rtx-3090-windows AMD Ryzen 9 5900X 12-Core testing with a ASUS ROG CROSSHAIR VIII HERO (3402 BIOS) and NVIDIA GeForce RTX 3090 24GB on Microsoft Windows 10 Pro Build 19043 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2105033-IB-RTX3090WI28&grs .
rtx-3090-windows Processor Motherboard Memory Disk Graphics Network OS Kernel Display Driver OpenCL File-System Screen Resolution Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads) ASUS ROG CROSSHAIR VIII HERO (3402 BIOS) 2 x 8192 MB 3600MHz F4-3600C16-8GTRG 932GB Sabrent Rocket 4.0 Plus + 15GB Corsair Voyager 3.0 USB NVIDIA GeForce RTX 3090 24GB Intel I211 Gigabit Connection Microsoft Windows 10 Pro Build 19043 10.0 (x86_64) 466.27 (27.21.14.6627) OpenCL 3.0 CUDA 11.3.101 NTFS 3840x2160 932GB Sabrent Rocket 4.0 Plus OpenBenchmarking.org Security Details - __user pointer sanitization: Disabled + Retpoline: Full + IBPB: Always + IBRS: Enabled + STIBP: Enabled
rtx-3090-windows luxcorerender: Danish Mood - GPU vkresample: 2x - Double blender: Pabellon Barcelona - NVIDIA OptiX luxcorerender: LuxCore Benchmark - GPU waifu2x-ncnn: 2x - 3 - Yes octanebench: Total Score realsr-ncnn: 4x - No blender: Classroom - NVIDIA OptiX vkpeak: fp32-scalar vkpeak: fp64-vec4 redshift: luxcorerender: Orange Juice - GPU vkpeak: fp16-vec4 blender: Barbershop - NVIDIA OptiX luxcorerender: DLSC - GPU vkfft: realsr-ncnn: 4x - Yes vkpeak: int32-vec4 vkpeak: fp32-vec4 vkpeak: fp64-scalar vkpeak: int32-scalar v-ray: NVIDIA CUDA GPU blender: Fishy Cat - CUDA v-ray: NVIDIA RTX GPU vkpeak: int16-scalar vkpeak: fp16-scalar blender: Pabellon Barcelona - CUDA blender: Barbershop - CUDA vkpeak: int16-vec4 blender: Classroom - CUDA indigobench: OpenCL GPU - Bedroom indigobench: OpenCL GPU - Supercar blender: BMW27 - CUDA fahbench: vkresample: 2x - Single blender: Fishy Cat - NVIDIA OptiX blender: BMW27 - NVIDIA OptiX luxcorerender: Rainbow Colors and Prism - GPU Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 3.252 4.874 20840.84 651.13 41670.38 63433 27.951 20521.23 27423.39 651.18 20647.37 13594.73 20676.40 16838.10 10.61 23.480 45.31 13.24 3.276 676.614641 4.892 29.46 20868.27 652.27 155 9.84 41706.09 323.77 13.34 63459 28.047 20572.99 27560.68 650.93 20638.77 1688 36.91 2164 13603.67 20694.26 120.80 387.20 16881.99 51.72 20.745 52.414 18.88 243.7352 9.314 22.64 12.99 29.33 10.68 23.829 44.97 13.22 3.242 683.709722 4.873 29.23 20852.17 648.95 156 9.89 41541.15 321.84 13.27 63656 27.906 20569.03 27555.17 649.05 20635.20 1684 37.04 2159 13594.74 20627.77 121.18 388.12 16867.59 51.81 20.713 52.467 18.90 243.8536 9.311 19.58 9.92 29.79 10.92 23.594 45.54 13.08 3.242 681.126534 4.848 29.45 20711.46 647.82 156 9.83 41456.56 322.13 13.29 63326 27.912 20470.21 27487.01 647.94 20550.13 1681 37.05 2156 13558.25 20633.00 121.18 387.04 16850.32 51.82 20.707 52.484 18.88 243.9071 9.313 19.59 9.92 29.22 OpenBenchmarking.org
LuxCoreRender Scene: Danish Mood - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: GPU Windows 10 Windows 10 Repeat Windows 10 Repeat 2 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 10.61 10.68 10.92 MIN: 10.06 / MAX: 10.98 MIN: 10.17 / MAX: 11.15 MIN: 10.52 / MAX: 11.24
VkResample Upscale: 2x - Precision: Double OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Double Windows 10 Windows 10 Repeat Windows 10 Repeat 2 6 12 18 24 30 SE +/- 0.20, N = 15 SE +/- 0.26, N = 13 SE +/- 0.24, N = 12 23.48 23.83 23.59
Blender Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX Windows 10 Windows 10 Repeat Windows 10 Repeat 2 10 20 30 40 50 SE +/- 0.00, N = 3 SE +/- 0.35, N = 3 SE +/- 0.09, N = 3 45.31 44.97 45.54
LuxCoreRender Scene: LuxCore Benchmark - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: LuxCore Benchmark - Acceleration: GPU Windows 10 Windows 10 Repeat Windows 10 Repeat 2 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 13.24 13.22 13.08 MIN: 12.65 / MAX: 13.62 MIN: 12.71 / MAX: 13.52 MIN: 12.57 / MAX: 13.48
Waifu2x-NCNN Vulkan Scale: 2x - Denoise: 3 - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 0.7371 1.4742 2.2113 2.9484 3.6855 SE +/- 0.013, N = 3 SE +/- 0.046, N = 15 SE +/- 0.016, N = 3 SE +/- 0.007, N = 3 3.252 3.276 3.242 3.242
OctaneBench Total Score OpenBenchmarking.org Score, More Is Better OctaneBench 2020.1 Total Score Windows 10 Windows 10 Repeat Windows 10 Repeat 2 150 300 450 600 750 676.61 683.71 681.13
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 1.1007 2.2014 3.3021 4.4028 5.5035 SE +/- 0.037, N = 10 SE +/- 0.015, N = 3 SE +/- 0.044, N = 3 SE +/- 0.033, N = 3 4.874 4.892 4.873 4.848
Blender Blend File: Classroom - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: NVIDIA OptiX Windows 10 Windows 10 Repeat Windows 10 Repeat 2 7 14 21 28 35 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 29.46 29.23 29.45
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-scalar Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 4K 8K 12K 16K 20K SE +/- 110.13, N = 3 SE +/- 108.41, N = 3 SE +/- 121.63, N = 3 SE +/- 104.45, N = 3 20840.84 20868.27 20852.17 20711.46
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-vec4 Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 140 280 420 560 700 SE +/- 3.32, N = 3 SE +/- 4.19, N = 2 SE +/- 1.15, N = 3 SE +/- 0.01, N = 3 651.13 652.27 648.95 647.82
RedShift Demo OpenBenchmarking.org Seconds, Fewer Is Better RedShift Demo 3.0 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 30 60 90 120 150 SE +/- 1.00, N = 3 SE +/- 1.00, N = 3 155 156 156
LuxCoreRender Scene: Orange Juice - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Orange Juice - Acceleration: GPU Windows 10 Windows 10 Repeat Windows 10 Repeat 2 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 9.84 9.89 9.83 MIN: 9.41 / MAX: 10.31 MIN: 9.37 / MAX: 10.25 MIN: 9.39 / MAX: 10.22
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-vec4 Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 9K 18K 27K 36K 45K SE +/- 210.18, N = 3 SE +/- 238.97, N = 3 SE +/- 88.16, N = 3 SE +/- 4.07, N = 3 41670.38 41706.09 41541.15 41456.56
Blender Blend File: Barbershop - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: NVIDIA OptiX Windows 10 Windows 10 Repeat Windows 10 Repeat 2 70 140 210 280 350 SE +/- 0.48, N = 3 SE +/- 0.42, N = 3 SE +/- 0.56, N = 3 323.77 321.84 322.13
LuxCoreRender Scene: DLSC - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: DLSC - Acceleration: GPU Windows 10 Windows 10 Repeat Windows 10 Repeat 2 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 13.34 13.27 13.29 MIN: 13.18 / MAX: 13.5 MIN: 13.09 / MAX: 13.44 MIN: 13.15 / MAX: 13.4
VkFFT OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.1.1 Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 14K 28K 42K 56K 70K SE +/- 831.88, N = 3 SE +/- 63.17, N = 3 SE +/- 660.76, N = 3 SE +/- 608.03, N = 3 63433 63459 63656 63326
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 27.95 28.05 27.91 27.91
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-vec4 Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 4K 8K 12K 16K 20K SE +/- 51.47, N = 3 SE +/- 99.15, N = 3 SE +/- 98.09, N = 3 SE +/- 0.29, N = 3 20521.23 20572.99 20569.03 20470.21
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-vec4 Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 6K 12K 18K 24K 30K SE +/- 71.75, N = 3 SE +/- 117.24, N = 3 SE +/- 119.42, N = 3 SE +/- 137.85, N = 3 27423.39 27560.68 27555.17 27487.01
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-scalar Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 140 280 420 560 700 SE +/- 3.24, N = 3 SE +/- 2.87, N = 3 SE +/- 1.16, N = 3 SE +/- 0.05, N = 3 651.18 650.93 649.05 647.94
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-scalar Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 4K 8K 12K 16K 20K SE +/- 97.28, N = 3 SE +/- 85.18, N = 3 SE +/- 84.81, N = 3 SE +/- 1.08, N = 3 20647.37 20638.77 20635.20 20550.13
Chaos Group V-RAY Mode: NVIDIA CUDA GPU OpenBenchmarking.org vpaths, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA CUDA GPU Windows 10 Windows 10 Repeat Windows 10 Repeat 2 400 800 1200 1600 2000 SE +/- 2.33, N = 3 SE +/- 0.67, N = 3 1688 1684 1681
Blender Blend File: Fishy Cat - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: CUDA Windows 10 Windows 10 Repeat Windows 10 Repeat 2 9 18 27 36 45 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 36.91 37.04 37.05
Chaos Group V-RAY Mode: NVIDIA RTX GPU OpenBenchmarking.org vrays, More Is Better Chaos Group V-RAY 5 Mode: NVIDIA RTX GPU Windows 10 Windows 10 Repeat Windows 10 Repeat 2 500 1000 1500 2000 2500 SE +/- 3.48, N = 3 SE +/- 3.48, N = 3 SE +/- 2.52, N = 3 2164 2159 2156
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-scalar Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 3K 6K 9K 12K 15K SE +/- 33.63, N = 3 SE +/- 34.81, N = 3 SE +/- 34.32, N = 3 SE +/- 1.67, N = 3 13594.73 13603.67 13594.74 13558.25
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-scalar Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 4K 8K 12K 16K 20K SE +/- 95.13, N = 3 SE +/- 109.48, N = 3 SE +/- 46.75, N = 3 SE +/- 51.90, N = 3 20676.40 20694.26 20627.77 20633.00
Blender Blend File: Pabellon Barcelona - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Pabellon Barcelona - Compute: CUDA Windows 10 Windows 10 Repeat Windows 10 Repeat 2 30 60 90 120 150 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 120.80 121.18 121.18
Blender Blend File: Barbershop - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CUDA Windows 10 Windows 10 Repeat Windows 10 Repeat 2 80 160 240 320 400 SE +/- 0.28, N = 3 SE +/- 0.56, N = 3 SE +/- 0.08, N = 3 387.20 388.12 387.04
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-vec4 Windows 10 H1-2021 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 4K 8K 12K 16K 20K SE +/- 5.69, N = 3 SE +/- 43.37, N = 3 SE +/- 2.91, N = 3 SE +/- 8.47, N = 3 16838.10 16881.99 16867.59 16850.32
Blender Blend File: Classroom - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: CUDA Windows 10 Windows 10 Repeat Windows 10 Repeat 2 12 24 36 48 60 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 51.72 51.81 51.82
IndigoBench Acceleration: OpenCL GPU - Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Bedroom Windows 10 Windows 10 Repeat Windows 10 Repeat 2 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 20.75 20.71 20.71
IndigoBench Acceleration: OpenCL GPU - Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: OpenCL GPU - Scene: Supercar Windows 10 Windows 10 Repeat Windows 10 Repeat 2 12 24 36 48 60 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 52.41 52.47 52.48
Blender Blend File: BMW27 - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CUDA Windows 10 Windows 10 Repeat Windows 10 Repeat 2 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 18.88 18.90 18.88
FAHBench OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 Windows 10 Windows 10 Repeat Windows 10 Repeat 2 50 100 150 200 250 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 SE +/- 0.18, N = 3 243.74 243.85 243.91
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single Windows 10 Windows 10 Repeat Windows 10 Repeat 2 3 6 9 12 15 SE +/- 0.009, N = 3 SE +/- 0.007, N = 3 SE +/- 0.010, N = 3 9.314 9.311 9.313
Blender Blend File: Fishy Cat - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: NVIDIA OptiX Windows 10 Windows 10 Repeat Windows 10 Repeat 2 5 10 15 20 25 SE +/- 3.08, N = 15 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 22.64 19.58 19.59
Blender Blend File: BMW27 - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: NVIDIA OptiX Windows 10 Windows 10 Repeat Windows 10 Repeat 2 3 6 9 12 15 SE +/- 3.10, N = 15 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 12.99 9.92 9.92
LuxCoreRender Scene: Rainbow Colors and Prism - Acceleration: GPU OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Rainbow Colors and Prism - Acceleration: GPU Windows 10 Windows 10 Repeat Windows 10 Repeat 2 7 14 21 28 35 SE +/- 0.40, N = 15 SE +/- 0.58, N = 15 SE +/- 0.50, N = 15 29.33 29.79 29.22 MIN: 16.77 / MAX: 35.64 MIN: 17.42 / MAX: 35.47 MIN: 17.98 / MAX: 35.38
Phoronix Test Suite v10.8.4