Design And Analysis of Low Power Single Exact Adder Dual Approximate Adder
Keywords:
Mirror Adder, SEDA Adder, Power Consumption, Voltage Scaling, Error MitigationAbstract
The notion of approximation computing has attracted a great deal of interest and recognition, primarily because of its noteworthy benefits with respect to energy efficiency in a variety of applications that are somewhat error-tolerant. The current study offers a suggested adder that is ideal for processor integration since it can execute dual approximate addition (SEDA) and n-bit single exact addition. In this study, approximate adders with dynamic runtime reconfigurability between accurate and approximate modes at the circuit level are designed. In this paper, we present the idea of highly configurable Single Exact Single Approximate (SESA) adders, which provide fine control over the trade-off between exact and approximate computing modes. Furthermore, we introduce the Single Exact Dual approximation (SEDA) adder, which provides the option to adjust the granularity level between exact and approximation modes. The SEDA adder, as opposed to SESA adders, makes it easier to carry out two approximation computations simultaneously. For both the SESA and SEDA adders, the maximum bounded error is present. After being installed at a 32nm technology node, the Tanner EDA tool was used to evaluate the SESA and SEDA adders.
Downloads
References
Lee, Y. H., Kuei, C. H., Kao, Y. Z., & Fan Jiang, S. S. (2021). Algorithm and VLSI architecture designs of a lossless embedded compression encoder for HD video coding systems. Journal of Circuits, Systems and Computers, 30(04), 2130004.
Sasikumar, A., Subramaniyaswamy, V., Jannali, R., Rao, V. S., & Ravi, L. (2022). Design and area optimization of CMOS operational amplifier circuit using hybrid flower pollination algorithm for IoT end-node devices. Microprocessors and Microsystems, 93, 104610.
Chung, Y., & Kim, Y. (2021). Comparison of approximate computing with sobel edge detection. IEIE Transactions on Smart Processing & Computing, 10(4), 355-361.
Hasan, M., Siddique, A. H., Mondol, A. H., Hossain, M., Zaman, H. U., & Islam, S. (2021). Comprehensive study of 1-bit full adder cells: review, performance comparison and scalability analysis. SN Applied Sciences, 3(6), 644.
Pandey, D., Singh, S., Mishra, V., Satapathy, S., & Banerjee, D. S. (2021, May). Sam: Segmentation based approximate multiplier for error tolerant applications. In 2021 IEEE International Symposium on Circuits and Systems (ISCAS) (pp. 1-5).
Mohammadi, A., Ghanatghestani, M. M., Molahosseini, A. S., & Mehrabani, Y. S. (2022). High-performance and energy-area efficient approximate full adder for error tolerant applications. ECS Journal of Solid State Science and Technology, 11(8), 081010.
Shin, H., Kang, M., & Kim, L. S. (2021, December). Fault-free: a fault-resilient deep neural network accelerator based on realistic reram devices. In 2021 58th ACM/IEEE Design Automation Conference (DAC) (pp. 1039-1044). IEEE.
Sasikumar, A., Ravi, L., Kotecha, K., Indragandhi, V., & Subramaniyaswamy, V. (2022). Reconfigurable and hardware efficient adaptive quantization model-based accelerator for binarized neural network. Computers and Electrical Engineering, 102, 108302.
Liu, W., Zhang, T., McLarnon, E., O’Neill, M., Montuschi, P., & Lombardi, F. (2019). Design and analysis of majority logic-based approximate adders and multipliers. IEEE transactions on emerging topics in computing, 9(3), 1609-1624.
Nojehdeh, M. E., & Altun, M. (2020). Systematic synthesis of approximate adders and multipliers with accurate error calculations. Integration, 70, 99-107.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 International Journal of Scientific Research in Science and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
