forked from BrianGladman/mpir
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtime.c
1537 lines (1295 loc) · 47.3 KB
/
time.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/* Time routines for speed measurments.
Copyright 1999, 2000, 2001, 2002, 2003, 2004 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
The GNU MP Library is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 2.1 of the License, or (at your
option) any later version.
The GNU MP Library is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
License for more details.
You should have received a copy of the GNU Lesser General Public License
along with the GNU MP Library; see the file COPYING.LIB. If not, write to
the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
MA 02110-1301, USA. */
/* Usage:
The code in this file implements the lowest level of time measuring,
simple one-time measuring of time between two points.
void speed_starttime (void)
double speed_endtime (void)
Call speed_starttime to start measuring, and then call speed_endtime
when done.
speed_endtime returns the time taken, in seconds. Or if the timebase
is in CPU cycles and the CPU frequency is unknown then speed_endtime
returns cycles. Applications can identify the cycles return by
checking for speed_cycletime (described below) equal to 1.0.
If some sort of temporary glitch occurs then speed_endtime returns
0.0. Currently this is for various cases where a negative time has
occurred. This unfortunately occurs with getrusage on some systems,
and with the hppa cycle counter on hpux.
double speed_cycletime
The time in seconds for each CPU cycle. For example on a 100 MHz CPU
this would be 1.0e-8.
If the CPU frequency is unknown, then speed_cycletime is either 0.0
or 1.0. It's 0.0 when speed_endtime is returning seconds, or it's
1.0 when speed_endtime is returning cycles.
It may be noted that "speed_endtime() / speed_cycletime" gives a
measured time in cycles, irrespective of whether speed_endtime is
returning cycles or seconds. (Assuming cycles can be had, ie. it's
either cycles already or the cpu frequency is known. See also
speed_cycletime_need_cycles below.)
double speed_unittime
The unit of time measurement accuracy for the timing method in use.
This is in seconds or cycles, as per speed_endtime.
char speed_time_string[]
A null-terminated string describing the time method in use.
void speed_time_init (void)
Initialize time measuring. speed_starttime() does this
automatically, so it's only needed if an application wants to inspect
the above global variables before making a measurement.
int speed_precision
The intended accuracy of time measurements. speed_measure() in
common.c for instance runs target routines with enough repetitions so
it takes at least "speed_unittime * speed_precision" (this expression
works for both cycles or seconds from speed_endtime).
A program can provide an option so the user to set speed_precision.
If speed_precision is zero when speed_time_init or speed_starttime
first run then it gets a default based on the measuring method
chosen. (More precision for higher accuracy methods.)
void speed_cycletime_need_seconds (void)
Call this to demand that speed_endtime will return seconds, and not
cycles. If only cycles are available then an error is printed and
the program exits.
void speed_cycletime_need_cycles (void)
Call this to demand that speed_cycletime is non-zero, so that
"speed_endtime() / speed_cycletime" will give times in cycles.
Notes:
Various combinations of cycle counter, read_real_time(), getrusage(),
gettimeofday() and times() can arise, according to which are available
and their precision.
Allowing speed_endtime() to return either seconds or cycles is only a
slight complication and makes it possible for the speed program to do
some sensible things without demanding the CPU frequency. If seconds are
being measured then it can always print seconds, and if cycles are being
measured then it can always print them without needing to know how long
they are. Also the tune program doesn't care at all what the units are.
GMP_CPU_FREQUENCY can always be set when the automated methods in freq.c
fail. This will be needed if times in seconds are wanted but a cycle
counter is being used, or if times in cycles are wanted but getrusage or
another seconds based timer is in use.
If the measuring method uses a cycle counter but supplements it with
getrusage or the like, then knowing the CPU frequency is mandatory since
the code compares values from the two.
Not done:
Solaris gethrtime() seems no more than a slow way to access the Sparc V9
cycle counter. gethrvtime() seems to be relevant only to light weight
processes, it doesn't for instance give nanosecond virtual time. So
neither of these are used.
Bugs:
getrusage_microseconds_p is fundamentally flawed, getrusage and
gettimeofday can have resolutions other than clock ticks or microseconds,
for instance IRIX 5 has a tick of 10 ms but a getrusage of 1 ms.
Enhancements:
The SGI hardware counter has 64 bits on some machines, which could be
used when available. But perhaps 32 bits is enough range, and then rely
on the getrusage supplement.
Maybe getrusage (or times) should be used as a supplement for any
wall-clock measuring method. Currently a wall clock with a good range
(eg. a 64-bit cycle counter) is used without a supplement.
On PowerPC the timebase registers could be used, but would have to do
something to find out the speed. On 6xx chips it's normally 1/4 bus
speed, on 4xx chips it's either that or an external clock. Measuring
against gettimeofday might be ok. */
#include "config.h"
#include <errno.h>
#include <setjmp.h>
#include <signal.h>
#include <stddef.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h> /* for getenv() */
#if HAVE_FCNTL_H
#include <fcntl.h> /* for open() */
#endif
#if HAVE_STDINT_H
#include <stdint.h> /* for uint64_t */
#endif
#if HAVE_UNISTD_H
#include <unistd.h> /* for sysconf() */
#endif
#include <sys/types.h>
#if TIME_WITH_SYS_TIME
# include <sys/time.h> /* for struct timeval */
# include <time.h>
#else
# if HAVE_SYS_TIME_H
# include <sys/time.h>
# else
# include <time.h>
# endif
#endif
#if HAVE_SYS_MMAN_H
#include <sys/mman.h> /* for mmap() */
#endif
#if HAVE_SYS_RESOURCE_H
#include <sys/resource.h> /* for struct rusage */
#endif
#if HAVE_SYS_SYSTEMCFG_H
#include <sys/systemcfg.h> /* for RTC_POWER on AIX */
#endif
#if HAVE_SYS_TIMES_H
#include <sys/times.h> /* for times() and struct tms */
#endif
#include "mpir.h"
#include "gmp-impl.h"
#if 1 && defined( _MSC_VER)
#define HAVE_GETRUSAGE 1
#define HAVE_GETTIMEOFDAY 1
#include "getrusage.h"
#include "gettimeofday.h"
#endif
#include "speed.h"
/* strerror is only used for some stuff on newish systems, no need to have a
proper replacement */
#if ! HAVE_STRERROR
#define strerror(n) "<strerror not available>"
#endif
char speed_time_string[256];
int speed_precision = 0;
double speed_unittime;
double speed_cycletime = 0.0;
/* don't rely on "unsigned" to "double" conversion, it's broken in SunOS 4
native cc */
#define M_2POWU (((double) INT_MAX + 1.0) * 2.0)
#define M_2POW32 4294967296.0
#define M_2POW64 (M_2POW32 * M_2POW32)
/* Conditionals for the time functions available are done with normal C
code, which is a lot easier than wildly nested preprocessor directives.
The choice of what to use is partly made at run-time, according to
whether the cycle counter works and the measured accuracy of getrusage
and gettimeofday.
A routine that's not available won't be getting called, but is an abort()
to be sure it isn't called mistakenly.
It can be assumed that if a function exists then its data type will, but
if the function doesn't then the data type might or might not exist, so
the type can't be used unconditionally. The "struct_rusage" etc macros
provide dummies when the respective function doesn't exist. */
#if HAVE_SPEED_CYCLECOUNTER
static const int have_cycles = HAVE_SPEED_CYCLECOUNTER;
#else
static const int have_cycles = 0;
#define speed_cyclecounter(p) ASSERT_FAIL (speed_cyclecounter not available)
#endif
/* "stck" returns ticks since 1 Jan 1900 00:00 GMT, where each tick is 2^-12
microseconds. Same #ifdefs here as in longlong.h. */
#if defined (__GNUC__) && (defined (__i370__) || defined (__s390__) || defined (__mvs__))
static const int have_stck = 1;
static const int use_stck = 1; /* always use when available */
typedef uint64_t stck_t; /* gcc for s390 is quite new, always has uint64_t */
#define STCK(timestamp) \
do { \
asm ("stck %0" : "=m" (timestamp)); \
} while (0)
#else
static const int have_stck = 0;
static const int use_stck = 0;
typedef unsigned long stck_t; /* dummy */
#define STCK(timestamp) ASSERT_FAIL (stck instruction not available)
#endif
#define STCK_PERIOD (1.0 / 4096e6) /* 2^-12 microseconds */
/* mftb
Enhancement: On 64-bit chips mftb gives a 64-bit value, no need for mftbu
and a loop (see powerpc64.asm). */
#if HAVE_HOST_CPU_FAMILY_powerpc
static const int have_mftb = 1;
#if defined (__GNUC__)
#define MFTB(a) \
do { \
unsigned __h1, __l, __h2; \
do { \
asm volatile ("mftbu %0\n" \
"mftb %1\n" \
"mftbu %2" \
: "=r" (__h1), \
"=r" (__l), \
"=r" (__h2)); \
} while (__h1 != __h2); \
a[0] = __l; \
a[1] = __h1; \
} while (0)
#else
#define MFTB(a) mftb_function (a)
#endif
#else /* ! powerpc */
static const int have_mftb = 0;
#define MFTB(a) \
do { \
a[0] = 0; \
a[1] = 0; \
ASSERT_FAIL (mftb not available); \
} while (0)
#endif
/* Unicos 10.X has syssgi(), but not mmap(). */
#if HAVE_SYSSGI && HAVE_MMAP
static const int have_sgi = 1;
#else
static const int have_sgi = 0;
#endif
#if HAVE_READ_REAL_TIME
static const int have_rrt = 1;
#else
static const int have_rrt = 0;
#define read_real_time(t,s) ASSERT_FAIL (read_real_time not available)
#define time_base_to_time(t,s) ASSERT_FAIL (time_base_to_time not available)
#define RTC_POWER 1
#define RTC_POWER_PC 2
#define timebasestruct_t struct timebasestruct_dummy
struct timebasestruct_dummy {
int flag;
unsigned int tb_high;
unsigned int tb_low;
};
#endif
#if HAVE_CLOCK_GETTIME
static const int have_cgt = 1;
#define struct_timespec struct timespec
#else
static const int have_cgt = 0;
#define struct_timespec struct timespec_dummy
#define clock_gettime(id,ts) (ASSERT_FAIL (clock_gettime not available), -1)
#define clock_getres(id,ts) (ASSERT_FAIL (clock_getres not available), -1)
#endif
#if HAVE_GETRUSAGE
static const int have_grus = 1;
#define struct_rusage struct rusage
#else
static const int have_grus = 0;
#define getrusage(n,ru) ASSERT_FAIL (getrusage not available)
#define struct_rusage struct rusage_dummy
#endif
#if HAVE_GETTIMEOFDAY
static const int have_gtod = 1;
#define struct_timeval struct timeval
#else
static const int have_gtod = 0;
#define gettimeofday(tv,tz) ASSERT_FAIL (gettimeofday not available)
#define struct_timeval struct timeval_dummy
#endif
#if HAVE_TIMES
static const int have_times = 1;
#define struct_tms struct tms
#else
static const int have_times = 0;
#define times(tms) ASSERT_FAIL (times not available)
#define struct_tms struct tms_dummy
#endif
struct tms_dummy {
long tms_utime;
};
struct timeval_dummy {
long tv_sec;
long tv_usec;
};
struct rusage_dummy {
struct_timeval ru_utime;
};
struct timespec_dummy {
long tv_sec;
long tv_nsec;
};
static int use_cycles;
static int use_mftb;
static int use_sgi;
static int use_rrt;
static int use_cgt;
static int use_gtod;
static int use_grus;
static int use_times;
static int use_tick_boundary;
static unsigned start_cycles[2];
static stck_t start_stck;
static unsigned start_mftb[2];
static unsigned start_sgi;
static timebasestruct_t start_rrt;
static struct_timespec start_cgt;
static struct_rusage start_grus;
static struct_timeval start_gtod;
static struct_tms start_times;
static double cycles_limit = 1e100;
static double mftb_unittime;
static double sgi_unittime;
static double cgt_unittime;
static double grus_unittime;
static double gtod_unittime;
static double times_unittime;
/* for RTC_POWER format, ie. seconds and nanoseconds */
#define TIMEBASESTRUCT_SECS(t) ((t)->tb_high + (t)->tb_low * 1e-9)
/* Return a string representing a time in seconds, nicely formatted.
Eg. "10.25ms". */
char *
unittime_string (double t)
{
static char buf[128];
const char *unit;
int prec;
/* choose units and scale */
if (t < 1e-6)
t *= 1e9, unit = "ns";
else if (t < 1e-3)
t *= 1e6, unit = "us";
else if (t < 1.0)
t *= 1e3, unit = "ms";
else
unit = "s";
/* want 4 significant figures */
if (t < 1.0)
prec = 4;
else if (t < 10.0)
prec = 3;
else if (t < 100.0)
prec = 2;
else
prec = 1;
sprintf (buf, "%.*f%s", prec, t, unit);
return buf;
}
static jmp_buf cycles_works_buf;
static void
cycles_works_handler (int sig)
{
longjmp (cycles_works_buf, 1);
}
int
cycles_works_p (void)
{
static int result = -1;
if (result != -1)
goto done;
#ifdef SIGILL
{
void (*old_handler)(int);
unsigned cycles[2];
old_handler = signal (SIGILL, cycles_works_handler);
if (old_handler == SIG_ERR)
{
if (speed_option_verbose)
printf ("cycles_works_p(): SIGILL not supported, assuming speed_cyclecounter() works\n");
goto yes;
}
if (setjmp (cycles_works_buf))
{
if (speed_option_verbose)
printf ("cycles_works_p(): SIGILL during speed_cyclecounter(), so doesn't work\n");
result = 0;
goto done;
}
speed_cyclecounter (cycles);
signal (SIGILL, old_handler);
if (speed_option_verbose)
printf ("cycles_works_p(): speed_cyclecounter() works\n");
}
#else
if (speed_option_verbose)
printf ("cycles_works_p(): SIGILL not defined, assuming speed_cyclecounter() works\n");
goto yes;
#endif
yes:
result = 1;
done:
return result;
}
/* The number of clock ticks per second, but looking at sysconf rather than
just CLK_TCK, where possible. */
long
clk_tck (void)
{
static long result = -1L;
if (result != -1L)
return result;
#if HAVE_SYSCONF
result = sysconf (_SC_CLK_TCK);
if (result != -1L)
{
if (speed_option_verbose)
printf ("sysconf(_SC_CLK_TCK) is %ld per second\n", result);
return result;
}
fprintf (stderr,
"sysconf(_SC_CLK_TCK) not working, using CLK_TCK instead\n");
#endif
#ifdef CLK_TCK
result = CLK_TCK;
if (speed_option_verbose)
printf ("CLK_TCK is %ld per second\n", result);
return result;
#else
fprintf (stderr, "CLK_TCK not defined, cannot continue\n");
abort ();
#endif
}
/* If two times can be observed less than half a clock tick apart, then
assume "get" is microsecond accurate.
Two times only 1 microsecond apart are not believed, since some kernels
take it upon themselves to ensure gettimeofday doesn't return the same
value twice, for the benefit of applications using it for a timestamp.
This is obviously very stupid given the speed of CPUs these days.
Making "reps" many calls to noop_1() is designed to waste some CPU, with
a view to getting measurements 2 microseconds (or more) apart. "reps" is
increased progressively until such a period is seen.
The outer loop "attempts" are just to allow for any random nonsense or
system load upsetting the measurements (ie. making two successive calls
to "get" come out as a longer interval than normal).
Bugs:
The assumption that any interval less than a half tick implies
microsecond resolution is obviously fairly rash, the true resolution
could be anything between a microsecond and that half tick. Perhaps
something special would have to be done on a system where this is the
case, since there's no obvious reliable way to detect it
automatically. */
#define MICROSECONDS_P(name, type, get, sec, usec) \
{ \
static int result = -1; \
type st, et; \
long dt, half_tick; \
unsigned attempt, reps, i, j; \
\
if (result != -1) \
return result; \
\
result = 0; \
half_tick = (1000000L / clk_tck ()) / 2; \
\
for (attempt = 0; attempt < 5; attempt++) \
{ \
reps = 0; \
for (;;) \
{ \
get (st); \
for (i = 0; i < reps; i++) \
for (j = 0; j < 100; j++) \
noop_1 (CNST_LIMB(0)); \
get (et); \
\
dt = (sec(et)-sec(st))*1000000L + usec(et)-usec(st); \
\
if (speed_option_verbose >= 2) \
printf ("%s attempt=%u, reps=%u, dt=%ld\n", \
name, attempt, reps, dt); \
\
if (dt >= 2) \
break; \
\
reps = (reps == 0 ? 1 : 2*reps); \
if (reps == 0) \
break; /* uint overflow, not normal */ \
} \
\
if (dt < half_tick) \
{ \
result = 1; \
break; \
} \
} \
\
if (speed_option_verbose) \
{ \
if (result) \
printf ("%s is microsecond accurate\n", name); \
else \
printf ("%s is only %s clock tick accurate\n", \
name, unittime_string (1.0/clk_tck())); \
} \
return result; \
}
int
gettimeofday_microseconds_p (void)
{
#define call_gettimeofday(t) gettimeofday (&(t), NULL)
#define timeval_tv_sec(t) ((t).tv_sec)
#define timeval_tv_usec(t) ((t).tv_usec)
MICROSECONDS_P ("gettimeofday", struct_timeval,
call_gettimeofday, timeval_tv_sec, timeval_tv_usec);
}
int
getrusage_microseconds_p (void)
{
#define call_getrusage(t) getrusage (0, &(t))
#define rusage_tv_sec(t) ((t).ru_utime.tv_sec)
#define rusage_tv_usec(t) ((t).ru_utime.tv_usec)
MICROSECONDS_P ("getrusage", struct_rusage,
call_getrusage, rusage_tv_sec, rusage_tv_usec);
}
/* Test whether getrusage goes backwards, return non-zero if it does
(suggesting it's flawed).
On a macintosh m68040-unknown-netbsd1.4.1 getrusage looks like it's
microsecond accurate, but has been seen remaining unchanged after many
microseconds have elapsed. It also regularly goes backwards by 1000 to
5000 usecs, this has been seen after between 500 and 4000 attempts taking
perhaps 0.03 seconds. We consider this too broken for good measuring.
We used to have configure pretend getrusage didn't exist on this system,
but a runtime test should be more reliable, since we imagine the problem
is not confined to just this exact system tuple. */
int
getrusage_backwards_p (void)
{
static int result = -1;
struct_rusage start, prev, next;
long d;
int i;
if (result != -1)
return result;
getrusage (0, &start);
memcpy (&next, &start, sizeof (next));
result = 0;
i = 0;
for (;;)
{
memcpy (&prev, &next, sizeof (prev));
getrusage (0, &next);
if (next.ru_utime.tv_sec < prev.ru_utime.tv_sec
|| (next.ru_utime.tv_sec == prev.ru_utime.tv_sec
&& next.ru_utime.tv_usec < prev.ru_utime.tv_usec))
{
if (speed_option_verbose)
printf ("getrusage went backwards (attempt %d: %ld.%06ld -> %ld.%06ld)\n",
i,
prev.ru_utime.tv_sec, prev.ru_utime.tv_usec,
next.ru_utime.tv_sec, next.ru_utime.tv_usec);
result = 1;
break;
}
/* minimum 1000 attempts, then stop after either 0.1 seconds or 50000
attempts, whichever comes first */
d = 1000000 * (next.ru_utime.tv_sec - start.ru_utime.tv_sec)
+ (next.ru_utime.tv_usec - start.ru_utime.tv_usec);
i++;
if (i > 50000 || (i > 1000 && d > 100000))
break;
}
return result;
}
/* CLOCK_PROCESS_CPUTIME_ID looks like it's going to be in a future version
of glibc (some time post 2.2).
CLOCK_VIRTUAL is process time, available in BSD systems (though sometimes
defined, but returning -1 for an error). */
#ifdef CLOCK_PROCESS_CPUTIME_ID
# define CGT_ID CLOCK_PROCESS_CPUTIME_ID
#else
# ifdef CLOCK_VIRTUAL
# define CGT_ID CLOCK_VIRTUAL
# endif
#endif
#ifdef CGT_ID
const int have_cgt_id = 1;
#else
const int have_cgt_id = 0;
# define CGT_ID (ASSERT_FAIL (CGT_ID not determined), -1)
#endif
int
cgt_works_p (void)
{
static int result = -1;
struct_timespec unit;
if (! have_cgt)
return 0;
if (! have_cgt_id)
{
if (speed_option_verbose)
printf ("clock_gettime don't know what ID to use\n");
result = 0;
return result;
}
if (result != -1)
return result;
/* trial run to see if it works */
if (clock_gettime (CGT_ID, &unit) != 0)
{
if (speed_option_verbose)
printf ("clock_gettime id=%d error: %s\n", CGT_ID, strerror (errno));
result = 0;
return result;
}
/* get the resolution */
if (clock_getres (CGT_ID, &unit) != 0)
{
if (speed_option_verbose)
printf ("clock_getres id=%d error: %s\n", CGT_ID, strerror (errno));
result = 0;
return result;
}
cgt_unittime = unit.tv_sec + unit.tv_nsec * 1e-9;
printf ("clock_gettime is %s accurate\n",
unittime_string (cgt_unittime));
result = 1;
return result;
}
static double
freq_measure_mftb_one (void)
{
#define call_gettimeofday(t) gettimeofday (&(t), NULL)
#define timeval_tv_sec(t) ((t).tv_sec)
#define timeval_tv_usec(t) ((t).tv_usec)
FREQ_MEASURE_ONE ("mftb", struct_timeval,
call_gettimeofday, MFTB,
timeval_tv_sec, timeval_tv_usec);
}
static jmp_buf mftb_works_buf;
static void
mftb_works_handler (int sig)
{
longjmp (mftb_works_buf, 1);
}
int
mftb_works_p (void)
{
unsigned a[2];
void (*old_handler)(int);
double cycletime;
/* suppress a warning about a[] unused */
a[0] = 0;
if (! have_mftb)
return 0;
#ifdef SIGILL
old_handler = signal (SIGILL, mftb_works_handler);
if (old_handler == SIG_ERR)
{
if (speed_option_verbose)
printf ("mftb_works_p(): SIGILL not supported, assuming mftb works\n");
return 1;
}
if (setjmp (mftb_works_buf))
{
if (speed_option_verbose)
printf ("mftb_works_p(): SIGILL during mftb, so doesn't work\n");
return 0;
}
MFTB (a);
signal (SIGILL, old_handler);
if (speed_option_verbose)
printf ("mftb_works_p(): mftb works\n");
#else
if (speed_option_verbose)
printf ("mftb_works_p(): SIGILL not defined, assuming mftb works\n");
#endif
#if ! HAVE_GETTIMEOFDAY
if (speed_option_verbose)
printf ("mftb_works_p(): no gettimeofday available to measure mftb\n");
return 0;
#endif
/* The time base is normally 1/4 of the bus speed on 6xx and 7xx chips, on
other chips it can be driven from an external clock. */
cycletime = freq_measure ("mftb", freq_measure_mftb_one);
if (cycletime == -1.0)
{
if (speed_option_verbose)
printf ("mftb_works_p(): cannot measure mftb period\n");
return 0;
}
mftb_unittime = cycletime;
return 1;
}
volatile unsigned *sgi_addr;
int
sgi_works_p (void)
{
#if HAVE_SYSSGI && HAVE_MMAP
static int result = -1;
size_t pagesize, offset;
__psunsigned_t phys, physpage;
void *virtpage;
unsigned period_picoseconds;
int size, fd;
if (result != -1)
return result;
phys = syssgi (SGI_QUERY_CYCLECNTR, &period_picoseconds);
if (phys == (__psunsigned_t) -1)
{
/* ENODEV is the error when a counter is not available */
if (speed_option_verbose)
printf ("syssgi SGI_QUERY_CYCLECNTR error: %s\n", strerror (errno));
result = 0;
return result;
}
sgi_unittime = period_picoseconds * 1e-12;
/* IRIX 5 doesn't have SGI_CYCLECNTR_SIZE, assume 32 bits in that case.
Challenge/ONYX hardware has a 64 bit byte counter, but there seems no
obvious way to identify that without SGI_CYCLECNTR_SIZE. */
#ifdef SGI_CYCLECNTR_SIZE
size = syssgi (SGI_CYCLECNTR_SIZE);
if (size == -1)
{
if (speed_option_verbose)
{
printf ("syssgi SGI_CYCLECNTR_SIZE error: %s\n", strerror (errno));
printf (" will assume size==4\n");
}
size = 32;
}
#else
size = 32;
#endif
if (size < 32)
{
printf ("syssgi SGI_CYCLECNTR_SIZE gives %d, expected 32 or 64\n", size);
result = 0;
return result;
}
pagesize = getpagesize();
offset = (size_t) phys & (pagesize-1);
physpage = phys - offset;
/* shouldn't cross over a page boundary */
ASSERT_ALWAYS (offset + size/8 <= pagesize);
fd = open("/dev/mmem", O_RDONLY);
if (fd == -1)
{
if (speed_option_verbose)
printf ("open /dev/mmem: %s\n", strerror (errno));
result = 0;
return result;
}
virtpage = mmap (0, pagesize, PROT_READ, MAP_PRIVATE, fd, (off_t) physpage);
if (virtpage == (void *) -1)
{
if (speed_option_verbose)
printf ("mmap /dev/mmem: %s\n", strerror (errno));
result = 0;
return result;
}
/* address of least significant 4 bytes, knowing mips is big endian */
sgi_addr = (unsigned *) ((char *) virtpage + offset
+ size/8 - sizeof(unsigned));
result = 1;
return result;
#else /* ! (HAVE_SYSSGI && HAVE_MMAP) */
return 0;
#endif
}
#define DEFAULT(var,n) \
do { \
if (! (var)) \
(var) = (n); \
} while (0)
void
speed_time_init (void)
{
double supplement_unittime = 0.0;
static int speed_time_initialized = 0;
if (speed_time_initialized)
return;
speed_time_initialized = 1;
speed_cycletime_init ();
if (have_cycles && cycles_works_p ())
{
use_cycles = 1;
DEFAULT (speed_cycletime, 1.0);
speed_unittime = speed_cycletime;
DEFAULT (speed_precision, 1000000);
strcpy (speed_time_string, "CPU cycle counter");
/* only used if a supplementary method is chosen below */
cycles_limit = (have_cycles == 1 ? M_2POW32 : M_2POW64) / 2.0
* speed_cycletime;
if (have_grus && getrusage_microseconds_p() && ! getrusage_backwards_p())
{
/* this is a good combination */
use_grus = 1;
supplement_unittime = grus_unittime = 1.0e-6;
strcpy (speed_time_string, "CPU cycle counter, supplemented by microsecond getrusage()");
}
else if (have_cycles == 1)
{
/* When speed_cyclecounter has a limited range, look for something
to supplement it. */
if (have_gtod && gettimeofday_microseconds_p())
{
use_gtod = 1;
supplement_unittime = gtod_unittime = 1.0e-6;
strcpy (speed_time_string, "CPU cycle counter, supplemented by microsecond gettimeofday()");
}
else if (have_grus)
{
use_grus = 1;
supplement_unittime = grus_unittime = 1.0 / (double) clk_tck ();
sprintf (speed_time_string, "CPU cycle counter, supplemented by %s clock tick getrusage()", unittime_string (supplement_unittime));
}
else if (have_times)
{
use_times = 1;
supplement_unittime = times_unittime = 1.0 / (double) clk_tck ();
sprintf (speed_time_string, "CPU cycle counter, supplemented by %s clock tick times()", unittime_string (supplement_unittime));
}
else if (have_gtod)
{
use_gtod = 1;
supplement_unittime = gtod_unittime = 1.0 / (double) clk_tck ();
sprintf (speed_time_string, "CPU cycle counter, supplemented by %s clock tick gettimeofday()", unittime_string (supplement_unittime));
}
else
{
fprintf (stderr, "WARNING: cycle counter is 32 bits and there's no other functions.\n");
fprintf (stderr, " Wraparounds may produce bad results on long measurements.\n");
}
}