Puisque l'on parlait d'utiliser le GPU pour accélérer certaines
parties du compilateur. Plus spécifiquement, la réalisation qu'il
existe un parallélisme exploitable dans les analyses de flot a été
exploité récemment:
We describe, implement and benchmark EigenCFA, an algorithm for
accelerating higher-order control-flow analysis (specifically, 0CFA)
with a GPU. Ultimately, our program transformations, reductions
and optimizations achieve a factor of 72 speedup over an optimized
CPU implementation.
[...]
Ultimately, sparse-matrix data structures and operations
turned out to be the critical accelerants. Because control-flow
graphs are sparse in practice (up to 96% empty), our control-flow
matrices are also sparse,
giving the sparse matrix operations an overwhelming space and
speed advantage.
We also achieved speedups by carefully permitting data
races.The monotonicity of 0CFA makes it sound to perform analysis
operations in parallel, possibly using stale or even
partially-updated data.
POPL 2011 http://matt.might.net/papers/prabhu2011eigencfa.pdf