International Conference on Innovations In Intelligent Instrumentation, Optimization and Electrical Sciences |
Foundation of Computer Science USA |
ICIIIOES - Number 7 |
December 2013 |
Authors: R. Saranya, S. Kousalya Devi, V. Lakshmi Prabha |
5936c440-3196-483b-bdd5-7bbbbfea66fd |
R. Saranya, S. Kousalya Devi, V. Lakshmi Prabha . Compression of FPGA Bit stream using modified Decode Aware Placement Algorithm. International Conference on Innovations In Intelligent Instrumentation, Optimization and Electrical Sciences. ICIIIOES, 7 (December 2013), 21-25.
FPGA uses a promising technology for developing high-performance embedded systems. Reconfiguration systems widely uses Field Programmable Gate Arrays and configured using bitstream often loaded from memory. The Bitstream Compression and Decompression technique reduce the size of the bitstream and also limits the memory constraint. The Compression mechanism improves the access bandwidth for communication and thereby decreases the reconfiguration time. The Existing Approach implements the combination of techniques Dictionary Selection, Bitmask Selection and Run Length Encoding with Decode-aware Placement technique. The drawback of this approach is the extent of continuous variation of bitstream in the Run Length Encoding. The proposed work of this paper is Golomb Encoding in place of Runlength encoding known as modified Decode Aware Compression method. Golomb Encoding is a compression technique which is capable of compressing larger size data into smaller size data. In addition, the achieved Compression Ratio is independent of the decompression hardware. It depends only on the entropy of the configuration bitstream. Finally, a time to configure FPGA depends only on the data rate of the configuration mechanism. The speed of a memory stores the configuration data, and the size of the configuration bit-stream.