March 2021 Linux Vulkan, RT, Compute

AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3204 BIOS) and NVIDIA GeForce RTX 2080 Ti 11GB on Ubuntu 20.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2103089-PTS-MARCH20299
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Limit displaying results to tests within:

CPU Massive 3 Tests
Creator Workloads 2 Tests
HPC - High Performance Computing 2 Tests
Machine Learning 2 Tests
Multi-Core 2 Tests
NVIDIA GPU Compute 12 Tests
Renderers 2 Tests
Vulkan Compute 5 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
RTX 3060 Ti
March 07 2021
  6 Hours, 13 Minutes
RTX 3080
March 07 2021
  5 Hours, 28 Minutes
RTX 2080 Ti
March 08 2021
  6 Hours, 7 Minutes
Invert Hiding All Results Option
  5 Hours, 56 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


March 2021 Linux Vulkan, RT, ComputeOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3204 BIOS)AMD Starship/Matisse32GB2000GB Corsair Force MP600 + 2000GBNVIDIA GeForce RTX 3060 Ti 8GBNVIDIA GeForce RTX 3080 10GBNVIDIA GeForce RTX 2080 Ti 11GBNVIDIA Device 228bNVIDIA Device 1aefNVIDIA TU102 HD AudioASUS MG28URealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 20.105.8.0-44-generic (x86_64)GNOME Shell 3.38.2X Server 1.20.9NVIDIA 460.394.6.0OpenCL 1.2 CUDA 11.2.1361.2.155GCC 10.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudiosMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionMarch 2021 Linux Vulkan, RT, Compute BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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 3060 Ti: GPU Compute Cores: 4864- RTX 3080: GPU Compute Cores: 8704- RTX 2080 Ti: GPU Compute Cores: 4352- 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 3060 TiRTX 3080RTX 2080 TiResult OverviewPhoronix Test Suite100%121%142%162%LuxCoreRender OpenCLChaos Group V-RAYBlenderGeeXLab Vulkan Ray-Tracing DemoVkFFTOctaneBenchVkResampleRedShift DemoRealSR-NCNNLeelaChessZeroFAHBenchWaifu2x-NCNN VulkanNCNNNAMD CUDA

RTX 3060 TiRTX 3080RTX 2080 TiPer Watt Result OverviewPhoronix Test Suite100%120%140%161%181%LuxCoreRender OpenCLChaos Group V-RAYMeta Performance Per WattsOctaneBenchFAHBenchLeelaChessZeroVkFFTGeeXLab Vulkan Ray-Tracing DemoP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

March 2021 Linux Vulkan, RT, Computeblender: Classroom - NVIDIA OptiXblender: Pabellon Barcelona - NVIDIA OptiXv-ray: NVIDIA CUDA GPUluxcorerender-cl: LuxCore Benchmarkv-ray: NVIDIA RTX GPUblender: Fishy Cat - NVIDIA OptiXgeexlab-rt: 1920 x 1080geexlab-rt: 3840 x 2160geexlab-rt: 2560 x 1440blender: BMW27 - NVIDIA OptiXvkfft: octanebench: Total Scorerealsr-ncnn: 4x - Yesvkresample: 2x - Singleredshift: lczero: OpenCLrealsr-ncnn: 4x - Nofahbench: waifu2x-ncnn: 2x - 3 - Yesncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU - regnety_400mnamd-cuda: ATPase Simulation - 327,506 Atomsluxcorerender-cl: Foodluxcorerender-cl: Rainbow Colors and Prismluxcorerender-cl: DLSCncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2RTX 3060 TiRTX 3080RTX 2080 Ti55.2387.0811745.76153542.3747.113.227.318.0434945379.83902254.35017.649242226748.834234.34974.39516.9169.3514.4632.0926.2218.0718.0715.8921.230.154192.9216.897.024.952.247.065.154.975.5636.3456.5416467.88215724.5080.422.546.211.6956307557.25492334.67711.268166316346.365317.32523.48017.2569.3714.2532.7826.2818.4317.3315.6221.250.155004.0822.029.615.282.236.565.224.945.6274.80104.159244.52124736.3466.319.039.119.6242314353.07937345.31014.763247232328.365295.26303.94315.9264.4713.5030.6324.7417.5517.2215.2520.780.154102.0511.825.514.822.296.565.034.965.29OpenBenchmarking.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.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Classroom - Compute: NVIDIA OptiXRTX 2080 TiRTX 3060 TiRTX 308020406080100SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 374.8055.2336.34

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 2080 TiRTX 3060 TiRTX 308020406080100SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3104.1587.0856.54

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.

OpenBenchmarking.orgvpaths, More Is BetterChaos Group V-RAY 5Mode: NVIDIA CUDA GPURTX 2080 TiRTX 3060 TiRTX 3080400800120016002000SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 392411741646

LuxCoreRender OpenCL

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on OpenCL accelerators/GPUs. The alternative luxcorerender test profile is for CPU execution due to a difference in tests, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: LuxCore BenchmarkRTX 2080 TiRTX 3060 TiRTX 3080246810SE +/- 0.08, N = 12SE +/- 0.09, N = 12SE +/- 0.02, N = 34.525.767.88MIN: 0.14 / MAX: 5.4MIN: 0.15 / MAX: 6.78MIN: 0.23 / MAX: 9.07

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.

OpenBenchmarking.orgvrays, More Is BetterChaos Group V-RAY 5Mode: NVIDIA RTX GPURTX 2080 TiRTX 3060 TiRTX 30805001000150020002500SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 5.78, N = 3124715352157

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 2080 TiRTX 3060 TiRTX 30801020304050SE +/- 0.17, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 336.3442.3724.50

GeeXLab Vulkan Ray-Tracing Demo

GeeXLab is a cross-platform tool for 3D programming and demo creation. The GeeXLab Vulkan Ray-Tracing Demo from Geeks3D.com is a path tracer based demo making use of the Vulkan ray-tracing extensions with supported graphics processors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterGeeXLab Vulkan Ray-Tracing Demo 2021.2.18.0Resolution: 1920 x 1080RTX 2080 TiRTX 3060 TiRTX 308020406080100SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 366.347.180.4

OpenBenchmarking.orgFPS, More Is BetterGeeXLab Vulkan Ray-Tracing Demo 2021.2.18.0Resolution: 3840 x 2160RTX 2080 TiRTX 3060 TiRTX 3080510152025SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 319.013.222.5

OpenBenchmarking.orgFPS, More Is BetterGeeXLab Vulkan Ray-Tracing Demo 2021.2.18.0Resolution: 2560 x 1440RTX 2080 TiRTX 3060 TiRTX 30801020304050SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 339.127.346.2

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.92Blend File: BMW27 - Compute: NVIDIA OptiXRTX 2080 TiRTX 3060 TiRTX 3080510152025SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 419.6218.0411.69

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.1.1RTX 2080 TiRTX 3060 TiRTX 308012K24K36K48K60KSE +/- 87.52, N = 3SE +/- 34.40, N = 3SE +/- 645.06, N = 34231434945563071. (CXX) g++ options: -O3 -pthread

OctaneBench

OctaneBench is a test of the OctaneRender on the GPU and requires the use of NVIDIA CUDA. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterOctaneBench 2020.1Total ScoreRTX 2080 TiRTX 3060 TiRTX 3080120240360480600353.08379.84557.25

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesRTX 2080 TiRTX 3060 TiRTX 30801224364860SE +/- 0.28, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 345.3154.3534.68

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.

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 2080 TiRTX 3060 TiRTX 308048121620SE +/- 0.01, N = 5SE +/- 0.02, N = 5SE +/- 0.05, N = 514.7617.6511.271. (CXX) g++ options: -O3 -pthread

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsRTX 2080 TiRTX 3060 TiRTX 30804080120160200131.48133.56196.14

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.0RTX 2080 TiRTX 3060 TiRTX 308050100150200250SE +/- 0.33, N = 3247242166

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.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: OpenCLRTX 2080 TiRTX 3060 TiRTX 30807K14K21K28K35KSE +/- 68.46, N = 3SE +/- 36.29, N = 3SE +/- 77.75, N = 32323222674316341. (CXX) g++ options: -flto -pthread

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.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoRTX 2080 TiRTX 3060 TiRTX 3080246810SE +/- 0.076, N = 15SE +/- 0.027, N = 5SE +/- 0.025, N = 68.3658.8346.365

FAHBench

FAHBench is a Folding@Home benchmark on the GPU. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.2RTX 2080 TiRTX 3060 TiRTX 308070140210280350SE +/- 3.64, N = 4SE +/- 0.14, N = 3SE +/- 0.38, N = 3295.26234.35317.33

Waifu2x-NCNN Vulkan

Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. 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 with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesRTX 2080 TiRTX 3060 TiRTX 30800.98891.97782.96673.95564.9445SE +/- 0.028, N = 8SE +/- 0.008, N = 8SE +/- 0.012, N = 93.9434.3953.480

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenetRTX 2080 TiRTX 3060 TiRTX 308048121620SE +/- 0.19, N = 15SE +/- 0.14, N = 15SE +/- 0.16, N = 1515.9216.9117.25MIN: 12.87 / MAX: 148.41MIN: 12.6 / MAX: 165.86MIN: 12.94 / MAX: 157.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg16RTX 2080 TiRTX 3060 TiRTX 30801530456075SE +/- 0.19, N = 15SE +/- 0.22, N = 15SE +/- 0.13, N = 1564.4769.3569.37MIN: 55.92 / MAX: 197.16MIN: 57.34 / MAX: 251.7MIN: 57.51 / MAX: 277.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnetRTX 2080 TiRTX 3060 TiRTX 308048121620SE +/- 0.10, N = 15SE +/- 0.14, N = 15SE +/- 0.12, N = 1513.5014.4614.25MIN: 11.55 / MAX: 150.82MIN: 11.57 / MAX: 172.15MIN: 11.62 / MAX: 146.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet50RTX 2080 TiRTX 3060 TiRTX 3080816243240SE +/- 0.16, N = 15SE +/- 0.26, N = 15SE +/- 0.28, N = 1530.6332.0932.78MIN: 24.98 / MAX: 184.22MIN: 24.39 / MAX: 181.2MIN: 24.87 / MAX: 191.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tinyRTX 2080 TiRTX 3060 TiRTX 3080612182430SE +/- 0.17, N = 15SE +/- 0.12, N = 15SE +/- 0.08, N = 1524.7426.2226.28MIN: 20.75 / MAX: 158.36MIN: 20.73 / MAX: 190.19MIN: 20.52 / MAX: 209.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet18RTX 2080 TiRTX 3060 TiRTX 3080510152025SE +/- 0.13, N = 15SE +/- 0.11, N = 15SE +/- 0.16, N = 1517.5518.0718.43MIN: 14.8 / MAX: 158.57MIN: 14.23 / MAX: 148.96MIN: 14.45 / MAX: 185.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: squeezenet_ssdRTX 2080 TiRTX 3060 TiRTX 308048121620SE +/- 0.08, N = 15SE +/- 0.12, N = 14SE +/- 0.17, N = 1517.2218.0717.33MIN: 14.2 / MAX: 168.75MIN: 14.13 / MAX: 170.56MIN: 13.69 / MAX: 168.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mobilenetRTX 2080 TiRTX 3060 TiRTX 308048121620SE +/- 0.17, N = 15SE +/- 0.19, N = 15SE +/- 0.16, N = 1515.2515.8915.62MIN: 12.38 / MAX: 152.28MIN: 12.07 / MAX: 199.19MIN: 12.03 / MAX: 156.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400mRTX 2080 TiRTX 3060 TiRTX 3080510152025SE +/- 0.20, N = 15SE +/- 0.14, N = 15SE +/- 0.14, N = 1520.7821.2321.25MIN: 17.42 / MAX: 165.33MIN: 17.34 / MAX: 158.36MIN: 17.24 / MAX: 229.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD CUDA 2.14ATPase Simulation - 327,506 AtomsRTX 2080 TiRTX 3060 TiRTX 30800.03490.06980.10470.13960.1745SE +/- 0.00066, N = 5SE +/- 0.00107, N = 15SE +/- 0.00166, N = 40.154100.154190.15500

GPU Temperature Monitor

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringRTX 2080 TiRTX 3060 TiRTX 30801530456075Min: 34 / Avg: 63.71 / Max: 77Min: 33 / Avg: 58.3 / Max: 71Min: 32 / Avg: 60.5 / Max: 73

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringRTX 2080 TiRTX 3060 TiRTX 308060120180240300Min: 21.17 / Avg: 162.79 / Max: 270.71Min: 16.34 / Avg: 121.86 / Max: 199.26Min: 6.14 / Avg: 195.22 / Max: 320.01

LuxCoreRender OpenCL

MinAvgMaxRTX 2080 Ti54.066.370.0RTX 3060 Ti49.063.467.0RTX 308053.065.569.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender OpenCL 2.3GPU Temperature Monitor20406080100

MinAvgMaxRTX 2080 Ti23.9169.4204.5RTX 3060 Ti20.4140.6166.8RTX 308015.8232.5273.9OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender OpenCL 2.3GPU Power Consumption Monitor70140210280350

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender OpenCL 2.3Scene: FoodRTX 2080 TiRTX 3060 TiRTX 30800.00450.0090.01350.0180.02250.010.020.02

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: FoodRTX 2080 TiRTX 3060 TiRTX 30800.9181.8362.7543.6724.59SE +/- 0.07, N = 12SE +/- 0.07, N = 12SE +/- 0.03, N = 32.052.924.08MIN: 0.11 / MAX: 2.71MIN: 0.14 / MAX: 3.71MIN: 0.29 / MAX: 5.04

MinAvgMaxRTX 2080 Ti59.063.866.0RTX 3060 Ti52.058.963.0RTX 308058.061.664.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender OpenCL 2.3GPU Temperature Monitor20406080100

MinAvgMaxRTX 2080 Ti27.9151.0194.7RTX 3060 Ti20.8112.0160.2RTX 308017.2187.9265.4OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender OpenCL 2.3GPU Power Consumption Monitor70140210280350

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismRTX 2080 TiRTX 3060 TiRTX 30800.03380.06760.10140.13520.1690.080.150.12

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and PrismRTX 2080 TiRTX 3060 TiRTX 3080510152025SE +/- 0.29, N = 15SE +/- 0.51, N = 15SE +/- 0.14, N = 511.8216.8922.02MIN: 4.13 / MAX: 12.85MIN: 6.42 / MAX: 18.31MIN: 18.62 / MAX: 23.39

MinAvgMaxRTX 2080 Ti58.071.474.0RTX 3060 Ti50.065.668.0RTX 308056.068.471.0OpenBenchmarking.orgCelsius, Fewer Is BetterLuxCoreRender OpenCL 2.3GPU Temperature Monitor20406080100

MinAvgMaxRTX 2080 Ti24.2207.8229.4RTX 3060 Ti20.4160.2174.8RTX 308017.5269.1292.2OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender OpenCL 2.3GPU Power Consumption Monitor70140210280350

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSCRTX 2080 TiRTX 3060 TiRTX 30800.0090.0180.0270.0360.0450.030.040.04

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSCRTX 2080 TiRTX 3060 TiRTX 30803691215SE +/- 0.11, N = 12SE +/- 0.14, N = 12SE +/- 0.01, N = 35.517.029.61MIN: 1.49 / MAX: 5.76MIN: 1.93 / MAX: 7.37MIN: 9.25 / MAX: 9.72

NCNN

MinAvgMaxRTX 2080 Ti34.036.753.0RTX 3060 Ti33.036.642.0RTX 308032.035.652.0OpenBenchmarking.orgCelsius, Fewer Is BetterNCNN 20201218GPU Temperature Monitor1530456075

MinAvgMaxRTX 2080 Ti21.221.825.1RTX 3060 Ti16.317.920.4RTX 30806.112.679.6OpenBenchmarking.orgWatts, Fewer Is BetterNCNN 20201218GPU Power Consumption Monitor20406080100

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnetRTX 2080 TiRTX 3060 TiRTX 30801.1882.3763.5644.7525.94SE +/- 0.08, N = 15SE +/- 0.10, N = 14SE +/- 0.11, N = 144.824.955.28MIN: 3.95 / MAX: 145.02MIN: 3.88 / MAX: 153.2MIN: 3.88 / MAX: 209.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazefaceRTX 2080 TiRTX 3060 TiRTX 30800.51531.03061.54592.06122.5765SE +/- 0.07, N = 15SE +/- 0.09, N = 15SE +/- 0.09, N = 152.292.242.23MIN: 1.83 / MAX: 154.65MIN: 1.75 / MAX: 138.88MIN: 1.77 / MAX: 123.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b0RTX 2080 TiRTX 3060 TiRTX 3080246810SE +/- 0.07, N = 15SE +/- 0.13, N = 15SE +/- 0.06, N = 156.567.066.56MIN: 5.57 / MAX: 146.82MIN: 5.49 / MAX: 146.78MIN: 5.41 / MAX: 126.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v2RTX 2080 TiRTX 3060 TiRTX 30801.17452.3493.52354.6985.8725SE +/- 0.07, N = 15SE +/- 0.11, N = 15SE +/- 0.08, N = 155.035.155.22MIN: 4.28 / MAX: 153.75MIN: 4.19 / MAX: 181.51MIN: 4.2 / MAX: 125.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3RTX 2080 TiRTX 3060 TiRTX 30801.11832.23663.35494.47325.5915SE +/- 0.04, N = 15SE +/- 0.09, N = 15SE +/- 0.07, N = 154.964.974.94MIN: 4.19 / MAX: 152.17MIN: 4.03 / MAX: 127.3MIN: 4.01 / MAX: 130.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2RTX 2080 TiRTX 3060 TiRTX 30801.26452.5293.79355.0586.3225SE +/- 0.06, N = 15SE +/- 0.09, N = 15SE +/- 0.10, N = 155.295.565.62MIN: 4.42 / MAX: 151.48MIN: 4.33 / MAX: 129.48MIN: 4.26 / MAX: 143.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread