Design and implementation of the fusion simulator based on multi-shader GPU

Authors:
Jae-Hoon An;Younghwan Kim;Kiman Jeon
Affiliations:
Soongsil University, Seoul, South Korea;Korea Electronic Technology Institute Gyeonggi, South Korea;Korea Electronic Technology Institute Gyeonggi, South Korea
Venue:
Proceedings of the 2013 Research in Adaptive and Convergent Systems
Year:
2013

Citing 4
Cited 0

CPU-assisted GPGPU on fused CPU-GPU architectures

HPCA '12 Proceedings of the 2012 IEEE 18th International Symposium on High-Performance Computer Architecture
Dynamically managed data for CPU-GPU architectures

Proceedings of the Tenth International Symposium on Code Generation and Optimization
Fast and efficient automatic memory management for GPUs using compiler-assisted runtime coherence scheme

Proceedings of the 21st international conference on Parallel architectures and compilation techniques
Workload and power budget partitioning for single-chip heterogeneous processors

Proceedings of the 21st international conference on Parallel architectures and compilation techniques

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an intelligent computing architecture that enables CPUs and GPUs to works by seamlessly moving the right tasks to the best suited for operation. Also, simulation is one of the most important verification tools used by computer systems to evaluate their architecture. In this reason, we proposed fusion processor simulator that support the CPUs and the GPUs are combined on the same level. Proposed fusion processor simulator mainly consists of a CPU simulator and a GPU simulator with shared L2 cache and off-chip memory.