Company Offers a New Way to Parallelize Applications

By Michael Feldman

September 30, 2010

Startups always begin with big ambitions and Massively Parallel Technologies (MPT) is no exception. This week, the company unveiled “Blue Cheetah,” which is described as a “total application ecosystem” that aims to revolutionize the traditional software development and distribution model, especially for highly parallel codes. The idea is to turbo-charge the ROI model by automating the application development process, bringing software to market faster, and making it widely reusable.

MPT is not exactly a startup, though. The Colorado-based company has been around since 2000, and is on its third CEO. The first two, company founder Scott Smith and HPC luminary John Gustafson, are now on the board of directors. Former Linux Networx exec Bobbi Hazard is the current CEO and will oversee the reboot of MPT as it rolls out the Blue Cheetah suite of tools. Kevin Howard, the CTO, who has been with the company since its inception, has driven the technical innovation behind the products, especially in regard to the parallelization techniques.

During the company’s early years, MPT offered BLAST-based bioinformatics products and services, based on the company’s “HOWARD” technology. Using some of that early work, as well as additional development performed under a DARPA HPCS program contract, the company developed a new parallel communication technology that Hazard claims is “a huge improvement over MPI and PVM.” According to her, more than half of their 400-plus patent filings are based on this area of the technology.

But Blue Cheetah extends far beyond its novel communication scheme. It encompasses the whole software lifecycle, from design, testing, and development to deployment, licensing and revenue distribution. As Hazard puts it: “Usually you get one set of products to do one thing and another set of products to do another,” says Hazard. “I don’t know of anywhere else where you can get them all together.”

Not all of this is available today, though. What MPT announced this week is a beta version of Blue Cheetah’s software development platform, called Cub. With it, developers can design and develop applications, as well as share code with others in a collaborative fashion. Cub also automatically generates application documentation based on the design. The output from this tool is an executable that can run in a uni-processor environment. If parallelization is desired, that is performed separately further down the toolchain.

The key to Blue Cheetah software development is teasing out an application’s fundamental process elements, which they call kernels, from the control functions. Basically, the idea is to separate the math from the program control logic. During design, the system translates the developer’s kernel specifications directly into executable code. This is not revolutionary in itself; pseudcode-to-code translation has been done with varying degrees of success for decades. In this case though, there is no intermediary programming language like C or Fortran to deal with. The design itself represents the program source.

The control functions encompass the if-then-else and looping constructs that wrap around the kernel invocations. Conveniently, Cub automatically generate all the control functionality itself, again, based on the original design. This functional decomposition not only frees the developer from maintaining any of the control software, it also removes the dependency of the kernel algorithms on the underlying hardware and subsequent parallelization schemes.

Another important side effect to this decomposition is that the algorithms are easier to share among applications. Code reuse is a core element of MPT’s software monetization scheme, and during the design phase, the system points the developer to existing kernels that may apply to his or her application. Matches are based on keyword searches, input/output parameters, dataset similarities, and so on. Anything from an individual FFT algorithm to a complete application library can be shared across applications, taking with it the licensing agreement associated with the original code. The choice of reusing existing kernels versus designing new ones is up to the developer, though.

Once the application design is complete, its licensing is set up. The developer determines the fee structure and sets up the payment scheme for their own code. Blue Cheetah offers both a pay-per-use model and a more traditional licensing model. The intention is to offer applications on-demand via their own 256-node “cloud” cluster, but MPT will also license Blue Cheetah to customers who want to take the whole system in-house.

If kernels are reused in multiple applications, the original developers will get paid for each instance of use. It’s essentially the opposite of the open source licensing model. MPT is hoping to attract both commercial and academic developers, especially those frustrated by the “free software” business model. “A whole ecosystem will be formulated over time, and get larger as more kernels and algorithms become available,” says Hazard.

Blue Cheetah includes special capabilities to help developers parallelize their applications across the multicore/multiprocessor/cluster/grid/cloud computing landscape. That certainly covers high performance computing, but all software applications that require a large-scale computing infrastructure (e.g., cloud computing, business analytics, math-intensive applications, etc.) are fair game. Hazard says they have had early interest from organizations who develop nanotech, biotech and multi-player gaming applications.

Parallelizing applications will be performed by the upcoming Blue Cheetah product called Coalition, which is scheduled for release in the January 2011 timeframe. The tool will take the code developed under Cub and automatically restructure it in such a way as to maximize parallelism, be it for multicore platforms or clusters. How it actually accomplishes this is not clear, although an auto-parallelization feature that bypasses MPI and promises better performance should pique the interest of HPC developers.

Further down the road, a separate product called Savannah will also be available to put a Blue Cheetah app into firmware. This is targeted at users who want maximum performance or are running the types of embedded applications that requires the application to be executed locally.

Another future Blue Cheetah tool, called Spots, will consume existing source code and perform process-control decomposition so that it can be fed into the Cub platform. Once in the system, the application can go through the rest of the Blue Cheetah toolchain, including auto-parallelization. How this code transformation occurs, and what types of source code are deemed consumable, is not defined, but Hazard implied that even legacy MPI codes could be restructured by Spots. This tool also checks incoming code for malware and plagiarism.

Redefining the software development ecosystem is certainly a lot for one small company to take on. MPT has no venture capital money behind it. But the company has attracted a large number of angel investors to fund the Blue Cheetah development.

They’ve also managed to catch the attention of Gene Amdahl, a computer science icon who developed Amdahl’s law of software parallelism. He is on MPT’s board of advisors and appears to be thoroughly impressed by the Blue Cheetah products. In a video on MPT’s website, he talks about the importance of parallel computing and the opportunity afforded by the company’s technology. “It will revolutionize the world of computing,” he says.

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