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
- Mars Needs Women
- IBM Will Minimize Impact of Future Disasters
- Sublime Text: One Editor to Rule Them All?
- December 2013 Issue of Linux Journal: Readers' Choice
- Raspberry Pi: the Perfect Home Server
- RSS Feeds
- Tech Tip: Really Simple HTTP Server with Python
- Linux Systems Administrator
- Web Administration Scripts
- Nothing is perfect
10 min 11 sec ago
- Mixtapes Community
5 hours 49 min ago
- KDE is one true DE
6 hours 23 min ago
- Command Line Shells (Bash, Zsh, etc.) are 2nd place
6 hours 52 min ago
8 hours 46 min ago
- yes it's Jupiter Broadcasting
10 hours 6 min ago
- nice to see PClinuxOS finally
12 hours 40 min ago
- Personally, I am no longer a
13 hours 36 min ago
- It's Jupiter
1 day 4 hours ago
- GIMP is certainly a graphic
1 day 5 hours ago