Inexpensive Correctly Rounded Floating-Point Division and Square Root With Input Scaling
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Details
| Translated title of the contribution | Inexpensive Correctly Rounded Floating-Point Division and Square Root With Input Scaling |
|---|---|
| Original language | English |
| Title of host publication | 2013 IEEE Workshop on Signal Processing Systems in Taipei, Taiwan, October 16th-18th, SIPS 2013 |
| Publisher | Institute of Electrical and Electronics Engineers IEEE |
| Pages | 159-164 |
| Number of pages | 6 |
| ISBN (Print) | 978-1-4673-6238-2 |
| Publication status | Published - 2013 |
| Publication type | A4 Article in a conference publication |
| Event | IEEE Workshop on Signal Processing Systems - Duration: 1 Jan 1900 → … |
Publication series
| Name | IEEE Workshop on Signal Processing Systems |
|---|---|
| ISSN (Print) | 2162-3562 |
Conference
| Conference | IEEE Workshop on Signal Processing Systems |
|---|---|
| Period | 1/01/00 → … |
Abstract
Recent embedded DSPs are incorporating IEEE-compliant floating point arithmetic to ease the development of, e.g., multiple antenna MIMO in software-defined radio. An obvious choice of FPU architecture in DSP is to include a fused multiply-add (FMA) operation, which accelerates most DSP applications. Another advantage of FMA is that it enables fast software algorithms for, e.g., division and square root without much additional hardware. However, these algorithms are nontrivial to perform at the target accuracy to get the correctly rounded result without danger of overflow. Previous FMA-based systems either rely on a powerhungry wide intermediate format or forego correct rounding. A wide format is unattractive in a power-sensitive embedded environment since it requires enlarged register files, wider data buses and possibly a larger multiplier. We present provably correct algorithms for efficient IEEE-compliant division and square root with only a 32-bit format using hardware prescaling and postscaling steps. The required hardware has approximately 8% of area and power footprint of a single FMA unit.
Publication forum classification
Field of science, Statistics Finland
Downloads statistics
No data available