Utilizing Concurrency: A New Theory for Memory Wall
نویسندگان
چکیده
In addition to locality, data access concurrency has emerged as a pillar factor of memory performance. In this research, we introduce a concurrency-aware solution, the memory Sluice Gate Theory, for solving the outstanding memory wall problem. Sluice gates are designed to control data transfer at each memory layer dynamically, and a global control algorithm, named layered performance matching, is developed to match the data transfer request/supply at each memory layer thus matching the overall performance between the CPU and memory system. Formal theoretical analyses are given to show, with sufficient data access concurrency and hardware support, the memory wall impact can be reduced to the minimum. Experimental testing is conducted which confirm the theoretical findings.
منابع مشابه
Sequential Consistency in Distributed Systems
Recently, distributed shared memory (DSM) systems have received much attention because such an abstraction simpliies programming. It has been shown that many practical applications using DSMs require competing operations. We have aimed at unifying theory and implementations of protocols for sequential consistency, which provides competing operations. By adopting concepts from concurrency contro...
متن کاملChaotic Genetic Algorithm based on Explicit Memory with a new Strategy for Updating and Retrieval of Memory in Dynamic Environments
Many of the problems considered in optimization and learning assume that solutions exist in a dynamic. Hence, algorithms are required that dynamically adapt with the problem’s conditions and search new conditions. Mostly, utilization of information from the past allows to quickly adapting changes after. This is the idea underlining the use of memory in this field, what involves key design issue...
متن کاملOptimization of majority protocol for controlling transactions concurrency in distributed databases by multi-agent systems
In this paper, we propose a new concurrency control algorithm based on multi-agent systems which is an extension of majority protocol. Then, we suggest a clustering approach to get better results in reliability, decreasing message passing and algorithm’s runtime. Here, we consider n different transactions working on non-conflict data items. Considering execution efficiency of some different...
متن کاملSequential Consistency in Distributed Systems : Theory and Implementation
Recently, distributed shared memory (DSM) systems have received much attention because such an abstraction simpliies programming. It has been shown that many practical applications using DSMs require competing operations. We have aimed at unifying theory and implementations of protocols for sequential consistency , which provides competing operations. The results are useful not only to clarify ...
متن کاملC-Bound: A Capacity and Concurrency Driven Analytical Model for Many-core Design
In this paper, we propose C-Bound, a data-driven analytical model, that incorporates both memory capacity and data access concurrency factors to optimize many-core design. C-Bound is characterized by combining the newly proposed latency model, concurrent average memory access time (CAMAT), with the well-known memory-bounded speedup model (Sun-Ni’s law) to facilitate computing tasks. Compared to...
متن کامل