TY - GEN

T1 - Accelerating the performance of stochastic encoding-based computations by sharing bits in consecutive bit streams

AU - Li, Peng

AU - Lilja, David J.

PY - 2013/9/9

Y1 - 2013/9/9

N2 - Stochastic encoding represents a value using the probability of ones in a random bit stream. Computation based on this encoding has good fault-tolerance and low hardware cost. However, one of its major issues is long processing time. We have to use a long enough bit stream to represent a value to guarantee that random fluctuations introduce only small errors to final computation results. For example, for most digital image processing algorithms, we need a 512-bit stream to represent an 8-bit pixel value stochastically to guarantee that the final computation error is less than 5%. To solve this issue, this paper proposes to share bits between adjacent bit streams to represent adjacent deterministic values. For example, in image processing applications, the bit stream which represents the current pixel value can share parts of the bits in the bit stream which represents the previous pixel value. We use an image contrast stretching algorithm to evaluate this method. Our experimental results show that the proposed methods can improve the performance by 90%.

AB - Stochastic encoding represents a value using the probability of ones in a random bit stream. Computation based on this encoding has good fault-tolerance and low hardware cost. However, one of its major issues is long processing time. We have to use a long enough bit stream to represent a value to guarantee that random fluctuations introduce only small errors to final computation results. For example, for most digital image processing algorithms, we need a 512-bit stream to represent an 8-bit pixel value stochastically to guarantee that the final computation error is less than 5%. To solve this issue, this paper proposes to share bits between adjacent bit streams to represent adjacent deterministic values. For example, in image processing applications, the bit stream which represents the current pixel value can share parts of the bits in the bit stream which represents the previous pixel value. We use an image contrast stretching algorithm to evaluate this method. Our experimental results show that the proposed methods can improve the performance by 90%.

KW - Computer reliability

KW - digital image processing

KW - fault tolerance

KW - logic design

KW - stochastic computing

UR - http://www.scopus.com/inward/record.url?scp=84883421094&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883421094&partnerID=8YFLogxK

U2 - 10.1109/ASAP.2013.6567585

DO - 10.1109/ASAP.2013.6567585

M3 - Conference contribution

AN - SCOPUS:84883421094

SN - 9781479904921

T3 - Proceedings of the International Conference on Application-Specific Systems, Architectures and Processors

SP - 257

EP - 260

BT - ASAP 2013 - Proceedings of the 2013 IEEE 24th International Conference on Application-Specific Systems, Architectures and Processors

T2 - 2013 IEEE 24th International Conference on Application-Specific Systems, Architectures and Processors, ASAP 2013

Y2 - 5 June 2013 through 7 June 2013

ER -