Using LLVM-based JIT compilation in genetic programming

Gregor, Michal; Spalek, Juraj

doi:10.1109/elektro.2016.7512108

Search citation statements

Order By: Relevance

Paper Sections

Select...

Faster Fitness1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2020

2023

Publication Types

Select...

Article2

Other1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…because there are many test cases, it can be beneficial not to interpret the code but to compile it and run the compiled binary code (e.g. Harding [22], Gregor and Spalek [20]). However running a traditional compiler is expensive and Fukunaga et al [15] and Vasicek and Slany [76] have advocated generating machine code inside the GP system and executing that.…”

Section: Faster Fitnessmentioning

confidence: 99%

A Trillion Genetic Programming Instructions per Second

Langdon¹

2022

Preprint

View full text Add to dashboard Cite

We summarise how a 3.0GHz 16 core AVX512 computer can interpret the equivalent of up to on average 1 103 370 000 000 GPop/s. Citations to existing publications are given. Implementation stress is placed on both parallel computing, bandwidth limits and avoiding repeated calculation. Information theory suggests in digital computing, failed disruption propagation gives huge speed ups as FDP and incremental evaluation can be used to reduce fitness evaluation time in phenotypically converged populations. Conversely FDP may be responsible for evolution stagnation. So the wider Evolutionary Computing, Artificial Life, Unconventional Computing and Software Engineering community may need to avoid deep nesting.

show abstract

Section: Faster Fitnessmentioning

confidence: 99%