TR 3960X Root 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/2009195-FI-TR3960XRO59 .
TR 3960X Root Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Threadripper 3960X 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 4 x 8192 MB DDR4-3200MT/s 1000GB Sabrent Rocket 4.0 1TB Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz) AMD Navi 10 HDMI Audio ASUS MG28U Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.9.0-rc5-14sep-patch (x86_64) 20200914 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.6 Mesa 20.0.8 (LLVM 10.0.0) GCC 9.3.0 ext4 3840x2160 OpenBenchmarking.org - --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 - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025 - Python 3.8.2 - 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 3960X Root lczero: BLAS lczero: Eigen lczero: Rand rodinia: OpenMP LavaMD rodinia: OpenMP HotSpot3D rodinia: OpenMP Leukocyte rodinia: OpenMP CFD Solver rodinia: OpenMP Streamcluster namd: ATPase Simulation - 327,506 Atoms incompact3d: Cylinder mocassin: Dust 2D tau100.0 lammps: 20k Atoms lammps: Rhodopsin Protein compress-zstd: 3 compress-zstd: 19 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 montage: Mosaic of M17, K band, 1.5 deg x 1.5 deg system-decompress-gzip: perf-bench: Epoll Wait perf-bench: Futex Hash perf-bench: Memcpy 1MB perf-bench: Memset 1MB perf-bench: Sched Pipe perf-bench: Futex Lock-Pi perf-bench: Syscall Basic tensorflow-lite: SqueezeNet tensorflow-lite: Inception V4 tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Float tensorflow-lite: Mobilenet Quant tensorflow-lite: Inception ResNet V2 astcenc: Fast astcenc: Medium astcenc: Thorough astcenc: Exhaustive hugin: Panorama Photo Assistant + Stitching Time ocrmypdf: Processing 60 Page PDF Document gpaw: Carbon Nanotube mnn: SqueezeNetV1.0 mnn: resnet-v2-50 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 ncnn: CPU - squeezenet_int8 ncnn: CPU - mobilenet_v3 ncnn: CPU - squeezenet ncnn: CPU - mnasnet ncnn: CPU - blazeface ncnn: CPU - googlenet_int8 ncnn: CPU - vgg16_int8 ncnn: CPU - resnet18_int8 ncnn: CPU - alexnet ncnn: CPU - resnet50_int8 ncnn: CPU - mobilenetv2_yolov3 blender: BMW27 - CPU-Only blender: Classroom - CPU-Only blender: Fishy Cat - CPU-Only blender: Barbershop - CPU-Only blender: Pabellon Barcelona - CPU-Only ai-benchmark: Device Inference Score ai-benchmark: Device Training Score ai-benchmark: Device AI Score tesseract-ocr: Time To OCR 7 Images kripke: Threadripper 3960X 963 965 196524 83.315 83.437 49.194 9.186 19.313 0.76646 169.128962 186 17.463 16.126 7323.9 76.8 0.34 2.68 19.25 4.14 39.21 72.119 2.774 15699 4552915 13.667930 70.524571 334568 242 20561759 75576.3 1135717 85722.5 51158.4 52203.4 1017070 4.69 5.75 9.16 71.19 43.657 16.541 150.017 7.765 27.060 5.055 5.099 28.771 14.25 6.85 7.22 6.55 2.86 38.96 69.93 20.20 11.35 54.69 17.09 56.87 158.35 74.68 244.74 177.90 1999 1496 3495 24.266 53276823 OpenBenchmarking.org
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: BLAS Threadripper 3960X 200 400 600 800 1000 SE +/- 13.68, N = 4 963 1. (CXX) g++ options: -flto -pthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: Eigen Threadripper 3960X 200 400 600 800 1000 SE +/- 15.84, N = 3 965 1. (CXX) g++ options: -flto -pthread
LeelaChessZero Backend: Random OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: Random Threadripper 3960X 40K 80K 120K 160K 200K SE +/- 325.50, N = 3 196524 1. (CXX) g++ options: -flto -pthread
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD Threadripper 3960X 20 40 60 80 100 SE +/- 0.13, N = 3 83.32 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP HotSpot3D OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP HotSpot3D Threadripper 3960X 20 40 60 80 100 SE +/- 0.60, N = 3 83.44 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Leukocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte Threadripper 3960X 11 22 33 44 55 SE +/- 0.15, N = 3 49.19 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver Threadripper 3960X 3 6 9 12 15 SE +/- 0.039, N = 3 9.186 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster Threadripper 3960X 5 10 15 20 25 SE +/- 0.06, N = 3 19.31 1. (CXX) g++ options: -O2 -lOpenCL
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Threadripper 3960X 0.1725 0.345 0.5175 0.69 0.8625 SE +/- 0.00250, N = 3 0.76646
Incompact3D Input: Cylinder OpenBenchmarking.org Seconds, Fewer Is Better Incompact3D 2020-09-17 Input: Cylinder Threadripper 3960X 40 80 120 160 200 SE +/- 0.55, N = 3 169.13 1. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
Monte Carlo Simulations of Ionised Nebulae Input: Dust 2D tau100.0 OpenBenchmarking.org Seconds, Fewer Is Better Monte Carlo Simulations of Ionised Nebulae 2019-03-24 Input: Dust 2D tau100.0 Threadripper 3960X 40 80 120 160 200 186 1. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: 20k Atoms Threadripper 3960X 4 8 12 16 20 SE +/- 0.07, N = 3 17.46 1. (CXX) g++ options: -O3 -pthread -lm
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: Rhodopsin Protein Threadripper 3960X 4 8 12 16 20 SE +/- 0.22, N = 4 16.13 1. (CXX) g++ options: -O3 -pthread -lm
Zstd Compression Compression Level: 3 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 3 Threadripper 3960X 1600 3200 4800 6400 8000 SE +/- 7.23, N = 3 7323.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 19 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 19 Threadripper 3960X 20 40 60 80 100 SE +/- 0.06, N = 3 76.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
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 Threadripper 3960X 0.0765 0.153 0.2295 0.306 0.3825 SE +/- 0.00, N = 3 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 Threadripper 3960X 0.603 1.206 1.809 2.412 3.015 SE +/- 0.00, N = 3 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 Threadripper 3960X 5 10 15 20 25 SE +/- 0.02, N = 3 19.25 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 Threadripper 3960X 0.9315 1.863 2.7945 3.726 4.6575 SE +/- 0.01, N = 3 4.14 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 Threadripper 3960X 9 18 27 36 45 SE +/- 0.06, N = 3 39.21 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
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 Threadripper 3960X 16 32 48 64 80 SE +/- 0.21, N = 3 72.12 1. (CC) gcc options: -std=gnu99 -lcfitsio -lm -O2
System GZIP Decompression OpenBenchmarking.org Seconds, Fewer Is Better System GZIP Decompression Threadripper 3960X 0.6242 1.2484 1.8726 2.4968 3.121 SE +/- 0.003, N = 3 2.774
perf-bench Benchmark: Epoll Wait OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Epoll Wait Threadripper 3960X 3K 6K 9K 12K 15K SE +/- 80.48, N = 3 15699 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
perf-bench Benchmark: Futex Hash OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Hash Threadripper 3960X 1000K 2000K 3000K 4000K 5000K SE +/- 23134.06, N = 3 4552915 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
perf-bench Benchmark: Memcpy 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memcpy 1MB Threadripper 3960X 4 8 12 16 20 SE +/- 0.23, N = 3 13.67 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
perf-bench Benchmark: Memset 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memset 1MB Threadripper 3960X 16 32 48 64 80 SE +/- 0.61, N = 12 70.52 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
perf-bench Benchmark: Sched Pipe OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Sched Pipe Threadripper 3960X 70K 140K 210K 280K 350K SE +/- 4994.21, N = 3 334568 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
perf-bench Benchmark: Futex Lock-Pi OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Lock-Pi Threadripper 3960X 50 100 150 200 250 242 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
perf-bench Benchmark: Syscall Basic OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Syscall Basic Threadripper 3960X 4M 8M 12M 16M 20M SE +/- 149541.59, N = 3 20561759 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -llzma -lnuma
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Threadripper 3960X 16K 32K 48K 64K 80K SE +/- 268.52, N = 3 75576.3
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Threadripper 3960X 200K 400K 600K 800K 1000K SE +/- 1159.10, N = 3 1135717
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Threadripper 3960X 20K 40K 60K 80K 100K SE +/- 45.48, N = 3 85722.5
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Threadripper 3960X 11K 22K 33K 44K 55K SE +/- 144.82, N = 3 51158.4
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Threadripper 3960X 11K 22K 33K 44K 55K SE +/- 104.34, N = 3 52203.4
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Threadripper 3960X 200K 400K 600K 800K 1000K SE +/- 3065.07, N = 3 1017070
ASTC Encoder Preset: Fast OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Fast Threadripper 3960X 1.0553 2.1106 3.1659 4.2212 5.2765 SE +/- 0.00, N = 3 4.69 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Medium Threadripper 3960X 1.2938 2.5876 3.8814 5.1752 6.469 SE +/- 0.01, N = 3 5.75 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 Threadripper 3960X 3 6 9 12 15 SE +/- 0.01, N = 3 9.16 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Exhaustive Threadripper 3960X 16 32 48 64 80 SE +/- 0.18, N = 3 71.19 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 Threadripper 3960X 10 20 30 40 50 SE +/- 0.19, N = 3 43.66
OCRMyPDF Processing 60 Page PDF Document OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 9.6.0+dfsg Processing 60 Page PDF Document Threadripper 3960X 4 8 12 16 20 SE +/- 0.05, N = 3 16.54
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 20.1 Input: Carbon Nanotube Threadripper 3960X 30 60 90 120 150 SE +/- 0.07, N = 3 150.02 1. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 Threadripper 3960X 2 4 6 8 10 SE +/- 0.128, N = 3 7.765 MIN: 6.94 / MAX: 8.16 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 Threadripper 3960X 6 12 18 24 30 SE +/- 0.34, N = 3 27.06 MIN: 24.56 / MAX: 30.44 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 Threadripper 3960X 1.1374 2.2748 3.4122 4.5496 5.687 SE +/- 0.076, N = 3 5.055 MIN: 4.9 / MAX: 5.45 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 Threadripper 3960X 1.1473 2.2946 3.4419 4.5892 5.7365 SE +/- 0.426, N = 3 5.099 MIN: 4.52 / MAX: 6.1 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: inception-v3 Threadripper 3960X 7 14 21 28 35 SE +/- 0.43, N = 3 28.77 MIN: 27.09 / MAX: 30.84 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN Target: CPU - Model: squeezenet_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet_int8 Threadripper 3960X 4 8 12 16 20 SE +/- 0.03, N = 3 14.25 MIN: 14.04 / MAX: 16.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenet_v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenet_v3 Threadripper 3960X 2 4 6 8 10 SE +/- 0.06, N = 3 6.85 MIN: 6.6 / MAX: 20.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet Threadripper 3960X 2 4 6 8 10 SE +/- 0.03, N = 3 7.22 MIN: 6.95 / MAX: 7.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mnasnet Threadripper 3960X 2 4 6 8 10 SE +/- 0.05, N = 3 6.55 MIN: 6.2 / MAX: 7.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: blazeface Threadripper 3960X 0.6435 1.287 1.9305 2.574 3.2175 SE +/- 0.02, N = 3 2.86 MIN: 2.72 / MAX: 3.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: googlenet_int8 Threadripper 3960X 9 18 27 36 45 SE +/- 0.16, N = 3 38.96 MIN: 37.97 / MAX: 44.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: vgg16_int8 Threadripper 3960X 16 32 48 64 80 SE +/- 0.34, N = 3 69.93 MIN: 68.08 / MAX: 109.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet18_int8 Threadripper 3960X 5 10 15 20 25 SE +/- 0.48, N = 3 20.20 MIN: 19.49 / MAX: 21.62 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: alexnet Threadripper 3960X 3 6 9 12 15 SE +/- 0.05, N = 3 11.35 MIN: 11.21 / MAX: 12.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50_int8 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet50_int8 Threadripper 3960X 12 24 36 48 60 SE +/- 0.20, N = 3 54.69 MIN: 53.98 / MAX: 60.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenetv2_yolov3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenetv2_yolov3 Threadripper 3960X 4 8 12 16 20 SE +/- 0.10, N = 3 17.09 MIN: 16.76 / MAX: 17.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: BMW27 - Compute: CPU-Only Threadripper 3960X 13 26 39 52 65 SE +/- 0.07, N = 3 56.87
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Classroom - Compute: CPU-Only Threadripper 3960X 30 60 90 120 150 SE +/- 0.45, N = 3 158.35
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Fishy Cat - Compute: CPU-Only Threadripper 3960X 20 40 60 80 100 SE +/- 0.11, N = 3 74.68
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Barbershop - Compute: CPU-Only Threadripper 3960X 50 100 150 200 250 SE +/- 0.14, N = 3 244.74
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Pabellon Barcelona - Compute: CPU-Only Threadripper 3960X 40 80 120 160 200 SE +/- 0.36, N = 3 177.90
AI Benchmark Alpha Device Inference Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Inference Score Threadripper 3960X 400 800 1200 1600 2000 1999
AI Benchmark Alpha Device Training Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Training Score Threadripper 3960X 300 600 900 1200 1500 1496
AI Benchmark Alpha Device AI Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device AI Score Threadripper 3960X 700 1400 2100 2800 3500 3495
Tesseract OCR Time To OCR 7 Images OpenBenchmarking.org Seconds, Fewer Is Better Tesseract OCR 4.1.1 Time To OCR 7 Images Threadripper 3960X 6 12 18 24 30 SE +/- 0.11, N = 3 24.27
Kripke OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.4 Threadripper 3960X 11M 22M 33M 44M 55M SE +/- 256553.95, N = 3 53276823 1. (CXX) g++ options: -O3 -fopenmp
Phoronix Test Suite v10.8.4