Skip to Main content Skip to Navigation
New interface
Conference papers

Non-generic floating-point software support for embedded media processing

Claude-Pierre Jeannerod 1, * Jingyan Jourdan-Lu 1, 2, * Christophe Monat 2, * 
* Corresponding author
1 ARIC - Arithmetic and Computing
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
2 Compilation Expertise Center
ST-GRENOBLE - STMicroelectronics [Grenoble]
Abstract : This paper presents some work in progress on the design and implementation of efficient floating-point software support for embedded integer processors. We provide quantitative evidence of the benefits of supporting various non-generic (that is, specialized, fused, or simultaneous) operations in addition to the five basic arithmetic operations: for individual calls, speedups range from 1.12 to 4.86, while on DSP kernels and benchmarks, our approach allows us to be up to 1.34x faster.
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download

https://hal.inria.fr/hal-00695333
Contributor : Claude-Pierre Jeannerod Connect in order to contact the contributor
Submitted on : Monday, May 7, 2012 - 6:10:05 PM
Last modification on : Tuesday, October 25, 2022 - 4:21:39 PM
Long-term archiving on: : Friday, November 30, 2012 - 11:25:09 AM

File

jeannerod_jourdan-lu_monat.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00695333, version 1

Citation

Claude-Pierre Jeannerod, Jingyan Jourdan-Lu, Christophe Monat. Non-generic floating-point software support for embedded media processing. 7th IEEE International Symposium on Industrial Embedded Systems (SIES'12), 2012, Karlsruhe, Germany. ⟨hal-00695333⟩

Share

Metrics

Record views

210

Files downloads

196