Benchmarks for a future article.
RTX 3070 Ti Processor: AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (3402 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 1000GB Sabrent Rocket 4.0 Plus + 2000GB, Graphics: NVIDIA GeForce RTX 3070 Ti 8GB, Audio: NVIDIA GA104 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8125 2.5GbE + Intel I211
OS: Ubuntu 21.04, Kernel: 5.11.0-17-generic (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11, Display Driver: NVIDIA 465.31, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 11.3.116, Vulkan: 1.2.168, Compiler: GCC 10.3.0 + CUDA 11.3, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/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-build-config=bootstrap-lto-lean --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 -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009OpenCL Notes: GPU Compute Cores: 6144Python Notes: Python 3.9.5Security Notes: 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
RTX 3090 Changed Graphics to NVIDIA GeForce RTX 3090 24GB .
OpenCL Change: GPU Compute Cores: 10496
RTX 3080 Changed Graphics to NVIDIA GeForce RTX 3080 10GB .
OpenCL Change: GPU Compute Cores: 8704
RTX 2080 Changed Graphics to Zotac NVIDIA GeForce RTX 2080 8GB .
OpenCL Change: GPU Compute Cores: 2944
RTX 3080 Ti Changed Graphics to NVIDIA GeForce RTX 3080 Ti 12GB .
OpenCL Change: GPU Compute Cores: 10240
RTX 2060 SUPER Changed Graphics to NVIDIA GeForce RTX 2060 SUPER 8GB .
OpenCL Change: GPU Compute Cores: 2176
TITAN RTX Changed Graphics to NVIDIA TITAN RTX 24GB .
OpenCL Change: GPU Compute Cores: 4608
RTX 3060 Changed Graphics to eVGA NVIDIA GeForce RTX 3060 12GB .
OpenCL Change: GPU Compute Cores: 3584
RTX 3070 Changed Graphics to NVIDIA GeForce RTX 3070 8GB .
OpenCL Change: GPU Compute Cores: 5888
RTX 3060 Ti Changed Graphics to NVIDIA GeForce RTX 3060 Ti 8GB .
OpenCL Change: GPU Compute Cores: 4864
RTX 2080 SUPER Changed Graphics to NVIDIA GeForce RTX 2080 SUPER 8GB .
OpenCL Change: GPU Compute Cores: 3072
RTX 2070 SUPER Changed Graphics to NVIDIA GeForce RTX 2070 SUPER 8GB .
OpenCL Change: GPU Compute Cores: 2560
RTX 2080 Ti Changed Graphics to NVIDIA GeForce RTX 2080 Ti 11GB .
OpenCL Change: GPU Compute Cores: 4352
RTX 2070 Changed Graphics to ASUS NVIDIA GeForce RTX 2070 8GB .
OpenCL Change: GPU Compute Cores: 2304
NVIDIA GPU Compute Benchmarks OpenBenchmarking.org Phoronix Test Suite AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads) ASUS ROG CROSSHAIR VIII HERO (3402 BIOS) AMD Starship/Matisse 16GB 1000GB Sabrent Rocket 4.0 Plus + 2000GB NVIDIA GeForce RTX 3070 Ti 8GB NVIDIA GeForce RTX 3090 24GB NVIDIA GeForce RTX 3080 10GB Zotac NVIDIA GeForce RTX 2080 8GB NVIDIA GeForce RTX 3080 Ti 12GB NVIDIA GeForce RTX 2060 SUPER 8GB NVIDIA TITAN RTX 24GB eVGA NVIDIA GeForce RTX 3060 12GB NVIDIA GeForce RTX 3070 8GB NVIDIA GeForce RTX 3060 Ti 8GB NVIDIA GeForce RTX 2080 SUPER 8GB NVIDIA GeForce RTX 2070 SUPER 8GB NVIDIA GeForce RTX 2080 Ti 11GB ASUS NVIDIA GeForce RTX 2070 8GB NVIDIA GA104 HD Audio NVIDIA GA102 HD Audio NVIDIA TU104 HD Audio NVIDIA TU106 HD Audio NVIDIA TU102 HD Audio NVIDIA GeForce RTX 3060 ASUS VP28U Realtek RTL8125 2.5GbE + Intel I211 Ubuntu 21.04 5.11.0-17-generic (x86_64) GNOME Shell 3.38.4 X Server 1.20.11 NVIDIA 465.31 4.6.0 OpenCL 3.0 CUDA 11.3.116 1.2.168 GCC 10.3.0 + CUDA 11.3 ext4 3840x2160 Processor Motherboard Chipset Memory Disk Graphics Audios Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution NVIDIA GPU Compute Benchmarks Performance System Logs - 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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/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-build-config=bootstrap-lto-lean --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 performance (Boost: Enabled) - CPU Microcode: 0xa201009 - RTX 3070 Ti: GPU Compute Cores: 6144 - RTX 3090: GPU Compute Cores: 10496 - RTX 3080: GPU Compute Cores: 8704 - RTX 2080: GPU Compute Cores: 2944 - RTX 3080 Ti: GPU Compute Cores: 10240 - RTX 2060 SUPER: GPU Compute Cores: 2176 - TITAN RTX: GPU Compute Cores: 4608 - RTX 3060: GPU Compute Cores: 3584 - RTX 3070: GPU Compute Cores: 5888 - RTX 3060 Ti: GPU Compute Cores: 4864 - RTX 2080 SUPER: GPU Compute Cores: 3072 - RTX 2070 SUPER: GPU Compute Cores: 2560 - RTX 2080 Ti: GPU Compute Cores: 4352 - RTX 2070: GPU Compute Cores: 2304 - Python 3.9.5 - 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
RTX 3070 Ti RTX 3090 RTX 3080 RTX 2080 RTX 3080 Ti RTX 2060 SUPER TITAN RTX RTX 3060 RTX 3070 RTX 3060 Ti RTX 2080 SUPER RTX 2070 SUPER RTX 2080 Ti RTX 2070 Result Overview Phoronix Test Suite 100% 176% 252% 328% 404% Blender Chaos Group V-RAY LuxCoreRender vkpeak clpeak Hashcat OctaneBench Mixbench LeelaChessZero RedShift Demo PlaidML IndigoBench SHOC Scalable HeterOgeneous Computing VkResample RealSR-NCNN ArrayFire ViennaCL cl-mem FAHBench Waifu2x-NCNN Vulkan NAMD CUDA
RTX 3070 Ti RTX 3090 RTX 3080 RTX 2080 RTX 3080 Ti RTX 2060 SUPER TITAN RTX RTX 3060 RTX 3070 RTX 3060 Ti RTX 2080 SUPER RTX 2070 SUPER RTX 2080 Ti RTX 2070 Per Watt Result Overview Phoronix Test Suite 100% 121% 141% 162% Chaos Group V-RAY ArrayFire Mixbench clpeak LuxCoreRender LeelaChessZero OctaneBench IndigoBench PlaidML FAHBench Hashcat SHOC Scalable HeterOgeneous Computing cl-mem P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M
NVIDIA GPU Compute Benchmarks blender: Barbershop - NVIDIA OptiX blender: Barbershop - CUDA lczero: OpenCL blender: Pabellon Barcelona - CUDA redshift: vkpeak: int16-vec4 vkpeak: int16-scalar vkpeak: int32-vec4 vkpeak: int32-scalar vkpeak: fp64-vec4 vkpeak: fp64-scalar vkpeak: fp16-vec4 vkpeak: fp16-scalar vkpeak: fp32-vec4 vkpeak: fp32-scalar octanebench: Total Score blender: Classroom - CUDA blender: Pabellon Barcelona - NVIDIA OptiX fahbench: v-ray: NVIDIA CUDA GPU blender: Fishy Cat - CUDA v-ray: NVIDIA RTX GPU blender: Classroom - NVIDIA OptiX luxcorerender: Danish Mood - GPU luxcorerender: LuxCore Benchmark - GPU luxcorerender: DLSC - GPU blender: Fishy Cat - NVIDIA OptiX luxcorerender: Orange Juice - GPU indigobench: OpenCL GPU - Bedroom indigobench: OpenCL GPU - Supercar realsr-ncnn: 4x - Yes blender: BMW27 - CUDA blender: BMW27 - NVIDIA OptiX clpeak: Double-Precision Double plaidml: No - Inference - VGG19 - OpenCL plaidml: No - Inference - VGG16 - OpenCL namd-cuda: ATPase Simulation - 327,506 Atoms arrayfire: BLAS OpenCL shoc: OpenCL - Texture Read Bandwidth viennacl: OpenCL BLAS - dGEMM-NN viennacl: OpenCL BLAS - dAXPY viennacl: OpenCL BLAS - sDOT viennacl: OpenCL BLAS - dCOPY viennacl: OpenCL BLAS - sAXPY viennacl: OpenCL BLAS - dGEMM-NT viennacl: OpenCL BLAS - dGEMV-N viennacl: OpenCL BLAS - sCOPY viennacl: OpenCL BLAS - dDOT viennacl: OpenCL BLAS - dGEMM-TN viennacl: OpenCL BLAS - dGEMV-T viennacl: OpenCL BLAS - dGEMM-TT vkresample: 2x - Single luxcorerender: Rainbow Colors and Prism - GPU realsr-ncnn: 4x - No plaidml: No - Inference - ResNet 50 - OpenCL hashcat: SHA-512 hashcat: SHA1 hashcat: MD5 betsy: ETC2 RGB - Highest hashcat: TrueCrypt RIPEMD160 + XTS cl-mem: Read cl-mem: Write cl-mem: Copy waifu2x-ncnn: 2x - 3 - Yes betsy: ETC1 - Highest shoc: OpenCL - GEMM SGEMM_N arrayfire: Conjugate Gradient OpenCL hashcat: 7-Zip clpeak: Integer Compute INT shoc: OpenCL - FFT SP clpeak: Single-Precision Float clpeak: Global Memory Bandwidth shoc: OpenCL - S3D shoc: OpenCL - MD5 Hash mixbench: NVIDIA CUDA - Single Precision mixbench: NVIDIA CUDA - Integer mixbench: NVIDIA CUDA - Double Precision mixbench: NVIDIA CUDA - Half Precision RTX 3070 Ti RTX 3090 RTX 3080 RTX 2080 RTX 3080 Ti RTX 2060 SUPER TITAN RTX RTX 3060 RTX 3070 RTX 3060 Ti RTX 2080 SUPER RTX 2070 SUPER RTX 2080 Ti RTX 2070 459.78 501.65 31739 184.76 201 10205.76 7730.75 11649.90 11695.96 367.88 366.91 23509.08 11727.92 15511.75 11707.87 454.496616 73.41 67.18 267.2819 1486 52.60 1982 44.18 6.03 7.41 8.71 34.17 8.67 13.733 38.947 40.564 27.80 17.09 368.71 160.06 202.76 0.12485 5805.75 2072.97 345 528 478 435 347 331 521 343 13.557 23.77 7.044 513.37 1916942857 13375128571 41477457143 5.736 512713 539.1 516.1 337.6 3.730 4.249 4710.76 1.668 720064 10957.10 1536.78 21524.49 528.73 286.107 26.2725 21337.83 10120.80 305.04 23025.87 345.19 373.69 40348 120.38 139 16881.76 13650.66 20597.70 20714.16 651.89 651.06 41672.10 20789.48 27527.94 20790.49 679.584181 51.28 44.12 344.9875 2099 34.40 2857 29.92 9.72 11.99 14.06 19.11 12.35 20.765 53.011 28.180 18.36 9.48 652.34 257.64 323.31 0.11988 8463.76 2219.90 600 723 607 498 602 365 657 598 9.302 34.27 5.517 816.85 3242516667 22828250000 69978700000 3.939 847886 825.7 745.5 363.0 3.235 3.012 8327.84 1.475 1153000 18051.59 2346.13 35210.03 813.57 429.599 44.1102 34169.74 16502.90 494.24 37668.36 407.33 442.84 37477 146.29 164 14570.68 11290.98 17024.27 17087.33 536.45 534.50 34278.04 17097.78 22809.11 17183.85 568.257212 60.87 52.80 321.3305 1785 41.41 2373 36.09 8.00 9.99 11.67 22.79 10.79 17.541 46.496 32.370 21.94 11.28 545.96 223.94 281.36 0.12099 7417.89 2210.17 499 629 367 555 480 501 241 356 601 498 377 501 11.268 28.20 6.036 730.16 2738585714 19257628571 58962414286 4.387 719975 672.8 646.2 354.7 3.366 3.317 6305.82 1.555 991970 15474.89 1918.51 29577.13 662.39 339.023 37.5181 29218.85 13956.21 421.88 31733.30 975.22 585.52 18660 354.5 338 9468.38 7123.95 10806.24 10862.12 341.36 338.65 21212.96 10871.18 10886.65 10901.17 260.458052 169.34 129.02 244.5184 780 96.86 959 86.74 3.71 4.69 5.15 50.15 5.58 7.742 24.881 59.556 51.52 29.08 345.81 129.95 164.37 0.13801 3346.88 1119.86 323 388 251 370 323 320 371 278 404 326 334 324 19.053 12.16 9.493 442.29 1696733333 12300142857 37998642857 6.873 452883 396.8 330.7 290.2 4.648 5.017 3350.00 2.074 642760 9079.54 1099.39 9258.58 369.30 197.206 24.0100 10803.63 10234.25 288.66 21586.18 358.78 386.72 39409 124.43 143 16203.01 12829.16 19408.56 19501.47 611.03 604.88 39163.48 19465.27 25895.83 19639.66 666.478575 52.64 45.88 335.0981 2049 35.46 2782 31.68 9.28 11.54 13.51 19.92 11.96 20.037 51.441 29.286 18.85 9.71 623.33 248.34 311.73 0.12066 8125.71 2167.41 559 705 363 592 490 560 231 356 645 557 368 560 9.561 33.25 5.635 789.35 3070157143 21660242857 65846485714 4.082 807600 804.8 733.2 355.0 3.283 3.084 8100.68 1.513 1097120 17317.31 2289.54 33723.34 794.55 419.328 41.8308 32644.68 15545.63 469.16 35590.07 1767.42 1083.28 14680 545.19 376 7201.01 5437.69 8206.71 8246.82 258.51 258.32 16219.42 8298.46 8311.48 8314.10 242.683228 299.30 183.31 207.9955 530 121.50 803 143.45 2.88 3.91 3.93 61.15 4.51 7.347 23.299 76.123 63.85 30.15 263.13 101.87 128.87 0.15502 2611.24 1110.73 247 388 255 369 327 243 374 277 401 247 326 22.327 14.13 11.642 378.75 1291485714 9398457143 28643142857 8.489 349900 396.8 333.0 288.2 5.322 6.139 3023.53 2.076 493227 7090.64 949.960 7122.60 368.68 188.783 18.3010 8225.59 7811.27 221.65 14480.23 907.46 551.44 29168 281.08 233 14765.38 11258.44 16941.28 17030.39 536.02 535.94 33598.08 17183.04 17203.15 17206.48 382.421153 152.70 97.57 307.5860 1006 69.46 1386 73.43 5.21 6.92 7.04 32.74 7.21 11.592 35.314 41.913 36.79 18.72 548.48 197.09 248.34 0.13304 4994.93 1168.30 496 542 316 495 403 493 462 305 531 486 372 495 13.560 16.83 7.337 652.41 2583083333 18687942857 56684485714 678875 567.8 494.7 319.3 3.855 5057.65 1.640 944400 13853.39 1578.37 14490.00 530.29 288.600 36.7519 15431.56 15399.95 425.45 28374.42 876.68 962.31 18675 316.30 300 5969.65 4488.85 6780.54 6809.18 213.53 213.55 13718.14 6836.83 9039.77 6818.80 293.779725 127.15 115.21 182.0035 852 84.55 1168 77.87 3.61 4.56 5.36 53.92 6.06 8.504 25.860 67.134 43.85 23.56 214.35 97.37 122.25 0.15471 3490.16 1255.28 205 327 289 315 306 222 275 329 204 303 23.135 15.36 10.362 340.13 1119700000 7762328571 24005014286 299913 318.0 302.2 270.0 4.850 2770.78 2.494 427609 6338.90 934.170 12561.56 315.44 172.083 15.1591 12815.83 5883.15 178.20 13379.48 466.42 507.79 29253 189.91 227 10070.32 7629.67 11492.63 11545.08 362.43 361.24 23200.57 11572.60 15292.85 11498.10 413.181789 76.05 72.98 267.0698 1417 54.13 1828 46.99 5.81 6.98 8.25 33.50 8.43 12.892 37.366 46.633 28.95 15.73 362.30 154.05 194.52 0.12611 5790.34 2131.07 341 397 327 371 358 339 222 280 399 340 334 17.549 23.45 7.815 495.68 1886685714 13145171429 40281500000 503188 393.2 380.4 294.9 4.035 3795.35 2.087 687591 10264.47 1135.09 20072.72 389.26 218.306 25.5521 21395.37 10033.78 302.02 22837.37 552.11 596.57 26639 218.45 237 8477.23 6403.14 9646.85 9700.50 305.19 304.87 19484.46 9720.67 12854.49 9684.39 384.178014 85.37 82.07 236.5058 1256 61.67 1658 53.66 4.91 6.04 7.19 39.24 7.61 11.451 34.006 50.635 31.82 17.42 303.92 133.75 168.99 0.12928 5040.87 2120.83 292 400 327 371 359 293 224 288 398 290 334 17.673 20.99 8.317 456.40 1589900000 11068742857 34158442857 427989 393.1 383.8 293.2 4.180 3432.76 2.083 587145 8378.39 1153.04 16021.63 388.87 211.717 21.6130 18247.61 8458.84 255.22 19243.59 913.26 555.03 20576 344.55 322 10383.04 7814.83 11765.09 11820.67 370.77 371.68 23328.09 11924.67 11917.03 11920.76 270.302147 160.42 123.53 261.5680 799 95.68 981 81.88 3.85 4.84 5.37 44.55 5.77 7.968 25.704 54.068 50.74 25.68 378.25 145.29 183.11 0.13522 3667.17 1168.27 353 427 251 405 330 349 389 288 441 354 356 350 17.516 12.15 8.880 472.09 1893616667 13596771429 41746057143 506217 437.5 347.0 301.7 4.395 3719.30 1.897 712650 10392.33 1203.71 10434.55 405.76 212.738 26.4571 11622.18 11161.70 314.85 23388.22 1011.95 595.81 17353 361.62 351 8534.72 6445.64 9705.63 9756.50 307.31 305.23 19106.95 9764.67 9791.33 9780.52 258.363708 174.29 130.76 227.9419 793 97.75 1008 90.56 3.58 4.53 4.97 51.39 5.44 7.648 24.451 64.220 51.85 25.90 305.27 120.83 152.36 0.14323 3017.86 1144.90 285 383 267 363 322 284 372 278 398 283 326 19.881 13.10 10.165 418.68 1535714286 11049914286 33955900000 412388 392.0 314.9 289.0 4.853 3269.42 2.089 580567 8446.24 1088.04 8456.17 363.95 199.717 21.3879 9668.05 9219.34 256.33 19471.03 899.59 548.91 27734 283.96 245 14076.57 10811.57 16279.27 16358.35 513.10 513.77 32202.58 16457.91 16487.61 16498.51 359.843904 152.39 98.64 305.3103 990 72.42 1324 73.30 5.01 6.51 6.83 33.92 7.10 11.031 33.352 44.225 38.49 19.24 522.31 187.25 235.75 0.13324 4821.38 1180.65 470 518 319 477 405 467 460 306 519 476 376 468 14.781 15.28 7.629 638.39 2460566667 17815328571 54074357143 644813 545.6 447.0 322.8 3.872 4835.13 1.677 892410 13127.46 1483.30 13781.33 507.08 271.247 34.9652 14851.91 14731.97 409.05 28438.06 1819.25 1113.49 14730 556.43 374 7362.19 5530.45 8319.68 8365.01 262.86 262.90 16496.22 8439.95 8451.07 8449.25 242.942045 308.70 186.12 205.3082 519 122.65 785 146.54 2.81 3.91 3.89 60.40 4.48 7.409 23.440 74.975 64.83 30.39 267.89 104.17 131.82 0.15247 2680.12 1081.44 252 388 257 367 322 251 369 268 400 249 320 22.297 13.26 11.493 380.72 1314657143 9571242857 29405171429 355538 396.8 324.0 284.6 5.305 3112.87 2.091 500673 7155.07 954.251 7244.69 369.26 192.706 18.6702 8377.73 7995.96 226.32 14636.77 OpenBenchmarking.org
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: NVIDIA OptiX RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 400 800 1200 1600 2000 SE +/- 0.26, N = 3 SE +/- 0.69, N = 3 SE +/- 1.83, N = 3 SE +/- 1.18, N = 3 SE +/- 0.26, N = 3 SE +/- 0.33, N = 3 SE +/- 0.51, N = 3 SE +/- 3.15, N = 3 SE +/- 0.20, N = 3 SE +/- 0.34, N = 3 SE +/- 3.68, N = 3 SE +/- 0.86, N = 3 SE +/- 0.77, N = 3 SE +/- 0.30, N = 3 1819.25 899.59 1011.95 913.26 552.11 466.42 876.68 907.46 1767.42 358.78 975.22 407.33 345.19 459.78 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 8.6 / Avg: 103.18 / Max: 108.29 Min: 8.26 / Avg: 180.06 / Max: 189.24 Min: 24.6 / Avg: 132.13 / Max: 141.09 Min: 10.09 / Avg: 134.05 / Max: 141.11 Min: 21.52 / Avg: 148.27 / Max: 156.85 Min: 17.08 / Avg: 163.31 / Max: 173.64 Min: 16.91 / Avg: 103.34 / Max: 108.8 Min: 13.06 / Avg: 192.45 / Max: 201.47 Min: 10.3 / Avg: 107.39 / Max: 112.83 Min: 28.55 / Avg: 290.17 / Max: 310.01 Min: 16.31 / Avg: 145.11 / Max: 152.06 Min: 28.56 / Avg: 243.51 / Max: 259.1 Min: 20.69 / Avg: 290.77 / Max: 311.99 Min: 24.62 / Avg: 197.89 / Max: 211.93
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CUDA RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 200 400 600 800 1000 SE +/- 0.11, N = 3 SE +/- 0.25, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.31, N = 3 SE +/- 0.24, N = 3 SE +/- 0.24, N = 3 SE +/- 0.26, N = 3 SE +/- 0.20, N = 3 SE +/- 0.21, N = 3 SE +/- 0.19, N = 3 SE +/- 0.45, N = 3 SE +/- 0.32, N = 3 SE +/- 0.27, N = 3 1113.49 548.91 595.81 555.03 596.57 507.79 962.31 551.44 1083.28 386.72 585.52 442.84 373.69 501.65 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 8.78 / Avg: 103.9 / Max: 109.61 Min: 9.19 / Avg: 179.2 / Max: 194.41 Min: 24.44 / Avg: 134.19 / Max: 145.4 Min: 10.23 / Avg: 133.98 / Max: 144.76 Min: 21.62 / Avg: 150.06 / Max: 161.36 Min: 16.8 / Avg: 164.67 / Max: 178.62 Min: 17.1 / Avg: 104.47 / Max: 111.33 Min: 14.03 / Avg: 191.75 / Max: 206.02 Min: 10.39 / Avg: 108.28 / Max: 115.49 Min: 37.44 / Avg: 293.85 / Max: 324.79 Min: 16.91 / Avg: 145.54 / Max: 154.79 Min: 21.12 / Avg: 244.54 / Max: 269.54 Min: 27.64 / Avg: 292.98 / Max: 325.06 Min: 24.8 / Avg: 198.1 / Max: 214.52
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: OpenCL RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 9K 18K 27K 36K 45K SE +/- 32.62, N = 3 SE +/- 103.74, N = 3 SE +/- 217.96, N = 3 SE +/- 110.32, N = 3 SE +/- 77.49, N = 3 SE +/- 168.57, N = 3 SE +/- 110.08, N = 3 SE +/- 46.38, N = 3 SE +/- 72.46, N = 3 SE +/- 106.84, N = 3 SE +/- 29.46, N = 3 SE +/- 186.45, N = 3 SE +/- 52.75, N = 3 SE +/- 101.51, N = 3 14730 27734 17353 20576 26639 29253 18675 29168 14680 39409 18660 37477 40348 31739 1. (CXX) g++ options: -flto -pthread Nodes Per Second Per Watt
OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.26 Backend: OpenCL RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 30 60 90 120 150 87.93 110.96 92.34 102.86 138.97 138.85 120.65 109.66 87.36 121.76 96.28 124.12 122.61 127.97 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.26 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 10.12 / Avg: 167.51 / Max: 179.89 Min: 8.3 / Avg: 249.95 / Max: 268.12 Min: 24.04 / Avg: 187.92 / Max: 207.89 Min: 10.27 / Avg: 200.04 / Max: 227.41 Min: 21.27 / Avg: 191.69 / Max: 199 Min: 17.34 / Avg: 210.69 / Max: 219.68 Min: 17.05 / Avg: 154.79 / Max: 169.54 Min: 12.85 / Avg: 265.99 / Max: 287.24 Min: 10.43 / Avg: 168.04 / Max: 179.55 Min: 35.82 / Avg: 323.67 / Max: 348.45 Min: 16.9 / Avg: 193.81 / Max: 219.34 Min: 27.92 / Avg: 301.95 / Max: 319.38 Min: 29.54 / Avg: 329.07 / Max: 348.03 Min: 24.6 / Avg: 248.03 / Max: 286.46
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: CUDA RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 120 240 360 480 600 SE +/- 0.25, N = 3 SE +/- 0.02, N = 3 SE +/- 0.34, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 556.43 283.96 361.62 344.55 218.45 189.91 316.30 281.08 545.19 124.43 354.50 146.29 120.38 184.76 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.68 / Avg: 125.85 / Max: 157.74 Min: 8.84 / Avg: 225.45 / Max: 257.46 Min: 24.44 / Avg: 157.27 / Max: 169.59 Min: 10.11 / Avg: 161.22 / Max: 172.26 Min: 21.73 / Avg: 181.6 / Max: 192.03 Min: 17.09 / Avg: 199.52 / Max: 212.11 Min: 17.16 / Avg: 130.81 / Max: 136.85 Min: 14.5 / Avg: 231.41 / Max: 270.34 Min: 10.34 / Avg: 129.67 / Max: 160.48 Min: 33.26 / Avg: 333.56 / Max: 349.86 Min: 17.35 / Avg: 168.7 / Max: 179.57 Min: 16.96 / Avg: 300.63 / Max: 316.92 Min: 25.03 / Avg: 331.88 / Max: 348.73 Min: 25.19 / Avg: 240.72 / Max: 255.61
RedShift Demo This is a test of MAXON's RedShift demo build that currently requires NVIDIA GPU acceleration. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better RedShift Demo 3.0 RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 80 160 240 320 400 SE +/- 1.33, N = 3 SE +/- 1.20, N = 3 SE +/- 1.67, N = 3 SE +/- 1.20, N = 3 SE +/- 0.88, N = 3 SE +/- 1.00, N = 3 SE +/- 1.20, N = 3 SE +/- 0.88, N = 3 SE +/- 0.88, N = 3 SE +/- 0.67, N = 3 SE +/- 0.88, N = 3 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 374 245 351 322 237 227 300 233 376 143 338 164 139 201 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better RedShift Demo 3.0 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.82 / Avg: 135.21 / Max: 146.97 Min: 8.38 / Avg: 217.18 / Max: 239.98 Min: 24.3 / Avg: 144.26 / Max: 158.74 Min: 10 / Avg: 147.76 / Max: 162.3 Min: 21.08 / Avg: 154 / Max: 165.39 Min: 16.48 / Avg: 162.56 / Max: 174.82 Min: 17.35 / Avg: 118.42 / Max: 124.88 Min: 11.19 / Avg: 225.44 / Max: 251.14 Min: 10.31 / Avg: 139.21 / Max: 151.91 Min: 32.17 / Avg: 310.27 / Max: 336.9 Min: 17.09 / Avg: 158.84 / Max: 173.62 Min: 16.9 / Avg: 274.12 / Max: 301.76 Min: 17.4 / Avg: 311.99 / Max: 338.69 Min: 22.72 / Avg: 211.52 / Max: 232.23
vkpeak Vkpeak is a Vulkan compute benchmark inspired by OpenCL's clpeak. Vkpeak provides Vulkan compute performance measurements for FP16 / FP32 / FP64 / INT16 / INT32 scalar and vec4 performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-vec4 RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 4K 8K 12K 16K 20K SE +/- 0.29, N = 3 SE +/- 14.70, N = 3 SE +/- 21.85, N = 3 SE +/- 0.06, N = 3 SE +/- 11.39, N = 3 SE +/- 0.82, N = 3 SE +/- 7.82, N = 3 SE +/- 5.90, N = 3 SE +/- 14.82, N = 3 SE +/- 4.40, N = 3 SE +/- 1.82, N = 3 SE +/- 0.42, N = 3 SE +/- 4.03, N = 3 SE +/- 0.81, N = 3 7362.19 14076.57 8534.72 10383.04 8477.23 10070.32 5969.65 14765.38 7201.01 16203.01 9468.38 14570.68 16881.76 10205.76 GIOPS Per Watt
OpenBenchmarking.org GIOPS Per Watt, More Is Better vkpeak 20210424 int16-vec4 RTX 2080 Ti RTX 2070 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 20 40 60 80 100 70.52 67.67 76.94 82.37 69.91 69.42 57.23 60.24 64.33 66.97 63.68 63.67 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better vkpeak 20210424 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 50 100 150 200 250 Min: 8.79 / Avg: 119.33 / Max: 160.63 Min: 7.02 / Avg: 199.62 / Max: 265.18 Min: 24.2 / Avg: 126.12 / Max: 176.14 Min: 9.79 / Avg: 140.53 / Max: 200.69 Min: 20.31 / Avg: 110.18 / Max: 153.31 Min: 16.97 / Avg: 122.25 / Max: 176.97 Min: 17.22 / Avg: 85.39 / Max: 108.64 Min: 10.59 / Avg: 212.69 / Max: 285.13 Min: 10.28 / Avg: 125.83 / Max: 161.95 Min: 25.9 / Avg: 268.96 / Max: 304.21 Min: 15.72 / Avg: 147.18 / Max: 200.91 Min: 18.02 / Avg: 217.56 / Max: 259.06 Min: 25.05 / Avg: 265.11 / Max: 303.36 Min: 22.36 / Avg: 160.29 / Max: 216.47
OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-scalar RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 3K 6K 9K 12K 15K SE +/- 0.15, N = 3 SE +/- 27.43, N = 3 SE +/- 0.30, N = 3 SE +/- 20.31, N = 3 SE +/- 3.46, N = 3 SE +/- 0.14, N = 3 SE +/- 5.77, N = 3 SE +/- 27.84, N = 3 SE +/- 0.09, N = 3 SE +/- 20.56, N = 3 SE +/- 0.36, N = 3 SE +/- 1.14, N = 3 SE +/- 1.11, N = 3 SE +/- 0.05, N = 3 5530.45 10811.57 6445.64 7814.83 6403.14 7629.67 4488.85 11258.44 5437.69 12829.16 7123.95 11290.98 13650.66 7730.75
OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-vec4 RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 4K 8K 12K 16K 20K SE +/- 0.63, N = 3 SE +/- 45.18, N = 3 SE +/- 8.84, N = 3 SE +/- 30.69, N = 3 SE +/- 4.72, N = 3 SE +/- 1.00, N = 3 SE +/- 0.54, N = 3 SE +/- 46.17, N = 3 SE +/- 20.82, N = 3 SE +/- 0.25, N = 3 SE +/- 0.27, N = 3 SE +/- 0.02, N = 3 SE +/- 2.62, N = 3 SE +/- 1.12, N = 3 8319.68 16279.27 9705.63 11765.09 9646.85 11492.63 6780.54 16941.28 8206.71 19408.56 10806.24 17024.27 20597.70 11649.90
OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-scalar RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 4K 8K 12K 16K 20K SE +/- 0.21, N = 3 SE +/- 43.31, N = 3 SE +/- 8.24, N = 3 SE +/- 30.36, N = 3 SE +/- 8.15, N = 3 SE +/- 0.75, N = 3 SE +/- 0.77, N = 3 SE +/- 44.08, N = 3 SE +/- 21.65, N = 3 SE +/- 0.24, N = 3 SE +/- 1.08, N = 3 SE +/- 1.14, N = 3 SE +/- 26.66, N = 3 SE +/- 0.71, N = 3 8365.01 16358.35 9756.50 11820.67 9700.50 11545.08 6809.18 17030.39 8246.82 19501.47 10862.12 17087.33 20714.16 11695.96
Result
OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-vec4 RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 140 280 420 560 700 SE +/- 0.06, N = 2 SE +/- 1.31, N = 3 SE +/- 0.50, N = 3 SE +/- 0.00, N = 2 SE +/- 0.31, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 1.43, N = 3 SE +/- 0.65, N = 3 SE +/- 0.61, N = 3 SE +/- 0.01, N = 3 SE +/- 0.35, N = 3 SE +/- 0.79, N = 3 SE +/- 0.01, N = 3 262.86 513.10 307.31 370.77 305.19 362.43 213.53 536.02 258.51 611.03 341.36 536.45 651.89 367.88 GFLOPS Per Watt
OpenBenchmarking.org GFLOPS Per Watt, More Is Better vkpeak 20210424 fp64-vec4 RTX 2070 RTX 2080 SUPER 0.5936 1.1872 1.7808 2.3744 2.968 2.203 2.638
OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-scalar RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 140 280 420 560 700 SE +/- 0.03, N = 3 SE +/- 1.54, N = 3 SE +/- 0.79, N = 3 SE +/- 0.95, N = 3 SE +/- 0.01, N = 3 SE +/- 0.34, N = 3 SE +/- 0.01, N = 3 SE +/- 1.43, N = 3 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 1.32, N = 3 SE +/- 1.37, N = 3 SE +/- 0.95, N = 3 262.90 513.77 305.23 371.68 304.87 361.24 213.55 535.94 258.32 604.88 338.65 534.50 651.06 366.91
OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-vec4 RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 9K 18K 27K 36K 45K SE +/- 45.05, N = 3 SE +/- 86.26, N = 3 SE +/- 64.46, N = 3 SE +/- 118.62, N = 3 SE +/- 49.62, N = 3 SE +/- 88.97, N = 3 SE +/- 0.44, N = 3 SE +/- 148.11, N = 3 SE +/- 40.81, N = 3 SE +/- 51.02, N = 3 SE +/- 0.93, N = 3 SE +/- 88.40, N = 3 SE +/- 91.14, N = 3 SE +/- 114.74, N = 3 16496.22 32202.58 19106.95 23328.09 19484.46 23200.57 13718.14 33598.08 16219.42 39163.48 21212.96 34278.04 41672.10 23509.08
OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-scalar RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 4K 8K 12K 16K 20K SE +/- 22.92, N = 3 SE +/- 43.12, N = 3 SE +/- 32.23, N = 3 SE +/- 60.69, N = 3 SE +/- 25.27, N = 3 SE +/- 43.84, N = 3 SE +/- 9.15, N = 3 SE +/- 92.50, N = 3 SE +/- 21.01, N = 3 SE +/- 30.73, N = 3 SE +/- 29.14, N = 3 SE +/- 43.04, N = 3 SE +/- 80.41, N = 3 SE +/- 57.85, N = 3 8439.95 16457.91 9764.67 11924.67 9720.67 11572.60 6836.83 17183.04 8298.46 19465.27 10871.18 17097.78 20789.48 11727.92
OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-vec4 RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 6K 12K 18K 24K 30K SE +/- 46.44, N = 3 SE +/- 79.54, N = 3 SE +/- 43.80, N = 3 SE +/- 60.73, N = 3 SE +/- 31.64, N = 3 SE +/- 58.84, N = 3 SE +/- 12.40, N = 3 SE +/- 134.86, N = 3 SE +/- 42.90, N = 3 SE +/- 108.44, N = 3 SE +/- 59.30, N = 3 SE +/- 75.50, N = 3 SE +/- 137.76, N = 3 SE +/- 78.89, N = 3 8451.07 16487.61 9791.33 11917.03 12854.49 15292.85 9039.77 17203.15 8311.48 25895.83 10886.65 22809.11 27527.94 15511.75
OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-scalar RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 4K 8K 12K 16K 20K SE +/- 56.83, N = 3 SE +/- 114.67, N = 3 SE +/- 43.99, N = 3 SE +/- 53.05, N = 3 SE +/- 13.93, N = 3 SE +/- 7.52, N = 3 SE +/- 0.24, N = 3 SE +/- 155.55, N = 3 SE +/- 61.71, N = 3 SE +/- 104.27, N = 3 SE +/- 88.42, N = 3 SE +/- 74.66, N = 3 SE +/- 65.40, N = 3 SE +/- 49.99, N = 3 8449.25 16498.51 9780.52 11920.76 9684.39 11498.10 6818.80 17206.48 8314.10 19639.66 10901.17 17183.85 20790.49 11707.87
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: CUDA RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 70 140 210 280 350 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.41, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.18, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.20, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 308.70 152.39 174.29 160.42 85.37 76.05 127.15 152.70 299.30 52.64 169.34 60.87 51.28 73.41 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.33 / Avg: 115.78 / Max: 121.1 Min: 7.75 / Avg: 209.81 / Max: 224.82 Min: 24.55 / Avg: 151.84 / Max: 160.94 Min: 10.06 / Avg: 157.38 / Max: 168.43 Min: 21.35 / Avg: 184.95 / Max: 197.87 Min: 17.28 / Avg: 200.86 / Max: 218.8 Min: 16.86 / Avg: 132.6 / Max: 141.31 Min: 14.19 / Avg: 213.21 / Max: 226.82 Min: 10.26 / Avg: 123.98 / Max: 129.78 Min: 27.85 / Avg: 323.56 / Max: 349.68 Min: 17.59 / Avg: 165.36 / Max: 174.21 Min: 25.45 / Avg: 297.31 / Max: 319.29 Min: 26.86 / Avg: 321.23 / Max: 349.09 Min: 24.89 / Avg: 249.09 / Max: 272.37
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 40 80 120 160 200 SE +/- 0.54, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.57, N = 3 SE +/- 0.03, N = 3 SE +/- 0.14, N = 3 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 186.12 98.64 130.76 123.53 82.07 72.98 115.21 97.57 183.31 45.88 129.02 52.80 44.12 67.18 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.2 / Avg: 119.7 / Max: 137.34 Min: 8.98 / Avg: 207.51 / Max: 231.58 Min: 25.11 / Avg: 145.37 / Max: 154.47 Min: 10.2 / Avg: 140.78 / Max: 148.97 Min: 21.8 / Avg: 153.85 / Max: 166.56 Min: 17.23 / Avg: 164.56 / Max: 178.72 Min: 17.06 / Avg: 113.57 / Max: 122.88 Min: 14.71 / Avg: 212.26 / Max: 236.13 Min: 10.39 / Avg: 124.32 / Max: 143.65 Min: 30.24 / Avg: 305.06 / Max: 341.15 Min: 17.18 / Avg: 153.14 / Max: 162.13 Min: 25.13 / Avg: 271.11 / Max: 312.14 Min: 33.72 / Avg: 311.84 / Max: 348.97 Min: 25.5 / Avg: 213.47 / Max: 237.33
FAHBench FAHBench is a Folding@Home benchmark on the GPU. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 70 140 210 280 350 SE +/- 0.59, N = 3 SE +/- 0.75, N = 3 SE +/- 0.18, N = 3 SE +/- 0.45, N = 3 SE +/- 0.27, N = 3 SE +/- 0.47, N = 3 SE +/- 0.16, N = 3 SE +/- 0.59, N = 3 SE +/- 0.40, N = 3 SE +/- 0.79, N = 3 SE +/- 0.35, N = 3 SE +/- 0.26, N = 3 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 205.31 305.31 227.94 261.57 236.51 267.07 182.00 307.59 208.00 335.10 244.52 321.33 344.99 267.28 Ns Per Day Per Watt
OpenBenchmarking.org Ns Per Day Per Watt, More Is Better FAHBench 2.3.2 RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.506 1.012 1.518 2.024 2.53 1.889 1.901 1.930 2.030 2.157 2.249 2.120 1.838 1.875 1.583 1.844 1.702 1.692 1.726 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better FAHBench 2.3.2 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 50 100 150 200 250 Min: 8.46 / Avg: 108.71 / Max: 151.8 Min: 6.32 / Avg: 160.64 / Max: 233.85 Min: 24.43 / Avg: 118.11 / Max: 164.45 Min: 9.93 / Avg: 128.84 / Max: 181.24 Min: 12.8 / Avg: 109.67 / Max: 151.59 Min: 8.52 / Avg: 118.73 / Max: 166.13 Min: 17.19 / Avg: 85.85 / Max: 115.67 Min: 11 / Avg: 167.33 / Max: 233.27 Min: 10.05 / Avg: 110.92 / Max: 157.88 Min: 24.45 / Avg: 211.73 / Max: 281.86 Min: 16.45 / Avg: 132.61 / Max: 190.56 Min: 19.96 / Avg: 188.85 / Max: 256.08 Min: 22.04 / Avg: 203.85 / Max: 272.71 Min: 23.55 / Avg: 154.86 / Max: 204.51
Chaos Group V-RAY This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org vpaths, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA CUDA GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 500 1000 1500 2000 2500 SE +/- 1.15, N = 3 SE +/- 0.58, N = 3 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 2.03, N = 3 SE +/- 0.88, N = 3 SE +/- 1.33, N = 3 519 990 793 799 1256 1417 852 1006 530 2049 780 1785 2099 1486 vpaths Per Watt
OpenBenchmarking.org vpaths Per Watt, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA CUDA GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 3 6 9 12 15 5.132 5.814 6.245 6.576 9.150 9.532 8.570 5.573 5.066 7.419 6.097 7.386 7.611 7.965 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Chaos Group V-RAY 5 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 8.79 / Avg: 101.13 / Max: 139.35 Min: 8.7 / Avg: 170.27 / Max: 226.79 Min: 23.92 / Avg: 126.99 / Max: 163.91 Min: 10.21 / Avg: 121.5 / Max: 158.56 Min: 21.38 / Avg: 137.27 / Max: 170.88 Min: 16.73 / Avg: 148.65 / Max: 187.54 Min: 17.03 / Avg: 99.42 / Max: 122.95 Min: 12.82 / Avg: 180.51 / Max: 237.2 Min: 10.37 / Avg: 104.63 / Max: 141.46 Min: 29.77 / Avg: 276.19 / Max: 342.2 Min: 16.37 / Avg: 127.94 / Max: 170.08 Min: 17.4 / Avg: 241.67 / Max: 307.18 Min: 22.88 / Avg: 275.78 / Max: 345.85 Min: 24.82 / Avg: 186.57 / Max: 238.65
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: CUDA RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 30 60 90 120 150 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.18, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 122.65 72.42 97.75 95.68 61.67 54.13 84.55 69.46 121.50 35.46 96.86 41.41 34.40 52.60 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.23 / Avg: 137.65 / Max: 178.91 Min: 8.31 / Avg: 217.14 / Max: 262.1 Min: 24.62 / Avg: 159.89 / Max: 197.49 Min: 10.52 / Avg: 160.52 / Max: 195.74 Min: 21.86 / Avg: 168.89 / Max: 198.22 Min: 16.9 / Avg: 180.28 / Max: 219.08 Min: 16.83 / Avg: 129.69 / Max: 159 Min: 15.26 / Avg: 231.72 / Max: 282.19 Min: 10.45 / Avg: 140.32 / Max: 178.96 Min: 28.9 / Avg: 287.09 / Max: 349.6 Min: 17.6 / Avg: 168.43 / Max: 205.3 Min: 17.59 / Avg: 264.25 / Max: 319.99 Min: 26.94 / Avg: 284.46 / Max: 348.56 Min: 25.49 / Avg: 226.37 / Max: 284.57
Chaos Group V-RAY This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org vrays, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA RTX GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 600 1200 1800 2400 3000 SE +/- 0.67, N = 3 SE +/- 1.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 1.76, N = 3 SE +/- 1.76, N = 3 SE +/- 0.88, N = 3 SE +/- 3.48, N = 3 SE +/- 0.67, N = 3 SE +/- 3.00, N = 3 SE +/- 9.02, N = 3 785 1324 1008 981 1658 1828 1168 1386 803 2782 959 2373 2857 1982 vrays Per Watt
OpenBenchmarking.org vrays Per Watt, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA RTX GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 4 8 12 16 20 7.947 8.144 8.493 8.834 13.136 13.682 12.497 8.018 7.727 10.393 9.002 10.538 10.428 12.420 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Chaos Group V-RAY 5 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 8.77 / Avg: 98.78 / Max: 128.98 Min: 8.19 / Avg: 162.56 / Max: 207.78 Min: 23.36 / Avg: 118.68 / Max: 146.56 Min: 9.92 / Avg: 111.04 / Max: 137.53 Min: 21.38 / Avg: 126.22 / Max: 157.61 Min: 16.82 / Avg: 133.6 / Max: 167.66 Min: 17.01 / Avg: 93.46 / Max: 115.93 Min: 13.09 / Avg: 172.87 / Max: 217.23 Min: 10.3 / Avg: 103.92 / Max: 134.35 Min: 30.65 / Avg: 267.68 / Max: 332.62 Min: 15.12 / Avg: 106.53 / Max: 147.88 Min: 18.6 / Avg: 225.19 / Max: 282.91 Min: 20.13 / Avg: 273.98 / Max: 348.06 Min: 23.53 / Avg: 159.58 / Max: 222.4
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: NVIDIA OptiX RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 30 60 90 120 150 SE +/- 0.63, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.16, N = 3 SE +/- 0.27, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.23, N = 3 SE +/- 0.31, N = 3 SE +/- 0.22, N = 3 146.54 73.30 90.56 81.88 53.66 46.99 77.87 73.43 143.45 31.68 86.74 36.09 29.92 44.18 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.01 / Avg: 117.03 / Max: 123.34 Min: 8.56 / Avg: 209.36 / Max: 227.21 Min: 24.57 / Avg: 150.75 / Max: 161.88 Min: 10.36 / Avg: 154.11 / Max: 166.8 Min: 22.06 / Avg: 165.1 / Max: 183.3 Min: 17.34 / Avg: 179.62 / Max: 201.42 Min: 17.41 / Avg: 119.16 / Max: 128.49 Min: 15.06 / Avg: 212.4 / Max: 229.15 Min: 10.32 / Avg: 126.03 / Max: 132.64 Min: 26.98 / Avg: 307.46 / Max: 348.97 Min: 16.99 / Avg: 160.86 / Max: 172.59 Min: 19.08 / Avg: 282.07 / Max: 318.86 Min: 26.49 / Avg: 306.86 / Max: 348.89 Min: 25.65 / Avg: 225.61 / Max: 255.39
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 6 SE +/- 0.05, N = 3 SE +/- 0.03, N = 4 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 2.81 5.01 3.58 3.85 4.91 5.81 3.61 5.21 2.88 9.28 3.71 8.00 9.72 6.03 MIN: 0.88 / MAX: 3.32 MIN: 1.68 / MAX: 6.06 MIN: 1.17 / MAX: 4.31 MIN: 1.19 / MAX: 4.64 MIN: 1.66 / MAX: 5.96 MIN: 1.82 / MAX: 7.01 MIN: 1.15 / MAX: 4.3 MIN: 1.69 / MAX: 6.28 MIN: 0.92 / MAX: 3.41 MIN: 2.69 / MAX: 11.32 MIN: 1.18 / MAX: 4.47 MIN: 2.38 / MAX: 9.7 MIN: 3.01 / MAX: 11.82 MIN: 2.03 / MAX: 7.29 M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.0101 0.0202 0.0303 0.0404 0.0505 0.028 0.029 0.030 0.032 0.042 0.045 0.041 0.029 0.027 0.036 0.029 0.038 0.038 0.037 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.5 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 50 100 150 200 250 Min: 8.99 / Avg: 99.54 / Max: 124.48 Min: 8.1 / Avg: 172.01 / Max: 208.66 Min: 24.47 / Avg: 117.81 / Max: 140.65 Min: 10.35 / Avg: 119.64 / Max: 142.3 Min: 15.12 / Avg: 118.17 / Max: 138.72 Min: 8.65 / Avg: 127.99 / Max: 150.55 Min: 17.03 / Avg: 88.21 / Max: 103.89 Min: 15.72 / Avg: 182.81 / Max: 218.35 Min: 10.33 / Avg: 105.19 / Max: 126.6 Min: 34.51 / Avg: 257.71 / Max: 300.92 Min: 17.62 / Avg: 129.45 / Max: 152.4 Min: 17.86 / Avg: 212.92 / Max: 251.26 Min: 17.62 / Avg: 254.47 / Max: 299.34 Min: 25.12 / Avg: 164.19 / Max: 188.82
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: LuxCore Benchmark - Acceleration: GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 3.91 6.51 4.53 4.84 6.04 6.98 4.56 6.92 3.91 11.54 4.69 9.99 11.99 7.41 MIN: 1.41 / MAX: 4.63 MIN: 1.93 / MAX: 7.74 MIN: 1.3 / MAX: 5.39 MIN: 1.66 / MAX: 5.75 MIN: 1.87 / MAX: 7.15 MIN: 2.27 / MAX: 8.27 MIN: 1.64 / MAX: 5.37 MIN: 2.23 / MAX: 8.19 MIN: 1.4 / MAX: 4.62 MIN: 3.63 / MAX: 13.73 MIN: 1.66 / MAX: 5.58 MIN: 3.32 / MAX: 11.84 MIN: 3.93 / MAX: 14.25 MIN: 2.28 / MAX: 8.81 M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.5 Scene: LuxCore Benchmark - Acceleration: GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.0135 0.027 0.0405 0.054 0.0675 0.036 0.036 0.037 0.039 0.049 0.052 0.049 0.036 0.035 0.043 0.047 0.044 0.045 0.060 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.5 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.16 / Avg: 107.81 / Max: 127.77 Min: 7.69 / Avg: 181.15 / Max: 213.79 Min: 24.32 / Avg: 123.31 / Max: 141.92 Min: 10.25 / Avg: 123.24 / Max: 144.98 Min: 14.44 / Avg: 123.59 / Max: 143.47 Min: 8.83 / Avg: 133.01 / Max: 154.89 Min: 16.91 / Avg: 92.95 / Max: 107.13 Min: 13.92 / Avg: 193.81 / Max: 230.16 Min: 10.29 / Avg: 111.76 / Max: 130.68 Min: 29.91 / Avg: 270.42 / Max: 312.45 Min: 15.06 / Avg: 99.05 / Max: 156.24 Min: 27.61 / Avg: 225.09 / Max: 259.13 Min: 22.13 / Avg: 268.96 / Max: 311.28 Min: 22.55 / Avg: 123.28 / Max: 193.74
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: DLSC - Acceleration: GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 3.89 6.83 4.97 5.37 7.19 8.25 5.36 7.04 3.93 13.51 5.15 11.67 14.06 8.71 MIN: 3.78 / MAX: 4.04 MIN: 6.56 / MAX: 6.93 MIN: 4.86 / MAX: 5.09 MIN: 5.07 / MAX: 5.51 MIN: 6.89 / MAX: 7.44 MIN: 8.13 / MAX: 8.41 MIN: 5.23 / MAX: 5.58 MIN: 6.59 / MAX: 7.3 MIN: 3.81 / MAX: 4.12 MIN: 12.39 / MAX: 13.74 MIN: 5.03 / MAX: 5.33 MIN: 11.22 / MAX: 11.86 MIN: 13.57 / MAX: 14.34 MIN: 8.19 / MAX: 8.87 M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.5 Scene: DLSC - Acceleration: GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.0142 0.0284 0.0426 0.0568 0.071 0.033 0.034 0.037 0.038 0.051 0.054 0.052 0.033 0.032 0.043 0.046 0.045 0.046 0.063 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.5 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.27 / Avg: 116.55 / Max: 126.75 Min: 9.58 / Avg: 201.96 / Max: 220.18 Min: 24.66 / Avg: 136.16 / Max: 147.06 Min: 10.52 / Avg: 141.04 / Max: 152.35 Min: 15.16 / Avg: 141.21 / Max: 152.45 Min: 9.3 / Avg: 153.42 / Max: 165.84 Min: 17.28 / Avg: 103.82 / Max: 112.34 Min: 15.27 / Avg: 210.39 / Max: 229.52 Min: 10.34 / Avg: 123.07 / Max: 133.26 Min: 34.51 / Avg: 313.62 / Max: 337.89 Min: 15.09 / Avg: 111.34 / Max: 161.81 Min: 19.96 / Avg: 257.71 / Max: 277.65 Min: 32.4 / Avg: 304.34 / Max: 328.84 Min: 23.02 / Avg: 139.13 / Max: 203.93
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: NVIDIA OptiX RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 14 28 42 56 70 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 2.59, N = 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 2.61, N = 15 60.40 33.92 51.39 44.55 39.24 33.50 53.92 32.74 61.15 19.92 50.15 22.79 19.11 34.17 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 10 / Avg: 125.67 / Max: 155.6 Min: 8.16 / Avg: 202.73 / Max: 243.84 Min: 24.72 / Avg: 140.97 / Max: 162.16 Min: 10.41 / Avg: 144.65 / Max: 169.7 Min: 21.91 / Avg: 136.65 / Max: 159.99 Min: 17.07 / Avg: 147.73 / Max: 173.35 Min: 17.14 / Avg: 103.57 / Max: 119.03 Min: 15 / Avg: 212.46 / Max: 258.65 Min: 10.34 / Avg: 129.04 / Max: 158.68 Min: 29.36 / Avg: 270.38 / Max: 347.64 Min: 15.34 / Avg: 148.27 / Max: 176.33 Min: 20.45 / Avg: 236.88 / Max: 305.42 Min: 20.62 / Avg: 268.35 / Max: 346.86 Min: 23.57 / Avg: 177.5 / Max: 228.71
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Orange Juice - Acceleration: GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 4.48 7.10 5.44 5.77 7.61 8.43 6.06 7.21 4.51 11.96 5.58 10.79 12.35 8.67 MIN: 3.75 / MAX: 4.81 MIN: 5.6 / MAX: 8.83 MIN: 4.44 / MAX: 6.12 MIN: 4.67 / MAX: 6.58 MIN: 6.03 / MAX: 9.24 MIN: 6.69 / MAX: 10.55 MIN: 4.73 / MAX: 7.39 MIN: 5.68 / MAX: 9.07 MIN: 3.75 / MAX: 4.99 MIN: 9.91 / MAX: 16.43 MIN: 4.54 / MAX: 6.31 MIN: 8.72 / MAX: 14.46 MIN: 10.23 / MAX: 17.13 MIN: 6.96 / MAX: 10.98 M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.5 Scene: Orange Juice - Acceleration: GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.0135 0.027 0.0405 0.054 0.0675 0.041 0.037 0.042 0.044 0.055 0.057 0.060 0.036 0.039 0.041 0.039 0.045 0.043 0.047 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.5 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.26 / Avg: 110.54 / Max: 127.1 Min: 8.88 / Avg: 191.74 / Max: 216.02 Min: 24.48 / Avg: 129.94 / Max: 145.97 Min: 10.12 / Avg: 132.4 / Max: 150.11 Min: 14.89 / Avg: 137.17 / Max: 151.93 Min: 8.97 / Avg: 148.65 / Max: 166.02 Min: 16.95 / Avg: 100.67 / Max: 111.79 Min: 15 / Avg: 199.64 / Max: 226.23 Min: 10.33 / Avg: 114.41 / Max: 131.46 Min: 36.5 / Avg: 291.82 / Max: 325.14 Min: 17.2 / Avg: 141.85 / Max: 160.04 Min: 24.53 / Avg: 241.45 / Max: 268.02 Min: 25.58 / Avg: 289.86 / Max: 322.93 Min: 24.55 / Avg: 184.52 / Max: 204.06
IndigoBench This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 5 10 15 20 25 SE +/- 0.001, N = 3 SE +/- 0.004, N = 3 SE +/- 0.002, N = 3 SE +/- 0.005, N = 3 SE +/- 0.004, N = 3 SE +/- 0.001, N = 3 SE +/- 0.006, N = 3 SE +/- 0.003, N = 3 SE +/- 0.016, N = 3 SE +/- 0.005, N = 3 SE +/- 0.005, N = 3 SE +/- 0.004, N = 3 SE +/- 0.003, N = 3 SE +/- 0.001, N = 3 7.409 11.031 7.648 7.968 11.451 12.892 8.504 11.592 7.347 20.037 7.742 17.541 20.765 13.733 M samples/s Per Watt
OpenBenchmarking.org M samples/s Per Watt, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.0178 0.0356 0.0534 0.0712 0.089 0.056 0.053 0.055 0.057 0.076 0.079 0.075 0.053 0.054 0.065 0.052 0.066 0.068 0.070 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better IndigoBench 4.4 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.45 / Avg: 131.29 / Max: 159.19 Min: 7.67 / Avg: 206.35 / Max: 245.28 Min: 23.53 / Avg: 139.08 / Max: 164.04 Min: 9.99 / Avg: 139.47 / Max: 170.13 Min: 21.59 / Avg: 151.37 / Max: 170.27 Min: 16.98 / Avg: 164.1 / Max: 186.35 Min: 17.24 / Avg: 113.37 / Max: 126.88 Min: 13.76 / Avg: 219.59 / Max: 260.99 Min: 10.35 / Avg: 135 / Max: 160.32 Min: 37.4 / Avg: 308.74 / Max: 344.6 Min: 17.59 / Avg: 147.8 / Max: 182.3 Min: 28.42 / Avg: 266.67 / Max: 299.14 Min: 31.43 / Avg: 306.83 / Max: 340.89 Min: 24.42 / Avg: 196.75 / Max: 223.99
Result
OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 12 24 36 48 60 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 23.44 33.35 24.45 25.70 34.01 37.37 25.86 35.31 23.30 51.44 24.88 46.50 53.01 38.95 M samples/s Per Watt
OpenBenchmarking.org M samples/s Per Watt, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.056 0.112 0.168 0.224 0.28 0.190 0.173 0.183 0.191 0.244 0.249 0.243 0.173 0.182 0.186 0.178 0.195 0.195 0.217 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better IndigoBench 4.4 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 7.93 / Avg: 123.49 / Max: 150.85 Min: 5.73 / Avg: 192.38 / Max: 237.67 Min: 22.85 / Avg: 133.71 / Max: 158.28 Min: 9.85 / Avg: 134.55 / Max: 166.11 Min: 20.01 / Avg: 139.22 / Max: 161.69 Min: 16.65 / Avg: 150.08 / Max: 174.37 Min: 17.26 / Avg: 106.42 / Max: 123.72 Min: 9.19 / Avg: 204.2 / Max: 251.77 Min: 9.98 / Avg: 127.71 / Max: 151.56 Min: 33.36 / Avg: 276.7 / Max: 314.68 Min: 14.95 / Avg: 139.79 / Max: 178.28 Min: 23.81 / Avg: 238.22 / Max: 270.71 Min: 26.37 / Avg: 272.17 / Max: 309.75 Min: 21.81 / Avg: 179.55 / Max: 212.1
RealSR-NCNN RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 20 40 60 80 100 SE +/- 0.43, N = 3 SE +/- 0.17, N = 3 SE +/- 0.22, N = 3 SE +/- 0.14, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.18, N = 3 SE +/- 0.31, N = 3 SE +/- 0.08, N = 3 SE +/- 0.30, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 74.98 44.23 64.22 54.07 50.64 46.63 67.13 41.91 76.12 29.29 59.56 32.37 28.18 40.56 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better RealSR-NCNN 20200818 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 8.63 / Avg: 163.5 / Max: 179.97 Min: 6.77 / Avg: 228.66 / Max: 267.14 Min: 24.41 / Avg: 196.57 / Max: 219.32 Min: 9.54 / Avg: 224.56 / Max: 256.88 Min: 20.71 / Avg: 177.45 / Max: 197.59 Min: 16.55 / Avg: 195.63 / Max: 219.97 Min: 16.96 / Avg: 152.33 / Max: 165.57 Min: 10.91 / Avg: 246.41 / Max: 289.79 Min: 10.27 / Avg: 163 / Max: 182.05 Min: 33.85 / Avg: 290.52 / Max: 342.72 Min: 14.66 / Avg: 197.25 / Max: 220.04 Min: 16.1 / Avg: 274.04 / Max: 319.8 Min: 29.39 / Avg: 293.48 / Max: 347.89 Min: 23.56 / Avg: 256.67 / Max: 289.82
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL, NVIDIA OptiX, and NVIDIA CUDA is supported. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CUDA RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 14 28 42 56 70 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 64.83 38.49 51.85 50.74 31.82 28.95 43.85 36.79 63.85 18.85 51.52 21.94 18.36 27.80 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 8.78 / Avg: 125.91 / Max: 147.21 Min: 8.44 / Avg: 206.09 / Max: 242.77 Min: 23.58 / Avg: 145.33 / Max: 164.48 Min: 10.16 / Avg: 142.89 / Max: 162.07 Min: 21.47 / Avg: 157.89 / Max: 190.92 Min: 17.21 / Avg: 168.37 / Max: 208.06 Min: 16.96 / Avg: 121.03 / Max: 140.67 Min: 15.06 / Avg: 210.88 / Max: 251.49 Min: 10.3 / Avg: 131.07 / Max: 152.21 Min: 37.92 / Avg: 279.31 / Max: 349.61 Min: 17.78 / Avg: 157.42 / Max: 178.49 Min: 18.27 / Avg: 256.87 / Max: 319.24 Min: 23.73 / Avg: 273.12 / Max: 349.15 Min: 24.91 / Avg: 207.86 / Max: 257.53
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: NVIDIA OptiX RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 4 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 5 SE +/- 2.65, N = 15 SE +/- 0.01, N = 4 SE +/- 0.01, N = 5 SE +/- 2.65, N = 15 30.39 19.24 25.90 25.68 17.42 15.73 23.56 18.72 30.15 9.71 29.08 11.28 9.48 17.09 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 2.92 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.49 / Avg: 113.1 / Max: 133.12 Min: 7.85 / Avg: 176.01 / Max: 222.82 Min: 24.37 / Avg: 128.12 / Max: 150.98 Min: 10.19 / Avg: 124.21 / Max: 146.75 Min: 21.56 / Avg: 124.46 / Max: 158.07 Min: 17.21 / Avg: 130.86 / Max: 170.36 Min: 17.09 / Avg: 98.33 / Max: 117.25 Min: 14.63 / Avg: 181.85 / Max: 226.03 Min: 10.43 / Avg: 120.35 / Max: 143.73 Min: 37.48 / Avg: 239.16 / Max: 334.57 Min: 15.7 / Avg: 128.72 / Max: 160.4 Min: 25.79 / Avg: 216.67 / Max: 297.94 Min: 26.45 / Avg: 241.84 / Max: 347.69 Min: 23.56 / Avg: 159.39 / Max: 223.89
clpeak Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 140 280 420 560 700 SE +/- 0.74, N = 3 SE +/- 1.40, N = 3 SE +/- 0.80, N = 3 SE +/- 0.96, N = 3 SE +/- 0.38, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 1.27, N = 3 SE +/- 0.74, N = 3 SE +/- 1.38, N = 3 SE +/- 0.84, N = 3 SE +/- 1.37, N = 3 SE +/- 0.05, N = 3 SE +/- 0.84, N = 3 267.89 522.31 305.27 378.25 303.92 362.30 214.35 548.48 263.13 623.33 345.81 545.96 652.34 368.71 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL GFLOPS Per Watt
OpenBenchmarking.org GFLOPS Per Watt, More Is Better clpeak OpenCL Test: Double-Precision Double RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 1.0829 2.1658 3.2487 4.3316 5.4145 3.815 4.201 3.632 4.283 4.252 4.813 4.004 4.006 3.434 3.661 3.678 3.750 3.963 3.385 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better clpeak GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 30 60 90 120 150 Min: 8.1 / Avg: 70.21 / Max: 76.49 Min: 6.79 / Avg: 124.34 / Max: 136.32 Min: 22.94 / Avg: 84.06 / Max: 91.05 Min: 9.74 / Avg: 88.32 / Max: 98.49 Min: 20.39 / Avg: 71.47 / Max: 77.36 Min: 16.95 / Avg: 75.28 / Max: 83.33 Min: 17.16 / Avg: 53.53 / Max: 58.53 Min: 10.49 / Avg: 136.92 / Max: 151.98 Min: 10.16 / Avg: 76.62 / Max: 82.94 Min: 33.8 / Avg: 170.25 / Max: 188.81 Min: 15.83 / Avg: 94.02 / Max: 108.19 Min: 25.41 / Avg: 145.59 / Max: 159.18 Min: 27.48 / Avg: 164.6 / Max: 180.98 Min: 22.7 / Avg: 108.94 / Max: 119.27
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 SE +/- 0.39, N = 3 SE +/- 0.55, N = 3 SE +/- 0.17, N = 3 SE +/- 0.32, N = 3 SE +/- 0.33, N = 3 SE +/- 0.31, N = 3 SE +/- 0.06, N = 3 SE +/- 0.48, N = 3 SE +/- 0.28, N = 3 SE +/- 0.52, N = 3 SE +/- 0.58, N = 3 SE +/- 0.38, N = 3 SE +/- 0.33, N = 3 SE +/- 0.28, N = 3 104.17 187.25 120.83 145.29 133.75 154.05 97.37 197.09 101.87 248.34 129.95 223.94 257.64 160.06 FPS Per Watt
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.3132 0.6264 0.9396 1.2528 1.566 0.892 1.286 0.884 0.987 1.084 1.227 0.918 1.293 0.856 1.300 0.967 1.256 1.392 0.959 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PlaidML GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.32 / Avg: 116.82 / Max: 179.82 Min: 7.84 / Avg: 145.57 / Max: 287.85 Min: 23.74 / Avg: 136.71 / Max: 214.78 Min: 10.15 / Avg: 147.25 / Max: 245.96 Min: 20.83 / Avg: 123.43 / Max: 194.29 Min: 17.17 / Avg: 125.6 / Max: 211.58 Min: 16.92 / Avg: 106.07 / Max: 148.84 Min: 11.74 / Avg: 152.48 / Max: 281.91 Min: 10.2 / Avg: 118.94 / Max: 179.25 Min: 25.48 / Avg: 191.02 / Max: 342.21 Min: 16.71 / Avg: 134.44 / Max: 215.29 Min: 16.97 / Avg: 178.26 / Max: 312.08 Min: 15.86 / Avg: 185.08 / Max: 335.39 Min: 23.89 / Avg: 166.87 / Max: 265.91
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 70 140 210 280 350 SE +/- 0.54, N = 3 SE +/- 0.63, N = 3 SE +/- 0.34, N = 3 SE +/- 0.45, N = 3 SE +/- 0.35, N = 3 SE +/- 0.45, N = 3 SE +/- 0.09, N = 3 SE +/- 0.54, N = 3 SE +/- 0.41, N = 3 SE +/- 0.58, N = 4 SE +/- 0.75, N = 3 SE +/- 0.47, N = 4 SE +/- 0.49, N = 4 SE +/- 0.72, N = 3 131.82 235.75 152.36 183.11 168.99 194.52 122.25 248.34 128.87 311.73 164.37 281.36 323.31 202.76 FPS Per Watt
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.4003 0.8006 1.2009 1.6012 2.0015 1.202 1.774 1.183 1.369 1.483 1.681 1.218 1.779 1.157 1.644 1.307 1.617 1.760 1.330 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PlaidML GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.09 / Avg: 109.66 / Max: 178.18 Min: 7.59 / Avg: 132.89 / Max: 266.12 Min: 23.83 / Avg: 128.78 / Max: 219.31 Min: 10.05 / Avg: 133.77 / Max: 236.77 Min: 20.65 / Avg: 113.97 / Max: 191.57 Min: 17.02 / Avg: 115.74 / Max: 209.21 Min: 16.86 / Avg: 100.38 / Max: 148.11 Min: 11.09 / Avg: 139.6 / Max: 286.99 Min: 10.17 / Avg: 111.43 / Max: 177.77 Min: 30.77 / Avg: 189.57 / Max: 342.33 Min: 16.18 / Avg: 125.73 / Max: 211.32 Min: 22.96 / Avg: 173.98 / Max: 309.08 Min: 21.11 / Avg: 183.73 / Max: 332.84 Min: 22.68 / Avg: 152.48 / Max: 263.5
NAMD CUDA NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. This version of the NAMD test profile uses CUDA GPU acceleration. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org days/ns, Fewer Is Better NAMD CUDA 2.14 ATPase Simulation - 327,506 Atoms RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.0349 0.0698 0.1047 0.1396 0.1745 SE +/- 0.00031, N = 5 SE +/- 0.00078, N = 5 SE +/- 0.00016, N = 5 SE +/- 0.00058, N = 5 SE +/- 0.00020, N = 5 SE +/- 0.00049, N = 5 SE +/- 0.00054, N = 5 SE +/- 0.00130, N = 5 SE +/- 0.00029, N = 5 SE +/- 0.00031, N = 5 SE +/- 0.00019, N = 5 SE +/- 0.00023, N = 5 SE +/- 0.00010, N = 5 SE +/- 0.00014, N = 3 0.15247 0.13324 0.14323 0.13522 0.12928 0.12611 0.15471 0.13304 0.15502 0.12066 0.13801 0.12099 0.11988 0.12485 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAMD CUDA 2.14 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 50 100 150 200 250 Min: 10.1 / Avg: 91.48 / Max: 185.83 Min: 8.71 / Avg: 118.81 / Max: 261.1 Min: 24.55 / Avg: 105.17 / Max: 209.98 Min: 10.31 / Avg: 108.2 / Max: 235.59 Min: 14.43 / Avg: 91.61 / Max: 183.82 Min: 8.97 / Avg: 93.12 / Max: 191.12 Min: 16.74 / Avg: 81.78 / Max: 148.8 Min: 13.92 / Avg: 127.32 / Max: 271.84 Min: 10.45 / Avg: 89.15 / Max: 179.33 Min: 17.89 / Avg: 154.79 / Max: 269.76 Min: 17.94 / Avg: 109.88 / Max: 214.11 Min: 24.86 / Avg: 140.85 / Max: 251.91 Min: 19 / Avg: 153.25 / Max: 267.87 Min: 22.03 / Avg: 54.9 / Max: 229.13
ArrayFire ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GFLOPS, More Is Better ArrayFire 3.7 Test: BLAS OpenCL RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 2K 4K 6K 8K 10K SE +/- 6.61, N = 4 SE +/- 8.53, N = 4 SE +/- 0.43, N = 4 SE +/- 0.34, N = 4 SE +/- 0.26, N = 4 SE +/- 0.72, N = 4 SE +/- 6.19, N = 4 SE +/- 12.10, N = 4 SE +/- 0.91, N = 4 SE +/- 1.74, N = 4 SE +/- 7.17, N = 4 SE +/- 5.63, N = 4 SE +/- 3.92, N = 4 SE +/- 17.44, N = 4 2680.12 4821.38 3017.86 3667.17 5040.87 5790.34 3490.16 4994.93 2611.24 8125.71 3346.88 7417.89 8463.76 5805.75 1. (CXX) g++ options: -rdynamic GFLOPS Per Watt
OpenBenchmarking.org GFLOPS Per Watt, More Is Better ArrayFire 3.7 Test: BLAS OpenCL RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 9 18 27 36 45 23.28 25.14 23.70 26.21 37.57 40.43 37.20 24.51 22.43 33.91 23.10 35.02 36.59 33.69 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ArrayFire 3.7 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.73 / Avg: 115.13 / Max: 157.9 Min: 8.54 / Avg: 191.79 / Max: 265.53 Min: 24.52 / Avg: 127.34 / Max: 174.66 Min: 10.15 / Avg: 139.92 / Max: 193.5 Min: 23.56 / Avg: 134.18 / Max: 197.58 Min: 19.65 / Avg: 143.22 / Max: 217.25 Min: 16.91 / Avg: 93.82 / Max: 127.49 Min: 14.14 / Avg: 203.83 / Max: 283.43 Min: 10.29 / Avg: 116.44 / Max: 158.68 Min: 37.36 / Avg: 239.65 / Max: 337.97 Min: 17.28 / Avg: 144.9 / Max: 193.12 Min: 28.27 / Avg: 211.82 / Max: 302.63 Min: 29.06 / Avg: 231.32 / Max: 326.54 Min: 23.63 / Avg: 172.34 / Max: 240.96
SHOC Scalable HeterOgeneous Computing The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 500 1000 1500 2000 2500 SE +/- 3.17, N = 3 SE +/- 1.11, N = 3 SE +/- 0.65, N = 3 SE +/- 2.81, N = 3 SE +/- 2.95, N = 4 SE +/- 1.91, N = 4 SE +/- 3.60, N = 4 SE +/- 3.30, N = 3 SE +/- 2.79, N = 4 SE +/- 6.37, N = 3 SE +/- 1.56, N = 3 SE +/- 0.73, N = 3 SE +/- 4.61, N = 3 SE +/- 1.31, N = 4 1081.44 1180.65 1144.90 1168.27 2120.83 2131.07 1255.28 1168.30 1110.73 2167.41 1119.86 2210.17 2219.90 2072.97 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: Texture Read Bandwidth RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 5 10 15 20 25 12.237 8.014 11.451 11.114 20.117 18.627 15.569 7.629 11.915 9.531 10.495 11.592 9.538 13.823 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 8.59 / Avg: 88.37 / Max: 135.13 Min: 6.82 / Avg: 147.32 / Max: 224.7 Min: 23.17 / Avg: 99.98 / Max: 145.62 Min: 9.82 / Avg: 105.12 / Max: 198.87 Min: 20.88 / Avg: 105.42 / Max: 142.98 Min: 16.92 / Avg: 114.41 / Max: 158.48 Min: 16.9 / Avg: 80.63 / Max: 108.65 Min: 11.35 / Avg: 153.13 / Max: 287.43 Min: 10.35 / Avg: 93.22 / Max: 137.55 Min: 34.01 / Avg: 227.4 / Max: 307.88 Min: 15.34 / Avg: 106.71 / Max: 185.55 Min: 25.49 / Avg: 190.67 / Max: 257.72 Min: 30.56 / Avg: 232.73 / Max: 305.32 Min: 24 / Avg: 149.96 / Max: 198.78
ViennaCL ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NN RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 130 260 390 520 650 SE +/- 0.67, N = 3 SE +/- 1.00, N = 3 SE +/- 1.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 1.20, N = 3 SE +/- 1.33, N = 3 SE +/- 1.00, N = 3 SE +/- 1.20, N = 3 SE +/- 0.67, N = 3 252 470 285 353 292 341 205 496 247 559 323 499 600 345 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dAXPY RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 160 320 480 640 800 SE +/- 0.33, N = 3 388 518 383 427 400 397 327 542 388 705 388 629 723 528 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 80 160 240 320 400 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 257 319 267 251 327 327 289 316 255 363 251 367 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dCOPY RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 130 260 390 520 650 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 367 477 363 405 371 371 315 495 369 592 370 555 607 478 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 110 220 330 440 550 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 322 405 322 330 359 358 306 403 327 490 323 480 498 435 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Result
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 130 260 390 520 650 SE +/- 0.67, N = 3 SE +/- 1.00, N = 3 SE +/- 1.53, N = 3 SE +/- 1.67, N = 3 SE +/- 1.33, N = 3 SE +/- 2.00, N = 2 SE +/- 1.67, N = 3 SE +/- 1.33, N = 3 251 467 284 349 293 339 493 243 560 320 501 602 347 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL GFLOPs/s Per Watt
OpenBenchmarking.org GFLOPs/s Per Watt, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT RTX 2070 SUPER RTX 3060 Ti RTX 2060 SUPER RTX 2080 0.5886 1.1772 1.7658 2.3544 2.943 2.351 2.616 2.191 2.610
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 100 200 300 400 500 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 369 460 372 389 224 222 222 462 374 231 371 241 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 80 160 240 320 400 SE +/- 1.20, N = 3 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 SE +/- 1.45, N = 3 SE +/- 1.20, N = 3 SE +/- 0.67, N = 3 268 306 278 288 288 280 275 305 277 356 278 356 365 331 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Result
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 130 260 390 520 650 SE +/- 0.67, N = 3 SE +/- 1.33, N = 3 SE +/- 3.00, N = 2 SE +/- 0.67, N = 3 SE +/- 1.20, N = 3 SE +/- 1.33, N = 3 SE +/- 0.67, N = 3 SE +/- 1.33, N = 3 249 476 283 354 290 340 204 486 247 557 326 498 598 343 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL GFLOPs/s Per Watt
OpenBenchmarking.org GFLOPs/s Per Watt, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 3060 Ti RTX 3070 RTX 3060 RTX 2060 SUPER RTX 3080 Ti RTX 3070 Ti 0.657 1.314 1.971 2.628 3.285 2.336 2.920 2.393 2.572 2.843 2.296 2.205 2.492 2.224 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ViennaCL 1.7.1 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 9.62 / Avg: 106.58 / Max: 171.31 Min: 6.8 / Avg: 163.04 / Max: 266.67 Min: 24.63 / Avg: 118.28 / Max: 182.65 Min: 10.06 / Avg: 119.75 / Max: 211.54 Min: 21.07 / Avg: 113.07 / Max: 191.79 Min: 16.44 / Avg: 118.52 / Max: 211.93 Min: 17.19 / Avg: 88.84 / Max: 142.29 Min: 11.06 / Avg: 168.65 / Max: 282.95 Min: 10.35 / Avg: 114.03 / Max: 176.55 Min: 34.6 / Avg: 223.52 / Max: 347.1 Min: 17.17 / Avg: 122.61 / Max: 209.61 Min: 26.87 / Avg: 192.92 / Max: 315.16 Min: 29.57 / Avg: 221.51 / Max: 344.55 Min: 23.81 / Avg: 154.21 / Max: 246.81
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 80 160 240 320 400 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 1.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 320 376 326 356 334 334 303 372 326 368 334 377 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
VkResample VkResample is a Vulkan-based image upscaling library based on VkFFT. The sample input file is upscaling a 4K image to 8K using Vulkan-based GPU acceleration. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 6 12 18 24 30 SE +/- 0.033, N = 5 SE +/- 0.020, N = 5 SE +/- 0.018, N = 5 SE +/- 0.012, N = 5 SE +/- 0.006, N = 5 SE +/- 0.004, N = 5 SE +/- 0.001, N = 5 SE +/- 0.032, N = 5 SE +/- 0.032, N = 5 SE +/- 0.007, N = 5 SE +/- 0.023, N = 5 SE +/- 0.006, N = 5 SE +/- 0.010, N = 5 SE +/- 0.003, N = 5 22.297 14.781 19.881 17.516 17.673 17.549 23.135 13.560 22.327 9.561 19.053 11.268 9.302 13.557 1. (CXX) g++ options: -O3 -pthread GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better VkResample 1.0 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 8.66 / Avg: 40.58 / Max: 167.46 Min: 7.55 / Avg: 48.84 / Max: 261.79 Min: 24.05 / Avg: 49.85 / Max: 188.2 Min: 9.67 / Avg: 41.06 / Max: 190.48 Min: 20.97 / Avg: 45.83 / Max: 181.4 Min: 16.73 / Avg: 45.37 / Max: 188.51 Min: 17.16 / Avg: 41.38 / Max: 137.83 Min: 11.1 / Avg: 53.8 / Max: 279.96 Min: 10.11 / Avg: 42.5 / Max: 175.74 Min: 25.07 / Avg: 78.5 / Max: 298.79 Min: 15.06 / Avg: 47.96 / Max: 188.32 Min: 17.84 / Avg: 69.97 / Max: 240.67 Min: 19.24 / Avg: 79.24 / Max: 310.69 Min: 24.18 / Avg: 63.12 / Max: 259.14
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Rainbow Colors and Prism - Acceleration: GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 8 16 24 32 40 SE +/- 0.01, N = 4 SE +/- 0.02, N = 4 SE +/- 0.03, N = 4 SE +/- 0.01, N = 4 SE +/- 0.05, N = 5 SE +/- 0.05, N = 6 SE +/- 0.00, N = 4 SE +/- 0.01, N = 5 SE +/- 0.01, N = 4 SE +/- 0.24, N = 6 SE +/- 0.00, N = 4 SE +/- 0.08, N = 6 SE +/- 0.00, N = 6 SE +/- 0.06, N = 6 13.26 15.28 13.10 12.15 20.99 23.45 15.36 16.83 14.13 33.25 12.16 28.20 34.27 23.77 MIN: 12.41 / MAX: 14.02 MIN: 13.65 / MAX: 16.66 MIN: 12.42 / MAX: 13.77 MIN: 11.25 / MAX: 12.81 MIN: 19.21 / MAX: 22.15 MIN: 20.97 / MAX: 24.32 MIN: 13.94 / MAX: 16.32 MIN: 15.76 / MAX: 18.22 MIN: 13.33 / MAX: 14.65 MIN: 30.01 / MAX: 35.85 MIN: 11.24 / MAX: 12.82 MIN: 26.09 / MAX: 31.07 MIN: 30.52 / MAX: 36.32 MIN: 21.81 / MAX: 25.33 M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.5 Scene: Rainbow Colors and Prism - Acceleration: GPU RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 0.0488 0.0976 0.1464 0.1952 0.244 0.126 0.101 0.115 0.111 0.186 0.217 0.173 0.107 0.131 0.160 0.106 0.151 0.166 0.164 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.5 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 10.25 / Avg: 105.55 / Max: 139.93 Min: 9.58 / Avg: 151.25 / Max: 207.44 Min: 24.69 / Avg: 113.74 / Max: 145.57 Min: 10.52 / Avg: 109.85 / Max: 140.58 Min: 15.14 / Avg: 113.14 / Max: 161.22 Min: 8.99 / Avg: 107.95 / Max: 172.87 Min: 16.83 / Avg: 88.72 / Max: 120.08 Min: 14.85 / Avg: 157.68 / Max: 218.08 Min: 10.35 / Avg: 108.15 / Max: 147.61 Min: 27.21 / Avg: 207.69 / Max: 330.8 Min: 17.23 / Avg: 114.88 / Max: 145.4 Min: 24.9 / Avg: 186.73 / Max: 280.55 Min: 18.98 / Avg: 206.99 / Max: 335.49 Min: 25.07 / Avg: 145.33 / Max: 215.28
RealSR-NCNN RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 3 6 9 12 15 SE +/- 0.017, N = 5 SE +/- 0.008, N = 6 SE +/- 0.004, N = 5 SE +/- 0.014, N = 5 SE +/- 0.004, N = 6 SE +/- 0.009, N = 6 SE +/- 0.009, N = 5 SE +/- 0.014, N = 6 SE +/- 0.012, N = 4 SE +/- 0.004, N = 7 SE +/- 0.020, N = 5 SE +/- 0.012, N = 7 SE +/- 0.005, N = 7 SE +/- 0.008, N = 6 11.493 7.629 10.165 8.880 8.317 7.815 10.362 7.337 11.642 5.635 9.493 6.036 5.517 7.044 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better RealSR-NCNN 20200818 GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 10.5 / Avg: 115.36 / Max: 179.65 Min: 8.81 / Avg: 138.2 / Max: 268.1 Min: 25.1 / Avg: 137.45 / Max: 219.17 Min: 10.59 / Avg: 143.63 / Max: 254.77 Min: 21.77 / Avg: 115 / Max: 197.48 Min: 17 / Avg: 120.11 / Max: 219.85 Min: 17.89 / Avg: 103.5 / Max: 163.54 Min: 14.57 / Avg: 151.82 / Max: 287.45 Min: 10.39 / Avg: 117.69 / Max: 178.33 Min: 33.92 / Avg: 174.67 / Max: 343.87 Min: 18.49 / Avg: 132.5 / Max: 220.3 Min: 24.98 / Avg: 164.12 / Max: 319.36 Min: 25.56 / Avg: 174.01 / Max: 347.98 Min: 25.57 / Avg: 156.99 / Max: 288.58
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 200 400 600 800 1000 SE +/- 0.55, N = 5 SE +/- 0.24, N = 6 SE +/- 0.41, N = 5 SE +/- 0.45, N = 5 SE +/- 0.18, N = 5 SE +/- 0.46, N = 6 SE +/- 0.20, N = 5 SE +/- 0.45, N = 6 SE +/- 0.43, N = 5 SE +/- 0.74, N = 6 SE +/- 0.92, N = 5 SE +/- 0.79, N = 6 SE +/- 1.07, N = 6 SE +/- 0.66, N = 5 380.72 638.39 418.68 472.09 456.40 495.68 340.13 652.41 378.75 789.35 442.29 730.16 816.85 513.37 FPS Per Watt
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 1.2013 2.4026 3.6039 4.8052 6.0065 4.161 5.339 4.017 4.572 5.069 5.323 4.313 5.127 4.087 4.908 4.317 5.164 5.126 4.260 GPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PlaidML GPU Power Consumption Monitor RTX 2070 RTX 2080 Ti RTX 2070 SUPER RTX 2080 SUPER RTX 3060 Ti RTX 3070 RTX 3060 TITAN RTX RTX 2060 SUPER RTX 3080 Ti RTX 2080 RTX 3080 RTX 3090 RTX 3070 Ti 60 120 180 240 300 Min: 8.05 / Avg: 91.49 / Max: 164.16 Min: 7.81 / Avg: 119.57 / Max: 247.26 Min: 24.03 / Avg: 104.23 / Max: 185.61 Min: 9.87 / Avg: 103.25 / Max: 200.52 Min: 20.62 / Avg: 90.03 / Max: 166.1 Min: 16.73 / Avg: 93.12 / Max: 179.45 Min: 16.72 / Avg: 78.86 / Max: 129.09 Min: 11.31 / Avg: 127.24 / Max: 273.91 Min: 10.05 / Avg: 92.66 / Max: 166.91 Min: 34.01 / Avg: 160.84 / Max: 317.93 Min: 15.55 / Avg: 102.45 / Max: 197.15 Min: 25.11 / Avg: 141.41 / Max: 283.1 Min: 28.89 / Avg: 159.36 / Max: 316.05 Min: 23.12 / Avg: 120.52 / Max: 211.83