Title :
Low power DCT using highly scalable multipliers
Author :
Castellanos, Ricardo ; Kalva, Hari ; Shankar, Ravi
Author_Institution :
Dept. of Comput. Sci. & Eng., Florida Atlantic Univ., Boca Raton, FL, USA
Abstract :
Low power consumption in computing systems is a key requirement for devices such as cell phones and cameras. In this paper we present a low power DCT implementation using a highly scalable multiplier. This paper focuses on IDCT with playback applications such as digital photo displays. The proposed solution exploits the fact that the size of the multiplications varies per stage in a multistage IDCT implementation and configuring multipliers to match the needs of each stage saves power. Results are compared with Wallace and array multipliers. We show that using a scalable multiplier and dynamically reconfiguring the width of the multiplier leads to significant power savings (over 72%) with negligible degradation in decoded image quality.
Keywords :
decoding; discrete cosine transforms; image coding; Wallace multipliers; array multipliers; camera; cell phones; digital photo displays; discrete cosine transforms; highly scalable multipliers; image quality decoding; low power DCT; low power consumption; Decoding; Discrete cosine transforms; Discrete transforms; Energy consumption; Image storage; Matrix decomposition; Quantization; Signal processing algorithms; Sparse matrices; Video compression;
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2009.5413517