<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote">On Wed, May 31, 2017 at 6:36 PM, Rafael Avila de Espindola <span dir="ltr"><<a href="mailto:rafael.espindola@gmail.com" target="_blank">rafael.espindola@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">Rui Ueyama <<a href="mailto:ruiu@google.com">ruiu@google.com</a>> writes:<br>
<br>
> Here is the table of your benchmark results. It seems they aren't different<br>
> to me.<br>
<br>
</span>There is very little difference in using an index or not. The regression<br>
is from without the patch to with the patch:</blockquote><div><br></div><div>If there's an index, the patch has totally no effect. And we got the almost same numbers for the test cases without an index.That sounds like we are handling archives without indices. What am I missing?</div><div><br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class=""><br>
> -threads<br>
><br>
> Index w/o Index<br>
> <a href="tel:3.128589132" value="+13128589132">3.128589132</a> <a href="tel:3.128069636" value="+13128069636">3.128069636</a> 1.000<br>
> 3.302902865 3.294943688 1.002<br>
<br>
</span> 3.294943688/<a href="tel:3.128069636" value="+13128069636">3.128069636</a> = 1.0533472944718036<br>
<span class=""><br>
> --no-threads<br>
><br>
> Index w/o Index<br>
> 4.648823604 <a href="tel:4.634666491" value="+14634666491">4.634666491</a> 1.003<br>
> 4.656633102 4.656090134 1.000<br>
<br>
</span>4.656090134/<a href="tel:4.634666491" value="+14634666491">4.634666491</a> = 1.0046224778075408<br>
<br>
Cheers,<br>
Rafael<br>
</blockquote></div><br></div></div>