2008
DOI: 10.1007/978-3-540-78671-9_7
|View full text |Cite
|
Sign up to set email alerts
|

A SIMD Interpreter for Genetic Programming on GPU Graphics Cards

Abstract: Abstract. Mackey-Glass chaotic time series prediction and nuclear protein classification show the feasibility of evaluating genetic programming populations directly on parallel consumer gaming graphics processing units. Using a Linux KDE computer equipped with an nVidia GeForce 8800 GTX graphics processing unit card the C++ SPMD interpretter evolves programs at Giga GP operations per second (895 million GPops). We use the RapidMind general processing on GPU (GPGPU) framework to evaluate an entire population of… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
79
0
1

Year Published

2009
2009
2017
2017

Publication Types

Select...
6
2

Relationship

1
7

Authors

Journals

citations
Cited by 105 publications
(82 citation statements)
references
References 14 publications
2
79
0
1
Order By: Relevance
“…The efficiency of rule interpreters is often reported by means of the number of primitives interpreted by the system per second, similarly to Genetic Programming interpreters, which determine the number of Genetic Programming operations per second (GPops/s) [31,53,54].…”
Section: Rule Interpreter Performancementioning
confidence: 99%
See 1 more Smart Citation
“…The efficiency of rule interpreters is often reported by means of the number of primitives interpreted by the system per second, similarly to Genetic Programming interpreters, which determine the number of Genetic Programming operations per second (GPops/s) [31,53,54].…”
Section: Rule Interpreter Performancementioning
confidence: 99%
“…Rule specification can be formally defined by means of a context-free grammar [52] as the shown in Figure 1. [53,54]. Traditional stack-based interpreters perform push and pop operations on a stack, involving the operator and operands found in the rule.…”
Section: Pittsburgh Individual Encodingmentioning
confidence: 99%
“…The efficiency of rules interpreters is often reported using the number of primitives interpreted by the system per second, similarly to Genetic Programming (GP) interpreters, which determine the number of GP operations per second (GPops/s) [3,[30][31][32]. GP interpreters evaluate expression trees, which represent solutions to perform a user-defined task.…”
Section: Rules Interpreter Performancementioning
confidence: 99%
“…Our GPU SIMD interpreter approach [49] took the opposite approach. It avoids the (surprisingly high) cost of compiling GP individuals by using an interpreter and secondly it processes the whole population in parallel.…”
Section: Interpreted Parallel Populationsmentioning
confidence: 99%
“…There are good reasons for using CUDA. For example, in [49] we used an early version of RapidMind (version 2), Robilliard et al [59] reimplemented it using an up to date version of CUDA and reported an (up to) 92% speed increase.…”
Section: Future Of Genetic Programming On Gpumentioning
confidence: 99%