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!

IBM Launches Commercial Quantum Network with Samsung, ORNL

December 14, 2017

In the race to commercialize quantum computing, IBM is one of several companies leading the pack. Today, IBM announced it had signed JPMorgan Chase, Daimler AG, Samsung and a number of other corporations to its IBM Q Net Read more…

By Tiffany Trader

TACC Researchers Test AI Traffic Monitoring Tool in Austin

December 13, 2017

Traffic jams and mishaps are often painful and sometimes dangerous facts of life. At this week’s IEEE International Conference on Big Data being held in Boston, researchers from TACC and colleagues will present a new Read more…

By HPCwire Staff

AMD Wins Another: Baidu to Deploy EPYC on Single Socket Servers

December 13, 2017

When AMD introduced its EPYC chip line in June, the company said a portion of the line was specifically designed to re-invigorate a single socket segment in what has become an overwhelmingly two-socket landscape in the d Read more…

By John Russell

HPE Extreme Performance Solutions

Explore the Origins of Space with COSMOS and Memory-Driven Computing

From the formation of black holes to the origins of space, data is the key to unlocking the secrets of the early universe. Read more…

Microsoft Wants to Speed Quantum Development

December 12, 2017

Quantum computing continues to make headlines in what remains of 2017 as several tech giants jockey to establish a pole position in the race toward commercialization of quantum. This week, Microsoft took the next step in Read more…

By Tiffany Trader

IBM Launches Commercial Quantum Network with Samsung, ORNL

December 14, 2017

In the race to commercialize quantum computing, IBM is one of several companies leading the pack. Today, IBM announced it had signed JPMorgan Chase, Daimler AG, Read more…

By Tiffany Trader

AMD Wins Another: Baidu to Deploy EPYC on Single Socket Servers

December 13, 2017

When AMD introduced its EPYC chip line in June, the company said a portion of the line was specifically designed to re-invigorate a single socket segment in wha Read more…

By John Russell

Microsoft Wants to Speed Quantum Development

December 12, 2017

Quantum computing continues to make headlines in what remains of 2017 as several tech giants jockey to establish a pole position in the race toward commercializ Read more…

By Tiffany Trader

HPC Iron, Soft, Data, People – It Takes an Ecosystem!

December 11, 2017

Cutting edge advanced computing hardware (aka big iron) does not stand by itself. These computers are the pinnacle of a myriad of technologies that must be care Read more…

By Alex R. Larzelere

IBM Begins Power9 Rollout with Backing from DOE, Google

December 6, 2017

After over a year of buildup, IBM is unveiling its first Power9 system based on the same architecture as the Department of Energy CORAL supercomputers, Summit a Read more…

By Tiffany Trader

Microsoft Spins Cycle Computing into Core Azure Product

December 5, 2017

Last August, cloud giant Microsoft acquired HPC cloud orchestration pioneer Cycle Computing. Since then the focus has been on integrating Cycle’s organization Read more…

By John Russell

GlobalFoundries, Ayar Labs Team Up to Commercialize Optical I/O

December 4, 2017

GlobalFoundries (GF) and Ayar Labs, a startup focused on using light, instead of electricity, to transfer data between chips, today announced they've entered in Read more…

By Tiffany Trader

HPE In-Memory Platform Comes to COSMOS

November 30, 2017

Hewlett Packard Enterprise is on a mission to accelerate space research. In August, it sent the first commercial-off-the-shelf HPC system into space for testing Read more…

By Tiffany Trader

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

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

AMD Showcases Growing Portfolio of EPYC and Radeon-based Systems at SC17

November 13, 2017

AMD’s charge back into HPC and the datacenter is on full display at SC17. Having launched the EPYC processor line in June along with its MI25 GPU the focus he 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

Japan Unveils Quantum Neural Network

November 22, 2017

The U.S. and China are leading the race toward productive quantum computing, but it's early enough that ultimate leadership is still something of an open questi 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

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

Leading Solution Providers

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

Perspective: What Really Happened at SC17?

November 22, 2017

SC is over. Now comes the myriad of follow-ups. Inboxes are filled with templated emails from vendors and other exhibitors hoping to win a place in the post-SC thinking of booth visitors. Attendees of tutorials, workshops and other technical sessions will be inundated with requests for feedback. Read more…

By Andrew Jones

IBM Begins Power9 Rollout with Backing from DOE, Google

December 6, 2017

After over a year of buildup, IBM is unveiling its first Power9 system based on the same architecture as the Department of Energy CORAL supercomputers, Summit a 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

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

Tensors Come of Age: Why the AI Revolution Will Help HPC

November 13, 2017

Thirty years ago, parallel computing was coming of age. A bitter battle began between stalwart vector computing supporters and advocates of various approaches to parallel computing. IBM skeptic Alan Karp, reacting to announcements of nCUBE’s 1024-microprocessor system and Thinking Machines’ 65,536-element array, made a public $100 wager that no one could get a parallel speedup of over 200 on real HPC workloads. Read more…

By John Gustafson & Lenore Mullin

Flipping the Flops and Reading the Top500 Tea Leaves

November 13, 2017

The 50th edition of the Top500 list, the biannual publication of the world’s fastest supercomputers based on public Linpack benchmarking results, was released Read more…

By Tiffany Trader

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

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