A parallel computer whose processors' main memory is physically separated from each others -- contrast with shared memory
Computer memory that is physically distributed among several processors that are connected by an interprocessor communications network. Each processor can only address its local memory, so data in other processors' memories must be transferred by interprocess communication.
Memory that is physically distributed among several modules. A distributed-memory architecture may appear to users to have a single address space and a single shared memory or may appear as disjoint memory made up of many separate address spaces.
Architectural class of machines in which the memory of the system is distributed over the nodes in the system. Access to the data in the system has to be done via an interconnection network that connects the nodes and may be either explicit via message passing or implicit (either using HPF or automatically in a ccNUMA system).
Hardware architecture in which multiple processors operate independently but each has it own private memory. See shared memory.
Memory that is split up into segments, each of which may be directly accessed by only one node of a concurrent processor. Distributed memory and shared memory are two major architectures that require very different programming styles.
Distributed memory is a concept used in parallel computing. It means that in a multi-processor system each processor has its own memory. This requires that computional tasks have to be distributed on the different processors for processing.