Performance enhancing factors for manycore architectures: State-of-the-art

Abstract

Manycore architecture system includes more number of processing elements to improve the performance while sustaining power considerations. Accelerating heterogeneous manycore computing elements involves huge amount of memory copy, computation and thread management. Applications of manycore architectures range from desktop computer to warehouse-scale computer. In this paper, the state-of-the-art trends and techniques of few manycore architectures that address various memory and performance issues are presented. Different parallel programming models that address issues on thread management, accessing virtual shared memory, dynamic load balancing, memory hierarchy and inter-language compatibility are discussed among some of the manycore architectures like NVIDIA's Graphics Processing Units (GPU), Intel's Many Integrated Core (MIC) and a joint venture of AMD's Accelerated Processing Units (APU).