/- 0.10, N = 3 205.11 205.48 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 1.4 Video Input: Summer Nature 1080p Linux 6.8 Linux 6.6 110 220 330 440 550 SE +/- 0.43, N = 3 SE +/- 0.66, N = 3 482.94 487.05 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 1.4 Video Input: Chimera 1080p 10-bit Linux 6.6 Linux 6.8 80 160 240 320 400 SE +/- 0.10, N = 3 SE +/- 0.34, N = 3 351.91 352.99 1. (CC) gcc options: -pthread
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 2024.0 Model: Face Detection FP16 - Device: CPU Linux 6.8 Linux 6.6 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 11.21 11.30 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU Linux 6.8 Linux 6.6 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 75.15 77.56 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU Linux 6.8 Linux 6.6 20 40 60 80 100 SE +/- 0.20, N = 3 SE +/- 0.10, N = 3 74.83 77.34 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU Linux 6.8 Linux 6.6 110 220 330 440 550 SE +/- 0.69, N = 3 SE +/- 0.07, N = 3 496.91 500.83 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU Linux 6.8 Linux 6.6 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 17.72 17.73 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU Linux 6.8 Linux 6.6 700 1400 2100 2800 3500 SE +/- 33.28, N = 3 SE +/- 19.77, N = 3 3076.01 3148.29 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU Linux 6.8 Linux 6.6 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.10, N = 3 85.52 85.91 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU Linux 6.6 Linux 6.8 300 600 900 1200 1500 SE +/- 2.14, N = 3 SE +/- 0.03, N = 3 1367.62 1369.87 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU Linux 6.8 Linux 6.6 200 400 600 800 1000 SE +/- 0.37, N = 3 SE +/- 2.37, N = 3 1152.64 1153.59 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU Linux 6.8 Linux 6.6 900 1800 2700 3600 4500 SE +/- 13.32, N = 3 SE +/- 9.09, N = 3 4252.58 4295.92 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU Linux 6.6 Linux 6.8 130 260 390 520 650 SE +/- 1.47, N = 3 SE +/- 2.28, N = 3 608.90 611.36 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU Linux 6.8 Linux 6.6 30 60 90 120 150 SE +/- 0.85, N = 3 SE +/- 0.68, N = 3 118.13 118.25 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU Linux 6.8 Linux 6.6 400 800 1200 1600 2000 SE +/- 2.70, N = 3 SE +/- 1.40, N = 3 1761.73 1764.44 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU Linux 6.6 Linux 6.8 300 600 900 1200 1500 SE +/- 0.74, N = 3 SE +/- 4.44, N = 3 1491.58 1516.00 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU Linux 6.6 Linux 6.8 300 600 900 1200 1500 SE +/- 5.06, N = 3 SE +/- 2.39, N = 3 1352.53 1365.55 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU Linux 6.8 Linux 6.6 110 220 330 440 550 SE +/- 0.54, N = 3 SE +/- 0.72, N = 3 523.96 525.95 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU Linux 6.8 Linux 6.6 400 800 1200 1600 2000 SE +/- 2.70, N = 3 SE +/- 0.95, N = 3 1838.91 1850.83 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Linux 6.8 Linux 6.6 7K 14K 21K 28K 35K SE +/- 175.08, N = 3 SE +/- 89.06, N = 3 32552.24 32704.42 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU Linux 6.6 Linux 6.8 130 260 390 520 650 SE +/- 0.41, N = 3 SE +/- 1.48, N = 3 590.41 590.70 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Linux 6.6 Linux 6.8 10K 20K 30K 40K 50K SE +/- 18.81, N = 3 SE +/- 49.88, N = 3 44647.97 45877.92 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Linux 6.6 Linux 6.8 0.099 0.198 0.297 0.396 0.495 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.41 0.44 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Linux 6.6 Linux 6.8 2 4 6 8 10 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 7.85 8.69 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Linux 6.6 Linux 6.8 10 20 30 40 50 SE +/- 0.18, N = 3 SE +/- 0.47, N = 15 43.21 44.64 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K Linux 6.6 Linux 6.8 4 8 12 16 20 SE +/- 0.24, N = 3 SE +/- 0.18, N = 6 16.79 17.60 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Linux 6.6 Linux 6.8 10 20 30 40 50 SE +/- 0.25, N = 3 SE +/- 0.13, N = 3 41.34 43.58 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Linux 6.6 Linux 6.8 11 22 33 44 55 SE +/- 0.49, N = 15 SE +/- 0.31, N = 3 45.13 47.83 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Linux 6.6 Linux 6.8 11 22 33 44 55 SE +/- 0.06, N = 3 SE +/- 0.27, N = 3 47.78 49.61 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 4K Linux 6.6 Linux 6.8 11 22 33 44 55 SE +/- 0.51, N = 15 SE +/- 0.49, N = 3 46.21 48.61 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 0.2813 0.5626 0.8439 1.1252 1.4065 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.19 1.25 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 16.28 17.72 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 20 40 60 80 100 SE +/- 0.22, N = 3 SE +/- 0.82, N = 15 87.71 93.28 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 9 18 27 36 45 SE +/- 0.33, N = 8 SE +/- 0.58, N = 3 39.08 41.19 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 20 40 60 80 100 SE +/- 0.88, N = 3 SE +/- 0.97, N = 15 88.99 95.04 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 20 40 60 80 100 SE +/- 0.90, N = 3 SE +/- 1.26, N = 15 96.10 96.60 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 20 40 60 80 100 SE +/- 0.69, N = 3 SE +/- 0.78, N = 15 93.56 99.92 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.9 Encoder Mode: Speed 11 Realtime - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 20 40 60 80 100 SE +/- 0.27, N = 3 SE +/- 1.02, N = 15 93.80 99.66 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K Linux 6.6 Linux 6.8 1.1358 2.2716 3.4074 4.5432 5.679 SE +/- 0.014, N = 3 SE +/- 0.008, N = 3 4.610 5.048 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Linux 6.6 Linux 6.8 11 22 33 44 55 SE +/- 0.13, N = 3 SE +/- 0.22, N = 3 44.30 46.83 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Linux 6.6 Linux 6.8 20 40 60 80 100 SE +/- 0.92, N = 3 SE +/- 0.81, N = 3 102.50 104.23 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K Linux 6.6 Linux 6.8 20 40 60 80 100 SE +/- 1.04, N = 3 SE +/- 1.12, N = 3 102.53 106.11 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 12.28 13.53 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.53, N = 3 88.16 90.42 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Linux 6.6 Linux 6.8 70 140 210 280 350 SE +/- 2.48, N = 3 SE +/- 1.38, N = 3 308.17 311.07 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Linux 6.8 Linux 6.6 80 160 240 320 400 SE +/- 0.40, N = 3 SE +/- 0.46, N = 3 373.13 373.79 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
uvg266 OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.8.0 Video Input: Bosphorus 4K - Video Preset: Slow Linux 6.6 Linux 6.8 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 9.79 10.87
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.8.0 Video Input: Bosphorus 4K - Video Preset: Medium Linux 6.6 Linux 6.8 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 10.97 12.18
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.8.0 Video Input: Bosphorus 1080p - Video Preset: Slow Linux 6.6 Linux 6.8 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 33.21 33.68
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.8.0 Video Input: Bosphorus 1080p - Video Preset: Medium Linux 6.6 Linux 6.8 9 18 27 36 45 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 36.70 37.20
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.8.0 Video Input: Bosphorus 4K - Video Preset: Very Fast Linux 6.6 Linux 6.8 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 31.84 35.17
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.8.0 Video Input: Bosphorus 4K - Video Preset: Super Fast Linux 6.6 Linux 6.8 8 16 24 32 40 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 33.35 35.75
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.8.0 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Linux 6.6 Linux 6.8 9 18 27 36 45 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 35.96 38.90
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.8.0 Video Input: Bosphorus 1080p - Video Preset: Very Fast Linux 6.6 Linux 6.8 30 60 90 120 150 SE +/- 0.03, N = 3 SE +/- 0.50, N = 3 112.86 115.03
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.8.0 Video Input: Bosphorus 1080p - Video Preset: Super Fast Linux 6.6 Linux 6.8 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.78, N = 3 126.57 129.52
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.8.0 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Linux 6.6 Linux 6.8 30 60 90 120 150 SE +/- 0.27, N = 3 SE +/- 0.57, N = 3 143.34 146.79
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 1.11 Video Input: Bosphorus 4K - Video Preset: Fast Linux 6.6 Linux 6.8 1.1482 2.2964 3.4446 4.5928 5.741 SE +/- 0.011, N = 3 SE +/- 0.064, N = 3 4.849 5.103 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Faster Linux 6.6 Linux 6.8 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 11.58 11.88 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 1080p - Video Preset: Fast Linux 6.6 Linux 6.8 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.14, N = 3 12.32 13.56 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 1080p - Video Preset: Faster Linux 6.6 Linux 6.8 7 14 21 28 35 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 28.72 30.24 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
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 3.6 Video Input: Bosphorus 4K Linux 6.6 Linux 6.8 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 22.35 25.44 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.6 Video Input: Bosphorus 1080p Linux 6.6 Linux 6.8 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 47.04 49.27 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 Linux 6.6 Linux 6.8 1.2398 2.4796 3.7194 4.9592 6.199 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 5.45 5.51
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/ao/real_time Linux 6.8 Linux 6.6 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 14.47 14.53
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/scivis/real_time Linux 6.8 Linux 6.6 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 14.25 14.29
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/pathtracer/real_time Linux 6.8 Linux 6.6 30 60 90 120 150 SE +/- 0.27, N = 3 SE +/- 0.45, N = 3 126.44 127.56
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Linux 6.8 Linux 6.6 2 4 6 8 10 SE +/- 0.03882, N = 3 SE +/- 0.01048, N = 3 6.53586 7.13171
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time Linux 6.8 Linux 6.6 2 4 6 8 10 SE +/- 0.01553, N = 3 SE +/- 0.00782, N = 3 6.18207 6.78016
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Linux 6.8 Linux 6.6 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 10.76 10.83
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Swirl Linux 6.8 Linux 6.6 80 160 240 320 400 SE +/- 0.88, N = 3 SE +/- 0.88, N = 3 366 367 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -llzma -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Rotate Linux 6.8 Linux 6.6 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 105 106 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -llzma -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Sharpen Linux 6.8 Linux 6.6 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 153 154 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -llzma -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Enhanced Linux 6.8 Linux 6.6 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 193 194 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -llzma -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Resizing Linux 6.8 Linux 6.6 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 116 118 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -llzma -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Noise-Gaussian Linux 6.8 Linux 6.6 30 60 90 120 150 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 129 133 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -llzma -lz -lm -lpthread -lgomp
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: HWB Color Space Linux 6.8 Linux 6.6 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 181 188 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -llzma -lz -lm -lpthread -lgomp
srsRAN Project srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project 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 Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Total Linux 6.6 Linux 6.8 2K 4K 6K 8K 10K SE +/- 20.83, N = 3 SE +/- 26.02, N = 3 9560.7 10095.4 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Total Linux 6.6 Linux 6.8 600 1200 1800 2400 3000 SE +/- 21.32, N = 9 SE +/- 24.53, N = 15 2582.6 2621.3 MIN: 1453.8 / MAX: 2649.8 MIN: 1454.6 / MAX: 2769.4 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Thread Linux 6.8 Linux 6.6 110 220 330 440 550 SE +/- 9.38, N = 14 SE +/- 0.20, N = 3 476.5 489.5 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Thread Linux 6.6 Linux 6.8 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 112 112 MIN: 79.2 MIN: 79.2 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
JPEG-XL libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 80 Linux 6.6 Linux 6.8 7 14 21 28 35 SE +/- 0.47, N = 15 SE +/- 0.21, N = 3 28.68 32.09 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 90 Linux 6.6 Linux 6.8 6 12 18 24 30 SE +/- 0.07, N = 3 SE +/- 0.13, N = 3 23.73 27.51 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 80 Linux 6.6 Linux 6.8 7 14 21 28 35 SE +/- 0.38, N = 14 SE +/- 0.41, N = 3 27.23 29.08 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 90 Linux 6.6 Linux 6.8 7 14 21 28 35 SE +/- 0.27, N = 15 SE +/- 0.27, N = 3 25.02 27.68 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 100 Linux 6.6 Linux 6.8 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 19.08 20.39 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
OpenBenchmarking.org MP/s, More Is Better JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 100 Linux 6.6 Linux 6.8 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 19.24 20.56 1. (CXX) g++ options: -fno-rtti -O3 -fPIE -pie -lm
JPEG-XL Decoding libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is suited for JPEG XL decode performance testing to PNG output file, the pts/jpexl test is for encode performance. The JPEG XL encoding/decoding is done using the libjxl codebase. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG-XL Decoding libjxl 0.10.1 CPU Threads: 1 Linux 6.8 Linux 6.6 12 24 36 48 60 SE +/- 0.23, N = 3 SE +/- 0.21, N = 3 54.11 54.29
WebP Image Encode OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.4 Encode Settings: Default Linux 6.6 Linux 6.8 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 17.16 17.32 1. (CC) gcc options: -fvisibility=hidden -O2 -lm -lpng16 -ljpeg
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.4 Encode Settings: Quality 100 Linux 6.6 Linux 6.8 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 10.43 10.45 1. (CC) gcc options: -fvisibility=hidden -O2 -lm -lpng16 -ljpeg
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.4 Encode Settings: Quality 100, Lossless Linux 6.6 Linux 6.8 0.3353 0.6706 1.0059 1.3412 1.6765 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 1.48 1.49 1. (CC) gcc options: -fvisibility=hidden -O2 -lm -lpng16 -ljpeg
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.4 Encode Settings: Quality 100, Highest Compression Linux 6.6 Linux 6.8 0.7628 1.5256 2.2884 3.0512 3.814 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.36 3.39 1. (CC) gcc options: -fvisibility=hidden -O2 -lm -lpng16 -ljpeg
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.4 Encode Settings: Quality 100, Lossless, Highest Compression Linux 6.6 Linux 6.8 0.1328 0.2656 0.3984 0.5312 0.664 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.59 0.59 1. (CC) gcc options: -fvisibility=hidden -O2 -lm -lpng16 -ljpeg
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 4.7 Preset: Fast Linux 6.6 Linux 6.8 140 280 420 560 700 SE +/- 2.79, N = 3 SE +/- 0.92, N = 3 662.73 666.85 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Medium Linux 6.6 Linux 6.8 60 120 180 240 300 SE +/- 0.27, N = 3 SE +/- 0.24, N = 3 262.80 262.83 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Thorough Linux 6.8 Linux 6.6 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 33.93 33.95 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Exhaustive Linux 6.8 Linux 6.6 0.6467 1.2934 1.9401 2.5868 3.2335 SE +/- 0.0108, N = 3 SE +/- 0.0119, N = 3 2.8691 2.8740 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Very Thorough Linux 6.8 Linux 6.6 1.0543 2.1086 3.1629 4.2172 5.2715 SE +/- 0.0122, N = 3 SE +/- 0.0155, N = 3 4.6817 4.6858 1. (CXX) g++ options: -O3 -flto -pthread
Stockfish This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 1024 CPU threads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 16.1 Chess Benchmark Linux 6.8 Linux 6.6 16M 32M 48M 64M 80M SE +/- 1376453.74, N = 12 SE +/- 1774428.97, N = 12 72639152 75922419 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -msse4.1 -mssse3 -msse2 -flto -flto-partition=one -flto=jobserver
RocksDB This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Random Read Linux 6.8 Linux 6.6 40M 80M 120M 160M 200M SE +/- 3162994.92, N = 15 SE +/- 1209121.69, N = 14 153785607 184532985 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Update Random Linux 6.6 Linux 6.8 70K 140K 210K 280K 350K SE +/- 306.76, N = 3 SE +/- 346.93, N = 3 301984 320850 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read While Writing Linux 6.8 Linux 6.6 2M 4M 6M 8M 10M SE +/- 79378.85, N = 3 SE +/- 9315.20, N = 3 8878813 9073367 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read Random Write Random Linux 6.6 Linux 6.8 600K 1200K 1800K 2400K 3000K SE +/- 9938.97, N = 3 SE +/- 6021.59, N = 3 2349337 2724328 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 Linux 6.8 Linux 6.6 3K 6K 9K 12K 15K SE +/- 14.78, N = 3 SE +/- 15.24, N = 3 14635.0 14679.9 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Graph500 This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org sssp max_TEPS, More Is Better Graph500 3.0 Scale: 26 Linux 6.8 Linux 6.6 50M 100M 150M 200M 250M 214883000 216393000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.org sssp median_TEPS, More Is Better Graph500 3.0 Scale: 26 Linux 6.8 Linux 6.6 30M 60M 90M 120M 150M 161136000 161857000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 Linux 6.8 Linux 6.6 200K 400K 600K 800K 1000K SE +/- 823.53, N = 3 SE +/- 317.47, N = 3 943736.9 948619.4 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
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 7.38.2 VGR Performance Metric Linux 6.6 Linux 6.8 160K 320K 480K 640K 800K 768533 769427 1. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm -ltk8.6
Chaos Group V-RAY This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 6.0 Mode: CPU Linux 6.6 Linux 6.8 15K 30K 45K 60K 75K SE +/- 282.60, N = 3 SE +/- 822.51, N = 3 67322 68903
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: IP Shapes 1D - Engine: CPU Linux 6.8 Linux 6.6 0.2995 0.599 0.8985 1.198 1.4975 SE +/- 0.02342, N = 15 SE +/- 0.03534, N = 15 1.33123 1.31782 MIN: 1.03 MIN: 1.01 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: IP Shapes 3D - Engine: CPU Linux 6.8 Linux 6.6 2 4 6 8 10 SE +/- 0.00709, N = 3 SE +/- 0.00967, N = 3 7.73804 7.72941 MIN: 7.62 MIN: 7.62 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Convolution Batch Shapes Auto - Engine: CPU Linux 6.6 Linux 6.8 0.2156 0.4312 0.6468 0.8624 1.078 SE +/- 0.010842, N = 3 SE +/- 0.009774, N = 5 0.958085 0.949172 MIN: 0.87 MIN: 0.86 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Deconvolution Batch shapes_1d - Engine: CPU Linux 6.8 Linux 6.6 3 6 9 12 15 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 11.52 11.37 MIN: 10.6 MIN: 6.49 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Deconvolution Batch shapes_3d - Engine: CPU Linux 6.8 Linux 6.6 0.4895 0.979 1.4685 1.958 2.4475 SE +/- 0.00666, N = 3 SE +/- 0.01366, N = 3 2.17554 2.15953 MIN: 2.09 MIN: 2.09 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Recurrent Neural Network Training - Engine: CPU Linux 6.8 Linux 6.6 300 600 900 1200 1500 SE +/- 1.24, N = 3 SE +/- 1.58, N = 3 1332.31 1325.98 MIN: 1301.27 MIN: 1291.17 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Recurrent Neural Network Inference - Engine: CPU Linux 6.8 Linux 6.6 160 320 480 640 800 SE +/- 0.44, N = 3 SE +/- 0.64, N = 3 763.01 757.07 MIN: 733.29 MIN: 727.64 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 600 1200 1800 2400 3000 SE +/- 2.03, N = 3 SE +/- 3.53, N = 3 2930 2916
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 600 1200 1800 2400 3000 SE +/- 2.03, N = 3 SE +/- 1.76, N = 3 2974 2962
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 700 1400 2100 2800 3500 SE +/- 2.65, N = 3 SE +/- 3.51, N = 3 3446 3424
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 12K 24K 36K 48K 60K SE +/- 173.06, N = 3 SE +/- 43.89, N = 3 53719 53229
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 20K 40K 60K 80K 100K SE +/- 131.90, N = 3 SE +/- 149.27, N = 3 100225 99823
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 12K 24K 36K 48K 60K SE +/- 12.02, N = 3 SE +/- 89.80, N = 3 54461 54057
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 20K 40K 60K 80K 100K SE +/- 150.23, N = 3 SE +/- 36.57, N = 3 101836 101487
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 13K 26K 39K 52K 65K SE +/- 77.47, N = 3 SE +/- 26.10, N = 3 61954 61521
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 30K 60K 90K 120K 150K SE +/- 358.28, N = 3 SE +/- 95.84, N = 3 117082 116514
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 160 320 480 640 800 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 739 735
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 160 320 480 640 800 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 750 743
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 200 400 600 800 1000 SE +/- 1.20, N = 3 SE +/- 0.00, N = 3 868 864
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 3K 6K 9K 12K 15K SE +/- 22.93, N = 3 SE +/- 10.12, N = 3 11806 11773
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 6K 12K 18K 24K 30K SE +/- 45.04, N = 3 SE +/- 777.74, N = 15 30119 28333
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 3K 6K 9K 12K 15K SE +/- 20.25, N = 3 SE +/- 15.32, N = 3 11970 11931
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 7K 14K 21K 28K 35K SE +/- 11.79, N = 3 SE +/- 32.04, N = 3 30515 30468
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 3K 6K 9K 12K 15K SE +/- 8.19, N = 3 SE +/- 6.03, N = 3 13922 13850
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Linux 6.8 Linux 6.6 7K 14K 21K 28K 35K SE +/- 46.53, N = 3 SE +/- 48.01, N = 3 34250 34124
Google Draco Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Lion Linux 6.8 Linux 6.6 1200 2400 3600 4800 6000 SE +/- 7.26, N = 3 SE +/- 9.67, N = 3 5547 5505 1. (CXX) g++ options: -O3
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 2024.0 Model: Face Detection FP16 - Device: CPU Linux 6.8 Linux 6.6 600 1200 1800 2400 3000 SE +/- 5.03, N = 3 SE +/- 12.80, N = 3 2824.07 2800.24 MIN: 2254.93 / MAX: 3165.67 MIN: 2144.88 / MAX: 3178.41 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU Linux 6.8 Linux 6.6 90 180 270 360 450 SE +/- 0.39, N = 3 SE +/- 0.29, N = 3 425.04 411.85 MIN: 153.23 / MAX: 530.53 MIN: 118.06 / MAX: 514.03 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU Linux 6.8 Linux 6.6 90 180 270 360 450 SE +/- 1.20, N = 3 SE +/- 0.49, N = 3 426.56 412.86 MIN: 145.66 / MAX: 516.1 MIN: 131.24 / MAX: 511.62 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU Linux 6.8 Linux 6.6 14 28 42 56 70 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 64.24 63.75 MIN: 15.88 / MAX: 98.58 MIN: 23.31 / MAX: 101.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU Linux 6.6 Linux 6.8 400 800 1200 1600 2000 SE +/- 0.28, N = 3 SE +/- 2.20, N = 3 1794.27 1794.00 MIN: 1695.76 / MAX: 1822.06 MIN: 1670.12 / MAX: 1830.77 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU Linux 6.8 Linux 6.6 3 6 9 12 15 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 10.27 10.05 MIN: 4.86 / MAX: 31.64 MIN: 4.71 / MAX: 32.45 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU Linux 6.8 Linux 6.6 80 160 240 320 400 SE +/- 0.65, N = 3 SE +/- 0.40, N = 3 373.54 371.82 MIN: 102.04 / MAX: 455.03 MIN: 87.53 / MAX: 446.75 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU Linux 6.6 Linux 6.8 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 23.33 23.28 MIN: 12 / MAX: 51.52 MIN: 11.89 / MAX: 46.96 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU Linux 6.8 Linux 6.6 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 27.67 27.64 MIN: 15.01 / MAX: 52.41 MIN: 15.37 / MAX: 52.58 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU Linux 6.8 Linux 6.6 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 7.40 7.36 MIN: 4.16 / MAX: 21.13 MIN: 4.22 / MAX: 25 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU Linux 6.6 Linux 6.8 12 24 36 48 60 SE +/- 0.13, N = 3 SE +/- 0.19, N = 3 52.47 52.26 MIN: 35 / MAX: 102.54 MIN: 27.34 / MAX: 96.1 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU Linux 6.8 Linux 6.6 60 120 180 240 300 SE +/- 1.96, N = 3 SE +/- 1.55, N = 3 270.47 270.19 MIN: 130.43 / MAX: 364.05 MIN: 140.17 / MAX: 358.21 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU Linux 6.8 Linux 6.6 8 16 24 32 40 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 36.13 36.07 MIN: 18.31 / MAX: 60.59 MIN: 18.65 / MAX: 65.82 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU Linux 6.6 Linux 6.8 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 21.38 21.02 MIN: 11.76 / MAX: 43.88 MIN: 12.34 / MAX: 44.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU Linux 6.6 Linux 6.8 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 23.37 23.06 MIN: 13.11 / MAX: 45.22 MIN: 10.63 / MAX: 43.28 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU Linux 6.8 Linux 6.6 30 60 90 120 150 SE +/- 0.13, N = 3 SE +/- 0.16, N = 3 121.97 121.52 MIN: 81.68 / MAX: 222.61 MIN: 82.39 / MAX: 220.52 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU Linux 6.8 Linux 6.6 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 17.24 17.15 MIN: 9.78 / MAX: 37.37 MIN: 9.61 / MAX: 36.36 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Linux 6.8 Linux 6.6 0.3758 0.7516 1.1274 1.5032 1.879 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 1.67 1.65 MIN: 0.83 / MAX: 11.89 MIN: 0.8 / MAX: 14.28 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU Linux 6.6 Linux 6.8 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.26, N = 3 108.24 108.19 MIN: 72.91 / MAX: 130.49 MIN: 73.68 / MAX: 125.37 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Linux 6.6 Linux 6.8 0.2588 0.5176 0.7764 1.0352 1.294 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.15 1.10 MIN: 0.57 / MAX: 12.39 MIN: 0.51 / MAX: 12.66 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
SPECFEM3D simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.1.1 Model: Mount St. Helens Linux 6.8 Linux 6.6 3 6 9 12 15 SE +/- 0.15, N = 12 SE +/- 0.15, N = 3 13.54 13.14 1. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.1.1 Model: Layered Halfspace Linux 6.8 Linux 6.6 11 22 33 44 55 SE +/- 0.04, N = 3 SE +/- 0.47, N = 3 49.36 49.26 1. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.1.1 Model: Tomographic Model Linux 6.8 Linux 6.6 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.15, N = 5 14.34 14.22 1. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.1.1 Model: Homogeneous Halfspace Linux 6.8 Linux 6.6 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.19, N = 3 18.04 17.58 1. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.org Seconds, Fewer Is Better SPECFEM3D 4.1.1 Model: Water-layered Halfspace Linux 6.8 Linux 6.6 10 20 30 40 50 SE +/- 0.45, N = 15 SE +/- 0.21, N = 3 44.89 43.92 1. (F9X) gfortran options: -O2 -fopenmp -std=f2008 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6 Linux 6.6 Linux 6.8 0.7769 1.5538 2.3307 3.1076 3.8845 SE +/- 0.004, N = 3 SE +/- 0.007, N = 3 3.453 3.441 1. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6, Lossless Linux 6.8 Linux 6.6 2 4 6 8 10 SE +/- 0.055, N = 3 SE +/- 0.016, N = 3 7.212 7.191 1. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 10, Lossless Linux 6.6 Linux 6.8 1.2751 2.5502 3.8253 5.1004 6.3755 SE +/- 0.016, N = 3 SE +/- 0.009, N = 3 5.667 5.610 1. (CXX) g++ options: -O3 -fPIC -lm
C-Ray OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 2.0 Resolution: 4K - Rays Per Pixel: 16 Linux 6.8 Linux 6.6 13 26 39 52 65 SE +/- 0.24, N = 3 SE +/- 0.42, N = 3 59.59 59.17 1. (CC) gcc options: -lpthread -lm
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 2.0 Resolution: 5K - Rays Per Pixel: 16 Linux 6.8 Linux 6.6 20 40 60 80 100 SE +/- 0.34, N = 3 SE +/- 0.17, N = 3 107.53 106.41 1. (CC) gcc options: -lpthread -lm
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 2.0 Resolution: 1080p - Rays Per Pixel: 16 Linux 6.8 Linux 6.6 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 14.88 14.76 1. (CC) gcc options: -lpthread -lm
RNNoise RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 0.2 Input: 26 Minute Long Talking Sample Linux 6.6 Linux 6.8 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 11.67 11.62 1. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: BMW27 - Compute: CPU-Only Linux 6.8 Linux 6.6 7 14 21 28 35 SE +/- 0.27, N = 3 SE +/- 0.13, N = 3 30.02 29.82
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Junkshop - Compute: CPU-Only Linux 6.6 Linux 6.8 10 20 30 40 50 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 43.50 43.26
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Classroom - Compute: CPU-Only Linux 6.6 Linux 6.8 20 40 60 80 100 SE +/- 0.52, N = 3 SE +/- 0.50, N = 3 80.98 80.75
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Fishy Cat - Compute: CPU-Only Linux 6.6 Linux 6.8 8 16 24 32 40 SE +/- 0.19, N = 3 SE +/- 0.26, N = 3 36.91 36.77
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Barbershop - Compute: CPU-Only Linux 6.6 Linux 6.8 70 140 210 280 350 SE +/- 0.78, N = 3 SE +/- 0.97, N = 3 301.81 299.41
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Pabellon Barcelona - Compute: CPU-Only Linux 6.8 Linux 6.6 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.27, N = 3 95.26 95.09
Linux 6.6 Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS), Chipset: AMD Starship/Matisse, Memory: 4 x 32GB DDR4-3000MT/s CMK64GX4M2D3000C16, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200
OS: Pop 22.04, Kernel: 6.6.6-76060606-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 23.3.2-1pop0~1704238321~22.04~36f1d0e (LLVM 15.0.7 DRM 3.54), Vulkan: 1.3.267, Compiler: GCC 11.4.0, 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-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: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x830107aPython 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: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 28 April 2024 11:55 by user phoronix.
Linux 6.8 Processor: AMD Ryzen Threadripper 3990X 64-Core @ 2.90GHz (64 Cores / 128 Threads), Motherboard: Gigabyte TRX40 AORUS PRO WIFI (F6 BIOS), Chipset: AMD Starship/Matisse, Memory: 4 x 32GB DDR4-3000MT/s CMK64GX4M2D3000C16, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Radeon RX 5700 8GB, Audio: AMD Navi 10 HDMI Audio, Monitor: DELL P2415Q, Network: Intel I211 + Intel Wi-Fi 6 AX200
OS: Pop 22.04, Kernel: 6.8.0-76060800daily20240311-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.4, OpenGL: 4.6 Mesa 24.0.3-1pop1~1711635559~22.04~7a9f319 (LLVM 15.0.7 DRM 3.57), Vulkan: 1.3.274, Compiler: GCC 11.4.0, 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-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: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x830107aPython 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: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 29 April 2024 05:15 by user phoronix.