Multiobjective GPU design space exploration optimization

Jooya, Ali; Dimopoulos, N.J.; Baniasadi, Amirali

doi:10.1016/j.micpro.2019.06.001

Cited by 5 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among application-specific performance predictions, Stargazer [96] uses a stepwise regression modeling, which can recognize the most important parameters so as to achieve high prediction accuracy even with sparse and random samples, i.e., less than 3.8% average prediction error with 300 sampled design points in a design space with nearly 1 million possibilities. Jooya et al [105] train multiple NN predictors and select the subset with the best generalization abilities to form an ensemble; with these performance/power predictions they further perform the Pareto-optimal multi-objective optimization. Among general predictions for performance of interest in GPUs, Wu et al [240] model scaling behaviors of general-purpose GPUs (GPGPUs).…”

Section: Graphics Processing Unit (Gpu)mentioning

confidence: 99%

A Survey of Machine Learning for Computer Architecture and Systems

Wu,

Xie

2021

Preprint

View full text Add to dashboard Cite

It has been a long time that computer architecture and systems are optimized to enable efficient execution of machine learning (ML) algorithms or models. Now, it is time to reconsider the relationship between ML and systems, and let ML transform the way that computer architecture and systems are designed. This embraces a twofold meaning: the improvement of designers' productivity, and the completion of the virtuous cycle. In this paper, we present a comprehensive review of work that applies ML for system design, which can be grouped into two major categories, ML-based modelling that involves predictions of performance metrics or some other criteria of interest, and ML-based design methodology that directly leverages ML as the design tool. For ML-based modelling, we discuss existing studies based on their target level of system, ranging from the circuit level to the architecture/system level. For ML-based design methodology, we follow a bottom-up path to review current work, with a scope of (micro-)architecture design (memory, branch prediction, NoC), coordination between architecture/system and workload (resource allocation and management, data center management, and security), compiler, and design automation. We further provide a future vision of opportunities and potential directions, and envision that applying ML for computer architecture and systems would thrive in the community. CCS Concepts: • Computing methodologies → Machine learning; • Computer systems organization → Architectures; • General and reference → Surveys and overviews.

show abstract

Section: Graphics Processing Unit (Gpu)mentioning

confidence: 99%

A Survey of Machine Learning for Computer Architecture and Systems

Wu,

Xie

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Design Space Exploration: GPU design space exploration has proven to be a particularly favorable application for ML due to a highly irregular design space; some kernels exhibit relatively linear scaling while others exhibit very complex relationships between configuration parameters, power, and performance [15], [16], [17]. Jia et al [15] proposed Stargazer, a regression-based framework based on natural cubic splines.…”

Section: Gpusmentioning

confidence: 99%

“…This approach, in contrast to Jia et al [15], therefore requires just a few samples for new applications. Jooya et al [17], similar to Jia et al [15], considered a per-application performance/power prediction model, but additionally proposed a scheme to predict per-application Pareto fronts. Many ANN-based predictors were trained and the most accurate subset was used as an ensemble for prediction.…”

Section: Gpusmentioning

confidence: 99%

“…Parallel threads are also utilized to scale design space exploration with increasing computational resources. System-level design space exploration has favored more standard supervised learning approaches [17], [64], [67]. Specific model choices vary, with linear [17], [64] and non-linear [67] regression models, as well as random forests and neural networks [64] finding implementation.…”

Section: Offline ML Applicationsmentioning

confidence: 99%

“…System-level design space exploration has favored more standard supervised learning approaches [17], [64], [67]. Specific model choices vary, with linear [17], [64] and non-linear [67] regression models, as well as random forests and neural networks [64] finding implementation. As in online ML applications, discussed in Section 4.1, some tasks are naturally limited to supervised learning methods.…”

Section: Offline ML Applicationsmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Machine Learning Applied to Computer Architecture Design

Penney¹,

Chen

2019

Preprint

View full text Add to dashboard Cite

Machine learning has enabled significant benefits in diverse fields, but, with a few exceptions, has had limited impact on computer architecture. Recent work, however, has explored broader applicability for design, optimization, and simulation. Notably, machine learning based strategies often surpass prior state-of-the-art analytical, heuristic, and human-expert approaches. This paper reviews machine learning applied system-wide to simulation and run-time optimization, and in many individual components, including memory systems, branch predictors, networks-on-chip, and GPUs. The paper further analyzes current practice to highlight useful design strategies and identify areas for future work, based on optimized implementation strategies, opportune extensions to existing work, and ambitious long term possibilities. Taken together, these strategies and techniques present a promising future for increasingly automated architectural design.

show abstract