Title | ||
---|---|---|
Abstract: Automatically Adapting Programs for Mixed-Precision Floating-Point Computation |
Abstract | ||
---|---|---|
As scientific computation continues to scale, it is crucial to use floating-point arithmetic processors as efficiently as possible. Lower precision allows streaming architectures to perform more operations per second and can reduce memory bandwidth pressure on all architectures. However, using a precision that is too low for a given algorithm and data set will result in inaccurate results. In this poster, we present a framework that uses binary instrumentation and modification to build mixed-precision configurations of existing binaries that were originally developed to use only double-precision. This allows developers to easily experiment with mixed-precision configurations without modifying their source code, and it permits auto-tuning of floating-point precision. We also implemented a simple search algorithm to automatically identify which code regions can use lower precision. We include results for several benchmarks that show both the efficacy and overhead of our tool. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/SC.Companion.2012.231 | SC Companion |
Keywords | DocType | Citations |
floating point arithmetic,algebra | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael O. Lam | 1 | 50 | 5.15 |
de Supinski, Bronis R. | 2 | 2667 | 154.44 |
Matthew LeGendre | 3 | 68 | 5.67 |
Jeffrey K. Hollingsworth | 4 | 1881 | 192.59 |