<div dir="ltr"><br><div class="gmail_extra"><br><br><div class="gmail_quote">On Wed, Jan 22, 2014 at 1:53 PM, Kay Sievers <span dir="ltr"><<a href="mailto:kay@vrfy.org" target="_blank">kay@vrfy.org</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="im">On Wed, Jan 22, 2014 at 12:42 PM, Ylinen, Mikko <<a href="mailto:mikko.ylinen@intel.com">mikko.ylinen@intel.com</a>> wrote:<br>
<br>
> I verified the numbers and used test/splash.bmp as the source image.<br>
> Looks like test/splash.bmp only adds 10ms more compared with BGRX.<br>
><br>
> My original BMP is 24bit, no alpha. As far as I can tell this is the same<br>
> as test/splash.bmp but without alpha channel.<br>
<br>
</div>Oh, so if we detect that we do not need to blend, which is probably<br>
the most expensive part, we should be in the same area as the<br>
original, I guess.<br>
<br>
What are your relative numbers, do the 10ms matter or is it already good enough?<br></blockquote><div><br></div><div>I think this is good enough. I still haven't played with build flags...</div><div><br></div><div>-- Mikko</div>
</div><br></div></div>