This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
compute_flow_dominators killing performance with -O1
- To: gcc at gcc dot gnu dot org
- Subject: compute_flow_dominators killing performance with -O1
- From: Brad Lucier <lucier at math dot purdue dot edu>
- Date: Fri, 31 Mar 2000 17:25:43 -0500 (EST)
- Cc: lucier at math dot purdue dot edu, feeley at iro dot umontreal dot ca
Mark Mitchell has been stomping some O(N^2) algorithms; here's another
candidate.
Brad Lucier
Compiler is gcc version 2.96 20000331; input file is at
http://www.math.purdue.edu/~lucier/_std.i.gz
popov-175% /export/u10/egcs-profile/lib/gcc-lib/alphaev6-unknown-linux-gnu/2.96/cc1 -O1 _std.i
__copysignf copysignf __copysign copysign __fabsf fabsf __fabs fabs __floorf __floor floorf floor __fdimf fdimf __fdim fdim ___H__20___std {GC 27190k -> 8575k in 0.188} {GC 12863k -> 8778k in 0.204} {GC 12534k -> 9230k in 0.216} ___init_proc {GC 18065k -> 1705k in 0.034} ____20___std
time in parse: 4.399808 (0%)
time in integration: 0.000976 (0%)
time in jump: 2.539552 (0%)
time in cse: 2.127680 (0%)
time in gcse: 0.000000 (0%)
time in loop: 0.005856 (0%)
time in cse2: 0.000000 (0%)
time in branch-prob: 0.000000 (0%)
time in flow: 1385.333424 (98%) <====!!!!!!! (only nonzero percentage)
time in combine: 2.894816 (0%)
time in regmove: 0.000000 (0%)
time in sched: 0.000000 (0%)
time in local-alloc: 1.057008 (0%)
time in global-alloc: 2.293600 (0%)
time in flow2: 6.874944 (0%)
time in peephole2: 0.000000 (0%)
time in sched2: 0.000000 (0%)
time in bbro: 0.000000 (0%)
time in shorten-branch: 0.104432 (0%)
time in final: 1.094096 (0%)
time in varconst: 0.006832 (0%)
time in symout: 0.000000 (0%)
time in dump: 0.000000 (0%)
time in gc: 0.642208 (0%)
Flat profile:
Each sample counts as 0.000976562 seconds.
% cumulative self self total
time seconds seconds calls ms/call ms/call name
92.30 280.12 280.12 738190 0.38 0.38 sbitmap_intersection_of_preds
1.41 284.39 4.27 738193 0.01 0.01 sbitmap_a_and_b
0.55 286.07 1.67 7772830 0.00 0.00 bitmap_operation
0.52 287.65 1.59 3 528.97 95345.03 compute_flow_dominators
...
-----------------------------------------------
1.59 284.45 3/3 flow_loops_find [7]
[8] 94.2 1.59 284.45 3 compute_flow_dominators [8]
280.12 0.04 738190/738190 sbitmap_intersection_of_preds [9]
4.27 0.00 738193/738193 sbitmap_a_and_b [10]
0.01 0.00 3/8 sbitmap_vector_alloc [222]
0.00 0.00 3/5 sbitmap_vector_zero [655]
0.00 0.00 3/18894 sbitmap_zero [715]
0.00 0.00 3/3 sbitmap_vector_ones [1388]
-----------------------------------------------
280.12 0.04 738190/738190 compute_flow_dominators [8]
[9] 92.3 280.12 0.04 738190 sbitmap_intersection_of_preds [9]
0.04 0.00 738190/738190 sbitmap_copy [191]
-----------------------------------------------