GPU Rendering
Blender can use GPU acceleration (CUDA or OpenCL) to render directly on the GPU with Cycles. And that’s where it gets interesting to compare both approaches including the appropriate cards.
The next benchmark contains a scene with ~470K vertices and ~900K triangles. The scene contains three identical car models and is rendered with the OpenGL renderer while the camera pans 360 degrees.
The Luxmark is the benchmark version of Luxrender and illustrates very well the real computing power and also profits immensely from the memory of the graphics card. With 24 GB, the Quadro RTX6000 is in a class of its own.
Deep Learning
Caffe is a deep learning framework developed by Berkeley AI Research (BAIR) in collaboration with the community. Yangqing Jia started the project during his doctoral studies at UC Berkeley.
Folding@home
Folding@home (FAH or F@h) is a distributed computing project for disease research that simulates protein folding, computational drug design and other types of molecular dynamics. Unfortunately, the program did not run on the Radeon Pro W5700 as the only card. Here, it will surely have to give in with new drivers and/or patched client within the SPECwpc.
- 1 - Overview & Benchmark Selection
- 2 - Creo 3.0
- 3 - Solidworks 2019
- 4 - Solidworks 2019 Enhanced
- 5 - 3ds Max 2015
- 6 - Inventor Pro 2020
- 7 - Various CAD and Science Applications
- 8 - Windows GDI und GDI+ Driver Performance
- 9 - Rendering & Compute
- 10 - Adobe Premiere Pro 2020 & DaVinci Resolve 16
- 11 - Adobe Lightroom Classic (2020)
- 12 - Autodesk Maya 2019 and Arnold
- 13 - Blender RTX (OptiX) & OctaneBench
- 14 - Thermal Imaging / Infrared
- 15 - Power Consumption
- 16 - PSU Recommendation