A Many Threaded CUDA Interpreter for Genetic Programming

Langdon W. B.

13th European Conference on Genetic Programming, İstanbul, Türkiye, 7 - 09 Nisan 2010, cilt.6021, ss.146-158 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 6021
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.146-158
  • İstanbul Teknik Üniversitesi Adresli: Hayır

Özet

A Single Instruction Multiple Thread CUDA interpreter provides SIMD like parallel evaluation of the whole GP population of million reverse polish notation (RPN) expressions on graphics cards and nVidia Tesla. Using sub-machine code tree GP a sustain peak performance of 665 billion GP operations per second (10,000 speed up) and an average of 22 peta GP ops per day is reported for a single GPU card on a Boolean induction benchmark never attempted before, let alone solved.