CPU vs GPU, mythbusted or mythdirected?
By Simon Bisson & Mary Branscombe in Editorial
Posted in visualisation, Processors, Silicon on
The folk from Mythbusters were on hand at NVision08 to show the audience the difference between CPU and GPU computing. In true Mythbusters fashion they did it with vast amounts of paint, and what must have been one of the world’s largest paintball guns.
First they began with a simple (for them) demonstration of serial operations - using a paintball gun wielding robot to draw a smiley face on a whiteboard. A hundred or so blue dots made the robot one of the slowest (and loudest) dot matrix printers we’ve seen.
Parallel operations would take something a little larger, and their 1100 paintball inkjet printer filled much of the stage. Powered up it would create a picture of the Mona Lisa in glorious 8-bit colour in a fraction of second. Huge air tanks held the compressed air the device needed to simultaneously launch all the paintballs in all the tubes.
The demonstration was certainly impressive, but it was more than a little misleading.
The type of data-centric work that CUDA GPUs handle is more about using parallel processes to handle lots of small pieces of data, not about building complex images from small pieces of data. With a parallel architecture like that you develop algorithms that break down big problems and big data sets into smaller, easier to work with, pieces. Farmed out across tens and hundreds of processors in a GPU, each data block can be processed, before being reassembled and the results delivered.
They’re not new techniques, either, for one thing the approach is at the heart of computational fluid dynamics and finite element analysis. The parallel techniques used in GPU computing are certainly impressive, and are already delivering supercomputing to the desktops of the scientists and engineers who need the power (an Nvision session on using GPU-based supercomputers to model the plasma dynamics around neutron stars and the black hole at the centre of the galaxy was particularly impressive). Low-cost high-performance computing is the GPU’s strength, especially when compared to the hefty power requirements of an equicalent array of traditional CPUs.
The Mythbusters’ demonstration was good (and an enjoyable piece of theatre), but it really told a different story. So how could the intrepid special effects team have told the real story of GPU computing?
How about one robot carrying a large, heavy cube across the stage? Suddenly it’s joined and over-taken by a swarm of smaller machines, all carrying smaller cubes - cubes that weigh as much as the single cube on the struggling robot. Or if paint is the preferred metaphor, a can of paint slowly emptying through a single pipe. Meanwhile another can empties through hundreds of holes in much less time.
So, how would you demonstrate it?
–S
Not yet rated
Loading ...
Wildfire!
By Simon Bisson & Mary Branscombe in Editorial
Posted in visualisation, FiRe, Google on
Driving from San Diego to Silicon Valley up the 101, we passed an airfield where helicopters were loading up with water and fire retardants. They were helping to control a wildfire in the Santa Cruz mountains, where dry bush had been burning for nearly six days. I knew what they were doing, and why, as I’d just had a crash course in California’s fire problems.
Back in San Diego, at FiRe, I spent some time listening in to a group of CTOs and other tech luminaries trying to come up with an improved IT architecture for fire fighters dealing with wildfires. Inspired by the response to 2007’s disastrous fire season, science fiction author and TV presenter David Brin presented a panel from all sides of the tech industry with a challenge from the local supervisor.
The panel included Larry Smarr, the head of UCSD’s super computuing visualisation lab. He had experience of helping coordinate volunteer imaging specialists during the fires, and of using the university’s IT resources to help disseminate information. The panel was joined by two local subject matter experts - one of whom was a fire chief who’d had to put his own men in the path of the fire to help track the source of the flames.
It turns out that San Diego has a lot of the basic infrastructure needed to build an effective fire detection and warning system - including sensors on mountain tops in risky areas. What’s really needed are a way of increasing sensor coverage at times of maximum risk - and of pinpointing fires directly. Information also needs to be routed to help support decisions that need to be made quickly - and presented in a manner that makes sense. Visualisation tools are important here, as they can bring information from multiple sensors and display it in an easy to understand manner alongside appropriate geographic information.
Two days weren’t enough to solve the problem, but plenty of good ideas made their way into an overall system diagram. FiRe’s brains trust may not have prevented the next round of fires, but some of its ideas will go back to the team at UCSD - as well as to the local fire departments. San Diego may not yet use airships to spot fires, but better image processing and improved sensors could go a long way to saving lives and property.
San Diego’s fires also made it to this week’s Google IO (our San Francisco destination). In a presentation on Google Earth, it tutned out that a local radio station used Google’s tools to create an impromptu early warning system on its web sites. Fire reports were plotted on a map, and used to help predict the likely trajectory of the wildfire.
Imaging and visualisation are critical technologies. We’re visual animals, and a well designed image can compress huge amounts of information into very few lines. Appropriate imaging (if it’s on UCSD’s super computers, or on Google Earth) is a powerful decision support tool - and one that in the face of wildfires most certainly saves lives.
Rated: 80% (1 votes)
Loading ...
Tag cloud
Archives
- November 2008
- October 2008
- September 2008
- August 2008
- July 2008
- June 2008
- May 2008
- April 2008
- March 2008
- February 2008
- January 2008
- December 2007
- November 2007
- October 2007
- September 2007
- August 2007
- July 2007
- June 2007
- May 2007
- April 2007
- March 2007
- February 2007
- January 2007
- December 2006
- November 2006
- October 2006
- September 2006
Most commented posts
- Java’s SSVAGENT.EXE: training the monkey
5 comments
- Wubi Tuesday
- Not very open, not very social
- The best mobile game ever
- A Big Day In The Enterprise IT World
- Employees are our most valuable asset (snigger)
- Biometrics - it's not the technology that's broken
- More battery life, fewer explosions
- Spam Fighting in Exchange
- IDF: Will SSD mean the end of 5GB free?
Highest Rated Blog Posts
- Nobody knows what Web 2.0 really is (100%)
- Songs of distant satellites (100%)
- Log in and lock in (100%)
- Mommy, why is there a home server in the office? (100%)
- Employees are our most valuable asset (snigger) (100%)
- Locking down IT or blocking creativity (100%)
- Video opera? What would you do with huge bandwidth and millions of pixels? (100%)
- Consumer BlackBerrys are good for business (100%)
- HD Trek (100%)
- Top tips for speeding up Vista (100%)