Back to Table of contents

Primeur weekly 2016-08-01

Special

National Strategic Computing Initiative Executive Council to unfold Strategic Plan ...

Quantum information science is to play a key role in the U.S. National Strategic Computing Initiative ...

Focus

Lenovo is heavily investing in new HPC technology, showing its commitment to the HPC market ...

South Africa's CHPC in the picture with new Lengau supercomputer, Student Cluster Competition victory and upcoming ICRI 2016 Conference ...

Exascale supercomputing

China starts developing new-era exascale supercomputer ...

Crowd computing

IBM intensifies fight against Zika ...

Middleware

Red Hat Satellite 6.2 introduces new features to help users increase efficiency across on-premise, Cloud, and container-based environments ...

Hardware

Mellanox Technologies receives Baidu's Award for Technology Leadership, drives company to new heights in machine learning ...

Medallia deploys Mellanox Ethernet solutions to supercharge real-time analytics and achieve the efficiency of hyperscale infrastructure ...

A research project coordinated by UC3M helps reduce the cost of parallel computing ...

Supermicro shipping latest Intel Xeon Phi processor server solutions in volume with Intel Omni-Path fabric ...

Vortex laser offers hope for Moore's Law ...

Penguin Computing provides high-performance computing cluster to University of Alaska Fairbanks ...

Fifth NVM Express Plugfest participation set a record; Next event scheduled for October 2016 ...

Physicists use supercomputers to find a way of making imitation graphene from salt ...

Chip makes parallel programmes run faster with less code ...

Applications

KnuEdge and University of California San Diego to host premiere industry conference to drive next-gen machine learning performance ...

Princeton Plasma Physics Laboratory and Princeton join high-performance software project ...

Red Hat unveils JBoss Data Grid 7 as platform for real-time data analytics ...

Teradata acquires Big Data Partnership consultancy and expands open source analytics services ...

PRACE to organize Women in HPC Workshop at SC16 ...

Lawrence Livermore National Laboratory chemist named Howes Scholar ...

NSF commits $35 million to improve scientific software ...

Making Big Data DANCE(S): XSEDE project successfully tests scheduled networking of Big Data ...

New ALS gene NEK1 found by Project MinE researchers at University of Massachusetts and UMC Utrecht ...

New ALS gene C21orf2 identified by international research consortium Project MinE ...

FogHorn Systems secures $12 million in Series A funding ...

The Cloud

IBM Cloud ranked as leading Platform as a Service (PaaS) according to analyst firm ...

Oracle buys NetSuite ...

New Cloud-computing platform to further the analysis of microbial genomes ...

USFlash

Australian Government to make a $14 million investment in NCI's supercomputing and data storage capacity ...

Chip makes parallel programmes run faster with less code

20 Jun 2016 Cambridge - Computer chips have stopped getting faster. For the past 10 years, chips' performance improvements have come from the addition of processing units known as cores. In theory, a programme on a 64-core machine would be 64 times as fast as it would be on a single-core machine. But it rarely works out that way. Most computer programmes are sequential, and splitting them up so that chunks of them can run in parallel causes all kinds of complications.

In the May/June issue of the Institute of Electrical and Electronics Engineers' journalMicro, researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) presented a new chip design they call Swarm, which should make parallel programmes not only much more efficient but easier to write, too.

In simulations, the researchers compared Swarm versions of six common algorithms with the best existing parallel versions, which had been individually engineered by seasoned software developers. The Swarm versions were between three and 18 times as fast, but they generally required only one-tenth as much code - or even less. And in one case, Swarm achieved a 75-fold speedup on a programme that computer scientists had so far failed to parallelize.

"Multicore systems are really hard to program", stated Daniel Sanchez, an assistant professor in MIT's Department of Electrical Engineering and Computer Science, who led the project. "You have to explicitly divide the work that you're doing into tasks, and then you need to enforce some synchronization between tasks accessing shared data. What this architecture does, essentially, is to remove all sorts of explicit synchronization, to make parallel programming much easier. There's an especially hard set of applications that have resisted parallelization for many, many years, and those are the kinds of applications we've focused on in this paper."

Many of those applications involve the exploration of what computer scientists call graphs. A graph consists of nodes, typically depicted as circles, and edges, typically depicted as line segments connecting the nodes. Frequently, the edges have associated numbers called "weights", which might represent, say, the strength of correlations between data points in a data set, or the distances between cities.

Graphs crop up in a wide range of computer science problems, but their most intuitive use may be to describe geographic relationships. Indeed, one of the algorithms that the CSAIL researchers evaluated is the standard algorithm for finding the fastest driving route between two points.

In principle, exploring graphs would seem to be something that could be parallelized: Different cores could analyze different regions of a graph or different paths through the graph at the same time. The problem is that with most graph-exploring algorithms, it gradually becomes clear that whole regions of the graph are irrelevant to the problem at hand. If, right off the bat, cores are tasked with exploring those regions, their exertions end up being fruitless.

Of course, fruitless analysis of irrelevant regions is a problem for sequential graph-exploring algorithms, too, not just parallel ones. So computer scientists have developed a host of application-specific techniques for prioritizing graph exploration. An algorithm might begin by exploring just those paths whose edges have the lowest weights, for instance, or it might look first at those nodes with the lowest number of edges.

What distinguishes Swarm from other multicore chips is that it has extra circuitry for handling that type of prioritization. It time-stamps tasks according to their priorities and begins working on the highest-priority tasks in parallel. Higher-priority tasks may engender their own lower-priority tasks, but Swarm slots those into its queue of tasks automatically.

Occasionally, tasks running in parallel may come into conflict. For instance, a task with a lower priority may write data to a particular memory location before a higher-priority task has read the same location. In those cases, Swarm automatically backs out the results of the lower-priority tasks. It thus maintains the synchronization between cores accessing the same data that programmers previously had to worry about themselves.

Indeed, from the programmer's perspective, using Swarm is pretty painless. When the programmer defines a function, he or she simply adds a line of code that loads the function into Swarm's queue of tasks. The programmer does have to specify the metric - such as edge weight or number of edges - that the programme uses to prioritize tasks, but that would be necessary, anyway. Usually, adapting an existing sequential algorithm to Swarm requires the addition of only a few lines of code.

The hard work falls to the chip itself, which Daniel Sanchez designed in collaboration with Mark Jeffrey and Suvinay Subramanian, both MIT graduate students in electrical engineering and computer science; Cong Yan, who did her master's as a member of Daniel Sanchez's group and is now a PhD student at the University of Washington; and Joel Emer, a professor of the practice in MIT's Department of Electrical Engineering and Computer Science, and a senior distinguished research scientist at the chip manufacturer Nvidia.

The Swarm chip has extra circuitry to store and manage its queue of tasks. It also has a circuit that records the memory addresses of all the data its cores are currently working on. That circuit implements something called a Bloom filter, which crams data into a fixed allotment of space and answers yes/no questions about its contents. If too many addresses are loaded into the filter, it will occasionally yield false positives - indicating "yes, I'm storing that address" - but it will never yield false negatives.

The Bloom filter is one of several circuits that help Swarm identify memory access conflicts. The researchers were able to show that time-stamping makes synchronization between cores easier to enforce. For instance, each data item is labeled with the time stamp of the last task that updated it, so tasks with later time-stamps know they can read that data without bothering to determine who else is using it.

Finally, all the cores occasionally report the time stamps of the highest-priority tasks they're still executing. If a core has finished tasks that have earlier time stamps than any of those reported by its fellows, it knows it can write its results to memory without courting any conflicts.
Source: Massachusetts Institute of Technology - MIT

Back to Table of contents

Primeur weekly 2016-08-01

Special

National Strategic Computing Initiative Executive Council to unfold Strategic Plan ...

Quantum information science is to play a key role in the U.S. National Strategic Computing Initiative ...

Focus

Lenovo is heavily investing in new HPC technology, showing its commitment to the HPC market ...

South Africa's CHPC in the picture with new Lengau supercomputer, Student Cluster Competition victory and upcoming ICRI 2016 Conference ...

Exascale supercomputing

China starts developing new-era exascale supercomputer ...

Crowd computing

IBM intensifies fight against Zika ...

Middleware

Red Hat Satellite 6.2 introduces new features to help users increase efficiency across on-premise, Cloud, and container-based environments ...

Hardware

Mellanox Technologies receives Baidu's Award for Technology Leadership, drives company to new heights in machine learning ...

Medallia deploys Mellanox Ethernet solutions to supercharge real-time analytics and achieve the efficiency of hyperscale infrastructure ...

A research project coordinated by UC3M helps reduce the cost of parallel computing ...

Supermicro shipping latest Intel Xeon Phi processor server solutions in volume with Intel Omni-Path fabric ...

Vortex laser offers hope for Moore's Law ...

Penguin Computing provides high-performance computing cluster to University of Alaska Fairbanks ...

Fifth NVM Express Plugfest participation set a record; Next event scheduled for October 2016 ...

Physicists use supercomputers to find a way of making imitation graphene from salt ...

Chip makes parallel programmes run faster with less code ...

Applications

KnuEdge and University of California San Diego to host premiere industry conference to drive next-gen machine learning performance ...

Princeton Plasma Physics Laboratory and Princeton join high-performance software project ...

Red Hat unveils JBoss Data Grid 7 as platform for real-time data analytics ...

Teradata acquires Big Data Partnership consultancy and expands open source analytics services ...

PRACE to organize Women in HPC Workshop at SC16 ...

Lawrence Livermore National Laboratory chemist named Howes Scholar ...

NSF commits $35 million to improve scientific software ...

Making Big Data DANCE(S): XSEDE project successfully tests scheduled networking of Big Data ...

New ALS gene NEK1 found by Project MinE researchers at University of Massachusetts and UMC Utrecht ...

New ALS gene C21orf2 identified by international research consortium Project MinE ...

FogHorn Systems secures $12 million in Series A funding ...

The Cloud

IBM Cloud ranked as leading Platform as a Service (PaaS) according to analyst firm ...

Oracle buys NetSuite ...

New Cloud-computing platform to further the analysis of microbial genomes ...

USFlash

Australian Government to make a $14 million investment in NCI's supercomputing and data storage capacity ...