AMD Ryzen Threadripper 3970X 32-Core testing with a ASUS ROG ZENITH II EXTREME (0702 BIOS) and llvmpipe 63GB on Ubuntu 19.10 via the Phoronix Test Suite.
Threadripper 3970X Processor: AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads), Motherboard: ASUS ROG ZENITH II EXTREME (0702 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Force MP600, Graphics: llvmpipe 63GB, Audio: AMD Navi 10 HDMI Audio, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200
OS: Ubuntu 19.10, Kernel: 5.3.0-18-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.8 (LLVM 9.0 128 bits), Compiler: GCC 9.2.1 20191008 + Clang 9.0.0-2, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-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: 0x8301025Java Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu119.10.1)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: 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
16 Cores Processor: AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (16 Cores) , Motherboard: ASUS ROG ZENITH II EXTREME (0702 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: 1000GB Force MP600, Graphics: llvmpipe 63GB, Audio: AMD Navi 10 HDMI Audio, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200
OS: Ubuntu 19.10, Kernel: 5.3.0-40-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.8 (LLVM 9.0 128 bits), Compiler: GCC 9.2.1 20191008 + Clang 9.0.0-2, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-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: 0x8301025Java Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu119.10.1)Python Notes: Python 2.7.17 + Python 3.7.5Security 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 RSB filling + tsx_async_abort: Not affected
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.
OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark Threadripper 3970X 16 Cores 6K 12K 18K 24K 30K SE +/- 14.75, N = 3 SE +/- 24.90, N = 3 24786.28 26671.34 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi
Apache Benchmark This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving Threadripper 3970X 16 Cores 9K 18K 27K 36K 45K SE +/- 25.01, N = 3 SE +/- 50.68, N = 3 36286.78 41019.20 1. (CC) gcc options: -shared -fPIC -O2 -pthread
OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Random Write - Clients: 16 Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 20.61, N = 15 SE +/- 29.55, N = 15 72 81
OpenBenchmarking.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient CPU Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.25, N = 3 SE +/- 0.23, N = 3 25.18 23.52 1. (CXX) g++ options: -rdynamic
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Degridding Threadripper 3970X 16 Cores 800 1600 2400 3200 4000 SE +/- 12.65, N = 3 SE +/- 2.81, N = 3 3738.11 3463.50 1. (CXX) g++ options: -lpthread
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Gridding Threadripper 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 2.78, N = 3 SE +/- 1.16, N = 3 2682.40 2368.48 1. (CXX) g++ options: -lpthread
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Degridding Threadripper 3970X 16 Cores 800 1600 2400 3200 4000 SE +/- 6.40, N = 3 SE +/- 0.00, N = 3 3795.21 3544.17 1. (CXX) g++ options: -lpthread
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Gridding Threadripper 3970X 16 Cores 1000 2000 3000 4000 5000 SE +/- 42.14, N = 15 SE +/- 29.54, N = 11 4771.16 3330.88 1. (CXX) g++ options: -lpthread
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Degridding Threadripper 3970X 16 Cores 800 1600 2400 3200 4000 SE +/- 8.15, N = 15 SE +/- 7.16, N = 11 3764.47 3482.69 1. (CXX) g++ options: -lpthread
OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Semaphore Release And Acquire Threadripper 3970X 16 Cores 3 6 9 12 15 11 11 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: BMW27 - Compute: CPU-Only Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 40.40 97.69
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Classroom - Compute: CPU-Only Threadripper 3970X 16 Cores 60 120 180 240 300 SE +/- 0.18, N = 3 SE +/- 0.30, N = 3 109.39 283.82
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Fishy Cat - Compute: CPU-Only Threadripper 3970X 16 Cores 40 80 120 160 200 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 67.04 163.13
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Barbershop - Compute: CPU-Only Threadripper 3970X 16 Cores 90 180 270 360 450 SE +/- 0.33, N = 3 SE +/- 0.65, N = 3 159.93 430.81
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Pabellon Barcelona - Compute: CPU-Only Threadripper 3970X 16 Cores 80 160 240 320 400 SE +/- 0.24, N = 3 SE +/- 0.17, N = 3 146.02 382.22
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: BMW27 - Compute: CPU-Only Threadripper 3970X 16 Cores 30 60 90 120 150 SE +/- 0.09, N = 3 SE +/- 0.17, N = 3 47.57 119.58
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Classroom - Compute: CPU-Only Threadripper 3970X 16 Cores 70 140 210 280 350 SE +/- 0.31, N = 3 SE +/- 0.36, N = 3 119.47 314.82
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Fishy Cat - Compute: CPU-Only Threadripper 3970X 16 Cores 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 71.28 178.46
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Barbershop - Compute: CPU-Only Threadripper 3970X 16 Cores 110 220 330 440 550 SE +/- 0.21, N = 3 SE +/- 0.54, N = 3 194.17 501.07
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Pabellon Barcelona - Compute: CPU-Only Threadripper 3970X 16 Cores 90 180 270 360 450 SE +/- 0.59, N = 3 SE +/- 0.44, N = 3 153.88 414.42
BlogBench BlogBench is designed to replicate the load of a real-world busy file server by stressing the file-system with multiple threads of random reads, writes, and rewrites. The behavior is mimicked of that of a blog by creating blogs with content and pictures, modifying blog posts, adding comments to these blogs, and then reading the content of the blogs. All of these blogs generated are created locally with fake content and pictures. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Read Threadripper 3970X 16 Cores 300K 600K 900K 1200K 1500K SE +/- 12676.46, N = 8 SE +/- 3455.51, N = 3 1260198 1283483 1. (CC) gcc options: -O2 -pthread
OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Write Threadripper 3970X 16 Cores 11K 22K 33K 44K 55K SE +/- 1160.31, N = 3 SE +/- 102.18, N = 3 49874 11700 1. (CC) gcc options: -O2 -pthread
Bork File Encrypter Bork is a small, cross-platform file encryption utility. It is written in Java and designed to be included along with the files it encrypts for long-term storage. This test measures the amount of time it takes to encrypt a sample file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Bork File Encrypter 1.4 File Encryption Time Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.005, N = 3 SE +/- 0.011, N = 3 8.121 8.556
OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: AES-256 Threadripper 3970X 16 Cores 1300 2600 3900 5200 6500 SE +/- 7.95, N = 3 SE +/- 14.95, N = 3 5902.14 5858.03 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: Twofish Threadripper 3970X 16 Cores 80 160 240 320 400 SE +/- 3.16, N = 3 SE +/- 0.02, N = 3 391.43 385.68 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: Blowfish Threadripper 3970X 16 Cores 100 200 300 400 500 SE +/- 0.50, N = 3 SE +/- 0.01, N = 3 475.10 471.10 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: CAST-256 Threadripper 3970X 16 Cores 30 60 90 120 150 SE +/- 1.54, N = 3 SE +/- 0.27, N = 3 154.15 154.99 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
BRL-CAD BRL-CAD 7.28.0 is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.28.0 VGR Performance Metric Threadripper 3970X 16 Cores 110K 220K 330K 440K 550K 507345 210066 1. (CXX) g++ options: -std=c++98 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 3000 Fall Threadripper 3970X 16 Cores 0.7713 1.5426 2.3139 3.0852 3.8565 SE +/- 0.002468, N = 3 SE +/- 0.003898, N = 3 3.394250 3.428156 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Stack Threadripper 3970X 16 Cores 0.9297 1.8594 2.7891 3.7188 4.6485 SE +/- 0.005908, N = 3 SE +/- 0.002167, N = 3 4.094888 4.132133 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Convex Threadripper 3970X 16 Cores 0.8601 1.7202 2.5803 3.4404 4.3005 SE +/- 0.000553, N = 3 SE +/- 0.003706, N = 3 3.787201 3.822767 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 136 Ragdolls Threadripper 3970X 16 Cores 0.4939 0.9878 1.4817 1.9756 2.4695 SE +/- 0.001302, N = 3 SE +/- 0.001501, N = 3 2.173580 2.195278 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Prim Trimesh Threadripper 3970X 16 Cores 0.1811 0.3622 0.5433 0.7244 0.9055 SE +/- 0.000329, N = 3 SE +/- 0.000909, N = 3 0.796787 0.804927 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Convex Trimesh Threadripper 3970X 16 Cores 0.2163 0.4326 0.6489 0.8652 1.0815 SE +/- 0.000443, N = 3 SE +/- 0.000327, N = 3 0.952042 0.961552 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
C-Ray This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Threadripper 3970X 16 Cores 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 16.38 34.16 1. (CC) gcc options: -lm -lpthread -O3
CacheBench This is a performance test of CacheBench, which is part of LLCbench. CacheBench is designed to test the memory and cache bandwidth performance Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read Threadripper 3970X 16 Cores 700 1400 2100 2800 3500 SE +/- 4.12, N = 3 SE +/- 0.65, N = 3 3035.03 3024.68 MIN: 3020.86 / MAX: 3044.34 MIN: 3022.65 / MAX: 3028.8 1. (CC) gcc options: -lrt
OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Write Threadripper 3970X 16 Cores 7K 14K 21K 28K 35K SE +/- 14.14, N = 3 SE +/- 29.01, N = 3 31832.50 31631.79 MIN: 27271.39 / MAX: 33182.75 MIN: 27804.64 / MAX: 32902.03 1. (CC) gcc options: -lrt
OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read / Modify / Write Threadripper 3970X 16 Cores 13K 26K 39K 52K 65K SE +/- 167.50, N = 3 SE +/- 147.71, N = 3 61162.94 61009.39 MIN: 53743.85 / MAX: 65830.07 MIN: 55206.66 / MAX: 65416.9 1. (CC) gcc options: -lrt
CLOMP CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Speedup, More Is Better CLOMP 3.3 Static OMP Speedup Threadripper 3970X 16 Cores 0.684 1.368 2.052 2.736 3.42 SE +/- 0.01, N = 25 SE +/- 0.05, N = 25 0.71 3.04 1. (CC) gcc options: --openmp -O3 -lm
CloverLeaf CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm8192.in input file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf Lagrangian-Eulerian Hydrodynamics Threadripper 3970X 16 Cores 0.2835 0.567 0.8505 1.134 1.4175 SE +/- 0.06, N = 12 SE +/- 0.00, N = 3 1.05 1.26 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
Compile Bench Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create Threadripper 3970X 16 Cores 150 300 450 600 750 SE +/- 1.98, N = 3 SE +/- 3.20, N = 3 716.22 548.75
CP2K Molecular Dynamics CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. This test profile currently makes use of the OpenMP implementation and using the Fayalite-FIST molecular dynamics run and measures the total time to complete. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better CP2K Molecular Dynamics 6.1 Fayalite-FIST Data Threadripper 3970X 16 Cores 110 220 330 440 550 494.65 423.75
OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: deep Threadripper 3970X 16 Cores 6K 12K 18K 24K 30K SE +/- 31.80, N = 3 SE +/- 1488.63, N = 15 29323.00 6879.91 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: lbry Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 464.63, N = 3 SE +/- 330.05, N = 15 89853 41063 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: skein Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 194.28, N = 3 SE +/- 200.78, N = 3 102703 49073 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: myr-gr Threadripper 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 71.26, N = 3 SE +/- 1707.65, N = 15 13923.00 15369.09 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: sha256t Threadripper 3970X 16 Cores 50K 100K 150K 200K 250K SE +/- 26.03, N = 3 SE +/- 826.56, N = 3 223623 106950 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Boat - Acceleration: CPU-only Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.097, N = 15 SE +/- 0.007, N = 3 6.010 5.060
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Masskrug - Acceleration: CPU-only Threadripper 3970X 16 Cores 0.8429 1.6858 2.5287 3.3716 4.2145 SE +/- 0.017, N = 3 SE +/- 0.009, N = 3 3.088 3.746
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Server Rack - Acceleration: CPU-only Threadripper 3970X 16 Cores 0.027 0.054 0.081 0.108 0.135 SE +/- 0.004, N = 12 SE +/- 0.000, N = 3 0.120 0.097
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Server Room - Acceleration: CPU-only Threadripper 3970X 16 Cores 0.4628 0.9256 1.3884 1.8512 2.314 SE +/- 0.009, N = 3 SE +/- 0.010, N = 3 1.991 2.057
dav1d Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 4K Threadripper 3970X 16 Cores 70 140 210 280 350 SE +/- 0.26, N = 3 SE +/- 0.51, N = 3 324.66 205.50 MIN: 214.04 / MAX: 344.18 MIN: 190.74 / MAX: 228.56 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 1080p Threadripper 3970X 16 Cores 160 320 480 640 800 SE +/- 3.50, N = 3 SE +/- 1.76, N = 3 726.09 556.99 MIN: 460.2 / MAX: 805.89 MIN: 471.9 / MAX: 604.99 1. (CC) gcc options: -pthread
Dbench Dbench is a benchmark designed by the Samba project as a free alternative to netbench, but dbench contains only file-system calls for testing the disk performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 12 Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 13.11, N = 9 SE +/- 14.76, N = 8 595.26 1466.07 1. (CC) gcc options: -lpopt -O2
OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 12 Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 26.66, N = 9 SE +/- 46.78, N = 9 665.37 1382.09
DeepSpeech Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU Threadripper 3970X 16 Cores 13 26 39 52 65 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 56.68 49.10
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Crown Threadripper 3970X 16 Cores 8 16 24 32 40 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 35.55 12.83 MIN: 32.78 / MAX: 37.31 MIN: 12.72 / MAX: 13.03
Ethr Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 2 Threadripper 3970X 16 Cores 700 1400 2100 2800 3500 SE +/- 3.00, N = 3 SE +/- 6.36, N = 3 1844.58 3314.79 MIN: 1810 / MAX: 1910 MIN: 3240 / MAX: 3400
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Threadripper 3970X 16 Cores 200K 400K 600K 800K 1000K SE +/- 8852.93, N = 3 SE +/- 6931.83, N = 3 1083225 606976 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read Threadripper 3970X 16 Cores 40M 80M 120M 160M 200M SE +/- 1599226.86, N = 3 SE +/- 155873.46, N = 3 180626444 72774397 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Sequential Fill Threadripper 3970X 16 Cores 200K 400K 600K 800K 1000K SE +/- 3258.34, N = 3 SE +/- 8372.80, N = 15 1147975 702809 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync Threadripper 3970X 16 Cores 6K 12K 18K 24K 30K SE +/- 999.84, N = 15 SE +/- 17.38, N = 3 29167 9106 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing Threadripper 3970X 16 Cores 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 71829.99, N = 6 SE +/- 32658.12, N = 4 6204076 2381360 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
FFmpeg This test uses FFmpeg for testing the system's audio/video encoding performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 4.0.2 H.264 HD To NTSC DV Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.056, N = 3 SE +/- 0.039, N = 3 7.331 5.041 1. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lxcb-shm -lxcb-shape -lxcb-xfixes -lasound -lSDL2 -lsndio -pthread -lbz2 -llzma -std=c11 -fomit-frame-pointer -fPIC -O3 -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT
FFTE FFTE is a package by Daisuke Takahashi to compute Discrete Fourier Transforms of 1-, 2- and 3- dimensional sequences of length (2^p)*(3^q)*(5^r). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MFLOPS, More Is Better FFTE 6.0 Test: N=256, 1D Complex FFT Routine Threadripper 3970X 2K 4K 6K 8K 10K SE +/- 15.75, N = 3 9483.92 1. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 Threadripper 3970X 16 Cores 1500 3000 4500 6000 7500 SE +/- 2.20, N = 3 SE +/- 16.83, N = 3 6875.5 6841.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 Threadripper 3970X 16 Cores 5K 10K 15K 20K 25K SE +/- 102.34, N = 3 SE +/- 48.64, N = 3 21610 21534 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Fhourstones This integer benchmark solves positions in the game of Connect-4, as played on a vertical 7x6 board. By default, it uses a 64Mb transposition table with the twobig replacement strategy. Positions are represented as 64-bit bitboards, and the hash function is computed using a single 64-bit modulo operation, giving 64-bit machines a slight edge. The alpha-beta searcher sorts moves dynamically based on the history heuristic. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Kpos / sec, More Is Better Fhourstones 3.1 Complex Connect-4 Solving Threadripper 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 35.91, N = 3 SE +/- 53.43, N = 3 14702.3 15067.4 1. (CC) gcc options: -O3
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 60K 120K 180K 240K 300K SE +/- 13593.30, N = 12 SE +/- 5033.22, N = 3 263667 277000
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 100K 200K 300K 400K 500K SE +/- 1855.92, N = 3 SE +/- 3844.19, N = 3 459333 364333
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 70K 140K 210K 280K 350K SE +/- 4041.45, N = 3 SE +/- 2185.81, N = 3 307000 320333
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.12 Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 13 26 39 52 65 SE +/- 0.20, N = 3 SE +/- 0.15, N = 3 56.2 45.2
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.12 Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 53.12, N = 12 SE +/- 8.11, N = 3 1030 1068
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.12 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 7.64, N = 3 SE +/- 6.56, N = 3 1794 1442
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.12 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 16.50, N = 3 SE +/- 2.73, N = 3 1200 1246
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.12 Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory 16 Cores 60K 120K 180K 240K 300K SE +/- 2333.33, N = 3 273333
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.12 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory 16 Cores 80K 160K 240K 320K 400K SE +/- 1527.53, N = 3 369000
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.12 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory 16 Cores 70K 140K 210K 280K 350K SE +/- 666.67, N = 3 319333
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 2.91, N = 3 SE +/- 10.95, N = 15 1151 1234 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 70K 140K 210K 280K 350K SE +/- 881.92, N = 3 SE +/- 2820.78, N = 15 294333 315733 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 102.96, N = 12 706 1309 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 70K 140K 210K 280K 350K SE +/- 26330.47, N = 12 180633 335000 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 15.41, N = 15 SE +/- 27.78, N = 15 1346 1553 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 90K 180K 270K 360K 450K SE +/- 3928.97, N = 15 SE +/- 7133.29, N = 15 344533 397600 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 12.94, N = 4 1052 961 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 60K 120K 180K 240K 300K SE +/- 10149.45, N = 15 SE +/- 3424.79, N = 4 269200 245750 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 5000 Files, 1MB Size, 4 Threads Threadripper 3970X 16 Cores 130 260 390 520 650 SE +/- 28.74, N = 12 SE +/- 81.95, N = 12 485.9 602.3 1. (CC) gcc options: -static
OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 4000 Files, 32 Sub Dirs, 1MB Size Threadripper 3970X 16 Cores 140 280 420 560 700 SE +/- 3.35, N = 3 SE +/- 4.34, N = 3 560.7 633.2 1. (CC) gcc options: -static
OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size, No Sync/FSync Threadripper 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 6.09, N = 3 SE +/- 6.33, N = 3 2724.8 2012.9 1. (CC) gcc options: -static
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.org Seconds, Fewer Is Better GEGL Operation: Crop Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.062, N = 3 SE +/- 0.043, N = 3 8.003 7.491
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Scale Threadripper 3970X 16 Cores 1.2737 2.5474 3.8211 5.0948 6.3685 SE +/- 0.040, N = 3 SE +/- 0.031, N = 3 5.661 4.940
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Cartoon Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 90.95 88.68
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Reflect Threadripper 3970X 16 Cores 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 29.98 29.41
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Antialias Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 39.00 36.36
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Tile Glass Threadripper 3970X 16 Cores 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 31.03 28.69
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Wavelet Blur Threadripper 3970X 16 Cores 14 28 42 56 70 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 62.40 60.11
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Color Enhance Threadripper 3970X 16 Cores 13 26 39 52 65 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 56.07 55.43
OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Rotate 90 Degrees Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 38.17 37.69
Git This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands Threadripper 3970X 16 Cores 1.1291 2.2582 3.3873 4.5164 5.6455 SE +/- 0.014, N = 3 SE +/- 0.006, N = 3 4.914 5.018 1. git version 2.20.1
glibc bench The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more.
Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: cos Threadripper 3970X 16 Cores 10 20 30 40 50 SE +/- 0.27, N = 3 SE +/- 0.02, N = 3 42.25 42.81
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: exp Threadripper 3970X 16 Cores 1.1235 2.247 3.3705 4.494 5.6175 SE +/- 0.01485, N = 3 SE +/- 0.00851, N = 3 4.99317 4.95189
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffs Threadripper 3970X 16 Cores 0.4022 0.8044 1.2066 1.6088 2.011 SE +/- 0.01753, N = 3 SE +/- 0.00045, N = 3 1.75870 1.78754
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: log2 Threadripper 3970X 16 Cores 1.327 2.654 3.981 5.308 6.635 SE +/- 0.00811, N = 3 SE +/- 0.01183, N = 3 5.88218 5.89799
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: modf Threadripper 3970X 16 Cores 0.5072 1.0144 1.5216 2.0288 2.536 SE +/- 0.00267, N = 3 SE +/- 0.00154, N = 3 2.23442 2.25415
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sqrt Threadripper 3970X 16 Cores 0.504 1.008 1.512 2.016 2.52 SE +/- 0.00274, N = 3 SE +/- 0.00107, N = 3 2.22027 2.23979
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffsll Threadripper 3970X 16 Cores 0.4001 0.8002 1.2003 1.6004 2.0005 SE +/- 0.01102, N = 3 SE +/- 0.00227, N = 3 1.75897 1.77800
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once Threadripper 3970X 16 Cores 0.3996 0.7992 1.1988 1.5984 1.998 SE +/- 0.00270, N = 3 SE +/- 0.00019, N = 3 1.76133 1.77594
OpenBenchmarking.org Seconds, Fewer Is Better GnuPG 1.4.22 2GB File Encryption Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 11.43 11.47 1. (CC) gcc options: -O2 -MT -MD -MP -MF
OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: json Threadripper 3970X 16 Cores 800K 1600K 2400K 3200K 4000K SE +/- 7331.16, N = 3 SE +/- 16615.41, N = 3 1564168 3523585
OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: build Threadripper 3970X 16 Cores 4000M 8000M 12000M 16000M 20000M SE +/- 170009930.60, N = 3 SE +/- 162720428.03, N = 3 20067677101 17244462905
OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: garbage Threadripper 3970X 16 Cores 200K 400K 600K 800K 1000K SE +/- 1243.04, N = 3 SE +/- 2753.72, N = 3 589712 897936
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 1.86, N = 3 1590 784 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate Threadripper 3970X 16 Cores 160 320 480 640 800 SE +/- 3.46, N = 3 SE +/- 1.53, N = 3 693 732 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen Threadripper 3970X 16 Cores 100 200 300 400 500 SE +/- 3.38, N = 3 SE +/- 0.33, N = 3 468 252 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced Threadripper 3970X 16 Cores 140 280 420 560 700 SE +/- 2.91, N = 3 669 357 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing Threadripper 3970X 16 Cores 500 1000 1500 2000 2500 SE +/- 8.01, N = 3 SE +/- 1.73, N = 3 2243 1847 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian Threadripper 3970X 16 Cores 140 280 420 560 700 SE +/- 2.00, N = 3 631 351 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 1.53, N = 3 SE +/- 1.33, N = 3 1499 1417 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing on the CPU with the water_GMX50 data. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020 Water Benchmark Threadripper 3970X 16 Cores 0.7398 1.4796 2.2194 2.9592 3.699 SE +/- 0.004, N = 3 SE +/- 0.002, N = 3 3.288 2.048 1. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
HPC Challenge HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-HPL Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.19, N = 3 73.20 89.99 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte Threadripper 3970X 16 Cores 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 16.12 11.17 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: EP-DGEMM Threadripper 3970X 16 Cores 11 22 33 44 55 SE +/- 0.44, N = 3 SE +/- 0.43, N = 3 29.80 49.58 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ptrans Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.01053, N = 3 SE +/- 0.00225, N = 3 7.44119 2.12629 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: EP-STREAM Triad Threadripper 3970X 16 Cores 0.7821 1.5642 2.3463 3.1284 3.9105 SE +/- 0.00672, N = 3 SE +/- 0.00112, N = 3 1.90348 3.47614 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GUP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Random Access Threadripper 3970X 16 Cores 0.0386 0.0772 0.1158 0.1544 0.193 SE +/- 0.00021, N = 3 SE +/- 0.00040, N = 3 0.17138 0.11362 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org usecs, Fewer Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Latency Threadripper 3970X 16 Cores 0.1057 0.2114 0.3171 0.4228 0.5285 SE +/- 0.00770, N = 3 SE +/- 0.00064, N = 3 0.46962 0.40788 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Bandwidth Threadripper 3970X 16 Cores 0.8948 1.7896 2.6844 3.5792 4.474 SE +/- 0.02486, N = 3 SE +/- 0.00338, N = 3 2.20814 3.97686 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org MB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Max Ping Pong Bandwidth Threadripper 3970X 16 Cores 5K 10K 15K 20K 25K SE +/- 271.12, N = 3 SE +/- 607.12, N = 3 21719.65 22271.54 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
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.
OpenBenchmarking.org Seconds, Fewer Is Better Inkscape Operation: SVG Files To PNG Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 26.27 25.26 1. Inkscape 0.92.4 (5da689c313, 2019-01-14)
Intel MPI Benchmarks Intel MPI Benchmarks for stressing MPI implementations. At this point the test profile aggregates results for some common MPI functionality. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Average Msg/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-P2P PingPong Threadripper 3970X 16 Cores 4M 8M 12M 16M 20M SE +/- 175648.50, N = 3 SE +/- 15568.26, N = 3 17789641.38 9362495.74 MIN: 4183 / MAX: 42591960 MIN: 3568 / MAX: 21761153 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org Average Mbytes/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Exchange Threadripper 3970X 16 Cores 1500 3000 4500 6000 7500 SE +/- 53.06, N = 3 SE +/- 11.57, N = 3 6258.07 7217.49 MAX: 25730.7 MAX: 27690.75 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org Average usec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Exchange Threadripper 3970X 16 Cores 30 60 90 120 150 SE +/- 3.02, N = 3 SE +/- 0.54, N = 3 149.28 104.95 MIN: 0.65 / MAX: 5739.97 MIN: 0.58 / MAX: 3114.62 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org Average Mbytes/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 PingPong Threadripper 3970X 16 Cores 1200 2400 3600 4800 6000 SE +/- 139.42, N = 15 SE +/- 201.66, N = 15 5106.63 5828.12 MIN: 5.04 / MAX: 18618.89 MIN: 5.29 / MAX: 21984.97 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org Average Mbytes/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Sendrecv Threadripper 3970X 16 Cores 1300 2600 3900 5200 6500 SE +/- 64.08, N = 3 SE +/- 114.95, N = 15 4955.00 6263.73 MAX: 30545.39 MAX: 41562.16 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org Average usec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Sendrecv Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.48, N = 3 SE +/- 0.45, N = 15 82.61 63.49 MIN: 0.38 / MAX: 2576.08 MIN: 0.19 / MAX: 1638.64 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Read Test Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 23.08, N = 3 SE +/- 10.56, N = 15 1047.58 1117.52 MIN: 520.5 / MAX: 1149.41 MIN: 229.66 / MAX: 1510.8 1. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 20.79, N = 3 SE +/- 4.10, N = 3 1594.31 1283.87 1. (CC) gcc options: -O3
OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 64Kb - File Size: 512MB - Disk Test: Write Performance Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 6.54, N = 3 SE +/- 3.66, N = 3 1677.55 1361.61 1. (CC) gcc options: -O3
OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 62.42, N = 12 SE +/- 4.09, N = 3 1529.57 1280.55 1. (CC) gcc options: -O3
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Pipe - Message Bytes: 128 Threadripper 3970X 16 Cores 800K 1600K 2400K 3200K 4000K SE +/- 36545.27, N = 8 SE +/- 43879.72, N = 6 3558893 3701949
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: FIFO Named Pipe - Message Bytes: 128 Threadripper 3970X 16 Cores 700K 1400K 2100K 2800K 3500K SE +/- 32378.59, N = 15 SE +/- 30085.47, N = 15 3388324 3353946
OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Unix Domain Socket - Message Bytes: 128 Threadripper 3970X 16 Cores 500K 1000K 1500K 2000K 2500K SE +/- 10877.55, N = 3 SE +/- 26516.90, N = 3 2416213 2555431
iPerf iPerf is a network bandwidth throughput testing software. This test profile is used for automated testing of an iperf client and requires you have access to an iperf server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 64 Threadripper 3970X 16 Cores 12K 24K 36K 48K 60K SE +/- 423.19, N = 3 SE +/- 1271.94, N = 12 54840 47216 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 64 Threadripper 3970X 16 Cores 15 30 45 60 75 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 67.1 67.1 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
Java SciMark This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Composite Threadripper 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 1.94, N = 4 SE +/- 7.84, N = 4 3009.12 3005.07
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Monte Carlo Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 2.62, N = 4 SE +/- 2.89, N = 4 1686.79 1679.21
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Fast Fourier Transform Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 9.49, N = 4 SE +/- 14.00, N = 4 2043.32 2040.93
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Sparse Matrix Multiply Threadripper 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 4.74, N = 4 SE +/- 8.43, N = 4 2683.18 2716.60
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Dense LU Matrix Factorization Threadripper 3970X 16 Cores 1400 2800 4200 5600 7000 SE +/- 2.88, N = 4 SE +/- 22.75, N = 4 6674.41 6637.13
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 2.45, N = 4 SE +/- 1.78, N = 4 1957.92 1951.48
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 Threadripper 3970X 16 Cores 500K 1000K 1500K 2000K 2500K SE +/- 33415.00, N = 4 SE +/- 3055.05, N = 3 2520750 1626000 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
LAME MP3 Encoding LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.020, N = 3 SE +/- 0.007, N = 3 7.188 7.182 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm