Tachyum Logo

We are creating the future now!

Tachyum is enabling human brain-scale AI and advancing the entire world to a greener era, by delivering the world’s first universal processor.


Volume 4, Number 2, April 2024

Prologue picture

Dr. Radoslav Danilák, Founder and CEO of Tachyum

In the first quarter of 2024, we revealed our platform strategy which includes offering evaluation platforms to early customers and partners for testing and evaluation. The evaluation platforms will be utilized as enablers for OEM (Original Equipment Manufacturer) and ODM (Original Design Manufacturer) partners to leverage into design production platforms.

We presented three evaluation platforms/reference designs: Prodigy ATX for generative AI (Artificial Intelligence), which excels in running LLMs (Large Language Models) which address an extensive range of use cases; Prodigy 1U for AI inference, cloud applications including web servers, storage, database, big data, and analytics; and Prodigy 2U for the highest performance applications, including HPC and big AI (including AI training). We have chosen Chenbro, a leading designer and manufacturer of rack servers and storage chassis for datacenters and enterprises, as a partner for Prodigy evaluation platforms.

Tachyum’s engineers added and demonstrated additional hardware units integrated with the Prodigy FPGA prototype: Performance Monitoring Unit (PMU) and Machine Check and Recovery (MCR) capabilities with the Linux Error Detection and Correction (EDAC) subsystem. The PMU is an essential tool for collecting information about performance bottlenecks and MCR with Linux EDAC driver is essential for data center applications. We also have completed testing of full-fledged hardware debugging features of the Prodigy FPGA prototype.

On the software side, Tachyum’s engineers upgraded the Prodigy software stack before the anticipated launch of its beta version. Quality completion of Prodigy’s software stack is a key component as we continue to advance towards chip production and distribution.

I would also like to mention, that we published materials detailing our RAS (Reliability, Availability, and Serviceability) strategy. The importance of RAS was recently stressed by Nvidia as part of their latest keynote at the GTC 2024 event. The revolutionary new architecture of our Prodigy Universal Processor requires that the design be complemented by high reliability, availability, and serviceability, to ensure that customer platforms are not only high performance but reliable and easy to service in the field.

Prodigy 4-Socket System Outperforms Nvidia GB200 NVL72

At its recent annual developer conference GTC 2024, Nvidia announced its Blackwell platform. It is the new NVIDIA B200 Tensor Core GPU, designed for artificial intelligence (AI) calculations and the NVIDIA GB200 Grace Blackwell Superchip that connects two B200s to the NVIDIA Grace CPU over a 900GB/s ultra-low-power NVLink chip-to-chip interconnect.

The GB200 is a key component of the NVIDIA GB200 NVL72 rack-scale system for the most compute-intensive workloads. Tachyum compared this system model with its Prodigy 4-socket system.

The comparison showed that Prodigy Racks deliver up to 12x higher AI performance and 8x higher HPC performance compared to Nvidia’s GB200 NVL72. A price comparison of the Nvidia GB200 versus Prodigy 4-socket reveals a 3x advantage for the Prodigy.

New White Papers

Tachyum Solidifies Reliability, Availability and Serviceability of Prodigy Universal Processor

Tachyum added to its extensive white paper library the publication of an overview examining its Reliability, Availability and Serviceability (RAS) strategy, including a detailed look at the key RAS features being built into Prodigy, the world’s first Universal Processor, which will help satisfy the demands of today’s data centers.

RAS is a set of related attributes that must be considered when designing, manufacturing, purchasing and utilizing a computer product or component. Designed from the ground up, Tachyum’s comprehensive RAS strategy encompasses multiple facets at the silicon, platform and system levels to ensure Prodigy deployments provide high performance along with high reliability and availability at all levels.

Decorative quotemark

“A comprehensive approach to RAS becomes increasingly important as process shrinks drive higher density for components and platforms. In addition to the ever-increasing density, manufacturing chips on shrinking process nodes increases the risk of soft errors. Prodigy addresses these increased risks with a thorough approach to device and system reliability, ensuring that Prodigy-based systems function with maximum uptime to address the performance and demands of today’s data centers.”

Dr. Radoslav Danilák


Tachyum Has Disclosed 1U and 2U Server/HPC/AI Reference Designs

Tachyum is bringing 1U and 2U platform solutions to market behind a strategy that ensures customers and partners will be able to quickly and easily test, benchmark and deploy Prodigy solutions across a broad range of supported applications and workloads.

Tachyum’s platform strategy includes offering evaluation platforms for early testing with OEMs and ODMs able to incorporate Prodigy into their own designs. The 2U evaluation platform, optimized to address the high-performance needs of HPC and Big AI, will be the first to sample in Q1 of 2025. The 1U platform, targeting applications such as AI inference and a wide range of cloud applications, follows in the second quarter.

Tachyum has chosen Chenbro as the chassis partner for the Prodigy evaluation platforms. Chenbro’s standard chassis products provide solutions for both 1U and 2U that address Prodigy’s high-performance requirements, allowing Tachyum to focus on the device and motherboard development.

Decorative quotemark

“We’re excited to partner with Tachyum. Our chassis solutions, coupled with Prodigy’s innovation, will drive new standards in AI and HPC.”

Eric Hui, President of Chenbro


Latest Achievements

Tachyum Completes Testing of Debugger on its Prodigy FPGA Prototype

Tachyum has completed testing of full-fledged hardware debugging features of the FPGA prototype of its Prodigy Universal Processor. This latest capability has undergone testing with GNU Debugger (gdb), a widely used Linux tool for debugging software, to ensure successful operations and is a key component of Prodigy’s continued march towards production.


Tachyum Demonstrates Machine Check and Recovery on Prodigy FPGA

Tachyum has added Machine Check and Recovery (MCR) capabilities with the Linux Error Detection and Correction (EDAC) subsystem to the Prodigy Universal Processor with successful deployment demonstrated as part of the FPGA emulation system.


Tachyum Demonstrates PMU Running on Prodigy FPGA Emulation System

Tachyum has added a Performance Monitoring Unit (PMU) to its Prodigy FPGA emulation system, empowering customers and partners with the ability to address bottlenecks and better optimize Prodigy performance for all applications and workloads.



Curious Artificial Intelligence

Curious Artificial Intelligence

April 9, 2024, Bratislava, Slovakia

Curious Artificial Intelligence

Matej Pecháč, Tachyum’s AI Software Engineer, gave an interesting lecture about “Curious Artificial Intelligence” as part of a lecture series about High Performance Computing applications organized by the Slovak National Supercomputing Center.

Students Visited Tachyum Offices

March 12, 2024, Bratislava, Slovakia

Students Visited Tachyum Offices

Tachyum welcomed a group of young students from SPŠE in Prešov to its premises in Bratislava to show them the innovative technologies being developed in Slovakia. It was a pleasure that 30 talented students took an active interest in the development of the world’s first universal processor. They spent three hours of interesting discussions with Tachyum engineers as well as with the sales and marketing teams.

Invest In Austria 2024

February 15, 2024, Vienna, Austria

Invest In Austria 2024

Tachyum was a part of InvestInAustria, an exclusive high-level event for selected CEOs of leading international companies. The event was held in the historic ambience of Schönbrunn Palace, where Robert Cisar, BD Manager of Tachyum had conversations with members of the Federal Government and representatives of Austrian state agencies about potential cooperation in the semiconductor industry.

ETP4HPC Conference

ETP4HPC Conference

February 13 - 14, 2024, Sassenheim, Netherlands

ETP4HPC Conference

Tachyum’s BD team was a part of the ETP4HPC conference in Sassenheim. The vision is to be a catalyst of Advanced Computing provision in Europe and beyond. Robert Cisar and Marwan Ajam Oghli discussed the framework ETP4HPC 2.0 to achieve the objectives and agreed on the main instructions and priorities.

Tachyum Logo

Tachyum® and Tachyum Prodigy®, TPU® are trademarks of Tachyum Ltd, registered in the United States and other countries. All other brand and product names are trademarks of their respective owners. This document is provided for informational purposes only. All statements regarding Tachyum's future direction and intent are subject to change or withdrawal without notice and represent goals and objectives only. © 2019-2024 Tachyum, Inc. All rights reserved.

Tachyum, Inc., 8275 South Eastern Ave, Ste 233, Las Vegas, NV 89123, USA

Tachyum s.r.o., Karadžičova 14, 821 08 Bratislava, Slovak Republic, EU

FacebookXLinkedInYouTubeRSS Feed