News

NVIDIA Announces 2nd Gen Maximus Technology

Benefits of Kepler Architecture (Tesla K20)

 

Benefits of Kepler Architecture (Tesla K20)

With the additional of the Tesla K20 GPU to the NVIDIA Maximus system, the compute work is channeled away from the CPU as well as the Quadro K5000. The Maximus set of software and drivers is able to transparently and automatically assign visualization, simulation or rendering work to the right GPU. According to NVIDIA, the 2nd generation Maximus technology is capable of reducing overheads to the system's CPU as well. The feature highlights of the Tesla K20 include the following aspects that enthusiasts would have already been familiar from the desktop GeForce 6 series:-

SMX

SMX promises to deliver more performance, due to its higher number of CUDA cores, than the Fermi architecture and it will deliver the stipulated level of performance with less power; in fact, it is touted to be three times as efficient as the previous generation SM.

Dynamic Parallelism

The Tesla K20 GPU supports Dynamic Parallelism and Hyper-Q technologies, making it easier for GPU developers to speed up all parallel recursive loops, resulting in the Kepler GPU being able to create its own jobs without having to go back to the CPU for such instructions. This will allow the compute work to be sped up, while at the same time reducing computing overheads at the system's CPU.

All Reponses

Please login to comment or register here.
No Comments currently, be the first to roll the ball.

All News Categories

News for Past 12 Months

Subscribe to HWZ Here!

Subscribe now to receive latest tech news, articles and promotions straight to your inbox!
 
 
By signing up, you indicate that you have read and agreed to the and .