[Bug manual/15267] New: Add note on performance characteristics of some libm functions

[Bug manual/15267] New: Add note on performance characteristics of some libm functions

[siddhesh at redhat dot com]

http://sourceware.org/bugzilla/show_bug.cgi?id=15267

             Bug #: 15267
           Summary: Add note on performance characteristics of some libm
                    functions
           Product: glibc
           Version: unspecified
            Status: NEW
          Severity: normal
          Priority: P2
         Component: manual
        AssignedTo: unassigned@sourceware.org
        ReportedBy: siddhesh@redhat.com
                CC: mtk.manpages@gmail.com, roland@gnu.org
    Classification: Unclassified


libm has a fallback to multiprecision calculation for some functions (log, exp,
atan, pow, etc.) which is much slower than the fast path.  While the inputs
that trigger this are unknown, it would be useful to document the fact that
there is such a performance difference, along with an explanation of why the
multiprecision stage is needed at all.

-- 
Configure bugmail: http://sourceware.org/bugzilla/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are on the CC list for the bug.

[Bug manual/15267] Add note on performance characteristics of some libm functions

[manu at gcc dot gnu.org]

http://sourceware.org/bugzilla/show_bug.cgi?id=15267

Manuel López-Ibáñez <manu at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |manu at gcc dot gnu.org

--- Comment #1 from Manuel López-Ibáñez <manu at gcc dot gnu.org> 2013-03-11 09:10:09 UTC ---
Some background on why such documentation could save a lot of frustration can
be found in bug 13932, and in http://entropymine.com/imageworsener/slowpow/,
and simply by googling "slowpow".

-- 
Configure bugmail: http://sourceware.org/bugzilla/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are on the CC list for the bug.

[Bug manual/15267] Add note on performance characteristics of some libm functions

[bugdal at aerifal dot cx]

http://sourceware.org/bugzilla/show_bug.cgi?id=15267

Rich Felker <bugdal at aerifal dot cx> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |bugdal at aerifal dot cx

--- Comment #2 from Rich Felker <bugdal at aerifal dot cx> 2013-03-15 05:57:21 UTC ---
Shouldn't this issue just be fixed? IEEE specifically omits the requirement of
correct rounding for transcendental functions because of the long-known issue
that there's no known efficient way to compute the correctly-rounded results.
As far as I can tell, no other libm implementations have these performance
bugs; they're unique to glibc and the "IBM Accurate Mathematical Library"
written for glibc.

-- 
Configure bugmail: http://sourceware.org/bugzilla/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are on the CC list for the bug.

[Bug manual/15267] Add note on performance characteristics of some libm functions

[carlos at redhat dot com]

http://sourceware.org/bugzilla/show_bug.cgi?id=15267

Carlos O'Donell <carlos at redhat dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |carlos at redhat dot com

--- Comment #3 from Carlos O'Donell <carlos at redhat dot com> 2013-03-15 14:37:59 UTC ---
(In reply to comment #2)
> Shouldn't this issue just be fixed? IEEE specifically omits the requirement of
> correct rounding for transcendental functions because of the long-known issue
> that there's no known efficient way to compute the correctly-rounded results.
> As far as I can tell, no other libm implementations have these performance
> bugs; they're unique to glibc and the "IBM Accurate Mathematical Library"
> written for glibc.

Sorry, are you advocating we "fix it" as opposed to "document it?"

If you are then I agree, but documenting things until you fix them is a good
intermediate step.

-- 
Configure bugmail: http://sourceware.org/bugzilla/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are on the CC list for the bug.

[Bug manual/15267] Add note on performance characteristics of some libm functions

[fweimer at redhat dot com]

https://sourceware.org/bugzilla/show_bug.cgi?id=15267

Florian Weimer <fweimer at redhat dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |fweimer at redhat dot com
              Flags|                            |security-

-- 
You are receiving this mail because:
You are on the CC list for the bug.

[Bug manual/15267] Add note on performance characteristics of some libm functions

[fweimer at redhat dot com]

https://sourceware.org/bugzilla/show_bug.cgi?id=15267

Florian Weimer <fweimer at redhat dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|fweimer at redhat dot com          |

-- 
You are receiving this mail because:
You are on the CC list for the bug.

[Bug manual/15267] Fix libm performance by relaxing ULP errors.

[carlos at redhat dot com]

https://sourceware.org/bugzilla/show_bug.cgi?id=15267

Carlos O'Donell <carlos at redhat dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
            Summary|Add note on performance     |Fix libm performance by
                   |characteristics of some     |relaxing ULP errors.
                   |libm functions              |

--- Comment #5 from Carlos O'Donell <carlos at redhat dot com> ---
I'm going to retitle this bug and instead of saying we're going to document the
performance issues, we should fix them.

We have already agreed to relax the ULPs to 9 ULPs for all functions and thus
remove the MP-fallback paths in these cases.

We have just had a user report that:

* acos
* asin

Both have MP-fallback cases that are very bad and should be fixed.

Szabolcs Nagy from Arm has worked on many of these fixes.

-- 
You are receiving this mail because:
You are on the CC list for the bug.

[Bug manual/15267] Fix libm performance by relaxing ULP errors.

[carlos at redhat dot com]

https://sourceware.org/bugzilla/show_bug.cgi?id=15267

Carlos O'Donell <carlos at redhat dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |nszabolcs at gmail dot com

-- 
You are receiving this mail because:
You are on the CC list for the bug.

[Bug manual/15267] Fix libm performance by relaxing ULP errors.

[wdijkstr at arm dot com]

https://sourceware.org/bugzilla/show_bug.cgi?id=15267

Wilco <wdijkstr at arm dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |wdijkstr at arm dot com

--- Comment #6 from Wilco <wdijkstr at arm dot com> ---
All slow paths have now been removed from all math functions.

-- 
You are receiving this mail because:
You are on the CC list for the bug.