Nvidia’s GPU Technology Conference kicked off with a keynote from CEO Jen-Hsun Huang that wasn’t shy of big statements. Huang touted that the company’s new Kepler architecture and thriving CUDA ecosystem would continue to “democratize high-performance computing as we know it.” He followed that up with something that got my attention, he announced that Nvidia plans to unleash their recently released Kepler in to the cloud.
Kepler is Nvidia’s latest GPU architecture and the successor to Fermi. Nvidia’s first Kepler products included GeForce-branded GPUs for desktops and laptops such as the top-of-the-line GeForce GTX 690 card, which sported a pair of Kepler GPUs.
To make it happen, the company has created a virtualized Kepler GPU tech, called VGX, so that no physical connections are needed to render and stream graphics to remote locations. This is exactly what Citrix did with CPU virtualization, so you could run huge programs like Autocad on any device you wanted. With Kepler they are taking its graphics power and making it acceessible to smartphones, tablets, netbooks and more.
Nvidia also announced the availability of the Tesla K10, which offers three times the single-precision floating point performance of Fermi-based Tesla cards, plus 1.8 times the memory bandwidth. Nvidia plans to follow up in the fourth quarter with the Tesla K20, which will treble the double-precision performance of Fermi and introduce the company’s “Hyper-Q” technology, which for the first time adds multiple work queues from a CPU, resulting in a much higher GPU utilization rate than was possible with single-queue architectures like Fermi and its predecessors.
Nvidia has been a fantastic company to watch evolve as they started out catering to hardcore gamers and now have a finger in everything from scientific computing to smartphones.