KEYWORDS: Digital signal processing, Image processing, Signal processing, Data processing, Printing, Scanners, Microelectromechanical systems, Digital electronics, Data integration, Algorithm development
This paper describes a high-performance scalable SIMD digital signal processor (DSP) developed for multifunctional printer systems. The proposed DSP supports a variable number of datapaths to cover a wide range of performance and maintains a RISC-like pipeline structure. Many special instructions suitable for image processing algorithms are included in the DSP. Various quad/dual instructions are supported to pack four data of byte length or two data of half-word length into one word length form. To process image data that have various bit-lengths, the proposed DSP is able to perform bit-field extraction/insertion before and after ALU operations. The DSP supports up to 4 extraction/insertion patterns at the same time, and one of them can be specified in the related instruction. Conditional instructions are supported to deal with complex relative conditions efficiently. In addition, an intelligent DMA block is integrated to align data in the course of data reading, because the alignment function can be implemented with a little hardware. Experimental results on typical image processing algorithms show that the proposed SIMD DSP is two times effective in performance compared to a commercial high-end DSP.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.