OPTIMIZATION ANALYSIS OF PPI_MO BASED MATRIX MULTIPLICATION USING IEEE 754 FLOATING POINT MULTIPLIER
1Asim Darshan, 2Ashish Raghuwanshi
Department of Electronics and Communication, IES college of Technology, Bhopal1,2
Abstract— In the present scenario, the rapid growth of wireless communication, multimedia applications, robotics and graphics increases the demand for resource efficient, high throughput and low power digital signal processing (DSP) systems. Floating point matrix multiplication is the most widely used fundamental processing element in almost all DSP systems ranging from audio/video signal processing to wireless sensor networks. Hardware implementation of Floating point matrix multiplication requires a huge number of arithmetic operations that affect the speed and consumes more area and power. Pipelining and parallel processing are the two methods used in the DSP systems to reduce the area. Matrix multiplication is the kernel operation used in many transform, image and discrete signal processing application. We develop new algorithms and new techniques for matrix multiplication on configurable devices. In this paper, we have proposed three designs for matrix-matrix multiplication. These design reduced hardware complexity, throughput rate and different input/output data format to match different application needs. The PPI-MO based matrix multiplication is design Xilinx software and simulated number of slice, look up table and delay.
Keywords— IEEE754, Single Precision Floating Point (SP FP), Double Precision Floating Point (DP FP), Matrix Multiplication