How We Should Program GPGPUs
The future for GPU programming is getting brighter; these devices will become more convenient to program. There is no magic bullet; only appropriate algorithms written in a transparent style can be compiled for GPUs; users must understand and accept their advantages and limitations. These are not standard processor cores.
The industry can expect additional development of programmable accelerators, targeting different application markets. The cost of entering the accelerator market is much lower than for the CPU market, making a niche target market potentially attractive. The compiler method described here is robust enough to provide a consistent interface for a wide range of accelerators.
Michael Wolfe has been a compiler engineer at The Portland Group since joining in 1996, where his responsibilities and interests include deep compiler analysis and optimizations ranging from improving power consumption for embedded microcores to improving the efficiency of FORTRAN on parallel clusters. He has a PhD in Computer Science from the University of Illinois and authored High Performance Compilers for Parallel Computing, Optimizing Supercompilers for Supercomputers and many technical papers.
- Readers' Choice Awards 2013
- Linux Kernel News - November 2013
- Mars Needs Women
- Sublime Text: One Editor to Rule Them All?
- RSS Feeds
- Raspberry Pi: the Perfect Home Server
- December 2013 Issue of Linux Journal: Readers' Choice
- Tech Tip: Really Simple HTTP Server with Python
- Advanced Hard Drive Caching Techniques
- IBM Will Minimize Impact of Future Disasters
- The kernel doesn't really
6 hours 9 min ago
6 hours 40 min ago
6 hours 40 min ago
8 hours 45 min ago
- This should be very helpful
9 hours 59 min ago
- As much as I share your point
12 hours 19 min ago
- So girls had it better ?
15 hours 51 min ago
- Reply to comment | Linux Journal
16 hours 11 min ago
- why is GNOME 3 in the fifth position at 14.1 %?
21 hours 43 min ago
- Sublime Is Brilliant!
1 day 2 hours ago