4 minutes de lecture
Press Release
LAS VEGAS, Nevada, May 4, 2022 – Tachyum™ Inc. today announced that it has progressed to running applications in Linux interactive mode on Prodigy FPGA hardware with SMP (Symmetric Multi-Processing) Linux and the floating-point unit enabled on the field-programmable gate array (FPGA) prototype of its Prodigy Universal Processor. This latest key milestone showcases Prodigy’s advanced level of maturity spanning its advanced CPU core, powerful software environment, and new third party hardware IP, bringing the company closer to product launch, and fulfilling its mission to transform data centers into greener Universal Computing Centers capable of enabling human brain-scale AI.
Tachyum successfully replaced the DDR5, PCI Express 5.0, and 112G SERDES IPs. The transition to new IPs is now successfully complete and the new IPs are integrated. The next milestone will be demonstrating the now completed vectorizing compiler to show Prodigy running vectorized code on the FPGA.
“We believe that with the new IPs we are ultimately ensuring that the final production version of Prodigy will perform better than expected. We are eager to bring Prodigy to market and revolutionize the concept of a data center, forever” said Dr. Radoslav Danilak, founder and CEO of Tachyum.
Successfully running code interactively proves the stability of the system and allows the company to move forward with additional testing before advancing to tape out and sampling later this year. With the replacement IP successfully integrated, Tachyum is able to continue building towards full production and profitability prior to launching an IPO.
This milestone is a critical turning point towards the final stage in the development of the Prodigy chip. It allows Tachyum to move from testing the design with billions of cycles in RTL simulation to the Quality Assurance (QA) stage to start running tests, regressions and conduct compatibility testing on the Prodigy FPGA prototype hardware, and start running quadrillions of cycles to test the chip before tape-out and sampling later this year, to ensure reliable operations.
Tachyum’s Prodigy processor can run HPC applications, convolutional AI, explainable AI, general AI, bio AI, and spiking neural networks, plus normal data center workloads, on a single homogeneous processor platform, using existing standard programming models. Without Prodigy, hyperscale data centers must use a combination of disparate CPU, GPU and TPU hardware, for these different workloads, creating inefficiency, expense, and the complexity of separate supply and maintenance infrastructures. Using specific hardware dedicated to each type of workload (e.g. data center, AI, HPC), results in underutilization of hardware resources, and more challenging programming, support, and maintenance. Prodigy’s ability to seamlessly switch among these various workloads dramatically changes the competitive landscape and the economics of data centers.
With all IPs being integrated, Tachyum will announce its newest suppliers soon. Customers and partners looking to gain early access to Prodigy can contact the company at to request pre-approval and an invitation to Tachyum’s Customer & Partner Portal.
A video demonstration of Linux booting interactive mode on FPGA prototype of Prodigy is currently available for viewing below.
https://www.linkedin.com/company/tachyum
https://www.facebook.com/Tachyum/
Tachyum is transforming AI, HPC, public and private cloud data center markets with Prodigy, the world’s first Universal Processor that delivers industry-leading performance, cost, and power efficiency for both specialty and general-purpose computing. When Prodigy processors are provisioned in a hyperscale data center, they enable all AI, HPC, and general-purpose applications to run on one hardware infrastructure, saving companies billions of dollars per year. A fully functional Prodigy emulation system is currently available to select customers and partners for early testing and software development. With data centers currently consuming over 3% of the planet’s electricity, predicted to be 10% by 2025, the ultra-low power Prodigy Universal Processor is critical, if we want to continue doubling worldwide data center capacity every four years. Tachyum, Co-founded by Dr. Radoslav Danilak with its flagship product Prodigy, is marching towards tape out and chip sampling in 2022, with software emulations and an FPGA-based emulator running native Linux available to early adopters. The company is building the world’s fastest 64 AI exaflops supercomputer in 2022 in the EU with Prodigy chips. Tachyum has offices in the United States and Slovakia. For more information, visit https://www.tachyum.com/.