In The News

Tachyumは、同社のProdigy Universal Processorが新しいhigh-performance computing（HPC）および人工知能（AI）スーパーコンピューターデータ センターの機能をどのように強化するかを詳細に説明したホワイトペーパーを発表した。このプロセッサーは、現在のスーパーコンピューターのパフォーマンスを超えるように設計されており、将来のシステムに設定されたベンチマークを超えることを目指している。Prodigyのアーキテクチャーは、均質なスーパーコンピューター環境を実現し、開発、導入、メンテナンスを簡素化するように設計されており、現在システムアーキテクチャーによって制限されているAIデータセンターや研究施設にとって理想的なソリューションとなっているとのこと。

Tachyum is partnering with M Computers, an IT services provider based in the Czech Republic, to bring its Prodigy high-capacity data processing technology to commercial, industrial and scientific research organisations in Central and Eastern Europe (CEE).

Le processeur Prodigy se démarque par sa polyvalence, en combinant les fonctions d’un CPU, d’un GP-GPU et d’un TPU. Le slovaque, qui en est à l’origine, s’attaquera au marché du calcul intensif l’an prochain.

“These improvements will allow for quick and seamless integration of technologies into Tachyum-based environments when deployed in data centers. As we near volume production of Prodigy, it is imperative that our software provides the tools supercomputers require to transform the industry.”

Built using field-programmable gate array (FPGA) emulation boards, Tachyum has been hailing Prodigy’s significantly improved performance and lower lower energy consumption for the past few years.

Targeted at hyperscale data centers, the Prodigy Universal Processor architecture is predicted to out-perform central processing units (CPUs), graphics processing units (GPUs), and tensor processing units (TPUs) for data center, artificial intelligence (AI), and high-performance computing (HPC) applications. For example, Prodigy will outperform NVIDIA’s fastest GPU in HPC, as well as AI training and inference tasks (125 HPC Prodigy racks can deliver 32 tensor EXAFLOPS).

Prodigy’s intense computing muscle can help AI use cases in particular. Convolutional neural networks, deep learning AI, symbolic AI, general AI, and bio AI are the disciplines that have emerged in recent years, each with its own set of algorithms and computing criteria. Human brain modeling, meanwhile, is in high demand by R&D ventures due to its promise of extracting information from large data sets. The Tachyum Universal Processor Platform is suitable for projects like the real-time Human Brain Project, which needs more than 1019 Flops (10,000,000,000,000,000,000 floating-point operations per second – 10 exaflops), as well as supplying computing resources for science and engineering solutions that today’s systems cannot offer.

Revolutionary microchip hailed as ‘generational’ breakthrough that will upend defense tech