Visit additional Tabor Communication Publications
August 26, 2008
The prospects for optical cable interconnects never looked so good. With single and double data rate (SDR and DDR) InfiniBand firmly entrenched in HPC clusters and quad data rate (QDR) deployments just around the corner, optical cable makers are looking to displace bulky copper cabling in the next generation of high performance systems. Optical is already the accepted medium for long distance network communications, and now companies like EMCORE, Zarlink, Finisar, Luxtera, Tyco Electronics and Fujitsu are targeting the datacenter with optical solutions for multi-gigabit InfiniBand, Ethernet, and Fibre Channel.
As short-distance connection speeds get into the multi-gigabit per second realm and clusters scale out, copper's weight, bulkiness and signal integrity problems start to work against it. At distances beyond 10 meters, traditional copper solutions usually can't maintain good signal integrity at DDR rates (5 Gbps per channel * 4) unless much heavier cabling is used. At QDR rates (10 Gbps per channel * 4), copper peters out at about 7 meters. Even at shorter distances, cable's weight and bulkiness can become a manageability issue because of limited bend radius and airflow blockage.
Optical has already notched a high-profile HPC win with the IBM Roadrunner supercomputer. That system is linked with EMCORE's optical gear using DDR (InfiniBand) connections. According to IBM, they used over 55 miles of cable to hook all the compute and storage nodes together. For a massive system such as this, the superior physical manageability of optical fiber versus copper was probably the deciding factor.
But copper is not going down without a fight. Engineering innovation has continued to push performance to match the speeds of the latest network protocols. W. L. Gore & Associates, in particular, has been developing "active" copper cable solutions, targeting high performance interconnects for both HPC and general-purpose enterprise computing. The active component is a silicon device built into each end of the cable assembly that boosts the electronic signal and reduces noise, which enables greater reach or smaller cable diameters at a given distance.
Gore's first generation active cables use Quellan's Q:ACTIVE silicon devices to support DDR InfiniBand, 10GbE and 8 Gigabit Fibre Channel. Compared to passive copper, which the company also offers, Gore's active cables are thinner and lighter, and can reach beyond 10 meters. Its current active product support InfiniBand connectors operating at 5 Gbps per channel, as well as QSFP (4-channel) and SFP+ (2-channel) connectors operating at 10 Gbps per channel.
Currently in development at Gore is an active QSFP offering aimed at the new QDR InfiniBand speeds. The product is being sampled now and will ship later this year. It will go head-to-head against optical assemblies being readied for QDR setups.
"We're expecting to get at least 15 meters with quad data rate -- hopefully 20," said Russell Hornung, Gore's director of new product development. The supported length will be a function of the acceptable cable gauge for customers. Since the majority of users are dealing with the problems associated with the weight of the copper, in most cases light gauge cable is going to be preferred. Hornung says they're looking to achieve 15 meters with standard 28 AWG cable.
According to Gore's research, more than half of the cabling in a datacenter is less than 10 meters and the majority -- maybe 90 percent -- is below 20 meters. If Gore's copper offerings are able to reach those lengths with reasonably thin cable, that doesn't leave much of a window for optical.
And compared to optical solutions, Gore thinks it has some big advantages in price and power consumption. Based on where the company has positioned its current active solutions, Hornung claims they are 20 to 25 percent less expensive than optical cables. Plus, according to him, they use only one-fifth the power of an optical solution at DDR. For QDR they expect to use only one-quarter to one-half the power, compared to optical. Their DDR assembly uses about 0.5 watt per cable (0.25 watt at each end), and depending on which chipset solutions they finally decide upon for the upcoming QDR products, they expect to use between 0.3 and 1.0 watt per cable.
The main reason active cables have a price and power advantage is that they only have CMOS devices drawing power at each end, while optical assemblies require CMOS plus a variety of optical-electronic components and one or more vertical-cavity surface-emitting lasers (VCSELs). The VCSELs tend to be the weak link in optical cables. Not only do they require a fair amount of power themselves, but they're also sensitive to overheating. To have these tiny lasers hanging off a heat-generating server is not an ideal cooling scenario, so reliability becomes a concern.
Of course, the CMOS devices in the active copper assemblies are not immune to the heat themselves, but the thermal considerations are a much larger problem for optical than active copper. Hornung says CMOS is orders of magnitude more reliable than VCSELs -- or any laser.
The VCSELs also are the biggest source of the cost differential between optical and copper, mainly because manufacturing lasers is not as advanced as it is for CMOS. Only some of the defective VCSELs can be found during fabrication. A significant fraction of bad lasers aren't detected until they undergo some burn-in -- after everything is assembled. By comparison, CMOS fabrication is a much more mature technology. Most troublesome silicon can be weeded out rather early in the manufacturing process.
The other complicating factor is that for multi-channel interconnects like DDR and QDR, most optical solutions use an array of VCSELs -- one per channel. (The exception is Luxtera, which can power four transmitters with a single laser.) Multiple lasers complicate the inherent weaknesses of the optical cables, and since these multi-VCSEL products are still fairly new, the industry lacks much experience with device longevity.
Most of the optical vendors claim they can match or beat copper solutions once a specified length is exceeded -- perhaps 10 meters or so. Beyond that, the cost of the copper itself starts to become a disadvantage compared to less-expensive optical fiber. But Hornung is not buying the economics. He believes the optical vendors are currently selling at below cost to get a foothold in the market. "To make a play in this space, they're having to stoop to dangerous pricing levels," he says. "We'll see where it ends."
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
May 15, 2013 |
Supercomputers at the Department of Energy’s National Energy Research Scientific Computing Center (NERSC) have worked on important computational problems such as collapse of the atomic state, the optimization of chemical catalysts, and now modeling popping bubbles.
May 10, 2013 |
Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
May 09, 2013 |
The Japanese government has revealed its plans to best its previous K Computer efforts with what they hope will be the first exascale system...
May 08, 2013 |
For engineers looking to leverage high-performance computing, the accessibility of a cloud-based approach is a powerful draw, but there are costs that may not be readily apparent.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
In this demonstration of SGI DMF ZeroWatt disk solution, Dr. Eng Lim Goh, SGI CTO, discusses a function of SGI DMF software to reduce costs and power consumption in an exascale (Big Data) storage datacenter.
The Cray CS300-AC cluster supercomputer offers energy efficient, air-cooled design based on modular, industry-standard platforms featuring the latest processor and network technologies and a wide range of datacenter cooling requirements.