Parallel decompositions, C/P/N/Q experiment, take 2
aleksey.shipilev at oracle.com
Thu Sep 27 06:03:58 PDT 2012
On 09/24/2012 05:26 PM, Aleksey Shipilev wrote:
> This is the second take on the experiment I've did couple of months ago
> . tl;dr version: hand-crafted generator for longs in
> (0; N], simple filter (with variable cost Q) to empty sink, called by C
> clients, stream operations services by (fj)pool of size P.
> The question to answer: how would performance change with juggling
> C/P/N/Q, in both sequential and parallel modes?
If anyone here cares, the updated data for 2x8x2 Xeon E5-2680
(SandyBridge) running Solaris 11, and latest lambda nightly with -d64
-XX:-TieredCompilation -XX:+UseParallelOldGC -XX:+UseNUMA
-XX:-UseBiasedLocking -XX:+UseCondCardMark, is here:
It is somewhat similar to what we see with old RHEL running on Nehalem.
More information about the lambda-dev