[Mono-list] Re: Time problems on Mono

Jacek Blaszczynski jacek.blaszczynski@acn.waw.pl
Sat, 11 Dec 2004 10:21:52 +0100

Hi All!

Perhaps it would be nice to port LINPACK test to C# and see the differences
between runtimes - obviously its used for TOP 500 supercompuetr list but is
a standardized measure of overall system performance with some well known



-----Original Message-----
From: mono-list-admin@lists.ximian.com
[mailto:mono-list-admin@lists.ximian.com] On Behalf Of Gregory Bowyer
Sent: Friday, December 10, 2004 7:34 PM
To: Mono-list@lists.ximian.com
Subject: [Mono-list] Re: Time problems on Mono

Martin Hansen wrote:
>>Yes, you can submit a test case that shows we're slow, so we can check 
>>and fix it.
> I made some speed tests too and found mono to be slower.
> If you have some sample programs that run faster on mono I would be
> My test was simple:
> // project created on 8/16/2004 at 4:00 PM using System;
> class MainClass
> {
> 	public static void Main(string[] args)
> 	{
> 	   double sum=0;
>   		for ( int m=0;m<9;m++){
>   			for ( int n=0; n<=(1000* 1000 * 1000) ;n+=1 )
>   	  		{
> 				sum *= 1.0;
> 			}
> 		}
>   	}
> }
> The results was
> Under .net 6 secs. Under mono 9 secs, adding --optimize=all did not make a
big difference.
> The same program in c++ compiled by g++ -O3 is also about 6 secs.
> But the most peculiar thing is that sometimes when compiled by mcs it
takes mono above 2 minutes to finish, I have not found the differencing
factor yet.
Not meaning to flame but isn't that test a bit of a no brainer for
performance issues, I mean its simply an aggressive loop that will take any
langugage / platform a while to work through

Mono-list maillist  -  Mono-list@lists.ximian.com