Adapteva Launches Crowd-Source Funding for Its Floating Point Accelerator

By Michael Feldman

September 28, 2012

Chipmaker Adapteva is attempting to bypass the conventional venture capital funding route and collect money via a micro-investor platform known as Kickstarter. In the process, the company will open up its software and hardware design for its manycore Epiphany architecture, and deliver a parallel computing kit to anyone who can ante up $99.

The Kickstarter funding model relies on lots of small investors pledging relatively small amounts of money to bootstrap a project, in this case, for Adapteva’s “Parallella” $99 supercomputer board. The way it works is that the project creators set a funding goal and deadline. If the desired investment is collected before the deadline, all the would-be investors are charged and the project is delivered.

For Adapteva, they’re asking for enough investors to reach $750,000 within the next 30 days (starting this past Thursday). So if they get at least 7,500 takers before October 27, everyone who pledged $99 gets a board, software toolkit, and an Ubuntu Linux distro. The idea is to draw in lots of would-be developers (most of which are probably going to be coming from academic institutions) to jumpstart the Epiphany software ecosystem.

The company is initially aiming Epiphany at embedded and mobile device applications with a need for lots of flops — codes such as image recognition, signal processing, game physics, and the like. But since these same attributes of high flops and low power are also critical to supercomputing, the company is looking to break into the HPC business as well.

The main problem they’ve had to date is attracting enough investors and developers to get the chip on the fast track. Since its inception in 2008, Adapteva has collected $2.5 million in private investment and has partnered with Brown Deer Technology to deliver an OpenCL port for the architecture. That’s been enough to support four generations of processor development and an initial SDK, but to compete with the big boys in the accelerator business, like NVIDIA and Intel, Epiphany needs to attract a much larger developer community.

According to Andreas Olofsson, founder and CEO of Adapteva, right now a board outfitted with an Epiphany accelerator costs thousands of dollars, which greatly limits access for software developers. “Let’s open this up to everybody and sell it cheap,” he told HPCwire. Olofsson felt that couldn’t be accomplished within the confines of a traditional funding model, which is why they went the Kickstarter route.

The Parallella board they’re offering is outfitted with a dual-core ARM CPU, a 16-core Epiphany accelerator chip, 1 GB of RAM, a MicroSD card, two USB ports, and HDMI port, and an Ethernet connection. The kit also includes an I/O interface that can be hooked up to a sensor or camera for a real-world application The whole thing measures 3.4″ by 2.1″ — about the size of a credit card — and draws anywhere between 2.5 and 5 watts.

The low power is enabled by the ultra-efficient Epiphany RISC design. Adapteva has a 26-gigaflop, 16-core chip in production today and a 64-core pre-production version waiting in the wings http://www.hpcwire.com/hpcwire/2012-08-22/adapteva_unveils_64-core_chip.html. The 64-core accelerator delivers up to 100 gigaflops (single precision) on just 2 watts of power. At 50 gigaflops/watt, this latest Epiphany processor is probably the champ of energy-efficient computing today, at least in the floating point realm.

But right now, those chips are expensive to produce, mainly because Adapteva is employing a low-volume manufacturing process, which yields about 50 dies per wafer. If they had full production mask sets, they could shift into high-volume manufacturing and get thousands of dies per wafer. That would reduce the cost of an Epiphany processor to a few dollars per chip, which would make the $99 price point for the entire board feasible.

To get to that production model, the chip foundry needs to retool, which is a significant expense. That’s where at least some of the investment funds collected by the Parallella project comes in. The money will also be used to shrink the current reference board down to its credit-card size and set up a high-volume chip production flow.

Adapteva has also set an additional Kickstarter “stretch goal” of $3 million. If they hit that by the end of October, the company will offer a board outfitted with the 64-core Epiphany chip. For that privilege, an investor will have to kick in an additional $100 on top of their original $99 pledge.
 
In either case, with each board Adapteva will include their complete software development stack of compilers (C/C++, OpenCL), debugger, libraries, and drivers for free. And the entire stack as well as the board design will be provided as open source.

All of this is dependent upon getting at least 7,500 developers willing to plunk down $99 dollars for the kit. They’re off to a decent start. According to Kickstarter’s Parallella site, a day after they launched the program, they’ve signed up 532 backers who pledged at least $99. Olofsson is optimistic that this is indeed the model that will attract developers and get the technology the attention it deserves. “If we can’t get 7,500 people excited about our architecture for $99, maybe we should go home,” he says.

 


Related Articles

Adapteva Unveils 64-Core Chip

Adapteva Builds Manycore Processor That Will Deliver 70 Gigaflops/Watt

Startup Launches Manycore Floating Point Acceleration Technology

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