MIT researchers develop new programming language for multicore image processing
August 06, 2012 // Nick Flaherty
Researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a new programming language for multicore image processing algorithms called Halide.
Not only are Halide programs easier to read, write and revise than image-processing programs written in a conventional language, but because Halide automates code-optimization procedures that would ordinarily take hours to perform by hand, they're also significantly faster says the team.
In tests, the MIT researchers used Halide to rewrite several common image-processing algorithms whose performance had already been optimized by seasoned programmers. The Halide versions were typically about one-third as long but offered significant performance gains — two-, three-, or even six-fold speedups. In one instance, the Halide program was actually longer than the original — but the speedup was 70-fold.
However the developmentis currently separate to the OpenCL multicore programming specification.
Jonathan Ragan-Kelley, a graduate student in the Department of Electrical Engineering and Computer Science (EECS), and Andrew Adams, a CSAIL postdoc, led the development of Halide, and they've released the code online.
Halide doesn't spare the programmer from thinking about how to parallelize efficiently on particular machines, but it splits that problem off from the description of the image-processing algorithms. A Halide program has two sections: one for the algorithms, and one for the processing "schedule." The schedule can specify the size and shape of the image chunks that each core needs to process at each step in the pipeline, and it can specify data dependencies — for instance, that steps being executed on particular cores will need access to the results of previous steps on different cores. Once the schedule is drawn up, however, Halide handles all the accounting automatically.
A programmer who wants to export a program to a different machine just changes the schedule, not the algorithm description. A programmer who wants to add a new processing step to the pipeline just plugs in a description of the new procedure, without having to modify the existing ones. (A new step in the pipeline will require a corresponding specification in the schedule, however.)
"When you have the idea that you might want to parallelize something a certain way or use stages a certain way, when writing that manually, it's really hard to express that idea correctly," says Ragan-Kelley. "If you have a new optimization idea that you want to apply, chances are you're going to spend three days debugging it because you've broken it in the process. With this, you change one line that expresses that idea, and it synthesizes the correct thing."
Although Halide programs are simpler to write and to read than ordinary image-processing programs, because the scheduling is handled automatically, they still frequently offer performance gains over even the most carefully hand-engineered code. Moreover, Halide code is so easy to modify that programmers could simply experiment with half-baked ideas to see if they improve performance.
"You can just flail around and try different things at random, and you'll often find something really good," says Adams. "Only much later, when you've thought about it very hard, will you figure out why it's good."
Automotive microcontroller benchmark takes energy efficiency into account
May 21, 2013
Today, cars are crammed with microprocessors, and many of them are not completely switched off when the driver parks and ...
EnSilica partners Cross Border Technologies to boost sales growth in key European markets
Industry's first ultra-wideband Doherty amplifiers support broadband operation
Graphics chip recognizes nearby pedestrians and bicycles
Electronics Manufacturing Services boom for medical industry says analyst
Gemalto teams with Encore Networks for mission critical M2M communications as US shifts to wireless
May 21, 2013
European smartcard specialist Gemalto has teamed up with US machine-to-machine (M2M) router supplier Encore Networks to provide ...
Solar industry capital spending hits seven-year low in 2013 but upturn is on the cards
Apple's overseas tax evasion stirs debate over US tax code
Could Intel enable USD200 Ultrabook?
InterviewWireless control drives Atmel in Europe
Atmel's recent acquisition of Osmo Devices with a WiFi Direct design center in Cambridge and some key microcontroller launches has seen the company focus heavily on wireless control in Europe says Jörg ...
Filter WizardCheck out the Filter Wizard Series of articles by Filter Guru Kendall Castor-Perry which provide invaluable practical Analog Design guidelines.
Linear video channel
READER OFFERRead more
The development platform for i.MX 6Quad from element14 (built to the Freescale SABRE Lite design) is an evaluation platform featuring the powerful i.MX 6Q, a multimedia application processor with Quad ARM Cortex-A9 cores at 1.2 GHz from Freescale Semiconductor.
This month, Freescale and element14 are giving away five such platforms, worth £128.06 each, for EETimes Europe's readers to win. The platform helps evaluate the rich set of peripherals and includes a 10/100/Gb Ethernet port, SATA-II, HDMI v1.4, LVDS, parallel RGB interface, touch screen interface, analog headphone/microphone, micro TF and SD card interface, USB, serial port, JTAG, camera interface, and input keys for Android.
And the winners are...
In our previous reader offer, Pico Technology was giving away one of its recently launched PicoScope 3207B, a 2-channel USB 3.0 oscilloscope worth 1451 Euros. Lucky winner Mr L. Sanchez-Gonzalez from Spain should be receiving his PicoScope 3207B soon. Let's wish them some interesting findings with his projects.
December 15, 2011 | Texas instruments | 222901974
Unique Ser/Des technology supports encrypted video and audio content with full duplex bi-directional control channel over a single wire interface.