<div dir="ltr">David, you recall correctly. I recall working with Clustervision. We installed the first 64 bit x86 cluster in the UK,<div>at the chemistry department in Manchester University. AMD CPUs, 1U pizza boxes.</div><div>For the life of me I Cannot recall the manufacturer... but it was a white box.</div><div>Remember that SuSE hired the guy who ported to the x86-64 architecture. I remember him giving LUG talks...</div><div>(arghhh.. name escapes me too...)</div></div><div class="gmail_extra"><br><div class="gmail_quote">On 22 June 2017 at 21:27, mathog <span dir="ltr"><<a href="mailto:mathog@caltech.edu" target="_blank">mathog@caltech.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">On Thu, Jun 22, 2017 at 10:04:34 -0600 Brian Dobbins wrote<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
On Wed, Jun 21, 2017 at 6:29 PM, Christopher Samuel <<a href="mailto:samuel@unimelb.edu.au" target="_blank">samuel@unimelb.edu.au</a>><br>
wrote:<br>
<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
I thought it interesting that the only performance info in that article<br>
for Epyc were SpecINT and (the only mention for SpecFP was for Radeon).<br>
<br>
</blockquote>
<br>
As did I, but a little digging shows a STREAM benchmark (on AMD's page)<br>
showing +25% performance of a single-socket Epyc vs. a dual-socket E5-2690<br>
v4 Broadwell system[1], and roughly 60% better specfp_rate2006 numbers when<br>
comparing socket-to-socket[2]. When I read stuff like this, I feel a<br>
little bit like Charlie Brown going to kick the football, and *hoping* it's<br>
not going to get whisked away by Lucy...<br>
</blockquote>
<br>
If by Lucy you mean Intel, then that suspicion may have some merit.<br>
<br>
Recall that when the Opterons first came out the major manufacturers did not ship any systems with it for what, a year, maybe longer? I vaguely recall SuperMicro going in quickly and Dell, HP, and IBM whistling in a corner. Something about contractual obligations to Intel, or a desire not to piss off Intel.<br>
<br>
Let's see, HP shipped its first system "in the first half" of 2004.<br>
<a href="http://www.networkworld.com/article/2330795/data-center/hp-to-ship-its-first-opteron-servers.html" rel="noreferrer" target="_blank">http://www.networkworld.com/ar<wbr>ticle/2330795/data-center/hp-<wbr>to-ship-its-first-opteron-serv<wbr>ers.html</a><br>
<br>
while the first Opterons shipped in, um, April 2003. So yes, about a year.<br>
When the multiple core Opterons came out once again the big manufacturers were slow to ship them, although in some cases it was apparently due to supply issues:<br>
<br>
<a href="https://www.theregister.co.uk/2007/11/06/ibm_opteron_x3455/" rel="noreferrer" target="_blank">https://www.theregister.co.uk/<wbr>2007/11/06/ibm_opteron_x3455/</a><br>
<br>
Regards,<br>
<br>
David Mathog<br>
<a href="mailto:mathog@caltech.edu" target="_blank">mathog@caltech.edu</a><br>
Manager, Sequence Analysis Facility, Biology Division, Caltech<br>
______________________________<wbr>_________________<br>
Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org" target="_blank">Beowulf@beowulf.org</a> sponsored by Penguin Computing<br>
To change your subscription (digest mode or unsubscribe) visit <a href="http://www.beowulf.org/mailman/listinfo/beowulf" rel="noreferrer" target="_blank">http://www.beowulf.org/mailman<wbr>/listinfo/beowulf</a><br>
</blockquote></div><br></div>