- author = "Scott R Lenser and Desney S Tan",
- title = "Genetic Algorithms for Synthesizing Data Value Predictors",
- howpublished = "CMU Computer Science 15740: Computer Architecture Final Project",
- year = "1999",
- month = "Fall",
- keywords = "genetic algorithms, genetic programming, data value prediction, instruction-level parallelism, speculative execution, pipeline branch prediction, GAlib, PVM, parallel GP, DEC Alpha",
-
URL = "
http://www.cs.cmu.edu/~slenser/ca_project",
-
URL = "
http://www.cs.cmu.edu/~slenser/ca_project/lensertan.pdf",
- size = "8 pages",
- abstract = "As processor architectures increase their reliance on speculative parallel execution of sequential programs, the importance of not only what instructions to execute, but also how to resolve data dependence has increased. Data dependences present a major hurdle to the amount of instruction-level parallelism that can be exploited. Datavalue prediction is a technique that by passes these dependences by speculating on the outcomes of producer instructions, allowing consumer instructions to execute in parallel. The goal of our project is to explore the application of genetic algorithms (GAs) to the design of value prediction hardware.",
-
notes = "two tree GP (64 bit prediction: 1 bit use or not
prediction)
BLUT and LUT lookup tables.
Crossover of graphs.
SPEC95 (CINT95) benchmark, Digital western lab's ATOM.
Cited by \cite{krauss:2020:EuroGP}",
