Dopia
Authors:
Open Access
- 28 March 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 32-45
Abstract
Recent desktop and mobile processors often integrate CPU and GPU onto the same die. The limited memory bandwidth of these integrated architectures can negatively affect the performance of data-parallel workloads when all computational resources are active. The combination of active CPU and GPU cores achieving the maximum performance depends on a workload's characteristics, making manual tuning a time-consuming task. Dopia is a fully automated framework that improves the performance of data-parallel workloads by adjusting the Degree Of Parallelism on Integrated Architectures. Dopia transparently analyzes and rewrites OpenCL kernels before executing them with the number of CPU and GPU cores expected to yield the best performance. Evaluated on AMD and Intel integrated processors, Dopia achieves 84% of the maximum performance attainable by an oracle.Keywords
Funding Information
- National Research Foundation of Korea (21A20151113068,2015K1A3A1A14021288)
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (IZKSZ2_162084)
This publication has 29 references indexed in Scilit:
- Understanding Co-Running Behaviors on Integrated CPU/GPU ArchitecturesIEEE Transactions on Parallel and Distributed Systems, 2016
- Predicting the memory bandwidth and optimal core allocations for multi-threaded applications on large-scale NUMA machines2016
- Workload Partitioning for Accelerating Applications on Heterogeneous PlatformsIEEE Transactions on Parallel and Distributed Systems, 2015
- SKMDACM Transactions on Computer Systems, 2015
- A Survey of CPU-GPU Heterogeneous Computing TechniquesACM Computing Surveys, 2015
- Celebrating diversity: a mixture of experts approach for runtime mapping in dynamic environments2015
- Adaptive heterogeneous scheduling for integrated GPUs2014
- Applying AMD's Kaveri APU for heterogeneous computing2014
- OWL2013
- Reprint of: The anatomy of a large-scale hypertextual web search engineComputer Networks, 2012