https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117932
Bug ID: 117932
Summary: [15 Regression] 100% compile-time slowdown from
r15-518-g99b1daae18c095 for PR26854 testcase at -O2
Product: gcc
Version: 15.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: rguenth at gcc dot gnu.org
Target Milestone: ---
At -O2 r15-518-g99b1daae18c095 (a change in GIMPLE sink heuristics) causes a
compile-time regression for all.i from PR26854
(http://www.math.purdue.edu/~lucier/gcc/test-files/bugzilla/1/all.i.gz)
changing from
121.65user 12.13system 2:13.86elapsed 99%CPU (0avgtext+0avgdata
8117936maxresident)k
to
245.64user 13.53system 4:19.34elapsed 99%CPU (0avgtext+0avgdata
11689244maxresident)k
Note the price is entirely paid during RTL opts in DF. time-report before
the change:
Time variable usr sys wall
GGC
phase setup : 0.00 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
1841k ( 0%)
phase parsing : 9.19 ( 8%) 5.04 ( 28%) 14.24 ( 10%)
123M ( 12%)
phase opt and generate : 113.22 ( 92%) 13.17 ( 72%) 126.46 ( 90%)
901M ( 88%)
garbage collection : 0.20 ( 0%) 0.00 ( 0%) 0.20 ( 0%)
0 ( 0%)
callgraph construction : 0.20 ( 0%) 0.01 ( 0%) 0.20 ( 0%)
648k ( 0%)
callgraph optimization : 0.91 ( 1%) 0.02 ( 0%) 0.94 ( 1%)
1536k ( 0%)
callgraph functions expansion : 85.17 ( 70%) 12.41 ( 68%) 97.64 ( 69%)
594M ( 58%)
callgraph ipa passes : 27.45 ( 22%) 0.71 ( 4%) 28.18 ( 20%)
143M ( 14%)
ipa function summary : 0.17 ( 0%) 0.00 ( 0%) 0.17 ( 0%)
11M ( 1%)
ipa cp : 0.13 ( 0%) 0.00 ( 0%) 0.13 ( 0%)
1216 ( 0%)
ipa inlining heuristics : 0.00 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
16 ( 0%)
ipa pure const : 0.06 ( 0%) 0.00 ( 0%) 0.05 ( 0%)
0 ( 0%)
ipa icf : 0.06 ( 0%) 0.00 ( 0%) 0.08 ( 0%)
0 ( 0%)
ipa SRA : 0.01 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
568 ( 0%)
ipa modref : 0.17 ( 0%) 0.00 ( 0%) 0.18 ( 0%)
3136 ( 0%)
cfg construction : 0.06 ( 0%) 0.00 ( 0%) 0.05 ( 0%)
6571k ( 1%)
cfg cleanup : 1.73 ( 1%) 0.00 ( 0%) 1.81 ( 1%)
16M ( 2%)
trivially dead code : 0.18 ( 0%) 0.00 ( 0%) 0.19 ( 0%)
0 ( 0%)
df scan insns : 0.05 ( 0%) 0.00 ( 0%) 0.05 ( 0%)
144 ( 0%)
df reaching defs : 8.42 ( 7%) 1.53 ( 8%) 9.98 ( 7%)
0 ( 0%)
df live regs : 3.35 ( 3%) 0.00 ( 0%) 3.37 ( 2%)
0 ( 0%)
df live&initialized regs : 2.89 ( 2%) 0.00 ( 0%) 2.79 ( 2%)
0 ( 0%)
df must-initialized regs : 0.03 ( 0%) 0.00 ( 0%) 0.04 ( 0%)
0 ( 0%)
df use-def / def-use chains : 8.42 ( 7%) 7.61 ( 42%) 16.02 ( 11%)
0 ( 0%)
df reg dead/unused notes : 0.65 ( 1%) 0.00 ( 0%) 0.67 ( 0%)
8227k ( 1%)
register information : 0.17 ( 0%) 0.00 ( 0%) 0.16 ( 0%)
0 ( 0%)
alias analysis : 0.38 ( 0%) 0.01 ( 0%) 0.38 ( 0%)
18M ( 2%)
alias stmt walking : 2.83 ( 2%) 0.38 ( 2%) 3.35 ( 2%)
174k ( 0%)
register scan : 0.03 ( 0%) 0.00 ( 0%) 0.03 ( 0%)
198k ( 0%)
rebuild jump labels : 0.13 ( 0%) 0.00 ( 0%) 0.13 ( 0%)
0 ( 0%)
preprocessing : 1.26 ( 1%) 0.76 ( 4%) 1.92 ( 1%)
2767k ( 0%)
lexical analysis : 1.72 ( 1%) 1.42 ( 8%) 3.18 ( 2%)
0 ( 0%)
parser (global) : 0.16 ( 0%) 0.25 ( 1%) 0.40 ( 0%)
4021k ( 0%)
parser struct body : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
308k ( 0%)
parser function body : 6.04 ( 5%) 2.61 ( 14%) 8.74 ( 6%)
116M ( 11%)
inline parameters : 0.18 ( 0%) 0.00 ( 0%) 0.18 ( 0%)
4598k ( 0%)
tree gimplify : 0.22 ( 0%) 0.04 ( 0%) 0.26 ( 0%)
74M ( 7%)
tree eh : 0.01 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
0 ( 0%)
tree CFG construction : 0.13 ( 0%) 0.00 ( 0%) 0.13 ( 0%)
88M ( 9%)
tree CFG cleanup : 1.28 ( 1%) 0.00 ( 0%) 1.27 ( 1%)
1378k ( 0%)
tree tail merge : 0.14 ( 0%) 0.00 ( 0%) 0.15 ( 0%)
9494k ( 1%)
tree VRP : 12.58 ( 10%) 0.03 ( 0%) 12.60 ( 9%)
2172k ( 0%)
tree Early VRP : 7.05 ( 6%) 0.05 ( 0%) 7.09 ( 5%)
36M ( 4%)
tree copy propagation : 0.56 ( 0%) 0.00 ( 0%) 0.55 ( 0%)
6264 ( 0%)
tree PTA : 4.88 ( 4%) 0.20 ( 1%) 5.07 ( 4%)
6650k ( 1%)
tree SSA other : 0.00 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
0 ( 0%)
tree SSA rewrite : 0.23 ( 0%) 0.09 ( 0%) 0.39 ( 0%)
36M ( 4%)
tree SSA incremental : 2.36 ( 2%) 0.11 ( 1%) 2.42 ( 2%)
9660k ( 1%)
tree operand scan : 0.11 ( 0%) 0.12 ( 1%) 0.20 ( 0%)
17M ( 2%)
dominator optimization : 6.35 ( 5%) 0.03 ( 0%) 6.40 ( 5%)
20M ( 2%)
backwards jump threading : 1.29 ( 1%) 0.01 ( 0%) 1.31 ( 1%)
1768k ( 0%)
isolate eroneous paths : 0.04 ( 0%) 0.00 ( 0%) 0.03 ( 0%)
0 ( 0%)
tree CCP : 1.27 ( 1%) 0.04 ( 0%) 1.31 ( 1%)
1687k ( 0%)
tree split crit edges : 0.01 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
8614k ( 1%)
tree reassociation : 0.11 ( 0%) 0.00 ( 0%) 0.14 ( 0%)
14k ( 0%)
tree PRE : 1.74 ( 1%) 0.15 ( 1%) 2.06 ( 1%)
13M ( 1%)
tree FRE : 15.70 ( 13%) 0.37 ( 2%) 15.85 ( 11%)
9299k ( 1%)
tree code sinking : 0.18 ( 0%) 0.00 ( 0%) 0.18 ( 0%)
18M ( 2%)
tree linearize phis : 0.06 ( 0%) 0.00 ( 0%) 0.08 ( 0%)
104k ( 0%)
tree backward propagate : 0.06 ( 0%) 0.00 ( 0%) 0.05 ( 0%)
0 ( 0%)
tree forward propagate : 0.51 ( 0%) 0.03 ( 0%) 0.53 ( 0%)
5384k ( 1%)
tree phiprop : 0.02 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
0 ( 0%)
tree conservative DCE : 0.48 ( 0%) 0.14 ( 1%) 0.52 ( 0%)
3984 ( 0%)
tree aggressive DCE : 0.54 ( 0%) 0.10 ( 1%) 0.62 ( 0%)
1447k ( 0%)
tree DSE : 1.34 ( 1%) 0.00 ( 0%) 1.32 ( 1%)
557k ( 0%)
PHI merge : 0.07 ( 0%) 0.00 ( 0%) 0.07 ( 0%)
28M ( 3%)
tree loop invariant motion : 0.29 ( 0%) 0.00 ( 0%) 0.28 ( 0%)
0 ( 0%)
tree canonical iv : 0.02 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
72k ( 0%)
complete unrolling : 0.08 ( 0%) 0.00 ( 0%) 0.08 ( 0%)
260k ( 0%)
tree slp vectorization : 1.16 ( 1%) 0.01 ( 0%) 1.17 ( 1%)
191M ( 19%)
tree loop distribution : 0.02 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
0 ( 0%)
tree iv optimization : 0.02 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
168 ( 0%)
predictive commoning : 0.10 ( 0%) 0.00 ( 0%) 0.10 ( 0%)
6090k ( 1%)
tree copy headers : 0.25 ( 0%) 0.00 ( 0%) 0.25 ( 0%)
201k ( 0%)
tree SSA uncprop : 0.05 ( 0%) 0.00 ( 0%) 0.06 ( 0%)
0 ( 0%)
gimple CSE sin/cos : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
0 ( 0%)
gimple widening/fma detection : 0.03 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
0 ( 0%)
tree strlen optimization : 0.45 ( 0%) 0.00 ( 0%) 0.45 ( 0%)
3216 ( 0%)
tree modref : 0.38 ( 0%) 0.00 ( 0%) 0.36 ( 0%)
5784 ( 0%)
dominance frontiers : 0.12 ( 0%) 0.00 ( 0%) 0.14 ( 0%)
0 ( 0%)
dominance computation : 1.01 ( 1%) 0.01 ( 0%) 1.00 ( 1%)
0 ( 0%)
control dependences : 0.01 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
0 ( 0%)
out of ssa : 1.19 ( 1%) 0.00 ( 0%) 1.19 ( 1%)
28k ( 0%)
expand vars : 0.02 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
12M ( 1%)
expand : 1.03 ( 1%) 0.05 ( 0%) 1.08 ( 1%)
65M ( 6%)
post expand cleanups : 0.07 ( 0%) 0.01 ( 0%) 0.07 ( 0%)
3483k ( 0%)
lower subreg : 0.00 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
0 ( 0%)
forward prop : 0.91 ( 1%) 0.04 ( 0%) 0.94 ( 1%)
1026k ( 0%)
CSE : 0.41 ( 0%) 0.00 ( 0%) 0.41 ( 0%)
2531k ( 0%)
dead code elimination : 2.29 ( 2%) 0.01 ( 0%) 2.30 ( 2%)
0 ( 0%)
dead store elim1 : 0.17 ( 0%) 0.02 ( 0%) 0.18 ( 0%)
10M ( 1%)
dead store elim2 : 0.16 ( 0%) 0.00 ( 0%) 0.16 ( 0%)
9444k ( 1%)
loop init : 0.47 ( 0%) 0.01 ( 0%) 0.58 ( 0%)
17M ( 2%)
loop unrolling : 0.05 ( 0%) 0.00 ( 0%) 0.05 ( 0%)
72 ( 0%)
loop fini : 0.22 ( 0%) 0.01 ( 0%) 0.20 ( 0%)
0 ( 0%)
CPROP : 0.05 ( 0%) 0.01 ( 0%) 0.04 ( 0%)
0 ( 0%)
PRE : 0.01 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
0 ( 0%)
CSE 2 : 0.42 ( 0%) 0.00 ( 0%) 0.42 ( 0%)
2408k ( 0%)
branch prediction : 0.16 ( 0%) 0.00 ( 0%) 0.15 ( 0%)
1588k ( 0%)
combiner : 0.72 ( 1%) 0.00 ( 0%) 0.73 ( 1%)
21M ( 2%)
if-conversion : 0.10 ( 0%) 0.00 ( 0%) 0.10 ( 0%)
278k ( 0%)
integrated RA : 1.29 ( 1%) 0.01 ( 0%) 1.31 ( 1%)
50M ( 5%)
LRA non-specific : 0.84 ( 1%) 0.00 ( 0%) 0.86 ( 1%)
4816k ( 0%)
LRA virtuals elimination : 0.10 ( 0%) 0.00 ( 0%) 0.08 ( 0%)
17k ( 0%)
LRA create live ranges : 0.39 ( 0%) 0.00 ( 0%) 0.39 ( 0%)
289k ( 0%)
LRA hard reg assignment : 0.25 ( 0%) 0.01 ( 0%) 0.26 ( 0%)
0 ( 0%)
LRA rematerialization : 0.16 ( 0%) 0.00 ( 0%) 0.16 ( 0%)
0 ( 0%)
reload : 0.01 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
72 ( 0%)
reload CSE regs : 0.56 ( 0%) 0.00 ( 0%) 0.56 ( 0%)
13M ( 1%)
ree : 0.06 ( 0%) 0.00 ( 0%) 0.06 ( 0%)
320 ( 0%)
thread pro- & epilogue : 0.19 ( 0%) 0.00 ( 0%) 0.19 ( 0%)
6376 ( 0%)
if-conversion 2 : 0.06 ( 0%) 0.00 ( 0%) 0.09 ( 0%)
56k ( 0%)
combine stack adjustments : 0.05 ( 0%) 0.00 ( 0%) 0.04 ( 0%)
0 ( 0%)
peephole 2 : 0.13 ( 0%) 0.00 ( 0%) 0.12 ( 0%)
821k ( 0%)
hard reg cprop : 0.15 ( 0%) 0.00 ( 0%) 0.15 ( 0%)
10056 ( 0%)
scheduling 2 : 0.90 ( 1%) 0.01 ( 0%) 0.91 ( 1%)
2706k ( 0%)
machine dep reorg : 2.22 ( 2%) 0.00 ( 0%) 2.22 ( 2%)
0 ( 0%)
reorder blocks : 0.25 ( 0%) 0.00 ( 0%) 0.27 ( 0%)
8526k ( 1%)
shorten branches : 0.16 ( 0%) 0.00 ( 0%) 0.16 ( 0%)
0 ( 0%)
final : 0.27 ( 0%) 0.00 ( 0%) 0.28 ( 0%)
10M ( 1%)
variable output : 0.02 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
728k ( 0%)
tree if-combine : 0.02 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
193k ( 0%)
if to switch conversion : 0.04 ( 0%) 0.00 ( 0%) 0.03 ( 0%)
336 ( 0%)
straight-line strength reduction : 0.20 ( 0%) 0.00 ( 0%) 0.19 ( 0%)
0 ( 0%)
store merging : 0.00 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
800 ( 0%)
initialize rtl : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
12k ( 0%)
tree loop if-conversion : 0.00 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
0 ( 0%)
access analysis : 0.47 ( 0%) 0.00 ( 0%) 0.48 ( 0%)
592k ( 0%)
rest of compilation : 0.85 ( 1%) 1.89 ( 10%) 2.74 ( 2%)
5087k ( 0%)
remove unused locals : 0.20 ( 0%) 0.00 ( 0%) 0.19 ( 0%)
0 ( 0%)
address taken : 0.13 ( 0%) 0.00 ( 0%) 0.13 ( 0%)
0 ( 0%)
rebuild frequencies : 0.05 ( 0%) 0.00 ( 0%) 0.05 ( 0%)
0 ( 0%)
repair loop structures : 0.01 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
0 ( 0%)
TOTAL : 122.41 18.21 140.70
1027M
and after:
Time variable usr sys wall
GGC
phase setup : 0.00 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
1841k ( 0%)
phase parsing : 9.29 ( 4%) 4.88 ( 25%) 14.18 ( 5%)
123M ( 2%)
phase opt and generate : 234.35 ( 96%) 14.70 ( 75%) 249.20 ( 95%)
5552M ( 98%)
garbage collection : 2.25 ( 1%) 0.02 ( 0%) 2.26 ( 1%)
0 ( 0%)
dump files : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
0 ( 0%)
callgraph construction : 0.17 ( 0%) 0.00 ( 0%) 0.18 ( 0%)
648k ( 0%)
callgraph optimization : 1.11 ( 0%) 0.02 ( 0%) 1.15 ( 0%)
1536k ( 0%)
callgraph functions expansion : 206.83 ( 85%) 13.87 ( 71%) 220.83 ( 84%)
5245M ( 92%)
callgraph ipa passes : 26.94 ( 11%) 0.78 ( 4%) 27.73 ( 11%)
143M ( 3%)
ipa function summary : 0.18 ( 0%) 0.00 ( 0%) 0.17 ( 0%)
11M ( 0%)
ipa cp : 0.13 ( 0%) 0.00 ( 0%) 0.14 ( 0%)
1216 ( 0%)
ipa inlining heuristics : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
16 ( 0%)
ipa pure const : 0.05 ( 0%) 0.00 ( 0%) 0.06 ( 0%)
0 ( 0%)
ipa icf : 0.07 ( 0%) 0.00 ( 0%) 0.06 ( 0%)
0 ( 0%)
ipa SRA : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
568 ( 0%)
ipa modref : 0.17 ( 0%) 0.00 ( 0%) 0.17 ( 0%)
3136 ( 0%)
cfg construction : 0.04 ( 0%) 0.00 ( 0%) 0.05 ( 0%)
5635k ( 0%)
cfg cleanup : 3.14 ( 1%) 0.01 ( 0%) 3.11 ( 1%)
15M ( 0%)
trivially dead code : 0.20 ( 0%) 0.00 ( 0%) 0.22 ( 0%)
0 ( 0%)
df scan insns : 0.05 ( 0%) 0.00 ( 0%) 0.05 ( 0%)
144 ( 0%)
df reaching defs : 9.42 ( 4%) 1.49 ( 8%) 10.91 ( 4%)
0 ( 0%)
df live regs : 47.73 ( 20%) 0.00 ( 0%) 47.78 ( 18%)
0 ( 0%)
df live&initialized regs : 39.47 ( 16%) 0.01 ( 0%) 39.52 ( 15%)
0 ( 0%)
df must-initialized regs : 0.04 ( 0%) 0.01 ( 0%) 0.05 ( 0%)
0 ( 0%)
df use-def / def-use chains : 7.82 ( 3%) 8.03 ( 41%) 15.87 ( 6%)
0 ( 0%)
df reg dead/unused notes : 0.75 ( 0%) 0.01 ( 0%) 0.71 ( 0%)
8444k ( 0%)
register information : 0.21 ( 0%) 0.00 ( 0%) 0.20 ( 0%)
0 ( 0%)
alias analysis : 0.59 ( 0%) 0.00 ( 0%) 0.58 ( 0%)
18M ( 0%)
alias stmt walking : 3.20 ( 1%) 0.39 ( 2%) 3.21 ( 1%)
174k ( 0%)
register scan : 0.03 ( 0%) 0.00 ( 0%) 0.03 ( 0%)
198k ( 0%)
rebuild jump labels : 0.12 ( 0%) 0.00 ( 0%) 0.14 ( 0%)
0 ( 0%)
preprocessing : 1.25 ( 1%) 0.70 ( 4%) 1.74 ( 1%)
2767k ( 0%)
lexical analysis : 1.89 ( 1%) 1.36 ( 7%) 3.02 ( 1%)
0 ( 0%)
parser (global) : 0.11 ( 0%) 0.29 ( 1%) 0.36 ( 0%)
4021k ( 0%)
parser function body : 6.04 ( 2%) 2.53 ( 13%) 9.06 ( 3%)
116M ( 2%)
inline parameters : 0.17 ( 0%) 0.00 ( 0%) 0.18 ( 0%)
4598k ( 0%)
tree gimplify : 0.23 ( 0%) 0.04 ( 0%) 0.27 ( 0%)
74M ( 1%)
tree eh : 0.01 ( 0%) 0.01 ( 0%) 0.01 ( 0%)
0 ( 0%)
tree CFG construction : 0.13 ( 0%) 0.00 ( 0%) 0.14 ( 0%)
88M ( 2%)
tree CFG cleanup : 1.34 ( 1%) 0.01 ( 0%) 1.38 ( 1%)
1378k ( 0%)
tree tail merge : 0.13 ( 0%) 0.01 ( 0%) 0.14 ( 0%)
9494k ( 0%)
tree VRP : 12.77 ( 5%) 0.03 ( 0%) 12.82 ( 5%)
2172k ( 0%)
tree Early VRP : 7.02 ( 3%) 0.06 ( 0%) 7.09 ( 3%)
36M ( 1%)
tree copy propagation : 0.56 ( 0%) 0.00 ( 0%) 0.56 ( 0%)
6264 ( 0%)
tree PTA : 4.95 ( 2%) 0.14 ( 1%) 5.10 ( 2%)
6650k ( 0%)
tree SSA rewrite : 0.22 ( 0%) 0.11 ( 1%) 0.37 ( 0%)
36M ( 1%)
tree SSA incremental : 2.43 ( 1%) 0.10 ( 1%) 2.50 ( 1%)
9660k ( 0%)
tree operand scan : 0.09 ( 0%) 0.16 ( 1%) 0.20 ( 0%)
17M ( 0%)
dominator optimization : 6.29 ( 3%) 0.05 ( 0%) 6.38 ( 2%)
20M ( 0%)
backwards jump threading : 1.31 ( 1%) 0.01 ( 0%) 1.31 ( 0%)
1768k ( 0%)
isolate eroneous paths : 0.03 ( 0%) 0.00 ( 0%) 0.03 ( 0%)
0 ( 0%)
tree CCP : 1.28 ( 1%) 0.06 ( 0%) 1.32 ( 1%)
1687k ( 0%)
tree split crit edges : 0.02 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
7469k ( 0%)
tree reassociation : 0.13 ( 0%) 0.00 ( 0%) 0.13 ( 0%)
14k ( 0%)
tree PRE : 1.91 ( 1%) 0.12 ( 1%) 2.06 ( 1%)
13M ( 0%)
tree FRE : 14.89 ( 6%) 0.27 ( 1%) 15.45 ( 6%)
9299k ( 0%)
tree code sinking : 0.21 ( 0%) 0.00 ( 0%) 0.20 ( 0%)
17M ( 0%)
tree linearize phis : 0.06 ( 0%) 0.00 ( 0%) 0.07 ( 0%)
104k ( 0%)
tree backward propagate : 0.06 ( 0%) 0.00 ( 0%) 0.06 ( 0%)
0 ( 0%)
tree forward propagate : 0.49 ( 0%) 0.01 ( 0%) 0.52 ( 0%)
5384k ( 0%)
tree phiprop : 0.00 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
0 ( 0%)
tree conservative DCE : 0.36 ( 0%) 0.15 ( 1%) 0.58 ( 0%)
3984 ( 0%)
tree aggressive DCE : 0.52 ( 0%) 0.08 ( 0%) 0.65 ( 0%)
1447k ( 0%)
tree DSE : 1.36 ( 1%) 0.00 ( 0%) 1.35 ( 1%)
557k ( 0%)
PHI merge : 0.06 ( 0%) 0.01 ( 0%) 0.06 ( 0%)
28M ( 1%)
tree loop invariant motion : 0.28 ( 0%) 0.00 ( 0%) 0.29 ( 0%)
0 ( 0%)
tree canonical iv : 0.02 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
72k ( 0%)
complete unrolling : 0.08 ( 0%) 0.00 ( 0%) 0.08 ( 0%)
260k ( 0%)
tree vectorization : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
0 ( 0%)
tree slp vectorization : 1.18 ( 0%) 0.01 ( 0%) 1.18 ( 0%)
191M ( 3%)
tree loop distribution : 0.03 ( 0%) 0.00 ( 0%) 0.03 ( 0%)
0 ( 0%)
tree iv optimization : 0.02 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
168 ( 0%)
predictive commoning : 0.10 ( 0%) 0.00 ( 0%) 0.10 ( 0%)
6090k ( 0%)
tree copy headers : 0.25 ( 0%) 0.00 ( 0%) 0.25 ( 0%)
201k ( 0%)
tree SSA uncprop : 0.05 ( 0%) 0.00 ( 0%) 0.05 ( 0%)
0 ( 0%)
gimple CSE sin/cos : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
0 ( 0%)
gimple expand pow/cabs : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
0 ( 0%)
gimple widening/fma detection : 0.03 ( 0%) 0.00 ( 0%) 0.04 ( 0%)
0 ( 0%)
tree strlen optimization : 0.43 ( 0%) 0.00 ( 0%) 0.44 ( 0%)
3216 ( 0%)
tree modref : 0.38 ( 0%) 0.00 ( 0%) 0.38 ( 0%)
5784 ( 0%)
dominance frontiers : 0.15 ( 0%) 0.00 ( 0%) 0.12 ( 0%)
0 ( 0%)
dominance computation : 5.06 ( 2%) 0.00 ( 0%) 5.10 ( 2%)
0 ( 0%)
control dependences : 0.01 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
0 ( 0%)
out of ssa : 1.20 ( 0%) 0.00 ( 0%) 1.19 ( 0%)
28k ( 0%)
expand vars : 0.02 ( 0%) 0.01 ( 0%) 0.02 ( 0%)
12M ( 0%)
expand : 1.09 ( 0%) 0.02 ( 0%) 1.12 ( 0%)
64M ( 1%)
post expand cleanups : 0.09 ( 0%) 0.01 ( 0%) 0.10 ( 0%)
3491k ( 0%)
lower subreg : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
0 ( 0%)
forward prop : 0.98 ( 0%) 0.07 ( 0%) 1.04 ( 0%)
1027k ( 0%)
CSE : 0.41 ( 0%) 0.00 ( 0%) 0.41 ( 0%)
2553k ( 0%)
dead code elimination : 4.01 ( 2%) 0.00 ( 0%) 4.02 ( 2%)
0 ( 0%)
dead store elim1 : 0.18 ( 0%) 0.02 ( 0%) 0.20 ( 0%)
10M ( 0%)
dead store elim2 : 0.15 ( 0%) 0.00 ( 0%) 0.15 ( 0%)
9442k ( 0%)
loop analysis : 0.00 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
0 ( 0%)
loop init : 1.08 ( 0%) 0.01 ( 0%) 1.00 ( 0%)
17M ( 0%)
loop invariant motion : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
0 ( 0%)
loop unrolling : 0.04 ( 0%) 0.00 ( 0%) 0.05 ( 0%)
72 ( 0%)
loop fini : 0.27 ( 0%) 0.00 ( 0%) 0.26 ( 0%)
0 ( 0%)
CPROP : 0.06 ( 0%) 0.00 ( 0%) 0.06 ( 0%)
0 ( 0%)
PRE : 0.02 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
0 ( 0%)
CSE 2 : 0.42 ( 0%) 0.00 ( 0%) 0.42 ( 0%)
2431k ( 0%)
branch prediction : 0.15 ( 0%) 0.00 ( 0%) 0.16 ( 0%)
1588k ( 0%)
combiner : 0.74 ( 0%) 0.01 ( 0%) 0.75 ( 0%)
21M ( 0%)
if-conversion : 0.12 ( 0%) 0.00 ( 0%) 0.12 ( 0%)
278k ( 0%)
integrated RA : 1.37 ( 1%) 0.00 ( 0%) 1.37 ( 1%)
50M ( 1%)
LRA non-specific : 0.87 ( 0%) 0.00 ( 0%) 0.88 ( 0%)
4815k ( 0%)
LRA virtuals elimination : 0.10 ( 0%) 0.00 ( 0%) 0.09 ( 0%)
17k ( 0%)
LRA create live ranges : 0.43 ( 0%) 0.00 ( 0%) 0.45 ( 0%)
290k ( 0%)
LRA hard reg assignment : 0.25 ( 0%) 0.04 ( 0%) 0.27 ( 0%)
0 ( 0%)
LRA rematerialization : 0.18 ( 0%) 0.00 ( 0%) 0.18 ( 0%)
0 ( 0%)
reload : 0.01 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
72 ( 0%)
reload CSE regs : 0.57 ( 0%) 0.00 ( 0%) 0.57 ( 0%)
13M ( 0%)
ree : 0.06 ( 0%) 0.00 ( 0%) 0.06 ( 0%)
320 ( 0%)
thread pro- & epilogue : 0.18 ( 0%) 0.00 ( 0%) 0.18 ( 0%)
6376 ( 0%)
if-conversion 2 : 3.98 ( 2%) 0.00 ( 0%) 3.99 ( 2%)
57k ( 0%)
combine stack adjustments : 0.05 ( 0%) 0.00 ( 0%) 0.04 ( 0%)
0 ( 0%)
peephole 2 : 2.92 ( 1%) 0.00 ( 0%) 2.94 ( 1%)
1150k ( 0%)
hard reg cprop : 4.05 ( 2%) 0.00 ( 0%) 4.07 ( 2%)
10k ( 0%)
scheduling 2 : 2.33 ( 1%) 0.00 ( 0%) 2.33 ( 1%)
2706k ( 0%)
machine dep reorg : 1.99 ( 1%) 0.00 ( 0%) 2.00 ( 1%)
0 ( 0%)
reorder blocks : 11.83 ( 5%) 1.16 ( 6%) 13.02 ( 5%)
4663M ( 82%)
shorten branches : 0.19 ( 0%) 0.00 ( 0%) 0.19 ( 0%)
0 ( 0%)
final : 0.95 ( 0%) 0.00 ( 0%) 0.96 ( 0%)
11M ( 0%)
variable output : 0.01 ( 0%) 0.00 ( 0%) 0.02 ( 0%)
728k ( 0%)
tree if-combine : 0.02 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
193k ( 0%)
if to switch conversion : 0.04 ( 0%) 0.00 ( 0%) 0.03 ( 0%)
336 ( 0%)
straight-line strength reduction : 0.20 ( 0%) 0.00 ( 0%) 0.20 ( 0%)
0 ( 0%)
store merging : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
800 ( 0%)
initialize rtl : 0.00 ( 0%) 0.00 ( 0%) 0.01 ( 0%)
12k ( 0%)
address lowering : 0.01 ( 0%) 0.00 ( 0%) 0.00 ( 0%)
0 ( 0%)
access analysis : 0.46 ( 0%) 0.02 ( 0%) 0.49 ( 0%)
592k ( 0%)
rest of compilation : 5.79 ( 2%) 1.90 ( 10%) 7.65 ( 3%)
4516k ( 0%)
remove unused locals : 0.18 ( 0%) 0.00 ( 0%) 0.19 ( 0%)
0 ( 0%)
address taken : 0.11 ( 0%) 0.00 ( 0%) 0.13 ( 0%)
0 ( 0%)
rebuild frequencies : 0.06 ( 0%) 0.00 ( 0%) 0.04 ( 0%)
0 ( 0%)
repair loop structures : 0.00 ( 0%) 0.00 ( 0%) 0.03 ( 0%)
0 ( 0%)
TOTAL : 243.64 19.58 263.38
5678M
