A Survey of CPU-GPU Heterogeneous Computing Techniques

@article{Mittal2015ASO,
  title={A Survey of CPU-GPU Heterogeneous Computing Techniques},
  author={Sparsh Mittal and J. Vetter},
  journal={ACM Comput. Surv.},
  year={2015},
  volume={47},
  pages={69:1-69:35}
}
  • Sparsh Mittal, J. Vetter
  • Published 2015
  • Computer Science
  • ACM Comput. Surv.
  • As both CPUs and GPUs become employed in a wide range of applications, it has been acknowledged that both of these Processing Units (PUs) have their unique features and strengths and hence, CPU-GPU collaboration is inevitable to achieve high-performance computing. This has motivated a significant amount of research on heterogeneous computing techniques, along with the design of CPU-GPU fused chips and petascale heterogeneous supercomputers. In this article, we survey Heterogeneous Computing… CONTINUE READING
    A Survey of Techniques for Architecting and Managing Asymmetric Multicore Processors
    • 52
    Scheduling challenges and opportunities in integrated CPU+GPU processors
    • 10
    • PDF
    A Survey of Techniques for Architecting and Managing GPU Register File
    • 26
    DRAGON: Breaking GPU Memory Capacity Limits with Direct NVM Access
    • 16
    • PDF
    Power-aware characterization and mapping of workloads on CPU-GPU processors
    • 7
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 21 REFERENCES
    Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU
    • 798
    • Highly Influential
    • PDF
    Where is the data? Why you cannot debate CPU vs. GPU performance without the answer
    • 275
    • Highly Influential
    • PDF
    StarPU: A Unified Platform for Task Scheduling on Heterogeneous Multicore Architectures
    • 1,002
    • Highly Influential
    • PDF
    Porting irregular reductions on heterogeneous CPU-GPU configurations
    • 26
    • Highly Influential
    QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators
    • 111
    • Highly Influential
    • PDF
    A dynamic self-scheduling scheme for heterogeneous multiprocessor architectures
    • 67
    • Highly Influential
    • PDF
    Heterogeneous Systems for Energy Efficient Scientific Computing
    • 21
    • Highly Influential
    Scaling Hierarchical N-body Simulations on GPU Clusters
    • 88
    • Highly Influential
    • PDF
    Enabling Multiple Accelerator Acceleration for Java/OpenMP
    • 7
    • Highly Influential
    • PDF
    Enabling task-level scheduling on heterogeneous platforms
    • 38
    • Highly Influential
    • PDF