HEDT CPUs July 2020 AMD Ryzen Threadripper 3960X 24-Core testing with a MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) and Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2007244-PTS-2007231N08 .
HEDT CPUs July 2020 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Core i9 10980XE Threadripper 3960X Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads) ASRock X299 Steel Legend (P1.30 BIOS) Intel Sky Lake-E DMI3 Registers 32GB Samsung SSD 970 PRO 512GB NVIDIA NV132 11GB Realtek ALC1220 ASUS MG28U Intel I219-V + Intel I211 Pop 20.04 5.4.0-7634-generic (x86_64) GNOME Shell 3.36.3 X Server 1.20.8 modesetting 1.20.8 4.3 Mesa 20.0.8 GCC 9.3.0 ext4 3840x2160 AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads) MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) AMD Starship/Matisse 1000GB Sabrent Rocket 4.0 1TB Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz) AMD Navi 10 HDMI Audio Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.4.0-39-generic (x86_64) GNOME Shell 3.36.1 4.6 Mesa 20.0.4 (LLVM 9.0.1) OpenBenchmarking.org Compiler Details - Core i9 10980XE: --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-arch=skylake --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 - Threadripper 3960X: --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 - Core i9 10980XE: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5002f01 - Threadripper 3960X: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025 Python Details - Core i9 10980XE: Python 2.7.18rc1 + Python 3.8.2 - Threadripper 3960X: Python 3.8.2 Security Details - Core i9 10980XE: 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: Mitigation of TSX disabled - Threadripper 3960X: 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
HEDT CPUs July 2020 wireguard: lczero: BLAS rodinia: OpenMP LavaMD rodinia: OpenMP HotSpot3D rodinia: OpenMP Leukocyte rodinia: OpenMP CFD Solver rodinia: OpenMP Streamcluster lzbench: XZ 0 - Compression lzbench: XZ 0 - Decompression lzbench: Zstd 1 - Compression lzbench: Zstd 1 - Decompression lzbench: Zstd 8 - Compression lzbench: Zstd 8 - Decompression lzbench: Crush 0 - Compression lzbench: Crush 0 - Decompression lzbench: Brotli 0 - Compression lzbench: Brotli 0 - Decompression lzbench: Brotli 2 - Compression lzbench: Brotli 2 - Decompression lzbench: Libdeflate 1 - Compression lzbench: Libdeflate 1 - Decompression crafty: Elapsed Time tscp: AI Chess Performance onednn: IP Batch 1D - f32 - CPU onednn: IP Batch All - f32 - CPU onednn: IP Batch 1D - u8s8f32 - CPU onednn: IP Batch All - u8s8f32 - CPU onednn: IP Batch 1D - bf16bf16bf16 - CPU onednn: IP Batch All - bf16bf16bf16 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Deconvolution Batch deconv_1d - f32 - CPU onednn: Deconvolution Batch deconv_3d - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Deconvolution Batch deconv_1d - u8s8f32 - CPU onednn: Deconvolution Batch deconv_3d - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU onednn: Deconvolution Batch deconv_1d - bf16bf16bf16 - CPU onednn: Deconvolution Batch deconv_3d - bf16bf16bf16 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU aom-av1: Speed 0 Two-Pass aom-av1: Speed 4 Two-Pass aom-av1: Speed 6 Realtime aom-av1: Speed 6 Two-Pass aom-av1: Speed 8 Realtime compress-7zip: Compress Speed Test stockfish: Total Time asmfish: 1024 Hash Memory, 26 Depth avifenc: 0 avifenc: 2 avifenc: 8 avifenc: 10 build-apache: Time To Compile build-linux-kernel: Time To Compile compress-pbzip2: 256MB File Compression opm: Flow MPI Norne - 1 opm: Flow MPI Norne - 2 opm: Flow MPI Norne - 4 opm: Flow MPI Norne - 8 opm: Flow MPI Norne - 16 opm: Flow MPI Norne - 18 compress-gzip: Linux Source Tree Archiving To .tar.gz compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 encode-flac: WAV To FLAC encode-mp3: WAV To MP3 m-queens: Time To Solve montage: Mosaic of M17, K band, 1.5 deg x 1.5 deg n-queens: Elapsed Time system-decompress-xz: daphne: OpenMP - NDT Mapping daphne: OpenMP - Points2Image daphne: OpenMP - Euclidean Cluster gmic: 2D Function Plotting, 1000 Times gmic: Plotting Isosurface Of A 3D Volume, 1000 Times gmic: 3D Elevated Function In Rand Colors, 100 Times hugin: Panorama Photo Assistant + Stitching Time ocrmypdf: Processing 60 Page PDF Document neatbench: CPU ai-benchmark: Device Inference Score ai-benchmark: Device Training Score ai-benchmark: Device AI Score tesseract-ocr: Time To OCR 7 Images brl-cad: VGR Performance Metric Core i9 10980XE Threadripper 3960X 243.290 1068 114.470 97.927 64.340 11.151 14.551 45 129 545 1489 95 1465 116 532 539 707 217 817 231 1295 9226476 1410806 2.19855 32.0930 0.514084 7.19860 5.53233 63.4831 9.85692 1.71524 2.60917 9.39221 0.458728 0.680155 171.445 56.8407 7.85544 9.20655 10.8124 1.42876 0.367699 1.70524 0.3 2.28 18.31 3.61 33.96 98104 49652366 54209155 67.200 40.222 4.899 4.745 23.270 48.634 2.234 406.912 236.575 171.095 204.705 322.177 359.104 32.181 19.293 9.029 8.805 47.734 71.569 8.641 3.350 893.54 21187.617818901 1342.83 145.643 18.070 60.178 46.156 19.280 25.8 1936 1547 3483 23.469 212219 229.218 1099 83.300 83.109 48.360 9.160 19.098 43 131 549 1505 109 1660 121 510 541 643 218 762 264 1251 8925339 1329102 1.35796 28.2454 1.18306 11.9961 9.03180 1.66015 2.55717 9.13818 4.71396 1.96091 189.102 52.1539 0.448066 0.998713 0.34 2.68 19.13 4.13 38.70 152349 75555027 74150577 54.921 32.835 4.685 4.523 20.551 33.911 302.591 192.630 152.857 192.577 316.595 353.256 33.791 19.919 7.688 7.123 22.971 72.247 4.524 3.379 989.85 23446.268852101 1232.43 154.862 18.705 81.432 42.605 16.128 35.6 2054 1493 3547 24.111 407079 OpenBenchmarking.org
WireGuard + Linux Networking Stack Stress Test OpenBenchmarking.org Seconds, Fewer Is Better WireGuard + Linux Networking Stack Stress Test Core i9 10980XE Threadripper 3960X 50 100 150 200 250 SE +/- 0.47, N = 3 SE +/- 1.09, N = 3 243.29 229.22
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.25 Backend: BLAS Core i9 10980XE Threadripper 3960X 200 400 600 800 1000 SE +/- 4.81, N = 3 SE +/- 16.02, N = 4 1068 1099 1. (CXX) g++ options: -pthread
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD Core i9 10980XE Threadripper 3960X 30 60 90 120 150 SE +/- 0.59, N = 3 SE +/- 0.11, N = 3 114.47 83.30 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP HotSpot3D OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP HotSpot3D Core i9 10980XE Threadripper 3960X 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.43, N = 3 97.93 83.11 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Leukocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte Core i9 10980XE Threadripper 3960X 14 28 42 56 70 SE +/- 0.54, N = 3 SE +/- 0.07, N = 3 64.34 48.36 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver Core i9 10980XE Threadripper 3960X 3 6 9 12 15 SE +/- 0.050, N = 3 SE +/- 0.071, N = 3 11.151 9.160 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster Core i9 10980XE Threadripper 3960X 5 10 15 20 25 SE +/- 0.13, N = 15 SE +/- 0.02, N = 3 14.55 19.10 1. (CXX) g++ options: -O2 -lOpenCL
lzbench Test: XZ 0 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: XZ 0 - Process: Compression Core i9 10980XE Threadripper 3960X 10 20 30 40 50 45 43 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: XZ 0 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: XZ 0 - Process: Decompression Core i9 10980XE Threadripper 3960X 30 60 90 120 150 SE +/- 0.33, N = 3 129 131 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Zstd 1 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 1 - Process: Compression Core i9 10980XE Threadripper 3960X 120 240 360 480 600 SE +/- 0.58, N = 3 545 549 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Zstd 1 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 1 - Process: Decompression Core i9 10980XE Threadripper 3960X 300 600 900 1200 1500 1489 1505 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Zstd 8 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 8 - Process: Compression Core i9 10980XE Threadripper 3960X 20 40 60 80 100 SE +/- 0.67, N = 3 95 109 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Zstd 8 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 8 - Process: Decompression Core i9 10980XE Threadripper 3960X 400 800 1200 1600 2000 SE +/- 1.33, N = 3 1465 1660 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Crush 0 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Crush 0 - Process: Compression Core i9 10980XE Threadripper 3960X 30 60 90 120 150 116 121 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Crush 0 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Crush 0 - Process: Decompression Core i9 10980XE Threadripper 3960X 120 240 360 480 600 532 510 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Brotli 0 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 0 - Process: Compression Core i9 10980XE Threadripper 3960X 120 240 360 480 600 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 539 541 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Brotli 0 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 0 - Process: Decompression Core i9 10980XE Threadripper 3960X 150 300 450 600 750 SE +/- 0.58, N = 3 707 643 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Brotli 2 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 2 - Process: Compression Core i9 10980XE Threadripper 3960X 50 100 150 200 250 SE +/- 0.33, N = 3 217 218 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Brotli 2 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 2 - Process: Decompression Core i9 10980XE Threadripper 3960X 200 400 600 800 1000 SE +/- 1.53, N = 3 817 762 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Libdeflate 1 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Libdeflate 1 - Process: Compression Core i9 10980XE Threadripper 3960X 60 120 180 240 300 231 264 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Libdeflate 1 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Libdeflate 1 - Process: Decompression Core i9 10980XE Threadripper 3960X 300 600 900 1200 1500 SE +/- 0.58, N = 3 SE +/- 2.40, N = 3 1295 1251 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
Crafty Elapsed Time OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time Core i9 10980XE Threadripper 3960X 2M 4M 6M 8M 10M SE +/- 22362.22, N = 3 SE +/- 14360.71, N = 3 9226476 8925339 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance Core i9 10980XE Threadripper 3960X 300K 600K 900K 1200K 1500K SE +/- 884.76, N = 5 SE +/- 1285.03, N = 5 1410806 1329102 1. (CC) gcc options: -O3 -march=native
oneDNN Harness: IP Batch 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: IP Batch 1D - Data Type: f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 0.4947 0.9894 1.4841 1.9788 2.4735 SE +/- 0.01914, N = 3 SE +/- 0.00461, N = 3 2.19855 1.35796 MIN: 2.08 MIN: 1.3 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: IP Batch All - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: IP Batch All - Data Type: f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 7 14 21 28 35 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 32.09 28.25 MIN: 30.59 MIN: 27.9 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 0.2662 0.5324 0.7986 1.0648 1.331 SE +/- 0.002493, N = 3 SE +/- 0.017087, N = 14 0.514084 1.183060 MIN: 0.49 MIN: 1.13 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 3 6 9 12 15 SE +/- 0.05636, N = 3 SE +/- 0.01572, N = 3 7.19860 11.99610 MIN: 6.86 MIN: 11.63 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: IP Batch 1D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: IP Batch 1D - Data Type: bf16bf16bf16 - Engine: CPU Core i9 10980XE 1.2448 2.4896 3.7344 4.9792 6.224 SE +/- 0.00112, N = 3 5.53233 MIN: 5.46 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: IP Batch All - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: IP Batch All - Data Type: bf16bf16bf16 - Engine: CPU Core i9 10980XE 14 28 42 56 70 SE +/- 0.03, N = 3 63.48 MIN: 62.83 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 3 6 9 12 15 SE +/- 0.04742, N = 3 SE +/- 0.03566, N = 3 9.85692 9.03180 MIN: 9.71 MIN: 8.88 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 0.3859 0.7718 1.1577 1.5436 1.9295 SE +/- 0.00156, N = 3 SE +/- 0.00518, N = 3 1.71524 1.66015 MIN: 1.68 MIN: 1.61 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 0.5871 1.1742 1.7613 2.3484 2.9355 SE +/- 0.00436, N = 3 SE +/- 0.01528, N = 3 2.60917 2.55717 MIN: 2.58 MIN: 2.5 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 3 6 9 12 15 SE +/- 0.05740, N = 3 SE +/- 0.05351, N = 3 9.39221 9.13818 MIN: 9.23 MIN: 8.95 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 1.0606 2.1212 3.1818 4.2424 5.303 SE +/- 0.000428, N = 3 SE +/- 0.005508, N = 3 0.458728 4.713960 MIN: 4.61 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 0.4412 0.8824 1.3236 1.7648 2.206 SE +/- 0.003916, N = 3 SE +/- 0.001505, N = 3 0.680155 1.960910 MIN: 0.66 MIN: 1.88 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 40 80 120 160 200 SE +/- 1.11, N = 3 SE +/- 1.01, N = 3 171.45 189.10 MIN: 167.84 MIN: 185.19 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 13 26 39 52 65 SE +/- 1.15, N = 15 SE +/- 0.11, N = 3 56.84 52.15 MIN: 50.94 MIN: 51.37 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU Core i9 10980XE 2 4 6 8 10 SE +/- 0.00830, N = 3 7.85544 MIN: 7.65 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16 - Engine: CPU Core i9 10980XE 3 6 9 12 15 SE +/- 0.00358, N = 3 9.20655 MIN: 9.02 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16 - Engine: CPU Core i9 10980XE 3 6 9 12 15 SE +/- 0.00, N = 3 10.81 MIN: 10.68 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 0.3215 0.643 0.9645 1.286 1.6075 SE +/- 0.008911, N = 3 SE +/- 0.002149, N = 3 1.428760 0.448066 MIN: 1.38 MIN: 0.43 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU Core i9 10980XE Threadripper 3960X 0.2247 0.4494 0.6741 0.8988 1.1235 SE +/- 0.004630, N = 3 SE +/- 0.000520, N = 3 0.367699 0.998713 MIN: 0.34 MIN: 0.97 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 1.5 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU Core i9 10980XE 0.3837 0.7674 1.1511 1.5348 1.9185 SE +/- 0.00114, N = 3 1.70524 MIN: 1.61 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
AOM AV1 Encoder Mode: Speed 0 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 0 Two-Pass Core i9 10980XE Threadripper 3960X 0.0765 0.153 0.2295 0.306 0.3825 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.30 0.34 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 4 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 4 Two-Pass Core i9 10980XE Threadripper 3960X 0.603 1.206 1.809 2.412 3.015 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.28 2.68 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 6 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Realtime Core i9 10980XE Threadripper 3960X 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 18.31 19.13 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 6 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Two-Pass Core i9 10980XE Threadripper 3960X 0.9293 1.8586 2.7879 3.7172 4.6465 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 3.61 4.13 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 8 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 8 Realtime Core i9 10980XE Threadripper 3960X 9 18 27 36 45 SE +/- 0.15, N = 3 SE +/- 0.13, N = 3 33.96 38.70 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test Core i9 10980XE Threadripper 3960X 30K 60K 90K 120K 150K SE +/- 468.74, N = 3 SE +/- 170.94, N = 3 98104 152349 1. (CXX) g++ options: -pipe -lpthread
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time Core i9 10980XE Threadripper 3960X 16M 32M 48M 64M 80M SE +/- 113161.61, N = 3 SE +/- 456523.74, N = 3 49652366 75555027 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth Core i9 10980XE Threadripper 3960X 16M 32M 48M 64M 80M SE +/- 693981.08, N = 3 SE +/- 352685.57, N = 3 54209155 74150577
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 0 Core i9 10980XE Threadripper 3960X 15 30 45 60 75 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 67.20 54.92 1. (CXX) g++ options: -O3 -fPIC
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 2 Core i9 10980XE Threadripper 3960X 9 18 27 36 45 SE +/- 0.20, N = 3 SE +/- 0.07, N = 3 40.22 32.84 1. (CXX) g++ options: -O3 -fPIC
libavif avifenc Encoder Speed: 8 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 8 Core i9 10980XE Threadripper 3960X 1.1023 2.2046 3.3069 4.4092 5.5115 SE +/- 0.024, N = 3 SE +/- 0.017, N = 3 4.899 4.685 1. (CXX) g++ options: -O3 -fPIC
libavif avifenc Encoder Speed: 10 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 10 Core i9 10980XE Threadripper 3960X 1.0676 2.1352 3.2028 4.2704 5.338 SE +/- 0.007, N = 3 SE +/- 0.008, N = 3 4.745 4.523 1. (CXX) g++ options: -O3 -fPIC
Timed Apache Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.41 Time To Compile Core i9 10980XE Threadripper 3960X 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 23.27 20.55
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile Core i9 10980XE Threadripper 3960X 11 22 33 44 55 SE +/- 0.70, N = 4 SE +/- 0.58, N = 3 48.63 33.91
Parallel BZIP2 Compression 256MB File Compression OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.12 256MB File Compression Core i9 10980XE 0.5027 1.0054 1.5081 2.0108 2.5135 SE +/- 0.006, N = 3 2.234 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
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 Core i9 10980XE Threadripper 3960X 90 180 270 360 450 SE +/- 0.19, N = 3 SE +/- 1.52, N = 3 406.91 302.59 1. flow 2020.04
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 Core i9 10980XE Threadripper 3960X 50 100 150 200 250 SE +/- 0.07, N = 3 SE +/- 0.17, N = 3 236.58 192.63 1. flow 2020.04
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 Core i9 10980XE Threadripper 3960X 40 80 120 160 200 SE +/- 0.12, N = 3 SE +/- 0.37, N = 3 171.10 152.86 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 Core i9 10980XE Threadripper 3960X 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.29, N = 3 204.71 192.58 1. flow 2020.04
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 Core i9 10980XE Threadripper 3960X 70 140 210 280 350 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 322.18 316.60 1. flow 2020.04
Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 18 OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media OPM Benchmark: Flow MPI Norne - Threads: 18 Core i9 10980XE Threadripper 3960X 80 160 240 320 400 SE +/- 0.11, N = 3 SE +/- 0.19, N = 3 359.10 353.26 1. flow 2020.04
Gzip Compression Linux Source Tree Archiving To .tar.gz OpenBenchmarking.org Seconds, Fewer Is Better Gzip Compression Linux Source Tree Archiving To .tar.gz Core i9 10980XE Threadripper 3960X 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 32.18 33.79
XZ Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 OpenBenchmarking.org Seconds, Fewer Is Better XZ Compression 5.2.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 Core i9 10980XE Threadripper 3960X 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 19.29 19.92 1. (CC) gcc options: -pthread -fvisibility=hidden -O2
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC Core i9 10980XE Threadripper 3960X 3 6 9 12 15 SE +/- 0.007, N = 5 SE +/- 0.019, N = 5 9.029 7.688 -logg 1. (CXX) g++ options: -O2 -fvisibility=hidden -lm
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 Core i9 10980XE Threadripper 3960X 2 4 6 8 10 SE +/- 0.028, N = 3 SE +/- 0.015, N = 3 8.805 7.123 -lncurses 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve Core i9 10980XE Threadripper 3960X 11 22 33 44 55 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 47.73 22.97 1. (CXX) g++ options: -fopenmp -O2 -march=native
Montage Astronomical Image Mosaic Engine Mosaic of M17, K band, 1.5 deg x 1.5 deg OpenBenchmarking.org Seconds, Fewer Is Better Montage Astronomical Image Mosaic Engine 6.0 Mosaic of M17, K band, 1.5 deg x 1.5 deg Core i9 10980XE Threadripper 3960X 16 32 48 64 80 SE +/- 0.03, N = 3 SE +/- 0.37, N = 3 71.57 72.25 1. (CC) gcc options: -std=gnu99 -lcfitsio -lm -O2
N-Queens Elapsed Time OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time Core i9 10980XE Threadripper 3960X 2 4 6 8 10 SE +/- 0.002, N = 3 SE +/- 0.007, N = 3 8.641 4.524 1. (CC) gcc options: -static -fopenmp -O3 -march=native
System XZ Decompression OpenBenchmarking.org Seconds, Fewer Is Better System XZ Decompression Core i9 10980XE Threadripper 3960X 0.7603 1.5206 2.2809 3.0412 3.8015 SE +/- 0.004, N = 3 SE +/- 0.013, N = 3 3.350 3.379
Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: NDT Mapping OpenBenchmarking.org Test Cases Per Minute, More Is Better Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: NDT Mapping Core i9 10980XE Threadripper 3960X 200 400 600 800 1000 SE +/- 2.69, N = 3 SE +/- 1.98, N = 3 893.54 989.85 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Points2Image OpenBenchmarking.org Test Cases Per Minute, More Is Better Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Points2Image Core i9 10980XE Threadripper 3960X 5K 10K 15K 20K 25K SE +/- 169.25, N = 14 SE +/- 263.10, N = 15 21187.62 23446.27 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Euclidean Cluster OpenBenchmarking.org Test Cases Per Minute, More Is Better Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Euclidean Cluster Core i9 10980XE Threadripper 3960X 300 600 900 1200 1500 SE +/- 2.51, N = 3 SE +/- 1.06, N = 3 1342.83 1232.43 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
G'MIC Test: 2D Function Plotting, 1000 Times OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: 2D Function Plotting, 1000 Times Core i9 10980XE Threadripper 3960X 30 60 90 120 150 SE +/- 1.16, N = 3 SE +/- 0.15, N = 3 145.64 154.86 1. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
G'MIC Test: Plotting Isosurface Of A 3D Volume, 1000 Times OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: Plotting Isosurface Of A 3D Volume, 1000 Times Core i9 10980XE Threadripper 3960X 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 18.07 18.71 1. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
G'MIC Test: 3D Elevated Function In Random Colors, 100 Times OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: 3D Elevated Function In Random Colors, 100 Times Core i9 10980XE Threadripper 3960X 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.16, N = 3 60.18 81.43 1. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
Hugin Panorama Photo Assistant + Stitching Time OpenBenchmarking.org Seconds, Fewer Is Better Hugin Panorama Photo Assistant + Stitching Time Core i9 10980XE Threadripper 3960X 10 20 30 40 50 SE +/- 0.54, N = 3 SE +/- 0.38, N = 3 46.16 42.61
OCRMyPDF Processing 60 Page PDF Document OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 9.6.0+dfsg Processing 60 Page PDF Document Core i9 10980XE Threadripper 3960X 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.11, N = 3 19.28 16.13
NeatBench Acceleration: CPU OpenBenchmarking.org FPS, More Is Better NeatBench 5 Acceleration: CPU Core i9 10980XE Threadripper 3960X 8 16 24 32 40 SE +/- 0.38, N = 3 SE +/- 0.18, N = 3 25.8 35.6
AI Benchmark Alpha Device Inference Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Inference Score Core i9 10980XE Threadripper 3960X 400 800 1200 1600 2000 1936 2054
AI Benchmark Alpha Device Training Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Training Score Core i9 10980XE Threadripper 3960X 300 600 900 1200 1500 1547 1493
AI Benchmark Alpha Device AI Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device AI Score Core i9 10980XE Threadripper 3960X 800 1600 2400 3200 4000 3483 3547
Tesseract OCR Time To OCR 7 Images OpenBenchmarking.org Seconds, Fewer Is Better Tesseract OCR 4.1.1 Time To OCR 7 Images Core i9 10980XE Threadripper 3960X 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 23.47 24.11
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.30.8 VGR Performance Metric Core i9 10980XE Threadripper 3960X 90K 180K 270K 360K 450K 212219 407079 -lSM -lICE -lXi -lGLU -lXext -lXrender 1. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lGL -lGLdispatch -lX11 -lpthread -ldl -luuid -lm
Phoronix Test Suite v10.8.4