Generative and multi-phase learning for computer systems optimization

Ding, Yi; Mishra, Nikita; Hoffmann, Henry

doi:10.1145/3307650.3326633

Cited by 32 publications

(29 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Resource allocation. Allocating system resources is a very challenging task given the latency and energy constraints of mobile devices [24,56]. Our choice of employing only stock Android without root access means we can only control which cores execute the workload on the worker, with no access, for instance, to low-level advanced tuning.…”

Section: Methodsmentioning

confidence: 99%

FLeet

Damaskinos

Guerraoui

Kermarrec

et al. 2020

Proceedings of the 21st International Middleware Conference

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

FLeet

Damaskinos

Guerraoui

Kermarrec

et al. 2020

Proceedings of the 21st International Middleware Conference

View full text Add to dashboard Cite

“…The collected information is then used to generate the required models. We select and run 9 different applications from Rodinia benchmark suite [5], which provides workloads with a wide range of behavior and is suitable for embedded processor [7], [8], [17], [18], [25]. We execute each application in the aforementioned six configurations on the Odroid XU3 heterogeneous platform [14] to collect power consumption, instructions-per-second, and execution time.…”

Section: Data Collectionmentioning

confidence: 99%

Concurrent Application Bias Scheduling for Energy Efficiency of Heterogeneous Multi-Core Platforms

Shamsa

Kanduri

Liljeberg

et al. 2022

IEEE Trans. Comput.

View full text Add to dashboard Cite

Minimizing energy consumption of concurrent applications on heterogeneous multi-core platforms is challenging given the diversity in energy-performance profiles of both the applications and hardware. Adaptive learning techniques made the exhaustive Pareto-optimal space exploration practically feasible to identify an energy efficient configuration. Existing approaches consider a single application's characteristic for optimizing energy consumption. However, an optimal configuration for a given application in isolation may not be optimal when other applications are run concurrently. Approaches that consider concurrent application scenarios overlook the weight of total energy consumption per application, restricting them from prioritizing among applications. We address this limitation by considering the mutual effect of concurrent applications on system wide energy consumption to adapt resource configuration at run-time. We characterize each application's power-performance profile as a weighted bias through off-line profiling. We infer this model combined with an on-line predictive strategy to make resource allocation decisions for minimizing energy consumption while honoring performance requirements. The proposed strategy is implemented as a user-space process and evaluated on a heterogeneous hardware platform of Odroid XU3 over the Rodinia benchmark suite. Experimental results show up to 61% of energy saving compared to the standard baseline of Linux governors and up to 27% of energy gain compared to state-of-the-art adaptive learning-based resource management techniques.

show abstract

“…[33] introduced a multi-layer NN based predictive routing algorithm which uses network state and congestion information to estimate routing costs and perform low-latency routing in NoC. A few other related works proposed for the design and optimization of NoC and/or multi/many-core systems using machine learning are: [5], [8], [11], [12], [14]- [16], [21], [24]- [27], [34], [36]- [38], [46]- [49], [52].…”

Section: Background and Prior Workmentioning

confidence: 99%

Reinforcement Learning Enabled Routing for High-Performance Networks-on-Chip

Reza

Le²

2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

Network-on-chip (NoC) has been the standard fabric for multi-core architectures. With the increase in cores in the multi-core architectures, the probability of congestion increases because of longer path among sources and destinations in the NoC and because of the presence of multiple applications in a chip. Congestion hampers system performance because of the delay in packet delivery, which in turn results in reduced effective utilization of resources and reduced throughout. Higher congestion also results in higher energy consumption in NoC as packets spend more time in the network. Reactive detection and/or a single fixed routing algorithm are not effective to prevent congestion from happening for different traffic patterns in NoC. Therefore, we propose reinforcement learning based proactive routing technique that selects the best routing algorithm from multiple available routing algorithms using NoC utilization and congestion information to improve communication performance. Simulation results demonstrate latency performance improvement while providing robust NoC performance for different NoC states and traffic demands.

show abstract

Generative and multi-phase learning for computer systems optimization

Cited by 32 publications

References 52 publications

FLeet

FLeet

Concurrent Application Bias Scheduling for Energy Efficiency of Heterogeneous Multi-Core Platforms

Reinforcement Learning Enabled Routing for High-Performance Networks-on-Chip

Contact Info

Product

Resources

About