Testing the new GeForce GTX Titan

Published by Powerkiter on

We recently tested the new NVIDIA Kepler boards for our GPGPU flow solver elbe. After initial tests on the Kepler K20 boards were very promising and led to speed-up factors of up to 2.5x (without any code modifications), we decided to purchase the new GeForce GTX Titan board to see if the consumer hardware can keep up with the professional boards. This consumer card features 2688 streaming processors, 6 GB device memory and single- and double-precision compute capability.

Running the elbe code for both 2D/3D and single/double precision calculations, we found a performance of up to 1.5 GNUPS (giga node updates per second), 2.5x more than on our recent Tesla C2075 GPGPUs, for a D2Q9 singlephase LBM calculation.

Further reading:

  • http://www.nvidia.de/object/nvidia-kepler-de.html
  • http://www.nvidia.de/titan-graphics-card
Categories: elbe

Related Posts

elbe

Final call: NVIDIA webinar on CUDA-accelerated CFD

Register now for our NVIDIA webinar on CUDA-accelerated Computational Fluid Dynamics! Together with three reseachers from the elbe team, I’ll discuss key concepts and several appliations of our CUDA-accelerated CFD solver elbe. https://info.nvidia.com/higher-ed-and-research-webinars-fluid-dynamics-reg-page.html

Conferences

GTC Europe 2016

The elbe team was part of the first European GPU Technology Conference that took place on September 28-29 in Amsterdam, Netherlands. More than 1700 attendees were on site to learn about deep learning, artificial intelligence Read more…

Conferences

SMM 2016

Busy 2016! After having successfully organized ICMMES-2016, we’re now contributing to this years’ SMM exhibition. SMM is the leading international maritime trade fair and will take place from Sept 6 thru Sept 9 2016, in Read more…