|
From: | Juergen Sauermann |
Subject: | Re: [Bug-apl] Performance optimisations: Results |
Date: | Sun, 06 Apr 2014 17:55:50 +0200 |
User-agent: | Mozilla/5.0 (X11; Linux i686; rv:17.0) Gecko/20130330 Thunderbird/17.0.5 |
Hi,
the current solution seems to be (master == thread-0): for (int c = 1, c < core_count; ++c) thread-0 waits for thread-c One could instead do something this: for (int dc = 1; dc < core_count); dc += dx) { parallel( thread-n waits for thread-n+dc ) if (thread-n+dc < core_count) ) } Same for start-up. In our case the time would be reduced from 80*tsync to 7*tsync which would give us about 11 times the current performance. /// Jürgen On 04/06/2014 05:28 PM, Elias Mårtenson wrote:
|
[Prev in Thread] | Current Thread | [Next in Thread] |