vortex peak performance regression

[Jan Hubicka]

Zoltan,
It looks like your patch:
+ 2001-11-30  Zoltan Hidvegi <hzoli@hzoli.2y.net>
+
+ 	* unroll.c (unroll_loop): Correct special exit cases.
+
causes regression in the spec2000 tester - most importantly the vortex
benchmark (- see www.suse.de/~aj/SPEC

It is not obvious for me why, but can you please double check
whether the regression is unavoidable.

The patches from same testing that does not look like real cause are:
+ 2001-11-30  Stephane Carrez  <Stephane.Carrez@sun.com>
+
+ 	* config/sparc/sparc.c (DF_MODES_NO_S): Fix pr/3623, define to
+ 	accept DFmode and DImode only.
+
+ 2001-11-30  Aldy Hernandez  <aldyh@redhat.com>
+
+ 	* config/rs6000/rs6000.h (STARTING_FRAME_OFFSET): Adjust for altivec.
+         (STACK_DYNAMIC_OFFSET): Same.
+
+ 2001-11-30  Richard Henderson  <rth@redhat.com>
+
+ 	* c-decl.c (duplicate_decls): Copy DECL_SAVED_TREE.
+
+ 2001-11-30  Aldy Hernandez  <aldyh@redhat.com>
+
+         * config/rs6000/rs6000.h (CALL_REALLY_USED_REGISTERS): New.
+         (CONDITIONAL_REGISTER_USAGE): Set call_really_used_registers to
+         the values in call_used_registers.
+
+ Fri Nov 30 12:48:26 2001  Jeffrey A Law  (law@cygnus.com)
+
+ 	* gthr-dce.h: If _DCE_THREADS is not defined, then just include
+ 	gthr-single.


Honza