This paper presents the basic parallel implementation and a variation for matrix – vector multiplication. We evaluated and compared the performance of the two implementations on a cluster of workstations using Message Passing Interface (MPI) library. The experimental results demonstrate that the basic implementation achieves lower performance than the other variation. Further, we analyzed the several classes of overheads contribute to lowered performance of the basic implementation. These analyses have identified cost of reading of data from disk and communication cost as the primary factors affecting performance of the basic parallel matrix – vector implementation. Finally, we present a performance model for estimating the performance of two proposed matrix – vector implementations on a cluster of heterogeneous workstations.