A new supercomputer rating system will be released by an international team led by Sandia on Nov. 17 at the upcoming Supercomputing Conference 2010 in New Orleans.
The rating system, Graph500, tests supercomputers for their skill in analyzing large, graph-based structures that link the huge numbers of data points present in biological, social, and security problems, among other areas.
“By creating this test, we hope to influence computer makers to build computers with the architecture to deal with these increasingly complex problems,” says Richard Murphy (1422).
“The very careful and thoughtful definition of this new competitive standard is both quite subtle and tremendously important, as it may heavily influence computer architecture for decades to come,” says Rob Leland, director of Computations, Computers, and Math Center 1400.
The group isn’t trying to compete with Linpack, the current standard test of supercomputer speed, says Richard. “There have been lots of attempts to supplant it, and our philosophy is simply that it doesn’t measure performance for the applications we need, so we need another, hopefully complementary, test.”
(Many scientists view Linpack as a ‘plain vanilla’ test mechanism that tells how fast a computer can perform basic calculations, but has little relationship to the actual problems the machines must solve.)
The impetus to achieve a supplemental test code came about at “an exciting dinner conversation at Supercomputing 2009 [conference],” Richard says. “A core group of us recruited other professional colleagues, and the effort grew into an international steering committee of over 30 people.” See www.graph500.org.
Many large computer makers have indicated interest, says Richard, who says there’s been buy-in from Intel Corp., IBM, AMD Inc., NVIDIA Corp., and Oracle Corp. “Whether or not they submit test results remain to be seen, but their representatives are on our steering committee.”
Each organization has donated time and expertise of committee members, he says.
While some computer makers and their architects may prefer to ignore a new test for fear their machine will not do well, the hope is that a large-scale demand for a more complex test will be a natural outgrowth of the greater complexity of problems.
How does it work?
Large data problems are very different from ordinary physics problems.
Unlike a typical computation-oriented application, large data analysis problems often involve searching large, sparse data sets performing very simple computational operations.
To deal with this, the Graph500 benchmark creates two computational kernels: a large graph that inscribes and links huge numbers of participants and a parallel search of that graph.
“We want to look at the results of ensembles of simulations, or the outputs of big simulations in an automated fashion,” says Richard. “The Graph500 is a methodology for doing just that. You can think of them being complementary in that way — graph problems can be used to figure out what simulation actually told us.”
Performance for these applications is dominated by the ability of the machine to sustain a large number of small, nearly random remote data accesses across its memory system and interconnects, as well as the parallelism available in the machine.
Five problems for these computational kernels could be cybersecurity, medical informatics, data enrichment, social networks, and symbolic networks. “Many of us on the steering committee believe that these kinds of problems have the potential to eclipse traditional physics-based high-performance computing over the next decade,” says Richard.
While general agreement exists that complex simulations work well for the physical sciences, where lab work and simulations play off each other, there is some doubt simulations can solve social problems that have essentially infinite numbers of components. These include terrorism, war, epidemics, and societal problems.
“These are exactly the areas that concern me,” Richard says. “There’s been good graph-based analysis of pandemic flu. Facebook shows tremendous social science implications. Economic modeling this way shows promise.”
Studies show that moving data around (not simple computations) will be the dominant energy problem on exascale machines, the next frontier in supercomputing and the subject of a nascent DOE initiative to achieve this next level of operations within a decade. (Petascale and exascale represent 10 to the 15th and 18th powers, respectively, operations per second.)
Part of the goal of the Graph500 list is to point out that in addition to more expense in data movement, any shift in application base from physics to large-scale data problems is likely to further increase the application requirements for data movement, because memory and computational capability increase proportionally. That is, an exascale computer requires an exascale memory.
“In short, we’re going to have to rethink how we build computers to solve these problems, and the Graph500 is meant as an early stake in the ground for these application requirements,” Richard says.
“We’re all engineers and we don’t want to over-hype or over-promise, but there’s real excitement about these kinds of big data problems right now,” he says. “We see them as an integral part of science, and the community as a whole is slowly embracing that concept. However, it’s so new we don’t want to sound as if we’re hyping the cure to all scientific ills. We’re asking, ‘What could a computer provide us?’ but ignoring the human factors in problems that may stump the fastest computer. That’ll have to be worked out.”