|
From: | Rik |
Subject: | Re: More extended performance profiling |
Date: | Mon, 12 Aug 2019 09:18:18 -0700 |
On 08/12/2019 08:00 AM, John W. Eaton
wrote:
On 8/11/19 8:48 PM, Rik wrote: I have opened a new report here https://savannah.gnu.org/bugs/index.php?56752.
Going backwards is hard. I still haven't got 3.4 - 3.8 to build. I will post my configure scripts and patches for each version (eventually) to bug #56752. The bm_toeplitz script includes an indexed assignment, a function call, and a binary arithmetic operations in the loop. As a quick check to see if just one of these might be the greatest contributing factor to the slowdown, could you try simple loops that have only one of these features at a time? For example, try replacing the statement in the loop with This was my first thought. I re-purposed the original for loop test with an empty body a = 1; b = 1; tic; for i=1:1000; for j=1:1000; ; end; end; toc Results below do show a slowdown of ~100%.
However, absolute numbers are very small. This is 50 milliseconds over 1 million loop iterations. Applied to the toeplitz benchmark it would only be around 100 milliseconds and I'm seeing 7 seconds of difference between 3.2.4 and dev for that.
Not significant. I used toeplitz benchmark and the following options with run-octave -f --no-gui-libs : 13.472 -f --no-gui : 13.715 -f --gui : 13.800 --Rik |
[Prev in Thread] | Current Thread | [Next in Thread] |