2990WX March

AMD Ryzen Threadripper 2990WX 32-Core testing with a ASUS ROG ZENITH EXTREME (1701 BIOS) and Gigabyte AMD Radeon RX 470/480/570/570X/580/580X/590 4GB on Ubuntu 20.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2103152-HA-2990WXMAR69
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

Limit displaying results to tests within:

C/C++ Compiler Tests 2 Tests
CPU Massive 2 Tests
Creator Workloads 6 Tests
Game Development 2 Tests
HPC - High Performance Computing 2 Tests
Imaging 2 Tests
Machine Learning 2 Tests
Multi-Core 3 Tests
Software Defined Radio 4 Tests
Server CPU Tests 2 Tests
Texture Compression 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
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
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
1
March 14
  11 Hours, 12 Minutes
2
March 15
  7 Hours, 34 Minutes
3
March 15
  9 Hours, 26 Minutes
Invert Hiding All Results Option
  9 Hours, 24 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):


2990WX MarchProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen Resolution123AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads)ASUS ROG ZENITH EXTREME (1701 BIOS)AMD 17h32GBSamsung SSD 970 EVO 500GB + 250GB Western Digital WDS250G2X0C-00L350Gigabyte AMD Radeon RX 470/480/570/570X/580/580X/590 4GB (1244/1750MHz)Realtek ALC1220LG Ultra HDIntel I211 + Qualcomm Atheros QCA6174 802.11ac + Wilocity Wil6200 802.11adUbuntu 20.105.8.0-44-generic (x86_64)GNOME Shell 3.38.1X Server 1.20.94.6 Mesa 20.2.1 (LLVM 11.0.0)1.2.131GCC 10.2.0ext41920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x800820dPython Details- Python 3.8.6Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

123Result OverviewPhoronix Test Suite 10.6.0100%101%101%102%Mobile Neural NetworkGNU RadiooneDNNLuaRadioAOM AV1SysbenchBasis UniversalsrsLTEJPEG XL DecodingLiquid-DSPJPEG XLsimdjsonASTC Encoder

2990WX Marchsimdjson: Kostyasimdjson: LargeRandsimdjson: PartialTweetssimdjson: DistinctUserIDjpegxl: PNG - 5jpegxl: PNG - 7jpegxl: PNG - 8jpegxl: JPEG - 5jpegxl: JPEG - 7jpegxl: JPEG - 8jpegxl-decode: 1jpegxl-decode: Allsrslte: OFDM_Testsrslte: PHY_DL_Testsrslte: PHY_DL_Testluaradio: Five Back to Back FIR Filtersluaradio: FM Deemphasis Filterluaradio: Hilbert Transformluaradio: Complex Phasegnuradio: Five Back to Back FIR Filtersgnuradio: Signal Source (Cosine)gnuradio: FIR Filtergnuradio: IIR Filtergnuradio: FM Deemphasis Filtergnuradio: Hilbert Transformaom-av1: Speed 0 Two-Passaom-av1: Speed 4 Two-Passaom-av1: Speed 6 Realtimeaom-av1: Speed 6 Two-Passaom-av1: Speed 8 Realtimeonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUliquid-dsp: 1 - 256 - 57liquid-dsp: 2 - 256 - 57liquid-dsp: 4 - 256 - 57liquid-dsp: 8 - 256 - 57liquid-dsp: 16 - 256 - 57liquid-dsp: 32 - 256 - 57liquid-dsp: 64 - 256 - 57astcenc: Mediumastcenc: Thoroughastcenc: Exhaustivebasis: ETC1Sbasis: UASTC Level 0basis: UASTC Level 2basis: UASTC Level 3mnn: SqueezeNetV1.0mnn: resnet-v2-50mnn: MobileNetV2_224mnn: mobilenet-v1-1.0mnn: inception-v3sysbench: RAM / Memorysysbench: CPU1232.280.922.963.3258.848.260.7253.2653.4722.9132.45173.9182300000227.986.2493.1405.098.1570.6369.93139.8601.9575.8809.1411.90.214.5117.2413.3352.036.6819412.45042.511773.5752120.40346.960315.9356725.46452.631223.8001613898.83886.8613965.63918.541.9161714208.13947.671.5598860627667120953333236713333460310000835613333147776666716169666675.20656.394445.642027.4347.49315.67125.0589.06238.0155.8714.31048.0486791.1257045.062.290.922.973.3358.358.260.7153.6054.0823.4932.59174.3582266667228.786.2488.1403.297.4565.6384.13176.9599.5584.0804.0410.30.214.4717.1513.3853.326.6814512.09622.528783.5922420.31166.966715.9299225.35402.629573.7918513707.43917.8013883.63897.241.8911214041.23911.831.5568359917000119076667236780000460586667835380000147463333316166000005.19206.387146.010927.1087.47715.72325.1638.78338.1515.9104.23448.0826809.3157054.822.290.922.973.3358.678.250.7252.8553.1923.3032.55174.9582733333229.186.5491.9404.797.4567.3373.63144.5607.0580.3791.9412.40.214.5017.1913.3353.856.7247612.52692.537473.6045420.40696.987315.9354225.41722.627733.7890413632.53817.6413706.63912.251.7670613829.23928.481.5651160272667120150000237340000460676667836323333147886666716147000005.21636.401545.710127.5167.49515.79225.1608.91237.5615.7184.04147.2106733.7057053.00OpenBenchmarking.org

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.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: Kostya1230.51531.03061.54592.06122.5765SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.282.292.291. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: Kostya123246810Min: 2.28 / Avg: 2.28 / Max: 2.28Min: 2.29 / Avg: 2.29 / Max: 2.29Min: 2.28 / Avg: 2.29 / Max: 2.291. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: LargeRandom1230.2070.4140.6210.8281.035SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.920.920.921. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: LargeRandom123246810Min: 0.92 / Avg: 0.92 / Max: 0.92Min: 0.92 / Avg: 0.92 / Max: 0.92Min: 0.92 / Avg: 0.92 / Max: 0.921. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: PartialTweets1230.66831.33662.00492.67323.3415SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.962.972.971. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: PartialTweets123246810Min: 2.96 / Avg: 2.96 / Max: 2.97Min: 2.96 / Avg: 2.97 / Max: 2.97Min: 2.97 / Avg: 2.97 / Max: 2.971. (CXX) g++ options: -O3 -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: DistinctUserID1230.74931.49862.24792.99723.7465SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.323.333.331. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: DistinctUserID123246810Min: 3.32 / Avg: 3.32 / Max: 3.33Min: 3.32 / Avg: 3.33 / Max: 3.33Min: 3.32 / Avg: 3.33 / Max: 3.331. (CXX) g++ options: -O3 -pthread

JPEG XL

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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: PNG - Encode Speed: 51231326395265SE +/- 0.09, N = 3SE +/- 0.38, N = 3SE +/- 0.89, N = 358.8458.3558.671. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: PNG - Encode Speed: 51231224364860Min: 58.66 / Avg: 58.84 / Max: 58.98Min: 57.82 / Avg: 58.35 / Max: 59.09Min: 57.51 / Avg: 58.67 / Max: 60.421. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: PNG - Encode Speed: 7123246810SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 38.268.268.251. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: PNG - Encode Speed: 71233691215Min: 8.23 / Avg: 8.26 / Max: 8.28Min: 8.16 / Avg: 8.26 / Max: 8.33Min: 8.16 / Avg: 8.25 / Max: 8.291. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: PNG - Encode Speed: 81230.1620.3240.4860.6480.81SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.720.710.721. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: PNG - Encode Speed: 8123246810Min: 0.72 / Avg: 0.72 / Max: 0.73Min: 0.71 / Avg: 0.71 / Max: 0.72Min: 0.71 / Avg: 0.72 / Max: 0.721. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: JPEG - Encode Speed: 51231224364860SE +/- 0.28, N = 3SE +/- 0.61, N = 3SE +/- 0.76, N = 353.2653.6052.851. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: JPEG - Encode Speed: 51231122334455Min: 52.71 / Avg: 53.26 / Max: 53.59Min: 52.45 / Avg: 53.6 / Max: 54.55Min: 51.88 / Avg: 52.85 / Max: 54.351. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: JPEG - Encode Speed: 71231224364860SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.40, N = 353.4754.0853.191. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: JPEG - Encode Speed: 71231122334455Min: 53.36 / Avg: 53.47 / Max: 53.54Min: 53.99 / Avg: 54.08 / Max: 54.17Min: 52.45 / Avg: 53.19 / Max: 53.821. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: JPEG - Encode Speed: 8123612182430SE +/- 0.16, N = 3SE +/- 0.15, N = 3SE +/- 0.15, N = 322.9123.4923.301. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL 0.3.3Input: JPEG - Encode Speed: 8123510152025Min: 22.7 / Avg: 22.91 / Max: 23.23Min: 23.24 / Avg: 23.49 / Max: 23.76Min: 23.03 / Avg: 23.3 / Max: 23.541. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl

JPEG XL Decoding

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is suited for JPEG XL decode performance testing to PNG output file, the pts/jpexl test is for encode performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding 0.3.3CPU Threads: 1123816243240SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 332.4532.5932.55
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding 0.3.3CPU Threads: 1123714212835Min: 32.43 / Avg: 32.45 / Max: 32.47Min: 32.46 / Avg: 32.59 / Max: 32.67Min: 32.49 / Avg: 32.55 / Max: 32.62

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding 0.3.3CPU Threads: All1234080120160200SE +/- 0.36, N = 3SE +/- 0.60, N = 3SE +/- 0.29, N = 3173.91174.35174.95
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding 0.3.3CPU Threads: All123306090120150Min: 173.19 / Avg: 173.91 / Max: 174.35Min: 173.39 / Avg: 174.35 / Max: 175.44Min: 174.37 / Avg: 174.95 / Max: 175.31

srsLTE

srsLTE is an open-source LTE software radio suite created by Software Radio Systems (SRS). srsLTE can be used for building your own software defined (SDR) LTE mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples / Second, More Is BettersrsLTE 20.10.1Test: OFDM_Test12320M40M60M80M100MSE +/- 57735.03, N = 3SE +/- 166666.67, N = 3SE +/- 133333.33, N = 38230000082266667827333331. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
OpenBenchmarking.orgSamples / Second, More Is BettersrsLTE 20.10.1Test: OFDM_Test12314M28M42M56M70MMin: 82200000 / Avg: 82300000 / Max: 82400000Min: 82100000 / Avg: 82266666.67 / Max: 82600000Min: 82600000 / Avg: 82733333.33 / Max: 830000001. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_Test12350100150200250SE +/- 1.36, N = 3SE +/- 1.76, N = 3SE +/- 0.86, N = 3227.9228.7229.11. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
OpenBenchmarking.orgeNb Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_Test1234080120160200Min: 225.5 / Avg: 227.93 / Max: 230.2Min: 225.3 / Avg: 228.73 / Max: 231.1Min: 227.4 / Avg: 229.1 / Max: 230.21. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f

OpenBenchmarking.orgUE Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_Test12320406080100SE +/- 0.48, N = 3SE +/- 0.43, N = 3SE +/- 0.37, N = 386.286.286.51. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
OpenBenchmarking.orgUE Mb/s, More Is BettersrsLTE 20.10.1Test: PHY_DL_Test1231632486480Min: 85.2 / Avg: 86.17 / Max: 86.7Min: 85.5 / Avg: 86.23 / Max: 87Min: 85.8 / Avg: 86.53 / Max: 871. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f

LuaRadio

LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR Filters123110220330440550SE +/- 1.15, N = 3SE +/- 0.58, N = 3SE +/- 1.14, N = 3493.1488.1491.9
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Five Back to Back FIR Filters12390180270360450Min: 490.9 / Avg: 493.07 / Max: 494.8Min: 487 / Avg: 488.13 / Max: 488.9Min: 489.7 / Avg: 491.9 / Max: 493.5

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis Filter12390180270360450SE +/- 0.51, N = 3SE +/- 2.02, N = 3SE +/- 0.90, N = 3405.0403.2404.7
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis Filter12370140210280350Min: 404 / Avg: 405 / Max: 405.7Min: 399.2 / Avg: 403.23 / Max: 405.4Min: 402.9 / Avg: 404.67 / Max: 405.8

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert Transform12320406080100SE +/- 0.17, N = 3SE +/- 0.52, N = 3SE +/- 0.45, N = 398.197.497.4
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert Transform12320406080100Min: 97.9 / Avg: 98.07 / Max: 98.4Min: 96.4 / Avg: 97.43 / Max: 98.1Min: 96.5 / Avg: 97.37 / Max: 98

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex Phase123120240360480600SE +/- 0.23, N = 3SE +/- 2.48, N = 3SE +/- 3.02, N = 3570.6565.6567.3
OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex Phase123100200300400500Min: 570.1 / Avg: 570.57 / Max: 570.8Min: 560.9 / Avg: 565.63 / Max: 569.3Min: 561.3 / Avg: 567.3 / Max: 570.9

GNU Radio

GNU Radio is a free software development toolkit providing signal processing blocks to implement software-defined radios (SDR) and signal processing systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR Filters12380160240320400SE +/- 5.54, N = 9SE +/- 3.80, N = 3SE +/- 4.94, N = 9369.9384.1373.61. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR Filters12370140210280350Min: 350.3 / Avg: 369.89 / Max: 392.1Min: 376.8 / Avg: 384.1 / Max: 389.6Min: 352.3 / Avg: 373.61 / Max: 3921. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)1237001400210028003500SE +/- 11.69, N = 9SE +/- 18.55, N = 3SE +/- 12.27, N = 93139.83176.93144.51. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)1236001200180024003000Min: 3090.3 / Avg: 3139.83 / Max: 3198.4Min: 3141.4 / Avg: 3176.87 / Max: 3204Min: 3092.1 / Avg: 3144.47 / Max: 31851. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR Filter123130260390520650SE +/- 4.29, N = 9SE +/- 2.03, N = 3SE +/- 1.71, N = 9601.9599.5607.01. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR Filter123110220330440550Min: 568 / Avg: 601.94 / Max: 609.8Min: 596.1 / Avg: 599.47 / Max: 603.1Min: 597.9 / Avg: 607 / Max: 612.91. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR Filter123130260390520650SE +/- 3.61, N = 9SE +/- 1.47, N = 3SE +/- 1.18, N = 9575.8584.0580.31. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR Filter123100200300400500Min: 553.1 / Avg: 575.82 / Max: 586.6Min: 581.4 / Avg: 583.97 / Max: 586.5Min: 576.3 / Avg: 580.28 / Max: 586.61. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis Filter1232004006008001000SE +/- 2.77, N = 9SE +/- 2.87, N = 3SE +/- 11.33, N = 9809.1804.0791.91. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis Filter123140280420560700Min: 798.9 / Avg: 809.13 / Max: 822.5Min: 798.3 / Avg: 803.97 / Max: 807.6Min: 719.9 / Avg: 791.88 / Max: 818.91. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert Transform12390180270360450SE +/- 2.03, N = 9SE +/- 1.57, N = 3SE +/- 1.42, N = 9411.9410.3412.41. 3.8.1.0
OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert Transform12370140210280350Min: 396.5 / Avg: 411.88 / Max: 417.8Min: 408.6 / Avg: 410.27 / Max: 413.4Min: 405.8 / Avg: 412.44 / Max: 419.21. 3.8.1.0

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) run on the CPU with a sample 1080p video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 0 Two-Pass1230.04730.09460.14190.18920.2365SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.210.210.211. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 0 Two-Pass12312345Min: 0.21 / Avg: 0.21 / Max: 0.21Min: 0.2 / Avg: 0.21 / Max: 0.21Min: 0.21 / Avg: 0.21 / Max: 0.211. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 4 Two-Pass1231.01482.02963.04444.05925.074SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 34.514.474.501. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 4 Two-Pass123246810Min: 4.47 / Avg: 4.51 / Max: 4.55Min: 4.46 / Avg: 4.47 / Max: 4.48Min: 4.46 / Avg: 4.5 / Max: 4.531. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 6 Realtime12348121620SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 317.2417.1517.191. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 6 Realtime12348121620Min: 17.21 / Avg: 17.24 / Max: 17.27Min: 17.06 / Avg: 17.15 / Max: 17.19Min: 17.01 / Avg: 17.19 / Max: 17.291. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 6 Two-Pass1233691215SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 313.3313.3813.331. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 6 Two-Pass12348121620Min: 13.18 / Avg: 13.33 / Max: 13.5Min: 13.21 / Avg: 13.38 / Max: 13.6Min: 13.18 / Avg: 13.33 / Max: 13.451. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 8 Realtime1231224364860SE +/- 0.83, N = 3SE +/- 0.82, N = 3SE +/- 0.00, N = 352.0353.3253.851. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2.1-rcEncoder Mode: Speed 8 Realtime1231122334455Min: 50.46 / Avg: 52.03 / Max: 53.28Min: 51.79 / Avg: 53.32 / Max: 54.61Min: 53.85 / Avg: 53.85 / Max: 53.861. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

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 initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU123246810SE +/- 0.09926, N = 3SE +/- 0.02263, N = 3SE +/- 0.01807, N = 36.681946.681456.72476MIN: 5.95MIN: 5.95MIN: 5.91. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU1233691215Min: 6.49 / Avg: 6.68 / Max: 6.82Min: 6.64 / Avg: 6.68 / Max: 6.71Min: 6.69 / Avg: 6.72 / Max: 6.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU1233691215SE +/- 0.13, N = 15SE +/- 0.16, N = 4SE +/- 0.14, N = 1512.4512.1012.53MIN: 11.43MIN: 11.23MIN: 11.331. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU12348121620Min: 11.81 / Avg: 12.45 / Max: 13.39Min: 11.7 / Avg: 12.1 / Max: 12.46Min: 11.69 / Avg: 12.53 / Max: 13.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU1230.57091.14181.71272.28362.8545SE +/- 0.00876, N = 3SE +/- 0.02431, N = 3SE +/- 0.02758, N = 32.511772.528782.53747MIN: 2.32MIN: 2.33MIN: 2.321. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU123246810Min: 2.5 / Avg: 2.51 / Max: 2.53Min: 2.49 / Avg: 2.53 / Max: 2.58Min: 2.48 / Avg: 2.54 / Max: 2.571. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU1230.8111.6222.4333.2444.055SE +/- 0.00442, N = 3SE +/- 0.00737, N = 3SE +/- 0.01752, N = 33.575213.592243.60454MIN: 3.17MIN: 3.18MIN: 1.971. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU123246810Min: 3.57 / Avg: 3.58 / Max: 3.58Min: 3.58 / Avg: 3.59 / Max: 3.61Min: 3.58 / Avg: 3.6 / Max: 3.641. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU123510152025SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 320.4020.3120.41MIN: 19.97MIN: 18.74MIN: 19.861. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU123510152025Min: 20.39 / Avg: 20.4 / Max: 20.41Min: 20.05 / Avg: 20.31 / Max: 20.46Min: 20.39 / Avg: 20.41 / Max: 20.421. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU123246810SE +/- 0.01479, N = 3SE +/- 0.01848, N = 3SE +/- 0.02797, N = 36.960316.966716.98731MIN: 6.16MIN: 6.12MIN: 6.091. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU1233691215Min: 6.94 / Avg: 6.96 / Max: 6.99Min: 6.93 / Avg: 6.97 / Max: 6.99Min: 6.93 / Avg: 6.99 / Max: 7.021. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU1231.33552.6714.00655.3426.6775SE +/- 0.01143, N = 3SE +/- 0.00690, N = 3SE +/- 0.00102, N = 35.935675.929925.93542MIN: 5.52MIN: 5.5MIN: 5.491. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU123246810Min: 5.91 / Avg: 5.94 / Max: 5.95Min: 5.92 / Avg: 5.93 / Max: 5.94Min: 5.93 / Avg: 5.94 / Max: 5.941. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU123612182430SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 325.4625.3525.42MIN: 24.65MIN: 24.3MIN: 24.21. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU123612182430Min: 25.42 / Avg: 25.46 / Max: 25.53Min: 25.33 / Avg: 25.35 / Max: 25.38Min: 25.31 / Avg: 25.42 / Max: 25.521. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU1230.5921.1841.7762.3682.96SE +/- 0.00877, N = 3SE +/- 0.00861, N = 3SE +/- 0.00732, N = 32.631222.629572.62773MIN: 2.5MIN: 2.5MIN: 2.511. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU123246810Min: 2.61 / Avg: 2.63 / Max: 2.64Min: 2.62 / Avg: 2.63 / Max: 2.65Min: 2.61 / Avg: 2.63 / Max: 2.641. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU1230.8551.712.5653.424.275SE +/- 0.00430, N = 3SE +/- 0.00167, N = 3SE +/- 0.00762, N = 33.800163.791853.78904MIN: 3.72MIN: 3.71MIN: 3.711. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU123246810Min: 3.79 / Avg: 3.8 / Max: 3.81Min: 3.79 / Avg: 3.79 / Max: 3.79Min: 3.77 / Avg: 3.79 / Max: 3.81. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU1233K6K9K12K15KSE +/- 154.68, N = 7SE +/- 145.74, N = 7SE +/- 176.85, N = 513898.813707.413632.5MIN: 13032.7MIN: 12922.4MIN: 12827.21. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU1232K4K6K8K10KMin: 13227 / Avg: 13898.77 / Max: 14340.1Min: 13160.5 / Avg: 13707.43 / Max: 14151.1Min: 12984.5 / Avg: 13632.48 / Max: 14007.71. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU1238001600240032004000SE +/- 17.43, N = 3SE +/- 27.48, N = 3SE +/- 39.34, N = 33886.863917.803817.64MIN: 3655.72MIN: 3769.84MIN: 3695.791. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU1237001400210028003500Min: 3862.51 / Avg: 3886.86 / Max: 3920.65Min: 3865.14 / Avg: 3917.8 / Max: 3957.77Min: 3774.09 / Avg: 3817.64 / Max: 3896.171. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU1233K6K9K12K15KSE +/- 178.47, N = 5SE +/- 182.34, N = 5SE +/- 149.77, N = 1213965.613883.613706.6MIN: 13115.7MIN: 12751.7MIN: 12260.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU1232K4K6K8K10KMin: 13378.5 / Avg: 13965.56 / Max: 14404.4Min: 13340.9 / Avg: 13883.58 / Max: 14312.8Min: 12368.9 / Avg: 13706.61 / Max: 14337.51. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU1238001600240032004000SE +/- 20.29, N = 3SE +/- 11.92, N = 3SE +/- 15.33, N = 33918.543897.243912.25MIN: 3855MIN: 3835.75MIN: 3811.141. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU1237001400210028003500Min: 3897.08 / Avg: 3918.54 / Max: 3959.1Min: 3873.53 / Avg: 3897.24 / Max: 3911.18Min: 3896.45 / Avg: 3912.25 / Max: 3942.911. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU1230.43110.86221.29331.72442.1555SE +/- 0.05033, N = 15SE +/- 0.06076, N = 15SE +/- 0.06494, N = 151.916171.891121.76706MIN: 1.23MIN: 1.25MIN: 1.221. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU123246810Min: 1.52 / Avg: 1.92 / Max: 2.12Min: 1.54 / Avg: 1.89 / Max: 2.15Min: 1.48 / Avg: 1.77 / Max: 2.21. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU1233K6K9K12K15KSE +/- 92.65, N = 3SE +/- 125.70, N = 3SE +/- 92.53, N = 314208.114041.213829.2MIN: 13948.2MIN: 13720.3MIN: 136211. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU1232K4K6K8K10KMin: 14022.8 / Avg: 14208.07 / Max: 14303.7Min: 13794.8 / Avg: 14041.23 / Max: 14207.5Min: 13714.2 / Avg: 13829.23 / Max: 14012.31. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU1238001600240032004000SE +/- 27.19, N = 3SE +/- 8.79, N = 3SE +/- 15.75, N = 33947.673911.833928.48MIN: 3865.39MIN: 3788.89MIN: 3822.061. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU1237001400210028003500Min: 3908.16 / Avg: 3947.67 / Max: 3999.79Min: 3894.82 / Avg: 3911.83 / Max: 3924.17Min: 3904.79 / Avg: 3928.48 / Max: 3958.311. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU1230.35210.70421.05631.40841.7605SE +/- 0.00396, N = 3SE +/- 0.00329, N = 3SE +/- 0.00128, N = 31.559881.556831.56511MIN: 1.43MIN: 1.43MIN: 1.441. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU123246810Min: 1.55 / Avg: 1.56 / Max: 1.57Min: 1.55 / Avg: 1.56 / Max: 1.56Min: 1.56 / Avg: 1.57 / Max: 1.571. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -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: 1 - Buffer Length: 256 - Filter Length: 5712313M26M39M52M65MSE +/- 6385.75, N = 3SE +/- 65592.17, N = 3SE +/- 229485.17, N = 36062766759917000602726671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 5712311M22M33M44M55MMin: 60616000 / Avg: 60627666.67 / Max: 60638000Min: 59794000 / Avg: 59917000 / Max: 60018000Min: 59830000 / Avg: 60272666.67 / Max: 605990001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 5712330M60M90M120M150MSE +/- 8819.17, N = 3SE +/- 524859.77, N = 3SE +/- 165025.25, N = 31209533331190766671201500001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 5712320M40M60M80M100MMin: 120940000 / Avg: 120953333.33 / Max: 120970000Min: 118400000 / Avg: 119076666.67 / Max: 120110000Min: 119920000 / Avg: 120150000 / Max: 1204700001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 5712350M100M150M200M250MSE +/- 161279.61, N = 3SE +/- 528488.41, N = 3SE +/- 585946.53, N = 32367133332367800002373400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 5712340M80M120M160M200MMin: 236410000 / Avg: 236713333.33 / Max: 236960000Min: 235850000 / Avg: 236780000 / Max: 237680000Min: 236240000 / Avg: 237340000 / Max: 2382400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57123100M200M300M400M500MSE +/- 920887.25, N = 3SE +/- 668539.04, N = 3SE +/- 870868.02, N = 34603100004605866674606766671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 5712380M160M240M320M400MMin: 458710000 / Avg: 460310000 / Max: 461900000Min: 459620000 / Avg: 460586666.67 / Max: 461870000Min: 459230000 / Avg: 460676666.67 / Max: 4622400001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57123200M400M600M800M1000MSE +/- 414782.41, N = 3SE +/- 1629918.20, N = 3SE +/- 670232.13, N = 38356133338353800008363233331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57123140M280M420M560M700MMin: 834840000 / Avg: 835613333.33 / Max: 836260000Min: 832160000 / Avg: 835380000 / Max: 837430000Min: 835000000 / Avg: 836323333.33 / Max: 8371700001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 32 - Buffer Length: 256 - Filter Length: 57123300M600M900M1200M1500MSE +/- 2370185.18, N = 3SE +/- 5967783.88, N = 3SE +/- 4056818.68, N = 31477766667147463333314788666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 32 - Buffer Length: 256 - Filter Length: 57123300M600M900M1200M1500MMin: 1474300000 / Avg: 1477766666.67 / Max: 1482300000Min: 1462700000 / Avg: 1474633333.33 / Max: 1480800000Min: 1471200000 / Avg: 1478866666.67 / Max: 14850000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57123300M600M900M1200M1500MSE +/- 1354416.64, N = 3SE +/- 1026320.29, N = 3SE +/- 1193035.34, N = 31616966667161660000016147000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57123300M600M900M1200M1500MMin: 1615100000 / Avg: 1616966666.67 / Max: 1619600000Min: 1615200000 / Avg: 1616600000 / Max: 1618600000Min: 1613000000 / Avg: 1614700000 / Max: 16170000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Medium1231.17372.34743.52114.69485.8685SE +/- 0.0362, N = 3SE +/- 0.0034, N = 3SE +/- 0.0222, N = 35.20655.19205.21631. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Medium123246810Min: 5.15 / Avg: 5.21 / Max: 5.28Min: 5.19 / Avg: 5.19 / Max: 5.2Min: 5.19 / Avg: 5.22 / Max: 5.261. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Thorough123246810SE +/- 0.0026, N = 3SE +/- 0.0067, N = 3SE +/- 0.0153, N = 36.39446.38716.40151. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Thorough1233691215Min: 6.39 / Avg: 6.39 / Max: 6.4Min: 6.38 / Avg: 6.39 / Max: 6.4Min: 6.38 / Avg: 6.4 / Max: 6.431. (CXX) g++ options: -O3 -flto -pthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Exhaustive1231020304050SE +/- 0.05, N = 3SE +/- 0.30, N = 3SE +/- 0.06, N = 345.6446.0145.711. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.4Preset: Exhaustive123918273645Min: 45.55 / Avg: 45.64 / Max: 45.69Min: 45.69 / Avg: 46.01 / Max: 46.6Min: 45.59 / Avg: 45.71 / Max: 45.781. (CXX) g++ options: -O3 -flto -pthread

Basis Universal

Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1S123612182430SE +/- 0.27, N = 3SE +/- 0.16, N = 3SE +/- 0.05, N = 327.4327.1127.521. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: ETC1S123612182430Min: 26.95 / Avg: 27.43 / Max: 27.88Min: 26.79 / Avg: 27.11 / Max: 27.28Min: 27.44 / Avg: 27.52 / Max: 27.61. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 0123246810SE +/- 0.013, N = 3SE +/- 0.011, N = 3SE +/- 0.038, N = 37.4937.4777.4951. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 01233691215Min: 7.47 / Avg: 7.49 / Max: 7.52Min: 7.46 / Avg: 7.48 / Max: 7.5Min: 7.42 / Avg: 7.5 / Max: 7.551. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 212348121620SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 315.6715.7215.791. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 212348121620Min: 15.62 / Avg: 15.67 / Max: 15.74Min: 15.68 / Avg: 15.72 / Max: 15.76Min: 15.75 / Avg: 15.79 / Max: 15.881. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 3123612182430SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 325.0625.1625.161. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.13Settings: UASTC Level 3123612182430Min: 25 / Avg: 25.06 / Max: 25.17Min: 25.07 / Avg: 25.16 / Max: 25.35Min: 25.1 / Avg: 25.16 / Max: 25.241. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: SqueezeNetV1.01233691215SE +/- 0.095, N = 15SE +/- 0.105, N = 15SE +/- 0.108, N = 39.0628.7838.912MIN: 8.06 / MAX: 18.98MIN: 8 / MAX: 22.86MIN: 8.28 / MAX: 17.911. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: SqueezeNetV1.01233691215Min: 8.45 / Avg: 9.06 / Max: 9.81Min: 8.2 / Avg: 8.78 / Max: 9.59Min: 8.77 / Avg: 8.91 / Max: 9.121. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: resnet-v2-50123918273645SE +/- 0.30, N = 15SE +/- 0.34, N = 15SE +/- 0.53, N = 338.0238.1537.56MIN: 35.17 / MAX: 122.04MIN: 35.3 / MAX: 124.03MIN: 35.2 / MAX: 119.581. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: resnet-v2-50123816243240Min: 36.05 / Avg: 38.02 / Max: 40.6Min: 36.37 / Avg: 38.15 / Max: 40.92Min: 36.73 / Avg: 37.56 / Max: 38.551. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: MobileNetV2_2241231.32982.65963.98945.31926.649SE +/- 0.069, N = 15SE +/- 0.058, N = 15SE +/- 0.211, N = 35.8715.9105.718MIN: 5.4 / MAX: 14.78MIN: 5.42 / MAX: 7.12MIN: 5.38 / MAX: 6.461. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: MobileNetV2_224123246810Min: 5.56 / Avg: 5.87 / Max: 6.65Min: 5.48 / Avg: 5.91 / Max: 6.49Min: 5.44 / Avg: 5.72 / Max: 6.131. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: mobilenet-v1-1.01230.96981.93962.90943.87924.849SE +/- 0.063, N = 15SE +/- 0.056, N = 15SE +/- 0.114, N = 34.3104.2344.041MIN: 3.38 / MAX: 40.78MIN: 3.39 / MAX: 44.28MIN: 3.38 / MAX: 29.441. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: mobilenet-v1-1.0123246810Min: 3.91 / Avg: 4.31 / Max: 4.89Min: 3.96 / Avg: 4.23 / Max: 4.8Min: 3.89 / Avg: 4.04 / Max: 4.261. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: inception-v31231122334455SE +/- 0.34, N = 15SE +/- 0.26, N = 15SE +/- 0.37, N = 348.0548.0847.21MIN: 44.63 / MAX: 136.06MIN: 45.19 / MAX: 105.01MIN: 43.85 / MAX: 97.151. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: inception-v31231020304050Min: 46.67 / Avg: 48.05 / Max: 50.48Min: 46.88 / Avg: 48.08 / Max: 49.98Min: 46.66 / Avg: 47.21 / Max: 47.911. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / Memory12315003000450060007500SE +/- 64.27, N = 3SE +/- 32.29, N = 3SE +/- 33.94, N = 36791.126809.316733.701. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / Memory12312002400360048006000Min: 6714.85 / Avg: 6791.12 / Max: 6918.86Min: 6768.93 / Avg: 6809.31 / Max: 6873.14Min: 6689.46 / Avg: 6733.7 / Max: 6800.41. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPU12312K24K36K48K60KSE +/- 2.08, N = 3SE +/- 3.63, N = 3SE +/- 1.70, N = 357045.0657054.8257053.001. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPU12310K20K30K40K50KMin: 57040.95 / Avg: 57045.06 / Max: 57047.71Min: 57047.74 / Avg: 57054.82 / Max: 57059.79Min: 57049.8 / Avg: 57053 / Max: 57055.591. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm