Name
Abstract | ||
|---|---|---|
The increase of performance in handheld devices due to their widespread adoption has required the integration of several distinct kinds of processor in a single chip. These technologies have turned current Systems on Chip into heterogeneous platforms. Stencil codes are a family of algorithms that appear in many relevant scientific and image processing codes. In order to improve the performance of these algorithms in heterogeneous platforms, the usage of accelerators is very important but, for a mobile applications developer, the development cost is very high. We propose a methodology, based in our framework Paralldroid, for automatically generating accelerated implementations of several well-known representative stencil codes. The performance of these codes has also been measured in order to demonstrate how Paralldroid is able to accelerate code without extensive or complex modifications. Results show great performance improvements for few code modifications. |
Year | Venue | Field |
|---|---|---|
2017 | ICA3PP | RenderScript,Android (operating system),Computer science,Image processing,Stencil code,Chip,Implementation,Mobile device,Acceleration,Embedded system |
DocType | Citations | PageRank |
Conference | 1 | 0.37 |
References | Authors | |
9 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sergio Afonso | 1 | 2 | 0.80 |
| Alejandro Acosta | 2 | 55 | 8.98 |
| F. Almeida | 3 | 343 | 49.54 |