plaidml-blender-for-geforce-rtx-3080 AMD Ryzen 9 3950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS) and NVIDIA GeForce RTX 3080 10GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2010065-PTS-PLAIDMLB85&gru&export=pdf&rdt&rro .
plaidml-blender-for-geforce-rtx-3080 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution RTX 3080 GeForce RTX 3080 2 \3 AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS) AMD Starship/Matisse 16GB 2000GB Corsair Force MP600 + 2000GB NVIDIA GeForce RTX 3080 10GB (1710/9501MHz) NVIDIA Device 1aef DELL P2415Q Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.4.0-48-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.8 NVIDIA 455.23.05 4.6.0 OpenCL 1.2 CUDA 11.1.70 1.2.142 GCC 9.3.0 + CUDA 11.1 ext4 3840x2160 NVIDIA GeForce RTX 3080 10GB (315/405MHz) NVIDIA GeForce RTX 3080 10GB (450/810MHz) NVIDIA GeForce RTX 3080 10GB (360/405MHz) OpenBenchmarking.org Processor Details - Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8701013 OpenCL Details - GPU Compute Cores: 8704 Python Details - RTX 3080, 2, \3: Python 3.8.2 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
plaidml-blender-for-geforce-rtx-3080 plaidml: No - Training - VGG16 - OpenCL plaidml: No - Training - VGG19 - OpenCL plaidml: No - Inference - VGG16 - OpenCL plaidml: No - Inference - VGG19 - OpenCL plaidml: No - Training - Mobilenet - OpenCL plaidml: No - Inference - IMDB LSTM - OpenCL plaidml: No - Inference - Mobilenet - OpenCL plaidml: No - Inference - ResNet 50 - OpenCL plaidml: Yes - Inference - Mobilenet - OpenCL plaidml: No - Inference - DenseNet 201 - OpenCL plaidml: No - Inference - Inception V3 - OpenCL plaidml: No - Inference - NASNer Large - OpenCL fahbench: octanebench: Total Score blender: BMW27 - CUDA blender: Classroom - CUDA blender: Fishy Cat - CUDA blender: Barbershop - CUDA blender: BMW27 - NVIDIA OptiX blender: Classroom - NVIDIA OptiX blender: Fishy Cat - NVIDIA OptiX blender: Barbershop - NVIDIA OptiX blender: Pabellon Barcelona - CUDA blender: Pabellon Barcelona - NVIDIA OptiX RTX 3080 GeForce RTX 3080 2 \3 47.42 40.77 280.08 223.42 241.25 1010.77 3051.48 724.51 3546.08 259.51 397.43 79.45 25.89 68.23 47.40 285.62 11.94 37.88 21.95 416.12 176.74 54.81 316.6180 563.14729 47.65 279.96 223.48 240.36 1009.31 3050.89 723.99 3544.18 258.72 396.66 79.20 317.1974 563.828369 25.97 68.33 47.14 286.37 11.93 37.94 21.97 419.18 175.89 54.77 40.76 280.15 223.70 240.61 1015.96 3061.4 727.84 3543.34 259.18 397.36 79.38 317.2851 561.981398 25.95 68.24 47.16 285.34 11.93 37.91 21.97 415.97 175.85 54.76 OpenBenchmarking.org
PlaidML FP16: No - Mode: Training - Network: VGG16 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Training - Network: VGG16 - Device: OpenCL 2 RTX 3080 11 22 33 44 55 SE +/- 0.20, N = 2 47.65 47.42
PlaidML FP16: No - Mode: Training - Network: VGG19 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Training - Network: VGG19 - Device: OpenCL \3 RTX 3080 9 18 27 36 45 40.76 40.77
PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL \3 2 RTX 3080 60 120 180 240 300 SE +/- 0.13, N = 3 SE +/- 0.23, N = 3 SE +/- 0.04, N = 3 280.15 279.96 280.08
PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL \3 2 RTX 3080 50 100 150 200 250 SE +/- 0.29, N = 3 SE +/- 0.16, N = 3 SE +/- 0.15, N = 3 223.70 223.48 223.42
PlaidML FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL \3 2 RTX 3080 50 100 150 200 250 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 240.61 240.36 241.25
PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL \3 2 RTX 3080 200 400 600 800 1000 SE +/- 1.86, N = 3 SE +/- 0.91, N = 3 SE +/- 2.40, N = 3 1015.96 1009.31 1010.77
PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL \3 2 RTX 3080 700 1400 2100 2800 3500 SE +/- 2.79, N = 3 SE +/- 3.22, N = 3 SE +/- 1.29, N = 3 3061.40 3050.89 3051.48
PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL \3 2 RTX 3080 160 320 480 640 800 SE +/- 1.65, N = 3 SE +/- 0.75, N = 3 SE +/- 1.44, N = 3 727.84 723.99 724.51
PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL \3 2 RTX 3080 800 1600 2400 3200 4000 SE +/- 4.28, N = 3 SE +/- 1.42, N = 3 SE +/- 0.40, N = 3 3543.34 3544.18 3546.08
PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL \3 2 RTX 3080 60 120 180 240 300 SE +/- 0.15, N = 3 SE +/- 0.26, N = 3 SE +/- 0.05, N = 3 259.18 258.72 259.51
PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL \3 2 RTX 3080 90 180 270 360 450 SE +/- 0.56, N = 3 SE +/- 0.47, N = 3 SE +/- 0.69, N = 3 397.36 396.66 397.43
PlaidML FP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCL OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCL \3 2 RTX 3080 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 79.38 79.20 79.45
FAHBench OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 \3 2 GeForce RTX 3080 70 140 210 280 350 SE +/- 0.25, N = 3 SE +/- 0.33, N = 3 SE +/- 0.37, N = 3 317.29 317.20 316.62
OctaneBench Total Score OpenBenchmarking.org Score, More Is Better OctaneBench 2020.1 Total Score \3 2 GeForce RTX 3080 120 240 360 480 600 561.98 563.83 563.15
Blender Blend File: BMW27 - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: BMW27 - Compute: CUDA \3 2 RTX 3080 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 25.95 25.97 25.89
Blender Blend File: Classroom - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Classroom - Compute: CUDA \3 2 RTX 3080 15 30 45 60 75 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 68.24 68.33 68.23
Blender Blend File: Fishy Cat - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Fishy Cat - Compute: CUDA \3 2 RTX 3080 11 22 33 44 55 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 47.16 47.14 47.40
Blender Blend File: Barbershop - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Barbershop - Compute: CUDA \3 2 RTX 3080 60 120 180 240 300 SE +/- 0.17, N = 3 SE +/- 0.23, N = 3 SE +/- 0.01, N = 3 285.34 286.37 285.62
Blender Blend File: BMW27 - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: BMW27 - Compute: NVIDIA OptiX \3 2 RTX 3080 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 11.93 11.93 11.94
Blender Blend File: Classroom - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Classroom - Compute: NVIDIA OptiX \3 2 RTX 3080 9 18 27 36 45 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 37.91 37.94 37.88
Blender Blend File: Fishy Cat - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Fishy Cat - Compute: NVIDIA OptiX \3 2 RTX 3080 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 21.97 21.97 21.95
Blender Blend File: Barbershop - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Barbershop - Compute: NVIDIA OptiX \3 2 RTX 3080 90 180 270 360 450 SE +/- 3.40, N = 3 SE +/- 0.29, N = 3 SE +/- 3.50, N = 3 415.97 419.18 416.12
Blender Blend File: Pabellon Barcelona - Compute: CUDA OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Pabellon Barcelona - Compute: CUDA \3 2 RTX 3080 40 80 120 160 200 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 175.85 175.89 176.74
Blender Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX \3 2 RTX 3080 12 24 36 48 60 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 54.76 54.77 54.81
Phoronix Test Suite v10.8.5