AMD EPYC 7003 EO 2021 Linux Comparison

2 x AMD EPYC 75F3 32-Core testing with a ASRockRack ROME2D16-2T (P3.10 BIOS) and ASPEED on Clear Linux OS 35150 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 2110218-TJ-2110212TJ25
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

Limit displaying results to tests within:

AV1 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 10 Tests
CPU Massive 17 Tests
Creator Workloads 21 Tests
Encoding 7 Tests
Fortran Tests 3 Tests
Game Development 4 Tests
HPC - High Performance Computing 12 Tests
Imaging 4 Tests
Common Kernel Benchmarks 3 Tests
LAPACK (Linear Algebra Pack) Tests 2 Tests
Machine Learning 5 Tests
Molecular Dynamics 3 Tests
MPI Benchmarks 2 Tests
Multi-Core 24 Tests
NVIDIA GPU Compute 5 Tests
Intel oneAPI 3 Tests
OpenMPI Tests 4 Tests
Productivity 3 Tests
Programmer / Developer System Benchmarks 8 Tests
Python 3 Tests
Raytracing 2 Tests
Renderers 5 Tests
Scientific Computing 6 Tests
Server 2 Tests
Server CPU Tests 13 Tests
Single-Threaded 3 Tests
Video Encoding 7 Tests
Common Workstation Benchmarks 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
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Ubuntu 21.10
October 20 2021
  23 Hours, 3 Minutes
Clear Linux 35150
October 21 2021
  18 Hours, 54 Minutes
Invert Hiding All Results Option
  20 Hours, 58 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):


AMD EPYC 7003 EO 2021 Linux ComparisonProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkMonitorOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionUbuntu 21.10Clear Linux 351502 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads)ASRockRack ROME2D16-2T (P3.10 BIOS)AMD Starship/Matisse16 x 8 GB DDR4-3200MT/s HMA81GR7CJR8N-XN1000GB Western Digital WD_BLACK SN850 1TBASPEEDAMD Starship/Matisse2 x Intel 10G X550TUbuntu 21.105.13.0-20-generic (x86_64)GNOME Shell 40.5X Server1.1.182GCC 11.2.0ext41024x768126GBVE228Clear Linux OS 351505.14.13-1083.native (x86_64)GNOME Shell 41.0X Server 1.20.11GCC 11.2.1 20211015 releases/gcc-11.2.0-353-g6a936be4ad + Clang 11.1.0 + LLVM 11.1.01920x1080OpenBenchmarking.orgKernel Details- Ubuntu 21.10: Transparent Huge Pages: madvise- Clear Linux 35150: Transparent Huge Pages: alwaysCompiler Details- Ubuntu 21.10: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-ZPT0kp/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Clear Linux 35150: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-languages=c,c++,fortran,go --enable-ld=default --enable-libstdcxx-pch --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=x86-64-v3 --with-gcc-major-version-only --with-glibc-version=2.19 --with-gnu-ld --with-isl --with-ppl=yes --with-tune=skylake-avx512 Processor Details- Ubuntu 21.10: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001114- Clear Linux 35150: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001114Python Details- Python 3.9.7Security 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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected Environment Details- Clear Linux 35150: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -fvisibility-inlines-hidden -Wl,--enable-new-dtags" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""

Ubuntu 21.10 vs. Clear Linux 35150 ComparisonPhoronix Test SuiteBaseline+99.5%+99.5%+199%+199%+298.5%+298.5%397.9%228.5%181.4%117%78%42.8%38.8%38.5%37.6%36.4%33.3%31.7%31.2%31.2%29.4%28%27.4%25.6%25.1%22.3%19.4%19%18.9%17.3%16.6%16.6%16.5%16.4%16.4%16.4%14.3%13.6%12.6%9.7%8.6%8.5%8.1%7.2%7.1%6%5.5%5.1%5.1%4.7%4.7%3.9%3.6%3.5%3.4%3.3%3.2%3.1%3%2.6%2.5%2.5%2.1%8, Long Mode - Compression SpeedGETMIXBosphorus 4K - Very FastNinja97.2%Unix Makefiles90.5%SETScaleColor EnhanceNo - Inference - VGG16 - CPU3 - Compression SpeedNo - Inference - VGG19 - CPUCPU - resnet50CPU - mobilenetBosphorus 4K - Ultra FastS.F.P.RCropCPU - googlenet29%Speed 5 - Bosphorus 4KCPU - SqueezeNet v1.126.9%19 - Compression SpeedCPU - vgg1624.2%T.B.TReflect100 - 250 - Read Only100 - 250 - Read Only - Average LatencyCPU - blazefaceCPU - DenseNet17%3, Long Mode - D.SBosphorus 4K100 - 500 - Read Only8, Long Mode - D.SRotate 90 Degrees100 - 500 - Read Only - Average Latencypython_startup15.6%L.a.L.l3 - D.SpathlibCPU - alexnet11.5%CPU - resnet189.9%CPU - mnasnetCPU - squeezenet_ssd9.4%Preset 8 - Bosphorus 4K19 - D.S19, Long Mode - D.S19, Long Mode - Compression SpeedP.S.O - Bosphorus 1080pCPU - MobileNet v26%10 - Bosphorus 1080pDisney Material100 - 500 - Read Write5.2%100 - 250 - Read Write - Average Latency100 - 500 - Read Write - Average Latency5.1%CPU-v2-v2 - mobilenet-v2json_loads4.9%SHA256Trace Time4.6%CPU - SqueezeNet v24.1%CPUCPU-v3-v3 - mobilenet-v3100 - 250 - Read Writeregex_compileCPU - regnety_400mpickle_pure_pythonExhaustive7 - Bosphorus 1080pCPU - yolov4-tiny2.9%C240 BuckyballPabellon Barcelona - CPU-OnlyV.Q.O - Bosphorus 1080pThoroughZstd CompressionRedis Memtier / Redis BenchmarkRedis Memtier / Redis BenchmarkKvazaarTimed LLVM CompilationTimed LLVM CompilationRedis Memtier / Redis BenchmarkGEGLGEGLPlaidMLZstd CompressionPlaidMLNCNNNCNNKvazaarACES DGEMMGEGLNCNNVP9 libvpx EncodingNumpy BenchmarkTNNZstd CompressionWireGuard + Linux Networking Stack Stress TestNCNNRawTherapeeGEGLPostgreSQL pgbenchPostgreSQL pgbenchNCNNTNNZstd Compressionx265PostgreSQL pgbenchZstd CompressionGEGLPostgreSQL pgbenchPyPerformanceRedis Memtier / Redis BenchmarkZstd CompressionPyPerformanceNCNNNCNNNCNNNCNNSVT-AV1Zstd CompressionZstd CompressionZstd CompressionSVT-VP9TNNSVT-HEVCAppleseedPostgreSQL pgbenchPostgreSQL pgbenchPostgreSQL pgbenchNCNNPyPerformanceOpenSSLPOV-RayHigh Performance Conjugate GradientTNNChaos Group V-RAYNCNNPostgreSQL pgbenchPyPerformanceNCNNPyPerformanceASTC EncoderSVT-HEVCNCNNNWChemBlenderSVT-VP9ASTC EncoderUbuntu 21.10Clear Linux 35150

AMD EPYC 7003 EO 2021 Linux Comparisoncompress-zstd: 3, Long Mode - Compression Speedcompress-zstd: 8, Long Mode - Compression Speedredis: GETredis: MIXkvazaar: Bosphorus 4K - Very Fastbuild-llvm: Ninjabuild-llvm: Unix Makefilescompress-zstd: 8 - Compression Speedgegl: Scalegegl: Color Enhanceplaidml: No - Inference - VGG16 - CPUplaidml: No - Inference - VGG19 - CPUkvazaar: Bosphorus 4K - Ultra Fastmt-dgemm: Sustained Floating-Point Rategegl: Cropnumpy: tnn: CPU - SqueezeNet v1.1compress-zstd: 19 - Compression Speedwireguard: rawtherapee: Total Benchmark Timegegl: Reflectpgbench: 100 - 250 - Read Onlypgbench: 100 - 250 - Read Only - Average Latencytnn: CPU - DenseNetcompress-zstd: 3, Long Mode - Decompression Speedx265: Bosphorus 4Kpgbench: 100 - 500 - Read Onlycompress-zstd: 8, Long Mode - Decompression Speedgegl: Rotate 90 Degreespgbench: 100 - 500 - Read Only - Average Latencypyperformance: python_startupredis: LPUSH and LPOP: lpopcompress-zstd: 3 - Decompression Speedpyperformance: pathlibsvt-av1: Preset 8 - Bosphorus 4Kcompress-zstd: 19 - Decompression Speedcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedsvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080ptnn: CPU - MobileNet v2svt-hevc: 10 - Bosphorus 1080pappleseed: Disney Materialpgbench: 100 - 500 - Read Writepgbench: 100 - 500 - Read Write - Average Latencypyperformance: json_loadsopenssl: SHA256povray: Trace Timetnn: CPU - SqueezeNet v2pyperformance: regex_compilepyperformance: pickle_pure_pythonastcenc: Exhaustivesvt-hevc: 7 - Bosphorus 1080pnwchem: C240 Buckyballblender: Pabellon Barcelona - CPU-Onlysvt-vp9: Visual Quality Optimized - Bosphorus 1080pastcenc: Thoroughblender: BMW27 - CPU-Onlypyperformance: nbodypybench: Total For Average Test Timesplaidml: No - Inference - ResNet 50 - CPUappleseed: Material Testerpyperformance: raytraceospray: XFrog Forest - SciVisoidn: RT.hdr_alb_nrm.3840x2160openssl: gromacs: MPI CPU - water_GMX50_bareredis: LPUSH and LPOP: lpushpyperformance: django_templatepyperformance: gonamd: ATPase Simulation - 327,506 Atomsopenssl: embree: Pathtracer ISPC - Crownopenssl: RSA4096pyperformance: floatopenssl: RSA4096embree: Pathtracer - Crownplaidml: No - Inference - NASNer Large - CPUplaidml: No - Inference - DenseNet 201 - CPUplaidml: No - Inference - Mobilenet - CPUplaidml: No - Inference - IMDB LSTM - CPUoctave-benchmark: nginx: Short Connection - 1000nginx: Short Connection - 500nginx: Long Connection - 1000nginx: Long Connection - 500pyperformance: crypto_pyaesonnx: fcn-resnet101-11 - OpenMP CPUonnx: bertsquad-10 - OpenMP CPUonnx: yolov4 - OpenMP CPUoctave-benchmark: ocrmypdf: Processing 60 Page PDF Documenthugin: Panorama Photo Assistant + Stitching Timebuild-wasmer: Time To Compilebuild-nodejs: Time To Compilebuild-linux-kernel: Time To Compilebuild-godot: Time To Compileaom-av1: Speed 10 Realtime - Bosphorus 4Kaom-av1: Speed 9 Realtime - Bosphorus 4Kaom-av1: Speed 8 Realtime - Bosphorus 4Kospray: Magnetic Reconnection - SciVisospray: NASA Streamlines - SciVisospray: San Miguel - SciVisgnuradio: Hilbert Transformgnuradio: FM Deemphasis Filtergnuradio: IIR Filtergnuradio: FIR Filtergnuradio: Signal Source (Cosine)gnuradio: Five Back to Back FIR Filterscompress-zstd: 8 - Decompression Speedqe: AUSURF112v-ray: CPUonnx: super-resolution-10 - OpenMP CPUonnx: shufflenet-v2-10 - OpenMP CPUncnn: CPU - regnety_400mncnn: CPU - squeezenet_ssdncnn: CPU - yolov4-tinyncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - googlenetncnn: CPU - blazefacencnn: CPU - efficientnet-b0ncnn: CPU - mnasnetncnn: CPU - shufflenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - mobilenetredis: SETpgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writevpxenc: Speed 5 - Bosphorus 4Kcompress-zstd: 3 - Compression Speedhpcg: Ubuntu 21.10Clear Linux 35150163.7184.4309980.80318221.7126.27115.998172.6923228.36.85849.84033.9830.3650.2422.4495267.770437.03251.70078.1404.99649.93727.90217263190.1452842.1973938.422.3017191424087.236.2750.2917.311189084.423717.215.261.5613560.13628.038.7404.95302.520539.6348.475275589008.49220.3985486428838.50562.0761513889.3335355.531858.576.98350.955.047626.241098668.53329.48611841417.441.801104066.27.3891291673.4941.42200.3041117090.067.50171114763.898.417027.473.247735835.8742141.95180785.84170340.6589.11914482716.04011.60445.79143.89880.25319.99043.52239.6235.9726.0555.56111.1183.33438.7881.2708.8790.53737.8739.53828.6243.14642725292503867.1258.7940.8467.7813.0129.1036.6353.4913.0138.3632.3425.8531.0732.8459.86383801.554.8825272014.695872.434.8293971.1918.21018405.90895409.9357.00228.699329.0204782.84.80435.91347.0741.4265.9329.4513906.003556.66319.41298.1323.80740.83323.36920536660.1223325.438459426.0020035534758.131.1630.2508.451358711.354224.413.566.8473863.83922.641.5433.62320.664571.9745.927436560078.92921.31032185991208.12164.5991463769.0497366.031811.575.10359.674.942925.761118818.39333.78607240917.241.821116179.57.4481300265.341.62210.3054717024.767.36271113280.398.317010.473.26101.594.6416.53703.764.00289.155.56111.1183.336678564.9864.3442.0250.8514.5031.9945.5069.0111.0937.6329.4925.8929.9931.2545.46683056.484.6435455018.818081.633.2841OpenBenchmarking.org

Zstd Compression

This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 3, Long Mode - Compression SpeedClear Linux 35150Ubuntu 21.102004006008001000SE +/- 2.86, N = 3SE +/- 1.37, N = 3966.7163.71. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***2. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8, Long Mode - Compression SpeedUbuntu 21.10Clear Linux 351502004006008001000SE +/- 1.53, N = 3SE +/- 11.06, N = 15184.4918.21. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***2. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***

Redis Memtier / Redis Benchmark

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. This test profile is for testing any system-installed Redis copy. The redis-server and redis-benchmark software must be present in PATH. To use a static / locally built version of Redis, run the pts/redis test profile instead. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterRedis Memtier / Redis BenchmarkTest: GETUbuntu 21.10Clear Linux 35150200K400K600K800K1000KSE +/- 3124.18, N = 3SE +/- 9977.44, N = 12309980.801018405.901. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre2. Ubuntu 21.10: Redis server v=6.0.15 sha=00000000:0 malloc=jemalloc-5.2.1 bits=64 build=4610f4c3acf7fb253. Clear Linux 35150: Redis server v=6.2.6 sha=00000000:0 malloc=libc bits=64 build=83ecfd2f655ff398

OpenBenchmarking.orgOperations Per Second, More Is BetterRedis Memtier / Redis BenchmarkTest: MIXUbuntu 21.10Clear Linux 35150200K400K600K800K1000KSE +/- 2160.46, N = 3SE +/- 15439.80, N = 9318221.71895409.931. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre2. Ubuntu 21.10: Redis server v=6.0.15 sha=00000000:0 malloc=jemalloc-5.2.1 bits=64 build=4610f4c3acf7fb253. Clear Linux 35150: Redis server v=6.2.6 sha=00000000:0 malloc=libc bits=64 build=83ecfd2f655ff398

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Very FastUbuntu 21.10Clear Linux 351501326395265SE +/- 0.06, N = 3SE +/- 0.07, N = 326.2757.00-O2-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaUbuntu 21.10Clear Linux 3515050100150200250SE +/- 0.41, N = 3SE +/- 2.02, N = 3116.00228.70

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesUbuntu 21.10Clear Linux 3515070140210280350SE +/- 0.08, N = 3SE +/- 0.75, N = 3172.69329.02

Zstd Compression

This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8 - Compression SpeedClear Linux 35150Ubuntu 21.1010002000300040005000SE +/- 8.57, N = 3SE +/- 34.72, N = 154832.43228.31. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***2. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ScaleUbuntu 21.10Clear Linux 35150246810SE +/- 0.044, N = 3SE +/- 0.049, N = 36.8584.804

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Color EnhanceUbuntu 21.10Clear Linux 351501122334455SE +/- 0.03, N = 3SE +/- 0.00, N = 349.8435.91

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUUbuntu 21.10Clear Linux 351501122334455SE +/- 0.22, N = 15SE +/- 0.16, N = 333.9847.07

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUUbuntu 21.10Clear Linux 35150918273645SE +/- 0.24, N = 3SE +/- 0.01, N = 330.3641.42

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Ultra FastUbuntu 21.10Clear Linux 351501530456075SE +/- 0.09, N = 3SE +/- 0.29, N = 350.2465.93-O2-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt

ACES DGEMM

This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateUbuntu 21.10Clear Linux 35150714212835SE +/- 0.30, N = 15SE +/- 0.42, N = 1522.4529.45-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -O3 -march=native -fopenmp

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: CropUbuntu 21.10Clear Linux 35150246810SE +/- 0.031, N = 3SE +/- 0.033, N = 37.7706.003

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkUbuntu 21.10Clear Linux 35150120240360480600SE +/- 1.06, N = 3SE +/- 0.88, N = 3437.03556.66

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 v1.1Ubuntu 21.10Clear Linux 3515070140210280350SE +/- 0.11, N = 3SE +/- 0.04, N = 3251.70319.41MIN: 251.29 / MAX: 253.11-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 319.14 / MAX: 3201. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Zstd Compression

This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19 - Compression SpeedUbuntu 21.10Clear Linux 3515020406080100SE +/- 0.90, N = 3SE +/- 0.81, N = 378.198.11. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***2. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***

WireGuard + Linux Networking Stack Stress Test

This is a benchmark of the WireGuard secure VPN tunnel and Linux networking stack stress test. The test runs on the local host but does require root permissions to run. The way it works is it creates three namespaces. ns0 has a loopback device. ns1 and ns2 each have wireguard devices. Those two wireguard devices send traffic through the loopback device of ns0. The end result of this is that tests wind up testing encryption and decryption at the same time -- a pretty CPU and scheduler-heavy workflow. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWireGuard + Linux Networking Stack Stress TestUbuntu 21.10Clear Linux 3515090180270360450SE +/- 5.83, N = 3SE +/- 3.95, N = 9405.00323.81

RawTherapee

RawTherapee is a cross-platform, open-source multi-threaded RAW image processing program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeUbuntu 21.10Clear Linux 351501122334455SE +/- 0.16, N = 3SE +/- 0.09, N = 349.9440.831. Ubuntu 21.10: RawTherapee, version 5.8, command line.2. Clear Linux 35150: RawTherapee, version , command line.

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: ReflectUbuntu 21.10Clear Linux 35150714212835SE +/- 0.02, N = 3SE +/- 0.01, N = 327.9023.37

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyUbuntu 21.10Clear Linux 35150400K800K1200K1600K2000KSE +/- 21431.80, N = 3SE +/- 20119.29, N = 317263192053666-O2-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyUbuntu 21.10Clear Linux 351500.03260.06520.09780.13040.163SE +/- 0.002, N = 3SE +/- 0.001, N = 30.1450.122-O2-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -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: DenseNetUbuntu 21.10Clear Linux 351507001400210028003500SE +/- 4.39, N = 3SE +/- 0.84, N = 32842.203325.44MIN: 2742.82 / MAX: 3539.14-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 3276.19 / MAX: 3391.41. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

Zstd Compression

This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 3, Long Mode - Decompression SpeedUbuntu 21.10Clear Linux 3515010002000300040005000SE +/- 38.54, N = 33938.44594.01. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***2. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***

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 4KUbuntu 21.10Clear Linux 35150612182430SE +/- 0.23, N = 5SE +/- 0.13, N = 322.3026.00-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyUbuntu 21.10Clear Linux 35150400K800K1200K1600K2000KSE +/- 5531.30, N = 3SE +/- 7404.19, N = 317191422003553-O2-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8, Long Mode - Decompression SpeedUbuntu 21.10Clear Linux 3515010002000300040005000SE +/- 23.42, N = 3SE +/- 3.11, N = 154087.24758.11. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***2. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***

GEGL

GEGL is the Generic Graphics Library and is the library/framework used by GIMP and other applications like GNOME Photos. This test profile times how long it takes to complete various GEGL operations on a static set of sample JPEG images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Rotate 90 DegreesUbuntu 21.10Clear Linux 35150816243240SE +/- 0.10, N = 3SE +/- 0.01, N = 336.2831.16

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyUbuntu 21.10Clear Linux 351500.06550.1310.19650.2620.3275SE +/- 0.001, N = 3SE +/- 0.001, N = 30.2910.250-O2-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: python_startupUbuntu 21.10Clear Linux 35150246810SE +/- 0.01, N = 3SE +/- 0.01, N = 37.318.45

Redis Memtier / Redis Benchmark

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. This test profile is for testing any system-installed Redis copy. The redis-server and redis-benchmark software must be present in PATH. To use a static / locally built version of Redis, run the pts/redis test profile instead. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis Memtier / Redis BenchmarkTest: LPUSH and LPOP: lpopUbuntu 21.10Clear Linux 35150300K600K900K1200K1500KSE +/- 6262.88, N = 3SE +/- 12884.54, N = 61189084.421358711.351. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre2. Ubuntu 21.10: Redis server v=6.0.15 sha=00000000:0 malloc=jemalloc-5.2.1 bits=64 build=4610f4c3acf7fb253. Clear Linux 35150: Redis server v=6.2.6 sha=00000000:0 malloc=libc bits=64 build=83ecfd2f655ff398

Zstd Compression

This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 3 - Decompression SpeedUbuntu 21.10Clear Linux 351509001800270036004500SE +/- 1.35, N = 23717.24224.41. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***2. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pathlibUbuntu 21.10Clear Linux 3515048121620SE +/- 0.03, N = 3SE +/- 0.03, N = 315.213.5

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8.7Encoder Mode: Preset 8 - Input: Bosphorus 4KUbuntu 21.10Clear Linux 351501530456075SE +/- 0.27, N = 3SE +/- 0.09, N = 361.5666.85-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Zstd Compression

This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19 - Decompression SpeedUbuntu 21.10Clear Linux 351508001600240032004000SE +/- 17.07, N = 3SE +/- 5.13, N = 33560.13863.81. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***2. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19, Long Mode - Decompression SpeedUbuntu 21.10Clear Linux 351508001600240032004000SE +/- 10.26, N = 15SE +/- 5.05, N = 33628.03922.61. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***2. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 19, Long Mode - Compression SpeedUbuntu 21.10Clear Linux 35150918273645SE +/- 0.48, N = 15SE +/- 0.35, N = 338.741.51. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***2. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***

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 1080pUbuntu 21.10Clear Linux 3515090180270360450SE +/- 5.36, N = 12SE +/- 4.96, N = 15404.95433.62-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -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: MobileNet v2Ubuntu 21.10Clear Linux 3515070140210280350SE +/- 3.36, N = 3SE +/- 0.30, N = 3302.52320.66MIN: 292.01 / MAX: 381.49-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 317.51 / MAX: 351.181. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p 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 1080pUbuntu 21.10Clear Linux 35150120240360480600SE +/- 3.94, N = 3SE +/- 5.39, N = 7539.63571.97-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney MaterialUbuntu 21.10Clear Linux 35150112233445548.4845.93

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read WriteUbuntu 21.10Clear Linux 3515013K26K39K52K65KSE +/- 818.76, N = 3SE +/- 548.57, N = 35890056007-O2-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyUbuntu 21.10Clear Linux 35150246810SE +/- 0.119, N = 3SE +/- 0.087, N = 38.4928.929-O2-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsUbuntu 21.10Clear Linux 35150510152025SE +/- 0.03, N = 3SE +/- 0.00, N = 320.321.3

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: SHA256Ubuntu 21.10Clear Linux 3515020000M40000M60000M80000M100000MSE +/- 37689879.19, N = 3SE +/- 155150645.70, N = 398548642883103218599120-pipe -fexceptions -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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 TimeUbuntu 21.10Clear Linux 35150246810SE +/- 0.017, N = 3SE +/- 0.020, N = 38.5058.121-lXpm -lIlmImf -lIlmImf-2_5 -lImath-2_5 -lHalf-2_5 -lIex-2_5 -lIexMath-2_5 -lIlmThread-2_5 -pthread -lIlmThread-fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -lpthread1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -R/usr/lib -lSDL -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

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 v2Ubuntu 21.10Clear Linux 351501428425670SE +/- 0.11, N = 3SE +/- 0.30, N = 362.0864.60MIN: 61.81 / MAX: 62.45-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 64.13 / MAX: 65.381. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileUbuntu 21.10Clear Linux 35150306090120150SE +/- 0.00, N = 3SE +/- 0.00, N = 3151146

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: pickle_pure_pythonUbuntu 21.10Clear Linux 3515080160240320400SE +/- 0.33, N = 3SE +/- 0.58, N = 3388376

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 3.2Preset: ExhaustiveUbuntu 21.10Clear Linux 351503691215SE +/- 0.0011, N = 3SE +/- 0.0320, N = 39.33359.0497-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CXX) g++ options: -O3 -flto -pthread

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 1080p 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 1080pUbuntu 21.10Clear Linux 3515080160240320400SE +/- 3.71, N = 3SE +/- 2.14, N = 3355.53366.03-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

NWChem

NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNWChem 7.0.2Input: C240 BuckyballUbuntu 21.10Clear Linux 351504008001200160020001858.51811.5-lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lz1. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lm -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-OnlyUbuntu 21.10Clear Linux 3515020406080100SE +/- 0.07, N = 3SE +/- 0.11, N = 376.9875.10

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: Visual Quality Optimized - Input: Bosphorus 1080pUbuntu 21.10Clear Linux 3515080160240320400SE +/- 2.47, N = 12SE +/- 4.31, N = 4350.95359.67-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

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 3.2Preset: ThoroughUbuntu 21.10Clear Linux 351501.13572.27143.40714.54285.6785SE +/- 0.0063, N = 3SE +/- 0.0128, N = 35.04764.9429-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CXX) g++ options: -O3 -flto -pthread

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: CPU-OnlyUbuntu 21.10Clear Linux 35150612182430SE +/- 0.08, N = 3SE +/- 0.05, N = 326.2425.76

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: nbodyUbuntu 21.10Clear Linux 3515020406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 3109111

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesUbuntu 21.10Clear Linux 351502004006008001000SE +/- 1.67, N = 3SE +/- 3.51, N = 3866881

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUUbuntu 21.10Clear Linux 35150246810SE +/- 0.04, N = 3SE +/- 0.02, N = 38.538.39

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material TesterUbuntu 21.10Clear Linux 3515070140210280350329.49333.79

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: raytraceUbuntu 21.10Clear Linux 3515090180270360450SE +/- 0.88, N = 3SE +/- 0.33, N = 3414409

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisUbuntu 21.10Clear Linux 3515048121620SE +/- 0.10, N = 3SE +/- 0.00, N = 317.4417.24MIN: 14.71 / MAX: 17.54MIN: 14.49 / MAX: 17.54

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160Ubuntu 21.10Clear Linux 351500.40950.8191.22851.6382.0475SE +/- 0.00, N = 3SE +/- 0.00, N = 31.801.82

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. The system/openssl test profiles relies on benchmarking the system/OS-supplied openssl binary rather than the pts/openssl test profile that uses the locally-built OpenSSL for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgverify/s, More Is BetterOpenSSLUbuntu 21.10Clear Linux 35150200K400K600K800K1000KSE +/- 630.46, N = 3SE +/- 113.24, N = 31104066.21116179.51. OpenSSL 1.1.1l 24 Aug 2021

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2021.2Implementation: MPI CPU - Input: water_GMX50_bareUbuntu 21.10Clear Linux 35150246810SE +/- 0.029, N = 3SE +/- 0.030, N = 37.3897.448-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CXX) g++ options: -O3

Redis Memtier / Redis Benchmark

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. This test profile is for testing any system-installed Redis copy. The redis-server and redis-benchmark software must be present in PATH. To use a static / locally built version of Redis, run the pts/redis test profile instead. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis Memtier / Redis BenchmarkTest: LPUSH and LPOP: lpushUbuntu 21.10Clear Linux 35150300K600K900K1200K1500KSE +/- 16158.55, N = 14SE +/- 15753.94, N = 31291673.491300265.301. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre2. Ubuntu 21.10: Redis server v=6.0.15 sha=00000000:0 malloc=jemalloc-5.2.1 bits=64 build=4610f4c3acf7fb253. Clear Linux 35150: Redis server v=6.2.6 sha=00000000:0 malloc=libc bits=64 build=83ecfd2f655ff398

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateUbuntu 21.10Clear Linux 35150918273645SE +/- 0.03, N = 3SE +/- 0.03, N = 341.441.6

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: goUbuntu 21.10Clear Linux 3515050100150200250SE +/- 0.33, N = 3SE +/- 0.00, N = 3220221

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsUbuntu 21.10Clear Linux 351500.06870.13740.20610.27480.3435SE +/- 0.00022, N = 3SE +/- 0.00017, N = 30.304110.30547

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. The system/openssl test profiles relies on benchmarking the system/OS-supplied openssl binary rather than the pts/openssl test profile that uses the locally-built OpenSSL for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsign/s, More Is BetterOpenSSLUbuntu 21.10Clear Linux 351504K8K12K16K20KSE +/- 13.83, N = 3SE +/- 1.19, N = 317090.017024.71. OpenSSL 1.1.1l 24 Aug 2021

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownUbuntu 21.10Clear Linux 351501530456075SE +/- 0.05, N = 3SE +/- 0.05, N = 367.5067.36MIN: 66.15 / MAX: 69.7MIN: 66.09 / MAX: 69.49

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: RSA4096Ubuntu 21.10Clear Linux 35150200K400K600K800K1000KSE +/- 385.98, N = 3SE +/- 161.41, N = 31114763.81113280.3-pipe -fexceptions -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: floatUbuntu 21.10Clear Linux 3515020406080100SE +/- 0.00, N = 3SE +/- 0.17, N = 398.498.3

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: RSA4096Ubuntu 21.10Clear Linux 351504K8K12K16K20KSE +/- 15.36, N = 3SE +/- 2.67, N = 317027.417010.4-pipe -fexceptions -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: CrownUbuntu 21.10Clear Linux 351501632486480SE +/- 0.10, N = 3SE +/- 0.14, N = 373.2573.26MIN: 71.54 / MAX: 75.84MIN: 71.57 / MAX: 75.62

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: NASNer Large - Device: CPUClear Linux 351500.35780.71561.07341.43121.789SE +/- 0.01, N = 31.59

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPUClear Linux 351501.0442.0883.1324.1765.22SE +/- 0.01, N = 34.64

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: CPUClear Linux 3515048121620SE +/- 0.19, N = 316.53

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPUClear Linux 35150150300450600750SE +/- 1.54, N = 3703.76

GNU Octave Benchmark

This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 6.3.0Clear Linux 351500.90051.8012.70153.6024.5025SE +/- 0.011, N = 54.002

Nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile relies upon nginx being present in the system PATH / already installed on the system if wanting to benchmark the operating system's provided nginx package. Use the pts/ngnx test profile if wanting to test a locally-built Nginx web server. Wrk is used for facilitating the HTTP web server load testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterNginxTest: Short Connection - Connections: 1000Ubuntu 21.108K16K24K32K40KSE +/- 43.89, N = 335835.871. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O22. nginx version: nginx/1.18.0 (Ubuntu)

Test: Short Connection - Connections: 1000

Clear Linux 35150: nginx: line 7: ./wrk/wrk: No such file or directory

OpenBenchmarking.orgRequests Per Second, More Is BetterNginxTest: Short Connection - Connections: 500Ubuntu 21.109K18K27K36K45KSE +/- 26.81, N = 342141.951. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O22. nginx version: nginx/1.18.0 (Ubuntu)

Test: Short Connection - Connections: 500

Clear Linux 35150: nginx: line 7: ./wrk/wrk: No such file or directory

OpenBenchmarking.orgRequests Per Second, More Is BetterNginxTest: Long Connection - Connections: 1000Ubuntu 21.1040K80K120K160K200KSE +/- 391.28, N = 3180785.841. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O22. nginx version: nginx/1.18.0 (Ubuntu)

Test: Long Connection - Connections: 1000

Clear Linux 35150: nginx: line 5: ./wrk/wrk: No such file or directory

OpenBenchmarking.orgRequests Per Second, More Is BetterNginxTest: Long Connection - Connections: 500Ubuntu 21.1040K80K120K160K200KSE +/- 911.83, N = 3170340.651. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O22. nginx version: nginx/1.18.0 (Ubuntu)

Test: Long Connection - Connections: 500

Clear Linux 35150: nginx: line 5: ./wrk/wrk: No such file or directory

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesUbuntu 21.10Clear Linux 3515020406080100SE +/- 0.09, N = 3SE +/- 0.12, N = 389.189.1

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: fcn-resnet101-11 - Device: OpenMP CPUUbuntu 21.104080120160200SE +/- 1.77, N = 71911. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Model: fcn-resnet101-11 - Device: OpenMP CPU

Clear Linux 35150: onnx: line 3: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: bertsquad-10 - Device: OpenMP CPUUbuntu 21.10100200300400500SE +/- 6.37, N = 34481. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Model: bertsquad-10 - Device: OpenMP CPU

Clear Linux 35150: onnx: line 3: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: yolov4 - Device: OpenMP CPUUbuntu 21.1060120180240300SE +/- 4.10, N = 122711. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Model: yolov4 - Device: OpenMP CPU

Clear Linux 35150: onnx: line 3: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

GNU Octave Benchmark

This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 6.2.0Ubuntu 21.10246810SE +/- 0.048, N = 56.040

OCRMyPDF

OCRMyPDF is an optical character recognition (OCR) text layer to scanned PDF files, producing new PDFs with the text now selectable/searchable/copy-paste capable. OCRMyPDF leverages the Tesseract OCR engine and is written in Python. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOCRMyPDF 10.3.1+dfsgProcessing 60 Page PDF DocumentUbuntu 21.103691215SE +/- 0.12, N = 311.60

Hugin

Hugin is an open-source, cross-platform panorama photo stitcher software package. This test profile times how long it takes to run the assistant and panorama photo stitching on a set of images. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHuginPanorama Photo Assistant + Stitching TimeUbuntu 21.101020304050SE +/- 0.40, N = 345.79

Panorama Photo Assistant + Stitching Time

Clear Linux 35150: The test quit with a non-zero exit status.

Timed Wasmer Compilation

This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 1.0.2Time To CompileUbuntu 21.101020304050SE +/- 0.28, N = 343.901. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc

Time To Compile

Clear Linux 35150: The test quit with a non-zero exit status.

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileUbuntu 21.1020406080100SE +/- 0.26, N = 380.25

Time To Compile

Clear Linux 35150: The test quit with a non-zero exit status.

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.14Time To CompileUbuntu 21.10510152025SE +/- 0.16, N = 919.99

Time To Compile

Clear Linux 35150: The test quit with a non-zero exit status.

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileUbuntu 21.101020304050SE +/- 0.32, N = 343.52

Time To Compile

Clear Linux 35150: The test quit with a non-zero exit status.

AOM AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.2Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KUbuntu 21.10918273645SE +/- 0.48, N = 339.621. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K

Clear Linux 35150: Test failed to run.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.2Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KUbuntu 21.10816243240SE +/- 0.09, N = 335.971. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K

Clear Linux 35150: Test failed to run.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.2Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KUbuntu 21.10612182430SE +/- 0.38, N = 326.051. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K

Clear Linux 35150: Test failed to run.

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisUbuntu 21.10Clear Linux 351501224364860SE +/- 0.00, N = 3SE +/- 0.00, N = 355.5655.56MIN: 29.41 / MAX: 58.82MIN: 38.46 / MAX: 58.82

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisUbuntu 21.10Clear Linux 3515020406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3111.11111.11MIN: 45.45 / MAX: 125MIN: 52.63 / MAX: 125

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisUbuntu 21.10Clear Linux 3515020406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 383.3383.33MIN: 66.67 / MAX: 90.91MIN: 62.5 / MAX: 90.91

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: Hilbert TransformUbuntu 21.10100200300400500SE +/- 0.99, N = 3438.71. 3.8.2.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis FilterUbuntu 21.102004006008001000SE +/- 6.05, N = 3881.21. 3.8.2.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR FilterUbuntu 21.10150300450600750SE +/- 0.37, N = 3708.81. 3.8.2.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR FilterUbuntu 21.102004006008001000SE +/- 5.06, N = 3790.51. 3.8.2.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)Ubuntu 21.108001600240032004000SE +/- 17.16, N = 33737.81. 3.8.2.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Five Back to Back FIR FiltersUbuntu 21.10160320480640800SE +/- 2.95, N = 3739.51. 3.8.2.0

Zstd Compression

This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 8 - Decompression SpeedUbuntu 21.1080016002400320040003828.61. *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***

Quantum ESPRESSO

Quantum ESPRESSO is an integrated suite of Open-Source computer codes for electronic-structure calculations and materials modeling at the nanoscale. It is based on density-functional theory, plane waves, and pseudopotentials. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterQuantum ESPRESSO 6.8Input: AUSURF112Ubuntu 21.1050100150200250SE +/- 0.28, N = 3243.141. (F9X) gfortran options: -ldevXlib -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3 -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Input: AUSURF112

Clear Linux 35150: Test failed to run.

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5Mode: CPUUbuntu 21.10Clear Linux 3515014K28K42K56K70KSE +/- 1753.86, N = 12SE +/- 1288.09, N = 126427266785

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: super-resolution-10 - Device: OpenMP CPUUbuntu 21.1011002200330044005500SE +/- 156.25, N = 952921. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Model: super-resolution-10 - Device: OpenMP CPU

Clear Linux 35150: onnx: line 3: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.8.2Model: shufflenet-v2-10 - Device: OpenMP CPUUbuntu 21.1011002200330044005500SE +/- 155.87, N = 1250381. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

Model: shufflenet-v2-10 - Device: OpenMP CPU

Clear Linux 35150: onnx: line 3: ./onnxruntime/build/Linux/Release/onnxruntime_perf_test: No such file or directory

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

FP16: No - Mode: Inference - Network: NASNer Large - Device: CPU

Ubuntu 21.10: Test failed to run.

FP16: No - Mode: Inference - Network: Inception V3 - Device: CPU

Ubuntu 21.10: Test failed to run.

Clear Linux 35150: Test failed to run.

FP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU

Ubuntu 21.10: Test failed to run.

FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU

Ubuntu 21.10: Test failed to run.

FP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPU

Ubuntu 21.10: Test failed to run.

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 20210720Target: CPU - Model: regnety_400mUbuntu 21.10Clear Linux 351501530456075SE +/- 1.87, N = 12SE +/- 1.73, N = 1067.1264.98MIN: 49.55 / MAX: 5490.47-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 51.79 / MAX: 1080.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdUbuntu 21.10Clear Linux 351501428425670SE +/- 2.10, N = 12SE +/- 3.58, N = 1058.7964.34MIN: 29.45 / MAX: 2730.32-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 28.06 / MAX: 2142.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyUbuntu 21.10Clear Linux 351501020304050SE +/- 2.11, N = 12SE +/- 4.00, N = 1040.8442.02MIN: 27.21 / MAX: 1106.77-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 27.79 / MAX: 241.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50Ubuntu 21.10Clear Linux 351501530456075SE +/- 5.27, N = 12SE +/- 7.79, N = 1067.7850.85MIN: 26.34 / MAX: 3411.32-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 27.96 / MAX: 717.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetUbuntu 21.10Clear Linux 3515048121620SE +/- 0.84, N = 12SE +/- 0.74, N = 1013.0114.50MIN: 6.66 / MAX: 628.35-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 7.26 / MAX: 361.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18Ubuntu 21.10Clear Linux 35150714212835SE +/- 1.95, N = 12SE +/- 2.74, N = 1029.1031.99MIN: 14.81 / MAX: 1391.06-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 14.92 / MAX: 514.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16Ubuntu 21.10Clear Linux 351501020304050SE +/- 0.67, N = 12SE +/- 1.27, N = 1036.6345.50MIN: 31.48 / MAX: 680.6-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 34.07 / MAX: 603.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetUbuntu 21.10Clear Linux 351501530456075SE +/- 2.35, N = 12SE +/- 4.13, N = 1053.4969.01MIN: 24.51 / MAX: 2810.72-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 23.65 / MAX: 2469.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefaceUbuntu 21.10Clear Linux 351503691215SE +/- 0.70, N = 12SE +/- 0.22, N = 1013.0111.09MIN: 8.6 / MAX: 1097.33-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 8.15 / MAX: 15.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0Ubuntu 21.10Clear Linux 35150918273645SE +/- 1.20, N = 12SE +/- 0.78, N = 1038.3637.63MIN: 26.68 / MAX: 1636.57-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 21.58 / MAX: 312.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetUbuntu 21.10Clear Linux 35150816243240SE +/- 1.08, N = 12SE +/- 0.97, N = 1032.3429.49MIN: 21.61 / MAX: 565.28-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 19.83 / MAX: 182.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2Ubuntu 21.10Clear Linux 35150612182430SE +/- 1.02, N = 12SE +/- 0.52, N = 1025.8525.89MIN: 18.36 / MAX: 987.4-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 21.03 / MAX: 74.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3Ubuntu 21.10Clear Linux 35150714212835SE +/- 0.84, N = 12SE +/- 1.53, N = 1031.0729.99MIN: 19.42 / MAX: 201.11-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 17.85 / MAX: 1892.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2Ubuntu 21.10Clear Linux 35150816243240SE +/- 0.86, N = 12SE +/- 1.53, N = 1032.8431.25MIN: 19.78 / MAX: 652.58-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 20.45 / MAX: 1053.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetUbuntu 21.10Clear Linux 351501326395265SE +/- 4.27, N = 12SE +/- 7.31, N = 1059.8645.46MIN: 22.8 / MAX: 1476.14-pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake - MIN: 22.22 / MAX: 1944.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Redis Memtier / Redis Benchmark

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. This test profile is for testing any system-installed Redis copy. The redis-server and redis-benchmark software must be present in PATH. To use a static / locally built version of Redis, run the pts/redis test profile instead. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterRedis Memtier / Redis BenchmarkTest: SETUbuntu 21.10Clear Linux 35150150K300K450K600K750KSE +/- 19493.33, N = 12SE +/- 5047.54, N = 12383801.55683056.481. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre2. Ubuntu 21.10: Redis server v=6.0.15 sha=00000000:0 malloc=jemalloc-5.2.1 bits=64 build=4610f4c3acf7fb253. Clear Linux 35150: Redis server v=6.2.6 sha=00000000:0 malloc=libc bits=64 build=83ecfd2f655ff398

Inkscape

Inkscape is an open-source vector graphics editor. This test profile times how long it takes to complete various operations by Inkscape. Learn more via the OpenBenchmarking.org test page.

Operation: SVG Files To PNG

Ubuntu 21.10: The test quit with a non-zero exit status.

Clear Linux 35150: The test quit with a non-zero exit status.

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyUbuntu 21.10Clear Linux 351501.09852.1973.29554.3945.4925SE +/- 0.298, N = 12SE +/- 0.193, N = 94.8824.643-O2-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteUbuntu 21.10Clear Linux 3515012K24K36K48K60KSE +/- 2278.47, N = 12SE +/- 2115.46, N = 95272054550-O2-O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.10.0Speed: Speed 5 - Input: Bosphorus 4KUbuntu 21.10Clear Linux 35150510152025SE +/- 0.45, N = 15SE +/- 0.06, N = 314.6918.81-U_FORTIFY_SOURCE-pipe -fexceptions -ffat-lto-objects -fno-trapping-math -mtune=skylake1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -std=gnu++11

Zstd Compression

This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd CompressionCompression Level: 3 - Compression SpeedUbuntu 21.10Clear Linux 351502K4K6K8K10KSE +/- 162.04, N = 12SE +/- 78.84, N = 35872.48081.61. Ubuntu 21.10: *** zstd command line interface 64-bits v1.4.8, by Yann Collet ***2. Clear Linux 35150: *** zstd command line interface 64-bits v1.5.0, by Yann Collet ***

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Ubuntu 21.10Clear Linux 35150816243240SE +/- 0.14, N = 3SE +/- 0.71, N = 1134.8333.28-lmpi_cxx1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi

134 Results Shown

Zstd Compression:
  3, Long Mode - Compression Speed
  8, Long Mode - Compression Speed
Redis Memtier / Redis Benchmark:
  GET
  MIX
Kvazaar
Timed LLVM Compilation:
  Ninja
  Unix Makefiles
Zstd Compression
GEGL:
  Scale
  Color Enhance
PlaidML:
  No - Inference - VGG16 - CPU
  No - Inference - VGG19 - CPU
Kvazaar
ACES DGEMM
GEGL
Numpy Benchmark
TNN
Zstd Compression
WireGuard + Linux Networking Stack Stress Test
RawTherapee
GEGL
PostgreSQL pgbench:
  100 - 250 - Read Only
  100 - 250 - Read Only - Average Latency
TNN
Zstd Compression
x265
PostgreSQL pgbench
Zstd Compression
GEGL
PostgreSQL pgbench
PyPerformance
Redis Memtier / Redis Benchmark
Zstd Compression
PyPerformance
SVT-AV1
Zstd Compression:
  19 - Decompression Speed
  19, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
SVT-VP9
TNN
SVT-HEVC
Appleseed
PostgreSQL pgbench:
  100 - 500 - Read Write
  100 - 500 - Read Write - Average Latency
PyPerformance
OpenSSL
POV-Ray
TNN
PyPerformance:
  regex_compile
  pickle_pure_python
ASTC Encoder
SVT-HEVC
NWChem
Blender
SVT-VP9
ASTC Encoder
Blender
PyPerformance
PyBench
PlaidML
Appleseed
PyPerformance
OSPray
Intel Open Image Denoise
OpenSSL
GROMACS
Redis Memtier / Redis Benchmark
PyPerformance:
  django_template
  go
NAMD
OpenSSL
Embree
OpenSSL
PyPerformance
OpenSSL
Embree
PlaidML:
  No - Inference - NASNer Large - CPU
  No - Inference - DenseNet 201 - CPU
  No - Inference - Mobilenet - CPU
  No - Inference - IMDB LSTM - CPU
GNU Octave Benchmark
Nginx:
  Short Connection - 1000
  Short Connection - 500
  Long Connection - 1000
  Long Connection - 500
PyPerformance
ONNX Runtime:
  fcn-resnet101-11 - OpenMP CPU
  bertsquad-10 - OpenMP CPU
  yolov4 - OpenMP CPU
GNU Octave Benchmark
OCRMyPDF
Hugin
Timed Wasmer Compilation
Timed Node.js Compilation
Timed Linux Kernel Compilation
Timed Godot Game Engine Compilation
AOM AV1:
  Speed 10 Realtime - Bosphorus 4K
  Speed 9 Realtime - Bosphorus 4K
  Speed 8 Realtime - Bosphorus 4K
OSPray:
  Magnetic Reconnection - SciVis
  NASA Streamlines - SciVis
  San Miguel - SciVis
GNU Radio:
  Hilbert Transform
  FM Deemphasis Filter
  IIR Filter
  FIR Filter
  Signal Source (Cosine)
  Five Back to Back FIR Filters
Zstd Compression
Quantum ESPRESSO
Chaos Group V-RAY
ONNX Runtime:
  super-resolution-10 - OpenMP CPU
  shufflenet-v2-10 - OpenMP CPU
NCNN:
  CPU - regnety_400m
  CPU - squeezenet_ssd
  CPU - yolov4-tiny
  CPU - resnet50
  CPU - alexnet
  CPU - resnet18
  CPU - vgg16
  CPU - googlenet
  CPU - blazeface
  CPU - efficientnet-b0
  CPU - mnasnet
  CPU - shufflenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU-v2-v2 - mobilenet-v2
  CPU - mobilenet
Redis Memtier / Redis Benchmark
PostgreSQL pgbench:
  100 - 250 - Read Write - Average Latency
  100 - 250 - Read Write
VP9 libvpx Encoding
Zstd Compression
High Performance Conjugate Gradient