Visit additional Tabor Communication Publications
December 21, 2007
Dec. 19 -- A team of UCLA scientists has now demonstrated substantial improvements in integrated circuits, achieved not by costly improvements in manufacturing but by improved computer-aided design software based on better mathematical algorithms.
"We can get circuits designed with 30 percent less wire length using improved optimization than what we had demonstrated three years ago, based on circuits that were samples from industry," said Jason Cong, UCLA professor and chair of computer science. "We believe that when you apply these methods to current industry circuits, you will see similar gains. Industry says even 5 percent is very significant.
"We are showing there is another way to make major improvements, with better design and better architecture," added Cong, who has collaborated for nearly a decade with Tony Chan, UCLA professor of mathematics and the National Science Foundation's assistant director for mathematics and physical sciences.
The traditional way to achieve smaller, faster integrated circuits -- also known as silicon chips -- is by building smaller and smaller transistors and thinner wires. While the computer industry has made smaller, improved devices, Cong, Chan and their colleagues are improving the design of the chip itself.
A goal of the collaboration is the development of silicon chips that are faster and cheaper and consume less power than the current generation of chips, said Cong, who is also a member of the California NanoSystems Institute at UCLA. "We think optimizing chip design is an exciting direction," he said.
Integrated circuits have a series of interconnected, nanosize nodes; the locations of the nodes on the chip's surface are very important because they can minimize the wire length on which the signal travels. Nodes include tiny "logic gates," as well as much larger memory blocks and other functional blocks. There are tens of millions of nodes on a chip.
"We have found there is a huge amount of room for improvement in the physical design of the chip itself, including where nodes are placed," said UCLA mathematics graduate student Eric Radke, who works with Chan and Cong. "We want to minimize the wire length in each node."
A challenge, Cong said, is "how do you place the nodes on a two-dimensional surface with big pieces and small pieces that are all connected to one another? It's like a jigsaw puzzle with millions of pieces. How do you place them to minimize the total interconnections (wires) among them?"
"It's fairly easy to model this problem mathematically," Radke said. "You can think of the nodes as points on a giant graph, and you can think of the interconnects as hyper-edges that connect more than two nodes. We can use mathematics to determine how the placement problem should be solved. We use a mathematical technique called multiscale methods, in which we group nodes together until we get a mathematical problem that is small enough to solve."
Chan and Radke design algorithms for computer software to improve the placement of the nodes and are using differential equations that they build into the algorithms. The scientists expect that the research will lead to improved software for enhanced chip design. Cong's laboratory has found strong evidence that existing computer-aided programs for integrated circuit design are far from optimal. Chan and Radke are now working to minimize the amount of time it takes a signal to get through a processor.
Research by Chan, Cong and their graduate students won the 2005 award for best paper at the International Symposium of Physical Design (ISPD). Their placement software, developed together with their former students Kenton Sze and Min Xie, also produced the best wire-length results in the 2006 Circuit Placement Contest organized by ISPD.
Chan and Cong are also working with Lieven Vandenberghe, UCLA professor and vice chair of electrical engineering, as well as computer science graduate student Guojie Luo and electrical engineering graduate student John Lee. "It's great to come to the meetings and hear everybody's ideas because everybody comes from a different background," Radke said.
The research is funded by the National Science Foundation and the Semiconductor Research Corp., the world's leading university research consortium for semiconductors and related technology.
UCLA is California's largest university, with an enrollment of nearly 37,000 undergraduate and graduate students. The UCLA College of Letters and Science and the university's 11 professional schools feature renowned faculty and offer more than 300 degree programs and majors. UCLA is a national and international leader in the breadth and quality of its academic, research, health care, cultural, continuing education and athletic programs. Four alumni and five faculty have been awarded the Nobel Prize.
In quieter times, sounding the bell of funding big science with big systems tends to resonate further than when ears are already burning with sour economic and national security news. For exascale's future, however, the time could be ripe to instill some sense of urgency....
In a recent solicitation, the NSF laid out needs for furthering its scientific and engineering infrastructure with new tools to go beyond top performance, Having already delivered systems like Stampede and Blue Waters, they're turning an eye to solving data-intensive challenges. We spoke with the agency's Irene Qualters and Barry Schneider about..
Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
May 23, 2013 |
The study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
May 22, 2013 |
At some point in the not-too-distant future, building powerful, miniature computing systems will be considered a hobby for high schoolers, just as robotics or even Lego-building are today. That could be made possible through recent advancements made with the Raspberry Pi computers.
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.
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.