XLoom Makes Its Play for the Optical Datacenter

By Michael Feldman

October 12, 2007

XLoom Communications is just one of a growing number of companies who want to bring optical connectivity inside the datacenter. On Monday, the company unveiled its new 20 Gbps optical transceiver device, the AVDAT 4X. The device is meant to be used as a drop-in optical interconnect for InfiniBand 4X and 10Gbase-CX4 connectors. With four 5 Gbps channels, the AVDAT is targeted mainly at DDR InfiniBand applications, although SDR InfiniBand, 10 GbE and Fibre Channel are also supported.

The device is based on XLoom’s iFlame optical engine, which the company introduced in September. The iFlame chip uses an array of four VCSELs (Vertical-Cavity Surface-Emitting Lasers) and four photo-diodes for data rates of 1.25 to 5 Gbps per channel, for a total aggregate of up to 20 Gbps. The entire flip-chip assembly fits into an area of less than one square centimeter. Multimode optical fiber is attached via a standard 12-ribbon fiber interface.

The whole idea behind going optical is to get rid of the multitude of problems associated with copper cabling, especially as interconnect data rates get into the multi-gigabit per second range. For example, at the 20 Gbps data rates for DDR InfiniBand, standard copper cabling is limited to a reach of around 8 to 10 meters. Beyond that, signal integrity starts to suffer, which degrades performance significantly. In addition, compared to optical fiber, the weight, bulkiness, and cost disadvantages of copper start to add up as distances increase. Most optical solutions, like XLoom’s, target applications where the media connection is between 15 to 100 meters. When QDR InfiniBand and 40 GbE become established over the next few years, even sub-5-meter distances are going to become challenging for conventional copper cabling.

By supporting the standard CX4 connector with the AVDAT offering, XLoom is hoping to attract the attention of InfiniBand vendors who would like to offer optical connectivity to their switches and host channel adapters. According to XLoom CEO David Sachs, one of the difficulties thus far has been getting the optical devices to fit into the CX4 electrical interface on these cards. He says the small size of their iFlame optical engine allowed them to achieve this without encroaching into the CX4 “keep out” space.

The company is looking to capitalize on optical connectivity in the datacenter as 10 GbE and 20 Gbps InfiniBand become more mainstream. “I think we’re going to see a lot of adoption for this for switch-to-switch connections, because that’s where the distances are required,” says Sachs. “Our aim is to take 10 to 15 percent of the copper market down the road, starting at the beginning of next year.”

Just considering InfiniBand, that works out to about 100,000 optical connections in 2008, based on IDC’s estimate of a million IB switches and HCA ports. Perhaps more importantly, IDC is predicting that DDR InfiniBand will be about 60 percent of the total in 2008, although the number of QDR ports will be negligible that year. To be ready for the IB surge, Sachs says the AVDAT devices will be generally available in the fourth quarter of this year and will be aggressively priced at about $100 per unit, when purchased in volume. “Everyone’s trying to bring down the overall pricing of the interconnect,” he says. “I think this is a step in the right direction.”

The XLoom offering is similar in technology and application to Intel’s Connects Cables and Zarlink’s ZLynx products, both announced earlier this year. Unlike the XLoom device, the Intel and Zarlink offerings are complete optical assemblies — two transceivers with attached fiber. Those products are presumably aimed at the system integrator or end-user, rather than as a value-added component for the switch and HCA vendors. Both of these solutions are also intended to start shipping before the end of the year.

In the future, XLoom plans to support QDR (40 Gbps) InfiniBand in a four-channel device, with a maximum data rate per channel of 10 Gbps. Although QDR products will be introduced by InfiniBand vendors in 2008, it is not likely to have a significant impact on the overall market until the following year, when IDC estimates around 250,000 QDR ports will be shipped. Luxtera Inc. has already staked a claim in the QDR InfiniBand space with their “Blazar” 40 Gbps optical cable product. That company hopes to establish itself at the high end of the optical InfiniBand market in 2008, although Sachs, like IDC, believes QDR won’t reach critical mass until 2009.

Not everyone is convinced that optical interconnects are about to take over the datacenter. Quellan Inc., an IC vendor that recently received $20 million in venture financing, has developed active cable technology that extends the reach of copper by a factor of three or four. Using analog silicon devices at each end of the cable, Quellan has managed to deliver enough noise reduction to allow copper cables to carry high data rates at distances well beyond 10 meters. At the same time, the increased signal quality allows thinner gauge copper to be used, which lessens some of the objections of cost and weight.

While Quellan CEO Tony Stelliga admits that in some situations optical connectivity makes sense, he says that with typical connection distances and at data rates of 10 to 20 Gbps, their active copper cable technology delivers enough capability for the majority of users. According to him, “95 percent of the connections in the datacenter are less than 25 meters and we can serve that reach now.”

Since Quellan’s technology uses only about 20 percent of the power of a typical optical solution at 20 Gbps (200 milliwatts versus 1 watt), their solution can claim better energy efficiency. But as distances stretch into the 20 or 25 meters range, the up-front cost of the copper cable and the weight/bulkiness issues start to assert themselves and the utility of copper becomes more problematic.

Companies like Intel, Luxtera, Zarlink and XLoom are all searching for the price-performance sweet spot for their respective optical products. With companies like Quellan pushing the envelope of copper cable technology, the nascent optical revolution in the datacenter may be a bit slower in coming than anticipated. But with QDR InfiniBand and 40 GbE in the pipeline, optical still seems like a safe bet in the long run.

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!

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…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a 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…

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…

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