Semiconductor startup Tachyum Inc. today announced that it has opened new offices in Slovakia that will enable it to best address the regional needs of its growing number of customers, partners, vendors and personnel throughout the European Union. Tachyum’s worldwide headquarters remain located in Silicon Valley.
Tachyum’s newest facilities will offer the company a foothold in the strategically important European marketplace as well as enabling it to leverage the technological expertise of its Slovakian employees as work progresses on deploying its flagship Prodigy Universal Processor Chip. Tachyum’s new Slovakian-based offices comprise 7,000 sq. ft. of modern Class-A offices capable of accommodating 50 people, an internal datacenter, laboratory, Q&A infrastructure and a supercomputer reference design site. Tachyum continues to seek highly qualified full-time engineers and scientists who are eager to bring their skill set and expertise in the fields of advanced compiler design and chip performance optimization to this regional headquarters.
“Our new Slovakian headquarters was needed to accommodate our growing workforce and represents our entry into the next successful phase of operations,” said Dr. Radoslav Danilak, Tachyum founder and CEO. “Slovakia is not only dear to my heart but continues to be a center of excellence throughout Europe in terms of economic opportunities and quality of engineers available who can help us deliver Prodigy to the world. Having a state-of-the-art workplace available to our team ensures that they are able to utilize a full suite of development tools and resources at the ready to ensure Prodigy’s success in the modern IT infrastructure.”
Prodigy, the company’s 64-core flagship product, is scheduled for high-rate production in 2021. It outperforms the fastest Xeon processors at 10x lower power (core vs. core) on data center workloads, as well as outperforming NVIDIA’s fastest GPU on neural net AI training and inference. Due to its high computational density and I/O bandwidth, networks of Prodigy processors comprising just 125 HPC racks, can deliver an ExaFLOPS (a billion, billion floating point operations per second) of capacity. Prodigy’s 3X lower cost per MIPS compared to other CPU competition, coupled with its 10X processor power savings, translates to a 4X reduction in Data Center TCO (Annual Total Cost of Ownership: CAPEX + OPEX). Even at 50 percent Prodigy attach rates, this translates to billions of dollars per year in real savings for hyperscalers such as Google, Facebook, Alibaba and Amazon.
Since Prodigy can seamlessly and dynamically switch from data center workloads to AI or HPC workloads, unused servers can be powered up, on demand, as ad hoc AI or HPC networks – CAPEX free, since the servers themselves are already purchased. Every Prodigy-provisioned data center, by definition, becomes a low-cost AI center of excellence, and a low-cost HPC system.
