News & Analysis
Comment
peter.clarke
LarryM99
Game platform programmers (at least the good ones) are already very adept at ...
Parallelization tool for Tegra to show at ESC
Peter Clarke
9/23/2011 7:37 AM EDT
LONDON – Vector Fabrics BV is planning to demonstrate its vfEmbedded software development tool for parallelizing code operating on Tegra multi-core processors from Nvidia Corp. at the upcoming Embedded Systems Conference in Boston.
The vfEmbedded tool supports the dual-core ARM Cortex-A9 configuration found in the Tegra-2 mobile chip, and will support the quad-core ARM processor in Nvidia's next-generation Tegra chip, which is codenamed Kal-el and designed for tablet and smartphone devices, according to Vector Fabrics (Eindhoven, The Netherlands)
"We're excited to see Nvidia push the mobile industry toward multi-core. To fully unlock the performance potential of these high-performance architectures however, developers need multicore development tools. Optimizing the software by hand is simply too complex, takes too much time, is error prone, and won't result in an optimal implementation. vfEmbedded tackles these challenges with ease," said Mike Beunder, CEO at Vector Fabrics, in a statement.
Presentations on vfEmbedded applied to code for Tegra will take place on the Vector Fabrics booth #424 during the exhibition.
The exhibition takes place September 26 to 29 at the Hynes Convention Center, Boston, Massachusetts. It is organized by UBM Electronics, which is also the publisher of EE Times.
Related links and articles:
esc.eetimes.com/boston/
News articles:
Consumer meets medical in ESC teardown
ESC study highlights software checking
EE Times' advance coverage of ESC Boston
|
|
|
|
|
Navigate to related information
LarryM99
9/29/2011 1:35 PM EDT
Game platform programmers (at least the good ones) are already very adept at multicore programming. Likewise for hardcore embedded guys. The real win here is for the other 99% of the programming population.
Larry M.
Sign in to Reply
peter.clarke
11/3/2011 9:00 AM EDT
@Larry
Expert programmers may be able to juggle these things for CPU-GPU interactions and dual-core set ups but I think the problems increase exponentially with core number. It may become too complex to optimize fully some problems beyond 4 cores or so but machines running software will have a better chance of being rigorous and avoiding software deadlocks and race conditions than humans.
Sign in to Reply