Tachyum demonstrates baseboard management controller on Prodigy emulation


LAS VEGAS, September 20, 2022 – Tachyum today announced that it has successfully demonstrated the final piece of its core software stack with a Baseboard Management Controller (BMC) running on a Prodigy emulation system. This step allows the company to provide OEMs/ODMs and system integrators with a full software and firmware stack and is a key component of the upcoming Tachyum Prodigy 4 socket reference design.

BMCs are specialized controllers that monitor the status of a computer or hardware, including aspects such as system health, logging events for fault analysis, and a range of management capabilities to distance. Tachyum’s Prodigy Server BMC is based on the AST2600 System-on-Chip (SoC), ASPEED’s 7th generation server management processor and the world’s first BMC SoC to adopt advanced 28nm process technology.

Tachyum joined OpenBMC, a Linux Foundation collaborative open source project, in May 2020 as a community contributor seeking to define standards for the standard BMC firmware stack that will run on heterogeneous systems, including data from enterprise, HPC, telecom, and cloud scale. centers. As part of the OpenBMC project, Tachyum is able to reuse much of the functionality previously supported by the project, including:

  • Host management: power, cooling, LEDs, inventory, events, watchdog
  • Full IPMI 2.0 (Intelligent Platform Management Interface) compliance with DCMI (Dublin Core Metadata Initiative)
  • Support code update for multiple BMC/BIOS images
  • Web-based user interface
  • REST (Representational State Transfer) interfaces
  • D-Bus based interfaces
  • Serial over LAN (SoL) based on SSH (Secure Socket Shell)
  • Remote KVM (kernel-based virtual machine)
  • Hardware Simulation
  • Automated tests
  • User Management
  • Virtual media
  • Verified Boot
  • OpenCompute Redfish Compliance

“We are excited to reach the end of our core software stack development efforts with the successful addition of BMC to our Unified Extensible Firmware Interface (UEFI), boot loaders, Linux/FreeBSD, KVM, compilers/debuggers, native libraries and applications,” said Dr. Radoslav Danilak, Founder and CEO of Tachyum. “Together, this comprehensive software stack represents the foundation of Tachyum supercomputers, AI, and cloud solutions. Now we can focus our attention on integrating Prodigy with high-level management software ahead of its upcoming official debut.

Tachyum’s Prodigy integrates 128 custom-designed high-performance 64-bit compute cores with CPU, GPU, and TPU functionality in a single device, allowing it to deliver performance up to 4x that of the highest performing x86 CPUs (for cloud workloads) and up to 3x that of the highest performing GPU for HPC and 6x for AI applications.

Prodigy delivers unprecedented data center performance, power and economy, dramatically reducing CAPEX and OPEX. Due to their utility for high-performance and business applications, Prodigy-powered data center servers can seamlessly and dynamically switch between workloads, eliminating the need for expensive dedicated AI hardware and dramatically increasing utilization. servers.

About Tachyum

Tachyum is transforming the AI, HPC, and public and private cloud data center markets with its recently launched flagship product. Prodigy, the world’s first general-purpose processor, unifies the functionality of a CPU, GPU, and TPU into a single processor that delivers industry-leading performance, cost, and power efficiency for specialty and high-end computing. general use. When Prodigy processors are delivered in a large-scale data center, they enable all AI, HPC, and general-purpose applications to run on hardware infrastructure, saving businesses billions of dollars. dollars per year.


Source: Tachyum

Previous Uptime Institute's 2022 Global Data Center Survey Reveals Strong Industry Growth as Operators Prepare to Expand Sustainability Requirements
Next Visit Sacramento launches Spanish section on its website