Lines Matching refs:on

2 Notes on performance
13 - Julian made the tree builder linear.  Saved 2--13% on a range of programs.
16   Saved 1--3% on a few programs.
19   Also, on x86, amd64, ppc32 and ppc64, --profile-flags style profiling was
28   in perf/heap on a 3GHz Prescott P4.
30   end.  Saved 7% on perf/heap with --num-callers=50, and about 1% on
33   gives about 40% speedup on artificial programs which just do
34   realloc() and nothing else, and about a 3-4% speedup on starting
38 - Nick converted to compress V bits, initial version saved 0--5% on most
39   cases, with a 30% improvement on one case (tsim_arch) which calls
42   and 22% on tsim_arch.