[Bug math/21236] New: NaN generation by optimized math functions

["charles at schwieters dot org" <sourceware-bugzilla at sourceware dot org>]

https://sourceware.org/bugzilla/show_bug.cgi?id=21236

            Bug ID: 21236
           Summary: NaN generation by optimized math functions
           Product: glibc
           Version: 2.24
            Status: UNCONFIRMED
          Severity: normal
          Priority: P2
         Component: math
          Assignee: unassigned at sourceware dot org
          Reporter: charles at schwieters dot org
  Target Milestone: ---

In code compiled with the Intel Fortran compiler
(ifort-v11 (IFORT) 16.0.3 20160415) with optimizing, my very old code suddenly
started misbehaving, giving NaNs unexpectedly. I traced this to when Debian
made the upgrade of libc6 from 2.24-8 --> 2.24-9. I then did some sleuthing to
discover that git commit fb0f7a6755c1bfaec38f490fbfcaa39a66ee3604 was the
culprit. Reversing this patch allowed things to work (as this binary does on
many, many different versions of glibc). 

Rather than make a fix myself (I an not qualified), I can describe the
behavior: the problem seems to only occur on machines with an avx cpu flag. On
machines which list no AVX cpu flags, the bad behavior does not occur.
Unfortunately, I have been unable to run this on a machine with AVX512
instructions.

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