EPYC 7702 April 2021

AMD EPYC 7702 64-Core testing with a ASRockRack EPYCD8 (P2.40 BIOS) and ASPEED on Ubuntu 20.04 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 2104043-IB-EPYC7702A33
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
Timed Code Compilation 4 Tests
C/C++ Compiler Tests 5 Tests
CPU Massive 9 Tests
Creator Workloads 6 Tests
Encoding 4 Tests
HPC - High Performance Computing 2 Tests
Multi-Core 13 Tests
NVIDIA GPU Compute 2 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 3 Tests
Software Defined Radio 3 Tests
Server CPU Tests 8 Tests
Single-Threaded 2 Tests
Video Encoding 4 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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
1
April 03 2021
  2 Hours, 17 Minutes
2
April 03 2021
  6 Hours, 40 Minutes
3
April 04 2021
  6 Hours, 53 Minutes
Invert Hiding All Results Option
  5 Hours, 17 Minutes

Only show results where is faster than
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):


EPYC 7702 April 2021ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen Resolution123AMD EPYC 7702 64-Core @ 2.00GHz (64 Cores / 128 Threads)ASRockRack EPYCD8 (P2.40 BIOS)AMD Starship/Matisse126GB3841GB Micron_9300_MTFDHAL3T8TDPASPEEDVE2282 x Intel I350Ubuntu 20.045.9.0-050900rc6daily20200921-generic (x86_64) 20200920GNOME Shell 3.36.4X Server 1.20.8GCC 9.3.0ext41920x1080OpenBenchmarking.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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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: 0x8301034 Python Details- Python 3.8.2Security 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: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

123Result OverviewPhoronix Test Suite100%104%107%111%115%SVT-VP9Timed Linux Kernel CompilationXcompact3d Incompact3dStockfishAOM AV1GNU RadioViennaCLZstd Compressionlibavif avifencSVT-HEVConeDNNTimed Erlang/OTP CompilationTimed Mesa CompilationTimed Node.js CompilationBlenderSysbenchsimdjsonGNU GMP GMPbenchLuaRadioBotanLiquid-DSPtoyBrot Fractal Generator

EPYC 7702 April 2021toybrot: TBBtoybrot: OpenMPtoybrot: C++ Taskstoybrot: C++ Threadsbotan: KASUMIbotan: KASUMI - Decryptbotan: AES-256botan: AES-256 - Decryptbotan: Twofishbotan: Twofish - Decryptbotan: Blowfishbotan: Blowfish - Decryptbotan: CAST-256botan: CAST-256 - Decryptbotan: ChaCha20Poly1305botan: ChaCha20Poly1305 - Decryptonednn: 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 - CPUincompact3d: X3D-benchmarking input.i3dincompact3d: input.i3d 129 Cells Per Directionincompact3d: input.i3d 193 Cells Per Directionstockfish: Total Timecompress-zstd: 3 - Compression Speedcompress-zstd: 8 - Compression Speedcompress-zstd: 8 - Decompression Speedcompress-zstd: 19 - Compression Speedcompress-zstd: 19 - Decompression Speedcompress-zstd: 3, Long Mode - Compression Speedcompress-zstd: 3, Long Mode - Decompression Speedcompress-zstd: 8, Long Mode - Compression Speedcompress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedcompress-zstd: 19, Long Mode - Decompression Speedbuild-linux-kernel: Time To Compilesysbench: RAM / Memorysysbench: CPUaom-av1: Speed 4 Two-Pass - Bosphorus 4Kaom-av1: Speed 6 Realtime - Bosphorus 4Kaom-av1: Speed 6 Two-Pass - Bosphorus 4Kaom-av1: Speed 8 Realtime - Bosphorus 4Kaom-av1: Speed 9 Realtime - Bosphorus 4Kaom-av1: Speed 4 Two-Pass - Bosphorus 1080paom-av1: Speed 6 Realtime - Bosphorus 1080paom-av1: Speed 6 Two-Pass - Bosphorus 1080paom-av1: Speed 8 Realtime - Bosphorus 1080paom-av1: Speed 9 Realtime - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-vp9: Visual Quality Optimized - Bosphorus 1080psvt-hevc: 1 - Bosphorus 1080psvt-hevc: 7 - Bosphorus 1080psvt-hevc: 10 - Bosphorus 1080pblender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlyavifenc: 0avifenc: 2avifenc: 6avifenc: 10avifenc: 6, Losslessavifenc: 10, Losslessbuild-erlang: Time To Compilebuild-mesa: Time To Compilebuild-nodejs: Time To Compileviennacl: CPU BLAS - sCOPYviennacl: CPU BLAS - sAXPYviennacl: CPU BLAS - sDOTviennacl: CPU BLAS - dCOPYviennacl: CPU BLAS - dAXPYviennacl: CPU BLAS - dDOTviennacl: CPU BLAS - dGEMV-Nviennacl: CPU BLAS - dGEMV-Tviennacl: CPU BLAS - dGEMM-NNviennacl: CPU BLAS - dGEMM-NTviennacl: CPU BLAS - dGEMM-TNviennacl: CPU BLAS - dGEMM-TTgnuradio: Five Back to Back FIR Filtersgnuradio: Signal Source (Cosine)gnuradio: FIR Filtergnuradio: IIR Filtergnuradio: FM Deemphasis Filtergnuradio: Hilbert Transformliquid-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 - 57liquid-dsp: 128 - 256 - 57luaradio: Five Back to Back FIR Filtersluaradio: FM Deemphasis Filterluaradio: Hilbert Transformluaradio: Complex Phasesimdjson: Kostyasimdjson: LargeRandsimdjson: PartialTweetssimdjson: DistinctUserIDgmpbench: Total Time123747178487599720777.65375.0914560.3764560.395302.438302.234369.321367.42120.055120.066633.174632.6561.279855.043071.483140.9988011.009011.719932.670163.4540.9118021.224942089.27732.052081.53730.7840.4338382082.99734.1731.14965689.6040655.5490918225.88324931346418135279.425102763.583.52559.5410.52892.4444.12986.241.52552.233.556128.1996671.093.8211.896.7222.2225.945.7918.2416.2258.3767.34238.14362.92279.134.41277.91462.6138.74100.0355142.58116.5253.30628.41210.4423.71229.4386.767157.67923.304128.1847576874611390132089630.96369390.595.192.9331.72913.8534.5486.7744346.559654000118920000237970000475650000937750000169060000027157000003129700000451.2339.282.7515.52.120.663.553.594542724479417579727877.66175.1014558.6264559.088302.492302.337369.219367.797120.065120.058635.007631.0891.275445.043201.470480.9803231.008991.747742.670363.461410.8727691.222242098.23732.6252085.38732.8100.4461412085.08732.2941.15166690.4806725.9610107725.55242091331698025243.62441.12770.282.12564.8404.52888.0444.02992.641.12553.731.1556104.8196717.843.8211.746.9822.1825.715.7718.2216.0954.4765.79361.00361.43273.5934.59276.07460.8638.88100.5854.80142.94117.1453.21628.39110.4683.75429.5006.796157.47923.232128.4687646795071367128390428.562091.489.794.692.9323.02868.2537.3489.7734.1346.159569333119036667238236667476116667936776667169306666727182666673124233333452.0339.882.7513.82.130.663.533.614546.4711979217611725877.66375.1034555.6254555.311302.285302.180368.993367.804120.055120.096635.338630.5051.287645.051031.467070.9868061.008941.735682.668773.453140.8938301.218412095.26732.3822122.66733.5120.4503102094.12732.4831.15391691.0617475.6855896325.61175031326301585250.32386.12768.582.32555.8408.02884.6473.12989.641.22553.031.1626121.1796694.413.8311.746.7921.6725.995.7618.1716.0454.3266.10360.74363.64277.8734.45279.74462.9139.04100.0855.02142.46116.6653.28728.41410.4883.77329.5566.809157.30223.232128.3787536884791383132790427.365392.589.894.792.5322.62879.4535.1488.3730.1347.159520333119086667238053333476420000936146667169126666727272666673119400000452.2339.982.7514.52.130.663.533.594542.4OpenBenchmarking.org

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBB12316003200480064008000SE +/- 35.23, N = 3SE +/- 12.41, N = 37471724471191. (CXX) g++ options: -O3 -march=native -lpthread -lm -lgcc -lgcc_s -lc

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMP2312K4K6K8K10KSE +/- 18.59, N = 3SE +/- 13.93, N = 37941792178481. (CXX) g++ options: -O3 -march=native -lpthread -lm -lgcc -lgcc_s -lc

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Tasks31216003200480064008000SE +/- 31.63, N = 3SE +/- 110.25, N = 37611759975791. (CXX) g++ options: -O3 -march=native -lpthread -lm -lgcc -lgcc_s -lc

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ Threads23116003200480064008000SE +/- 11.93, N = 3SE +/- 30.64, N = 37278725872071. (CXX) g++ options: -O3 -march=native -lpthread -lm -lgcc -lgcc_s -lc

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI12320406080100SE +/- 0.01, N = 3SE +/- 0.01, N = 377.6577.6677.661. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - Decrypt12320406080100SE +/- 0.01, N = 3SE +/- 0.03, N = 375.0975.1075.101. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-25632110002000300040005000SE +/- 4.16, N = 3SE +/- 0.67, N = 34555.634558.634560.381. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - Decrypt32110002000300040005000SE +/- 5.30, N = 3SE +/- 1.20, N = 34555.314559.094560.401. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish31270140210280350SE +/- 0.11, N = 3SE +/- 0.02, N = 3302.29302.44302.491. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - Decrypt31270140210280350SE +/- 0.04, N = 3SE +/- 0.03, N = 3302.18302.23302.341. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish32180160240320400SE +/- 0.14, N = 3SE +/- 0.12, N = 3368.99369.22369.321. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - Decrypt12380160240320400SE +/- 0.08, N = 3SE +/- 0.08, N = 3367.42367.80367.801. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256132306090120150SE +/- 0.01, N = 3SE +/- 0.02, N = 3120.06120.06120.071. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - Decrypt213306090120150SE +/- 0.01, N = 3SE +/- 0.02, N = 3120.06120.07120.101. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305123140280420560700SE +/- 0.48, N = 3SE +/- 0.61, N = 3633.17635.01635.341. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - Decrypt321140280420560700SE +/- 0.53, N = 3SE +/- 0.23, N = 3630.51631.09632.661. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

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: CPU3120.28970.57940.86911.15881.4485SE +/- 0.01102, N = 3SE +/- 0.00139, N = 31.287641.279851.27544MIN: 1.22MIN: 1.22MIN: 1.221. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU3211.13652.2733.40954.5465.6825SE +/- 0.00299, N = 3SE +/- 0.00358, N = 35.051035.043205.04307MIN: 4.87MIN: 4.85MIN: 4.91. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU1230.33370.66741.00111.33481.6685SE +/- 0.00614, N = 3SE +/- 0.00090, N = 31.483141.470481.46707MIN: 1.24MIN: 1.21MIN: 1.211. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU1320.22470.44940.67410.89881.1235SE +/- 0.001469, N = 3SE +/- 0.001130, N = 30.9988010.9868060.980323MIN: 0.94MIN: 0.9MIN: 0.941. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU1230.2270.4540.6810.9081.135SE +/- 0.00095, N = 3SE +/- 0.00167, N = 31.009011.008991.00894MIN: 0.97MIN: 0.97MIN: 0.971. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU2310.39320.78641.17961.57281.966SE +/- 0.00765, N = 3SE +/- 0.00100, N = 31.747741.735681.71993MIN: 1.65MIN: 1.65MIN: 1.641. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU2130.60081.20161.80242.40323.004SE +/- 0.00818, N = 3SE +/- 0.00016, N = 32.670362.670162.66877MIN: 2.5MIN: 2.51MIN: 2.481. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU2130.77881.55762.33643.11523.894SE +/- 0.00371, N = 3SE +/- 0.00642, N = 33.461413.454003.45314MIN: 3.38MIN: 3.4MIN: 3.381. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU1320.20520.41040.61560.82081.026SE +/- 0.007517, N = 3SE +/- 0.011992, N = 40.9118020.8938300.872769MIN: 0.81MIN: 0.81MIN: 0.81. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU1230.27560.55120.82681.10241.378SE +/- 0.00091, N = 3SE +/- 0.00239, N = 31.224941.222241.21841MIN: 1.15MIN: 1.13MIN: 1.121. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU2315001000150020002500SE +/- 11.83, N = 3SE +/- 3.90, N = 32098.232095.262089.27MIN: 2065.31MIN: 2072.7MIN: 2067.671. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU231160320480640800SE +/- 1.26, N = 3SE +/- 1.01, N = 3732.63732.38732.05MIN: 720.33MIN: 718.93MIN: 720.721. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU3215001000150020002500SE +/- 10.59, N = 3SE +/- 3.09, N = 32122.662085.382081.53MIN: 2083.97MIN: 2066.13MIN: 2065.051. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU321160320480640800SE +/- 1.21, N = 3SE +/- 1.60, N = 3733.51732.81730.78MIN: 720.15MIN: 720.04MIN: 719.751. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU3210.10130.20260.30390.40520.5065SE +/- 0.001517, N = 3SE +/- 0.001158, N = 30.4503100.4461410.433838MIN: 0.39MIN: 0.38MIN: 0.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU321400800120016002000SE +/- 6.39, N = 3SE +/- 1.02, N = 32094.122085.082082.99MIN: 2069.05MIN: 2067.79MIN: 2067.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU132160320480640800SE +/- 0.14, N = 3SE +/- 0.35, N = 3734.17732.48732.29MIN: 722.64MIN: 720.58MIN: 720.41. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU3210.25960.51920.77881.03841.298SE +/- 0.00189, N = 3SE +/- 0.00070, N = 31.153911.151661.14965MIN: 1.09MIN: 1.08MIN: 1.091. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3d321150300450600750SE +/- 0.84, N = 3SE +/- 0.64, N = 3691.06690.48689.601. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Direction2311.34122.68244.02365.36486.706SE +/- 0.08892473, N = 3SE +/- 0.08476458, N = 35.961010775.685589635.549091821. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per Direction132612182430SE +/- 0.28, N = 3SE +/- 0.22, N = 325.8825.6125.551. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Time32130M60M90M120M150MSE +/- 1858448.97, N = 4SE +/- 1363379.57, N = 81326301581331698021346418131. (CXX) g++ options: -fprofile-use -m64 -lpthread -O3 -march=native -fno-exceptions -std=c++17 -pedantic -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -flto

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3 - Compression Speed23111002200330044005500SE +/- 2.38, N = 3SE +/- 3.83, N = 35243.65250.35279.41. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Compression Speed3215001000150020002500SE +/- 11.70, N = 3SE +/- 26.18, N = 32386.12441.12510.01. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Decompression Speed1326001200180024003000SE +/- 5.72, N = 3SE +/- 1.83, N = 32763.52768.52770.21. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Compression Speed23120406080100SE +/- 0.44, N = 3SE +/- 1.26, N = 382.182.383.51. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Decompression Speed3126001200180024003000SE +/- 7.03, N = 3SE +/- 5.02, N = 32555.82559.52564.81. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Compression Speed23190180270360450SE +/- 6.05, N = 3SE +/- 3.33, N = 3404.5408.0410.51. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 3, Long Mode - Decompression Speed3216001200180024003000SE +/- 3.16, N = 3SE +/- 0.59, N = 32884.62888.02892.41. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Compression Speed213100200300400500SE +/- 0.80, N = 3SE +/- 8.81, N = 15444.0444.1473.11. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Decompression Speed1326001200180024003000SE +/- 2.45, N = 15SE +/- 5.14, N = 32986.22989.62992.61. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Compression Speed231918273645SE +/- 0.09, N = 3SE +/- 0.23, N = 341.141.241.51. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Decompression Speed1325001000150020002500SE +/- 1.71, N = 3SE +/- 3.23, N = 32552.22553.02553.71. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

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 5.10.20Time To Compile132816243240SE +/- 0.28, N = 10SE +/- 0.28, N = 1033.5531.1631.16

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 / Memory23113002600390052006500SE +/- 9.71, N = 3SE +/- 9.05, N = 36104.816121.176128.191. (CC) gcc options: -pthread -O2 -funroll-loops -O3 -march=native -rdynamic -ldl -laio -lm

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPU13220K40K60K80K100KSE +/- 20.57, N = 3SE +/- 9.51, N = 396671.0996694.4196717.841. (CC) gcc options: -pthread -O2 -funroll-loops -O3 -march=native -rdynamic -ldl -laio -lm

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 3.0Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K1230.86181.72362.58543.44724.309SE +/- 0.01, N = 3SE +/- 0.01, N = 33.823.823.831. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K2313691215SE +/- 0.04, N = 3SE +/- 0.03, N = 311.7411.7411.891. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K132246810SE +/- 0.04, N = 3SE +/- 0.01, N = 36.726.796.981. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K321510152025SE +/- 0.30, N = 3SE +/- 0.20, N = 321.6722.1822.221. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K213612182430SE +/- 0.21, N = 3SE +/- 0.12, N = 325.7125.9425.991. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p3211.30282.60563.90845.21126.514SE +/- 0.01, N = 3SE +/- 0.01, N = 35.765.775.791. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p32148121620SE +/- 0.05, N = 3SE +/- 0.01, N = 318.1718.2218.241. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p32148121620SE +/- 0.03, N = 3SE +/- 0.03, N = 316.0416.0916.221. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p3211326395265SE +/- 0.38, N = 3SE +/- 0.25, N = 354.3254.4758.371. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.0Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p2311530456075SE +/- 0.53, N = 3SE +/- 0.03, N = 365.7966.1067.341. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 1080p13280160240320400SE +/- 0.35, N = 3SE +/- 0.55, N = 3238.14360.74361.001. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p21380160240320400SE +/- 1.33, N = 3SE +/- 3.53, N = 3361.43362.92363.641. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080p23160120180240300SE +/- 2.47, N = 3SE +/- 3.78, N = 3273.59277.87279.101. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080p132816243240SE +/- 0.05, N = 3SE +/- 0.08, N = 334.4134.4534.591. (CC) gcc options: -O3 -march=native -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080p21360120180240300SE +/- 0.37, N = 3SE +/- 1.54, N = 3276.07277.91279.741. (CC) gcc options: -O3 -march=native -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080p213100200300400500SE +/- 2.49, N = 3SE +/- 3.83, N = 3460.86462.61462.911. (CC) gcc options: -O3 -march=native -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt

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-Only321918273645SE +/- 0.24, N = 3SE +/- 0.11, N = 339.0438.8838.74

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: CPU-Only23120406080100SE +/- 0.60, N = 3SE +/- 0.04, N = 3100.58100.08100.03

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: CPU-Only3121224364860SE +/- 0.03, N = 3SE +/- 0.05, N = 355.0255.0054.80

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Barbershop - Compute: CPU-Only213306090120150SE +/- 0.05, N = 3SE +/- 0.10, N = 3142.94142.58142.46

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: CPU-Only231306090120150SE +/- 0.36, N = 3SE +/- 0.22, N = 3117.14116.66116.52

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 01321224364860SE +/- 0.01, N = 3SE +/- 0.00, N = 353.3153.2953.221. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 2312714212835SE +/- 0.02, N = 3SE +/- 0.03, N = 328.4128.4128.391. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 63213691215SE +/- 0.01, N = 3SE +/- 0.01, N = 310.4910.4710.441. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 103210.84891.69782.54673.39564.2445SE +/- 0.001, N = 3SE +/- 0.007, N = 33.7733.7543.7121. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 6, Lossless321714212835SE +/- 0.03, N = 3SE +/- 0.01, N = 329.5629.5029.441. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.9.0Encoder Speed: 10, Lossless321246810SE +/- 0.017, N = 3SE +/- 0.010, N = 36.8096.7966.7671. (CXX) g++ options: -O3 -fPIC -lm

Timed Erlang/OTP Compilation

This test times how long it takes to compile Erlang/OTP. Erlang is a programming language and run-time for massively scalable soft real-time systems with high availability requirements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Erlang/OTP Compilation 23.2Time To Compile123306090120150SE +/- 0.43, N = 3SE +/- 0.50, N = 3157.68157.48157.30

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To Compile132612182430SE +/- 0.02, N = 3SE +/- 0.02, N = 323.3023.2323.23

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 Compile231306090120150SE +/- 0.31, N = 3SE +/- 0.03, N = 3128.47128.38128.18

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPY312160320480640800SE +/- 5.84, N = 3SE +/- 11.85, N = 37537577641. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPY213150300450600750SE +/- 6.89, N = 3SE +/- 0.58, N = 36796876881. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOT132110220330440550SE +/- 13.58, N = 3SE +/- 27.14, N = 34614795071. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPY23130060090012001500SE +/- 14.53, N = 3SE +/- 8.82, N = 31367138313901. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPY21330060090012001500SE +/- 41.77, N = 3SE +/- 3.33, N = 31283132013271. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOT1232004006008001000SE +/- 6.84, N = 38969049041. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-N321714212835SE +/- 1.05, N = 3SE +/- 0.47, N = 327.328.530.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-T213140280420560700SE +/- 14.00, N = 3SE +/- 7.86, N = 36206366531. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NN23120406080100SE +/- 0.35, N = 3SE +/- 0.17, N = 391.492.593.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NT23120406080100SE +/- 0.15, N = 3SE +/- 0.15, N = 389.789.890.51. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TN23120406080100SE +/- 0.03, N = 3SE +/- 0.15, N = 394.694.795.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TT31220406080100SE +/- 0.30, N = 3SE +/- 0.20, N = 292.592.992.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

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 Filters32170140210280350SE +/- 3.89, N = 3SE +/- 3.91, N = 3322.6323.0331.71. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Signal Source (Cosine)2316001200180024003000SE +/- 4.36, N = 3SE +/- 27.86, N = 32868.22879.42913.81. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FIR Filter132120240360480600SE +/- 0.73, N = 3SE +/- 0.95, N = 3534.5535.1537.31. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: IIR Filter132110220330440550SE +/- 0.90, N = 3SE +/- 1.77, N = 3486.7488.3489.71. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: FM Deemphasis Filter321160320480640800SE +/- 5.82, N = 3SE +/- 2.41, N = 3730.1734.1744.01. 3.8.1.0

OpenBenchmarking.orgMiB/s, More Is BetterGNU RadioTest: Hilbert Transform21380160240320400SE +/- 0.32, N = 3SE +/- 2.03, N = 3346.1346.5347.11. 3.8.1.0

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: 5732113M26M39M52M65MSE +/- 66338.36, N = 3SE +/- 43364.09, N = 35952033359569333596540001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 5712330M60M90M120M150MSE +/- 28480.01, N = 3SE +/- 60092.52, N = 31189200001190366671190866671. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 5713250M100M150M200M250MSE +/- 116237.31, N = 3SE +/- 92616.29, N = 32379700002380533332382366671. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57123100M200M300M400M500MSE +/- 493637.29, N = 3SE +/- 230289.67, N = 34756500004761166674764200001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57321200M400M600M800M1000MSE +/- 1134097.78, N = 3SE +/- 935420.29, N = 39361466679367766679377500001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 32 - Buffer Length: 256 - Filter Length: 57132400M800M1200M1600M2000MSE +/- 218581.28, N = 3SE +/- 88191.71, N = 31690600000169126666716930666671. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57123600M1200M1800M2400M3000MSE +/- 4836091.17, N = 3SE +/- 1003881.36, N = 32715700000271826666727272666671. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 57321700M1400M2100M2800M3500MSE +/- 503322.30, N = 3SE +/- 2649108.86, N = 33119400000312423333331297000001. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid

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 Filters123100200300400500SE +/- 0.38, N = 3SE +/- 1.34, N = 3451.2452.0452.2

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: FM Deemphasis Filter12370140210280350SE +/- 0.19, N = 3SE +/- 0.03, N = 3339.2339.8339.9

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Hilbert Transform12320406080100SE +/- 0.03, N = 3SE +/- 0.00, N = 382.782.782.7

OpenBenchmarking.orgMiB/s, More Is BetterLuaRadio 0.9.1Test: Complex Phase231110220330440550SE +/- 0.22, N = 3SE +/- 0.64, N = 3513.8514.5515.5

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: Kostya1230.47930.95861.43791.91722.3965SE +/- 0.00, N = 3SE +/- 0.00, N = 32.122.132.131. (CXX) g++ options: -O3 -march=native -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: LargeRandom1230.14850.2970.44550.5940.7425SE +/- 0.00, N = 3SE +/- 0.00, N = 30.660.660.661. (CXX) g++ options: -O3 -march=native -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: PartialTweets2310.79881.59762.39643.19523.994SE +/- 0.01, N = 3SE +/- 0.00, N = 33.533.533.551. (CXX) g++ options: -O3 -march=native -pthread

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 0.8.2Throughput Test: DistinctUserID1320.81231.62462.43693.24924.0615SE +/- 0.01, N = 3SE +/- 0.00, N = 33.593.593.611. (CXX) g++ options: -O3 -march=native -pthread

GNU GMP GMPbench

GMPbench is a test of the GNU Multiple Precision Arithmetic (GMP) Library. GMPbench is a single-threaded integer benchmark that leverages the GMP library to stress the CPU with widening integer multiplication. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.2.1Total Time132100020003000400050004542.04542.44546.41. (CC) gcc options: -O3 -fomit-frame-pointer -lm

117 Results Shown

toyBrot Fractal Generator:
  TBB
  OpenMP
  C++ Tasks
  C++ Threads
Botan:
  KASUMI
  KASUMI - Decrypt
  AES-256
  AES-256 - Decrypt
  Twofish
  Twofish - Decrypt
  Blowfish
  Blowfish - Decrypt
  CAST-256
  CAST-256 - Decrypt
  ChaCha20Poly1305
  ChaCha20Poly1305 - Decrypt
oneDNN:
  IP Shapes 1D - f32 - CPU
  IP Shapes 3D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
Xcompact3d Incompact3d:
  X3D-benchmarking input.i3d
  input.i3d 129 Cells Per Direction
  input.i3d 193 Cells Per Direction
Stockfish
Zstd Compression:
  3 - Compression Speed
  8 - Compression Speed
  8 - Decompression Speed
  19 - Compression Speed
  19 - Decompression Speed
  3, Long Mode - Compression Speed
  3, Long Mode - Decompression Speed
  8, Long Mode - Compression Speed
  8, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
  19, Long Mode - Decompression Speed
Timed Linux Kernel Compilation
Sysbench:
  RAM / Memory
  CPU
AOM AV1:
  Speed 4 Two-Pass - Bosphorus 4K
  Speed 6 Realtime - Bosphorus 4K
  Speed 6 Two-Pass - Bosphorus 4K
  Speed 8 Realtime - Bosphorus 4K
  Speed 9 Realtime - Bosphorus 4K
  Speed 4 Two-Pass - Bosphorus 1080p
  Speed 6 Realtime - Bosphorus 1080p
  Speed 6 Two-Pass - Bosphorus 1080p
  Speed 8 Realtime - Bosphorus 1080p
  Speed 9 Realtime - Bosphorus 1080p
SVT-VP9:
  VMAF Optimized - Bosphorus 1080p
  PSNR/SSIM Optimized - Bosphorus 1080p
  Visual Quality Optimized - Bosphorus 1080p
SVT-HEVC:
  1 - Bosphorus 1080p
  7 - Bosphorus 1080p
  10 - Bosphorus 1080p
Blender:
  BMW27 - CPU-Only
  Classroom - CPU-Only
  Fishy Cat - CPU-Only
  Barbershop - CPU-Only
  Pabellon Barcelona - CPU-Only
libavif avifenc:
  0
  2
  6
  10
  6, Lossless
  10, Lossless
Timed Erlang/OTP Compilation
Timed Mesa Compilation
Timed Node.js Compilation
ViennaCL:
  CPU BLAS - sCOPY
  CPU BLAS - sAXPY
  CPU BLAS - sDOT
  CPU BLAS - dCOPY
  CPU BLAS - dAXPY
  CPU BLAS - dDOT
  CPU BLAS - dGEMV-N
  CPU BLAS - dGEMV-T
  CPU BLAS - dGEMM-NN
  CPU BLAS - dGEMM-NT
  CPU BLAS - dGEMM-TN
  CPU BLAS - dGEMM-TT
GNU Radio:
  Five Back to Back FIR Filters
  Signal Source (Cosine)
  FIR Filter
  IIR Filter
  FM Deemphasis Filter
  Hilbert Transform
Liquid-DSP:
  1 - 256 - 57
  2 - 256 - 57
  4 - 256 - 57
  8 - 256 - 57
  16 - 256 - 57
  32 - 256 - 57
  64 - 256 - 57
  128 - 256 - 57
LuaRadio:
  Five Back to Back FIR Filters
  FM Deemphasis Filter
  Hilbert Transform
  Complex Phase
simdjson:
  Kostya
  LargeRand
  PartialTweets
  DistinctUserID
GNU GMP GMPbench