Tachyum Joins UEFI Forum to Help Advance the State of the Technology Market

Estimated reading time: 2 minutes

Semiconductor startup Tachyum Inc. announced today that it has joined the Unified Extensible Firmware Interface (UEFI) Forum, a community of industry-leading OEMs, IHVs, chip manufacturers, and BIOS firmware and operating system members interested in improving information processing system performance and advancing security and interoperability through standards and best practices.

Tachyum is actively working on reference designs for its ODM, OEM, IHV, integrators and HPC/AI customers. That includes hardware as well as any necessary software and firmware, including UEFI. Tachyum is not only delivering chips but whole platforms to speed up adoption of its Prodigy Universal Processor. Tachyum will provide all necessary components, engineering models and drawings, as well as source code for its software and firmware components, enabling easy customization and differentiation by its partners.

“Creating reference designs, including firmware and software, is a proven winning solution,” said Dr. Radoslav Danilak, Tachyum founder and CEO. “As the founder of SandForce, a company that led the SSD revolution, I saw this recipe succeeding worldwide with the majority of the SSD vendors using a complete package of SandForce SSDs chips, firmware and software. We want to replicate that successful story here at Tachyum.”

Through a collaborative approach with world-class companies, institutions and experts, UEFI Forum continues to shape the future of personal and enterprise computing by jointly discovering new firmware technologies, developing those industry standards, and sharing knowledge and resources within the platform technologies community. By becoming a Contributor member of the association, Tachyum is positioned to help impact future specifications and shape new market opportunities as they arise.

“The UEFI Forum is made up of the world’s leading academic and technology industry leaders coming together to promote standardized interfaces that simplify and secure platforms and systems with developing next-generation technologies,” said Danilak. “We think it is important to be both members and advocates of these types of organizations to ensure that new innovations, like Prodigy Universal Processor-based systems, are able to get to market quickly without roadblocks that might otherwise inhibit the community at large from benefitting from them.”

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, 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.