Benchmarks by Michael Larabel for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2012250-HA-NVIDIAGPU61 NVIDIA Linux GPU Performance Comptue RTX 30 RTX 20 - Phoronix Test Suite NVIDIA Linux GPU Performance Comptue RTX 30 RTX 20 Benchmarks by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2012250-HA-NVIDIAGPU61&grs&sor .
NVIDIA Linux GPU Performance Comptue RTX 30 RTX 20 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution RTX 2060 RTX 2060 SUPER RTX 2070 RTX 2070 SUPER RTX 2080 RTX 2080 SUPER RTX 2080 Ti TITAN RTX RTX 3060 TI RTX 3080 AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3003 BIOS) AMD Starship/Matisse 16GB 2000GB Corsair Force MP600 NVIDIA GeForce RTX 2060 6GB (1365/7000MHz) NVIDIA TU106 HD Audio ASUS MG28U Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.4.0-58-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.8 NVIDIA 460.27.04 4.6.0 OpenCL 1.2 CUDA 11.2.66 1.2.155 GCC 9.3.0 ext4 3840x2160 NVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz) ASUS NVIDIA GeForce RTX 2070 8GB (435/405MHz) NVIDIA GeForce RTX 2070 SUPER 8GB (1605/7000MHz) NVIDIA TU104 HD Audio Zotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz) NVIDIA GeForce RTX 2080 SUPER 8GB (1650/7750MHz) NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz) NVIDIA TU102 HD Audio NVIDIA TITAN RTX 24GB (1350/7000MHz) NVIDIA GeForce RTX 3060 Ti 8GB (1665/7000MHz) NVIDIA Device 228b NVIDIA GeForce RTX 3080 10GB (1710/9501MHz) NVIDIA Device 1aef 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=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,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 (Boost: Enabled) - CPU Microcode: 0xa201009 OpenCL Details - RTX 2060: GPU Compute Cores: 1920 - RTX 2060 SUPER: GPU Compute Cores: 2176 - RTX 2070: GPU Compute Cores: 2304 - RTX 2070 SUPER: GPU Compute Cores: 2560 - RTX 2080: GPU Compute Cores: 2944 - RTX 2080 SUPER: GPU Compute Cores: 3072 - RTX 2080 Ti: GPU Compute Cores: 4352 - TITAN RTX: GPU Compute Cores: 4608 - RTX 3060 TI: GPU Compute Cores: 4864 - RTX 3080: GPU Compute Cores: 8704 Python Details - Python 2.7.18 + Python 3.8.5 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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
NVIDIA Linux GPU Performance Comptue RTX 30 RTX 20 clpeak: Single-Precision Float blender: Barbershop - NVIDIA OptiX blender: Classroom - NVIDIA OptiX blender: Pabellon Barcelona - NVIDIA OptiX luxcorerender-cl: Food blender: BMW27 - NVIDIA OptiX blender: Fishy Cat - NVIDIA OptiX clpeak: Integer Compute INT luxcorerender-cl: DLSC octanebench: Total Score redshift: luxcorerender-cl: LuxCore Benchmark plaidml: No - Inference - IMDB LSTM - OpenCL financebench: Black-Scholes OpenCL cl-mem: Write plaidml: No - Inference - VGG19 - OpenCL plaidml: No - Inference - VGG16 - OpenCL realsr-ncnn: 4x - Yes plaidml: No - Inference - NASNer Large - OpenCL vkresample: 2x - Single plaidml: No - Inference - Mobilenet - OpenCL betsy: ETC2 RGB - Highest clpeak: Global Memory Bandwidth vkresample: 2x - Double clpeak: Double-Precision Double hashcat: SHA1 plaidml: No - Inference - Inception V3 - OpenCL hashcat: TrueCrypt RIPEMD160 + XTS hashcat: SHA-512 betsy: ETC1 - Highest plaidml: No - Inference - ResNet 50 - OpenCL cl-mem: Read hashcat: MD5 hashcat: 7-Zip plaidml: Yes - Inference - Mobilenet - OpenCL rodinia: OpenCL Particle Filter plaidml: No - Inference - DenseNet 201 - OpenCL realsr-ncnn: 4x - No lczero: OpenCL plaidml: No - Training - VGG19 - OpenCL mandelgpu: GPU vkfft: plaidml: No - Training - VGG16 - OpenCL fahbench: arrayfire: Conjugate Gradient OpenCL waifu2x-ncnn: 2x - 3 - Yes cl-mem: Copy viennacl: OpenCL LU Factorization ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - mnasnet luxcorerender-cl: Rainbow Colors and Prism RTX 2060 RTX 2060 SUPER RTX 2070 RTX 2070 SUPER RTX 2080 RTX 2080 SUPER RTX 2080 Ti TITAN RTX RTX 3060 TI RTX 3080 5369.81 1779.46 147.65 206.86 1.21 36.27 67.13 5224.68 3.30 195.009806 469 2.80 392.02 12.565 251.6 88.38 110.96 85.948 31.81 27.195 1282.27 8.748 277.40 350.961 231.27 8248933333 171.78 311800 1049366667 6.189 320.95 297.5 25930633333 439000 1720.24 8.960 125.45 12.707 9752 22.04 253858256.7 22903 27.12 183.2913 2.650 5.779 239.5 74.5062 1.8 21.41 4.44 4.15 14.32 12.42 11.61 24.58 18.29 14.47 4.42 56.98 13.43 5.48 4.01 7.98 6985.02 1758.17 144.40 194.41 1.32 30.90 58.94 6956.55 4.19 244.224553 378 3.63 440.36 10.454 340.1 100.61 126.76 75.892 38.42 22.282 1581.85 7.733 369.42 309.619 261.53 9314900000 203.78 349600 1183433333 5.451 376.59 397.1 29272000000 490533 2011.99 7.981 147.13 11.540 11399 24.58 278640038.1 29585 30.00 207.0770 2.073 5.313 288.3 74.0853 1.93 22.80 4.67 4.34 14.63 13.04 11.53 25.71 18.49 14.77 4.47 57.22 14.18 5.70 4.33 11.41 7190.53 1826.30 148.17 198.63 1.30 31.34 58.34 7094.24 4.14 243.261218 375 3.56 447.47 10.225 323.9 103.03 129.65 74.654 39.07 22.269 1566.36 7.646 369.14 302.845 268.18 9535466667 202.05 356700 1213266667 5.309 379.70 397.1 29955566667 500233 2004.51 7.858 148.04 11.187 11495 283803060.1 29546 30.27 205.2322 2.086 5.314 285.7 74.1817 1.87 21.41 4.60 4.19 14.51 12.66 11.74 25.05 18.68 14.55 4.45 57.13 13.60 5.59 4.15 10.94 8591.77 996.82 89.12 132.73 1.86 25.44 48.03 8551.57 4.32 264.534943 351 3.67 499.43 8.224 320.6 121.35 152.58 63.178 42.32 19.523 1701.99 6.653 370.17 261.969 309.27 11183366667 220.43 423733 1426733333 4.824 422.86 397.1 35466033333 593700 2300.01 6.900 149.68 9.972 12841 27.78 321637774.3 29427 33.75 229.7600 2.060 4.761 292.3 75.7984 1.88 21.79 4.64 4.30 14.55 12.77 11.36 25.25 18.58 14.53 4.46 57.13 13.48 5.60 4.22 10.04 8860.55 971.62 86.13 132.90 1.88 26.24 45.51 9330.83 4.23 261.329504 341 3.55 545.48 7.620 331.9 128.62 161.88 59.403 45.39 19.024 1726.88 6.153 369.65 235.512 344.68 12203533333 242.54 461367 1559500000 4.375 442.78 397.1 38493233333 637367 2333.79 6.288 152.28 9.473 13576 28.32 343080891.1 28745 34.13 244.4171 2.072 4.605 290.5 77.1727 1.86 21.81 4.50 4.25 14.45 12.69 11.37 24.62 18.77 14.58 4.48 57.25 13.56 5.56 4.10 9.27 10347.92 911.32 81.14 126.93 1.97 25.22 42.60 10244.08 4.32 268.114368 325 3.60 588.04 6.749 350.8 143.39 180.23 54.037 49.16 17.507 1816.87 5.507 405.68 216.539 373.96 13653000000 266.39 527287 1734100000 4.004 468.60 437.8 43136966667 711967 2489.11 5.809 160.48 8.842 14634 32.29 368037096.6 30475 38.7 260.8957 1.893 4.358 302.0 76.6869 1.88 22.13 4.65 4.30 14.47 12.72 11.22 24.73 18.65 14.36 4.50 57.08 13.12 5.68 4.21 9.19 12677.18 899.14 73.99 103.97 2.18 21.67 32.80 13432.89 5.53 354.856769 246 4.58 754.69 6.014 446.6 185.09 231.73 44.186 63.53 14.767 2414.96 508.00 152.853 519.03 17751300000 351.18 657967 2241700000 3.177 636.84 545.6 55488333333 885300 3316.31 4.507 213.54 7.605 16952 36.9 447272306.0 34110 44.02 304.0362 1.670 3.856 324.0 78.3244 1.95 21.45 4.74 4.43 14.36 12.64 11.44 24.69 18.32 14.65 4.48 56.69 13.96 6.02 4.56 12.14 14109.68 905.22 73.40 102.51 2.23 18.64 31.72 13791.91 5.95 383.463739 235 5.03 782.29 5.691 495.4 194.50 244.00 41.731 66.50 13.561 2551.38 4.116 530.48 149.204 545.22 18576400000 359.13 688167 2350366667 3.043 654.76 568.2 58104300000 937233 3392.96 4.296 228.78 7.360 17009 37.56 460475602.6 36216 44.51 307.0348 1.637 3.827 320.8 81.3167 1.83 21.88 4.49 4.20 14.35 12.77 11.25 24.95 18.21 14.36 4.43 56.52 13.32 6.03 4.02 13.56 16033.64 565.99 56.33 84.95 2.97 20.15 36.74 8365.85 7.13 383.416583 239 5.91 689.61 8.328 384.3 133.11 167.73 54.144 48.04 17.676 1875.37 6.040 389.18 264.871 306.12 11103733333 236.40 427100 1406900000 4.358 454.66 392.8 32927600000 581300 2428.74 7.040 177.41 8.784 16799 29.38 280941400.2 32556 34.98 235.7167 2.092 4.371 294.1 75.7896 1.86 21.35 4.54 4.25 15.11 12.54 11.41 24.69 18.57 14.51 4.47 57.18 13.41 5.55 4.11 17.11 29490.81 421.51 38.85 55.63 4.00 11.48 21.48 15586.03 9.60 565.099512 165 7.84 1019.79 4.869 645.3 223.64 280.31 34.206 79.23 11.220 3062.00 3.664 662.24 148.284 545.91 19151100000 398.64 723200 2426033333 2.701 730.76 674.2 56429133333 981300 3623.82 4.290 261.32 6.345 18668 40.88 421918457.5 40997 47.50 320.6571 1.557 3.512 354.7 79.3217 1.91 22.15 4.56 4.34 14.50 12.78 11.71 25.34 18.45 14.74 4.52 56.96 13.95 5.61 4.20 21.91 OpenBenchmarking.org
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Single-Precision Float RTX 3080 RTX 3060 TI TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 6K 12K 18K 24K 30K SE +/- 0.32, N = 3 SE +/- 0.44, N = 3 SE +/- 193.76, N = 15 SE +/- 138.31, N = 3 SE +/- 174.06, N = 3 SE +/- 6.84, N = 3 SE +/- 84.78, N = 15 SE +/- 90.04, N = 15 SE +/- 75.69, N = 15 SE +/- 56.79, N = 15 29490.81 16033.64 14109.68 12677.18 10347.92 8860.55 8591.77 7190.53 6985.02 5369.81 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
Blender Blend File: Barbershop - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Barbershop - Compute: NVIDIA OptiX RTX 3080 RTX 3060 TI RTX 2080 Ti TITAN RTX RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2060 SUPER RTX 2060 RTX 2070 400 800 1200 1600 2000 SE +/- 1.49, N = 3 SE +/- 0.84, N = 3 SE +/- 1.58, N = 3 SE +/- 1.56, N = 3 SE +/- 0.14, N = 3 SE +/- 0.81, N = 3 SE +/- 1.90, N = 3 SE +/- 0.52, N = 3 SE +/- 2.01, N = 3 SE +/- 2.84, N = 3 421.51 565.99 899.14 905.22 911.32 971.62 996.82 1758.17 1779.46 1826.30
Blender Blend File: Classroom - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Classroom - Compute: NVIDIA OptiX RTX 3080 RTX 3060 TI TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2060 SUPER RTX 2060 RTX 2070 30 60 90 120 150 SE +/- 0.16, N = 3 SE +/- 0.23, N = 3 SE +/- 0.17, N = 3 SE +/- 0.50, N = 3 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 SE +/- 0.32, N = 3 SE +/- 0.38, N = 3 SE +/- 0.39, N = 3 SE +/- 0.95, N = 3 38.85 56.33 73.40 73.99 81.14 86.13 89.12 144.40 147.65 148.17
Blender Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX RTX 3080 RTX 3060 TI TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2070 SUPER RTX 2080 RTX 2060 SUPER RTX 2070 RTX 2060 50 100 150 200 250 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.26, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 55.63 84.95 102.51 103.97 126.93 132.73 132.90 194.41 198.63 206.86
LuxCoreRender OpenCL Scene: Food OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender OpenCL 2.3 Scene: Food RTX 3080 RTX 3060 TI TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2060 SUPER RTX 2070 RTX 2060 0.9 1.8 2.7 3.6 4.5 SE +/- 0.07, N = 14 SE +/- 0.05, N = 12 SE +/- 0.03, N = 5 SE +/- 0.04, N = 12 SE +/- 0.01, N = 3 SE +/- 0.03, N = 4 SE +/- 0.04, N = 12 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 4.00 2.97 2.23 2.18 1.97 1.88 1.86 1.32 1.30 1.21 MIN: 0.17 / MAX: 5.07 MIN: 0.19 / MAX: 3.74 MIN: 0.23 / MAX: 2.76 MIN: 0.15 / MAX: 2.71 MIN: 0.27 / MAX: 2.37 MIN: 0.23 / MAX: 2.29 MIN: 0.18 / MAX: 2.3 MIN: 0.23 / MAX: 1.59 MIN: 0.23 / MAX: 1.55 MIN: 0.24 / MAX: 1.44
Blender Blend File: BMW27 - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: BMW27 - Compute: NVIDIA OptiX RTX 3080 TITAN RTX RTX 3060 TI RTX 2080 Ti RTX 2080 SUPER RTX 2070 SUPER RTX 2080 RTX 2060 SUPER RTX 2070 RTX 2060 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 2.49, N = 15 SE +/- 2.49, N = 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 11.48 18.64 20.15 21.67 25.22 25.44 26.24 30.90 31.34 36.27
Blender Blend File: Fishy Cat - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Fishy Cat - Compute: NVIDIA OptiX RTX 3080 TITAN RTX RTX 2080 Ti RTX 3060 TI RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 15 30 45 60 75 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 21.48 31.72 32.80 36.74 42.60 45.51 48.03 58.34 58.94 67.13
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS, More Is Better clpeak OpenCL Test: Integer Compute INT RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 3060 TI RTX 2070 RTX 2060 SUPER RTX 2060 3K 6K 9K 12K 15K SE +/- 232.90, N = 3 SE +/- 135.03, N = 15 SE +/- 138.31, N = 15 SE +/- 165.30, N = 3 SE +/- 43.62, N = 3 SE +/- 72.96, N = 15 SE +/- 74.13, N = 15 SE +/- 85.50, N = 15 SE +/- 78.58, N = 15 SE +/- 4.93, N = 3 15586.03 13791.91 13432.89 10244.08 9330.83 8551.57 8365.85 7094.24 6956.55 5224.68 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
LuxCoreRender OpenCL Scene: DLSC OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender OpenCL 2.3 Scene: DLSC RTX 3080 RTX 3060 TI TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2070 SUPER RTX 2080 RTX 2060 SUPER RTX 2070 RTX 2060 3 6 9 12 15 SE +/- 0.14, N = 12 SE +/- 0.10, N = 12 SE +/- 0.01, N = 3 SE +/- 0.08, N = 12 SE +/- 0.00, N = 3 SE +/- 0.06, N = 12 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 9.60 7.13 5.95 5.53 4.32 4.32 4.23 4.19 4.14 3.30 MIN: 3.45 / MAX: 9.87 MIN: 2.58 / MAX: 7.38 MIN: 5.62 / MAX: 6.04 MIN: 2.02 / MAX: 5.76 MIN: 4.13 / MAX: 4.4 MIN: 1.6 / MAX: 4.51 MIN: 4.15 / MAX: 4.3 MIN: 4.11 / MAX: 4.29 MIN: 3.79 / MAX: 4.28 MIN: 3.16 / MAX: 3.4
OctaneBench Total Score OpenBenchmarking.org Score, More Is Better OctaneBench 2020.1 Total Score RTX 3080 TITAN RTX RTX 3060 TI RTX 2080 Ti RTX 2080 SUPER RTX 2070 SUPER RTX 2080 RTX 2060 SUPER RTX 2070 RTX 2060 120 240 360 480 600 565.10 383.46 383.42 354.86 268.11 264.53 261.33 244.22 243.26 195.01
RedShift Demo OpenBenchmarking.org Seconds, Fewer Is Better RedShift Demo 3.0 RTX 3080 TITAN RTX RTX 3060 TI RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 100 200 300 400 500 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 0.67, N = 3 SE +/- 1.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 SE +/- 1.00, N = 3 SE +/- 0.88, N = 3 165 235 239 246 325 341 351 375 378 469
LuxCoreRender OpenCL Scene: LuxCore Benchmark OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender OpenCL 2.3 Scene: LuxCore Benchmark RTX 3080 RTX 3060 TI TITAN RTX RTX 2080 Ti RTX 2070 SUPER RTX 2060 SUPER RTX 2080 SUPER RTX 2070 RTX 2080 RTX 2060 2 4 6 8 10 SE +/- 0.10, N = 12 SE +/- 0.07, N = 12 SE +/- 0.02, N = 3 SE +/- 0.04, N = 13 SE +/- 0.05, N = 12 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 7.84 5.91 5.03 4.58 3.67 3.63 3.60 3.56 3.55 2.80 MIN: 0.15 / MAX: 9.17 MIN: 0.25 / MAX: 6.86 MIN: 0.32 / MAX: 5.72 MIN: 0.19 / MAX: 5.4 MIN: 0.2 / MAX: 4.25 MIN: 0.23 / MAX: 4.15 MIN: 0.27 / MAX: 4.14 MIN: 0.23 / MAX: 4.1 MIN: 0.23 / MAX: 4.07 MIN: 0.23 / MAX: 3.2
PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 3060 TI RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 200 400 600 800 1000 SE +/- 1.56, N = 3 SE +/- 1.34, N = 3 SE +/- 1.36, N = 3 SE +/- 0.42, N = 3 SE +/- 0.10, N = 3 SE +/- 1.14, N = 3 SE +/- 0.23, N = 3 SE +/- 1.13, N = 3 SE +/- 0.53, N = 3 SE +/- 0.58, N = 3 1019.79 782.29 754.69 689.61 588.04 545.48 499.43 447.47 440.36 392.02
FinanceBench Benchmark: Black-Scholes OpenCL OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-06-06 Benchmark: Black-Scholes OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 3060 TI RTX 2070 RTX 2060 SUPER RTX 2060 3 6 9 12 15 SE +/- 0.020, N = 3 SE +/- 0.005, N = 3 SE +/- 0.007, N = 3 SE +/- 0.022, N = 3 SE +/- 0.019, N = 3 SE +/- 0.003, N = 3 SE +/- 0.000, N = 3 SE +/- 0.017, N = 3 SE +/- 0.010, N = 3 SE +/- 0.001, N = 3 4.869 5.691 6.014 6.749 7.620 8.224 8.328 10.225 10.454 12.565 1. (CXX) g++ options: -O3 -lOpenCL
cl-mem Benchmark: Write OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Write RTX 3080 TITAN RTX RTX 2080 Ti RTX 3060 TI RTX 2080 SUPER RTX 2060 SUPER RTX 2080 RTX 2070 RTX 2070 SUPER RTX 2060 140 280 420 560 700 SE +/- 0.03, N = 3 SE +/- 1.30, N = 3 SE +/- 0.38, N = 3 SE +/- 0.19, N = 3 SE +/- 0.17, N = 3 SE +/- 0.20, N = 3 SE +/- 0.79, N = 3 SE +/- 0.13, N = 3 SE +/- 0.23, N = 3 SE +/- 0.12, N = 3 645.3 495.4 446.6 384.3 350.8 340.1 331.9 323.9 320.6 251.6 1. (CC) gcc options: -O2 -flto -lOpenCL
PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 50 100 150 200 250 SE +/- 0.28, N = 3 SE +/- 0.14, N = 3 SE +/- 0.15, N = 3 SE +/- 0.20, N = 3 SE +/- 0.08, N = 3 SE +/- 0.27, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 223.64 194.50 185.09 143.39 133.11 128.62 121.35 103.03 100.61 88.38
PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 60 120 180 240 300 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.00, N = 3 SE +/- 0.11, N = 3 SE +/- 0.18, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 280.31 244.00 231.73 180.23 167.73 161.88 152.58 129.65 126.76 110.96
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.22, N = 3 SE +/- 0.21, N = 3 SE +/- 0.27, N = 3 SE +/- 0.09, N = 3 SE +/- 0.38, N = 3 SE +/- 0.29, N = 3 SE +/- 0.45, N = 3 SE +/- 0.37, N = 3 SE +/- 0.35, N = 3 34.21 41.73 44.19 54.04 54.14 59.40 63.18 74.65 75.89 85.95
PlaidML FP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.18, N = 3 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 79.23 66.50 63.53 49.16 48.04 45.39 42.32 39.07 38.42 31.81
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 11.22 13.56 14.77 17.51 17.68 19.02 19.52 22.27 22.28 27.20 1. (CXX) g++ options: -O3 -pthread
PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 3060 TI RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2060 SUPER RTX 2070 RTX 2060 700 1400 2100 2800 3500 SE +/- 8.25, N = 3 SE +/- 2.13, N = 3 SE +/- 4.12, N = 3 SE +/- 4.77, N = 3 SE +/- 1.68, N = 3 SE +/- 0.70, N = 3 SE +/- 3.23, N = 3 SE +/- 2.50, N = 3 SE +/- 3.57, N = 3 SE +/- 1.88, N = 3 3062.00 2551.38 2414.96 1875.37 1816.87 1726.88 1701.99 1581.85 1566.36 1282.27
Betsy GPU Compressor Codec: ETC2 RGB - Quality: Highest OpenBenchmarking.org Seconds, Fewer Is Better Betsy GPU Compressor 1.1 Beta Codec: ETC2 RGB - Quality: Highest RTX 3080 TITAN RTX RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 2 4 6 8 10 SE +/- 0.063, N = 13 SE +/- 0.058, N = 13 SE +/- 0.057, N = 14 SE +/- 0.066, N = 13 SE +/- 0.064, N = 12 SE +/- 0.053, N = 15 SE +/- 0.064, N = 12 SE +/- 0.060, N = 13 SE +/- 0.084, N = 9 3.664 4.116 5.507 6.040 6.153 6.653 7.646 7.733 8.748 1. (CXX) g++ options: -O3 -O2 -lpthread -ldl
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Global Memory Bandwidth RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2070 SUPER RTX 2080 RTX 2060 SUPER RTX 2070 RTX 2060 140 280 420 560 700 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.66, N = 3 SE +/- 0.18, N = 3 SE +/- 0.04, N = 3 SE +/- 0.21, N = 3 SE +/- 0.04, N = 3 SE +/- 0.41, N = 3 SE +/- 0.01, N = 3 SE +/- 0.14, N = 3 662.24 530.48 508.00 405.68 389.18 370.17 369.65 369.42 369.14 277.40 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
VkResample Upscale: 2x - Precision: Double OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Double RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 3060 TI RTX 2070 RTX 2060 SUPER RTX 2060 80 160 240 320 400 SE +/- 0.30, N = 3 SE +/- 0.10, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.63, N = 3 SE +/- 0.26, N = 3 SE +/- 0.88, N = 3 SE +/- 0.78, N = 3 SE +/- 0.28, N = 3 SE +/- 0.05, N = 3 148.28 149.20 152.85 216.54 235.51 261.97 264.87 302.85 309.62 350.96 1. (CXX) g++ options: -O3 -pthread
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 3060 TI RTX 2070 RTX 2060 SUPER RTX 2060 120 240 360 480 600 SE +/- 0.00, N = 3 SE +/- 1.44, N = 3 SE +/- 1.36, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.89, N = 3 SE +/- 0.77, N = 3 SE +/- 0.69, N = 3 SE +/- 0.61, N = 3 545.91 545.22 519.03 373.96 344.68 309.27 306.12 268.18 261.53 231.27 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
Hashcat Benchmark: SHA1 OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: SHA1 RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 3060 TI RTX 2070 RTX 2060 SUPER RTX 2060 4000M 8000M 12000M 16000M 20000M SE +/- 13325289.24, N = 3 SE +/- 24080351.60, N = 3 SE +/- 20384389.45, N = 3 SE +/- 3601851.38, N = 3 SE +/- 14178073.84, N = 3 SE +/- 1017076.42, N = 3 SE +/- 16045802.50, N = 3 SE +/- 2514844.82, N = 3 SE +/- 7522189.40, N = 3 SE +/- 2302414.19, N = 3 19151100000 18576400000 17751300000 13653000000 12203533333 11183366667 11103733333 9535466667 9314900000 8248933333
PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 3060 TI RTX 2070 SUPER RTX 2060 SUPER RTX 2070 RTX 2060 90 180 270 360 450 SE +/- 0.67, N = 3 SE +/- 0.19, N = 3 SE +/- 0.39, N = 3 SE +/- 0.03, N = 3 SE +/- 0.46, N = 3 SE +/- 0.67, N = 3 SE +/- 0.01, N = 3 SE +/- 0.18, N = 3 SE +/- 0.28, N = 3 SE +/- 0.18, N = 3 398.64 359.13 351.18 266.39 242.54 236.40 220.43 203.78 202.05 171.78
Hashcat Benchmark: TrueCrypt RIPEMD160 + XTS OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: TrueCrypt RIPEMD160 + XTS RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 3060 TI RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 150K 300K 450K 600K 750K SE +/- 750.56, N = 3 SE +/- 1120.02, N = 3 SE +/- 1591.99, N = 3 SE +/- 4580.29, N = 15 SE +/- 133.33, N = 3 SE +/- 550.76, N = 3 SE +/- 66.67, N = 3 SE +/- 556.78, N = 3 SE +/- 57.74, N = 3 SE +/- 57.74, N = 3 723200 688167 657967 527287 461367 427100 423733 356700 349600 311800
Hashcat Benchmark: SHA-512 OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: SHA-512 RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 3060 TI RTX 2070 RTX 2060 SUPER RTX 2060 500M 1000M 1500M 2000M 2500M SE +/- 2669165.50, N = 3 SE +/- 3263093.28, N = 3 SE +/- 1258305.74, N = 3 SE +/- 2042873.79, N = 3 SE +/- 814452.78, N = 3 SE +/- 933333.33, N = 3 SE +/- 750555.35, N = 3 SE +/- 845248.16, N = 3 SE +/- 1281058.59, N = 3 SE +/- 635959.47, N = 3 2426033333 2350366667 2241700000 1734100000 1559500000 1426733333 1406900000 1213266667 1183433333 1049366667
Betsy GPU Compressor Codec: ETC1 - Quality: Highest OpenBenchmarking.org Seconds, Fewer Is Better Betsy GPU Compressor 1.1 Beta Codec: ETC1 - Quality: Highest RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 2 4 6 8 10 SE +/- 0.052, N = 14 SE +/- 0.051, N = 14 SE +/- 0.049, N = 14 SE +/- 0.060, N = 14 SE +/- 0.051, N = 14 SE +/- 0.048, N = 14 SE +/- 0.054, N = 13 SE +/- 0.052, N = 13 SE +/- 0.052, N = 13 SE +/- 0.054, N = 13 2.701 3.043 3.177 4.004 4.358 4.375 4.824 5.309 5.451 6.189 1. (CXX) g++ options: -O3 -O2 -lpthread -ldl
PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 160 320 480 640 800 SE +/- 1.40, N = 3 SE +/- 2.07, N = 3 SE +/- 0.39, N = 3 SE +/- 0.40, N = 3 SE +/- 0.51, N = 3 SE +/- 0.34, N = 3 SE +/- 0.62, N = 3 SE +/- 0.70, N = 3 SE +/- 0.68, N = 3 SE +/- 0.61, N = 3 730.76 654.76 636.84 468.60 454.66 442.78 422.86 379.70 376.59 320.95
cl-mem Benchmark: Read OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Read RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 3060 TI RTX 2060 150 300 450 600 750 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.17, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.44, N = 3 SE +/- 0.00, N = 3 674.2 568.2 545.6 437.8 397.1 397.1 397.1 397.1 392.8 297.5 1. (CC) gcc options: -O2 -flto -lOpenCL
Hashcat Benchmark: MD5 OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: MD5 TITAN RTX RTX 3080 RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 3060 TI RTX 2070 RTX 2060 SUPER RTX 2060 12000M 24000M 36000M 48000M 60000M SE +/- 33241139.17, N = 3 SE +/- 39942305.61, N = 3 SE +/- 63030953.60, N = 3 SE +/- 13808974.54, N = 3 SE +/- 30944592.06, N = 3 SE +/- 41910871.04, N = 3 SE +/- 23055223.56, N = 3 SE +/- 9342079.24, N = 3 SE +/- 8911415.90, N = 3 SE +/- 11770207.21, N = 3 58104300000 56429133333 55488333333 43136966667 38493233333 35466033333 32927600000 29955566667 29272000000 25930633333
Hashcat Benchmark: 7-Zip OpenBenchmarking.org H/s, More Is Better Hashcat 6.1.1 Benchmark: 7-Zip RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 3060 TI RTX 2070 RTX 2060 SUPER RTX 2060 200K 400K 600K 800K 1000K SE +/- 503.32, N = 3 SE +/- 520.68, N = 3 SE +/- 3113.41, N = 3 SE +/- 1963.27, N = 3 SE +/- 1713.99, N = 3 SE +/- 435.89, N = 3 SE +/- 3659.23, N = 3 SE +/- 726.48, N = 3 SE +/- 1192.10, N = 3 SE +/- 1101.51, N = 3 981300 937233 885300 711967 637367 593700 581300 500233 490533 439000
PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2060 SUPER RTX 2070 RTX 2060 800 1600 2400 3200 4000 SE +/- 12.23, N = 3 SE +/- 16.11, N = 3 SE +/- 16.01, N = 3 SE +/- 1.35, N = 3 SE +/- 1.99, N = 3 SE +/- 3.97, N = 3 SE +/- 0.32, N = 3 SE +/- 2.83, N = 3 SE +/- 1.56, N = 3 SE +/- 1.92, N = 3 3623.82 3392.96 3316.31 2489.11 2428.74 2333.79 2300.01 2011.99 2004.51 1720.24
Rodinia Test: OpenCL Particle Filter OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenCL Particle Filter RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 3060 TI RTX 2070 RTX 2060 SUPER RTX 2060 3 6 9 12 15 SE +/- 0.018, N = 3 SE +/- 0.016, N = 3 SE +/- 0.076, N = 3 SE +/- 0.010, N = 3 SE +/- 0.006, N = 3 SE +/- 0.014, N = 3 SE +/- 0.067, N = 3 SE +/- 0.017, N = 3 SE +/- 0.027, N = 3 SE +/- 0.009, N = 3 4.290 4.296 4.507 5.809 6.288 6.900 7.040 7.858 7.981 8.960 1. (CXX) g++ options: -O2 -lOpenCL
PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 3060 TI RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 60 120 180 240 300 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.26, N = 3 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 SE +/- 0.07, N = 3 261.32 228.78 213.54 177.41 160.48 152.28 149.68 148.04 147.13 125.45
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No RTX 3080 TITAN RTX RTX 2080 Ti RTX 3060 TI RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 3 6 9 12 15 SE +/- 0.093, N = 3 SE +/- 0.105, N = 3 SE +/- 0.108, N = 3 SE +/- 0.056, N = 3 SE +/- 0.101, N = 3 SE +/- 0.131, N = 3 SE +/- 0.110, N = 3 SE +/- 0.096, N = 3 SE +/- 0.111, N = 3 SE +/- 0.091, N = 3 6.345 7.360 7.605 8.784 8.842 9.473 9.972 11.187 11.540 12.707
LeelaChessZero Backend: OpenCL OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 3060 TI RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 4K 8K 12K 16K 20K SE +/- 122.65, N = 3 SE +/- 110.73, N = 3 SE +/- 54.85, N = 3 SE +/- 26.30, N = 3 SE +/- 48.26, N = 3 SE +/- 51.64, N = 3 SE +/- 49.97, N = 3 SE +/- 54.87, N = 3 SE +/- 69.95, N = 3 SE +/- 66.84, N = 3 18668 17009 16952 16799 14634 13576 12841 11495 11399 9752 1. (CXX) g++ options: -flto -pthread
PlaidML FP16: No - Mode: Training - Network: VGG19 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Training - Network: VGG19 - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2060 SUPER RTX 2060 9 18 27 36 45 SE +/- 0.08, N = 2 SE +/- 0.15, N = 2 SE +/- 0.05, N = 2 SE +/- 0.04, N = 2 40.88 37.56 36.90 32.29 29.38 28.32 27.78 24.58 22.04
MandelGPU OpenCL Device: GPU OpenBenchmarking.org Samples/sec, More Is Better MandelGPU 1.3pts1 OpenCL Device: GPU TITAN RTX RTX 2080 Ti RTX 3080 RTX 2080 SUPER RTX 2080 RTX 2070 SUPER RTX 2070 RTX 3060 TI RTX 2060 SUPER RTX 2060 100M 200M 300M 400M 500M SE +/- 2487384.16, N = 3 SE +/- 590928.34, N = 3 SE +/- 2886689.51, N = 3 SE +/- 774665.97, N = 3 SE +/- 1494897.42, N = 3 SE +/- 516930.54, N = 3 SE +/- 776602.98, N = 3 SE +/- 805777.35, N = 3 SE +/- 1645708.79, N = 3 SE +/- 1171800.01, N = 3 460475602.6 447272306.0 421918457.5 368037096.6 343080891.1 321637774.3 283803060.1 280941400.2 278640038.1 253858256.7 1. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL
VkFFT OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.1.1 RTX 3080 TITAN RTX RTX 2080 Ti RTX 3060 TI RTX 2080 SUPER RTX 2060 SUPER RTX 2070 RTX 2070 SUPER RTX 2080 RTX 2060 9K 18K 27K 36K 45K SE +/- 284.10, N = 3 SE +/- 413.34, N = 3 SE +/- 78.30, N = 3 SE +/- 86.88, N = 3 SE +/- 51.40, N = 3 SE +/- 257.75, N = 3 SE +/- 149.21, N = 3 SE +/- 213.44, N = 3 SE +/- 95.96, N = 3 SE +/- 44.06, N = 3 40997 36216 34110 32556 30475 29585 29546 29427 28745 22903 1. (CXX) g++ options: -O3 -pthread
PlaidML FP16: No - Mode: Training - Network: VGG16 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Training - Network: VGG16 - Device: OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2070 RTX 2060 SUPER RTX 2060 11 22 33 44 55 SE +/- 0.36, N = 2 SE +/- 0.18, N = 2 SE +/- 0.33, N = 2 SE +/- 0.20, N = 2 47.50 44.51 44.02 38.70 34.98 34.13 33.75 30.27 30.00 27.12
FAHBench OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2080 RTX 3060 TI RTX 2070 SUPER RTX 2060 SUPER RTX 2070 RTX 2060 70 140 210 280 350 SE +/- 0.30, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.20, N = 3 SE +/- 0.18, N = 3 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 SE +/- 0.10, N = 3 SE +/- 0.18, N = 3 320.66 307.03 304.04 260.90 244.42 235.72 229.76 207.08 205.23 183.29
ArrayFire Test: Conjugate Gradient OpenCL OpenBenchmarking.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient OpenCL RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 2070 SUPER RTX 2080 RTX 2060 SUPER RTX 2070 RTX 3060 TI RTX 2060 0.5963 1.1926 1.7889 2.3852 2.9815 SE +/- 0.004, N = 3 SE +/- 0.010, N = 3 SE +/- 0.010, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.003, N = 3 SE +/- 0.002, N = 3 SE +/- 0.002, N = 3 SE +/- 0.002, N = 3 SE +/- 0.003, N = 3 1.557 1.637 1.670 1.893 2.060 2.072 2.073 2.086 2.092 2.650 1. (CXX) g++ options: -rdynamic
Waifu2x-NCNN Vulkan Scale: 2x - Denoise: 3 - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes RTX 3080 TITAN RTX RTX 2080 Ti RTX 2080 SUPER RTX 3060 TI RTX 2080 RTX 2070 SUPER RTX 2060 SUPER RTX 2070 RTX 2060 1.3003 2.6006 3.9009 5.2012 6.5015 SE +/- 0.047, N = 5 SE +/- 0.056, N = 3 SE +/- 0.057, N = 3 SE +/- 0.060, N = 3 SE +/- 0.008, N = 3 SE +/- 0.053, N = 3 SE +/- 0.067, N = 4 SE +/- 0.055, N = 3 SE +/- 0.049, N = 3 SE +/- 0.064, N = 3 3.512 3.827 3.856 4.358 4.371 4.605 4.761 5.313 5.314 5.779
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy RTX 3080 RTX 2080 Ti TITAN RTX RTX 2080 SUPER RTX 3060 TI RTX 2070 SUPER RTX 2080 RTX 2060 SUPER RTX 2070 RTX 2060 80 160 240 320 400 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.21, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 354.7 324.0 320.8 302.0 294.1 292.3 290.5 288.3 285.7 239.5 1. (CC) gcc options: -O2 -flto -lOpenCL
ViennaCL OpenCL LU Factorization OpenBenchmarking.org GFLOPS, More Is Better ViennaCL 1.4.2 OpenCL LU Factorization TITAN RTX RTX 3080 RTX 2080 Ti RTX 2080 RTX 2080 SUPER RTX 2070 SUPER RTX 3060 TI RTX 2060 RTX 2070 RTX 2060 SUPER 20 40 60 80 100 SE +/- 0.19, N = 3 SE +/- 0.10, N = 3 SE +/- 0.20, N = 3 SE +/- 0.16, N = 3 SE +/- 0.12, N = 3 SE +/- 0.40, N = 3 SE +/- 0.09, N = 3 SE +/- 0.20, N = 3 SE +/- 0.18, N = 3 SE +/- 0.40, N = 3 81.32 79.32 78.32 77.17 76.69 75.80 75.79 74.51 74.18 74.09 1. (CXX) g++ options: -rdynamic -lOpenCL
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: blazeface RTX 2060 TITAN RTX RTX 2080 RTX 3060 TI RTX 2070 RTX 2070 SUPER RTX 2080 SUPER RTX 3080 RTX 2060 SUPER RTX 2080 Ti 0.4388 0.8776 1.3164 1.7552 2.194 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 5 SE +/- 0.02, N = 4 SE +/- 0.05, N = 3 SE +/- 0.02, N = 15 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 4 SE +/- 0.04, N = 3 1.80 1.83 1.86 1.86 1.87 1.88 1.88 1.91 1.93 1.95 MIN: 1.79 / MAX: 1.96 MIN: 1.78 / MAX: 2.03 MIN: 1.81 / MAX: 2.28 MIN: 1.78 / MAX: 2.03 MIN: 1.8 / MAX: 2.15 MIN: 1.78 / MAX: 2.2 MIN: 1.77 / MAX: 2.21 MIN: 1.82 / MAX: 2.14 MIN: 1.85 / MAX: 2.11 MIN: 1.85 / MAX: 2.39 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 RTX 3060 TI RTX 2060 RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 TITAN RTX RTX 2080 SUPER RTX 3080 RTX 2060 SUPER 5 10 15 20 25 SE +/- 0.64, N = 4 SE +/- 0.56, N = 3 SE +/- 0.58, N = 3 SE +/- 0.60, N = 3 SE +/- 0.24, N = 15 SE +/- 0.41, N = 5 SE +/- 0.66, N = 3 SE +/- 0.60, N = 3 SE +/- 0.70, N = 3 SE +/- 0.07, N = 4 21.35 21.41 21.41 21.45 21.79 21.81 21.88 22.13 22.15 22.80 MIN: 20.24 / MAX: 29.48 MIN: 20.54 / MAX: 32.23 MIN: 20.58 / MAX: 23.53 MIN: 20.52 / MAX: 33.08 MIN: 20.42 / MAX: 29.15 MIN: 20.55 / MAX: 24.56 MIN: 20.33 / MAX: 23.41 MIN: 20.69 / MAX: 28.53 MIN: 20.53 / MAX: 30.78 MIN: 22.31 / MAX: 25.04 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 RTX 2060 TITAN RTX RTX 2080 RTX 3060 TI RTX 3080 RTX 2070 RTX 2070 SUPER RTX 2080 SUPER RTX 2060 SUPER RTX 2080 Ti 1.0665 2.133 3.1995 4.266 5.3325 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 5 SE +/- 0.05, N = 4 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 15 SE +/- 0.23, N = 3 SE +/- 0.07, N = 4 SE +/- 0.21, N = 3 4.44 4.49 4.50 4.54 4.56 4.60 4.64 4.65 4.67 4.74 MIN: 4.21 / MAX: 4.75 MIN: 4.26 / MAX: 4.85 MIN: 4.19 / MAX: 13.41 MIN: 4.25 / MAX: 5.73 MIN: 4.3 / MAX: 4.85 MIN: 4.35 / MAX: 13.48 MIN: 4.23 / MAX: 5.42 MIN: 4.19 / MAX: 5.42 MIN: 4.31 / MAX: 5.1 MIN: 4.31 / MAX: 5.6 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 RTX 2060 RTX 2070 TITAN RTX RTX 2080 RTX 3060 TI RTX 2070 SUPER RTX 2080 SUPER RTX 2060 SUPER RTX 3080 RTX 2080 Ti 0.9968 1.9936 2.9904 3.9872 4.984 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.05, N = 5 SE +/- 0.06, N = 4 SE +/- 0.04, N = 15 SE +/- 0.10, N = 3 SE +/- 0.08, N = 4 SE +/- 0.09, N = 3 SE +/- 0.11, N = 3 4.15 4.19 4.20 4.25 4.25 4.30 4.30 4.34 4.34 4.43 MIN: 4.06 / MAX: 4.44 MIN: 4.14 / MAX: 4.4 MIN: 4.14 / MAX: 4.93 MIN: 4.07 / MAX: 4.62 MIN: 4.02 / MAX: 5.79 MIN: 4.06 / MAX: 19.54 MIN: 4.12 / MAX: 4.69 MIN: 4.12 / MAX: 4.79 MIN: 4.17 / MAX: 4.73 MIN: 4.13 / MAX: 11.06 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 RTX 2060 TITAN RTX RTX 2080 Ti RTX 2080 RTX 2080 SUPER RTX 3080 RTX 2070 RTX 2070 SUPER RTX 2060 SUPER RTX 3060 TI 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.19, N = 3 SE +/- 0.03, N = 3 SE +/- 0.24, N = 4 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.14, N = 2 SE +/- 0.06, N = 15 SE +/- 0.12, N = 4 SE +/- 0.73, N = 4 14.32 14.35 14.36 14.45 14.47 14.50 14.51 14.55 14.63 15.11 MIN: 14.04 / MAX: 14.98 MIN: 13.84 / MAX: 22.5 MIN: 13.91 / MAX: 27.4 MIN: 13.6 / MAX: 27.41 MIN: 14.11 / MAX: 24.43 MIN: 14.11 / MAX: 14.97 MIN: 14.12 / MAX: 15.9 MIN: 13.96 / MAX: 25.49 MIN: 14.15 / MAX: 16.53 MIN: 13.72 / MAX: 369.11 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mobilenet RTX 2060 RTX 3060 TI RTX 2080 Ti RTX 2070 RTX 2080 RTX 2080 SUPER RTX 2070 SUPER TITAN RTX RTX 3080 RTX 2060 SUPER 3 6 9 12 15 SE +/- 0.14, N = 3 SE +/- 0.17, N = 4 SE +/- 0.18, N = 3 SE +/- 0.17, N = 3 SE +/- 0.16, N = 5 SE +/- 0.11, N = 3 SE +/- 0.14, N = 15 SE +/- 0.16, N = 3 SE +/- 0.12, N = 3 SE +/- 0.17, N = 4 12.42 12.54 12.64 12.66 12.69 12.72 12.77 12.77 12.78 13.04 MIN: 11.98 / MAX: 24.63 MIN: 11.94 / MAX: 15.69 MIN: 12.22 / MAX: 14.36 MIN: 12.23 / MAX: 24.28 MIN: 11.97 / MAX: 24.76 MIN: 12.26 / MAX: 13.5 MIN: 11.98 / MAX: 34.45 MIN: 12.01 / MAX: 24.52 MIN: 12.35 / MAX: 20.47 MIN: 12.34 / MAX: 24 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 RTX 2080 SUPER TITAN RTX RTX 2070 SUPER RTX 2080 RTX 3060 TI RTX 2080 Ti RTX 2060 SUPER RTX 2060 RTX 3080 RTX 2070 3 6 9 12 15 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 15 SE +/- 0.06, N = 5 SE +/- 0.15, N = 4 SE +/- 0.04, N = 3 SE +/- 0.04, N = 4 SE +/- 0.22, N = 3 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 11.22 11.25 11.36 11.37 11.41 11.44 11.53 11.61 11.71 11.74 MIN: 10.85 / MAX: 11.85 MIN: 11 / MAX: 11.61 MIN: 10.75 / MAX: 15.63 MIN: 11.04 / MAX: 17.87 MIN: 10.77 / MAX: 22.45 MIN: 11.09 / MAX: 11.74 MIN: 11.27 / MAX: 18.29 MIN: 11.08 / MAX: 18.93 MIN: 11.28 / MAX: 12.12 MIN: 11.39 / MAX: 12.18 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 RTX 2060 RTX 2080 RTX 2080 Ti RTX 3060 TI RTX 2080 SUPER TITAN RTX RTX 2070 RTX 2070 SUPER RTX 3080 RTX 2060 SUPER 6 12 18 24 30 SE +/- 0.15, N = 3 SE +/- 0.23, N = 5 SE +/- 0.33, N = 3 SE +/- 0.35, N = 4 SE +/- 0.40, N = 3 SE +/- 0.37, N = 3 SE +/- 0.54, N = 3 SE +/- 0.18, N = 15 SE +/- 0.56, N = 3 SE +/- 0.09, N = 4 24.58 24.62 24.69 24.69 24.73 24.95 25.05 25.25 25.34 25.71 MIN: 23.83 / MAX: 37.73 MIN: 23.99 / MAX: 26.48 MIN: 23.98 / MAX: 37.45 MIN: 23.66 / MAX: 26.48 MIN: 23.79 / MAX: 35.29 MIN: 23.91 / MAX: 36.02 MIN: 24.29 / MAX: 41.55 MIN: 23.93 / MAX: 36.67 MIN: 24.02 / MAX: 26.96 MIN: 24.88 / MAX: 31.53 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 TITAN RTX RTX 2060 RTX 2080 Ti RTX 3080 RTX 2060 SUPER RTX 3060 TI RTX 2070 SUPER RTX 2080 SUPER RTX 2070 RTX 2080 5 10 15 20 25 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.20, N = 3 SE +/- 0.35, N = 3 SE +/- 0.15, N = 4 SE +/- 0.28, N = 4 SE +/- 0.07, N = 15 SE +/- 0.19, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 5 18.21 18.29 18.32 18.45 18.49 18.57 18.58 18.65 18.68 18.77 MIN: 17.88 / MAX: 20.03 MIN: 17.99 / MAX: 28.28 MIN: 17.72 / MAX: 19.14 MIN: 17.4 / MAX: 28.56 MIN: 18.01 / MAX: 28.46 MIN: 17.78 / MAX: 20.78 MIN: 17.91 / MAX: 28.99 MIN: 18.24 / MAX: 19.54 MIN: 18.38 / MAX: 19.17 MIN: 18.01 / MAX: 30.34 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 RTX 2080 SUPER TITAN RTX RTX 2060 RTX 3060 TI RTX 2070 SUPER RTX 2070 RTX 2080 RTX 2080 Ti RTX 3080 RTX 2060 SUPER 4 8 12 16 20 SE +/- 0.14, N = 3 SE +/- 0.25, N = 3 SE +/- 0.26, N = 3 SE +/- 0.21, N = 4 SE +/- 0.07, N = 15 SE +/- 0.19, N = 3 SE +/- 0.12, N = 5 SE +/- 0.19, N = 3 SE +/- 0.25, N = 3 SE +/- 0.19, N = 4 14.36 14.36 14.47 14.51 14.53 14.55 14.58 14.65 14.74 14.77 MIN: 14.01 / MAX: 15.12 MIN: 13.96 / MAX: 17.74 MIN: 14.01 / MAX: 23.82 MIN: 13.97 / MAX: 25.49 MIN: 14.06 / MAX: 27.16 MIN: 14.18 / MAX: 15.25 MIN: 14.21 / MAX: 16.27 MIN: 14.13 / MAX: 15.56 MIN: 14.13 / MAX: 15.8 MIN: 14.08 / MAX: 16.79 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 RTX 2060 TITAN RTX RTX 2070 RTX 2070 SUPER RTX 2060 SUPER RTX 3060 TI RTX 2080 RTX 2080 Ti RTX 2080 SUPER RTX 3080 1.017 2.034 3.051 4.068 5.085 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 13 SE +/- 0.01, N = 4 SE +/- 0.03, N = 3 SE +/- 0.01, N = 5 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 4.42 4.43 4.45 4.46 4.47 4.47 4.48 4.48 4.50 4.52 MIN: 4.31 / MAX: 4.8 MIN: 4.32 / MAX: 5.06 MIN: 4.34 / MAX: 4.91 MIN: 4.31 / MAX: 4.82 MIN: 4.37 / MAX: 4.78 MIN: 4.34 / MAX: 5.99 MIN: 4.36 / MAX: 14.35 MIN: 4.38 / MAX: 4.9 MIN: 4.35 / MAX: 5.04 MIN: 4.42 / MAX: 13.63 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 TITAN RTX RTX 2080 Ti RTX 3080 RTX 2060 RTX 2080 SUPER RTX 2070 RTX 2070 SUPER RTX 3060 TI RTX 2060 SUPER RTX 2080 13 26 39 52 65 SE +/- 0.17, N = 3 SE +/- 0.27, N = 3 SE +/- 0.09, N = 3 SE +/- 0.31, N = 3 SE +/- 0.37, N = 3 SE +/- 0.13, N = 3 SE +/- 0.13, N = 15 SE +/- 0.43, N = 4 SE +/- 0.14, N = 4 SE +/- 0.17, N = 5 56.52 56.69 56.96 56.98 57.08 57.13 57.13 57.18 57.22 57.25 MIN: 55.22 / MAX: 72.77 MIN: 55.51 / MAX: 58.35 MIN: 56.04 / MAX: 59.71 MIN: 55.41 / MAX: 58.77 MIN: 55.71 / MAX: 70.92 MIN: 56.01 / MAX: 66.17 MIN: 54.93 / MAX: 68.8 MIN: 54.93 / MAX: 68.94 MIN: 55.71 / MAX: 64.21 MIN: 55.82 / MAX: 67.69 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 RTX 2080 SUPER TITAN RTX RTX 3060 TI RTX 2060 RTX 2070 SUPER RTX 2080 RTX 2070 RTX 3080 RTX 2080 Ti RTX 2060 SUPER 4 8 12 16 20 SE +/- 0.39, N = 3 SE +/- 0.68, N = 2 SE +/- 0.33, N = 4 SE +/- 0.55, N = 3 SE +/- 0.21, N = 14 SE +/- 0.35, N = 5 SE +/- 0.27, N = 3 SE +/- 0.37, N = 3 SE +/- 0.49, N = 3 SE +/- 0.43, N = 4 13.12 13.32 13.41 13.43 13.48 13.56 13.60 13.95 13.96 14.18 MIN: 12.41 / MAX: 14.53 MIN: 12.38 / MAX: 25.82 MIN: 12.46 / MAX: 28.14 MIN: 12.61 / MAX: 15.67 MIN: 12.43 / MAX: 26.89 MIN: 12.71 / MAX: 20.62 MIN: 12.94 / MAX: 24.05 MIN: 12.96 / MAX: 24.07 MIN: 12.74 / MAX: 15.74 MIN: 12.62 / MAX: 15.92 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 RTX 2060 RTX 3060 TI RTX 2080 RTX 2070 RTX 2070 SUPER RTX 3080 RTX 2080 SUPER RTX 2060 SUPER RTX 2080 Ti TITAN RTX 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.05, N = 4 SE +/- 0.04, N = 5 SE +/- 0.02, N = 3 SE +/- 0.06, N = 15 SE +/- 0.06, N = 3 SE +/- 0.21, N = 3 SE +/- 0.06, N = 4 SE +/- 0.26, N = 3 SE +/- 0.57, N = 3 5.48 5.55 5.56 5.59 5.60 5.61 5.68 5.70 6.02 6.03 MIN: 5.32 / MAX: 5.98 MIN: 5.34 / MAX: 7.32 MIN: 5.37 / MAX: 6.08 MIN: 5.42 / MAX: 5.85 MIN: 5.28 / MAX: 16.37 MIN: 5.45 / MAX: 5.87 MIN: 5.29 / MAX: 17.94 MIN: 5.43 / MAX: 17.45 MIN: 5.37 / MAX: 11.96 MIN: 5.28 / MAX: 339.41 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 RTX 2060 TITAN RTX RTX 2080 RTX 3060 TI RTX 2070 RTX 3080 RTX 2080 SUPER RTX 2070 SUPER RTX 2060 SUPER RTX 2080 Ti 1.026 2.052 3.078 4.104 5.13 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 5 SE +/- 0.06, N = 4 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 SE +/- 0.21, N = 3 SE +/- 0.07, N = 15 SE +/- 0.10, N = 3 SE +/- 0.26, N = 3 4.01 4.02 4.10 4.11 4.15 4.20 4.21 4.22 4.33 4.56 MIN: 3.83 / MAX: 4.42 MIN: 3.88 / MAX: 4.28 MIN: 3.82 / MAX: 4.59 MIN: 3.87 / MAX: 5.49 MIN: 4 / MAX: 16.56 MIN: 3.91 / MAX: 10.98 MIN: 3.86 / MAX: 4.92 MIN: 3.86 / MAX: 5.14 MIN: 4.04 / MAX: 4.77 MIN: 3.93 / MAX: 5.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LuxCoreRender OpenCL Scene: Rainbow Colors and Prism OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender OpenCL 2.3 Scene: Rainbow Colors and Prism RTX 3080 RTX 3060 TI TITAN RTX RTX 2080 Ti RTX 2060 SUPER RTX 2070 RTX 2070 SUPER RTX 2080 RTX 2080 SUPER RTX 2060 5 10 15 20 25 SE +/- 0.65, N = 12 SE +/- 0.48, N = 12 SE +/- 0.02, N = 3 SE +/- 0.27, N = 12 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.20, N = 12 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 21.91 17.11 13.56 12.14 11.41 10.94 10.04 9.27 9.19 7.98 MIN: 12.02 / MAX: 23.73 MIN: 8.56 / MAX: 18.35 MIN: 12.87 / MAX: 14.06 MIN: 6.39 / MAX: 12.87 MIN: 9.87 / MAX: 11.85 MIN: 9.85 / MAX: 11.46 MIN: 5.24 / MAX: 10.68 MIN: 8.34 / MAX: 9.64 MIN: 7.68 / MAX: 9.63 MIN: 7.02 / MAX: 8.25
Phoronix Test Suite v10.8.4