TR 3970X Pre OB Launch AMD Ryzen Threadripper 3970X 32-Core testing with a ASUS ROG ZENITH II EXTREME (0702 BIOS) and NVIDIA TITAN RTX 24GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2008192-PTS-TR3970XP52&grs&sor .
TR 3970X Pre OB Launch Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution Verification 1 Verification 2 Verification 3 AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads) ASUS ROG ZENITH II EXTREME (0702 BIOS) AMD Starship/Matisse 64GB 1000GB Corsair Force MP600 NVIDIA TITAN RTX 24GB (1350/7000MHz) NVIDIA TU102 HD Audio ASUS MG28U Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.4.0-42-generic (x86_64) GNOME Shell 3.36.2 X Server 1.20.8 NVIDIA 450.36.06 4.6.0 OpenCL 1.2 CUDA 11.0.185 GCC 9.3.0 + CUDA 11.0 ext4 3840x2160 GNOME Shell 3.36.4 OpenBenchmarking.org Compiler 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,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 - CPU Microcode: 0x8301025 OpenCL Details - GPU Compute Cores: 4608 Python Details - Python 3.8.2 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
TR 3970X Pre OB Launch ecp-candle: P1B2 opm: Flow MPI Norne - 4 octave-benchmark: opm: Flow MPI Norne - 2 opm: Flow MPI Norne - 8 compress-zstd: 3 crafty: Elapsed Time fhourstones: Complex Connect-4 Solving astcenc: Exhaustive astcenc: Thorough hugin: Panorama Photo Assistant + Stitching Time ocrmypdf: Processing 60 Page PDF Document ecp-candle: P3B1 opm: Flow MPI Norne - 1 sockperf: Throughput compress-zstd: 19 ai-benchmark: Device Training Score smallpt: Global Illumination Renderer; 128 Samples opm: Flow MPI Norne - 16 c-ray: Total Time - 4K, 16 Rays Per Pixel ecp-candle: P3B2 opm: Flow MPI Norne - 32 tscp: AI Chess Performance ai-benchmark: Device AI Score astcenc: Fast tesseract-ocr: Time To OCR 7 Images ai-benchmark: Device Inference Score astcenc: Medium neatbench: CPU sockperf: Latency Under Load sockperf: Latency Ping Pong Verification 1 Verification 2 Verification 3 32.829 149.900 6.315 178.811 190.224 8553.5 8746208 15186.5 56.38 7.41 42.502 15.092 563.241 293.135 503276 102.8 1625 2.798 312.326 16.345 732.832 601.891 1325270 3983 4.59 24.131 2358 5.51 40.7 14.597 2.939 31.077 148.645 6.436 182.265 187.416 8378.0 8864816 14999.4 55.69 7.32 42.931 14.969 567.349 293.744 506476 103.1 2.800 311.899 16.325 731.985 601.506 1326537 4.58 5.51 40.9 14.885 2.900 32.901 154.464 6.231 184.028 191.445 8486.4 8848712 15048.2 55.77 7.34 42.817 14.955 565.7 295.114 506177 103.4 1634 2.785 310.941 16.279 730.332 599.922 1323353 3992 4.59 24.100 2358 5.51 40.7 13.423 2.983 OpenBenchmarking.org
ECP-CANDLE Benchmark: P1B2 OpenBenchmarking.org Seconds, Fewer Is Better ECP-CANDLE 0.3 Benchmark: P1B2 Verification 2 Verification 1 Verification 3 8 16 24 32 40 31.08 32.83 32.90
Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 4 OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 4 Verification 2 Verification 1 Verification 3 30 60 90 120 150 SE +/- 0.34, N = 3 SE +/- 0.48, N = 3 SE +/- 0.49, N = 3 148.65 149.90 154.46 1. flow 2020.04
GNU Octave Benchmark OpenBenchmarking.org Seconds, Fewer Is Better GNU Octave Benchmark 5.2.0 Verification 3 Verification 1 Verification 2 2 4 6 8 10 SE +/- 0.020, N = 5 SE +/- 0.048, N = 5 SE +/- 0.057, N = 5 6.231 6.315 6.436
Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 2 OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 2 Verification 1 Verification 2 Verification 3 40 80 120 160 200 SE +/- 1.10, N = 3 SE +/- 0.54, N = 3 SE +/- 0.77, N = 3 178.81 182.27 184.03 1. flow 2020.04
Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 8 OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 8 Verification 2 Verification 1 Verification 3 40 80 120 160 200 SE +/- 0.40, N = 3 SE +/- 0.51, N = 3 SE +/- 2.28, N = 3 187.42 190.22 191.45 1. flow 2020.04
Zstd Compression Compression Level: 3 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 3 Verification 1 Verification 3 Verification 2 2K 4K 6K 8K 10K SE +/- 27.83, N = 3 SE +/- 15.58, N = 3 SE +/- 35.77, N = 3 8553.5 8486.4 8378.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Crafty Elapsed Time OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time Verification 2 Verification 3 Verification 1 2M 4M 6M 8M 10M SE +/- 6041.30, N = 3 SE +/- 32987.01, N = 3 SE +/- 3079.59, N = 3 8864816 8848712 8746208 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
Fhourstones Complex Connect-4 Solving OpenBenchmarking.org Kpos / sec, More Is Better Fhourstones 3.1 Complex Connect-4 Solving Verification 1 Verification 3 Verification 2 3K 6K 9K 12K 15K SE +/- 39.77, N = 3 SE +/- 26.11, N = 3 SE +/- 26.74, N = 3 15186.5 15048.2 14999.4 1. (CC) gcc options: -O3
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Exhaustive Verification 2 Verification 3 Verification 1 13 26 39 52 65 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 55.69 55.77 56.38 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Thorough Verification 2 Verification 3 Verification 1 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 7.32 7.34 7.41 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Hugin Panorama Photo Assistant + Stitching Time OpenBenchmarking.org Seconds, Fewer Is Better Hugin Panorama Photo Assistant + Stitching Time Verification 1 Verification 3 Verification 2 10 20 30 40 50 SE +/- 0.30, N = 3 SE +/- 0.22, N = 3 SE +/- 0.37, N = 3 42.50 42.82 42.93
OCRMyPDF Processing 60 Page PDF Document OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 9.6.0+dfsg Processing 60 Page PDF Document Verification 3 Verification 2 Verification 1 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 14.96 14.97 15.09
ECP-CANDLE Benchmark: P3B1 OpenBenchmarking.org Seconds, Fewer Is Better ECP-CANDLE 0.3 Benchmark: P3B1 Verification 1 Verification 3 Verification 2 120 240 360 480 600 563.24 565.70 567.35
Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 1 OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 1 Verification 1 Verification 2 Verification 3 60 120 180 240 300 SE +/- 1.30, N = 3 SE +/- 0.36, N = 3 SE +/- 1.99, N = 3 293.14 293.74 295.11 1. flow 2020.04
Sockperf Test: Throughput OpenBenchmarking.org Messages Per Second, More Is Better Sockperf 3.4 Test: Throughput Verification 2 Verification 3 Verification 1 110K 220K 330K 440K 550K SE +/- 4016.61, N = 5 SE +/- 1928.14, N = 5 SE +/- 2299.22, N = 5 506476 506177 503276 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
Zstd Compression Compression Level: 19 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 19 Verification 3 Verification 2 Verification 1 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 103.4 103.1 102.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
AI Benchmark Alpha Device Training Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Training Score Verification 3 Verification 1 400 800 1200 1600 2000 1634 1625
Smallpt Global Illumination Renderer; 128 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 128 Samples Verification 3 Verification 1 Verification 2 0.63 1.26 1.89 2.52 3.15 SE +/- 0.003, N = 3 SE +/- 0.009, N = 3 SE +/- 0.002, N = 3 2.785 2.798 2.800 1. (CXX) g++ options: -fopenmp -O3
Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 16 OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 16 Verification 3 Verification 2 Verification 1 70 140 210 280 350 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.44, N = 3 310.94 311.90 312.33 1. flow 2020.04
C-Ray Total Time - 4K, 16 Rays Per Pixel OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Verification 3 Verification 2 Verification 1 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 16.28 16.33 16.35 1. (CC) gcc options: -lm -lpthread -O3
ECP-CANDLE Benchmark: P3B2 OpenBenchmarking.org Seconds, Fewer Is Better ECP-CANDLE 0.3 Benchmark: P3B2 Verification 3 Verification 2 Verification 1 160 320 480 640 800 730.33 731.99 732.83
Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 32 OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 32 Verification 3 Verification 2 Verification 1 130 260 390 520 650 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.26, N = 3 599.92 601.51 601.89 1. flow 2020.04
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance Verification 2 Verification 1 Verification 3 300K 600K 900K 1200K 1500K SE +/- 638.00, N = 5 SE +/- 1905.00, N = 5 SE +/- 1190.38, N = 5 1326537 1325270 1323353 1. (CC) gcc options: -O3 -march=native
AI Benchmark Alpha Device AI Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device AI Score Verification 3 Verification 1 900 1800 2700 3600 4500 3992 3983
ASTC Encoder Preset: Fast OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Fast Verification 2 Verification 1 Verification 3 1.0328 2.0656 3.0984 4.1312 5.164 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 4.58 4.59 4.59 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Tesseract OCR Time To OCR 7 Images OpenBenchmarking.org Seconds, Fewer Is Better Tesseract OCR 4.1.1 Time To OCR 7 Images Verification 3 Verification 1 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 24.10 24.13
AI Benchmark Alpha Device Inference Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Inference Score Verification 3 Verification 1 500 1000 1500 2000 2500 2358 2358
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Medium Verification 1 Verification 2 Verification 3 1.2398 2.4796 3.7194 4.9592 6.199 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 5.51 5.51 5.51 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
NeatBench Acceleration: CPU OpenBenchmarking.org FPS, More Is Better NeatBench 5 Acceleration: CPU Verification 2 Verification 3 Verification 1 9 18 27 36 45 SE +/- 1.01, N = 16 SE +/- 0.95, N = 16 SE +/- 0.77, N = 16 40.9 40.7 40.7
Sockperf Test: Latency Under Load OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Under Load Verification 3 Verification 1 Verification 2 4 8 12 16 20 SE +/- 0.58, N = 25 SE +/- 0.19, N = 5 SE +/- 0.19, N = 5 13.42 14.60 14.89 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
Sockperf Test: Latency Ping Pong OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Ping Pong Verification 2 Verification 1 Verification 3 0.6712 1.3424 2.0136 2.6848 3.356 SE +/- 0.039, N = 25 SE +/- 0.035, N = 25 SE +/- 0.027, N = 25 2.900 2.939 2.983 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
Phoronix Test Suite v10.8.5