SRC Debuts Defense-Hardened FPGA Server

By Tiffany Trader

May 28, 2015

The SRC Saturn 1 server debuted today, built by reconfigurable computing specialists SRC Computers and positioned as an x86 alternative for high-volume workloads in hyperscale computing and big data analytics.

While we have seen several FPGA-based server solutions come to market in the past year, the Saturn-1 is distinguished by its pedigree and insulation from the usual complexities of FPGA programming. SRC was founded in 1996 by supercomputing innovator Seymour R. Cray and Intel investor and former director James Guzy. Cray was focused on how to get the most horsepower out of a very small number of processors and how to harness the power of multiple processors, while Guzy et. al. at Intel were building a general purpose processor designed for the personal computer. Recognizing that there are limitations to using a general purpose processor for very specific tasks, the duo came up with the platform that would become the Saturn 1.

For 12 years, the FPGA-based server and development platform CARTE have been used for a variety of defense and intelligence solutions, but SRC thinks the time is right to enter a wider market.

Vice President of Sales and Marketing at SRC Computers Dave Eaton explained to HPCwire that many of the requirements developed for defense carry over to high-performance enterprise apps, for example the push for more performance per processor, minimized footprint and reduced power.

“The server market is starting to ask a lot of the same questions,” says Eaton.

Moore’s law-driven performance boosts based on faster clock rates petered out in the mid-2000s. Multicore technology adds several cores to one die to increase throughput, but it doesn’t address the inherent problem: microprocessor performance has hit a wall. Unlike the x86 microprocessor, which uses 90 percent of its resources to store and shuttle data to the remaining 10 percent, the SRC sheds unnecessary overhead by using only the logic required by the workload. All instructions are executed at the same time – in just one clock cycle. SRC reports that the server is up to 500x faster than traditional x86 designs.

SRC has put over $100 million into designing this new platform, which has been hardened by over a decade of government use. The firmware is version 8 and CARTE is on version 12.

SRC Saturn 1 Server slide

The Saturn 1 server cartridge is available from SRC Computers as a standalone server and through HP as part of its Moonshot chassis. As depicted in the image above, there are two Stratix-IV FPGAs on one card. The top one, the user FPGA, is completely available for the customer’s application, and the system FPGA below that, has software written by SRC that ties all the components together into a unified system. There are also two memory banks, a small four-core Intel processor, and the edge connector which has multiple Ethernet ports.

The server cartridges can be dropped into an HP moonshot chassis, which has a passive backplane and is processor agnostic. Each server runs at 45 watts, and with 42 Saturn 1 servers in a Moonshot chassis, the power load is 2000 watts. A rack outfitted with 9 chassis draws about 20,000 watts.

The server is equipped with Stata-IV FPGAs, but the platform is actually processor-agnostic. Earlier iterations employed Lucent, Altera, Xilinx, before returning to Altera with the current version. The driving factor for FPGA selection is access to pure horsepower and avoidance of unnecessary industry-specific add-ons.

The deterministic nature of the platform means that programs executed on the Saturn 1 will run with the exact same performance every single time. Other benefits compared with traditional x86 processors include orders of magnitude performance increases, reduction in processing power consumption, and smaller footprint.

Another benefit that SRC emphasizes is ease-of-use. The time and effort required to program FPGAs has kept them from enjoying wider adoption. Instead of being relegated to a low-level language like Verilog, SRC customers can use the custom development environment, CARTE, to write programs with a familiar high-level language, such as C+, Python and Ruby, so the server can be deployed just like a regular x86 server. SRC reports that companies have ported their applications to the Saturn server in just three days.

As for HPC-specific use cases, Eaton says that the Saturn 1 is ideal for addressing hot spots – that specific place in a program or algorithm that burns up 90-95 percent of CPU cycles. He shares the example of a financial institution that prices options using a Black-Sholes algorithm souped-up with additional CPU-intensive constants and adjustments. Since moving over to Saturn 1, shops like this one are seeing 20-30x speedups above what they were getting on the most-performant x86 machines. This also allows them to add even more features to the algorithms without slowing down the processing, says Eaton.

For those worried about the lack of flexibility of the FPGA model, it may be helpful to know that processors can be completely reprogrammed in a little less than a second. This means servers can be optimized on the fly to match peak workloads. For example, using the Saturn 1, a company like Google would be able to configure the processors to handle search requests during peak daylight hours and then at night when searches are less frequent, the server environment could be optimized for Web crawling.

“You’ve heard about the search for the software-defined server?” inquires Eaton. “It’s one thing to have a software-defined server where I can change memory configuration or change how much hard drive space is there, now we’re talking about defining the actual processor on the server itself with software.”

The SRC server is shipping immediately, however very large orders of several hundred systems may take 6-8 weeks to satisfy. Servers cost $19,950 each and volume pricing is available. Licenses for the CARTE development environment are $14,000 per seat and the company offers a three-day workshop for learning CARTE that is priced according to the number of participants. Support for both the software and hardware comes through SRC if desired, or if the HP Moonshot chassis version is purchased, HP can provide support based on the customer needs.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, code-named Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from its predecessors, including the red-hot H100 and A100 GPUs. Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. While Nvidia may not spring to mind when thinking of the quant Read more…

2024 Winter Classic: Meet the HPE Mentors

March 18, 2024

The latest installment of the 2024 Winter Classic Studio Update Show features our interview with the HPE mentor team who introduced our student teams to the joys (and potential sorrows) of the HPL (LINPACK) and accompany Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the field was normalized for boys in 1969 when the Apollo 11 missi Read more…

Apple Buys DarwinAI Deepening its AI Push According to Report

March 14, 2024

Apple has purchased Canadian AI startup DarwinAI according to a Bloomberg report today. Apparently the deal was done early this year but still hasn’t been publicly announced according to the report. Apple is preparing Read more…

Survey of Rapid Training Methods for Neural Networks

March 14, 2024

Artificial neural networks are computing systems with interconnected layers that process and learn from data. During training, neural networks utilize optimization algorithms to iteratively refine their parameters until Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, code-named Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Survey of Rapid Training Methods for Neural Networks

March 14, 2024

Artificial neural networks are computing systems with interconnected layers that process and learn from data. During training, neural networks utilize optimizat Read more…

PASQAL Issues Roadmap to 10,000 Qubits in 2026 and Fault Tolerance in 2028

March 13, 2024

Paris-based PASQAL, a developer of neutral atom-based quantum computers, yesterday issued a roadmap for delivering systems with 10,000 physical qubits in 2026 a Read more…

India Is an AI Powerhouse Waiting to Happen, but Challenges Await

March 12, 2024

The Indian government is pushing full speed ahead to make the country an attractive technology base, especially in the hot fields of AI and semiconductors, but Read more…

Charles Tahan Exits National Quantum Coordination Office

March 12, 2024

(March 1, 2024) My first official day at the White House Office of Science and Technology Policy (OSTP) was June 15, 2020, during the depths of the COVID-19 loc Read more…

AI Bias In the Spotlight On International Women’s Day

March 11, 2024

What impact does AI bias have on women and girls? What can people do to increase female participation in the AI field? These are some of the questions the tech Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Analyst Panel Says Take the Quantum Computing Plunge Now…

November 27, 2023

Should you start exploring quantum computing? Yes, said a panel of analysts convened at Tabor Communications HPC and AI on Wall Street conference earlier this y Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Training of 1-Trillion Parameter Scientific AI Begins

November 13, 2023

A US national lab has started training a massive AI brain that could ultimately become the must-have computing resource for scientific researchers. Argonne N Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire