Categories: Wire Stories

New TED AI Lab Featuring Cerebras Systems CS-1 AI Accelerator Opens in Tokyo

CS-1 Selected to Dramatically Reduce Training Time and Offer Ultra-Low Latency Inference for AI Models

TOKYO & SUNNYVALE, Calif.–(BUSINESS WIRE)–Tokyo Electron Device (TED) and Cerebras Systems, a company dedicated to accelerating Artificial Intelligence (AI) compute, today announced the opening of the TED AI Lab, featuring the industry-leading Cerebras Systems CS-1 AI accelerator. Designed to test, verify and support deep learning applications, including Natural Language Processing (NLP), the new TED AI Lab selected CS-1 in order to dramatically reduce training time for increasingly complex AI models.

�We are thrilled to continue our longstanding partnership with TED, and we commend them on opening a leading-edge AI lab that will support customers in performing the hardest AI work more quickly and more easily,” said Andrew Feldman, CEO and co-founder of Cerebras. “As Cerebras continues our rapid global expansion, we look forward to realizing our mission of driving AI compute excellence in the innovative market of Japan.”

TED AI Lab Overview

Located in TED’s Engineering Center (Tsuzuki-ku, Yokohama), the new TED AI Lab provides an environment for customers who want to train AI models more rapidly than ever before and optimally scale AI development. Users of the ultra-fast Cerebras CS-1 deep learning system can evaluate performance of the dedicated AI accelerator, optimize for system scale.

“Cerebras Systems is pleased with the opening of the TED AI Lab, featuring the Cerebras CS-1,” said Hiromasa Ebi, GM, Cerebras Systems G.K. “Through the TED AI Lab’s verification environment service, we hope that customers in data centers, research institutes, and academic institutions who are looking for a large-scale deep learning environment using big data will be able to try out Cerebras’ ultra-fast deep learning system in order to achieve faster processing times, at less power consumption and less space. Cerebras Systems looks forward to continuing to work with Tokyo Electron Device to expand business opportunities and contribute to the development of AI technology in Japan.”

Verification Support Service

The TED AI Lab include the Cerebras CS-1 system, and the entire system environment is available for use. TED engineers will provide lectures on product usage, Q&A sessions, and other verification support, helping users to reproduce and verify their own on-premise environments. In addition to remote access, users can connect and use the system on-site even when the cloud environment is not available for security reasons.

?TED AI Lab Configuration?

TED AI Lab Configuration

AI Accelerator

Cerebras CS-1 System

Server

Dell PowerEdge R640

Switch

Arista DCS-7060CX2-32S

Storage

Pure FlashBlade 123TB?17TB x 7 blade?

Details of the TED AI Lab tour and validation support services

URL?https://cn.teldevice.co.jp/technical_support/ted-ai-lab/

TED will continue to support AI development with cutting-edge products and services, as well as advanced technical support, to meet the various challenges faced by customers throughout AI development.

About Cerebras Systems

Cerebras Systems is a team of pioneering computer architects, computer scientists, deep learning researchers, and engineers of all types. We have come together to build a new class of computer to accelerate artificial intelligence work by three orders of magnitude beyond the current state of the art. The CS-2 is the fastest AI computer in existence. It contains a collection of industry firsts, including the Cerebras Wafer Scale Engine (WSE-2). The WSE-2 is the largest chip ever built. It contains 2.6 trillion transistors and covers more than 46,225 square millimeters of silicon. The largest graphics processor on the market has 54 billion transistors and covers 815 square millimeters. In artificial intelligence work, large chips process information more quickly producing answers in less time. As a result, neural networks that in the past took months to train, can now train in minutes on the Cerebras CS-2 powered by the WSE-2.

About Tokyo Electron Device (TED) CN BU:

Tokyo Electron Device (TED) is a technical trading firm with a “trading business” function that provides semiconductor products and IT solutions as well as a “development business” function that performs commissioned designing and the development of own-brand products.

URL? https://www.teldevice.co.jp/eng/

The CN BU has marketing functions to catch the world’s most advanced technology quickly and handles storage, network and security products widely and it provides it as a business solution in the cloud era.

We consistently provide optimal solutions for customers from installation to support.

For more information, visit: http://cn.teldevice.co.jp/company_english/about_us

Contacts

Press contact (for media only)

Kim Ziesemer

Email: pr@zmcommunications.com

Alex

Recent Posts

Solarvest and Finhero Launch Vietnam’s First Solar Financing Fintech Solution

HO CHIN MIN CITY, VIETNAM - Media OutReach Newswire - 19 November 2024 - Solarvest…

37 mins ago

The Establishment Agreement of the International Mangrove Center was signed in Shenzhen, China

SHENZHEN, CHINA - Media OutReach Newswire - 18 November 2024 - On November 6, 2024,…

13 hours ago

Arla Foods Ingredients moves forward with acquisition of Volac Whey Nutrition business

TAIPEI, TAIWAN - Media OutReach Newswire - 18 November 2024 - Arla Foods Ingredients is…

16 hours ago

Golden Bull Award 2024 Raises the Bar, Celebrates Singapore’s Dynamic Businesses for Excellence and Growth

SINGAPORE - Media OutReach Newswire – 18 November 2024 - The esteemed Golden Bull Award,…

17 hours ago

China empowers the development of Asia-Pacific region

LIMA, PERU - Media OutReach Newswire - 18 November 2024 - Chinese President Xi Jinping…

17 hours ago

Amazon Singapore Unwraps 12 days of Incredible Deals this Black Friday from 21 November to 2 December

Shoppers can enjoy 12 days of exciting deals from top local and international brands, including…

19 hours ago