Distributed shared memory for function-grained graph reduction machine

The paper proposes an efficient DSM system, which enables tasks to access the virtual global memory, for the function grained graph reduction machine. The function grained graph reduction machine is a parallel machine with distributed memory, which stores the graph nodes representing function applications in the distributed memory and enables its processing elements to reduce them by executing tasks concurrently. The machine requires a global memory access system so that a task can access any of the distributed graph nodes. We describe DSM system that uses H-object as the unit of sharing and simplifies memory coherence problem by using the weak coherence semantics and two types of read operations. We also present the experimental results using the prototype machine built on a transputer network system