On Sun, Nov 4, 2012 at 10:04 PM, Karl Rupp <span dir="ltr"><<a href="mailto:rupp@mcs.anl.gov" target="_blank">rupp@mcs.anl.gov</a>></span> wrote:<br><div class="gmail_extra"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="im"><br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
The copy_to_cpu-part could be managed via page-locked memory, yet I<br>
still have to investigate its robustness. It is certainly a nice<br>
option for APUs, because it has zero overhead. The only drawback is<br>
that APUs just lack performance in general...<br>
<br>
Overall, I don't want to give away the robustness you described<br>
above. There will always be some operations that work better on the<br>
CPU, while others work better on accelerators, so hopping between<br>
them is (unfortunately) rather the rule than the exception in real<br>
world applications.<br>
<br>
<br>
Okay, then I have a procedural question. Should we write about this for<br>
the GPU book, or just describe the<br>
current state of affairs?<br>
</blockquote>
<br></div>
Considering that I wanted to contact you anyway with respect to help on the write-up for the book: Can we postpone this decision to around November 20th? I guess I will have have a much clearer picture on the topic then.<br>
</blockquote><div><br></div><div>Yes, I think we can writeup the old stuff in time for mid-Jan, so waiting does no harm.</div><div><br></div><div> Matt</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Best regards,<br>
Karli<br>
</blockquote></div><br><br clear="all"><div><br></div>-- <br>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>
-- Norbert Wiener<br>
</div>