Using FPGA devices to accelerate the evaluation phase of tree-based genetic programming: an extended analysis

Created by W.Langdon from gp-bibliography.bib Revision:1.8194

@Article{Crary:2025:GPEM,

• author = "Christopher Crary and Wesley Piard and Greg Stitt and Benjamin Hicks and Caleb Bean and Bogdan Burlacu and Wolfgang Banzhaf",
• title = "Using {FPGA} devices to accelerate the evaluation phase of tree-based genetic programming: an extended analysis",
• journal = "Genetic Programming and Evolvable Machines",
• year = "2025",
• volume = "26",
• pages = "Article no 8",
• note = "Online first",
• keywords = "genetic algorithms, genetic programming, Tree-based genetic programming, Field-programmable gate array, Domain-specific architecture, Hardware acceleration, FPGA, DEAP, Operon",
• ISSN = "1389-2576",
• DOI = "doi:10.1007/s10710-024-09505-2",
• size = "48 pages",
• abstract = "we establish the potential of accelerating the evaluation phase of tree-based genetic programming through contemporary field-programmable gate array (FPGA) technology. This exploration stems from the fact that FPGAs can sometimes leverage increased levels of both data and function parallelism, as well as superior power/energy efficiency, when compared to general-purpose CPU/GPU systems. we introduce a fixed-depth, tree-based architecture that can fully parallelize tree evaluation for type-consistent primitives that are unrolled and pipelined. We show that our accelerator on a 14nm FPGA achieves an average speedup of 43 times when compared to a recent open-source GPU solution, TensorGP, implemented on 8nm process-node technology, and an average speedup of 4902 times when compared to a popular baseline GP software tool, DEAP, running parallelised across all cores of a 2-socket, 28-core (56-thread), 14nm CPU server. Despite our single-FPGA accelerator being 2.4 times slower on average when compared to the recent state-of-the-art Operon tool executing on the same 2-processor, 28-core CPU system, we show that this single-FPGA system is 1.4 times better than Operon in terms of performance-per-watt. we also describe six future extensions that could provide at least a 64 to 192 times speedup over our current design. Therefore, our initial results provide considerable motivation for the continued exploration of FPGA-based GP systems. Overall, any success in significantly improving runtime and energy efficiency could potentially enable novel research efforts through faster and/or less costly GP runs, similar to how GPUs unlocked the power of deep learning during the past fifteen years.",

}

Genetic Programming entries for Christopher C Crary Wesley P Piard Greg Stitt Benjamin Hicks Caleb Bean Bogdan Burlacu Wolfgang Banzhaf

Citations