Accelerating floating-point fitness functions in evolutionary algorithms: a FPGA-CPU-GPU performance comparison.
Juan Antonio Gómez PulidoMiguel A. Vega-RodríguezJuan Manuel Sánchez-PérezSilvio Priem-MendesVitor CarreiraPublished in: Genet. Program. Evolvable Mach. (2011)
Keyphrases
- evolutionary algorithm
- floating point
- fitness function
- graphics processing units
- memory bandwidth
- evolutionary computation
- genetic programming
- multi objective
- genetic algorithm ga
- fixed point
- gpu implementation
- optimization problems
- simulated annealing
- genetic algorithm
- differential evolution
- multi objective optimization
- genetic operators
- graphics processors
- crossover operator
- field programmable gate array
- parallel computation
- sparse matrices
- general purpose
- instruction set
- mutation operator
- parallel programming
- evolutionary search
- evolutionary strategy
- differential evolution algorithm
- floating point arithmetic
- evolutionary process
- initial population
- constrained optimization problems
- fitness evaluation
- particle swarm optimization
- search space
- neural network
- low cost