Nvidia Tegra K1 targeting customized ARM micro-server market

Source: Internet
Author: User
Keywords Customization Nvidia micro Server Tegra aiming

"Tenkine Server channel May 26 News" into the 2014, arm in the data center of the increasingly rapid layout, one of the signs is that AMD will launch 64-bit ARM server chip. But not only does AMD target the ARM micro-server market, but Nvidia is also evaluating the micro-server market. This does not NVIDIA announced the launch of a micro-server-oriented 64-bit Tegra K1 chip, and other arm chip manufacturers to compete.

Tegra K1 uses the same Kepler architecture as the PC computer, and the Nvidia Kepler Gpu,nvidia Kepler, which contains 192 nvidia CUDA cores, is the first very broad GPU architecture that covers the entire range from supercomputers to PCs and mobile devices. At the same time Tegra K1 will cortex A15 ARM CPU and the third generation of power-saving core combination, can achieve a record level of performance and battery endurance. NVIDIA's variable symmetric multiprocessing SMP architecture enables four high-performance cores to be fully enabled when needed to achieve maximum performance, and each core can be automatically enabled and shut down independently of the workload.

We know that Nvidia has been betting on a graphics processor, or GPU acceleration, on mobile terminals and high-performance computing. This can be seen from Nvidia's launch of the grid server. The Nvidia grid portfolio consists of hardware, software, and devices that provide GPU acceleration from the data center to any user. It includes the nvidia grid enterprise solution, the NVIDIA Grid Vision computing device for small and midsize enterprises (VCA), and the nvidia grid cloud gaming platform for gaming-service businesses. The core of the Nvidia Grid Enterprise solution is the NVIDIA grid VGX software as well as the Nvidia grid K1 and K2 cards. The former is a complete set of GPU virtualization, remote, and management libraries, while K1 and K2 cards are specifically built for demanding server environments.

Currently, Dell, HP, and IBM already offer servers based on Nvidia grid. Citrix, Microsoft and VMware also offer software that supports NVIDIA grid. The Nvidia grid graphics card includes multiple graphics processors, enabling virtualization software from Citrix, Microsoft, and VMware to quickly deliver desktop images and graphics to remote clients in a distributed computing environment. HP will add NVIDIA graphics cards to its own ProLiant GEN8 ws460c Blade server.

The grid card supports Nvidia's newest K1 and K2 graphics processors based on the Kepler architecture, with the same GPU design in some of the world's fastest supercomputers. HP previously provided the Quadro processor in the ProLiant ws460c Gen8 Blade, and the new video card will increase the number of virtual machines that can be deployed. HP declares that grid will also improve graphics delivery to remote clients. And it is expected to use the graphics card rich blade Server to replace the workstation to achieve remote to thin client delivery high-end graphics.

It is clear that Nvidia Tegra K1 targeting the micro-server market is also emulating the Nvidia grid to establish its position in the micro-server chip market, with Nvidia's expertise in GPU acceleration and nvidia Tegra K1 has achieved good market results in the mobile end market, and believes that with its excellent performance and power consumption control, we have reason to believe that Nvidia Tegra K1 will take a place in the micro-server chip market. However, nvidia in the ARM micro-server chip market also face AMD, Appliedmicro and other manufacturers of competition.

Online Mall goods/Specifications/Promotional prices (author: Li to the Executive editor: Li Xiangjing)

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.