Performance evaluation of throughput computing workloads using multi-core processors and graphics processors

14th International Conference on Science, Engineering and Technology

自然科学;工业技术

Dave, Gaurav P^1 ; Sureshkumar, N.^1 ; Blessy Trencia Lincy, S.S.^1

School of Computer Engineering, VIT University, Vellore

632014, India^1

关键词: Data-level parallelism;    Multi-core processor;    Multicore architectures;    Performance evaluations;    Performance improvements;    Processing activity;    Shared memory programming;    Throughput computing;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/263/4/042101/pdf
DOI  :  10.1088/1757-899X/263/4/042101

来源: IOP

【 摘 要 】

Current trend in processor manufacturing focuses on multi-core architectures rather than increasing the clock speed for performance improvement. Graphic processors have become as commodity hardware for providing fast co-processing in computer systems. Developments in IoT, social networking web applications, big data created huge demand for data processing activities and such kind of throughput intensive applications inherently contains data level parallelism which is more suited for SIMD architecture based GPU. This paper reviews the architectural aspects of multi/many core processors and graphics processors. Different case studies are taken to compare performance of throughput computing applications using shared memory programming in OpenMP and CUDA API based programming.