Tuesday, May 31, 2016

Digest for comp.programming.threads@googlegroups.com - 2 updates in 2 topics

bleachbot <bleachbot@httrack.com>: May 30 11:27PM +0200

Ramine <ramine@1.1>: May 30 05:30PM -0700

Hello....
 
I have updated all my project again, i have corrected a bug inside the
interface of the Intel TBBMalloc Memory Manager, now it is working
correctly , you will find it inside cmem.pas source code,
also i have done a benchmark of the scalable Intel TBBMalloc and the new
FastMM4 and here is the results:
 
On 32 bit and on a Quadcore with 4 threads, the scalable Intel TBBMalloc
was 2.71X times faster than the newer FastMM4.
 
And on 64 bit and on a Quadcore with 4 threads, the scalable Intel
TBBMalloc was 2.56X times faster than the newer FastMM4.
 
So the Intel TBBMalloc more scalable than FastMM4.
 
But FastMM4 is not prone to fragmentatoin as is the scalable Intel
TBBMalloc.
 
So you can download again all my updated projects from:
 
https://sites.google.com/site/aminer68/
Please note that my projects are at same version, even if i have updated
the Intel TBBMalloc interface inside cmem.pas source code.
 
Thank you,
Amine Moulay Ramdane.
You received this digest because you're subscribed to updates for this group. You can change your settings on the group membership page.
To unsubscribe from this group and stop receiving emails from it send an email to comp.programming.threads+unsubscribe@googlegroups.com.

No comments: