CW-WDM MSA Group Forms to Drive New Industry Standard for Optical Laser Sources

June 24, 2020

SANTA CLARA, Calif., June 24, 2020 — The CW-WDM MSA (Continuous-Wave Wavelength Division Multiplexing Multi-Source Agreement) Group announced its formation as an industry consortium dedicated to defining and promoting specifications for multi-wavelength advanced integrated optics.

IEEE and MSA standards specify four WDM interfaces for today’s high volume datacom optics. Emerging advanced integrated optics applications, such as silicon photonics (SiPh) based high-density co-packaged optics, optical computing, and AI, are expected to move to 8, 16, and 32 wavelengths. Standardizing higher wavelength counts is a crucial part of an emerging ecosystem which is enabling a leap in efficiency, cost, and bandwidth scaling compared to current technology. Increasing the number of wavelengths, while staying in the O-band and aligning with ITU and IEEE standards, allows developers and suppliers to leverage their strategic investments in the current generation of optical products to accelerate time to market of next generation products.

“We support and encourage consortiums like the CW-WDM MSA Group in order to accelerate important technical innovations,” said Christopher Berner, Head of Compute at OpenAI. “OpenAI must be on the cutting edge of AI capabilities and low latency, high bandwidth optical interconnect is a central piece of our compute strategy to achieve our mission of delivering artificial intelligence technology that benefits all of humanity.”

The CW-WDM MSA is different from optical communication standards groups in that it solely focuses on specifying the laser source instead of the full communications link, and is not targeted at any specific application. Such an approach allows developers to fully optimize optics to their customers’ requirements without interoperability constraints while simultaneously creating a large business opportunity for laser source suppliers.

“Laser sources have been the critical building block of fiber optic communications, and standardizing their specifications has been key to the success of telecom and datacom optics,” said Chris Cole, Chair of the CW-WDM MSA. “ITU-T established complete baselines for DWDM and CWDM grids. The IEEE then specified subsets of these grids for high volume data center applications, starting with 40G and 100G Ethernet optics. The CW-WDM MSA will similarly leverage ITU-T and IEEE standards to specify 8, 16 and 32 wavelength grids in O-band for emerging advanced datacom and computing optics. With the definition of multiple grid sets, the MSA will enable developers to choose what is optimum for their application, while allowing laser suppliers to only have to invest in one technology platform.”

Promoter Members of the CW-WDM MSA are Arista Networks, Ayar Labs, CST Global, imec, Intel, Lumentum, Luminous Computing, MACOM, Quintessent, Sumitomo Electric, and II-VI.

In addition, several Observer Members have signed on to be briefed on the development of the standard to enable early technology development based on the new specifications. Observer Members are AMF, Axalume, Broadcom, Coherent Solutions, Furukawa Electric, GlobalFoundries, Keysight Technologies, NeoPhotonics, NVIDIA, Samtec, Scintil Photonics, and Tektronix.

For more information about the CW-WDM MSA, please visit cw-wdm.org

Christophe Metivier, VP, Manufacturing and Platform Engineering, Arista Networks, said:  “Scaling network bandwidth while reducing power per bit is a critical issue for hyperscale data centers. We support the goals of this MSA to standardize wavelength grids for next-generation multi-channel optics transceivers that will have significantly lower power per bit.”

Charlie Wuischpard, CEO, Ayar Labs, said:  “To meet the ever-increasing bandwidth demands of HPC, AI and telecom applications, integrated optical I/O will become a necessity. To achieve the required bandwidth density and energy efficiency for these new applications, a new set of optical standards is a vital piece of the puzzle to strengthen the ecosystem and supply chain for this technology to become a reality.”

John E. Johnson, Ph.D., Director, III-V Component R&D, Optical Systems Division, Broadcom, said:   “Parallel optical architectures will benefit greatly from newly developed WDM grids optimized specifically for the density and scalability of silicon photonics optical engines. We are excited to apply our long history of ultra-reliable high-power CW and WDM laser design and production to the CW-WDM MSA objective and participate in the scaling of parallel compute.”

Andrew McKee, CTO, CST Global, said:  “As a foundry, the standardization of optical components is critical to ultimately providing high volume, low cost solutions. Using our InP100 commercial laser platform, this MSA will enable us to provide next generation DFB lasers to our customers in a much more standardized fashion, thereby eliminating the high levels of often complex customization that we see today.”

Joris Van Campenhout, Program Director of Optical I/O, imec, said:  “At imec, we believe that wavelength division multiplexing with high channel count is a key enabler for reaping the full benefits of silicon photonics in many application domains. However, every silicon photonics device needs a light source, and we are excited to work with all members in the CW-WDM MSA to help in standardizing multi-wavelength lasers that will propel next-generation silicon photonics.”

Balaji Iyer, VP of Business Development, Luminous Computing, said: “Optics is playing a more substantial and significant role in computing systems. This MSA provides the first step in coordinating the industry towards a new paradigm, and Luminous is excited to be leading the way along with our partners.”

Jessen Wehrwein, VP, Corporate Marketing, MACOM, said: “Cost-effective, multi-wavelength WDM links are poised to enable very high bandwidth interfaces that can address the increased global bandwidth requirement. CW laser source along with silicon photonics can lead to co-packaged optics that are energy efficient and lower in cost and more scalable than discrete components. MACOM is excited to be part of the CW-WDM MSA and further support the industry with our leadership in laser development and fabrication.”

Henning Lysdal, VP, Photonics Architecture, NVIDIA, said: “NVIDIA sees the data center as the new basic unit of computing, and we welcome increased focus on optimizing CW lasers for this application.”

Brian Koch, VP of Technology, Quintessent, said: “Quintessent is pleased to support the CW-WDM MSA as a Promoter Member. We look forward to helping enable the evolving and emerging applications that will require multi-wavelength sources.”

Kenneth Jackson, Product Marketing Director, Sumitomo Electric Device Innovations USA, said: “Sumitomo Electric is pleased to be a Promoter Member of the CW-WDM MSA. The definition of frequency grids in the 1310nm wavelength range similar to what exists at 1550nm wavelengths will enable the next generation of high data-throughput optical communications links for high performance computing, artificial intelligence and machine learning. Our expertise in Indium Phosphide semiconductor processing and device fabrication will allow us to provide optimal solutions for our customers.”

Charles Roxlo, VP, InP Devices BU, II-VI Incorporated, said: “It’s our pleasure to support the CW-WDM MSA as a Promoter Member. The use of an expanded set of wavelengths in high-performance computing and other networking applications will enable higher-capacity optical interconnects. With a long history of shipping InP-based laser devices, we are looking forward to helping develop this new specification.”

About the MSA

Today’s high volume datacom optics defined by IEEE and MSA standards specify serial or four WDM interfaces. The CW-WDM MSA (Continuous-Wave Wavelength Division Multiplexing Multi-Source Agreement) was formed to standardize WDM CW sources in O-band for emerging advanced integrated optics applications that are expected to move to 8, 16, and 32 wavelengths. Such higher wavelength counts are needed for emerging applications such as silicon photonics (SiPh) based high-density co-packaged optics, optical computing, and AI, and enable a leap in performance, efficiency, cost, and bandwidth scaling compared with previous technology generations. The new specifications will leverage IEEE and ITU-T standards. There is no plan to standardize link parameters as these will remain unique to applications. Standardization of mechanical form factors will not be part of the first MSA standard but will be considered in follow-on specs.


Source: CW-WDM MSA (Continuous-Wave Wavelength Division Multiplexing Multi-Source Agreement) Group

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!

Edge-to-Cloud: Exploring an HPC Expedition in Self-Driving Learning

April 25, 2024

The journey begins as Kate Keahey's wandering path unfolds, leading to improbable events. Keahey, Senior Scientist at Argonne National Laboratory and the University of Chicago, leads Chameleon. This innovative projec Read more…

Quantum Internet: Tsinghua Researchers’ New Memory Framework could be Game-Changer

April 25, 2024

Researchers from the Center for Quantum Information (CQI), Tsinghua University, Beijing, have reported successful development and testing of a new programmable quantum memory framework. “This work provides a promising Read more…

Intel’s Silicon Brain System a Blueprint for Future AI Computing Architectures

April 24, 2024

Intel is releasing a whole arsenal of AI chips and systems hoping something will stick in the market. Its latest entry is a neuromorphic system called Hala Point. The system includes Intel's research chip called Loihi 2, Read more…

Anders Dam Jensen on HPC Sovereignty, Sustainability, and JU Progress

April 23, 2024

The recent 2024 EuroHPC Summit meeting took place in Antwerp, with attendance substantially up since 2023 to 750 participants. HPCwire asked Intersect360 Research senior analyst Steve Conway, who closely tracks HPC, AI, Read more…

AI Saves the Planet this Earth Day

April 22, 2024

Earth Day was originally conceived as a day of reflection. Our planet’s life-sustaining properties are unlike any other celestial body that we’ve observed, and this day of contemplation is meant to provide all of us Read more…

Intel Announces Hala Point – World’s Largest Neuromorphic System for Sustainable AI

April 22, 2024

As we find ourselves on the brink of a technological revolution, the need for efficient and sustainable computing solutions has never been more critical.  A computer system that can mimic the way humans process and s Read more…

Shutterstock 1748437547

Edge-to-Cloud: Exploring an HPC Expedition in Self-Driving Learning

April 25, 2024

The journey begins as Kate Keahey's wandering path unfolds, leading to improbable events. Keahey, Senior Scientist at Argonne National Laboratory and the Uni Read more…

Quantum Internet: Tsinghua Researchers’ New Memory Framework could be Game-Changer

April 25, 2024

Researchers from the Center for Quantum Information (CQI), Tsinghua University, Beijing, have reported successful development and testing of a new programmable Read more…

Intel’s Silicon Brain System a Blueprint for Future AI Computing Architectures

April 24, 2024

Intel is releasing a whole arsenal of AI chips and systems hoping something will stick in the market. Its latest entry is a neuromorphic system called Hala Poin Read more…

Anders Dam Jensen on HPC Sovereignty, Sustainability, and JU Progress

April 23, 2024

The recent 2024 EuroHPC Summit meeting took place in Antwerp, with attendance substantially up since 2023 to 750 participants. HPCwire asked Intersect360 Resear Read more…

AI Saves the Planet this Earth Day

April 22, 2024

Earth Day was originally conceived as a day of reflection. Our planet’s life-sustaining properties are unlike any other celestial body that we’ve observed, Read more…

Kathy Yelick on Post-Exascale Challenges

April 18, 2024

With the exascale era underway, the HPC community is already turning its attention to zettascale computing, the next of the 1,000-fold performance leaps that ha Read more…

Software Specialist Horizon Quantum to Build First-of-a-Kind Hardware Testbed

April 18, 2024

Horizon Quantum Computing, a Singapore-based quantum software start-up, announced today it would build its own testbed of quantum computers, starting with use o Read more…

MLCommons Launches New AI Safety Benchmark Initiative

April 16, 2024

MLCommons, organizer of the popular MLPerf benchmarking exercises (training and inference), is starting a new effort to benchmark AI Safety, one of the most pre 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…

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…

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…

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…

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…

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…

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…

Leading Solution Providers

Contributors

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…

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…

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…

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…

Eyes on the Quantum Prize – D-Wave Says its Time is Now

January 30, 2024

Early quantum computing pioneer D-Wave again asserted – that at least for D-Wave – the commercial quantum era has begun. Speaking at its first in-person Ana Read more…

GenAI Having Major Impact on Data Culture, Survey Says

February 21, 2024

While 2023 was the year of GenAI, the adoption rates for GenAI did not match expectations. Most organizations are continuing to invest in GenAI but are yet to Read more…

The GenAI Datacenter Squeeze Is Here

February 1, 2024

The immediate effect of the GenAI GPU Squeeze was to reduce availability, either direct purchase or cloud access, increase cost, and push demand through the roof. A secondary issue has been developing over the last several years. Even though your organization secured several racks... Read more…

Intel’s Xeon General Manager Talks about Server Chips 

January 2, 2024

Intel is talking data-center growth and is done digging graves for its dead enterprise products, including GPUs, storage, and networking products, which fell to Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire