SONIC – A Plug-In Architecture for Video Processing
This paper presents the SONIC reconfigurable computing architecture and the first implementation, SONIC-1. SONIC is designed to support the software plug-in methodology to accelerate video image processing applications. SONIC differs from other architectures through the use of plug-in Processing Elements (PIPEs) and the Application Programmer’s Interface (API). Each PIPE contains a reconfigurable processor, a scaleable router that also formats video data, and a frame-buffer memory. The SONIC architecture integrates multiple PIPEs together using a specialised bus structure that enables flexible and optimal pipelined processing. SONIC-1 communicates with the host PC through the PCI bus and has 8 PIPEs. We have developed an easy to use API that allows SONIC-1 to be used by multiple applications simultaneously. Preliminary results show that a 19 tap separable 2-D FIR filter implemented on a single PIPE achieves processing rates of more than 15 frames per second operating on 512 x 512 video transferred over the PCI bus. We estimate that using all 8 PIPEs, we could obtain real-time processing rates for complex operations such as image warping.
KeywordsVideo Processing Image Warping Hardware Acceleration Reconfigurable Logic Video Image Processing
Unable to display preview. Download preview PDF.
- 1.Athanas, P.M., Abbott, A.L.: Real-Time Image Processing on a Custom Computing Platform. IEEE Computer 28(2), 16–24 (1995)Google Scholar
- 2.Mackinlay, P.I., Cheung, P.Y.K., Luk, W., Sandiford, R.D.: Riley-2: A flexible platform for codesign and dynamic reconfigurable computing research. In: Luk, W., Cheung, P.Y.K., Glesner, M. (eds.) Field-Programmable Logic and Applications. LNCS, vol. 1304, pp. 91–100. Springer, Heidelberg (1997)CrossRefGoogle Scholar
- 3.Singh, S., Slous, R.: Accelerating Adobe Photoshop with Reconfigurable Logic. In: IEEE Symposium on FPGAs for Custom Computing Machines, April 15th - 17th, pp. 236–244 (1998)Google Scholar
- 5.Kung, H.T.: Computational Models For Parallel Computers. In: Elliot, R.J., Hoare, C.A.R. (eds.) Scientific applications of Microprocessors, pp. 1–15. Prentice Hall, Englewood Cliffs (1989)Google Scholar
- 6.Hudson, R.D., Lehn, D.I., Athanas, P.M.: A Run-Time Reconfigurable Engine for Image Interpolation. In: IEEE Symposium on FPGAs for Custom Computing Machines, April 15th - 17th, pp. 88–95 (1998)Google Scholar