Re: About Amdahl's law 1 ...

Path	csiph.com!usenet.pasdenom.info!news.albasani.net!.POSTED!not-for-mail
From	aminer <aminer@toto.net>
Newsgroups	comp.programming.threads, comp.programming
Subject	Re: About Amdahl's law 1 ...
Date	Thu, 10 Oct 2013 14:45:31 -0700
Organization	albasani.net
Lines	37
Message-ID	<52571FFB.6070606@toto.net> (permalink)
References	<l36mub$7to$1@news.albasani.net> <0.c17b192606e82c58f6a0.20131010191426BST.87vc150z99.fsf@bsb.me.uk>
Mime-Version	1.0
Content-Type	text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding	7bit
X-Trace	news.albasani.net /kwKV75L0tJUUWFvTGP/ZJLiwTgqm4QA8fBjuDrC4Naaok8959HPLiJCtIN/2+RzaFEemlgBn6HWAxF+1ZJXfTiHhjjq7jOEbhlpBOBQrZqsPbnJk6paV5NFcTPqPTeh
NNTP-Posting-Date	Thu, 10 Oct 2013 18:45:31 +0000 (UTC)
Injection-Info	news.albasani.net; logging-data="NqfHBi89CNGhkxTbj4KzRF8srvAL1V32dWkiJUfGVcuXm2ybolBwAL2IRphcXNLp1kJbBTVpty/26Kyx0IXtGvQqxrv2Z3O4jundmEN6QN7poVWjyKGYeqZmg6V3vZEk"; mail-complaints-to="abuse@albasani.net"
User-Agent	Mozilla/5.0 (Windows NT 6.0; WOW64; rv:17.0) Gecko/20130801 Thunderbird/17.0.8
To	Ben Bacarisse <ben.usenet@bsb.me.uk>
In-Reply-To	<0.c17b192606e82c58f6a0.20131010191426BST.87vc150z99.fsf@bsb.me.uk>
Cancel-Lock	sha1:8Exxx+ma6ihWXGn1hqnbCgNLEeY=
Xref	csiph.com comp.programming.threads:1894 comp.programming:3906

Cross-posted to 2 groups.

Show key headers only | View raw

On 10/10/2013 11:14 AM, Ben Bacarisse wrote:
>> You can not use the Amdahl's to predict the exact scalability,
>> >i think , and i have explained it to you that the Amdahl's laws
>> >in parallel computing gives you the scalability in the worst case
>> >contention scenario
> No, it's a best-case formula giving the optimal speed-up if nothing gets
> in the way (such as contention).

You have not understood my ideas Mr. Ben Bacarisse, if you have the 
percentage
of the serial part and percentage of the parallel part and you plug those
datas into the Amdahl's law you will get the optimal/maximum speed-up,
but i have noticed that you have not understood my ideas, the question 
is how to obtain
the time inside the serial part and the time inside the parallel part?
what i have tried to explain to you is that the purpose of the Amdahl's law
is to predict to worst case scalability, and to do this prediction,
you have just to find the maximum bound of the time inside the critical
sections and the maximum of the time inside the parallel part and
do your calculations to predict the worst case scalability, and of course
you have to avoid the context switches by using the same number of 
threads than the number
of cores and you have to lower cache-coherence traffic by using scalable 
Locks. Please reread what i have wrote and you will understand what i mean.

Thank you,
Amine Moulay Ramdane.

Thread

About Amdahl's law 1 ... aminer <aminer@toto.net> - 2013-10-10 13:08 -0700
  Re: About Amdahl's law 1 ... aminer <aminer@toto.net> - 2013-10-10 13:57 -0700
  Re: About Amdahl's law 1 ... Ben Bacarisse <ben.usenet@bsb.me.uk> - 2013-10-10 19:14 +0100
    Re: About Amdahl's law 1 ... aminer <aminer@toto.net> - 2013-10-10 14:45 -0700
      Re: About Amdahl's law 1 ... Ben Bacarisse <ben.usenet@bsb.me.uk> - 2013-10-10 20:56 +0100
  Re: About Amdahl's law 1 ... aminer <aminer@toto.net> - 2013-10-10 14:30 -0700
    Re: About Amdahl's law 1 ... Robert Wessel <robertwessel2@yahoo.com> - 2013-10-10 23:12 -0500

csiph-web