[Bug tree-optimization/30735] New: 50% slow down due to mem-ssa merge

[Bug tree-optimization/30735] New: 50% slow down due to mem-ssa merge

[hjl at lucon dot org]

There is a huge regression of gcc 4.3 performance detected on
cpu2006/454.calculix benchmark at -O2 optimization level on
x86_64-redhat-linux.

Regression is caused by mem-ssa merge 12/12/2006 (revision 119760).
http://gcc.gnu.org/viewcvs?view=rev&revision=119760

mem-ssa merge may introduce unnecessary memory <-> register moves.


-- 
           Summary: 50% slow down due to mem-ssa merge
           Product: gcc
           Version: 4.3.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: hjl at lucon dot org


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] 50% slow down due to mem-ssa merge

[hjl at lucon dot org]

------- Comment #1 from hjl at lucon dot org  2007-02-08 17:01 -------
Created an attachment (id=13021)
 --> (http://gcc.gnu.org/bugzilla/attachment.cgi?id=13021&action=view)
A testcase

# /usr/gcc-good/bin/gfortran -v
Using built-in specs.
Target: i686-pc-linux-gnu
Configured with: /net/gnu-13/export/gnu/src/gcc/gcc/configure
--enable-clocale=gnu --with-system-zlib --with-demangler-in-ld --enable-shared
--enable-threads=posix --enable-haifa --enable-checking=assert
--prefix=/usr/gcc-4.3 --with-local-prefix=/usr/local
Thread model: posix
gcc version 4.3.0 20061211 (experimental) [trunk revision 119728]
# /usr/gcc-4.3/bin/gfortran -v
Using built-in specs.
Target: i686-pc-linux-gnu
Configured with: /net/gnu-13/export/gnu/src/gcc/gcc/configure
--enable-clocale=gnu --with-system-zlib --enable-decimal-float=yes
--with-demangler-in-ld --enable-shared --enable-threads=posix --enable-haifa
--enable-checking=assert --prefix=/usr/gcc-4.3 --with-local-prefix=/usr/local
Thread model: posix
gcc version 4.3.0 20070206 (experimental) [trunk revision 121636]
# make
/usr/gcc-good/bin/gfortran -c -O2 -ffast-math -static -o old.o e_c3d.f
/usr/gcc-4.3/bin/gfortran -O2 -ffast-math -static  -c -o tr535.o tr535.f
/usr/gcc-4.3/bin/gfortran -O2 -ffast-math -static -o old old.o tr535.o
/usr/gcc-4.3/bin/gfortran -c -O2 -ffast-math -static -o new.o e_c3d.f
/usr/gcc-4.3/bin/gfortran -O2 -ffast-math -static -o new new.o tr535.o
time ./old
0.03user 0.00system 0:00.03elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+82minor)pagefaults 0swaps
time ./new
0.10user 0.00system 0:00.10elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+83minor)pagefaults 0swaps


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] 50% slow down due to mem-ssa merge

[rguenth at gcc dot gnu dot org]

------- Comment #2 from rguenth at gcc dot gnu dot org  2007-02-08 17:07 -------
Try one of the partitioning patches I proposed.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] 50% slow down due to mem-ssa merge

[hjl at lucon dot org]

------- Comment #3 from hjl at lucon dot org  2007-02-08 17:13 -------
(In reply to comment #2)
> Try one of the partitioning patches I proposed.
> 

Which one? Please provide a link or attach it here. Thanks.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] 50% slow down due to mem-ssa merge

[dnovillo at gcc dot gnu dot org]

-- 

dnovillo at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
         AssignedTo|unassigned at gcc dot gnu   |dnovillo at gcc dot gnu dot
                   |dot org                     |org
             Status|UNCONFIRMED                 |ASSIGNED
     Ever Confirmed|0                           |1
   Last reconfirmed|0000-00-00 00:00:00         |2007-02-08 18:42:31
               date|                            |


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] 50% slow down due to mem-ssa merge

[dnovillo at gcc dot gnu dot org]

------- Comment #4 from dnovillo at gcc dot gnu dot org  2007-02-13 00:59 -------

I have now reproduced this locally and I'm working on a fix.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] 50% slow down due to mem-ssa merge

[pthaugen at us dot ibm dot com]

------- Comment #5 from pthaugen at us dot ibm dot com  2007-02-15 23:36 -------
Seeing similar behavior on PPC for CPU2000. Comparing revisions 119759 and
119760, 179.art degrades 24% and 200.sixtrack degrades 50%.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] [4.3 Regression] 50% slow down due to mem-ssa merge

[pinskia at gcc dot gnu dot org]

-- 

pinskia at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
            Summary|50% slow down due to mem-ssa|[4.3 Regression] 50% slow
                   |merge                       |down due to mem-ssa merge
   Target Milestone|---                         |4.3.0


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] [4.3 Regression] 50% slow down due to mem-ssa merge

[dnovillo at gcc dot gnu dot org]

------- Comment #6 from dnovillo at gcc dot gnu dot org  2007-04-11 17:14 -------
Subject: Bug 30735

Author: dnovillo
Date: Wed Apr 11 17:14:06 2007
New Revision: 123719

URL: http://gcc.gnu.org/viewcvs?root=gcc&view=rev&rev=123719
Log:

        PR 30735
        PR 31090
        * doc/invoke.texi: Document --params max-aliased-vops and
        avg-aliased-vops.
        * tree-ssa-operands.h (get_mpt_for, dump_memory_partitions,
        debug_memory_partitions): Move to tree-flow.h
        * params.h (AVG_ALIASED_VOPS): Define.
        * tree-ssa-alias.c (struct mp_info_def): Remove.  Update all
        users.
        (mp_info_t): Likewise.
        (get_mem_sym_stats_for): New.
        (set_memory_partition): Move from tree-flow-inline.h.
        (mark_non_addressable): Only clear the set of symbols for the
        partition if it exists.
        (dump_memory_partitions): Move from tree-ssa-operands.c
        (debug_memory_partitions): Likewise.
        (need_to_partition_p): New.
        (dump_mem_ref_stats): New.
        (debug_mem_ref_stats): New.
        (dump_mem_sym_stats): New.
        (debug_mem_sym_stats): New.
        (update_mem_sym_stats_from_stmt): New.
        (compare_mp_info_entries): New.
        (mp_info_cmp): Call it.
        (sort_mp_info): Change argument to a list of mem_sym_stats_t
        objects.
        (get_mpt_for): Move from tree-ssa-operands.c.
        (find_partition_for): New.
        (create_partition_for): Remove.
        (estimate_vop_reduction): New.
        (update_reference_counts): New.
        (build_mp_info): New.
        (compute_memory_partitions): Refactor.
        Document new heuristic.
        Call build_mp_info, update_reference_counts,
        find_partition_for and estimate_vop_reduction.
        (compute_may_aliases): Populate virtual operands before
        calling debugging dumps.
        (delete_mem_sym_stats): New.
        (delete_mem_ref_stats): New.
        (init_mem_ref_stats): New.
        (init_alias_info): Call it.
        (maybe_create_global_var): Remove alias_info argument.
        Get number of call sites and number of pure/const call sites
        from gimple_mem_ref_stats().
        (dump_alias_info): Call dump_memory_partitions first.
        (dump_points_to_info_for): Show how many times a pointer has
        been dereferenced.
        * opts.c (decode_options): For -O2 set --param
        max-aliased-vops to 500.
        For -O3 set --param max-aliased-vops to 1000 and --param
        avg-aliased-vops to 3.
        * fortran/options.c (gfc_init_options): Remove assignment to
        MAX_ALIASED_VOPS.
        * tree-flow-inline.h (gimple_mem_ref_stats): New.
        * tree-dfa.c (dump_variable): Dump memory reference
        statistics.
        Dump NO_ALIAS* settings.
        (referenced_var_lookup): Tidy.
        (mem_sym_stats): New.
        * tree-ssa-copy.c (may_propagate_copy): Return true if DEST
        and ORIG are different SSA names for a memory partition.
        * tree-ssa.c (delete_tree_ssa): Call delete_mem_ref_stats.
        * tree-flow.h (struct mem_sym_stats_d): Define.
        (mem_sym_stats_t): Define.
        (struct mem_ref_stats_d): Define.
        (struct gimple_df): Add field mem_ref_stats.
        (enum noalias_state): Define.
        (struct var_ann_d): Add bitfield noalias_state.
        (mem_sym_stats, delete_mem_ref_stats, dump_mem_ref_stats,
        debug_mem_ref_stats, debug_memory_partitions,
        debug_mem_sym_stats): Declare.
        * tree-ssa-structalias.c (update_alias_info): Update call
        sites, pure/const call sites and asm sites in structure
        returned by gimple_mem_ref_stats.
        Remove local variable IS_POTENTIAL_DEREF.
        Increase NUM_DEREFS if the memory expression is a potential
        dereference.
        Call update_mem_sym_stats_from_stmt.
        If the memory references memory, call
        update_mem_sym_stats_from_stmt for all the direct memory
        symbol references found.
        (intra_create_variable_infos): Set noalias_state field for
        pointer arguments according to the value of
        flag_argument_noalias.
        * tree-ssa-structalias.h (struct alias_info): Remove fields
        num_calls_found and num_pure_const_calls_found.
        (update_mem_sym_stats_from_stmt): Declare.
        * params.def (PARAM_MAX_ALIASED_VOPS): Change description.
        Set default value to 100.
        (PARAM_AVG_ALIASED_VOPS): Define.


Modified:
    trunk/gcc/ChangeLog
    trunk/gcc/doc/invoke.texi
    trunk/gcc/fortran/options.c
    trunk/gcc/opts.c
    trunk/gcc/params.def
    trunk/gcc/params.h
    trunk/gcc/tree-dfa.c
    trunk/gcc/tree-flow-inline.h
    trunk/gcc/tree-flow.h
    trunk/gcc/tree-ssa-alias.c
    trunk/gcc/tree-ssa-copy.c
    trunk/gcc/tree-ssa-operands.c
    trunk/gcc/tree-ssa-operands.h
    trunk/gcc/tree-ssa-structalias.c
    trunk/gcc/tree-ssa-structalias.h
    trunk/gcc/tree-ssa.c
    trunk/gcc/tree-vrp.c


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] [4.3 Regression] 50% slow down due to mem-ssa merge

[mmitchel at gcc dot gnu dot org]

------- Comment #7 from mmitchel at gcc dot gnu dot org  2007-06-29 17:52 -------
A patch has been checked in; can this be closed now?


-- 

mmitchel at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Priority|P3                          |P2


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] [4.3 Regression] 50% slow down due to mem-ssa merge

[hjl at lucon dot org]

------- Comment #8 from hjl at lucon dot org  2007-06-29 17:57 -------
(In reply to comment #7)
> A patch has been checked in; can this be closed now?
> 

See

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=31090#c16


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735

[Bug tree-optimization/30735] [4.3 Regression] 50% slow down due to mem-ssa merge

[rguenth at gcc dot gnu dot org]

------- Comment #9 from rguenth at gcc dot gnu dot org  2007-11-10 17:07 -------
Likewise.

*** This bug has been marked as a duplicate of 33974 ***


-- 

rguenth at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|ASSIGNED                    |RESOLVED
         Resolution|                            |DUPLICATE


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=30735