stargazer-nvidia-test 2 x Intel Xeon E5-2640 v4 testing with a Supermicro X10DRG-O+-CPU v1.00 (2.0c BIOS) and MSI NVIDIA GeForce GTX 1080 Ti 11GB on Ubuntu 18.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2103180-HA-STARGAZER99 .
stargazer-nvidia-test Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Display Server Display Driver OpenCL Vulkan Compiler File-System Screen Resolution MSI NVIDIA GeForce GTX 1080 Ti 2 x Intel Xeon E5-2640 v4 @ 3.40GHz (20 Cores / 40 Threads) Supermicro X10DRG-O+-CPU v1.00 (2.0c BIOS) Intel Xeon E7 v4/Xeon 24 x 32 GB DDR4-1600MT/s HMA84GR7AFR4N-UH 1920GB INTEL SSDSC2KB01 MSI NVIDIA GeForce GTX 1080 Ti 11GB NVIDIA GP102 HDMI Audio 2 x Broadcom NetXtreme II BCM57810 10 + 2 x Intel I350 Ubuntu 18.04 5.4.0-67-generic (x86_64) X Server NVIDIA OpenCL 1.2 CUDA 11.2.136 1.2.155 GCC 7.5.0 + CUDA 11.1 ext4 1024x768 OpenBenchmarking.org - Transparent Huge Pages: madvise - --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - Scaling Governor: intel_pstate powersave - CPU Microcode: 0xb000038 - Python 2.7.17 + Python 3.6.9 - itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable
stargazer-nvidia-test mixbench: OpenCL - Integer mixbench: NVIDIA CUDA - Integer mixbench: OpenCL - Double Precision mixbench: OpenCL - Single Precision mixbench: NVIDIA CUDA - Half Precision mixbench: NVIDIA CUDA - Double Precision mixbench: NVIDIA CUDA - Single Precision viennacl: OpenCL LU Factorization cl-mem: Copy cl-mem: Read cl-mem: Write fahbench: rodinia: OpenCL Particle Filter arrayfire: Conjugate Gradient OpenCL financebench: Black-Scholes OpenCL ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - regnety_400m clpeak: Integer Compute INT clpeak: Single-Precision Float clpeak: Double-Precision Double clpeak: Global Memory Bandwidth MSI NVIDIA GeForce GTX 1080 Ti 3022.39 3337.10 348.58 9440.16 215.58 427.41 11702.31 41.0898 306.0 367.3 211.0 190.6026 8.466 3.439 77.027166 651.39 355.69 377.80 322.05 349.05 489.13 127.35 457.54 455.08 363.46 188.25 826.70 451.41 537.26 4229.23 1279.94 7362.82 423.70 355.52 OpenBenchmarking.org
Mixbench Backend: OpenCL - Benchmark: Integer OpenBenchmarking.org GIOPS, More Is Better Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Integer MSI NVIDIA GeForce GTX 1080 Ti 600 1200 1800 2400 3000 SE +/- 71.53, N = 12 3022.39 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench Backend: NVIDIA CUDA - Benchmark: Integer OpenBenchmarking.org GIOPS, More Is Better Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Integer MSI NVIDIA GeForce GTX 1080 Ti 700 1400 2100 2800 3500 SE +/- 5.36, N = 3 3337.10 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench Backend: OpenCL - Benchmark: Double Precision OpenBenchmarking.org GFLOPS, More Is Better Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Double Precision MSI NVIDIA GeForce GTX 1080 Ti 80 160 240 320 400 SE +/- 6.68, N = 15 348.58 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench Backend: OpenCL - Benchmark: Single Precision OpenBenchmarking.org GFLOPS, More Is Better Mixbench 2020-06-23 Backend: OpenCL - Benchmark: Single Precision MSI NVIDIA GeForce GTX 1080 Ti 2K 4K 6K 8K 10K SE +/- 225.98, N = 15 9440.16 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench Backend: NVIDIA CUDA - Benchmark: Half Precision OpenBenchmarking.org GFLOPS, More Is Better Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Half Precision MSI NVIDIA GeForce GTX 1080 Ti 50 100 150 200 250 SE +/- 0.12, N = 3 215.58 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench Backend: NVIDIA CUDA - Benchmark: Double Precision OpenBenchmarking.org GFLOPS, More Is Better Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Double Precision MSI NVIDIA GeForce GTX 1080 Ti 90 180 270 360 450 SE +/- 0.94, N = 3 427.41 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench Backend: NVIDIA CUDA - Benchmark: Single Precision OpenBenchmarking.org GFLOPS, More Is Better Mixbench 2020-06-23 Backend: NVIDIA CUDA - Benchmark: Single Precision MSI NVIDIA GeForce GTX 1080 Ti 3K 6K 9K 12K 15K SE +/- 94.68, N = 3 11702.31 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
ViennaCL OpenCL LU Factorization OpenBenchmarking.org GFLOPS, More Is Better ViennaCL 1.4.2 OpenCL LU Factorization MSI NVIDIA GeForce GTX 1080 Ti 9 18 27 36 45 SE +/- 0.76, N = 15 41.09 1. (CXX) g++ options: -rdynamic -lOpenCL
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy MSI NVIDIA GeForce GTX 1080 Ti 70 140 210 280 350 SE +/- 0.10, N = 3 306.0 1. (CC) gcc options: -O2 -flto -lOpenCL
cl-mem Benchmark: Read OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Read MSI NVIDIA GeForce GTX 1080 Ti 80 160 240 320 400 SE +/- 0.37, N = 3 367.3 1. (CC) gcc options: -O2 -flto -lOpenCL
cl-mem Benchmark: Write OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Write MSI NVIDIA GeForce GTX 1080 Ti 50 100 150 200 250 SE +/- 2.38, N = 3 211.0 1. (CC) gcc options: -O2 -flto -lOpenCL
FAHBench OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 MSI NVIDIA GeForce GTX 1080 Ti 40 80 120 160 200 SE +/- 2.00, N = 3 190.60
Rodinia Test: OpenCL Particle Filter OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenCL Particle Filter MSI NVIDIA GeForce GTX 1080 Ti 2 4 6 8 10 SE +/- 0.080, N = 6 8.466 1. (CXX) g++ options: -m64 -lm -lcuda -lcudart -lcudadevrt -lcudart_static -lrt -lpthread -ldl
ArrayFire Test: Conjugate Gradient OpenCL OpenBenchmarking.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient OpenCL MSI NVIDIA GeForce GTX 1080 Ti 0.7738 1.5476 2.3214 3.0952 3.869 SE +/- 0.022, N = 3 3.439 1. (CXX) g++ options: -rdynamic
FinanceBench Benchmark: Black-Scholes OpenCL OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Black-Scholes OpenCL MSI NVIDIA GeForce GTX 1080 Ti 20 40 60 80 100 SE +/- 8.68, N = 12 77.03 1. (CXX) g++ options: -O3 -march=native -fopenmp
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mobilenet MSI NVIDIA GeForce GTX 1080 Ti 140 280 420 560 700 SE +/- 175.62, N = 9 651.39 MIN: 24.83 / MAX: 2529.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 MSI NVIDIA GeForce GTX 1080 Ti 80 160 240 320 400 SE +/- 193.36, N = 9 355.69 MIN: 9.22 / MAX: 2167.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 MSI NVIDIA GeForce GTX 1080 Ti 80 160 240 320 400 SE +/- 196.61, N = 9 377.80 MIN: 8.13 / MAX: 2429.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: shufflenet-v2 MSI NVIDIA GeForce GTX 1080 Ti 70 140 210 280 350 SE +/- 152.49, N = 9 322.05 MIN: 9.06 / MAX: 2212.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mnasnet MSI NVIDIA GeForce GTX 1080 Ti 80 160 240 320 400 SE +/- 177.07, N = 9 349.05 MIN: 8.47 / MAX: 2348.59 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: efficientnet-b0 MSI NVIDIA GeForce GTX 1080 Ti 110 220 330 440 550 SE +/- 210.61, N = 9 489.13 MIN: 11.4 / MAX: 2409.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: blazeface MSI NVIDIA GeForce GTX 1080 Ti 30 60 90 120 150 SE +/- 84.25, N = 9 127.35 MIN: 4.33 / MAX: 1156.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: googlenet MSI NVIDIA GeForce GTX 1080 Ti 100 200 300 400 500 SE +/- 199.92, N = 9 457.54 MIN: 21.92 / MAX: 3198.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: vgg16 MSI NVIDIA GeForce GTX 1080 Ti 100 200 300 400 500 SE +/- 27.68, N = 9 455.08 MIN: 49.07 / MAX: 966.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet18 MSI NVIDIA GeForce GTX 1080 Ti 80 160 240 320 400 SE +/- 62.04, N = 9 363.46 MIN: 17.57 / MAX: 1420.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: alexnet MSI NVIDIA GeForce GTX 1080 Ti 40 80 120 160 200 SE +/- 27.13, N = 9 188.25 MIN: 12.25 / MAX: 482.5 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet50 MSI NVIDIA GeForce GTX 1080 Ti 200 400 600 800 1000 SE +/- 180.53, N = 9 826.70 MIN: 30.68 / MAX: 3046.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: yolov4-tiny MSI NVIDIA GeForce GTX 1080 Ti 100 200 300 400 500 SE +/- 66.15, N = 9 451.41 MIN: 38.22 / MAX: 1367.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: squeezenet_ssd MSI NVIDIA GeForce GTX 1080 Ti 120 240 360 480 600 SE +/- 156.67, N = 9 537.26 MIN: 28.19 / MAX: 2768.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: regnety_400m MSI NVIDIA GeForce GTX 1080 Ti 900 1800 2700 3600 4500 SE +/- 1659.34, N = 9 4229.23 MIN: 48.3 / MAX: 20492.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS, More Is Better clpeak OpenCL Test: Integer Compute INT MSI NVIDIA GeForce GTX 1080 Ti 300 600 900 1200 1500 SE +/- 203.28, N = 15 1279.94 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Single-Precision Float MSI NVIDIA GeForce GTX 1080 Ti 1600 3200 4800 6400 8000 SE +/- 1049.15, N = 12 7362.82 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double MSI NVIDIA GeForce GTX 1080 Ti 90 180 270 360 450 SE +/- 4.67, N = 3 423.70 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Global Memory Bandwidth MSI NVIDIA GeForce GTX 1080 Ti 80 160 240 320 400 SE +/- 0.47, N = 3 355.52 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
Phoronix Test Suite v10.8.4