Continuous learning of compiler heuristics

Michele Tartara, Stefano Crespi Reghizzi

ACM Transactions on Architecture and Code Optimization 2013 article cited by 37

Source Open-access PDF More in Software & Coding

importance 4/10 ai assisted Parallel Computing and Optimization Techniques compiler software stage: research

Problem

Iterative compilation with machine learning finds optimal code optimizations but needs extremely long compilation and training times (days or weeks).

Why it matters

Faster optimized executables without lengthy compilation saves compute time and removes expert-defined heuristics.

What the AI did

A 'long-term learning' algorithm that acquires knowledge at every compilation and continuously learns compiler heuristics without an initial training phase or manual expert definitions.

Results

Reduced compilation times versus iterative compilation and removed the initial training phase; no numeric results stated

Impact

Qualitative improvement over iterative compilation claimed; no external adoption stated in evidence.

Record

Venue	ACM Transactions on Architecture and Code Optimization
Published	2013
Work type	article
Authors	Michele Tartara, Stefano Crespi Reghizzi
Citations	37 (OpenAlex, at import time)
References	32
Model or method	long-term learning algorithm (continuous machine learning)
Organization	not stated in source
Primary source	https://doi.org/10.1145/2400682.2400705
Open access	bronze
Keywords	compiler heuristics, continuous learning, iterative compilation, machine learning, code optimization

Importance rating

4 / 10

real but narrower advance

Compiler optimization affects software performance broadly, but abstract only claims reduced compilation times versus iterative compilation; no scale of users or industry impact stated.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Software & Coding

#	Paper	Year	Citations	Importance
1	ImageNet classification with deep convolutional neural networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton	2017	106,345	8
2	Deep Residual Learning for Image Recognition Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun	2016	221,134	8
3	Faster sorting algorithms discovered using deep reinforcement learning Daniel J. Mankowitz, Andrea Michi, Anton Zhernov, Marco Gelmi, Marco S...	2023	175	8
4	A deep learning‐based approach for software vulnerability detection using code metrics Fazli Subhan, Xiaoxue Wu, Lili Bo, Xiaobing Sun, Muhammad Rahman	2022	42	7
5	Deep Learning-Based Attack Detection and Classification in Android Devices Alfonso Gómez, Antonio Muñoz	2023	41	7