COLA-Gen: Active Learning Techniques for Automatic Code Generation of Benchmarks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

COLA-Gen: Active Learning Techniques for Automatic Code Generation of Benchmarks

(1, 2) , (1, 2) , (1, 2) , (1, 2)
1
2

Résumé

Benchmarking is crucial in code optimization. It is required to have a set of programs that we consider representative to validate optimization techniques or evaluate predictive performance models. However, there is a shortage of available benchmarks for code optimization, more pronounced when using machine learning techniques. The problem lies in the number of programs for testing because these techniques are sensitive to the quality and quantity of data used for training. Our work aims to address these limitations. We present a methodology to efficiently generate benchmarks for the code optimization domain. It includes an automatic code generator, an associated DSL handling, the high-level specification of the desired code, and a smart strategy for extending the benchmark as needed. The strategy is based on Active Learning techniques and helps to generate the most representative data for our benchmark. We observed that Machine Learning models trained on our benchmark produce better quality predictions and converge faster. The optimization based on the Active Learning method achieved up to 15% more speed-up than the passive learning method using the same amount of data.
Fichier non déposé

Dates et versions

hal-03907689 , version 1 (20-12-2022)

Identifiants

Citer

Maksim Berezov, Corinne Ancourt, Justyna Zawalska, Maryna Savchenko. COLA-Gen: Active Learning Techniques for Automatic Code Generation of Benchmarks. 13th Workshop on Parallel Programming and Run-Time Management Techniques for Many-Core Architectures and 11th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms (PARMA-DITAM 2022), Jun 2022, Budapest, Hungary. pp.1-14, ⟨10.4230/OASIcs.PARMA-DITAM.2022.3⟩. ⟨hal-03907689⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More