Прочтение статьи займет 3 минут
Пресс-релиз
SAN JOSE, Calif., June 20, 2018 – Dr. Radoslav “Rado” Danilak, co-founder and CEO at Silicon Valley startup Tachyum Inc., will be discussing how to best address the unprecedented compute performance and power efficiency needs required for artificial intelligence, high performance computing and hyperscale workloads as part of ISC High Performance 2018 in Frankfurt, Germany, June 24-28.
Danilak has been invited to present a workshop entitled “Prodigy Universal Processor for AI/HPC and Hyperscale Workloads” June 26 at 2:30 p.m. The 30-minute presentation will feature information about Tachyum’s recently announced Prodigy processor chips and how their performance attributes will advance progress to deep learning neural network training and inference; general AI, symbolic AI, bio AI; big data; in-memory data analytics; and most other hyperscale workloads, making them faster and more efficient than existing solutions.
“Complex problems often require complex solutions and that’s been true in the semiconductor industry in its approach to density, power efficiency and cost – until now,” said Danilak. “At Tachyum, we are pushing the industry off the edge of the plateau they’ve been stuck on with a series of Prodigy chips that overcome the problems caused by device physics to unlock new potentials in AI and HPC environments. I look forward to sharing our approach with attendees at ISC High Performance 2018 as I showcase how Prodigy helps run most hyperscale datacenter workloads faster and more efficient than current approaches.”
Tachyum’s new Prodigy processor family offers the programming ease comparable to a CPU with performance and efficiency comparable to GP-GPU, for a universal-purpose processor that can handle hyperscale workloads, AI, HPC and other demanding applications with ease. A typical hyperscale data center using servers equipped with Prodigy will provide 10 times the compute performance at the same power budget. Prodigy will reduce data center TCO by a factor of four; conversely, a Prodigy-based data center delivering the same performance as conventional servers can be built in as small as 1 percent the space and consume one-tenth the energy.
ISC High Performance is dedicated to tackling HPC technological development and its application in scientific fields, as well as its adoption in commercial environments. The 2018 topics selected to appeal to the global HPC community will be presented by speakers considered experts in their chosen field. Additional information about the event for high performance computing, networking and storage is available at https://www.isc-hpc.com/
https://www.linkedin.com/company/tachyum
https://www.facebook.com/Tachyum
Named for the Greek “tachy,” meaning speed, combined with “-um,” indicating an element, Tachyum emerged from stealth mode in 2017 to engineer disruptive intelligent information processing products. Tachyum’s founders have a track record of solving problems caused by device physics to deliver transformational products to market, and are backed by IPM Growth, the Central & Eastern European venture capital platform, as Tachyum’s lead investor.