<br><br>
<div class="gmail_quote">2008/12/10 Steffen Grunewald <span dir="ltr"><<a href="mailto:steffen.grunewald@aei.mpg.de">steffen.grunewald@aei.mpg.de</a>></span><br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">
<div class="Ih2E3d"> </div>Cluster with high core count: this would give the opportunity to do stupid<br>things on the "several hundreds" scale, but not speed up the single stupid<br>thing.<br>
<div class="Ih2E3d"></div></blockquote>
<div>Steffen, if I'm not wrong you have just restated Amdahl's Law.</div>
<div> </div>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">
<div class="Ih2E3d"><span id=""></span><br>> As Vincent says, you need to look at what the code is before hitting the "I<br>> need Cuda" button.<br><br></div>Sometimes the approach to "throw enough money at a problem, and it will<br>
resolve itself" is the easier one, compared with the need to power-up your<br>brains :(<br><br>Thanks for your patience,</blockquote>
<div> </div>
<div>No problem. Sounds to me actually like you need to encourage some code profiling,</div>
<div>before saying that any particular machine is the answer to this one.</div>
<div> </div>
<div> </div>
<div> </div></div>
<br />--
<br />This message has been scanned for viruses and
<br />dangerous content by
<a href="http://www.mailscanner.info/"><b>MailScanner</b></a>, and is
<br />believed to be clean.