We investigate an automatic method for classifying which regions of sequential programs could be parallelized, using dynamic features of the code collected ...

Abstract—We investigate an automatic method for classifying which regions of sequential programs could be parallelized, using dynamic features of the code ...

We investigate an automatic method for classifying which regions of sequential programs could be parallelized, using dynamic features of the code collected ...

Predicting Parallelization of Sequential Programs Using Supervised Learning. Fried, Daniel; Li, Zhen; Jannesari Ladani, Ali; Wolf, Felix Gerd Eugen.

We propose a data-driven method that can be applied to parallelism detection. The proposed framework combines contextual flow graphs and a deep graph ...

... Predicting Parallelization of Sequential Programs Using Supervised Learning. In Proc. of the 12th IEEE International Conference on Machine Learning and ...

This paper proposes a parallel architecture for Ensemble Machine Learning Models, harnessing multicore CPUs to expedite performance.

... {Predicting Parallelization of Sequential Programs Using Supervised Learning}, booktitle = {Proc. of the 12th IEEE International Conference on Machine Learning ...

Our approach achieves comparable state-of-the-art performance on parallel region classification with an accuracy up to 92.6% when evaluated with popular ...

In this paper, we present a dynamic approach for automatically identifying potential parallelism in sequential programs. Our method is based on the notion of ...