Statistical analysis of Parallel Matrix Multiplication in SIMD model using ‘p’,‘p2’,‘p3’ processor's with different interconnection network

In the previous paper we introduce the statistical definitions of an algorithm in parallel architecture (PRAM)[1]. In this paper we make a proper selection for the given matrix-matrix multiplication operation through in SIMD and to decide which is the best suitable algorithm that generates a high throughput with a minimum time, a comparison analysis and a performance evaluation for the parallel algorithms is carried out using the different interconnection networks with `p', `p2', `p3' number of processors. In this paper, a theoretical analysis for the performance and evaluation of the Parallel Matrix Multiplication Algorithms (PMMA) is carried out. However a two `4 × 4' matrix multiplication experimental analysis is performed to support the theoretical analysis results.