[Ecls-list] More on special variables and multithreading
Juan Jose Garcia-Ripoll
juanjose.garciaripoll at googlemail.com
Fri Jan 22 17:57:27 UTC 2010
On Fri, Jan 22, 2010 at 6:36 PM, Yue Li <xyly781 at gmail.com> wrote:
> The second and third points seems to me will provide better
> performance, so can I say the first one is the current main cause of
> the slow down?
I do not understand fully your question. The system I am describing is the
_new_ one. The old one does not implement _any_ of those three points: it
had a terrible slowdown compared to the single-threaded version which was
due to the use of hash tables.
The major difference from SBCL in this new version is the size of the
thread-local storage. I do not want to fix it beforehand because that would
mean allocating always large buffers for all threads. I would like threads
to start with small or even no thread-local storage for special variables
and then grow from there.
This flexibility has a consequence, which is a small slowdown due to an
addition memory read and comparison operations but I am sure the inline
version will get much better.
Instituto de Física Fundamental, CSIC
c/ Serrano, 113b, Madrid 28006 (Spain)
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the ecl-devel