Call math_opt_barrier inside if
Commit Message
Since floating-point operation may trigger floating-point exceptions,
we call math_opt_barrier inside if to prevent code motion.
Tested on x86-64. OK for trunk?
H.J.
---
[BZ #19465]
* sysdeps/ieee754/dbl-64/s_fma.c (__fma): Call math_opt_barrier
inside if.
---
sysdeps/ieee754/dbl-64/s_fma.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
Comments
On Thu, 14 Jan 2016, H.J. Lu wrote:
> Since floating-point operation may trigger floating-point exceptions,
> we call math_opt_barrier inside if to prevent code motion.
>
> Tested on x86-64. OK for trunk?
Please send a patch updating all implementations for which this issue is
applicable.
On Thu, Jan 14, 2016 at 2:13 PM, Joseph Myers <joseph@codesourcery.com> wrote:
> On Thu, 14 Jan 2016, H.J. Lu wrote:
>
>> Since floating-point operation may trigger floating-point exceptions,
>> we call math_opt_barrier inside if to prevent code motion.
>>
>> Tested on x86-64. OK for trunk?
>
> Please send a patch updating all implementations for which this issue is
> applicable.
There are
dbl-64/e_sqrt.c: libc_feholdexcept_setround (&env, FE_TONEAREST);
dbl-64/s_fma.c: libc_feholdexcept_setround (&env, FE_TONEAREST);
dbl-64/s_fmaf.c: libc_feholdexcept_setround (&env, FE_TOWARDZERO);
under sysdeps/ieee754. dbl-64/s_fma.c is the only one with this
problem.
On Thu, 14 Jan 2016, H.J. Lu wrote:
> On Thu, Jan 14, 2016 at 2:13 PM, Joseph Myers <joseph@codesourcery.com> wrote:
> > On Thu, 14 Jan 2016, H.J. Lu wrote:
> >
> >> Since floating-point operation may trigger floating-point exceptions,
> >> we call math_opt_barrier inside if to prevent code motion.
> >>
> >> Tested on x86-64. OK for trunk?
> >
> > Please send a patch updating all implementations for which this issue is
> > applicable.
>
> There are
>
> dbl-64/e_sqrt.c: libc_feholdexcept_setround (&env, FE_TONEAREST);
> dbl-64/s_fma.c: libc_feholdexcept_setround (&env, FE_TONEAREST);
> dbl-64/s_fmaf.c: libc_feholdexcept_setround (&env, FE_TOWARDZERO);
>
> under sysdeps/ieee754. dbl-64/s_fma.c is the only one with this
> problem.
I disagree with that analysis. The question isn't whether there's a call
to a particular internal interface. The question is whether there are
conditionals on arithmetic, such that the arithmetic is exact in the
conditional case but may be inexact if moved before the conditional. I
think at least ldbl-96/s_fmal.c, ldbl-96/s_fma.c and ldbl-128/s_fmal.c
have the same issue.
@@ -175,7 +175,10 @@ __fma (double x, double y, double z)
/* Ensure correct sign of exact 0 + 0. */
if (__glibc_unlikely ((x == 0 || y == 0) && z == 0))
- return x * y + z;
+ {
+ x = math_opt_barrier (x);
+ return x * y + z;
+ }
fenv_t env;
libc_feholdexcept_setround (&env, FE_TONEAREST);