Pico Computing Takes Scale-Up Approach to FPGAs

By Michael Feldman

February 17, 2010

As high performance computing vendors polish their server and workstation portfolios with the latest multicore CPU and GPGPU wonders, Pico Computing is quietly making inroads into the HPC application space with its FPGA-based platforms. By picking the spots where reconfigurable computing makes the most sense, the company is looking to leverage its scalable FPGA technology to greatest effect.

Seattle-based Pico was formed in November 2004 by founder Robert Trout. Using internal funding, the startup spent a couple of years on product development and subsequently started bringing its Xilinx-based FPGA computing platforms to market in 2007 and 2008. True to its name, Pico is a small company, with a staff of a dozen or so full-timers. As a private entity, they are not obliged to release financial results, but according to Mark Hur, Pico’s director of sales and marketing, the company is profitable today.

The company currently offers a range of platforms from a single FPGA card to large-scale FPGA “clusters” that contain over 100 of the devices in a 4U chassis. The company’s flagship E-16 Virtex-5 FPGA card was released in 2007. “To this day, that’s been the most successful product we’ve launched thus far,” says Hur. According to him, there are now multiple clusters of E-16s in the marketplace.

Recently, Pico demonstrated a password recovery system using a cluster of 77 Virtex-5 FPGAs, housed in a 4U enclosure and consuming less than 900 watts of power. According to the company, the system provides the computational equivalent of about 1,000 dual-core CPUs (Intel Core 2 Duo) for different recovery algorithms, specifically FileVault, Wi-Fi Protected Access (WPA), and Wired Equivalent Privacy (WEP). In fact, for the WEP algorithm, the Pico cluster delivered a 4,620-fold performance improvement and a 1,000-fold decrease in power consumption compared to the dual-core CPU implementation.

That level of performance and compute density for cryptography applications helps explain why Pico’s most beloved market is data security. The three-letter federal agencies in the US government are the main customers here, and they buy both off-the-shelf and custom products from the company. Security still represents the majority of Pico’s business today, although you’re not likely to see an NSA code cracking case study on the company’s Web site anytime soon.

Other favorite application areas for Pico include bioinformatics, financial analytics, image processing, and certain other types of scientific computing. The reason that FPGAs are so adept at these types of applications, from both a performance and power consumption point of view, is their ability to morph their hardware structures to match operators and data types for a given algorithm. This is especially true when the underlying algorithms are not based on typical integer or floating point data types.

In genomics applications, for example, a lot of algorithms are based on the four fundamental nucleoside bases (adenine, thymine, guanine, cytosine) that make up RNA and DNA. Thus a nucleoside data type would only be two bits wide. And unlike CPUs and GPUs, you can map FPGA resources to match that data size exactly. “You don’t need full 32-bit or 64-bit data paths and operators,” explains David Pellerin, Pico’s director of strategic marketing. “It’s wasteful.” That’s why some applications that get 100-fold acceleration from a GPU can get 1,000-fold from an FPGA, when compared to a CPU.

Pellerin, who used to be the chief technology officer at Impulse Accelerated Technologies, the makers of FPGA programming language Impulse C, was brought aboard Pico to energize the company’s marketing story and get behind some of the new product rollouts they’ve launched over the past few months. The newest offerings are based on the latest Spartan-6 and Virtex-6 hardware from FPGA-maker Xilinx. Pico’s most recent addition, the M-series modules, allows customers to construct standard-sized PCIe cards with up to 12 FPGAs.

Pico’s flagship E-series cards, on the other hand, plug into PCIe slots on a desktop system. But like the M-series, they can also be scaled into multiple FPGA configurations to build a computationally-dense FPGA cluster inside a single compute node. For HPC workloads especially, up to seven of the latest E-18 cards can be plugged into a PCIe carrier card, and multiple carrier cards can be installed into a 4U rack-mounted chassis. The idea is for customers to begin development with a single card plugged into a laptop or desktop, and when it’s time to deploy the full configuration, multiple cards can be plugged into PCIe backplane and installed in rack-mounted appliance or server.

From the software side, Pico has a consistent set of APIs that apply across its entire product set, and these interfaces can be accessed from either low-level Verilog code, or an FPGA-friendly C language, like Impulse C. Most of Pico’s customers writing cryptography apps use Verilog, but Impulse C tends to be more popular in bioinformatics and more traditional HPC codes.

Unlike other FPGA board makers, where one or two devices is matched to a host processor, Pico builds modular devices and backplanes such that as many as 177 FPGAs can be connected to a single CPU. That level of scalability means customers can squeeze a huge amount of computing hardware into very small enclosures. Since the core of most of these algorithms is just highly parallelized bit arithmetic, the CPU’s role is limited to driving the sequential part of the application. “For many applications, certainly in areas like cryptography and bioinformatics, the more FPGAs you can throw at the problem, the better it’s going to be,” says Pellerin.

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!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

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

March 18, 2024

Nvidia's latest and fastest GPU, codenamed 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…

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…

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…

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…

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…

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…

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

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…

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…

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…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire