CATREEN : Context-Aware Code Timing Estimation with Stacked Recurrent Networks

Abderaouf Amalou , Elisa Fromont (1, 2) , Isabelle Puaut (3)

1 IUF - Institut universitaire de France
2 LACODAM - Large Scale Collaborative Data Mining
3 PACAP - Pushing Architecture and Compilation for Application Performance

Automatic prediction of the execution time of programs for a given architecture is crucial, both for performance analysis in general and for compiler designers in particular. In this paper, we present CATREEN, a recurrent neural network able to predict the steady-state execution time of each basic block in a program. Contrarily to other models, CATREEN can take into account the execution context formed by the previously executed basic blocks which allows accounting for the processor micro-architecture without explicit modeling of micro-architectural elements (caches, pipelines, branch predictors, etc.). The evaluations conducted with synthetic programs and real ones (programs from Mibench and Polybench) show that CATREEN can provide accurate prediction for execution time with 11.4% and 16.5% error on average, respectively and that we got an improvement of 18% and 27.6% respectively when comparing our tool estimations to the state-of-the-art LSTM-based model.

Domaines: Informatique [cs]

Abderaouf Amalou, Elisa Fromont, Isabelle Puaut. CATREEN : Context-Aware Code Timing Estimation with Stacked Recurrent Networks. ICTAI 2022 - 34th IEEE International Conference on Tools with Artificial Intelligence, Oct 2022, Virtually, China. pp.1-6, ⟨10.1109/ICTAI56018.2022.00090⟩. ⟨hal-03890057v1⟩