In modern clustering environments where memory hierarchy has many layers (distributed memory, shared memory layer, cache, etc.), an important question is how to fully utilize all available resources and identify the most dominant layer in certain computation. When combining algorithms on all layers together, what would be the best method to get the best performance out of all the resources we have?
Mixed mode programming model that uses thread programming on the shared memory layer and message passing programming on the distributed memory layer is a method that many researchers are using to utilize the memory resources. In this paper, we take an algorithmic approach that uses matrix multiplication as a tool to show how cache algorithms affect the performance of both shared memory and istributed memory algorithms. It is also important to consider the underlying sequential component of the algorithm; in fact not doing so may be misleading and simply combining shared memory and distributed memory algorithms could lead to incorrect conclusions.