DATA-DEPENDENCY DECOMPOSITION OF COLOUR SPACE TRANSFORMATION FOR MICROPROCESSOR BY USING PARALLEL SA-C PROGRAMMING

J.-L. Kuo and K.-L. Chao

Keywords

Nominal decomposition, reconfigurable computing system, single assignment C, parallel computing, VHDL, colour space, chromaticity coordinate, data flow graph, lookup table

Abstract

This paper proposes nominal decomposition for calculating colour space transformation in single assignment language, to speed up execution time. Chromaticity coordinate transformation is discussed within the framework of nominal decomposition. The gamma curve look-up table (LUT) for function mapping is also discussed with reference to Taylor expansion with 20-point and 100-point LUT types. The numerical value is decomposed into nominal value and base value, respectively. K-Table matrices for different bases are also proposed, to provide the base change for the associated derivation. Such an algorithm is suitable for the programming of single assignment C (SA-C). The hardware description language very-high-speed integrated circuit hardware description language (VHDL) can be generated by using data flow graph (DFG) in a SA-C compiler. The results will show that the proposed algorithm can shorten the execution time to a certain extent. It is evident that the proposed algorithm can be very helpful in implementing the hardware interface or software driver for the processor display and printer system.

Important Links:



Go Back