On Sunday 17 July 2005 19:48, Daniel Berlin wrote: > On Sun, 2005-07-17 at 18:05 +0200, Steven Bosscher wrote: > > Hi, > > > > There are some huge compile time regressions between 16/7 and 17/7, most > > likely due to the IPA work from Kenny and Dan. These are the build times > > in seconds, taken from Diego Novillo's nightly SPEC tester box: > > As i expected, the sixtrack slowdown is entirely in global-alloc, in > daten.f > > with -fno-tree-promote-statics > global alloc : 0.23 ( 4%) usr 0.00 ( 0%) sys 0.24 ( 3%) > wall 448 kB ( 3%) ggc > > without: > > global alloc : 375.96 (83%) usr 5.00 (62%) sys 453.83 (82%) > wall 10714 kB ( 5%) ggc > > > Cute, no? > > It just has a lot more variables to deal with now that they aren't > statics that live in memory (a lot of things now get SRA'd that didn't > before, etc).
Sounds like something we have to investigate anyway. Can you see how many pseudo-registers it has with and without -ftree-promote-statics, and maybe squeeze an oprofile out of it? Gr. Steven
