On Sun, 22 Jun 2008, Jack Howarth wrote: > Richard, > There is a regression in the induct polyhedron benchmark execution > when gfortran compiled with -ffast-math -O3 introduced with gcc 4.3 > that isn't present in gcc 4.2.4. > > http://gcc.gnu.org/bugzilla/show_bug.cgi?id=36599 > > According to the SuSe polyhedron benchmark servers, the bottleneck > in the induct benchmark was eliminated between 2008-04-27 and > 2008-04-28 in gcc trunk. My guess is that your changes... > > r134730 | rguenth | 2008-04-27 12:27:08 -0400 (Sun, 27 Apr 2008) | 42 lines > > 2008-04-27 Richard Guenther <[EMAIL PROTECTED]> > > PR tree-optimization/18754 > PR tree-optimization/34223 > * tree-pass.h (pass_complete_unrolli): Declare. > * tree-ssa-loop-ivcanon.c (try_unroll_loop_completely): Print > loop size before and after unconditionally of UL_NO_GROWTH in effect. > Rewrite loop into loop closed SSA form if it is not already. > (tree_unroll_loops_completely): Re-structure to iterate over > innermost loops with intermediate CFG cleanups. > Unroll outermost loops only if requested or the code does not grow > doing so. > * tree-ssa-loop.c (gate_tree_vectorize): Don't shortcut if no > loops are available. > (tree_vectorize): Instead do so here. > (tree_complete_unroll): Also unroll outermost loops. > (tree_complete_unroll_inner): New function. > (gate_tree_complete_unroll_inner): Likewise. > (pass_complete_unrolli): New pass. > * tree-ssa-loop-manip.c (find_uses_to_rename_use): Only record > uses outside of the loop. > (tree_duplicate_loop_to_header_edge): Only verify loop-closed SSA > form if it is available. > * tree-flow.h (tree_unroll_loops_completely): Add extra parameter. > * passes.c (init_optimization_passes): Schedule complete inner > loop unrolling pass before the first CCP pass after final inlining. > > * gcc.dg/tree-ssa/loop-36.c: New testcase. > * gcc.dg/tree-ssa/loop-37.c: Likewise. > * gcc.dg/vect/vect-118.c: Likewise. > * gcc.dg/Wunreachable-8.c: XFAIL bogus warning. > * gcc.dg/vect/vect-66.c: Increase loop trip count. > * gcc.dg/vect/no-section-anchors-vect-66.c: Likewise. > * gcc.dg/vect/no-section-anchors-vect-69.c: Likewise. > * gcc.dg/vect/vect-76.c: Likewise. > * gcc.dg/vect/vect-outer-6.c: Likewise. > * gcc.dg/vect/vect-outer-1.c: Likewise. > * gcc.dg/vect/vect-outer-1a.c: Likewise. > * gcc.dg/vect/vect-11a.c: Likewise. > * gcc.dg/vect/vect-shift-1.c: Likewise. > * gcc.target/i386/vectorize1.c: Likewise. > > > ...solved this performance regression. Is it possible that these changes could > be backported to gcc 4.3.2 to eliminate the performance regression in gcc 4.3 > compared to gcc 4.2?
No. This patch adds a new feature. Richard.
