On 12/10/2018 09:26, Lawrence D'Oliveiro wrote: > On Fri, 12 Oct 2018 09:12:25 +0300, Povilas Kanapickas wrote: > >> All of the above increase the complexity and size of the retrieval >> function. > > For what it’s worth, on modern cache-intensive architectures, you can > often get a net speedup by writing more complex code that does fewer > memory accesses.
I was wondering the same. Maybe the fact that the table can now fit into the L1 cache on most microarchitectures with some space to spare will make the code much faster than before :-) Only benchmarks will show. Regards, Povilas _______________________________________________ Freetype mailing list Freetype@nongnu.org https://lists.nongnu.org/mailman/listinfo/freetype
