diff options
| -rw-r--r-- | ChangeLog | 17 | ||||
| -rw-r--r-- | manual/probes.texi | 98 | ||||
| -rw-r--r-- | sysdeps/ieee754/dbl-64/e_atan2.c | 7 | ||||
| -rw-r--r-- | sysdeps/ieee754/dbl-64/e_log.c | 7 | ||||
| -rw-r--r-- | sysdeps/ieee754/dbl-64/s_atan.c | 7 | ||||
| -rw-r--r-- | sysdeps/ieee754/dbl-64/s_tan.c | 2 | ||||
| -rw-r--r-- | sysdeps/ieee754/dbl-64/slowexp.c | 13 | ||||
| -rw-r--r-- | sysdeps/ieee754/dbl-64/slowpow.c | 14 |
8 files changed, 160 insertions, 5 deletions
@@ -1,3 +1,20 @@ +2013-10-11 Siddhesh Poyarekar <siddhesh@redhat.com> + Jeff Law <law@redhat.com> + + * sysdeps/ieee754/dbl-64/e_atan2.c: Include stap-probe.h. + (atan2Mp): Add systemtap probe marker. + * sysdeps/ieee754/dbl-64/e_log.c: include stap-probe.h. + (__ieee754_log): Add systemtap probe marker. + * sysdeps/ieee754/dbl-64/s_atan.c: Include stap-probe.h. + (atanMp): Add systemtap probe marker. + * sysdeps/ieee754/dbl-64/s_tan.c: Include stap-probe.h. + (tanMp): Add systemtap probe marker. + * sysdeps/ieee754/dbl-64/slowexp.c: Include stap-probe.h. + (__slowexp): Add systemtap probe marker. + * sysdeps/ieee754/dbl-64/slowpow.c: Include stap-probe.h. + (__slowpow): Add systemtap probe marker. + * manual/probes.texi: Document probes. + 2013-10-11 Eric Biggers <ebiggers3@gmail.com> [BZ #15362] diff --git a/manual/probes.texi b/manual/probes.texi index 1a45c69b91..5492bb79ff 100644 --- a/manual/probes.texi +++ b/manual/probes.texi @@ -16,6 +16,7 @@ arguments. @menu * Memory Allocation Probes:: Probes in the memory allocation subsystem +* Mathematical Function Probes:: Probes in mathematical functions @end menu @node Memory Allocation Probes @@ -255,3 +256,100 @@ This probe is triggered when function @code{free} decides to adjust the dynamic brk/mmap thresholds. Argument @var{$arg1} and @var{$arg2} are the adjusted mmap and trim thresholds, respectively. @end deftp + +@node Mathematical Function Probes +@section Mathematical Function Probes + +Some mathematical functions fall back to multiple precision arithmetic for +some inputs to get last bit precision for their return values. This multiple +precision fallback is much slower than the default algorithms and may have a +significant impact on application performance. The systemtap probe markers +described in this section may help you determine if your application calls +mathematical functions with inputs that may result in multiple-precision +arithmetic. + +Unless explicitly mentioned otherwise, a precision of 1 implies 24 bits of +precision in the mantissa of the multiple precision number. Hence, a precision +level of 32 implies 768 bits of precision in the mantissa. + +@deftp Probe slowexp_p6 (double @var{$arg1}, double @var{$arg2}) +This probe is hit when the @code{exp} function is called with an input that +results in multiple precision computation with precision 6. Argument +@var{$arg1} is the input value and @var{$arg2} is the computed output. +@end deftp + +@deftp Probe slowexp_p32 (double @var{$arg1}, double @var{$arg2}) +This probe is hit when the @code{exp} function is called with an input that +results in multiple precision computation with precision 32. Argument +@var{$arg1} is the input value and @var{$arg2} is the computed output. +@end deftp + +@deftp Probe slowpow_p10 (double @var{$arg1}, double @var{$arg2}, double @var{$arg3}, double @var{$arg4}) +This probe is hit when the @code{pow} function is called with inputs that +result in multiple precision computation with precision 10. Arguments +@var{$arg1} and @var{$arg2} are the input values, @code{$arg3} is the value +computed in the fast phase of the algorithm and @code{$arg4} is the final +accurate value. +@end deftp + +@deftp Probe slowpow_p32 (double @var{$arg1}, double @var{$arg2}, double @var{$arg3}, double @var{$arg4}) +This probe is hit when the @code{pow} function is called with an input that +results in multiple precision computation with precision 32. Arguments +@var{$arg1} and @var{$arg2} are the input values, @code{$arg3} is the value +computed in the fast phase of the algorithm and @code{$arg4} is the final +accurate value. +@end deftp + +@deftp Probe slowlog (int @var{$arg1}, double @var{$arg2}, double @var{$arg3}) +This probe is hit when the @code{log} function is called with an input that +results in multiple precision computation. Argument @var{$arg1} is the +precision with which the computation succeeded. Argument @var{$arg2} is the +input and @var{$arg3} is the computed output. +@end deftp + +@deftp Probe slowlog_inexact (int @var{$arg1}, double @var{$arg2}, double @var{$arg3}) +This probe is hit when the @code{log} function is called with an input that +results in multiple precision computation and none of the multiple precision +computations result in an accurate result. Argument @var{$arg1} is the maximum +precision with which computations were performed. Argument @var{$arg2} is the +input and @var{$arg3} is the computed output. +@end deftp + +@deftp Probe slowatan2 (int @var{$arg1}, double @var{$arg2}, double @var{$arg3}, double @var{$arg4}) +This probe is hit when the @code{atan2} function is called with an input that +results in multiple precision computation. Argument @var{$arg1} is the +precision with which computation succeeded. Arguments @var{$arg2} and +@var{$arg3} are inputs to the @code{atan2} function and @var{$arg4} is the +computed result. +@end deftp + +@deftp Probe slowatan2_inexact (int @var{$arg1}, double @var{$arg2}, double @var{$arg3}, double @var{$arg4}) +This probe is hit when the @code{atan} function is called with an input that +results in multiple precision computation and none of the multiple precision +computations result in an accurate result. Argument @var{$arg1} is the maximum +precision with which computations were performed. Arguments @var{$arg2} and +@var{$arg3} are inputs to the @code{atan2} function and @var{$arg4} is the +computed result. +@end deftp + +@deftp Probe slowatan (int @var{$arg1}, double @var{$arg2}, double @var{$arg3}) +This probe is hit when the @code{atan} function is called with an input that +results in multiple precision computation. Argument @var{$arg1} is the +precision with which computation succeeded. Argument @var{$arg2} is the +input to the @code{atan} function and @var{$arg3} is the computed result. +@end deftp + +@deftp Probe slowatan_inexact (int @var{$arg1}, double @var{$arg2}, double @var{$arg3}) +This probe is hit when the @code{atan} function is called with an input that +results in multiple precision computation and none of the multiple precision +computations result in an accurate result. Argument @var{$arg1} is the maximum +precision with which computations were performed. Argument @var{$arg2} is the +input to the @code{atan} function and @var{$arg3} is the computed result. +@end deftp + +@deftp Probe slowtan (double @var{$arg1}, double @var{$arg2}) +This probe is hit when the @code{tan} function is called with an input that +results in multiple precision computation with precision 32. Argument +@var{$arg1} is the input to the function and @var{$arg2} is the computed +result. +@end deftp diff --git a/sysdeps/ieee754/dbl-64/e_atan2.c b/sysdeps/ieee754/dbl-64/e_atan2.c index 4ebe9c01f9..40756223ce 100644 --- a/sysdeps/ieee754/dbl-64/e_atan2.c +++ b/sysdeps/ieee754/dbl-64/e_atan2.c @@ -42,6 +42,7 @@ #include "uatan.tbl" #include "atnat2.h" #include <math_private.h> +#include <stap-probe.h> #ifndef SECTION # define SECTION @@ -597,7 +598,11 @@ atan2Mp (double x, double y, const int pr[]) __mp_dbl (&mpz1, &z1, p); __mp_dbl (&mpz2, &z2, p); if (z1 == z2) - return z1; + { + LIBC_PROBE (slowatan2, 4, &p, &x, &y, &z1); + return z1; + } } + LIBC_PROBE (slowatan2_inexact, 4, &p, &x, &y, &z1); return z1; /*if impossible to do exact computing */ } diff --git a/sysdeps/ieee754/dbl-64/e_log.c b/sysdeps/ieee754/dbl-64/e_log.c index f9300f9cef..17ab75aa39 100644 --- a/sysdeps/ieee754/dbl-64/e_log.c +++ b/sysdeps/ieee754/dbl-64/e_log.c @@ -39,6 +39,7 @@ #include "mpa.h" #include "MathLib.h" #include <math_private.h> +#include <stap-probe.h> #ifndef SECTION # define SECTION @@ -242,8 +243,12 @@ stage_n: __mp_dbl (&mpy1, &y1, p); __mp_dbl (&mpy2, &y2, p); if (y1 == y2) - return y1; + { + LIBC_PROBE (slowlog, 3, &p, &x, &y1); + return y1; + } } + LIBC_PROBE (slowlog_inexact, 3, &p, &x, &y1); return y1; } diff --git a/sysdeps/ieee754/dbl-64/s_atan.c b/sysdeps/ieee754/dbl-64/s_atan.c index 7b6c83ffb6..35ab5c1926 100644 --- a/sysdeps/ieee754/dbl-64/s_atan.c +++ b/sysdeps/ieee754/dbl-64/s_atan.c @@ -42,6 +42,7 @@ #include "uatan.tbl" #include "atnat.h" #include <math.h> +#include <stap-probe.h> void __mpatan (mp_no *, mp_no *, int); /* see definition in mpatan.c */ static double atanMp (double, const int[]); @@ -306,8 +307,12 @@ atanMp (double x, const int pr[]) __mp_dbl (&mpy1, &y1, p); __mp_dbl (&mpy2, &y2, p); if (y1 == y2) - return y1; + { + LIBC_PROBE (slowatan, 3, &p, &x, &y1); + return y1; + } } + LIBC_PROBE (slowatan_inexact, 3, &p, &x, &y1); return y1; /*if impossible to do exact computing */ } diff --git a/sysdeps/ieee754/dbl-64/s_tan.c b/sysdeps/ieee754/dbl-64/s_tan.c index 54f863e544..cc0dbbbc9f 100644 --- a/sysdeps/ieee754/dbl-64/s_tan.c +++ b/sysdeps/ieee754/dbl-64/s_tan.c @@ -41,6 +41,7 @@ #include <math.h> #include <math_private.h> #include <fenv.h> +#include <stap-probe.h> #ifndef SECTION # define SECTION @@ -838,6 +839,7 @@ tanMp (double x) p = 32; __mptan (x, &mpy, p); __mp_dbl (&mpy, &y, p); + LIBC_PROBE (slowtan, 2, &x, &y); return y; } diff --git a/sysdeps/ieee754/dbl-64/slowexp.c b/sysdeps/ieee754/dbl-64/slowexp.c index 8f353f634f..525224f44a 100644 --- a/sysdeps/ieee754/dbl-64/slowexp.c +++ b/sysdeps/ieee754/dbl-64/slowexp.c @@ -29,6 +29,8 @@ /**************************************************************************/ #include <math_private.h> +#include <stap-probe.h> + #ifndef USE_LONG_DOUBLE_FOR_MP # include "mpa.h" void __mpexp (mp_no *x, mp_no *y, int p); @@ -60,13 +62,22 @@ __slowexp (double x) __mp_dbl (&mpw, &w, p); __mp_dbl (&mpz, &z, p); if (w == z) - return w; + { + /* Track how often we get to the slow exp code plus + its input/output values. */ + LIBC_PROBE (slowexp_p6, 2, &x, &w); + return w; + } else { p = 32; __dbl_mp (x, &mpx, p); __mpexp (&mpx, &mpy, p); __mp_dbl (&mpy, &res, p); + + /* Track how often we get to the uber-slow exp code plus + its input/output values. */ + LIBC_PROBE (slowexp_p32, 2, &x, &res); return res; } #else diff --git a/sysdeps/ieee754/dbl-64/slowpow.c b/sysdeps/ieee754/dbl-64/slowpow.c index a379728b14..d200c39e59 100644 --- a/sysdeps/ieee754/dbl-64/slowpow.c +++ b/sysdeps/ieee754/dbl-64/slowpow.c @@ -34,6 +34,8 @@ #include "mpa.h" #include <math_private.h> +#include <stap-probe.h> + #ifndef SECTION # define SECTION #endif @@ -97,7 +99,12 @@ __slowpow (double x, double y, double z) __sub (&mpp, &eps, &mpr1, p); __mp_dbl (&mpr1, &res1, p); if (res == res1) - return res; + { + /* Track how often we get to the slow pow code plus + its input/output values. */ + LIBC_PROBE (slowpow_p10, 4, &x, &y, &z, &res); + return res; + } /* If we don't, then we repeat using a higher precision. 768 bits of precision ought to be enough for anybody. */ @@ -109,5 +116,10 @@ __slowpow (double x, double y, double z) __mul (&mpy, &mpz, &mpw, p); __mpexp (&mpw, &mpp, p); __mp_dbl (&mpp, &res, p); + + /* Track how often we get to the uber-slow pow code plus + its input/output values. */ + LIBC_PROBE (slowpow_p32, 4, &x, &y, &z, &res); + return res; } |