<html>
    <head>
      <base href="https://bugs.freedesktop.org/">
    </head>
    <body><span class="vcard"><a class="email" href="mailto:jfonseca@vmware.com" title="Jose Fonseca <jfonseca@vmware.com>"> <span class="fn">Jose Fonseca</span></a>
</span> changed
          <a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - [llvmpipe] piglit linestipple regression"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=96518">bug 96518</a>
          <br>
             <table border="1" cellspacing="0" cellpadding="8">
          <tr>
            <th>What</th>
            <th>Removed</th>
            <th>Added</th>
          </tr>

         <tr>
           <td style="text-align:right;">CC</td>
           <td>
                
           </td>
           <td>brianp@vmware.com
           </td>
         </tr></table>
      <p>
        <div>
            <b><a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - [llvmpipe] piglit linestipple regression"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=96518#c2">Comment # 2</a>
              on <a class="bz_bug_link 
          bz_status_NEW "
   title="NEW - [llvmpipe] piglit linestipple regression"
   href="https://bugs.freedesktop.org/show_bug.cgi?id=96518">bug 96518</a>
              from <span class="vcard"><a class="email" href="mailto:jfonseca@vmware.com" title="Jose Fonseca <jfonseca@vmware.com>"> <span class="fn">Jose Fonseca</span></a>
</span></b>
        <pre>Althought generally FMA is more precise, it's possible that it give less
precise results.  Especially when dealing with things like whole integers, it's
quite possible that the lower precision of a non-fused MAD ends up "snapping"
things to the right values.  Whereas FMA preserves any intermediate rounding
error in the final result.


>From my POV, the issue is either:

- llvmpipe/draw stipple implementation needs better rounding (eg.g,
RoundToNearest as opposed to Truncate)

- the linestipple piglit test needs to be updated to not rely on precise
rounding of the stipple.


Either way I doubt the solution is to avoid FMA.</pre>
        </div>
      </p>


      <hr>
      <span>You are receiving this mail because:</span>

      <ul>
          <li>You are the assignee for the bug.</li>
          <li>You are the QA Contact for the bug.</li>
      </ul>
    </body>
</html>