[Beowulf] curiosity killed the cat
deadline at eadline.org
Thu Jun 2 13:54:00 PDT 2016
> On 02/06/16 05:25, Andrew Piskorski wrote:
>> You mean GAMMA (Genoa Active Message MAchine):
Used both of these
> GAMMA's last update was 2009, according to their website.
Very good, but only worked for Intel e1000 (IIRC)
> Brice pulled the plug on Open-MX in December 2015.
Worked well, but some of my more recent tests with
Chelsio and Mellanox 10Gbe were mixed using Open-MX.
Many of the 10Gbe (and above) vendors seem to
be paying more attention to performance than
before. I like that for my small scale Limulus
boxes I can get 8-9 usec latency using tcp,
which provides a great performance bump over old 1 Gbe
HPL increased from 480 to 658 DP CPU GFLOPS using 4
Skylake procs). I should have my Hadoop terasort
numbers by the end of the month as well.
> Christopher Samuel Senior Systems Administrator
> VLSCI - Victorian Life Sciences Computation Initiative
> Email: samuel at unimelb.edu.au Phone: +61 (0)3 903 55545
> http://www.vlsci.org.au/ http://twitter.com/vlsci
> Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing
> To change your subscription (digest mode or unsubscribe) visit
> Mailscanner: Clean
More information about the Beowulf