Faster Genetic Programming GPquick via multicore and Advanced Vector Extensions

02/25/2019
by   W. B. Langdon, et al.
0

We evolve floating point Sextic polynomial populations of genetic programming binary trees for up to a million generations. Programs with almost four hundred million instructions are created by crossover. To support unbounded Long-Term Evolution Experiment LTEE GP we use both SIMD parallel AVX 512 bit instructions and 48 threads to yield performance of up to 139 billion GP operations per second, 139 giga GPops, on a single Intel Xeon Gold 6126 2.60GHz server.

READ FULL TEXT

page 14

page 17

research
03/24/2017

Long-Term Evolution of Genetic Programming Populations

We evolve binary mux-6 trees for up to 100000 generations evolving some ...
research
01/13/2020

Fast Generation of Big Random Binary Trees

random_tree() is a linear time and space C++ implementation able to crea...
research
12/01/2021

Evolving Open Complexity

Information theoretic analysis of large evolved programs produced by run...
research
06/09/2022

Functional Code Building Genetic Programming

General program synthesis has become an important application area for g...
research
04/04/2022

Failed Disruption Propagation in Integer Genetic Programming

We inject a random value into the evaluation of highly evolved deep inte...
research
09/19/2018

Exploiting Tournament Selection for Efficient Parallel Genetic Programming

Genetic Programming (GP) is a computationally intensive technique which ...
research
06/09/2018

A Preliminary Exploration of Floating Point Grammatical Evolution

Current GP frameworks are highly effective on a range of real and simula...

Please sign up or login with your details

Forgot password? Click here to reset