Tomorrow I will push the latest changes to P3 to github. See the news section on the P3 github wiki for changes.
The following draft paper (under submission) describes the design of the P3 combinator parsing library.
Tom Ridge. Simple, efficient, sound and complete combinator parsing for all context-free grammars, using an oracle (unpublished draft). ridge14p3_design.pdf. Old slides are here (best viewable in firefox, due to latexmathml).
The draft includes various performance measurements, particularly against the Haskell Happy parser generator. For reference, the testing infrastructure was as follows:
model: 58 model name: Intel(R) Core(TM) i5-3470 CPU @ 3.20GHz stepping: 9 microcode: 0x12 cpu MHz: 1600.000 cache size: 6144 KB