Mercurial > hg > graal-jvmci-8
diff src/cpu/sparc/vm/c2_globals_sparc.hpp @ 1365:6476042f815c
6940701: Don't align loops in stubs for Niagara sparc
Summary: Don't align loops in stubs for Niagara sparc since NOPs are expensive.
Reviewed-by: twisti, never
author | kvn |
---|---|
date | Wed, 07 Apr 2010 09:37:47 -0700 |
parents | 473cce303f13 |
children | c18cbe5936b8 |
line wrap: on
line diff
--- a/src/cpu/sparc/vm/c2_globals_sparc.hpp Tue Apr 06 15:18:10 2010 -0700 +++ b/src/cpu/sparc/vm/c2_globals_sparc.hpp Wed Apr 07 09:37:47 2010 -0700 @@ -60,9 +60,6 @@ define_pd_global(intx, INTPRESSURE, 48); // large register set define_pd_global(intx, InteriorEntryAlignment, 16); // = CodeEntryAlignment define_pd_global(intx, NewSizeThreadIncrease, ScaleForWordSize(4*K)); -// The default setting 16/16 seems to work best. -// (For _228_jack 16/16 is 2% better than 4/4, 16/4, 32/32, 32/16, or 16/32.) -define_pd_global(intx, OptoLoopAlignment, 16); // = 4*wordSize define_pd_global(intx, RegisterCostAreaRatio, 12000); define_pd_global(bool, UseTLAB, true); define_pd_global(bool, ResizeTLAB, true);