Genoa compiler benchmarks by Michael Larabel for a future article.
GCC 13.1.1 Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Fedora Linux 38, Kernel: 6.2.15-300.fc38.x86_64 (x86_64), Compiler: GCC 13.1.1 20230511, File-System: xfs, Screen Resolution: 640x480
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-multilib --enable-offload-defaulted --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driverDisk Notes: none / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.11.3Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Clang 16.0.3 OS: Fedora Linux 38, Kernel: 6.2.15-300.fc38.x86_64 (x86_64), Compiler: Clang 16.0.3 + LLVM 16.0.3, File-System: xfs, Screen Resolution: 640x480
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"Disk Notes: none / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.11.3Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
AMD EPYC Genoa Compilers OpenBenchmarking.org Phoronix Test Suite 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) AMD Titanite_4G (RTI1004D BIOS) AMD Device 14a4 1520GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 ASPEED VGA HDMI Broadcom NetXtreme BCM5720 PCIe Fedora Linux 38 6.2.15-300.fc38.x86_64 (x86_64) GCC 13.1.1 20230511 Clang 16.0.3 + LLVM 16.0.3 xfs 640x480 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Compilers File-System Screen Resolution AMD EPYC Genoa Compilers Performance System Logs - Transparent Huge Pages: madvise - CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto" - GCC 13.1.1: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-multilib --enable-offload-defaulted --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver - none / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096 - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa101111 - Python 3.11.3 - SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
GCC 13.1.1 vs. Clang 16.0.3 Comparison Phoronix Test Suite Baseline +92% +92% +184% +184% +276% +276% 367.9% 171.9% 31.4% 29.6% 25.7% 25.3% 18.3% 17.6% 14.6% 14.5% 14.4% 14.4% 14.2% 14.1% 13.1% 12.6% 10.9% 10.9% 10.1% 8.7% 8.6% 8.3% 8.2% 8.1% 7.5% 7.4% 6.8% 6.7% 6.7% 6.6% 6.5% 6.2% 5.8% 5.1% 4.9% 4.7% 4.4% 4.2% 4.2% 3.5% 3.4% 3.3% 3% 2.9% 2.8% 2.7% 2.2% 2.2% 2.1% 6.4% R.N.N.T - bf16bf16bf16 - CPU R.N.N.I - bf16bf16bf16 - CPU OpenMP - BM1 61.1% OpenMP - BM1 61.1% ChaCha20-Poly1305 60.9% ChaCha20 57.2% 49.1% Swirl 34% Sharpen Q.1.H.C DistinctUserID PartialTweets HWB Color Space 24.5% Bosphorus 1080p - Very Fast Bosphorus 4K Noise-Gaussian 17.5% Enhanced 16.6% 44100 - 512 Q.1.L.H.C 192000 - 512 Keyed Algorithms 44100 - 1024 192000 - 1024 3 - Compression Speed Q.1.L N.C.P.M 9 - Compression Speed 6, Lossless Unkeyed Algorithms 9.9% CoreMark Size 666 - I.P.S 9.7% Bosphorus 1080p - Medium Fast Trace Time SecureMark-TLS Bosphorus 4K - Medium 2048 x 2048 - Total Time 7.7% Bosphorus 4K - Slow Bosphorus 1080p - Super Fast Bosphorus 4K - Medium Kostya Resizing 384 - 256 - 57 TopTweet Bosphorus 1080p - Ultra Fast A.C.P 10, Lossless Preset 4 - Bosphorus 4K Total Time - 4.1.R.P.P 4.6% 256 - 256 - 57 Default 4096 4% 2 Medium SHA512 LargeRand 3.3% 2048 3.2% Preset 12 - Bosphorus 4K 3.1% 100 - 800 - Read Only - Average Latency Church Facade 100 - 800 - Read Only T.T.S.S 2.8% Total Time 2.8% Lion 1 - D.S 2.6% Bosphorus 4K - Super Fast 2.3% OpenMP - BM2 2.2% OpenMP - BM2 2.2% 2 Preset 8 - Bosphorus 4K 128 - 256 - 57 wyhash t1ha2_atonce 21.7% oneDNN oneDNN miniBUDE miniBUDE OpenSSL OpenSSL Kripke GraphicsMagick GraphicsMagick WebP Image Encode simdjson simdjson GraphicsMagick uvg266 x265 GraphicsMagick GraphicsMagick Stargate Digital Audio Workstation WebP Image Encode Stargate Digital Audio Workstation Crypto++ Stargate Digital Audio Workstation Stargate Digital Audio Workstation LZ4 Compression WebP Image Encode OpenJPEG LZ4 Compression libavif avifenc Crypto++ Coremark uvg266 ASTC Encoder POV-Ray SecureMark uvg266 AOBench Kvazaar uvg266 Kvazaar simdjson GraphicsMagick Liquid-DSP simdjson uvg266 TSCP libavif avifenc SVT-AV1 QuantLib C-Ray libavif avifenc Liquid-DSP WebP Image Encode MariaDB libavif avifenc ASTC Encoder OpenSSL simdjson MariaDB SVT-AV1 PostgreSQL Google Draco PostgreSQL eSpeak-NG Speech Engine Stockfish Google Draco LZ4 Compression Kvazaar miniBUDE miniBUDE SQLite SVT-AV1 Liquid-DSP SMHasher SMHasher GCC 13.1.1 Clang 16.0.3
TSCP This is a performance test of TSCP, Tom Kerrigan's Simple Chess Program, which has a built-in performance benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance Clang 16.0.3 GCC 13.1.1 400K 800K 1200K 1600K 2000K SE +/- 2743.38, N = 5 SE +/- 2555.19, N = 5 1758567 1661988 1. (CC) gcc options: -O3 -march=native -flto
OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Unkeyed Algorithms GCC 13.1.1 Clang 16.0.3 90 180 270 360 450 SE +/- 0.35, N = 3 SE +/- 0.05, N = 3 435.81 396.46 1. (CXX) g++ options: -O3 -march=native -flto -fPIC -pthread -pipe
OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 1 - Decompression Speed GCC 13.1.1 Clang 16.0.3 4K 8K 12K 16K 20K SE +/- 51.33, N = 3 SE +/- 77.84, N = 3 17800.8 17350.5 1. (CC) gcc options: -O3 -march=native -flto
OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed Clang 16.0.3 GCC 13.1.1 12 24 36 48 60 SE +/- 0.54, N = 3 SE +/- 0.04, N = 3 52.31 46.24 1. (CC) gcc options: -O3 -march=native -flto
OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed GCC 13.1.1 Clang 16.0.3 4K 8K 12K 16K 20K SE +/- 141.14, N = 3 SE +/- 103.96, N = 3 16409.9 16246.7 1. (CC) gcc options: -O3 -march=native -flto
Z3 Theorem Prover The Z3 Theorem Prover / SMT solver is developed by Microsoft Research under the MIT license. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Z3 Theorem Prover 4.12.1 SMT File: 2.smt2 GCC 13.1.1 16 32 48 64 80 SE +/- 0.06, N = 3 72.23 1. (CXX) g++ options: -lpthread -O3 -march=native -flto -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -fPIC
SMT File: 2.smt2
Clang 16.0.3: The test quit with a non-zero exit status. E: z3: line 2: ./z3-z3-4.12.1/build/z3: No such file or directory
Z3 Theorem Prover The Z3 Theorem Prover / SMT solver is developed by Microsoft Research under the MIT license. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Z3 Theorem Prover 4.12.1 SMT File: 1.smt2 GCC 13.1.1 6 12 18 24 30 SE +/- 0.19, N = 3 25.90 1. (CXX) g++ options: -lpthread -O3 -march=native -flto -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -fPIC
SMT File: 1.smt2
Clang 16.0.3: The test quit with a non-zero exit status. E: z3: line 2: ./z3-z3-4.12.1/build/z3: No such file or directory
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 GCC 13.1.1 Clang 16.0.3 50 100 150 200 250 SE +/- 0.85, N = 3 SE +/- 0.20, N = 3 219.39 217.47 1. (CC) gcc options: -O3 -march=native -flto -rdynamic -lm
Stargate Digital Audio Workstation Stargate is an open-source, cross-platform digital audio workstation (DAW) software package with "a unique and carefully curated experience" with scalability from old systems up through modern multi-core systems. Stargate is GPLv3 licensed and makes use of Qt5 (PyQt5) for its user-interface. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 512 Clang 16.0.3 GCC 13.1.1 2 4 6 8 10 SE +/- 0.001401, N = 3 SE +/- 0.001560, N = 3 6.691175 5.837183 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 512 Clang 16.0.3 GCC 13.1.1 0.6481 1.2962 1.9443 2.5924 3.2405 SE +/- 0.007221, N = 3 SE +/- 0.007283, N = 3 2.880358 2.516856 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 1024 Clang 16.0.3 GCC 13.1.1 2 4 6 8 10 SE +/- 0.005456, N = 3 SE +/- 0.000734, N = 3 7.161300 6.270559 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 1024 Clang 16.0.3 GCC 13.1.1 0.7329 1.4658 2.1987 2.9316 3.6645 SE +/- 0.007486, N = 3 SE +/- 0.006270, N = 3 3.257372 2.855186 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
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 Clang 16.0.3 GCC 13.1.1 200 400 600 800 1000 SE +/- 5.60, N = 3 SE +/- 3.96, N = 3 780.95 718.81 1. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Medium Clang 16.0.3 GCC 13.1.1 120 240 360 480 600 SE +/- 2.38, N = 3 SE +/- 2.85, N = 3 570.62 552.03 1. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough Clang 16.0.3 GCC 13.1.1 30 60 90 120 150 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 117.75 117.03 1. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive GCC 13.1.1 Clang 16.0.3 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 12.84 12.77 1. (CXX) g++ options: -O3 -march=native -flto -pthread
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 Clang 16.0.3 GCC 13.1.1 1100 2200 3300 4400 5500 SE +/- 44.34, N = 3 SE +/- 29.18, N = 3 5106 5243 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.6 Model: Church Facade Clang 16.0.3 GCC 13.1.1 1400 2800 4200 5600 7000 SE +/- 4.84, N = 3 SE +/- 13.35, N = 3 6559 6750 1. (CXX) g++ options: -O3 -march=native -flto
OpenJPEG OpenJPEG is an open-source JPEG 2000 codec written in the C programming language. The default input for this test profile is the NASA/JPL-Caltech/MSSS Curiosity panorama 717MB TIFF image file converting to JPEG2000 format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenJPEG 2.4 Encode: NASA Curiosity Panorama M34 Clang 16.0.3 GCC 13.1.1 40K 80K 120K 160K 200K SE +/- 571.61, N = 3 SE +/- 812.57, N = 3 162086 179824 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100 Clang 16.0.3 GCC 13.1.1 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 11.75 11.54 -ltiff 1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -flto -lm -lpng16 -ljpeg
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless Clang 16.0.3 GCC 13.1.1 0.342 0.684 1.026 1.368 1.71 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.52 1.35 -ltiff 1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -flto -lm -lpng16 -ljpeg
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Highest Compression Clang 16.0.3 GCC 13.1.1 0.936 1.872 2.808 3.744 4.68 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.16 3.21 -ltiff 1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -flto -lm -lpng16 -ljpeg
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless, Highest Compression Clang 16.0.3 GCC 13.1.1 0.1418 0.2836 0.4254 0.5672 0.709 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.63 0.55 -ltiff 1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -flto -lm -lpng16 -ljpeg
eSpeak-NG Speech Engine This test times how long it takes the eSpeak speech synthesizer to read Project Gutenberg's The Outline of Science and output to a WAV file. This test profile is now tracking the eSpeak-NG version of eSpeak. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better eSpeak-NG Speech Engine 1.51 Text-To-Speech Synthesis GCC 13.1.1 Clang 16.0.3 7 14 21 28 35 SE +/- 0.02, N = 4 SE +/- 0.15, N = 4 27.49 28.27 1. (CXX) g++ options: -O3 -march=native -flto -lpthread
SecureMark SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS Clang 16.0.3 GCC 13.1.1 70K 140K 210K 280K 350K SE +/- 1404.09, N = 3 SE +/- 872.41, N = 3 312570 288753 1. (CC) gcc options: -pedantic -O3
QuantLib QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.30 Clang 16.0.3 GCC 13.1.1 700 1400 2100 2800 3500 SE +/- 7.81, N = 3 SE +/- 2.59, N = 3 3391.1 3238.8 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
miniBUDE MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 GCC 13.1.1 Clang 16.0.3 1500 3000 4500 6000 7500 SE +/- 7.29, N = 3 SE +/- 185.48, N = 15 6902.23 4285.59 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 GCC 13.1.1 Clang 16.0.3 60 120 180 240 300 SE +/- 0.29, N = 3 SE +/- 7.42, N = 15 276.09 171.42 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 GCC 13.1.1 Clang 16.0.3 2K 4K 6K 8K 10K SE +/- 43.34, N = 3 SE +/- 80.21, N = 3 8251.34 8072.49 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 GCC 13.1.1 Clang 16.0.3 70 140 210 280 350 SE +/- 1.73, N = 3 SE +/- 3.21, N = 3 330.05 322.90 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Timed MrBayes Analysis This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Clang 16.0.3 GCC 13.1.1 30 60 90 120 150 SE +/- 0.66, N = 3 SE +/- 0.12, N = 3 112.11 113.34 -mabm 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mrdrnd -mbmi -mbmi2 -madx -O3 -std=c99 -pedantic -march=native -flto -lm
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 3.1 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU Clang 16.0.3 GCC 13.1.1 500 1000 1500 2000 2500 SE +/- 8.52, N = 15 SE +/- 42.69, N = 15 468.27 2191.22 -fopenmp=libomp - MIN: 441.14 -fopenmp - MIN: 1875.06 1. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU Clang 16.0.3 GCC 13.1.1 500 1000 1500 2000 2500 SE +/- 2.20, N = 3 SE +/- 26.76, N = 15 885.03 2406.70 -fopenmp=libomp - MIN: 871.44 -fopenmp - MIN: 2191.9 1. (CXX) g++ options: -O3 -march=native -flto -msse4.1 -fPIC -pie -ldl -lpthread
Kripke Kripke is a simple, scalable, 3D Sn deterministic particle transport code. Its primary purpose is to research how data layout, programming paradigms and architectures effect the implementation and performance of Sn transport. Kripke is developed by LLNL. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.4 GCC 13.1.1 Clang 16.0.3 70M 140M 210M 280M 350M SE +/- 6307414.85, N = 15 SE +/- 4076394.65, N = 15 324078880 217323727 -fopenmp -fopenmp=libomp 1. (CXX) g++ options: -O3 -march=native -flto
GPAW GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GPAW 22.1 Input: Carbon Nanotube Clang 16.0.3 GCC 13.1.1 30 60 90 120 150 SE +/- 0.24, N = 3 SE +/- 0.24, N = 3 140.28 140.86 1. (CC) gcc options: -shared -O3 -march=native -flto -lxc -lblas -lmpi
Stockfish This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 15 Total Time GCC 13.1.1 Clang 16.0.3 110M 220M 330M 440M 550M SE +/- 3102500.18, N = 3 SE +/- 8586129.93, N = 15 532213592 517643140 -lgcov -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -mbmi2 -fno-peel-loops -fno-tracer -flto=jobserver -fprofile-use 1. (CXX) g++ options: -m64 -lpthread -O3 -march=native -flto -fno-exceptions -std=c++17 -pedantic -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2
7-Zip Compression This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating GCC 13.1.1 150K 300K 450K 600K 750K SE +/- 7447.92, N = 3 691246 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Test: Compression Rating
Clang 16.0.3: The test quit with a non-zero exit status. E: compress-7zip: line 2: ./CPP/7zip/Bundles/Alone2/_o/7zz: No such file or directory
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating GCC 13.1.1 200K 400K 600K 800K 1000K SE +/- 4772.36, N = 3 1155277 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Test: Decompression Rating
Clang 16.0.3: The test quit with a non-zero exit status. E: compress-7zip: line 2: ./CPP/7zip/Bundles/Alone2/_o/7zz: No such file or directory
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: WPA PSK GCC 13.1.1 300K 600K 900K 1200K 1500K SE +/- 4630.81, N = 3 1261333 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
Test: WPA PSK
Clang 16.0.3: The test quit with a non-zero exit status. E: john-the-ripper: line 3: ./john: No such file or directory
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: Blowfish GCC 13.1.1 70K 140K 210K 280K 350K SE +/- 401.92, N = 3 323256 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
Test: Blowfish
Clang 16.0.3: The test quit with a non-zero exit status. E: john-the-ripper: line 3: ./john: No such file or directory
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: HMAC-SHA512 GCC 13.1.1 60M 120M 180M 240M 300M SE +/- 2757367.12, N = 3 286625667 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
Test: HMAC-SHA512
Clang 16.0.3: The test quit with a non-zero exit status. E: john-the-ripper: line 3: ./john: No such file or directory
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: MD5 GCC 13.1.1 6M 12M 18M 24M 30M SE +/- 29475.04, N = 3 28819667 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
Test: MD5
Clang 16.0.3: The test quit with a non-zero exit status. E: john-the-ripper: line 3: ./john: No such file or directory
Zstd Compression This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed GCC 13.1.1 Clang 16.0.3 70 140 210 280 350 SE +/- 4.38, N = 3 SE +/- 3.40, N = 3 312.6 309.8 -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -flto -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Decompression Speed GCC 13.1.1 Clang 16.0.3 400 800 1200 1600 2000 SE +/- 3.39, N = 3 SE +/- 6.60, N = 3 1662.6 1632.7 -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -flto -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed Clang 16.0.3 GCC 13.1.1 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 16.8 16.8 -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -flto -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed GCC 13.1.1 Clang 16.0.3 300 600 900 1200 1500 SE +/- 9.49, N = 3 SE +/- 1.96, N = 3 1413.0 1387.5 -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -flto -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed GCC 13.1.1 Clang 16.0.3 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 8.31 8.26 -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -flto -pthread -lz
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed Clang 16.0.3 GCC 13.1.1 300 600 900 1200 1500 SE +/- 4.51, N = 3 SE +/- 4.13, N = 3 1343.5 1341.4 -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -flto -pthread -lz
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: Slow Clang 16.0.3 GCC 13.1.1 9 18 27 36 45 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 37.37 34.77 -lpthread 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -flto -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Clang 16.0.3 GCC 13.1.1 9 18 27 36 45 SE +/- 0.17, N = 3 SE +/- 0.06, N = 3 38.37 35.94 -lpthread 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -flto -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Clang 16.0.3 GCC 13.1.1 16 32 48 64 80 SE +/- 0.57, N = 3 SE +/- 0.74, N = 4 69.85 68.57 -lpthread 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -flto -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast GCC 13.1.1 Clang 16.0.3 16 32 48 64 80 SE +/- 0.34, N = 3 SE +/- 0.16, N = 3 70.10 68.54 -lpthread 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -flto -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast GCC 13.1.1 Clang 16.0.3 16 32 48 64 80 SE +/- 0.43, N = 3 SE +/- 0.62, N = 3 70.51 70.16 -lpthread 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -flto -lm -lrt
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Swirl GCC 13.1.1 Clang 16.0.3 600 1200 1800 2400 3000 SE +/- 15.88, N = 3 SE +/- 3.84, N = 3 2958 2207 1. (CC) gcc options: -fopenmp -O3 -march=native -flto -ltiff -ljpeg -lX11 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Rotate GCC 13.1.1 Clang 16.0.3 140 280 420 560 700 SE +/- 3.28, N = 3 SE +/- 0.33, N = 3 660 659 1. (CC) gcc options: -fopenmp -O3 -march=native -flto -ltiff -ljpeg -lX11 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen Clang 16.0.3 GCC 13.1.1 400 800 1200 1600 2000 SE +/- 12.49, N = 3 SE +/- 1.00, N = 3 1723 1311 1. (CC) gcc options: -fopenmp -O3 -march=native -flto -ltiff -ljpeg -lX11 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced GCC 13.1.1 Clang 16.0.3 500 1000 1500 2000 2500 SE +/- 4.26, N = 3 SE +/- 2.33, N = 3 2216 1901 1. (CC) gcc options: -fopenmp -O3 -march=native -flto -ltiff -ljpeg -lX11 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Resizing Clang 16.0.3 GCC 13.1.1 30 60 90 120 150 SE +/- 2.70, N = 15 SE +/- 6.54, N = 12 128 120 1. (CC) gcc options: -fopenmp -O3 -march=native -flto -ltiff -ljpeg -lX11 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Noise-Gaussian GCC 13.1.1 Clang 16.0.3 200 400 600 800 1000 SE +/- 9.66, N = 6 SE +/- 11.26, N = 3 981 835 1. (CC) gcc options: -fopenmp -O3 -march=native -flto -ltiff -ljpeg -lX11 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: HWB Color Space GCC 13.1.1 Clang 16.0.3 200 400 600 800 1000 SE +/- 15.72, N = 3 SE +/- 5.51, N = 3 1089 875 1. (CC) gcc options: -fopenmp -O3 -march=native -flto -ltiff -ljpeg -lX11 -lz -lm -lpthread
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.5 Encoder Mode: Preset 4 - Input: Bosphorus 4K Clang 16.0.3 GCC 13.1.1 1.3041 2.6082 3.9123 5.2164 6.5205 SE +/- 0.025, N = 3 SE +/- 0.067, N = 3 5.796 5.527 1. (CXX) g++ options: -O3 -march=native -flto -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.5 Encoder Mode: Preset 8 - Input: Bosphorus 4K Clang 16.0.3 GCC 13.1.1 13 26 39 52 65 SE +/- 0.58, N = 5 SE +/- 0.42, N = 3 56.14 54.95 1. (CXX) g++ options: -O3 -march=native -flto -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.5 Encoder Mode: Preset 12 - Input: Bosphorus 4K GCC 13.1.1 Clang 16.0.3 40 80 120 160 200 SE +/- 1.61, N = 3 SE +/- 1.96, N = 12 176.03 170.79 1. (CXX) g++ options: -O3 -march=native -flto -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.5 Encoder Mode: Preset 13 - Input: Bosphorus 4K Clang 16.0.3 GCC 13.1.1 30 60 90 120 150 SE +/- 1.04, N = 12 SE +/- 1.27, N = 7 146.22 143.43 1. (CXX) g++ options: -O3 -march=native -flto -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
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 Clang 16.0.3 GCC 13.1.1 6 12 18 24 30 SE +/- 0.34, N = 3 SE +/- 0.22, N = 6 25.38 21.59 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread -lrt -ldl
C-Ray This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel GCC 13.1.1 Clang 16.0.3 0.7207 1.4414 2.1621 2.8828 3.6035 SE +/- 0.058, N = 15 SE +/- 0.042, N = 3 3.063 3.203 1. (CC) gcc options: -lm -lpthread -O3 -march=native -flto
POV-Ray This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time Clang 16.0.3 GCC 13.1.1 2 4 6 8 10 SE +/- 0.053, N = 7 SE +/- 0.053, N = 8 5.654 6.123 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -flto -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
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: Medium Clang 16.0.3 GCC 13.1.1 7 14 21 28 35 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 29.65 27.43 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Medium Clang 16.0.3 GCC 13.1.1 10 20 30 40 50 SE +/- 0.29, N = 3 SE +/- 0.09, N = 3 42.49 39.08 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Clang 16.0.3 GCC 13.1.1 11 22 33 44 55 SE +/- 0.42, N = 3 SE +/- 0.50, N = 3 47.40 46.63 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast GCC 13.1.1 Clang 16.0.3 11 22 33 44 55 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 46.97 46.84 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Clang 16.0.3 GCC 13.1.1 11 22 33 44 55 SE +/- 0.56, N = 3 SE +/- 0.37, N = 3 47.56 46.72 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast Clang 16.0.3 GCC 13.1.1 30 60 90 120 150 SE +/- 0.64, N = 3 SE +/- 0.05, N = 3 133.05 112.43 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast Clang 16.0.3 GCC 13.1.1 30 60 90 120 150 SE +/- 0.55, N = 3 SE +/- 0.33, N = 3 146.20 136.19 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Clang 16.0.3 GCC 13.1.1 30 60 90 120 150 SE +/- 2.25, N = 3 SE +/- 1.08, N = 11 156.50 147.37 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 2 Clang 16.0.3 GCC 13.1.1 8 16 24 32 40 SE +/- 0.29, N = 3 SE +/- 0.05, N = 3 32.66 33.81 1. (CXX) g++ options: -O3 -fPIC -march=native -flto -lm
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 6 Clang 16.0.3 GCC 13.1.1 0.5675 1.135 1.7025 2.27 2.8375 SE +/- 0.020, N = 3 SE +/- 0.025, N = 5 2.496 2.522 1. (CXX) g++ options: -O3 -fPIC -march=native -flto -lm
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 6, Lossless Clang 16.0.3 GCC 13.1.1 1.0458 2.0916 3.1374 4.1832 5.229 SE +/- 0.035, N = 3 SE +/- 0.059, N = 3 4.220 4.648 1. (CXX) g++ options: -O3 -fPIC -march=native -flto -lm
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 10, Lossless Clang 16.0.3 GCC 13.1.1 0.8343 1.6686 2.5029 3.3372 4.1715 SE +/- 0.020, N = 3 SE +/- 0.023, N = 3 3.527 3.708 1. (CXX) g++ options: -O3 -fPIC -march=native -flto -lm
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 64 - Buffer Length: 256 - Filter Length: 57 Clang 16.0.3 GCC 13.1.1 1000M 2000M 3000M 4000M 5000M SE +/- 1808314.13, N = 3 SE +/- 8346922.25, N = 3 4680200000 4641933333 1. (CC) gcc options: -O3 -march=native -flto -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Clang 16.0.3 GCC 13.1.1 2000M 4000M 6000M 8000M 10000M SE +/- 913479.31, N = 3 SE +/- 13312441.97, N = 3 8665233333 8490666667 1. (CC) gcc options: -O3 -march=native -flto -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 256 - Buffer Length: 256 - Filter Length: 57 Clang 16.0.3 GCC 13.1.1 3000M 6000M 9000M 12000M 15000M SE +/- 2603416.56, N = 3 SE +/- 4096068.58, N = 3 11762333333 11285333333 1. (CC) gcc options: -O3 -march=native -flto -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 384 - Buffer Length: 256 - Filter Length: 57 Clang 16.0.3 GCC 13.1.1 3000M 6000M 9000M 12000M 15000M SE +/- 9527737.29, N = 3 SE +/- 7264831.57, N = 3 12418333333 11647666667 1. (CC) gcc options: -O3 -march=native -flto -pthread -lm -lc -lliquid
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 3.1 Algorithm: SHA256 Clang 16.0.3 GCC 13.1.1 60000M 120000M 180000M 240000M 300000M SE +/- 64283484.40, N = 3 SE +/- 48171917.42, N = 3 264445169827 260892560200 -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: SHA512 Clang 16.0.3 GCC 13.1.1 20000M 40000M 60000M 80000M 100000M SE +/- 4419075.00, N = 3 SE +/- 845012614.25, N = 5 82701625690 80035854752 -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl
OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.1 Algorithm: RSA4096 GCC 13.1.1 Clang 16.0.3 15K 30K 45K 60K 75K SE +/- 24.90, N = 3 SE +/- 10.37, N = 3 71935.9 71901.7 -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl
OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.1 Algorithm: RSA4096 Clang 16.0.3 GCC 13.1.1 600K 1200K 1800K 2400K 3000K SE +/- 437.47, N = 3 SE +/- 105.74, N = 3 2931038.9 2921019.6 -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: ChaCha20 GCC 13.1.1 Clang 16.0.3 200000M 400000M 600000M 800000M 1000000M SE +/- 152062084.95, N = 3 SE +/- 51499603.07, N = 3 1014036223867 645125858407 -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: AES-128-GCM GCC 13.1.1 Clang 16.0.3 400000M 800000M 1200000M 1600000M 2000000M SE +/- 1317927821.70, N = 3 SE +/- 616604050.97, N = 3 1801352965597 1796351136523 -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: AES-256-GCM GCC 13.1.1 Clang 16.0.3 300000M 600000M 900000M 1200000M 1500000M SE +/- 293680009.95, N = 3 SE +/- 2176141824.81, N = 3 1544053984720 1538350610540 -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: ChaCha20-Poly1305 GCC 13.1.1 Clang 16.0.3 150000M 300000M 450000M 600000M 750000M SE +/- 116220547.85, N = 3 SE +/- 48134544.35, N = 3 708873524927 440446591887 -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -flto -lssl -lcrypto -ldl
Memcached Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:5 GCC 13.1.1 400K 800K 1200K 1600K 2000K SE +/- 6222.06, N = 3 2033827.48 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Set To Get Ratio: 1:5
Clang 16.0.3: The test run did not produce a result. E: memcached: line 7: ./memtier_benchmark: No such file or directory
OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:10 GCC 13.1.1 700K 1400K 2100K 2800K 3500K SE +/- 12793.89, N = 3 3302722.11 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Set To Get Ratio: 1:10
Clang 16.0.3: The test run did not produce a result. E: memcached: line 7: ./memtier_benchmark: No such file or directory
OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 GCC 13.1.1 900K 1800K 2700K 3600K 4500K SE +/- 15774.50, N = 3 4105286.36 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Set To Get Ratio: 1:100
Clang 16.0.3: The test run did not produce a result. E: memcached: line 7: ./memtier_benchmark: No such file or directory
SQLite This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database with a variable number of concurrent repetitions -- up to the maximum number of CPU threads available. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.41.2 Threads / Copies: 1 GCC 13.1.1 Clang 16.0.3 0.4601 0.9202 1.3803 1.8404 2.3005 SE +/- 0.002, N = 3 SE +/- 0.015, N = 3 2.028 2.045 1. (CC) gcc options: -O3 -march=native -flto -lz -lm
Faiss Faiss is developed by Meta/Facebook. Faiss is a library for efficient similarity search and clustering of dense vectors. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Faiss 1.7.4 Test: demo_sift1M GCC 13.1.1 13 26 39 52 65 SE +/- 0.19, N = 2 59.40 1. (F9X) gfortran options: -O2 -frecursive -m64 -fopenmp -msse3 -mssse3 -msse4.1 -mavx -mavx2 -fno-tree-vectorize -lm -lpthread -lgfortran -lc
Test: demo_sift1M
Clang 16.0.3: The test quit with a non-zero exit status.
SQLite This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database with a variable number of concurrent repetitions -- up to the maximum number of CPU threads available. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.41.2 Threads / Copies: 2 Clang 16.0.3 GCC 13.1.1 0.5616 1.1232 1.6848 2.2464 2.808 SE +/- 0.032, N = 3 SE +/- 0.027, N = 3 2.442 2.496 1. (CC) gcc options: -O3 -march=native -flto -lz -lm
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Only Clang 16.0.3 GCC 13.1.1 700K 1400K 2100K 2800K 3500K SE +/- 34767.93, N = 12 SE +/- 57281.48, N = 12 3457173 3362193 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -flto -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency Clang 16.0.3 GCC 13.1.1 0.0538 0.1076 0.1614 0.2152 0.269 SE +/- 0.002, N = 12 SE +/- 0.004, N = 12 0.232 0.239 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -flto -lpgcommon -lpgport -lpq -lm
MariaDB This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 11.0.1 Clients: 2048 GCC 13.1.1 Clang 16.0.3 80 160 240 320 400 SE +/- 0.65, N = 3 SE +/- 2.37, N = 3 385 373 -fPIC -pie -shared -lrt -lstdc++ -lcrypt -lssl -lcrypto 1. (CXX) g++ options: -O3 -march=native -flto -fstack-protector -lpthread -lz -ldl -lm
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 11.0.1 Clients: 4096 GCC 13.1.1 Clang 16.0.3 90 180 270 360 450 SE +/- 2.65, N = 3 SE +/- 3.39, N = 3 394 379 -fPIC -pie -shared -lrt -lstdc++ -lcrypt -lssl -lcrypto 1. (CXX) g++ options: -O3 -march=native -flto -fstack-protector -lpthread -lz -ldl -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: Kostya Clang 16.0.3 GCC 13.1.1 0.9968 1.9936 2.9904 3.9872 4.984 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.43 4.15 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet Clang 16.0.3 GCC 13.1.1 2 4 6 8 10 SE +/- 0.06, N = 15 SE +/- 0.01, N = 3 7.33 6.88 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom GCC 13.1.1 Clang 16.0.3 0.2835 0.567 0.8505 1.134 1.4175 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.26 1.22 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets Clang 16.0.3 GCC 13.1.1 2 4 6 8 10 SE +/- 0.12, N = 12 SE +/- 0.02, N = 3 8.22 6.56 1. (CXX) g++ options: -O3 -march=native -flto
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: DistinctUserID Clang 16.0.3 GCC 13.1.1 2 4 6 8 10 SE +/- 0.07, N = 15 SE +/- 0.02, N = 3 8.52 6.78 1. (CXX) g++ options: -O3 -march=native -flto
GCC 13.1.1 Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Fedora Linux 38, Kernel: 6.2.15-300.fc38.x86_64 (x86_64), Compiler: GCC 13.1.1 20230511, File-System: xfs, Screen Resolution: 640x480
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"Compiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,m2,lto --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-multilib --enable-offload-defaulted --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driverDisk Notes: none / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.11.3Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 20 May 2023 15:05 by user .
Clang 16.0.3 Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1004D BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Fedora Linux 38, Kernel: 6.2.15-300.fc38.x86_64 (x86_64), Compiler: Clang 16.0.3 + LLVM 16.0.3, File-System: xfs, Screen Resolution: 640x480
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"Disk Notes: none / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa101111Python Notes: Python 3.11.3Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 21 May 2023 10:51 by user .