Fujitsu Develops 56 Gbps Receiver Circuit

June 13, 2014

KAWASAKI, Japan, June 13 — Fujitsu Laboratories Ltd. today announced the development of a receiver circuit capable of receiving communications at 56 Gbps. This marks the world’s fastest data communications between CPUs equipped in next-generation servers.

In recent years, raising data-processing speeds in servers has meant increasing CPU performance, together with boosting the speed of data communications between chips, such as CPUs. However, one obstacle to this has been improving the performance of the circuits that correct degraded waveforms in incoming signals.

Fujitsu Laboratories has used a new “look-ahead” architecture in the circuit that compensates for quality degradation in incoming signals, parallelizing the processing and increasing the operating frequency for the circuit in order to double its speed. This technology holds the promise of increasing the performance of next-generation servers and supercomputers.

Details of this technology are being presented at the 2014 Symposia on VLSI Technology and Circuits, opening June 9 in Hawaii (VLSI Circuits Presentation 11-2).

Background

In order to enhance the performance of datacenters underpinning the spread of cloud computing in recent years, a need has arisen for servers that process data faster. While this can be achieved partly through faster CPUs, large-scale systems connecting many CPUs are also being built, and the amount of data transmitted, either within the same CPU-equipped chassis or across separate chassis, is growing dramatically. To cope with these volumes, data communication speeds in the current generation of servers is increasing from a few gigabits per second today to ten or more gigabits per second. Because it is anticipated that data processing volumes will continue to experience explosive growth, however, for the next generation of high-performance servers, the goal is to double current levels to 56 Gbps. Furthermore, the Optical Internetworking Forum (OIF) is moving forward on the standardization of 56 Gbps for the optical modules used for optical transmission between chassis.

Issues

An effective way to speed up the receiver circuit is to improve the processing performance of the decision feedback equalizer (DFE) circuit that compensates for the degraded input-signal waveform (Figure 2).The principle behind DFE is to correct the input signal based on the bit-value of the previous bit and to emphasize changes in the input signal, but the actual circuit design works by choosing between two predefined corrected candidates. If the previous bit value was a 0, the correction process would apply a positive correction to the input signal (additive) to emphasize the change from 0 to 1. If the previous bit value was 1, it would apply a negative correction to the input signal (subtractive) to emphasize the change from 1 to 0. If another 0 was received, the positive compensation would increase the signal level, but not to such a level as would create a problem for the 1/0 decision circuit.

In ordinary circuit designs that run at 56 Gbps, there are 16 DFE circuits coupled together. Using 4 DFE circuits as an example, they run at 1/4th the actual frequency. So for 28-Gbps communications rates, 1/4th of that is 142 picoseconds, and four bits-worth of compensation can be applied during that interval. But at 56 Gbps, 1/4th of that speed amounts to 71 picoseconds, during which time only 2 bits-worth of compensation can be applied, resulting in timing errors.

About the Technology

Fujitsu Laboratories took a new approach, a “look-ahead” method that can be implemented as a parallel process, pre-calculating two candidates based on the selection result for the previous bit, and simultaneously deciding the value of the previous bit and the current bit after deciding the value of the bit two bits previous. This shortens calculation times, resulting in a receiver circuit that can operate at 56 Gbps.

Features of the new technology are as follows:

1. Look-ahead compensation process

In the existing method, the result of the previous bit’s selection circuit (A) is implemented by a circuit combining the result of the selection circuit for the bit two bits previous (B) and the input signal for the selection circuit one bit previous (+/- compensation data) (C). In the look-ahead method, the input signal for the selection circuit one bit previous (+/- compensation data) (D) and the input signal for the selection circuit of the current bit (+/- compensation data) (E) are combined using a look-ahead circuit, and candidates for the selection circuit are pre-computed. Doing this relies on only the result from the selection circuit for the bit two bits previous, without using the result from the selection circuit for the bit one bit previous, while functioning essentially the same as the existing method.

2. Parallelized look-ahead processing using a hold circuit

Multiple look-ahead circuits that apply DFE one bit at a time can operate independently (Figure 5). Fujitsu Laboratories inserted a hold circuit between the selection circuit and look-ahead circuit, with the input and output of each hold circuit being synchronized, making it possible to parallelize these

Because the calculation time for the look-ahead circuit is roughly the same as the selection time for the selector, overall calculation time is dependent on the number of selectors deciding based on data from two bits previous, so in a four-bit structure, that would be two. Running at 1/4th of 56 Gbps allows computations to be safely completed within 71 picoseconds. This makes it possible to receive data at 56 Gbps, doubling existing communications speeds.

Results

This technology makes it possible to increase bandwidth of communications between CPUs in future servers and supercomputers, even if CPU performance doubles, without increasing pin counts, and will contribute to increased performance in large-scale systems where numerous CPUs are interconnected. In addition, it complies with standards for optical-module communications, and compared to the 400-Gbps Ethernet in OIF-CEI-28G optical-module communications, the number of circuits running in parallel (number of lanes) can be halved, allowing for smaller optical modules running on less power, and higher system performance.

Future Plans

Fujitsu Laboratories plans to apply this technology to the interfaces of CPUs and optical modules, with the goal of a practical implementation in fiscal 2016. The company is also considering applications to next-generation servers, supercomputers, and other products.

About Fujitsu

Fujitsu is the leading Japanese information and communication technology (ICT) company offering a full range of technology products, solutions and services. Approximately 162,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society with our customers. Fujitsu Limited (TSE: 6702) reported consolidated revenues of 4.8 trillion yen (US$46 billion) for the fiscal year ended March 31, 2014. For more information, please see http://www.fujitsu.com.

Source: Fujitsu

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

UCSD Web-based Tool Tracking CA Wildfires Generates 1.5M Views

October 16, 2017

Tracking the wildfires raging in northern CA is an unpleasant but necessary part of guiding efforts to fight the fires and safely evacuate affected residents. One such tool – Firemap – is a web-based tool developed b Read more…

By John Russell

Exascale Imperative: New Movie from HPE Makes a Compelling Case

October 13, 2017

Why is pursuing exascale computing so important? In a new video – Hewlett Packard Enterprise: Eighteen Zeros – four HPE executives, a prominent national lab HPC researcher, and HPCwire managing editor Tiffany Trader Read more…

By John Russell

Intel Delivers 17-Qubit Quantum Chip to European Research Partner

October 10, 2017

On Tuesday, Intel delivered a 17-qubit superconducting test chip to research partner QuTech, the quantum research institute of Delft University of Technology (TU Delft) in the Netherlands. The announcement marks a major milestone in the 10-year, $50-million collaborative relationship with TU Delft and TNO, the Dutch Organization for Applied Research, to accelerate advancements in quantum computing. Read more…

By Tiffany Trader

HPE Extreme Performance Solutions

“Lunch & Learn” to Explore the Growing Applications of Genomic Analytics

In the digital age of medicine, healthcare providers are rapidly transforming their approach to patient care. Traditional technologies are no longer sufficient to process vast quantities of medical data (including patient histories, treatment plans, diagnostic reports, and more), challenging organizations to invest in a new style of IT to enable faster and higher-quality care. Read more…

Fujitsu Tapped to Build 37-Petaflops ABCI System for AIST

October 10, 2017

Fujitsu announced today it will build the long-planned AI Bridging Cloud Infrastructure (ABCI) which is set to become the fastest supercomputer system in Japan and will begin operation in fiscal 2018 (starts in April). A Read more…

By John Russell

Intel Delivers 17-Qubit Quantum Chip to European Research Partner

October 10, 2017

On Tuesday, Intel delivered a 17-qubit superconducting test chip to research partner QuTech, the quantum research institute of Delft University of Technology (TU Delft) in the Netherlands. The announcement marks a major milestone in the 10-year, $50-million collaborative relationship with TU Delft and TNO, the Dutch Organization for Applied Research, to accelerate advancements in quantum computing. Read more…

By Tiffany Trader

Fujitsu Tapped to Build 37-Petaflops ABCI System for AIST

October 10, 2017

Fujitsu announced today it will build the long-planned AI Bridging Cloud Infrastructure (ABCI) which is set to become the fastest supercomputer system in Japan Read more…

By John Russell

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Intel Debuts Programmable Acceleration Card

October 5, 2017

With a view toward supporting complex, data-intensive applications, such as AI inference, video streaming analytics, database acceleration and genomics, Intel i Read more…

By Doug Black

OLCF’s 200 Petaflops Summit Machine Still Slated for 2018 Start-up

October 3, 2017

The Department of Energy’s planned 200 petaflops Summit computer, which is currently being installed at Oak Ridge Leadership Computing Facility, is on track t Read more…

By John Russell

US Exascale Program – Some Additional Clarity

September 28, 2017

The last time we left the Department of Energy’s exascale computing program in July, things were looking very positive. Both the U.S. House and Senate had pas Read more…

By Alex R. Larzelere

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

NERSC Scales Scientific Deep Learning to 15 Petaflops

August 28, 2017

A collaborative effort between Intel, NERSC and Stanford has delivered the first 15-petaflops deep learning software running on HPC platforms and is, according Read more…

By Rob Farber

Oracle Layoffs Reportedly Hit SPARC and Solaris Hard

September 7, 2017

Oracle’s latest layoffs have many wondering if this is the end of the line for the SPARC processor and Solaris OS development. As reported by multiple sources Read more…

By John Russell

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

Google Releases Deeplearn.js to Further Democratize Machine Learning

August 17, 2017

Spreading the use of machine learning tools is one of the goals of Google’s PAIR (People + AI Research) initiative, which was introduced in early July. Last w Read more…

By John Russell

Graphcore Readies Launch of 16nm Colossus-IPU Chip

July 20, 2017

A second $30 million funding round for U.K. AI chip developer Graphcore sets up the company to go to market with its “intelligent processing unit” (IPU) in Read more…

By Tiffany Trader

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Leading Solution Providers

Amazon Debuts New AMD-based GPU Instances for Graphics Acceleration

September 12, 2017

Last week Amazon Web Services (AWS) streaming service, AppStream 2.0, introduced a new GPU instance called Graphics Design intended to accelerate graphics. The Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

EU Funds 20 Million Euro ARM+FPGA Exascale Project

September 7, 2017

At the Barcelona Supercomputer Centre on Wednesday (Sept. 6), 16 partners gathered to launch the EuroEXA project, which invests €20 million over three-and-a-half years into exascale-focused research and development. Led by the Horizon 2020 program, EuroEXA picks up the banner of a triad of partner projects — ExaNeSt, EcoScale and ExaNoDe — building on their work... Read more…

By Tiffany Trader

Cray Moves to Acquire the Seagate ClusterStor Line

July 28, 2017

This week Cray announced that it is picking up Seagate's ClusterStor HPC storage array business for an undisclosed sum. "In short we're effectively transitioning the bulk of the ClusterStor product line to Cray," said CEO Peter Ungaro. Read more…

By Tiffany Trader

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

IBM Advances Web-based Quantum Programming

September 5, 2017

IBM Research is pairing its Jupyter-based Data Science Experience notebook environment with its cloud-based quantum computer, IBM Q, in hopes of encouraging a new class of entrepreneurial user to solve intractable problems that even exceed the capabilities of the best AI systems. Read more…

By Alex Woodie

Intel Launches Software Tools to Ease FPGA Programming

September 5, 2017

Field Programmable Gate Arrays (FPGAs) have a reputation for being difficult to program, requiring expertise in specialty languages, like Verilog or VHDL. Easin Read more…

By Tiffany Trader

Intel, NERSC and University Partners Launch New Big Data Center

August 17, 2017

A collaboration between the Department of Energy’s National Energy Research Scientific Computing Center (NERSC), Intel and five Intel Parallel Computing Cente Read more…

By Linda Barney

  • arrow
  • Click Here for More Headlines
  • arrow
Share This