Mellanox Connects the Dots

By Michael Feldman

July 23, 2008

High performance computing continues to be one of the fastest growing segments of the IT industry. But there’s a general consensus that the commercial sector is still underutilizing HPC technologies. In some cases, users have deployed HPC but lack the most effective software or hardware for their application. In other cases, users haven’t even made the jump from technical computing workstations to HPC servers.

Over the past four years, the Council on Competitiveness has released a series of studies that point to a gap between HPC use and its potential. Taken as a whole, the reports highlight the most common barriers to greater HPC use: cost, especially software cost, and lack of HPC talent. Thanks to more open source software (and the competitive pricing it engenders) and ever-more powerful hardware, overall system costs are coming down. But the human expertise needed to specify, procure, configure, and operate an HPC set up is still a limiting factor for most businesses. This is especially true of smaller firms, where specialized IT talent can’t be justified.

Even though HPC now uses a lot of commodity solutions derived from open source software and off-the-shelf parts, there is a dizzying array of combinations to deal with. To make sure all the pieces fit together, the software stack — operating system, libraries, drivers, compilers, etc. — must be qualified and optimized for each unique hardware configuration. Even for an experienced system integrator, this is no small task.

It has usually been left to HPC vendors to help fill the expertise gap. Most of the larger OEMs, like IBM and HP who have deep partnerships across the vendor community, double as system integrators. Even most of the tier 2 OEMs offer some kind of integration capability. But that’s assuming the customer has already made it to the system procurement stage. What’s really needed is someone to give businesses a boost into the HPC ecosystem in the first place — but in a vendor neutral kind of way.

From what I could glean from a recent conversation with Gilad Shainer, director of technical marketing at Mellanox, that’s what their new HPC Advisory Council is all about. Shainer says his company formed the organization to help bring users and HPC technologies together. Specifically, their mission is to qualify and optimize HPC solutions, give early access to new technology, help develop new solutions through collaboration, find ways to push HPC into new markets, and help develop joint marketing programs.

To do this they’ve brought the whole cast of HPC characters into the mix: OEMS, chip makers, storage vendors, interconnect suppliers, end users, ISVs, and some key technical people. They’ve already lined up big industry names, including HP, Intel, Microsoft and more than 30 other commercial firms, while the end user members come mostly from research institutions such as national labs or universities. Their full membership is listed on their website, although Shainer says three or four additional groups joined up a few days after the announcement of the Advisory Council last week. Of course, Mellanox is a member too, as well as being the umbrella for the whole organization.

Why Mellanox? As the leading provider of InfiniBand switch silicon and multi-protocol adapters, the company’s products end up connecting a lot of the other pieces of the HPC ecosystem. You’ll find Mellanox switch silicon in everything from the IBM’s petaflop Roadrunner supercomputer to generic 10-node clusters. Also, according the Shainer, the company is perceived as a vendor-neutral technology provider. “Many people see Mellanox as the Switzerland of HPC,” he claims. While competitor QLogic and Ethernet switch vendors may not exactly see it that way, certainly Mellanox is in a rather unique position with respect to a lot of HPC providers.

The other part of the equation for Mellanox is that an organization like this can help drive InfiniBand adoption, a non-mainstream technology compared to the ubiquitous Ethernet. A large part of the challenge for HPC newbies is coming up with a software stack that makes InfiniBand interoperable with their application and hardware set up. Since most HPC vendors are now committed to InfiniBand as well, it’s in their interest to help users assemble a consistent software stack that works across a range of applications and hardware configurations. Also, because Mellanox is starting to expand its horizons beyond traditional HPC — into ultra-scale Web applications and enterprise virtualization — anything that makes InfiniBand more palatable to mainstream users will help ease the technology’s entry into the larger enterprise market.

One of the concrete steps the Advisory Council has already taken is the establishment of an HPC cluster center at Mellanox’ U.S. headquarters in Santa Clara, Calif. They’ve gathered equipment and software from council members and constructed a number of AMD- and Intel-based HPC systems for application testing and benchmarking. Users can request time on a cluster, free of charge, and log in remotely to try out their software or even use it for application development. ISVs can also use the systems for software development and testing. Although membership to the Advisory Council is free, members are obligated to support the cluster center. According to Shainer, there are five systems (complete with attached storage and files systems) currently running at the facility, with more on the way.

Another piece of the Advisory Council’s work is the “network of knowledge,” a mailing list that can be accessed by end users to get technical support. For example, a prospective customer may have a particular application to host and wants to know the types of systems that would be most appropriate. Or a current user is experiencing a storage bottleneck with their set up and is looking for a solution. The mailing list is sent out to a community of technical experts, which are provided by each participating Advisory Council member (and even some from non-participating members). Obviously, vendors are interested in attracting new customers and keeping the current ones happy, so participation in the mailing list seems to have some built-in motivation.

The second part of the Advisory Council’s work is to engage in outreach. Here they’re specifically targeting technical computing users who could move from workstations up to HPC clusters. As mentioned before, because of the lack of HPC expertise, a lot of these users are unable to make the leap from the desktop to the HPC server on their own. This may even be the case where small businesses are supplying components to larger firms that use HPC systematically. For example, an aerospace company may be designing aircraft with HPC simulation, but the widgets that go into it are being developed on PCs.

The Advisory Council’s approach will be to use member ISVs like Wolfram Research (makers of Mathematica) to reach into their desktop user community and show users a path to HPC server-based systems. This includes providing a recipe for scaling end user applications to parallel platforms and hands-on support. In the past, ISVs may have been motivated to move customers up the food chain on their own, but without support from the larger HPC ecosystem, it was difficult for the software vendors to do this.

Between the OEMs, the ISVs, component makers, and other members, Mellanox seems to have assembled a critical mass of people, although it remains to be seen whether the Advisory Council represents the right formula to catalyze HPC adoption. Multi-vendor partnerships get announced all the time, and most don’t amount to much in the long term. But if Mellanox has managed to pull together an effective advisory group, it will be yet another “interconnect” success story for the company.

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