This is the mail archive of the gcc@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: Pretty good gcc-3.1 on sparc32-linux


On Fri, Apr 19, 2002 at 06:20:40PM +0200, Christian Jönsson wrote:
> On Thu, Apr 18, 2002 at 01:02:33PM -0700, Richard Henderson wrote:
> > On Thu, Apr 18, 2002 at 08:39:53PM +0200, Christian Jönsson wrote:
> > > Well, that could of course very well be the case. Do you suggest that
> > > I try something special to find something out for all of us or should
> > > I just drop the issue?
> > 
> > The delayed branch scheduling pass is a known problem child.  It's
> > been waiting to be rewritten for a few years now.
> > 
> > I suppose you could compile that test case by hand with -Q to verify
> > that that is where the bulk of the time is being spent, but...
> 
> I didn't do that but I timed the tests (memory usage was up to about 16%
> of 320 MB in most cases but up to 36% for -Os early):
> 
> -O0:
> 99.80user 3.88system 1:43.58elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (2931major+20234minor)pagefaults 0swaps

Here's the output when compiled with -fmem-report and -ftime-report:

Tree                 Number            Bytes    % Total
error_mark                1              16       0.021
identifier_node         478              29k     39.615
tree_list               119            2856       3.698
tree_vec                  1              16       0.021
block                     1              64       0.083
void_type                 2             224       0.290
integer_type             36            4032       5.221
real_type                 3             336       0.435
complex_type              4             448       0.580
vector_type              15            1680       2.175
boolean_type              1             112       0.145
pointer_type             14            1568       2.030
reference_type            1             112       0.145
array_type               17            1904       2.466
record_type              15            1680       2.175
function_type            51            5712       7.397
integer_cst              98            2352       3.046
function_decl           153              16k     22.190
label_decl                2             224       0.290
type_decl                37            4144       5.366
parm_decl                 2             224       0.290
result_decl               1             112       0.145
field_decl               15            1680       2.175
Total                  1067              75k

RTX                  Number            Bytes    % Total
expr_list             32515             508k      5.238
insn                  73229            2288k     23.595
jump_insn             16386            1024k     10.560
barrier                8194             128k      1.320
code_label             8195             512k      5.281
note                  16392             512k      5.282
set                   89614            1400k     14.437
use                       1               8       0.000
const_int               182            1456       0.015
const_double             21             672       0.007
const_vector             19             152       0.002
pc                        1               8       0.000
reg                   73234            1144k     11.798
mem                   49373             771k      7.954
label_ref             16386             256k      2.640
symbol_ref              390            3120       0.031
cc0                       1               8       0.000
if_then_else           8192             128k      1.320
compare                8192             128k      1.320
plus                  48906             764k      7.879
ior                       3              48       0.000
eq                        1              16       0.000
ge                     4096              64k      0.660
le                     4096              64k      0.660
Total                457619            9698k

Size   Allocated        Used    Overhead
8             36k       6560         828 
16          7408k       5356k        108k
32          4328k       2801k         46k
64          1568k       1566k         13k
112           48k         40k        384 
24            16k       5400         192 
Total         13M       9776k        170k

String pool
entries		478
identifiers	478 (100.00%)
slots		16384
bytes		4911  (3233  overhead)
table size	64k
coll/search	0.0167
ins/search	0.0280
avg. entry	10.27 bytes (+/- 5.84)
longest entry	36

??? tree nodes created

(No per-node statistics)
obstack permanent_obstack: 8 bytes, 1 chunks
Type hash: size 1021, 73 elements, 0.045902 collisions

Execution times (seconds)
 garbage collection    :   8.15 ( 8%) usr   0.03 ( 0%) sys  10.09 ( 7%) wall
 cfg construction      :   1.72 ( 2%) usr   0.15 ( 1%) sys   2.52 ( 2%) wall
 cfg cleanup           :   0.95 ( 1%) usr   0.00 ( 0%) sys   1.23 ( 1%) wall
 life analysis         :   4.36 ( 4%) usr   0.56 ( 5%) sys   5.86 ( 4%) wall
 life info update      :   2.19 ( 2%) usr   0.00 ( 0%) sys   2.42 ( 2%) wall
 preprocessing         :   1.46 ( 1%) usr   0.80 ( 7%) sys   2.89 ( 2%) wall
 lexical analysis      :   1.64 ( 2%) usr   2.20 (19%) sys   4.84 ( 3%) wall
 parser                :   9.45 ( 9%) usr   1.81 (15%) sys  13.14 ( 9%) wall
 expand                :   5.05 ( 5%) usr   1.27 (11%) sys   8.16 ( 6%) wall
 integration           :   1.36 ( 1%) usr   0.04 ( 0%) sys   1.59 ( 1%) wall
 jump                  :   1.50 ( 1%) usr   0.09 ( 1%) sys   2.00 ( 1%) wall
 flow analysis         :   0.96 ( 1%) usr   0.05 ( 0%) sys   1.58 ( 1%) wall
 local alloc           :  14.85 (15%) usr   0.71 ( 6%) sys  19.08 (13%) wall
 global alloc          :  29.85 (29%) usr   3.03 (26%) sys  42.05 (30%) wall
 shorten branches      :   1.35 ( 1%) usr   0.10 ( 1%) sys   2.03 ( 1%) wall
 final                 :   8.84 ( 9%) usr   0.75 ( 6%) sys  12.22 ( 9%) wall
 rest of compilation   :   7.77 ( 8%) usr   0.20 ( 2%) sys   9.83 ( 7%) wall
 TOTAL                 : 101.56            11.81           141.64
 
> -O1:
> 254.14user 3.45system 4:18.17elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (2745major+24005minor)pagefaults 0swaps

Tree                 Number            Bytes    % Total
error_mark                1              16       0.021
identifier_node         478              29k     39.615
tree_list               119            2856       3.698
tree_vec                  1              16       0.021
block                     1              64       0.083
void_type                 2             224       0.290
integer_type             36            4032       5.221
real_type                 3             336       0.435
complex_type              4             448       0.580
vector_type              15            1680       2.175
boolean_type              1             112       0.145
pointer_type             14            1568       2.030
reference_type            1             112       0.145
array_type               17            1904       2.466
record_type              15            1680       2.175
function_type            51            5712       7.397
integer_cst              98            2352       3.046
function_decl           153              16k     22.190
label_decl                2             224       0.290
type_decl                37            4144       5.366
parm_decl                 2             224       0.290
result_decl               1             112       0.145
field_decl               15            1680       2.175
Total                  1067              75k

RTX                  Number            Bytes    % Total
expr_list             33688             526k     15.435
insn_list              9169             143k      4.201
sequence               8194              64k      1.877
insn                  25497             796k     23.365
jump_insn              8194             512k     15.017
barrier                   2              32       0.001
code_label                5             320       0.009
note                   8293             259k      7.599
set                   25495             398k     11.681
use                       2              16       0.000
const_int               185            1480       0.042
const_double             21             672       0.019
const_vector             19             152       0.004
pc                        1               8       0.000
reg                   10553             164k      4.835
mem                     990              15k      0.454
label_ref              8194             128k      3.754
symbol_ref              390            3120       0.089
cc0                       1               8       0.000
if_then_else           8192             128k      3.753
compare                8192             128k      3.753
plus                    768              12k      0.352
ior                       3              48       0.001
eq                        1              16       0.000
ge                        1              16       0.000
gt                     4096              64k      1.877
lt                     4095              63k      1.876
Total                164241            3410k

Size   Allocated        Used    Overhead
8            104k         70k       2392 
16          3832k       1900k         56k
32          1288k       1056k         13k
64           740k        542k       6660 
112           48k         40k        384 
24            12k       5352         144 
Total       6024k       3616k         79k

String pool
entries		478
identifiers	478 (100.00%)
slots		16384
bytes		4910  (3234  overhead)
table size	64k
coll/search	0.0017
ins/search	0.0537
avg. entry	10.27 bytes (+/- 5.84)
longest entry	36

??? tree nodes created

(No per-node statistics)
obstack permanent_obstack: 8 bytes, 1 chunks
Type hash: size 1021, 73 elements, 0.045902 collisions

Execution times (seconds)
 garbage collection    :   3.32 ( 1%) usr   0.03 ( 0%) sys   6.31 ( 1%) wall
 cfg construction      :   1.81 ( 1%) usr   0.18 ( 2%) sys   3.80 ( 1%) wall
 cfg cleanup           :  75.42 (26%) usr   0.26 ( 3%) sys 148.66 (25%) wall
 life analysis         :  10.41 ( 4%) usr   0.11 ( 1%) sys  21.39 ( 4%) wall
 life info update      :   0.92 ( 0%) usr   0.00 ( 0%) sys   1.70 ( 0%) wall
 preprocessing         :   1.04 ( 0%) usr   0.71 ( 7%) sys   3.47 ( 1%) wall
 lexical analysis      :   1.72 ( 1%) usr   1.67 (17%) sys   5.92 ( 1%) wall
 parser                :   8.94 ( 3%) usr   1.76 (18%) sys  13.69 ( 2%) wall
 expand                :   2.72 ( 1%) usr   0.45 ( 5%) sys   4.58 ( 1%) wall
 integration           :   1.37 ( 0%) usr   0.07 ( 1%) sys   2.06 ( 0%) wall
 jump                  :   0.67 ( 0%) usr   0.08 ( 1%) sys   1.30 ( 0%) wall
 CSE                   :  21.03 ( 7%) usr   0.86 ( 9%) sys  45.58 ( 8%) wall
 loop analysis         :   0.04 ( 0%) usr   0.00 ( 0%) sys   0.05 ( 0%) wall
 flow analysis         :   2.65 ( 1%) usr   0.89 ( 9%) sys   8.48 ( 1%) wall
 combiner              :   2.60 ( 1%) usr   0.05 ( 1%) sys   6.00 ( 1%) wall
 if-conversion         :   0.71 ( 0%) usr   0.28 ( 3%) sys   1.64 ( 0%) wall
 local alloc           :   1.49 ( 1%) usr   0.06 ( 1%) sys   2.83 ( 0%) wall
 global alloc          :   3.46 ( 1%) usr   0.33 ( 3%) sys   7.56 ( 1%) wall
 reload CSE regs       :   3.46 ( 1%) usr   0.09 ( 1%) sys   6.64 ( 1%) wall
 flow 2                :   0.52 ( 0%) usr   0.00 ( 0%) sys   1.09 ( 0%) wall
 if-conversion 2       :   0.55 ( 0%) usr   0.27 ( 3%) sys   1.44 ( 0%) wall
 rename registers      :   1.90 ( 1%) usr   0.56 ( 6%) sys   4.67 ( 1%) wall
 delay branch sched    : 142.35 (48%) usr   0.74 ( 8%) sys 290.36 (48%) wall
 shorten branches      :   0.34 ( 0%) usr   0.01 ( 0%) sys   0.69 ( 0%) wall
 final                 :   2.71 ( 1%) usr   0.10 ( 1%) sys   6.00 ( 1%) wall
 rest of compilation   :   2.17 ( 1%) usr   0.04 ( 0%) sys   4.81 ( 1%) wall
 TOTAL                 : 294.42             9.61           600.95
 
> -O2:
> 
> 345.29user 9.24system 5:54.47elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (2796major+69498minor)pagefaults 0swaps

Tree                 Number            Bytes    % Total
error_mark                1              16       0.021
identifier_node         478              29k     39.615
tree_list               119            2856       3.698
tree_vec                  1              16       0.021
block                     1              64       0.083
void_type                 2             224       0.290
integer_type             36            4032       5.221
real_type                 3             336       0.435
complex_type              4             448       0.580
vector_type              15            1680       2.175
boolean_type              1             112       0.145
pointer_type             14            1568       2.030
reference_type            1             112       0.145
array_type               17            1904       2.466
record_type              15            1680       2.175
function_type            51            5712       7.397
integer_cst              98            2352       3.046
function_decl           153              16k     22.190
label_decl                2             224       0.290
type_decl                37            4144       5.366
parm_decl                 2             224       0.290
result_decl               1             112       0.145
field_decl               15            1680       2.175
Total                  1067              75k

RTX                  Number            Bytes    % Total
expr_list             36255             566k     15.222
insn_list             15407             240k      6.469
sequence               8193              64k      1.720
insn                  28127             878k     23.619
jump_insn              8193             512k     13.760
barrier                   1              16       0.000
code_label                4             256       0.007
note                   8202             256k      6.888
set                   28125             439k     11.809
use                       2              16       0.000
const_int               229            1832       0.048
const_double             21             672       0.018
const_vector             19             152       0.004
pc                        1               8       0.000
reg                    8284             129k      3.478
mem                    3818              59k      1.603
label_ref              8193             128k      3.440
symbol_ref              390            3120       0.082
cc0                       1               8       0.000
if_then_else           8192             128k      3.439
compare                8192             128k      3.439
plus                   3604              56k      1.513
ior                       3              48       0.001
eq                        1              16       0.000
ge                        1              16       0.000
gt                     4096              64k      1.720
lt                     4095              63k      1.719
Total                181649            3721k

Size   Allocated        Used    Overhead
8             72k         70k       1656 
16          4028k       2132k         59k
32          1288k       1135k         13k
64           804k        542k       7236 
112           48k         40k        384 
24            16k       6768         192 
Total       6256k       3928k         82k

String pool
entries		478
identifiers	478 (100.00%)
slots		16384
bytes		4910  (3234  overhead)
table size	64k
coll/search	0.0017
ins/search	0.0537
avg. entry	10.27 bytes (+/- 5.84)
longest entry	36

??? tree nodes created

(No per-node statistics)
obstack permanent_obstack: 8 bytes, 1 chunks
Type hash: size 1021, 73 elements, 0.059016 collisions

Execution times (seconds)
 garbage collection    :   4.35 ( 1%) usr   0.15 ( 1%) sys   7.94 ( 1%) wall
 cfg construction      :   3.99 ( 1%) usr   0.09 ( 1%) sys   8.02 ( 1%) wall
 cfg cleanup           :  73.49 (19%) usr   0.38 ( 2%) sys 157.02 (22%) wall
 life analysis         :  11.64 ( 3%) usr   0.72 ( 5%) sys  24.64 ( 3%) wall
 life info update      :   3.10 ( 1%) usr   0.05 ( 0%) sys   7.03 ( 1%) wall
 preprocessing         :   1.37 ( 0%) usr   0.66 ( 4%) sys   3.42 ( 0%) wall
 lexical analysis      :   1.79 ( 0%) usr   1.71 (11%) sys  10.08 ( 1%) wall
 parser                :   9.62 ( 2%) usr   1.49 ( 9%) sys  21.23 ( 3%) wall
 expand                :   3.07 ( 1%) usr   0.56 ( 4%) sys   7.64 ( 1%) wall
 integration           :   1.42 ( 0%) usr   0.12 ( 1%) sys   2.86 ( 0%) wall
 jump                  :  14.82 ( 4%) usr   0.93 ( 6%) sys  30.48 ( 4%) wall
 CSE                   :  29.15 ( 8%) usr   0.56 ( 4%) sys  58.06 ( 8%) wall
 global CSE            :   4.87 ( 1%) usr   1.50 ( 9%) sys  12.72 ( 2%) wall
 loop analysis         :   0.46 ( 0%) usr   0.00 ( 0%) sys   0.78 ( 0%) wall
 CSE 2                 :   3.86 ( 1%) usr   0.20 ( 1%) sys   7.77 ( 1%) wall
 flow analysis         :   2.73 ( 1%) usr   0.80 ( 5%) sys   6.80 ( 1%) wall
 combiner              :   2.14 ( 1%) usr   0.01 ( 0%) sys   4.44 ( 1%) wall
 if-conversion         :   0.69 ( 0%) usr   0.23 ( 1%) sys   2.08 ( 0%) wall
 regmove               :   0.83 ( 0%) usr   0.01 ( 0%) sys   1.62 ( 0%) wall
 scheduling            :   4.23 ( 1%) usr   3.28 (21%) sys  15.58 ( 2%) wall
 local alloc           :   2.01 ( 1%) usr   0.05 ( 0%) sys   4.22 ( 1%) wall
 global alloc          :  23.07 ( 6%) usr   0.66 ( 4%) sys  47.16 ( 6%) wall
 reload CSE regs       :   8.03 ( 2%) usr   0.30 ( 2%) sys  16.20 ( 2%) wall
 flow 2                :   0.67 ( 0%) usr   0.00 ( 0%) sys   1.55 ( 0%) wall
 if-conversion 2       :   0.58 ( 0%) usr   0.24 ( 2%) sys   1.95 ( 0%) wall
 peephole 2            :   0.89 ( 0%) usr   0.00 ( 0%) sys   1.64 ( 0%) wall
 rename registers      :   2.33 ( 1%) usr   0.48 ( 3%) sys   5.53 ( 1%) wall
 scheduling 2          :   3.00 ( 1%) usr   0.12 ( 1%) sys   6.19 ( 1%) wall
 delay branch sched    : 160.80 (42%) usr   0.29 ( 2%) sys 243.70 (33%) wall
 reorder blocks        :   0.38 ( 0%) usr   0.01 ( 0%) sys   0.56 ( 0%) wall
 shorten branches      :   0.34 ( 0%) usr   0.02 ( 0%) sys   0.42 ( 0%) wall
 final                 :   3.07 ( 1%) usr   0.18 ( 1%) sys   4.64 ( 1%) wall
 rest of compilation   :   2.34 ( 1%) usr   0.02 ( 0%) sys   4.55 ( 1%) wall
 TOTAL                 : 385.29            15.85           728.70

> -O3 -fomit-frame-pointer:
> 
> 352.51user 8.62system 6:01.28elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (2797major+69499minor)pagefaults 0swaps

Tree                 Number            Bytes    % Total
error_mark                1              16       0.021
identifier_node         478              29k     39.615
tree_list               119            2856       3.698
tree_vec                  1              16       0.021
block                     1              64       0.083
void_type                 2             224       0.290
integer_type             36            4032       5.221
real_type                 3             336       0.435
complex_type              4             448       0.580
vector_type              15            1680       2.175
boolean_type              1             112       0.145
pointer_type             14            1568       2.030
reference_type            1             112       0.145
array_type               17            1904       2.466
record_type              15            1680       2.175
function_type            51            5712       7.397
integer_cst              98            2352       3.046
function_decl           153              16k     22.190
label_decl                2             224       0.290
type_decl                37            4144       5.366
parm_decl                 2             224       0.290
result_decl               1             112       0.145
field_decl               15            1680       2.175
Total                  1067              75k

RTX                  Number            Bytes    % Total
expr_list             36255             566k     15.220
insn_list             15422             240k      6.474
sequence               8193              64k      1.720
insn                  28127             878k     23.616
jump_insn              8193             512k     13.758
barrier                   1              16       0.000
code_label                4             256       0.007
note                   8202             256k      6.887
set                   28125             439k     11.807
use                       2              16       0.000
const_int               229            1832       0.048
const_double             21             672       0.018
const_vector             19             152       0.004
pc                        1               8       0.000
reg                    8287             129k      3.479
mem                    3818              59k      1.603
label_ref              8193             128k      3.439
symbol_ref              390            3120       0.082
cc0                       1               8       0.000
if_then_else           8192             128k      3.439
compare                8192             128k      3.439
plus                   3604              56k      1.513
ior                      18             288       0.008
eq                        1              16       0.000
ge                        1              16       0.000
gt                     4096              64k      1.720
lt                     4095              63k      1.719
Total                181682            3721k

Size   Allocated        Used    Overhead
8             72k         70k       1656 
16          4028k       2132k         59k
32          1288k       1135k         13k
64           804k        542k       7236 
112           48k         40k        384 
24            16k       6768         192 
Total       6256k       3929k         82k

String pool
entries		478
identifiers	478 (100.00%)
slots		16384
bytes		4910  (3234  overhead)
table size	64k
coll/search	0.0017
ins/search	0.0537
avg. entry	10.27 bytes (+/- 5.84)
longest entry	36

??? tree nodes created

(No per-node statistics)
obstack permanent_obstack: 8 bytes, 1 chunks
Type hash: size 1021, 73 elements, 0.059016 collisions

Execution times (seconds)
 garbage collection    :   4.24 ( 1%) usr   0.17 ( 1%) sys   9.77 ( 1%) wall
 cfg construction      :   4.08 ( 1%) usr   0.32 ( 2%) sys   9.77 ( 1%) wall
 cfg cleanup           :  73.00 (18%) usr   0.21 ( 1%) sys 126.92 (13%) wall
 life analysis         :  11.01 ( 3%) usr   0.63 ( 4%) sys  29.56 ( 3%) wall
 life info update      :   3.62 ( 1%) usr   0.00 ( 0%) sys   9.48 ( 1%) wall
 preprocessing         :   1.33 ( 0%) usr   0.56 ( 3%) sys   2.69 ( 0%) wall
 lexical analysis      :   1.85 ( 0%) usr   1.71 (10%) sys   4.02 ( 0%) wall
 parser                :   8.25 ( 2%) usr   1.10 ( 7%) sys  13.88 ( 1%) wall
 expand                :   3.04 ( 1%) usr   0.43 ( 3%) sys   4.66 ( 0%) wall
 integration           :   1.36 ( 0%) usr   0.04 ( 0%) sys   2.19 ( 0%) wall
 jump                  :  15.68 ( 4%) usr   0.89 ( 5%) sys  40.12 ( 4%) wall
 CSE                   :  32.12 ( 8%) usr   0.90 ( 5%) sys  84.81 ( 9%) wall
 global CSE            :   5.53 ( 1%) usr   1.72 (10%) sys  19.34 ( 2%) wall
 loop analysis         :   0.46 ( 0%) usr   0.00 ( 0%) sys   1.02 ( 0%) wall
 CSE 2                 :   3.96 ( 1%) usr   0.10 ( 1%) sys   9.67 ( 1%) wall
 flow analysis         :   2.91 ( 1%) usr   0.95 ( 6%) sys   9.48 ( 1%) wall
 combiner              :   2.21 ( 1%) usr   0.08 ( 0%) sys   5.59 ( 1%) wall
 if-conversion         :   0.73 ( 0%) usr   0.27 ( 2%) sys   2.42 ( 0%) wall
 regmove               :   0.83 ( 0%) usr   0.01 ( 0%) sys   2.31 ( 0%) wall
 scheduling            :   4.03 ( 1%) usr   2.77 (17%) sys  16.55 ( 2%) wall
 local alloc           :   1.98 ( 0%) usr   0.04 ( 0%) sys   5.03 ( 1%) wall
 global alloc          :  22.84 ( 6%) usr   0.73 ( 4%) sys  60.56 ( 6%) wall
 reload CSE regs       :   7.93 ( 2%) usr   0.38 ( 2%) sys  20.97 ( 2%) wall
 flow 2                :   0.68 ( 0%) usr   0.01 ( 0%) sys   1.45 ( 0%) wall
 if-conversion 2       :   0.61 ( 0%) usr   0.29 ( 2%) sys   2.31 ( 0%) wall
 peephole 2            :   0.54 ( 0%) usr   0.00 ( 0%) sys   0.84 ( 0%) wall
 rename registers      :   6.11 ( 2%) usr   0.72 ( 4%) sys  16.67 ( 2%) wall
 scheduling 2          :   2.89 ( 1%) usr   0.16 ( 1%) sys   7.88 ( 1%) wall
 delay branch sched    : 168.02 (42%) usr   1.19 ( 7%) sys 428.19 (45%) wall
 reorder blocks        :   0.36 ( 0%) usr   0.00 ( 0%) sys   0.48 ( 0%) wall
 shorten branches      :   0.35 ( 0%) usr   0.02 ( 0%) sys   0.83 ( 0%) wall
 final                 :   2.97 ( 1%) usr   0.01 ( 0%) sys   7.58 ( 1%) wall
 rest of compilation   :   2.26 ( 1%) usr   0.02 ( 0%) sys   4.78 ( 0%) wall
 TOTAL                 : 397.94            16.53           962.12
 
> -O3 -g:
> 
> 629.73user 10.15system 10:39.86elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (2830major+69525minor)pagefaults 0swaps

Tree                 Number            Bytes    % Total
error_mark                1              16       0.021
identifier_node         479              29k     39.665
tree_list               119            2856       3.695
tree_vec                  1              16       0.021
block                     1              64       0.083
void_type                 2             224       0.290
integer_type             36            4032       5.217
real_type                 3             336       0.435
complex_type              4             448       0.580
vector_type              15            1680       2.174
boolean_type              1             112       0.145
pointer_type             14            1568       2.029
reference_type            1             112       0.145
array_type               17            1904       2.464
record_type              15            1680       2.174
function_type            51            5712       7.391
integer_cst              98            2352       3.043
function_decl           153              16k     22.172
label_decl                2             224       0.290
type_decl                37            4144       5.362
parm_decl                 2             224       0.290
result_decl               1             112       0.145
field_decl               15            1680       2.174
Total                  1068              75k

RTX                  Number            Bytes    % Total
expr_list             36255             566k     15.220
insn_list             15422             240k      6.474
sequence               8193              64k      1.720
insn                  28127             878k     23.615
jump_insn              8193             512k     13.758
barrier                   1              16       0.000
code_label                4             256       0.007
note                   8204             256k      6.889
set                   28125             439k     11.807
use                       2              16       0.000
const_int               229            1832       0.048
const_double             21             672       0.018
const_vector             19             152       0.004
pc                        1               8       0.000
reg                    8287             129k      3.479
mem                    3818              59k      1.603
label_ref              8193             128k      3.439
symbol_ref              390            3120       0.082
cc0                       1               8       0.000
if_then_else           8192             128k      3.439
compare                8192             128k      3.439
plus                   3604              56k      1.513
ior                      18             288       0.008
eq                        1              16       0.000
ge                        1              16       0.000
gt                     4096              64k      1.719
lt                     4095              63k      1.719
Total                181684            3722k

Size   Allocated        Used    Overhead
8             72k         70k       1656 
16          4028k       2132k         59k
32          1288k       1135k         13k
64           804k        542k       7236 
112           48k         40k        384 
24            16k       6768         192 
Total       6256k       3929k         82k

String pool
entries		479
identifiers	479 (100.00%)
slots		16384
bytes		4917  (3227  overhead)
table size	64k
coll/search	0.0019
ins/search	0.0536
avg. entry	10.27 bytes (+/- 5.84)
longest entry	36

??? tree nodes created

(No per-node statistics)
obstack permanent_obstack: 8 bytes, 1 chunks
Type hash: size 1021, 73 elements, 0.059016 collisions

Execution times (seconds)
 garbage collection    :   4.16 ( 1%) usr   0.10 ( 0%) sys   8.55 ( 1%) wall
 cfg construction      :   3.90 ( 1%) usr   0.22 ( 1%) sys   9.41 ( 1%) wall
 cfg cleanup           :  78.18 (11%) usr   0.66 ( 3%) sys 200.11 (13%) wall
 life analysis         :  11.26 ( 2%) usr   0.47 ( 2%) sys  27.27 ( 2%) wall
 life info update      :   3.87 ( 1%) usr   0.00 ( 0%) sys   8.94 ( 1%) wall
 preprocessing         :   1.55 ( 0%) usr   0.84 ( 3%) sys   4.83 ( 0%) wall
 lexical analysis      :   1.75 ( 0%) usr   1.79 ( 7%) sys  10.31 ( 1%) wall
 parser                :   9.52 ( 1%) usr   1.62 ( 7%) sys  20.31 ( 1%) wall
 expand                :   3.13 ( 0%) usr   0.32 ( 1%) sys   7.48 ( 0%) wall
 integration           :   1.40 ( 0%) usr   0.03 ( 0%) sys   2.62 ( 0%) wall
 jump                  :  14.79 ( 2%) usr   0.77 ( 3%) sys  38.97 ( 2%) wall
 CSE                   :  31.03 ( 4%) usr   0.96 ( 4%) sys  79.02 ( 5%) wall
 global CSE            :   4.68 ( 1%) usr   1.73 ( 7%) sys  16.23 ( 1%) wall
 loop analysis         :   0.45 ( 0%) usr   0.00 ( 0%) sys   1.03 ( 0%) wall
 CSE 2                 :   3.80 ( 1%) usr   0.14 ( 1%) sys  10.39 ( 1%) wall
 flow analysis         :   2.95 ( 0%) usr   0.83 ( 3%) sys   9.80 ( 1%) wall
 combiner              :   2.08 ( 0%) usr   0.13 ( 1%) sys   4.89 ( 0%) wall
 if-conversion         :   0.66 ( 0%) usr   0.29 ( 1%) sys   3.25 ( 0%) wall
 regmove               :   0.78 ( 0%) usr   0.03 ( 0%) sys   1.83 ( 0%) wall
 scheduling            : 149.54 (21%) usr   9.35 (39%) sys 398.84 (25%) wall
 local alloc           :   1.94 ( 0%) usr   0.04 ( 0%) sys   4.66 ( 0%) wall
 global alloc          :  24.15 ( 3%) usr   0.69 ( 3%) sys  54.11 ( 3%) wall
 reload CSE regs       :   7.83 ( 1%) usr   0.08 ( 0%) sys  15.12 ( 1%) wall
 flow 2                :   0.64 ( 0%) usr   0.00 ( 0%) sys   1.19 ( 0%) wall
 if-conversion 2       :   0.63 ( 0%) usr   0.25 ( 1%) sys   1.39 ( 0%) wall
 peephole 2            :   0.57 ( 0%) usr   0.00 ( 0%) sys   0.92 ( 0%) wall
 rename registers      :   4.67 ( 1%) usr   0.60 ( 2%) sys  10.73 ( 1%) wall
 scheduling 2          : 171.59 (24%) usr   1.20 ( 5%) sys 348.41 (22%) wall
 delay branch sched    : 163.74 (23%) usr   0.80 ( 3%) sys 272.09 (17%) wall
 reorder blocks        :   0.34 ( 0%) usr   0.03 ( 0%) sys   0.70 ( 0%) wall
 shorten branches      :   0.35 ( 0%) usr   0.09 ( 0%) sys   0.72 ( 0%) wall
 final                 :   3.05 ( 0%) usr   0.05 ( 0%) sys   5.88 ( 0%) wall
 symout                :   0.01 ( 0%) usr   0.00 ( 0%) sys   0.03 ( 0%) wall
 rest of compilation   :   2.15 ( 0%) usr   0.06 ( 0%) sys   4.67 ( 0%) wall
 TOTAL                 : 711.28            24.22          1585.28
 
> -Os:
> 
> 423.80user 12.99system 7:16.87elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (2796major+93248minor)pagefaults 0swaps

Tree                 Number            Bytes    % Total
error_mark                1              16       0.021
identifier_node         479              29k     39.665
tree_list               119            2856       3.695
tree_vec                  1              16       0.021
block                     1              64       0.083
void_type                 2             224       0.290
integer_type             36            4032       5.217
real_type                 3             336       0.435
complex_type              4             448       0.580
vector_type              15            1680       2.174
boolean_type              1             112       0.145
pointer_type             14            1568       2.029
reference_type            1             112       0.145
array_type               17            1904       2.464
record_type              15            1680       2.174
function_type            51            5712       7.391
integer_cst              98            2352       3.043
function_decl           153              16k     22.172
label_decl                2             224       0.290
type_decl                37            4144       5.362
parm_decl                 2             224       0.290
result_decl               1             112       0.145
field_decl               15            1680       2.174
Total                  1068              75k

RTX                  Number            Bytes    % Total
expr_list             36089             563k     15.234
insn_list             15085             235k      6.368
sequence               8193              64k      1.729
insn                  27967             873k     23.612
jump_insn              8193             512k     13.834
barrier                   1              16       0.000
code_label                4             256       0.007
note                   8202             256k      6.925
set                   27965             436k     11.805
use                       2              16       0.000
const_int               228            1824       0.048
const_double             21             672       0.018
const_vector             19             152       0.004
pc                        1               8       0.000
reg                    8289             129k      3.499
mem                    3659              57k      1.545
label_ref              8193             128k      3.459
symbol_ref              390            3120       0.082
cc0                       1               8       0.000
if_then_else           8192             128k      3.458
compare                8192             128k      3.458
plus                   3445              53k      1.454
ior                       3              48       0.001
eq                        1              16       0.000
ge                        1              16       0.000
gt                     4096              64k      1.729
lt                     4095              63k      1.729
Total                180527            3701k

Size   Allocated        Used    Overhead
8             72k         70k       1656 
16          4000k       2117k         58k
32          1288k       1130k         13k
64           804k        542k       7236 
112           48k         40k        384 
24            16k       6792         192 
Total       6228k       3908k         81k

String pool
entries		479
identifiers	479 (100.00%)
slots		16384
bytes		4927  (3217  overhead)
table size	64k
coll/search	0.0017
ins/search	0.0538
avg. entry	10.29 bytes (+/- 5.84)
longest entry	36

??? tree nodes created

(No per-node statistics)
obstack permanent_obstack: 8 bytes, 1 chunks
Type hash: size 1021, 73 elements, 0.059016 collisions

Execution times (seconds)
 garbage collection    :   4.32 ( 1%) usr   0.07 ( 0%) sys  11.06 ( 1%) wall
 cfg construction      :   3.54 ( 1%) usr   0.24 ( 1%) sys   8.95 ( 1%) wall
 cfg cleanup           :  77.18 (16%) usr   0.20 ( 1%) sys 197.12 (17%) wall
 life analysis         :  16.12 ( 3%) usr   0.89 ( 4%) sys  43.11 ( 4%) wall
 life info update      :   3.04 ( 1%) usr   0.00 ( 0%) sys   7.48 ( 1%) wall
 preprocessing         :   1.42 ( 0%) usr   0.79 ( 4%) sys   4.81 ( 0%) wall
 lexical analysis      :   1.65 ( 0%) usr   1.90 ( 9%) sys  10.98 ( 1%) wall
 parser                :   9.14 ( 2%) usr   1.27 ( 6%) sys  23.28 ( 2%) wall
 expand                :   3.09 ( 1%) usr   0.24 ( 1%) sys   8.61 ( 1%) wall
 integration           :   1.42 ( 0%) usr   0.16 ( 1%) sys   4.22 ( 0%) wall
 jump                  :  14.04 ( 3%) usr   0.65 ( 3%) sys  36.66 ( 3%) wall
 CSE                   :  26.66 ( 6%) usr   1.01 ( 5%) sys  68.30 ( 6%) wall
 global CSE            :  84.83 (18%) usr   6.52 (30%) sys 226.83 (19%) wall
 loop analysis         :   0.46 ( 0%) usr   0.00 ( 0%) sys   0.94 ( 0%) wall
 CSE 2                 :   4.18 ( 1%) usr   0.10 ( 0%) sys  10.33 ( 1%) wall
 flow analysis         :   2.74 ( 1%) usr   1.09 ( 5%) sys   9.41 ( 1%) wall
 combiner              :   2.22 ( 0%) usr   0.02 ( 0%) sys   5.23 ( 0%) wall
 if-conversion         :   0.66 ( 0%) usr   0.29 ( 1%) sys   2.55 ( 0%) wall
 regmove               :   0.81 ( 0%) usr   0.00 ( 0%) sys   1.88 ( 0%) wall
 scheduling            :   3.83 ( 1%) usr   3.89 (18%) sys  20.34 ( 2%) wall
 local alloc           :   2.15 ( 0%) usr   0.06 ( 0%) sys   5.84 ( 0%) wall
 global alloc          :  23.98 ( 5%) usr   0.54 ( 2%) sys  59.98 ( 5%) wall
 reload CSE regs       :   8.20 ( 2%) usr   0.09 ( 0%) sys  21.81 ( 2%) wall
 flow 2                :   0.70 ( 0%) usr   0.00 ( 0%) sys   1.66 ( 0%) wall
 if-conversion 2       :   0.51 ( 0%) usr   0.27 ( 1%) sys   1.75 ( 0%) wall
 peephole 2            :   0.54 ( 0%) usr   0.00 ( 0%) sys   1.12 ( 0%) wall
 rename registers      :   5.85 ( 1%) usr   0.35 ( 2%) sys  15.09 ( 1%) wall
 scheduling 2          :   3.13 ( 1%) usr   0.06 ( 0%) sys   7.84 ( 1%) wall
 delay branch sched    : 166.57 (35%) usr   0.62 ( 3%) sys 347.28 (29%) wall
 reorder blocks        :   0.35 ( 0%) usr   0.05 ( 0%) sys   0.86 ( 0%) wall
 shorten branches      :   0.38 ( 0%) usr   0.03 ( 0%) sys   1.02 ( 0%) wall
 final                 :   2.96 ( 1%) usr   0.40 ( 2%) sys   6.80 ( 1%) wall
 rest of compilation   :   2.17 ( 0%) usr   0.03 ( 0%) sys   5.22 ( 0%) wall
 TOTAL                 : 478.99            21.87          1178.80
 

Cheers,

/ChJ


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]