5950X LLVM Clang 15

AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS) and AMD Radeon RX 6800 16GB on Ubuntu 22.04 via the Phoronix Test Suite. Benchmarks for a future article by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2209177-NE-5950XLLVM12
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Clang 14
September 16 2022
  3 Hours, 56 Minutes
Clang 15
September 17 2022
  8 Hours, 15 Minutes
Invert Behavior (Only Show Selected Data)
  6 Hours, 6 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

Clang 14

Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 500GB Western Digital WDS500G3X0C-00SJG0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc5daily20220915-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-03294e1 2022-09-16 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.228, Compiler: Clang 14.0.6-1~oibaf~j, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016
Python Notes: Python 3.10.4
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Clang 15

OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc5daily20220915-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-03294e1 2022-09-16 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.228, Compiler: Clang 15.0.1-++20220915084339+3637f345d2ab-1~exp1~20220915084350.58, File-System: ext4, Screen Resolution: 3840x2160

5950X LLVM Clang 15OpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS)AMD Starship/Matisse32GB500GB Western Digital WDS500G3X0C-00SJG0AMD Radeon RX 6800 16GB (2475/1000MHz)AMD Navi 21 HDMI AudioASUS MG28URealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 22.046.0.0-060000rc5daily20220915-generic (x86_64)GNOME Shell 42.4X Server 1.21.1.3 + Wayland4.6 Mesa 22.3.0-devel (git-03294e1 2022-09-16 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48)1.3.228Clang 14.0.6-1~oibaf~jClang 15.0.1-++20220915084339+3637f345d2ab-1~exp1~20220915084350.58ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilersFile-SystemScreen Resolution5950X LLVM Clang 15 BenchmarksSystem Logs- Transparent Huge Pages: madvise- CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016- Python 3.10.4- 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 14 vs. Clang 15 ComparisonPhoronix Test SuiteBaseline+7%+7%+14%+14%+21%+21%27.8%18.4%10.8%5.7%5.1%4.7%4.6%4.4%4.1%3.9%3.3%3.2%3.1%2.8%2.7%2.6%2.5%2.2%2.1%2%2%PNG - 7CPU - DenseNetCPU - MobileNet v216 - 256 - 578%SHA2568%OFDM_Test6.4%CoreMark Size 666 - I.P.S6.1%Q.1.L4.P.1.P.M.2.QWAV To FLAC5%Timed Time - Size 1,000N.C.P.MTrace Time2048 x 2048 - Total Time4.P.1.P.M.2.Q4.P.1.P.S.2.QBosphorus 4K5.P.T.5.P.S.6.QWAV To MP33.1%Speed 8 Realtime - Bosphorus 4KZstd Compression 9VMAF Optimized - Bosphorus 4K19, Long Mode - D.S2.5%BLASP.S.O - Bosphorus 4KA.C.P2.1%CPU - resnet50Speed 9 Realtime - Bosphorus 4KJPEG XL libjxlTNNTNNLiquid-DSPOpenSSLsrsRANCoremarkWebP Image EncodesrsRANFLAC Audio EncodingSQLite SpeedtestOpenJPEGPOV-RayAOBenchsrsRANsrsRANx265srsRANLAME MP3 EncodingQuantLibAOM AV1KTX-Software toktxSVT-VP9Zstd CompressionLeelaChessZeroSVT-VP9TSCPNCNNAOM AV1Clang 14Clang 15

5950X LLVM Clang 15jpegxl: PNG - 7tnn: CPU - DenseNettnn: CPU - MobileNet v2liquid-dsp: 16 - 256 - 57openssl: SHA256srsran: OFDM_Testcoremark: CoreMark Size 666 - Iterations Per Secondwebp: Quality 100, Losslesssrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMencode-flac: WAV To FLACsqlite-speedtest: Timed Time - Size 1,000openjpeg: NASA Curiosity Panorama M34povray: Trace Timeaobench: 2048 x 2048 - Total Timesrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMsrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMx265: Bosphorus 4Ksrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMencode-mp3: WAV To MP3quantlib: aom-av1: Speed 8 Realtime - Bosphorus 4Ktoktx: Zstd Compression 9svt-vp9: VMAF Optimized - Bosphorus 4Kcompress-zstd: 19, Long Mode - Decompression Speedlczero: BLASsvt-vp9: PSNR/SSIM Optimized - Bosphorus 4Ktscp: AI Chess Performancencnn: CPU - resnet50aom-av1: Speed 9 Realtime - Bosphorus 4Kncnn: CPU - googlenetnettle: sha512encode-opus: WAV To Opus Encodeopenfoam: motorBike - Mesh Timencnn: CPU - regnety_400mlibraw: Post-Processing Benchmarksrsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAMsrsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMsvt-hevc: 10 - Bosphorus 4Kaom-av1: Speed 10 Realtime - Bosphorus 4Kncnn: CPU - mobilenetsrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMsvt-av1: Preset 10 - Bosphorus 4Kliquid-dsp: 32 - 256 - 57svt-hevc: 7 - Bosphorus 4Knettle: chachasrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMtnn: CPU - SqueezeNet v2openfoam: drivaerFastback, Small Mesh Size - Execution Timetoktx: UASTC 3 + Zstd Compression 19jpegxl: JPEG - 7blosc: blosclz bitshufflexmrig: Monero - 1Mopenfoam: motorBike - Execution Timexmrig: Wownero - 1Msrsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMgraphics-magick: HWB Color Spaceopenfoam: drivaerFastback, Small Mesh Size - Mesh Timencnn: CPU - alexnetvosk: tnn: CPU - SqueezeNet v1.1nettle: aes256primesieve: 1e12ncnn: CPU - vgg16nettle: poly1305-aesncnn: CPU - vision_transformerncnn: CPU - efficientnet-b0openssl: RSA4096ncnn: CPU - mnasnetdraco: Lionncnn: CPU - shufflenet-v2blosc: blosclz shufflesvt-av1: Preset 12 - Bosphorus 4Kncnn: CPU - resnet18openssl: RSA4096compress-zstd: 3 - Compression Speedfinancebench: Repo OpenMPsvt-av1: Preset 8 - Bosphorus 4Kncnn: CPU-v2-v2 - mobilenet-v2toktx: UASTC 3toktx: UASTC 4 + Zstd Compression 19financebench: Bonds OpenMPcompress-zstd: 19 - Compression Speedastcenc: Exhaustiveastcenc: Mediumasmfish: 1024 Hash Memory, 26 Depthc-ray: Total Time - 4K, 16 Rays Per Pixelastcenc: Thoroughtoktx: Zstd Compression 19ncnn: CPU-v3-v3 - mobilenet-v3compress-zstd: 19, Long Mode - Compression SpeedClang 14Clang 1511.603831.699472.686105446666729893817370177200000706551.8763881.74199.813.07645.3995140822.77129.745557.4211.426.5379.95.8773744.653.092.16150.123957.976154.40223987120.1169.7111.07737.495.43337.063711.3659.69533.9526.285.4669.6111.37178.182.263111523333364.721198.85563.464.574371.0842110.572103.0214077.17012.9103.19813589.4201.8140537.2639867.3814.455304.9327286.2410.53646.683398.2398.834.93316387.73.7239093.9419848.8104.37211.474806.65138.626297.79362048.5113.996.502158.34140300.99869850.21.3239103.37085924193426.00212.806914.5063.5236.314.823236.767426.46097626666727681428940166466667665975.9328951.84210.013.72443.3694915721.80928.562579.4218.327.3782.46.0603848.954.502.10751.393860.877855.56219454419.7171.0910.86751.685.53737.74711.1660.73543.1535.186.8070.7011.54180.781.116110070000063.891214.34570.165.317375.3435910.455104.1614221.47081.8104.20313469.2203.6141737.5754487.3214.346302.6407339.7210.60646.993419.9099.454.90314488.23.7039303.9219936.9103.91411.514790.25121.126383.03398448.3764.006.486158.72040390.20182350.31.3214103.53815932663225.96612.794414.5143.5236.3OpenBenchmarking.org

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.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: PNG - Encode Speed: 7Clang 14Clang 1548121620SE +/- 0.00, N = 3SE +/- 0.01, N = 311.6014.821. (CXX) g++ options: -O3 -march=native -flto -funwind-tables -Xclang -mrelax-all -O2 -fPIE -pie

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNetClang 14Clang 158001600240032004000SE +/- 2.95, N = 3SE +/- 3.00, N = 33831.703236.77MIN: 3738.1 / MAX: 3946.4MIN: 3140.1 / MAX: 3351.741. (CXX) g++ options: -O3 -march=native -flto -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2Clang 14Clang 15100200300400500SE +/- 0.95, N = 3SE +/- 0.20, N = 3472.69426.46MIN: 470.05 / MAX: 476.68MIN: 424.42 / MAX: 427.811. (CXX) g++ options: -O3 -march=native -flto -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57Clang 15Clang 14200M400M600M800M1000MSE +/- 859638.17, N = 3SE +/- 866666.67, N = 397626666710544666671. (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.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256Clang 15Clang 146000M12000M18000M24000M30000MSE +/- 46992215.82, N = 3SE +/- 16320548.29, N = 327681428940298938173701. (CC) gcc options: -pthread -m64 -Qunused-arguments -O3 -march=native -flto -lssl -lcrypto -ldl

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples / Second, More Is BettersrsRAN 22.04.1Test: OFDM_TestClang 15Clang 1440M80M120M160M200MSE +/- 635959.47, N = 3SE +/- 1946792.23, N = 3166466667177200000-latomic -ldl1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondClang 15Clang 14150K300K450K600K750KSE +/- 996.85, N = 3SE +/- 996.03, N = 3665975.93706551.881. (CC) gcc options: -O2 -O3 -march=native -flto -lrt" -lrt

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessClang 14Clang 150.4140.8281.2421.6562.07SE +/- 0.01, N = 3SE +/- 0.02, N = 31.741.841. (CC) gcc options: -fvisibility=hidden -O3 -march=native -flto -lm

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMClang 14Clang 1550100150200250SE +/- 0.90, N = 3SE +/- 0.46, N = 3199.8210.0-latomic -ldl1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm

FLAC Audio Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.4WAV To FLACClang 15Clang 1448121620SE +/- 0.03, N = 5SE +/- 0.07, N = 513.7213.081. (CXX) g++ options: -O3 -march=native -flto -fvisibility=hidden -logg -lm

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Clang 14Clang 151020304050SE +/- 0.08, N = 3SE +/- 0.16, N = 345.4043.371. (CC) gcc options: -O3 -march=native -flto -lz

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.orgms, Fewer Is BetterOpenJPEG 2.4Encode: NASA Curiosity Panorama M34Clang 14Clang 1511K22K33K44K55KSE +/- 521.26, N = 5SE +/- 295.03, N = 351408491571. (CXX) g++ options: -O3 -march=native -flto -rdynamic

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.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeClang 14Clang 15510152025SE +/- 0.06, N = 3SE +/- 0.12, N = 322.7721.811. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -flto -lSDL -lSM -lICE -lX11 -lIlmImf -lIlmImf-2_5 -lImath-2_5 -lHalf-2_5 -lIex-2_5 -lIexMath-2_5 -lIlmThread-2_5 -lIlmThread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

AOBench

AOBench is a lightweight ambient occlusion renderer, written in C. The test profile is using a size of 2048 x 2048. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeClang 14Clang 15714212835SE +/- 0.07, N = 3SE +/- 0.35, N = 429.7528.561. (CC) gcc options: -lm -O3 -march=native -flto

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMClang 14Clang 15130260390520650SE +/- 1.59, N = 3SE +/- 3.55, N = 3557.4579.4-latomic -ldl1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMClang 14Clang 1550100150200250SE +/- 0.78, N = 3SE +/- 0.15, N = 3211.4218.3-latomic -ldl1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm

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.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KClang 14Clang 15612182430SE +/- 0.21, N = 3SE +/- 0.13, N = 326.5327.371. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread -lrt -ldl -lnuma

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMClang 14Clang 1520406080100SE +/- 0.12, N = 3SE +/- 0.35, N = 379.982.4-latomic -ldl1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Clang 15Clang 14246810SE +/- 0.047, N = 3SE +/- 0.050, N = 36.0605.8771. (CC) gcc options: -O3 -pipe -march=native -flto -lncurses -lm

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.orgMFLOPS, More Is BetterQuantLib 1.21Clang 14Clang 158001600240032004000SE +/- 24.48, N = 3SE +/- 20.26, N = 33744.63848.91. (CXX) g++ options: -O3 -march=native -rdynamic

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KClang 14Clang 151224364860SE +/- 0.26, N = 3SE +/- 0.60, N = 353.0954.501. (CXX) g++ options: -O3 -march=native -flto -std=c++11 -U_FORTIFY_SOURCE -lm

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 9Clang 14Clang 150.48620.97241.45861.94482.431SE +/- 0.001, N = 3SE +/- 0.001, N = 32.1612.107

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 4KClang 14Clang 151224364860SE +/- 0.50, N = 15SE +/- 0.45, N = 1250.1251.391. (CC) gcc options: -O3 -fcommon -march=native -flto -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedClang 15Clang 148001600240032004000SE +/- 4.56, N = 3SE +/- 12.33, N = 33860.83957.91. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASClang 14Clang 152004006008001000SE +/- 14.83, N = 6SE +/- 9.69, N = 97617781. (CXX) g++ options: -flto -O3 -march=native -pthread

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4KClang 14Clang 151224364860SE +/- 0.05, N = 3SE +/- 0.09, N = 354.4055.561. (CC) gcc options: -O3 -fcommon -march=native -flto -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceClang 15Clang 14500K1000K1500K2000K2500KSE +/- 10751.06, N = 5SE +/- 22581.52, N = 5219454422398711. (CC) gcc options: -O3 -march=native -flto

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50Clang 14Clang 15510152025SE +/- 0.04, N = 3SE +/- 0.09, N = 1520.1119.71MIN: 19.33 / MAX: 21.9MIN: 18.65 / MAX: 28.151. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KClang 14Clang 151632486480SE +/- 0.07, N = 3SE +/- 0.90, N = 369.7171.091. (CXX) g++ options: -O3 -march=native -flto -std=c++11 -U_FORTIFY_SOURCE -lm

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetClang 14Clang 153691215SE +/- 0.04, N = 3SE +/- 0.08, N = 1511.0710.86MIN: 10.23 / MAX: 12.75MIN: 10.16 / MAX: 40.481. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

Nettle

GNU Nettle is a low-level cryptographic library used by GnuTLS and other software. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: sha512Clang 14Clang 15160320480640800SE +/- 0.19, N = 3SE +/- 2.18, N = 3737.49751.681. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lm -lcrypto

Opus Codec Encoding

Opus is an open audio codec. Opus is a lossy audio compression format designed primarily for interactive real-time applications over the Internet. This test uses Opus-Tools and measures the time required to encode a WAV file to Opus. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus EncodeClang 15Clang 141.24582.49163.73744.98326.229SE +/- 0.026, N = 5SE +/- 0.020, N = 55.5375.4331. (CXX) g++ options: -O3 -march=native -flto -logg -lm

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: motorBike - Mesh TimeClang 15Clang 1491827364537.7537.06-lfiniteVolume -lmeshTools-lfoamToVTK -llagrangian -lfileFormats1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lgenericPatchFields -ldynamicMesh -lOpenFOAM -ldl -lm

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mClang 14Clang 153691215SE +/- 0.04, N = 2SE +/- 0.06, N = 1411.3611.16MIN: 11.22 / MAX: 11.87MIN: 10.58 / MAX: 14.91. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

LibRaw

LibRaw is a RAW image decoder for digital camera photos. This test profile runs LibRaw's post-processing benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkClang 14Clang 151428425670SE +/- 0.19, N = 3SE +/- 0.18, N = 359.6960.731. (CXX) g++ options: -O3 -march=native -flto -fopenmp -ljpeg -lz -lm

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMClang 14Clang 15120240360480600SE +/- 0.45, N = 3SE +/- 0.15, N = 3533.9543.1-latomic -ldl1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMClang 14Clang 15120240360480600SE +/- 0.70, N = 3SE +/- 0.75, N = 3526.2535.1-latomic -ldl1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KClang 14Clang 1520406080100SE +/- 0.13, N = 3SE +/- 0.05, N = 385.4686.801. (CC) gcc options: -O3 -march=native -flto -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KClang 14Clang 151632486480SE +/- 0.73, N = 3SE +/- 0.37, N = 369.6170.701. (CXX) g++ options: -O3 -march=native -flto -std=c++11 -U_FORTIFY_SOURCE -lm

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mobilenetClang 15Clang 143691215SE +/- 0.07, N = 15SE +/- 0.09, N = 311.5411.37MIN: 10.83 / MAX: 19.94MIN: 10.82 / MAX: 12.011. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMClang 14Clang 154080120160200SE +/- 0.52, N = 3SE +/- 0.97, N = 3178.1180.7-latomic -ldl1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 10 - Input: Bosphorus 4KClang 15Clang 1420406080100SE +/- 0.11, N = 3SE +/- 0.16, N = 381.1282.26

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.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 32 - Buffer Length: 256 - Filter Length: 57Clang 15Clang 14200M400M600M800M1000MSE +/- 1479864.86, N = 3SE +/- 952773.73, N = 3110070000011152333331. (CC) gcc options: -O3 -march=native -flto -pthread -lm -lc -lliquid

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4KClang 15Clang 141428425670SE +/- 0.81, N = 3SE +/- 0.66, N = 563.8964.721. (CC) gcc options: -O3 -march=native -flto -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

Nettle

GNU Nettle is a low-level cryptographic library used by GnuTLS and other software. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: chachaClang 14Clang 1530060090012001500SE +/- 2.17, N = 3SE +/- 1.49, N = 31198.851214.34MIN: 589.65 / MAX: 3386.11MIN: 598.24 / MAX: 3435.951. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lm -lcrypto

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMClang 14Clang 15120240360480600SE +/- 0.33, N = 3SE +/- 0.62, N = 3563.4570.1-latomic -ldl1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2Clang 15Clang 141530456075SE +/- 0.10, N = 3SE +/- 0.03, N = 365.3264.57MIN: 64.97 / MAX: 65.75MIN: 64.4 / MAX: 64.851. (CXX) g++ options: -O3 -march=native -flto -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeClang 15Clang 1480160240320400375.34371.08-lfiniteVolume -lmeshTools-lfoamToVTK -llagrangian -lfileFormats1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lgenericPatchFields -ldynamicMesh -lOpenFOAM -ldl -lm

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19Clang 14Clang 153691215SE +/- 0.05, N = 3SE +/- 0.02, N = 310.5710.46

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.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: JPEG - Encode Speed: 7Clang 14Clang 1520406080100SE +/- 0.09, N = 3SE +/- 0.03, N = 3103.02104.161. (CXX) g++ options: -O3 -march=native -flto -funwind-tables -Xclang -mrelax-all -O2 -fPIE -pie

C-Blosc

C-Blosc (c-blosc2) simple, compressed, fast and persistent data store library for C. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.3Test: blosclz bitshuffleClang 14Clang 153K6K9K12K15KSE +/- 37.67, N = 3SE +/- 104.51, N = 314077.114221.41. (CXX) g++ options: -O3 -march=native -flto

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1MClang 14Clang 1515003000450060007500SE +/- 60.21, N = 3SE +/- 40.85, N = 37012.97081.81. (CXX) g++ options: -O3 -march=native -flto -fexceptions -fno-rtti -maes -Ofast -funroll-loops -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: motorBike - Execution TimeClang 15Clang 1420406080100104.20103.20-lfiniteVolume -lmeshTools-lfoamToVTK -llagrangian -lfileFormats1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lgenericPatchFields -ldynamicMesh -lOpenFOAM -ldl -lm

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1MClang 15Clang 143K6K9K12K15KSE +/- 79.54, N = 3SE +/- 32.20, N = 313469.213589.41. (CXX) g++ options: -O3 -march=native -flto -fexceptions -fno-rtti -maes -Ofast -funroll-loops -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMClang 14Clang 154080120160200SE +/- 0.70, N = 3SE +/- 5.69, N = 3201.8203.6-latomic -ldl1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm

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.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: HWB Color SpaceClang 14Clang 1530060090012001500SE +/- 2.52, N = 3SE +/- 4.04, N = 3140514171. (CC) gcc options: -fopenmp -O3 -march=native -flto -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh TimeClang 15Clang 1491827364537.5837.26-lfiniteVolume -lmeshTools-lfoamToVTK -llagrangian -lfileFormats1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lgenericPatchFields -ldynamicMesh -lOpenFOAM -ldl -lm

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: alexnetClang 14Clang 15246810SE +/- 0.04, N = 3SE +/- 0.03, N = 157.387.32MIN: 7.09 / MAX: 8.55MIN: 6.89 / MAX: 16.131. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

VOSK Speech Recognition Toolkit

VOSK is an open-source offline speech recognition API/toolkit. VOSK supports speech recognition in 17 languages and has a variety of models available and interfaces for different programming languages. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterVOSK Speech Recognition Toolkit 0.3.21Clang 14Clang 1548121620SE +/- 0.16, N = 5SE +/- 0.10, N = 1314.4614.35

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1Clang 14Clang 1570140210280350SE +/- 0.21, N = 3SE +/- 0.16, N = 3304.93302.64MIN: 304.53 / MAX: 305.79MIN: 302.22 / MAX: 303.121. (CXX) g++ options: -O3 -march=native -flto -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

Nettle

GNU Nettle is a low-level cryptographic library used by GnuTLS and other software. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: aes256Clang 14Clang 1516003200480064008000SE +/- 2.05, N = 3SE +/- 2.86, N = 37286.247339.72MIN: 5504.06 / MAX: 10861.66MIN: 5536.69 / MAX: 10939.291. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lm -lcrypto

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 8.0Length: 1e12Clang 15Clang 143691215SE +/- 0.01, N = 3SE +/- 0.02, N = 310.6110.541. (CXX) g++ options: -O3 -march=native -flto

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vgg16Clang 15Clang 141122334455SE +/- 0.27, N = 15SE +/- 0.32, N = 346.9946.68MIN: 44.38 / MAX: 56.74MIN: 45.34 / MAX: 53.651. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

Nettle

GNU Nettle is a low-level cryptographic library used by GnuTLS and other software. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: poly1305-aesClang 14Clang 157001400210028003500SE +/- 1.13, N = 3SE +/- 2.21, N = 33398.233419.901. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lm -lcrypto

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerClang 15Clang 1420406080100SE +/- 0.20, N = 15SE +/- 0.35, N = 399.4598.83MIN: 97.82 / MAX: 192.86MIN: 97.58 / MAX: 104.021. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0Clang 14Clang 151.10932.21863.32794.43725.5465SE +/- 0.03, N = 3SE +/- 0.02, N = 154.934.90MIN: 4.83 / MAX: 5.47MIN: 4.71 / MAX: 15.11. (CXX) g++ options: -O3 -march=native -flto -rdynamic -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.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Clang 15Clang 1470K140K210K280K350KSE +/- 146.06, N = 3SE +/- 17.46, N = 3314488.2316387.71. (CC) gcc options: -pthread -m64 -Qunused-arguments -O3 -march=native -flto -lssl -lcrypto -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetClang 14Clang 150.8371.6742.5113.3484.185SE +/- 0.02, N = 3SE +/- 0.02, N = 153.723.70MIN: 3.63 / MAX: 4.33MIN: 3.52 / MAX: 5.971. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

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.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: LionClang 15Clang 148001600240032004000SE +/- 5.46, N = 3SE +/- 6.89, N = 3393039091. (CXX) g++ options: -O3 -march=native -flto

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: shufflenet-v2Clang 14Clang 150.88651.7732.65953.5464.4325SE +/- 0.04, N = 3SE +/- 0.02, N = 153.943.92MIN: 3.8 / MAX: 4.39MIN: 3.73 / MAX: 141. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

C-Blosc

C-Blosc (c-blosc2) simple, compressed, fast and persistent data store library for C. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.3Test: blosclz shuffleClang 14Clang 154K8K12K16K20KSE +/- 46.57, N = 3SE +/- 96.37, N = 319848.819936.91. (CXX) g++ options: -O3 -march=native -flto

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 12 - Input: Bosphorus 4KClang 15Clang 1420406080100SE +/- 0.24, N = 3SE +/- 0.11, N = 3103.91104.37

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet18Clang 15Clang 143691215SE +/- 0.10, N = 15SE +/- 0.03, N = 311.5111.47MIN: 10.37 / MAX: 14.62MIN: 10.93 / MAX: 12.711. (CXX) g++ options: -O3 -march=native -flto -rdynamic -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.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096Clang 15Clang 1410002000300040005000SE +/- 2.63, N = 3SE +/- 2.20, N = 34790.24806.61. (CC) gcc options: -pthread -m64 -Qunused-arguments -O3 -march=native -flto -lssl -lcrypto -ldl

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Compression SpeedClang 15Clang 1411002200330044005500SE +/- 14.64, N = 3SE +/- 6.01, N = 35121.15138.61. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPClang 15Clang 146K12K18K24K30KSE +/- 284.62, N = 5SE +/- 372.37, N = 326383.0326297.791. (CXX) g++ options: -O3 -march=native -fopenmp

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.2Encoder Mode: Preset 8 - Input: Bosphorus 4KClang 15Clang 141122334455SE +/- 0.45, N = 3SE +/- 0.34, N = 348.3848.51

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v2-v2 - Model: mobilenet-v2Clang 15Clang 140.91.82.73.64.5SE +/- 0.03, N = 15SE +/- 0.05, N = 34.003.99MIN: 3.71 / MAX: 13.25MIN: 3.8 / MAX: 4.541. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3Clang 14Clang 15246810SE +/- 0.004, N = 3SE +/- 0.009, N = 36.5026.486

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 19Clang 15Clang 144080120160200SE +/- 0.25, N = 3SE +/- 0.20, N = 3158.72158.34

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPClang 15Clang 149K18K27K36K45KSE +/- 154.34, N = 3SE +/- 20.59, N = 340390.2040301.001. (CXX) g++ options: -O3 -march=native -fopenmp

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedClang 14Clang 151122334455SE +/- 0.06, N = 3SE +/- 0.06, N = 350.250.31. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma

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.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ExhaustiveClang 15Clang 140.29790.59580.89371.19161.4895SE +/- 0.0029, N = 3SE +/- 0.0011, N = 31.32141.32391. (CXX) g++ options: -O3 -march=native -flto -pthread

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: MediumClang 14Clang 1520406080100SE +/- 0.18, N = 3SE +/- 0.12, N = 3103.37103.541. (CXX) g++ options: -O3 -march=native -flto -pthread

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthClang 14Clang 1513M26M39M52M65MSE +/- 746401.00, N = 3SE +/- 68853.93, N = 35924193459326632

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.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelClang 14Clang 15612182430SE +/- 0.04, N = 3SE +/- 0.08, N = 326.0025.971. (CC) gcc options: -lm -lpthread -O3 -march=native -flto

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.orgMT/s, More Is BetterASTC Encoder 4.0Preset: ThoroughClang 15Clang 143691215SE +/- 0.02, N = 3SE +/- 0.02, N = 312.7912.811. (CXX) g++ options: -O3 -march=native -flto -pthread

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19Clang 15Clang 1448121620SE +/- 0.03, N = 3SE +/- 0.11, N = 314.5114.51

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU-v3-v3 - Model: mobilenet-v3Clang 15Clang 140.7921.5842.3763.1683.96SE +/- 0.02, N = 15SE +/- 0.02, N = 33.523.52MIN: 3.33 / MAX: 11.49MIN: 3.44 / MAX: 3.991. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedClang 14Clang 15816243240SE +/- 0.03, N = 3SE +/- 0.00, N = 336.336.31. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma

Clang 14

Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 500GB Western Digital WDS500G3X0C-00SJG0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc5daily20220915-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-03294e1 2022-09-16 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.228, Compiler: Clang 14.0.6-1~oibaf~j, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016
Python Notes: Python 3.10.4
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 16 September 2022 17:28 by user phoronix.

Clang 15

Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 500GB Western Digital WDS500G3X0C-00SJG0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200

OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc5daily20220915-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-03294e1 2022-09-16 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.228, Compiler: Clang 15.0.1-++20220915084339+3637f345d2ab-1~exp1~20220915084350.58, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Environment Notes: CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016
Python Notes: Python 3.10.4
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 17 September 2022 08:19 by user phoronix.