Tests fot a future article on Phoronix by Michael Larabel.
Core i9 10900K Processor: Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads), Motherboard: Gigabyte Z490 AORUS MASTER (F3 BIOS), Chipset: Intel Comet Lake PCH, Memory: 16GB, Disk: Samsung SSD 970 EVO 250GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2060/875MHz), Audio: Realtek ALC1220, Network: Intel Device 15f3 + Intel Wi-Fi 6 AX201
OS: Ubuntu 20.04, Kernel: 5.7.0-999-generic (x86_64) 20200519, Desktop: GNOME Shell 3.36.1, Display Server: X Server 1.20.8, Display Driver: amdgpu 19.1.0, OpenGL: 4.6 Mesa 20.0.4 (LLVM 9.0.1), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --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,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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Not affected
Ryzen 9 3950X Processor: AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads)Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1201 BIOS)Chipset: AMD Starship/MatisseMemory: 16GB, Disk: Samsung SSD 970 EVO 250GB, Graphics: AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2060/875MHz), Audio: AMD Navi 10 HDMI AudioNetwork: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200
Compiler Notes: --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,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 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013Graphics Notes: GLAMORJava Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1)Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
Big Comparison Core i9 10900K vs. Ryzen 9 3950X Linux Benchmarks OpenBenchmarking.org Phoronix Test Suite 10.4.0m1 Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads) AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads) Gigabyte Z490 AORUS MASTER (F3 BIOS) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1201 BIOS) Intel Comet Lake PCH AMD Starship/Matisse 16GB Samsung SSD 970 EVO 250GB AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2060/875MHz) Realtek ALC1220 AMD Navi 10 HDMI Audio Intel Device 15f3 + Intel Wi-Fi 6 AX201 Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.7.0-999-generic (x86_64) 20200519 GNOME Shell 3.36.1 X Server 1.20.8 amdgpu 19.1.0 4.6 Mesa 20.0.4 (LLVM 9.0.1) GCC 9.3.0 ext4 3840x2160 Processors Motherboards Chipsets Memory Disk Graphics Audios Networks OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Big Comparison Core I9 10900K Vs. Ryzen 9 3950X Linux Benchmarks Performance System Logs - --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,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 - NONE / errors=remount-ro,relatime,rw - Core i9 10900K: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8 - Ryzen 9 3950X: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701013 - OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-3ubuntu1) - Python 2.7.18rc1 + Python 3.8.2 - Core i9 10900K: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Not affected - Ryzen 9 3950X: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected - Ryzen 9 3950X: GLAMOR
Core i9 10900K vs. Ryzen 9 3950X Comparison Phoronix Test Suite 10.4.0m1 Baseline +56.1% +56.1% +112.2% +112.2% +168.3% +168.3% 224.2% 176.9% 163.9% 148.7% 148.6% 105.7% 105.2% 98.5% 90.4% 79.1% 77.2% 75.7% 74.3% 73.9% 71.7% 71.4% 70.7% 68% 67.5% 65% 63.2% 58.8% 57.3% 55.3% 54.5% 53.1% 50.2% 49.9% 49.8% 49.1% 48.7% 48.6% 48.3% 45.4% 45.3% 44.1% 43.5% 43.5% 43.2% 43% 42.9% 42.6% 41.7% 41.3% 40.9% 40.7% 40.4% 40.1% 40.1% 40% 39.9% 39.6% 39.3% 38.5% 38.4% 38.2% 37.8% 37.4% 36.8% 36.6% 36% 35% 34.9% 33.6% 33.5% 32.2% 32.1% 31.7% 30.7% 30.5% 30% 29.8% 29.1% 29.1% 28.8% 28% 27.7% 27.6% 26.8% 26.4% 26.4% 26.3% 25.3% 24.9% 24.4% 24.2% 23.6% 23.5% 23.4% 22.2% 22.1% 21.5% 21.5% 21.5% 21.3% 20.9% 20.5% 20.4% 20.2% 20.1% 20% 20% 19.3% 19.3% 19.1% 18.9% 18.1% 17.8% 16.8% 16.5% 16.5% 15.8% 15.5% 15.1% 14.5% 14.5% 13.4% 13.1% 13% 12.9% 11.8% 11.7% 10.8% 10.6% 10.3% 10.2% 10% 9% 8.8% 8.6% 8.4% 7.8% 7.8% 7.3% 7.1% 6.7% 6.2% 6.1% 5.8% 5.6% 5.2% 5.1% 5.1% 4.9% 4.6% 4.1% 4.1% 4% 4% 3.8% 3.7% 3.5% 3.5% 3.4% 3.2% 3.2% 2.9% 2.8% 2.6% 2.3% 2.3% 2.2% 2.1% Atomic Fayalite-FIST Data Wavelet Volume - 3840 x 2160 Wavelet Volume - 3840 x 2160 m7m OpenMP CUTCP scikit_linearridgeregression Swirl 89.6% Rand Fill Sync myr-gr 78.1% Crypto O.M.G D.B.d - u8s8f32 Time To Solve S.N.1 72.6% TBB C++ Threads C++ Tasks EP.C 69.7% Create Processes 69.6% OpenMP OpenMP CFD Solver F.E.T 67.4% EP.D 67.4% Total Time - 4.1.R.P.P Tradebeans 64% Chimera 1080p 63.8% CPU Cache OpenGL - 3840 x 2160 - Medium 63% 2.A.2.B.S 60.7% Apache Spark Bayes 60.1% SP.B H.2.H.T.N.D 57.8% Vector Math A.L.B.C.C 56.9% Unnamed Pipe - 4096 FIFO Named Pipe - 4096 Elapsed Time Eigen 51.8% 1.A.2.B.S 51% DLSC G.I.R.1.S Classroom - CPU-Only Pabellon Barcelona - CPU-Only Enhanced Hair Savina Reactors.IO induct2 47.8% C.1.1.b 47.5% O.S 47.4% 1.A.2.B.S.2.T 46.9% Fishy Cat - CPU-Only 1.P.N.G GET 45.2% LPOP 45.2% R.C.a.P Summer Nature 4K 44.1% Noise-Gaussian Disney Material CPU MotionMark - Firefox 43.1% Total Time Total Time UASTC Level 3 Sharpen Read 41.6% C.u.1.0.3.s.i.i.C.L.1 Bedroom 2.F.E 40.8% OpenMP LavaMD Emily Resizing Rand Read 1.A.2.B.S.4.T 40% 3 CPU Stress Time To Compile Monte Carlo SET 39.1% IP Batch 1D - f32 38.7% C.S.T Barbershop - CPU-Only Time To Compile G.A.U.J.F 38.1% Launch Programs 38% Create Threads 37.8% B.C CoreMark Size 666 - I.P.S poly1305-aes 37.4% LPUSH 37.4% chacha 37.1% Time To Compile Context Switching Socket Activity ac 35.7% Pathtracer - Crown BMW27 - CPU-Only Chimera 1080p 34.9% 1 - Thread 34.3% FLOAT 34.2% Reactor 33.7% T.T.F.S.S 1 - Process 33.6% json aes256 32.4% Large Scene UASTC Level 2 linpk 32% Maze Solver - Google Chrome Speed 6 Realtime 31.7% 19 tConvolve MT - Gridding 30.7% V.P.M SADD 30.3% 1920 x 1080 - Windowed - Low - OpenGL 30.1% tConvolve MPI - Gridding 30.1% Time To Compile 1.H.M.2.D Float + SSE - 2D FFT Size 4096 29.4% Timed Time - Size 1,000 29.4% CPU Basemark - Google Chrome C240 Buckyball Speed 8 Realtime 28.2% pickle_pure_python 28.1% MD5 fatigue2 27.8% Material Tester Supercar O.B 27.4% H.2.V.E Water Benchmark Volumetric Caustic H2 25.9% R.4.b.P chaos 25.3% S.N.1 25.2% Read Test Chimera 1080p 24.8% Rand 24.8% Matrix Math Read While Writing Rand Forest 23.9% unsharp-mask 23.7% float 23.6% HWB Color Space OpenGL - 3840 x 2160 - High W.c - Google Chrome Memory Allocations 23.3% StyleBench - Firefox 23.2% A.C.P 23% S.N.1 22.6% deep Pathtracer - Asian Dragon I.M.D.S 22% go 21.9% 21.8% Rotate 21.6% vklBenchmark Pathtracer - Asian Dragon Obj No - Inference - Inception V3 - CPU raytrace 21.3% CPU No - Inference - VGG16 - CPU Jython 20.8% A.U.C.T 20.8% auto-levels 20.6% lbry Pod2html 20.5% air tConvolve MT - Degridding 20.3% json_loads 20.2% Time To Compile aermod 20.1% skein Time To Compile Maze Solver - Firefox Blowfish No - Inference - VGG19 - CPU rnflow 19.2% Speed 5 19.2% Tradesoap 19.1% AES-256 Latency Ping Pong 19% Average 19% D.B.d - f32 P.D.S 18.8% django_template 18.8% XZ 0 - Compression 18.6% Brotli 0 - Decompression 18.5% Wavelet Blur 18.2% 3840 x 2160 18.1% P.R.W.S.S.M Apache Spark ALS 17.9% D.B.d - u8s8f32 17.9% tConvolve MPI - Degridding 17.9% Tile Glass 17.9% W.c - Firefox T.F.A.T.T 17.6% 2to3 17.4% P.I.O.A.3.V.1.T 17% Reflect 16.9% crypto_pyaes 16.8% Non-Exponential WebXPRT - Firefox 16.7% ARES-6 - Firefox 16.7% Latency Under Load regex_compile 16.5% sha256t Brotli 2 - Decompression 16.4% Rotate 90 Degrees 16.3% Antialias 16.2% Blowfish 16.1% I.E.C.P.K.A 16.1% C.1.1.b 15.9% BT.C 15.8% U.U.D.S - 4096 15.8% L.S.T.A.T.t.g 15.8% Earthgecko Skyline Crush 0 - Decompression 15.7% C.1.1.b 15.7% ARES-6 - Google Chrome 15.6% No - Inference - DenseNet 201 - CPU C.C.4.S 15.5% Time To Compile 15.2% H.2.1.V.E 15.2% Relative Entropy Crush 0 - Compression 14.9% 2048 x 2048 - Total Time 14.6% Windowed Gaussian Memorial IP Batch 1D - u8s8f32 14.3% Write 14.2% KASUMI 14.2% Libdeflate 1 - Decompression 14.2% A.S.P 14.1% Cartoon 13.8% Jetstream - Google Chrome 13.7% Zstd 1 - Decompression 13.6% PSPDFKit WASM - Firefox 13.6% Twofish 13.5% IP Batch All - f32 Keyed Algorithms 13.2% Pathtracer ISPC - Crown Time To Compile 13% P.P.S Renderer2 - 3840 x 2160 12.8% CAST-256 12.6% tConvolve OpenMP - Degridding 12.5% nbody 12.3% Octane - Firefox 12.3% tConvolve OpenMP - Gridding 12.2% R.N.N.T - f32 12.2% Speed 6 Two-Pass 12% Write Test Time To Compile Crop 11.4% P.P.A 11.4% Create Files 11.1% Seq Fill 10.8% Water Caustic F.F.T UASTC Level 0 10.5% 32 - Process 10.4% mdbx 10.3% 4.A.6.B.S scikit_qda 10.3% 10.2% Summer Nature 4K rotate 10.1% Octane - Google Chrome 10% R.M.W All Algorithms 10% Zstd 8 - Decompression 9.9% 1920 x 1080 - Windowed - OpenGL 9.8% Color Enhance 9.7% TCP Socket - 4096 9% resize 9% D.B.d - f32 T.T.C.C.G.C 8.9% scikit_svm PSPDFKit WASM - Google Chrome 8.8% Quasigroup 8.8% Jetstream - Firefox 8.7% OpenMP Stencil test_fpu2 mp_prop_design 8.4% 6 8.4% Throughput 8.3% Zstd 1 - Compression 8.3% Speed 4 Two-Pass 8.1% C.u.1.0.3.s.i.i.C.L.9 8% Stock - 2D FFT Size 4096 7.9% Jetstream 2 - Google Chrome 7.9% ATPase Simulation - 327,506 Atoms pathlib 7.6% Serial D.T 7.2% WAV To FLAC 7.2% 7.1% SMP Parallel 5 7% doduc 7% Libdeflate 1 - Compression 7% python_startup 7% D.L.M.F 6.8% 10 6.8% Jetstream 2 - Firefox 6.7% Zstd 8 - Compression protein 6.5% 1000 Stack 6.2% 1 6.2% Graceful 1920 x 1080 - Windowed - High - OpenGL Summer Nature 4K Speed 0 5.3% R.N.N.I - f32 garbage leblancbig 5% Brotli 2 - Compression 5% Kraken - Google Chrome Unkeyed Algorithms 4.9% Speedometer - Firefox 4.7% Pathtracer ISPC - Asian Dragon Obj Scale 4.6% IP Batch All - u8s8f32 4.5% T.H.R 4.5% 1000 Convex 4.5% gas_dyn2 4.5% Solitaire 4.3% Pathtracer ISPC - Asian Dragon FT.C 1920 x 1080 - Windowed - Medium - OpenGL J.S.O.R MG.C 3.9% 136 Ragdolls Rand Fill Interpreter 3.6% S.F.P.R blosclz W.i - Firefox 3840 x 2160 - Ultimate 3.3% EXPoSE 3.3% Many Spheres - 3840 x 2160 Many Spheres - 3840 x 2160 2.D.T.P 3.2% Speed 0 Two-Pass 2.9% C.S.T CanvasMark - Firefox 2.8% Vulkan - 3840 x 2160 - Medium OpenMP LBM U.L.2.R.P.P 2.3% WebXPRT - Google Chrome 2.3% Speedometer - Google Chrome 3840 x 2160 - Low Brotli 0 - Compression Scala Dotty 2.1% Time To Compile 2.1% Composite Raytests 2% Stress-NG ebizzy CP2K Molecular Dynamics ParaView ParaView Cpuminer-Opt Parboil Mlpack Benchmark GraphicsMagick BLAKE2 Facebook RocksDB Cpuminer-Opt Stress-NG Parboil oneDNN MKL-DNN m-queens libgav1 toyBrot Fractal Generator toyBrot Fractal Generator toyBrot Fractal Generator NAS Parallel Benchmarks OSBench toyBrot Fractal Generator Rodinia Bork File Encrypter NAS Parallel Benchmarks C-Ray DaCapo Benchmark libgav1 Stress-NG Basemark GPU Multichase Pointer Chaser Renaissance NAS Parallel Benchmarks FFmpeg Stress-NG Core-Latency IPC_benchmark IPC_benchmark N-Queens LeelaChessZero Multichase Pointer Chaser LuxCoreRender Smallpt Blender Blender GraphicsMagick Tungsten Renderer Renaissance Polyhedron Fortran Benchmarks libgav1 Rodinia Multichase Pointer Chaser Blender Primesieve Redis Redis LuxCoreRender libgav1 GraphicsMagick Appleseed NeatBench Selenium Tachyon Stockfish Basis Universal GraphicsMagick CacheBench Zstd Compression IndigoBench GnuPG Rodinia Appleseed GraphicsMagick Facebook RocksDB Multichase Pointer Chaser Zstd Compression Stress-NG Timed MPlayer Compilation Java SciMark Redis oneDNN MKL-DNN 7-Zip Compression Blender Timed LLVM Compilation Renaissance OSBench OSBench Numenta Anomaly Benchmark Coremark Nettle Redis Nettle Timed Linux Kernel Compilation Stress-NG Stress-NG Polyhedron Fortran Benchmarks Embree Blender dav1d Hackbench Hierarchical INTegration Java Gradle Build YafaRay Hackbench Go Benchmarks Nettle rays1bench Basis Universal Polyhedron Fortran Benchmarks Selenium AOM AV1 Zstd Compression ASKAP BRL-CAD Redis Unigine Superposition ASKAP Timed FFmpeg Compilation asmFish FFTW SQLite Speedtest Sysbench Selenium NWChem AOM AV1 PyPerformance John The Ripper Polyhedron Fortran Benchmarks Appleseed IndigoBench Optcarrot Aircrack-ng x264 GROMACS Tungsten Renderer DaCapo Benchmark OpenSSL PyPerformance dav1d IOR dav1d LeelaChessZero Stress-NG Facebook RocksDB Renaissance GIMP PyPerformance GraphicsMagick Basemark GPU Selenium OSBench Selenium TSCP dav1d Cpuminer-Opt Embree Renaissance PyPerformance LULESH GraphicsMagick OpenVKL Embree PlaidML PyPerformance DeepSpeech PlaidML DaCapo Benchmark Renaissance GIMP Cpuminer-Opt Perl Benchmarks Polyhedron Fortran Benchmarks ASKAP PyPerformance Build2 Polyhedron Fortran Benchmarks Cpuminer-Opt Timed ImageMagick Compilation Selenium John The Ripper PlaidML Polyhedron Fortran Benchmarks VP9 libvpx Encoding DaCapo Benchmark Botan Sockperf Swet oneDNN MKL-DNN Timed HMMer Search PyPerformance lzbench lzbench GEGL Tesseract TTSIOD 3D Renderer Renaissance oneDNN MKL-DNN ASKAP GEGL Selenium PyBench PyPerformance G'MIC GEGL PyPerformance Tungsten Renderer Selenium Selenium Sockperf PyPerformance Cpuminer-Opt lzbench GEGL GEGL Botan Crypto++ dav1d NAS Parallel Benchmarks IPC_benchmark Gzip Compression Numenta Anomaly Benchmark lzbench dav1d Selenium PlaidML Fhourstones Timed GDB GNU Debugger Compilation x265 Numenta Anomaly Benchmark lzbench AOBench Numenta Anomaly Benchmark Intel Open Image Denoise oneDNN MKL-DNN CacheBench Botan lzbench Renaissance GEGL Selenium lzbench Selenium Botan oneDNN MKL-DNN Crypto++ Embree Timed Apache Compilation Himeno Benchmark Algebraic Multi-Grid Benchmark ET: Legacy Botan ASKAP PyPerformance Selenium ASKAP oneDNN MKL-DNN AOM AV1 IOR Timed PHP Compilation GEGL Timed MrBayes Analysis OSBench Facebook RocksDB Tungsten Renderer Java SciMark Basis Universal Hackbench Polyhedron Fortran Benchmarks Multichase Pointer Chaser Mlpack Benchmark Cython benchmark dav1d GIMP Selenium CacheBench Crypto++ lzbench Unigine Valley GEGL IPC_benchmark GIMP oneDNN MKL-DNN Git Mlpack Benchmark Selenium Minion Selenium Parboil Polyhedron Fortran Benchmarks Polyhedron Fortran Benchmarks rav1e Sockperf lzbench AOM AV1 XZ Compression FFTW Selenium Nebular Empirical Analysis Tool NAMD PyPerformance Radiance Benchmark libjpeg-turbo tjbench FLAC Audio Encoding Numpy Benchmark Radiance Benchmark rav1e Polyhedron Fortran Benchmarks lzbench PyPerformance Java SciMark rav1e Selenium lzbench Polyhedron Fortran Benchmarks Bullet Physics Engine rav1e Scikit-Learn Minion Unigine Superposition dav1d VP9 libvpx Encoding oneDNN MKL-DNN High Performance Conjugate Gradient Go Benchmarks Pennant lzbench Selenium Crypto++ Selenium Embree GEGL oneDNN MKL-DNN Renaissance Bullet Physics Engine Polyhedron Fortran Benchmarks Minion Embree NAS Parallel Benchmarks Unigine Superposition Java SciMark NAS Parallel Benchmarks Bullet Physics Engine Facebook RocksDB Perl Benchmarks ACES DGEMM C-Blosc Selenium Xonotic Numenta Anomaly Benchmark ParaView ParaView LibreOffice AOM AV1 ctx_clock Selenium Basemark GPU Parboil Basis Universal Selenium Selenium Xonotic lzbench Renaissance Timed GCC Compilation Java SciMark Bullet Physics Engine Core i9 10900K Ryzen 9 3950X
Big Comparison Core i9 10900K vs. Ryzen 9 3950X Linux Benchmarks pennant: sedovbig pennant: leblancbig nwchem: C240 Buckyball selenium: Basemark - Google Chrome selenium: Basemark - Firefox renaissance: Akka Unbalanced Cobwebbed Tree selenium: MotionMark - Firefox build-gcc: Time To Compile cryptopp: All Algorithms numenta-nab: EXPoSE plaidml: No - Inference - DenseNet 201 - CPU renaissance: Savina Reactors.IO basis: UASTC Level 2 + RDO Post-Processing renaissance: Apache Spark Bayes selenium: WebXPRT - Firefox selenium: WebXPRT - Google Chrome lczero: BLAS java-gradle-perf: Reactor build-llvm: Time To Compile polyhedron: gas_dyn2 blender: Barbershop - CPU-Only renaissance: Apache Spark PageRank renaissance: Rand Forest cryptopp: Keyed Algorithms core-latency: Average Latency Between CPU Cores selenium: CanvasMark - Firefox libgav1: Chimera 1080p 10-bit blender: Pabellon Barcelona - CPU-Only lczero: Eigen lczero: Rand renaissance: Genetic Algorithm Using Jenetics + Futures fftw: Float + SSE - 2D FFT Size 4096 libgav1: Chimera 1080p rocksdb: Rand Fill cryptopp: Integer + Elliptic Curve Public Key Algorithms selenium: MotionMark - Google Chrome plaidml: No - Inference - ResNet 50 - CPU blender: Classroom - CPU-Only renaissance: In-Memory Database Shootout unigine-heaven: 1920 x 1080 - Windowed - OpenGL polyhedron: test_fpu2 hpcg: brl-cad: VGR Performance Metric plaidml: No - Inference - Inception V3 - CPU selenium: Jetstream 2 - Firefox amg: cachebench: Read numpy: cp2k: Fayalite-FIST Data unigine-valley: 1920 x 1080 - Windowed - OpenGL hint: FLOAT fftw: Stock - 2D FFT Size 4096 unigine-super: 1920 x 1080 - Windowed - Ultra - OpenGL unigine-super: 1920 x 1080 - Windowed - High - OpenGL asmfish: 1024 Hash Memory, 26 Depth unigine-super: 1920 x 1080 - Windowed - Medium - OpenGL unigine-super: 1920 x 1080 - Windowed - Low - OpenGL rocksdb: Rand Fill Sync radiance: Serial selenium: Jetstream - Firefox rocksdb: Read While Writing selenium: Jetstream - Google Chrome appleseed: Emily polyhedron: mp_prop_design gromacs: Water Benchmark parboil: OpenMP LBM parboil: OpenMP MRI Gridding blender: Fishy Cat - CPU-Only selenium: Jetstream 2 - Google Chrome polyhedron: channel2 polyhedron: fatigue2 libgav1: Summer Nature 4K plaidml: No - Inference - VGG19 - CPU numenta-nab: Earthgecko Skyline renaissance: Scala Dotty plaidml: No - Inference - Mobilenet - CPU mt-dgemm: Sustained Floating-Point Rate cachebench: Write cachebench: Read / Modify / Write npb: BT.C npb: EP.D mlpack: scikit_qda selenium: ARES-6 - Firefox plaidml: No - Inference - VGG16 - CPU dav1d: Chimera 1080p 10-bit dav1d: Chimera 1080p 10-bit fhourstones: Complex Connect-4 Solving selenium: StyleBench - Google Chrome rav1e: 1 blender: BMW27 - CPU-Only renaissance: Apache Spark ALS appleseed: Disney Material build-linux-kernel: Time To Compile compress-gzip: Linux Source Tree Archiving To .tar.gz minion: Quasigroup appleseed: Material Tester yafaray: Total Time For Sample Scene polyhedron: rnflow rav1e: 5 pyperformance: python_startup stress-ng: CPU Cache stress-ng: Atomic openvkl: vklBenchmark gegl: Cartoon build-gdb: Time To Compile selenium: Speedometer - Firefox build2: Time To Compile cpuminer-opt: myr-gr compress-zstd: 19 vpxenc: Speed 0 perl-benchmark: Pod2html hackbench: 32 - Process cryptopp: Unkeyed Algorithms sockperf: Latency Under Load askap: tConvolve MT - Degridding askap: tConvolve MT - Gridding mrbayes: Primate Phylogeny Analysis pyperformance: raytrace stockfish: Total Time etlegacy: Renderer2 - 3840 x 2160 selenium: CanvasMark - Google Chrome mkl-dnn: Deconvolution Batch deconv_1d - u8s8f32 toybrot: OpenMP himeno: Poisson Pressure Solver namd: ATPase Simulation - 327,506 Atoms toybrot: TBB toybrot: C++ Threads toybrot: C++ Tasks luxcorerender: DLSC luxcorerender: Rainbow Colors and Prism indigobench: Bedroom indigobench: Supercar polyhedron: induct2 graphics-magick: Sharpen john-the-ripper: MD5 graphics-magick: Enhanced graphics-magick: Noise-Gaussian rocksdb: Rand Read graphics-magick: Resizing graphics-magick: Swirl graphics-magick: Rotate graphics-magick: HWB Color Space selenium: Speedometer - Google Chrome mkl-dnn: IP Batch All - f32 radiance: SMP Parallel mkl-dnn: IP Batch All - u8s8f32 selenium: StyleBench - Firefox askap: tConvolve MPI - Degridding askap: tConvolve MPI - Gridding gegl: Wavelet Blur minion: Solitaire tachyon: Total Time mlpack: scikit_ica npb: SP.B perl-benchmark: Interpreter basemark: Vulkan - 3840 x 2160 - High rawtherapee: Total Benchmark Time gegl: Color Enhance polyhedron: protein mlpack: scikit_linearridgeregression sqlite-speedtest: Timed Time - Size 1,000 cpuminer-opt: skein git: Time To Complete Common Git Commands deepspeech: CPU basemark: OpenGL - 3840 x 2160 - High pyperformance: 2to3 libreoffice: 20 Documents To PDF selenium: ARES-6 - Google Chrome m-queens: Time To Solve renaissance: Twitter HTTP Requests embree: Pathtracer - Asian Dragon Obj selenium: Octane - Firefox java-scimark2: Composite gmic: Plotting Isosurface Of A 3D Volume, 1000 Times build-php: Time To Compile embree: Pathtracer ISPC - Asian Dragon Obj paraview: Many Spheres - 3840 x 2160 paraview: Many Spheres - 3840 x 2160 basis: ETC1S c-ray: Total Time - 4K, 16 Rays Per Pixel selenium: Octane - Google Chrome pyperformance: go sockperf: Throughput encode-flac: WAV To FLAC minion: Graceful build-ffmpeg: Time To Compile basis: UASTC Level 3 blosc: blosclz xonotic: 3840 x 2160 - Ultimate rav1e: 6 libgav1: Summer Nature 1080p npb: FT.C mkl-dnn: Recurrent Neural Network Training - f32 cython-bench: mkl-dnn: Recurrent Neural Network Inference - f32 cpuminer-opt: m7m lzbench: XZ 0 - Compression lzbench: XZ 0 - Decompression stress-ng: Context Switching gegl: Rotate 90 Degrees lulesh: gegl: Antialias embree: Pathtracer - Crown cpuminer-opt: deep compress-7zip: Compress Speed Test pyperformance: django_template embree: Pathtracer ISPC - Crown xonotic: 3840 x 2160 - Ultra polyhedron: doduc pyperformance: crypto_pyaes tesseract: 3840 x 2160 redis: LPUSH embree: Pathtracer - Asian Dragon redis: SET numenta-nab: Bayesian Changepoint cpuminer-opt: sha256t cpuminer-opt: lbry polyhedron: mdbx pyperformance: chaos stress-ng: CPU Stress john-the-ripper: Blowfish aircrack-ng: stress-ng: Matrix Math stress-ng: Crypto stress-ng: Socket Activity stress-ng: Vector Math aom-av1: Speed 0 Two-Pass xonotic: 3840 x 2160 - High embree: Pathtracer ISPC - Asian Dragon aobench: 2048 x 2048 - Total Time polyhedron: air lzbench: Zstd 8 - Compression lzbench: Zstd 8 - Decompression pyperformance: regex_compile polyhedron: aermod dacapobench: Tradebeans pyperformance: nbody coremark: CoreMark Size 666 - Iterations Per Second aom-av1: Speed 6 Realtime compress-zstd: 3 lzbench: Crush 0 - Compression lzbench: Crush 0 - Decompression gegl: Reflect selenium: Kraken - Firefox selenium: Kraken - Google Chrome pyperformance: float pyperformance: json_loads rav1e: 10 gegl: Tile Glass redis: SADD smhasher: t1ha0_aes_avx2 smhasher: t1ha0_aes_avx2 xonotic: 3840 x 2160 - Low build-mplayer: Time To Compile pyperformance: pathlib aom-av1: Speed 6 Two-Pass lzbench: Brotli 2 - Decompression lzbench: Brotli 2 - Compression ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping dacapobench: H2 xsbench: ebizzy: tungsten: Water Caustic mlpack: scikit_svm compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 lzbench: Libdeflate 1 - Compression lzbench: Libdeflate 1 - Decompression build-imagemagick: Time To Compile botan: AES-256 pyperformance: pickle_pure_python basis: UASTC Level 2 lzbench: Brotli 0 - Decompression lzbench: Brotli 0 - Compression vpxenc: Speed 5 lzbench: Zstd 1 - Decompression lzbench: Zstd 1 - Compression rodinia: OpenMP Streamcluster mkl-dnn: Deconvolution Batch deconv_1d - f32 botan: Blowfish botan: Twofish botan: CAST-256 botan: KASUMI openssl: RSA 4096-bit Performance dav1d: Summer Nature 4K rocksdb: Seq Fill polyhedron: ac pybench: Total For Average Test Times build-apache: Time To Compile selenium: PSPDFKit WASM - Firefox compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 dav1d: Summer Nature 4K dav1d: Chimera 1080p selenium: Maze Solver - Firefox rodinia: OpenMP LavaMD selenium: WASM collisionDetection - Firefox aom-av1: Speed 4 Two-Pass selenium: PSPDFKit WASM - Google Chrome parboil: OpenMP Stencil tungsten: Hair oidn: Memorial dav1d: Chimera 1080p npb: MG.C polyhedron: linpk numenta-nab: Relative Entropy mkl-dnn: IP Batch 1D - f32 mkl-dnn: IP Batch 1D - u8s8f32 osbench: Create Threads swet: Average basemark: OpenGL - 3840 x 2160 - Medium go-benchmark: json rodinia: OpenMP CFD Solver selenium: Maze Solver - Google Chrome primesieve: 1e12 Prime Number Generation aom-av1: Speed 8 Realtime sockperf: Latency Ping Pong selenium: WASM collisionDetection - Google Chrome neat: gimp: unsharp-mask askap: tConvolve OpenMP - Gridding askap: tConvolve OpenMP - Degridding smhasher: MeowHash smhasher: MeowHash basemark: Vulkan - 3840 x 2160 - Medium redis: GET smhasher: Spooky32 smhasher: Spooky32 bork: File Encryption Time gimp: auto-levels rays1bench: Large Scene redis: LPOP dacapobench: Tradesoap gimp: rotate sysbench: CPU smhasher: fasthash32 smhasher: fasthash32 selenium: WASM imageConvolute - Firefox smhasher: t1ha2_atonce smhasher: t1ha2_atonce gnupg: 2GB File Encryption go-benchmark: garbage x265: H.265 1080p Video Encoding n-queens: Elapsed Time scikit-learn: neatbench: CPU smhasher: wyhash smhasher: wyhash ipc-benchmark: Unnamed Unix Domain Socket - 4096 numenta-nab: Windowed Gaussian gegl: Crop selenium: WASM imageConvolute - Google Chrome ipc-benchmark: TCP Socket - 4096 encode-mp3: WAV To MP3 basis: UASTC Level 0 npb: EP.C smallpt: Global Illumination Renderer; 128 Samples dacapobench: Jython gimp: resize tungsten: Volumetric Caustic tjbench: Decompression Throughput dav1d: Summer Nature 1080p ffmpeg: H.264 HD To NTSC DV paraview: Wavelet Volume - 3840 x 2160 paraview: Wavelet Volume - 3840 x 2160 dav1d: Summer Nature 1080p osbench: Create Files ipc-benchmark: FIFO Named Pipe - 4096 ipc-benchmark: Unnamed Pipe - 4096 osbench: Memory Allocations osbench: Create Processes osbench: Launch Programs gegl: Scale paraview: Wavelet Contour - 3840 x 2160 paraview: Wavelet Contour - 3840 x 2160 tungsten: Non-Exponential hmmer: Pfam Database Search nettle: aes256 x264: H.264 Video Encoding bullet: Raytests multichase: 1GB Array, 256 Byte Stride, 4 Threads multichase: 1GB Array, 256 Byte Stride, 2 Threads multichase: 1GB Array, 256 Byte Stride compress-pbzip2: 256MB File Compression mkl-dnn: Deconvolution Batch deconv_3d - u8s8f32 multichase: 256MB Array, 256 Byte Stride mkl-dnn: Deconvolution Batch deconv_3d - f32 nettle: sha512 multichase: 4MB Array, 64 Byte Stride hackbench: 1 - Thread hackbench: 1 - Process optcarrot: Optimized Benchmark parboil: OpenMP CUTCP tscp: AI Chess Performance nettle: chacha ior: Write Test ior: Read Test ctx-clock: Context Switch Time nettle: poly1305-aes blake2: bullet: 136 Ragdolls bullet: 1000 Convex bullet: 1000 Stack bullet: 3000 Fall bullet: Prim Trimesh bullet: Convex Trimesh java-scimark2: Monte Carlo java-scimark2: Fast Fourier Transform java-scimark2: Sparse Matrix Multiply java-scimark2: Dense LU Matrix Factorization java-scimark2: Jacobi Successive Over-Relaxation Core i9 10900K Ryzen 9 3950X 4227.746 3917.814 12612.4 1074.56 759.91 9184.565 231.54 716.255 1961.581817 624.538 3.35 15777.244 573.950 1704.120 294 264 378 188.102 505.431 39.99 473.60 2894.892 1465.498 789.168824 97.21 14181 31.25 426.20 607 231501 1249.404 27489 83.73 656303 6377.634939 1 7.38 338.66 2968.390 160.184 28.67 4.36353 192500 9.23 102.083 23126.76 4322.00 444.12 855.403 176.703 510613895.03709 6969.1 34.3 77.7 39969419 113.6 229.3 2875 577.884 237.52 2911882 258.92 299.753452 49.13 0.978 165.151103 54.937194 179.55 149.132 43.45 36.69 34.85 16.09 90.165 1339.483 17.18 5.351115 36212.481005556 55905.544804571 26329.21 1791.93 62.50 36.73 19.28 131.44 132.44 17312.0 37.6 0.205 114.39 1654.489 174.867928 61.708 28.833 93.440554 164.002915 108.878 12.58 0.670 6.04 22.76 230445.25 192.83 78.938 77.059 104 84.939 17627 30.3 8.20 0.09327881 49.161 407.907548 17.423 1946.32 1142.24 63.719 352 35260191 288.5 5033 121.267 80088 4394.725879 1.20434 79924 79413 79172 2.19 2.47 1.894 4.435 14.45 175 1383667 269 317 68514144 1266 529 888 1219 130 56.9110 182.363 19.0225 104 1953.46 1161.18 52.123 55.284448 65.7816 53.21 5283.52 0.00066725 81.93 53.309 50.055 11.62 4.05 44.924 45343 41.515 78.36647 59.64 241 6.403 17.47 59.649 2003.908 16.1775 38776 3053.01 16.006 47.704 18.2419 6344.437 63.28 42.177 52.130 54153 187 639629 7.699 41.961286 46.059 46.509 10910.3 318.7844013 1.622 135.37 11106.03 169.855 35.064 28.0154 407.75 51 138 5661607.84 32.369 11.960647 32.111 15.4524 12397 65002 38.3 17.7342 398.0959725 6.13 83.2 431.0337 2289561.42 17.5550 2770462.5 36.066 102523 38917 3.87 79.8 4730.92 23257 45911.889 62670.62 2677.73 8781.93 94530.77 0.35 438.9449334 20.5126 27.170 1.95 104 1884 133 4.57 2478 89.9 517909.118687 25.31 2866.6 131 612 25.416 715.7 779.3 82.5 18.3 3.460 24.658 3071108.17 46158.73 32.315 532.2734013 29.273 14.4 4.66 908 233 706.616 2615 2639580 495906 23.6946 20.91 22.326 290 1482 25.033 4925.383 331 25.170 783 543 30.43 1776 615 17.306 3.03768 556.522 446.240 175.908 115.381 3755.9 177.43 1431900 4.34 760 17.907 1148 21.925 185.20 700.92 5.4 21.053 414.4 2.93 1387 16.403124 20.2258 11.12 782.60 11256.14 2.31 16.561 3.30905 1.17466 8.883476 972233554 304.94 3100011 18.283 5.4 17.181 49.01 3.222 343.4547 13.970 11.946 1307.36 2164.78 51.813 40764.97 404.07 3788204.92 41.073 15360.87 5.124 9.693 81.82 3942561.25 2889 9.573 27065.9969 31.994 7842.52 27.1 32.065 17287.64 7.949 788879 72.38 10.350 8.782 18.3 18892.81 24.548 1260891 7.665 6.764 35.7272 1575932 6.974 6.514 1828.53 7.852 3319 6.135 6.98866 237.108141 671.39 4.562 1305.639 81.60 735.61 10.474451 1462821 1460097 56.163311 16.390483 26.023388 4.822 1961.623 188.23 5.14902 4.281 8093.59 126.49 2.043963 50.128 46.168 44.604 3.118 2.23525 41.813 4.76923 639.74 5.206 2.245 2.029 180.40 2.718560 1623785 1359.761 249.66 867.37 144 3725.66 4.03 2.233182 3.584657 3.810223 3.359547 0.782503 0.937118 1258.51 1930.39 2779.91 7302.38 1993.88 4297.572 4112.808 9794.6 1387.04 757.95 11096.640 161.79 731.029 1783.999801 644.836 3.87 10635.882 587.383 2727.905 252 258 380 251.425 365.636 41.78 342.25 3301.718 1815.569 697.187580 152.54 13796 21.19 285.86 400 185500 1725.093 21239 51.13 680458 5494.248758 1 7.34 226.13 3622.027 158.578 26.44 4.58602 251130 11.21 95.645 26109.85 3052.12 414.61 324.193 160.954 380487205.36603 6457.7 34.3 82.2 51867171 118.2 176.2 5148 538.599 218.55 3615702 227.80 213.491346 53.27 1.236 160.964244 31.274319 123.52 138.227 42.71 46.89 24.18 19.19 77.869 1367.865 17.28 5.537606 31703.460470254 61491.832424857 22727.17 1070.70 68.93 42.85 23.31 113.65 114.24 14986.6 37.7 0.193 84.77 1950.220 121.874074 45.114 33.392 101.658951 128.457773 81.477 15 0.626 6.46 37.15 747139.32 234.25 89.855 88.759 99.34 70.665 9898.85 39.6 7.79 0.11237626 54.263 389.039005 14.949 1617.76 874.050 70.989 427 50373394 255.8 5050 69.5926 47670 4966.364401 1.11719 46547 46331 46370 3.29 3.56 2.669 5.660 21.35 248 1771667 400 455 95962407 1774 1007 730 1507 133 50.1698 170.288 19.8851 84.4 1657.41 892.666 61.585 57.688167 46.0091 53.76 8390.19 0.00069115 80.95 52.809 54.906 12.37 2.04 58.132 54471 45.230 64.61712 73.68 283 6.605 20.20 34.304 2094.159 19.6503 34528 3115.94 18.735 42.697 19.0858 6546.761 65.30 42.788 31.594 49230 228 590729 8.250 39.558481 35.442 32.607 11288.3 308.6831229 1.497 78.41 11557.65 190.560 38.658 26.6223 838.57 43 136 7734523.74 37.640 9.8209433 37.298 20.8580 15150 90026 45.5 20.0572 393.3117643 6.56 97.2 364.8969 1666744.78 21.4302 1992290.86 26.176 119460 46910 4.27 100 6620.82 27740 58218.496 77933.94 4743.61 11945.15 148736.74 0.34 442.1980742 21.3600 31.131 1.62 111 1714 155 5.49 4064 101 711755.162474 19.22 4013.6 114 529 29.718 725.2 743.1 102 22.0 3.241 29.061 2357409.7 544.3905119 20.967 15.5 4.16 780 222 834.379 3293 2653413 1373026 21.3900 19.21 24.112 271 1298 20.860 5865.127 424 19.048 661 555 25.53 1563 568 25.517 2.55517 479.252 393.003 156.180 101.025 4707.4 187.35 1292441 5.89 894 20.240 1304 15.514 204.01 519.76 4.5 14.967 351.9 2.71 1509 15.106023 13.6067 12.73 626.95 10835.78 3.05 14.391 4.58909 1.34228 12.243907 816912713 187.04 2321631 10.914 4.1 11.821 38.24 3.835 278.3210 12.957 14.776 1164.69 1924.76 415.32 2609128.25 8.578 11.692 108.20 2716044.92 3442 10.542 34951.1082 26.2 11.194 750702 62.85 6.760 8.273 26.2 1088654 6.695 7.538 35.8952 1445302 6.954 7.197 1077.26 5.237 4010 6.689 5.53479 221.087385 547.69 7.197 3246.419 202.90 587.62 11.633563 2260588 2268105 69.227616 27.797222 35.923322 5.042 1976.572 189.67 4.40751 5.086 6114.17 159.92 2.084161 70.200 67.811 67.366 2.63474 67.194 4.37431 640.16 4.720 3.016 2.711 141.62 1.324664 1320223 992.023 279.04 1083.44 140 2711.19 7.64 2.150808 3.745295 4.047731 3.367286 0.788758 0.943135 1752.90 2134.31 2784.06 6834.75 2073.68 OpenBenchmarking.org
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial timeseries data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page
Java Gradle Build This test runs Java software project builds using the Gradle build system. It is intended to give developers an idea as to the build performance for development activities and build servers. Learn more via the OpenBenchmarking.org test page
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
Algebraic Multi-Grid Benchmark AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page