TY - GEN
T1 - Tunable precision control for approximate image filtering in an in-memory architecture with embedded neurons
AU - Dube, Ayushi
AU - Wagle, Ankit
AU - Singh, Gian
AU - Vrudhula, Sarma
N1 - Publisher Copyright:
© 2022 Association for Computing Machinery.
PY - 2022/10/30
Y1 - 2022/10/30
N2 - This paper presents a novel hardware-software co-design consisting of a Processing in-Memory (PiM) architecture with embedded neural processing elements (NPE) that are highly reconfigurable. The PiM platform and proposed approximation strategies are employed for various image filtering applications while providing the user with fine-grain dynamic control over energy efficiency, precision, and throughput (EPT). The proposed co-design can change the Peak Signal to Noise Ratio (PSNR, output quality metric for image filtering applications) from 25dB to 50dB (acceptable PSNR range for image filtering applications) without incurring any extra cost in terms of energy or latency. While switching from accurate to approximate mode of computation in the proposed co-design, the maximum improvement in energy efficiency and throughput is 2X. However, the gains in energy efficiency against a MACbased PE array with the proposed memory platform are 3X-6X. The corresponding improvements in throughput are 2.26X-4.52X, respectively.
AB - This paper presents a novel hardware-software co-design consisting of a Processing in-Memory (PiM) architecture with embedded neural processing elements (NPE) that are highly reconfigurable. The PiM platform and proposed approximation strategies are employed for various image filtering applications while providing the user with fine-grain dynamic control over energy efficiency, precision, and throughput (EPT). The proposed co-design can change the Peak Signal to Noise Ratio (PSNR, output quality metric for image filtering applications) from 25dB to 50dB (acceptable PSNR range for image filtering applications) without incurring any extra cost in terms of energy or latency. While switching from accurate to approximate mode of computation in the proposed co-design, the maximum improvement in energy efficiency and throughput is 2X. However, the gains in energy efficiency against a MACbased PE array with the proposed memory platform are 3X-6X. The corresponding improvements in throughput are 2.26X-4.52X, respectively.
KW - Peak Signal to Noise Ratio (PSNR)
KW - Processing in-Memory (PiM)
KW - and throughput (EPT)
KW - energy efficiency
KW - neural processing elements (NPE)
KW - precision
UR - http://www.scopus.com/inward/record.url?scp=85145650491&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85145650491&partnerID=8YFLogxK
U2 - 10.1145/3508352.3549385
DO - 10.1145/3508352.3549385
M3 - Conference contribution
AN - SCOPUS:85145650491
T3 - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
BT - Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 41st IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2022
Y2 - 30 October 2022 through 4 November 2022
ER -