Name
Abstract | ||
|---|---|---|
Many embedded applications strive for high performance and power efficiency but rely on latency-intensive floating-point operations. This expensiveness can be offset, for example, by approximate and mixed-precision floating-point computation. In this paper, we present a novel concept called anytime instructions. Anytime instructions explicitly specify the number of result bits that are calculated at full precision. After presenting the basics of anytime instructions, we apply this novel concept to floating-point division by presenting an anytime division functional unit that is implemented in a VLIW processor. In this setup, we show the effectiveness of anytime instructions in iterative computations. We show a latency improvement of 54.8 % for computing 53 iterations of the Babylonian method for square-root calculation while not sacrificing the accuracy of the final square-root result.
|
Year | DOI | Venue |
|---|---|---|
2019 | 10.1145/3310273.3322833 | Proceedings of the 16th ACM International Conference on Computing Frontiers |
Keywords | Field | DocType |
approximate computing, floating-point divider, programmable accuracy functional unit | Electrical efficiency,Methods of computing square roots,Latency (engineering),Floating point,Very long instruction word,Computer science,Parallel computing,Embedded applications,Offset (computer science),Computation | Conference |
ISBN | Citations | PageRank |
978-1-4503-6685-4 | 2 | 0.38 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Marcel Brand | 1 | 2 | 1.74 |
| Michael Witterauf | 2 | 15 | 6.36 |
| Frank Hannig | 3 | 595 | 75.66 |
| Juergen Teich | 4 | 90 | 18.01 |