vgvassilev wrote: > > Can you summarize the before and after file stat counts in the description > > of this PR? > > Done so in the "Filesystem access in unchanged" section. > > > Also, 40% is the max empirical finding, however, what's our theoretical > > expectation? Nominally one would think that if a pcm is dominated by copied > > content the reuse will yield much higher numbers... That is, is there any > > performance gains still left on the table beyond what we see currently? > > Clarified this in the "How high can this go section". > > @vgvassilev
Thank you. I am surprised that the peak memory went up. Do we understand why and can we minimize it? https://github.com/llvm/llvm-project/pull/209795 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
