This is the mail archive of the
gcc-bugs@gcc.gnu.org
mailing list for the GCC project.
[Bug tree-optimization/18687] [4.3/4.4/4.5/4.6 Regression] >200% compile time regression compared to gcc-3.4
- From: "hubicka at gcc dot gnu.org" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: Sat, 8 Jan 2011 16:02:34 +0000
- Subject: [Bug tree-optimization/18687] [4.3/4.4/4.5/4.6 Regression] >200% compile time regression compared to gcc-3.4
- Auto-submitted: auto-generated
- References: <bug-18687-4@http.gcc.gnu.org/bugzilla/>
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=18687
Jan Hubicka <hubicka at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |hubicka at gcc dot gnu.org
Known to fail| |
--- Comment #52 from Jan Hubicka <hubicka at gcc dot gnu.org> 2011-01-08 16:02:07 UTC ---
hashes oprofile is as follows:
samples % app name symbol name
8237 2.9617 libc-2.11.1.so _int_malloc
6877 2.4727 cc1 bitmap_set_bit
5820 2.0927 cc1 htab_find_slot_with_hash
4238 1.5238 cc1 operand_equal_p
4233 1.5220 cc1 record_reg_classes.constprop.9
4069 1.4631 cc1 bitmap_bit_p
3780 1.3592 libc-2.11.1.so memset
3399 1.2222 cc1 nonzero_bits1
2992 1.0758 cc1 ggc_internal_alloc_stat
2516 0.9047 libc-2.11.1.so _int_free
2454 0.8824 as /usr/bin/as
2244 0.8069 cc1 fold_binary_loc
2229 0.8015 libc-2.11.1.so malloc
1909 0.6864 libc-2.11.1.so free
1857 0.6677 cc1 constrain_operands.part.12
1696 0.6098 cc1 is_gimple_reg
1688 0.6069 cc1 et_splay
1667 0.5994 cc1 note_stores
1632 0.5868 cc1 walk_tree_1
1585 0.5699 cc1 for_each_rtx_1
1577 0.5670 cc1 pool_alloc
1572 0.5652 cc1 tree_strip_nop_conversions
and the other testcase:
samples % image name app name symbol name
5195 5.1031 cc1 cc1
operand_equal_p
2848 2.7976 cc1 cc1
bitmap_set_bit
2080 2.0432 libc-2.11.1.so libc-2.11.1.so _int_malloc
1879 1.8458 cc1 cc1
htab_find_slot_with_hash
1432 1.4067 cc1 cc1
bitmap_bit_p
1298 1.2750 cc1 cc1
mem_attrs_htab_eq
1290 1.2672 cc1 cc1
record_reg_classes.constprop.9
1063 1.0442 cc1 cc1 walk_tree_1
1010 0.9921 cc1 cc1
tree_strip_nop_conversions
1004 0.9862 cc1 cc1
bitmap_ior_into
963 0.9460 libc-2.11.1.so libc-2.11.1.so memset
934 0.9175 cc1 cc1
df_worklist_dataflow
882 0.8664 cc1 cc1
mark_all_vars_used_1
806 0.7917 as as /usr/bin/as
795 0.7809 opreport opreport
/usr/bin/opreport
793 0.7790 cc1 cc1
ggc_internal_alloc_stat
784 0.7701 cc1 cc1
is_gimple_reg
732 0.7190 cc1 cc1
constrain_operands.part.12
701 0.6886 cc1 cc1
bitmap_ior_and_compl
672 0.6601 cc1 cc1 et_splay
650 0.6385 libc-2.11.1.so libc-2.11.1.so _int_free
612 0.6012 cc1 cc1
for_each_rtx_1
608 0.5972 libc-2.11.1.so libc-2.11.1.so memcpy
603 0.5923 libc-2.11.1.so libc-2.11.1.so malloc
596 0.5855 cc1 cc1
bitmap_elt_insert_after
581 0.5707 cc1 cc1
ix86_decompose_address
570 0.5599 cc1 cc1 bitmap_copy
568 0.5580 cc1 cc1 cse_insn
so apparently not much of surprise.