Algorithmic foundations for a parallel vector access memory system
Proceedings of the twelfth annual ACM symposium on Parallel algorithms and architectures
Dynamic Access Ordering for Streamed Computations
IEEE Transactions on Computers
| Hi-index | 0.00 |
The performance of a vector processor accessing vectors is strongly dependent on the conflicts produced in the memory subsystem. The concurrent memory access of several vector streams causes inter-conflicts between the references of different vectors. In a complex memory system (several memory modules are mapped in every bus) the number of conflicts increases because the bus must be shared by the vector streams. This paper proposes a method that allows a concurrent access to several vector streams reducing the average memory access time in vector processors with complex memory systems.