LLVM performance test

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
10 messages Options
Reply | Threaded
Open this post in threaded view
|

LLVM performance test

Lauro Ramos Venancio
Hi all,

I did a performance test of two real applications (FFMPEG and GTK) on
ARM. For more details see:
http://laurovenancio.wordpress.com/2007/08/07/llvm-perf-tests/

Lauro
_______________________________________________
LLVM Developers mailing list
[hidden email]         http://llvm.cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
Reply | Threaded
Open this post in threaded view
|

Re: LLVM performance test

Evan Cheng-2
This is pretty awesome. Thanks Lauro!

Evan

On Aug 13, 2007, at 4:10 PM, Lauro Ramos Venancio wrote:

> Hi all,
>
> I did a performance test of two real applications (FFMPEG and GTK) on
> ARM. For more details see:
> http://laurovenancio.wordpress.com/2007/08/07/llvm-perf-tests/
>
> Lauro
> _______________________________________________
> LLVM Developers mailing list
> [hidden email]         http://llvm.cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev

_______________________________________________
LLVM Developers mailing list
[hidden email]         http://llvm.cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
Reply | Threaded
Open this post in threaded view
|

Re: LLVM performance test

Kenneth.Hoste
In reply to this post by Lauro Ramos Venancio
Hi Lauro,

On 14 Aug 2007, at 01:10, Lauro Ramos Venancio wrote:

> Hi all,
>
> I did a performance test of two real applications (FFMPEG and GTK) on
> ARM. For more details see:
> http://laurovenancio.wordpress.com/2007/08/07/llvm-perf-tests/

Could you give me some more information about the applications you  
compiled and ran? Where can I obtain source codes, which input did  
you provide, ... These two seem interesting for some future work of  
mine (comparing real applications that are used by normal users with  
industry standard benchmarks like SPEC CPU).

Tips for additional applications are also welcome :-)

greetings,

Kenneth

>
> Lauro
> _______________________________________________
> LLVM Developers mailing list
> [hidden email]         http://llvm.cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev

--

Computer Science is no more about computers than astronomy is about  
telescopes. (E. W. Dijkstra)

Kenneth Hoste
ELIS - Ghent University
email: [hidden email]
blog: http://www.elis.ugent.be/~kehoste/blog
website: http://www.elis.ugent.be/~kehoste
_______________________________________________
LLVM Developers mailing list
[hidden email]         http://llvm.cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
Reply | Threaded
Open this post in threaded view
|

Re: LLVM performance test

Kenneth.Hoste
This was meant for Lauro only, my apologies.

On 14 Aug 2007, at 11:49, Kenneth Hoste wrote:

> Hi Lauro,
>
> On 14 Aug 2007, at 01:10, Lauro Ramos Venancio wrote:
>
>> Hi all,
>>
>> I did a performance test of two real applications (FFMPEG and GTK) on
>> ARM. For more details see:
>> http://laurovenancio.wordpress.com/2007/08/07/llvm-perf-tests/
>
> Could you give me some more information about the applications you
> compiled and ran? Where can I obtain source codes, which input did
> you provide, ... These two seem interesting for some future work of
> mine (comparing real applications that are used by normal users with
> industry standard benchmarks like SPEC CPU).
>
> Tips for additional applications are also welcome :-)
>
> greetings,
>
> Kenneth
>
>>
>> Lauro
>> _______________________________________________
>> LLVM Developers mailing list
>> [hidden email]         http://llvm.cs.uiuc.edu
>> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
>
> --  
>
> Computer Science is no more about computers than astronomy is about
> telescopes. (E. W. Dijkstra)
>
> Kenneth Hoste
> ELIS - Ghent University
> email: [hidden email]
> blog: http://www.elis.ugent.be/~kehoste/blog
> website: http://www.elis.ugent.be/~kehoste
> _______________________________________________
> LLVM Developers mailing list
> [hidden email]         http://llvm.cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev

--  

Computer Science is no more about computers than astronomy is about  
telescopes. (E. W. Dijkstra)

Kenneth Hoste
ELIS - Ghent University
email: [hidden email]
blog: http://www.elis.ugent.be/~kehoste/blog
website: http://www.elis.ugent.be/~kehoste
_______________________________________________
LLVM Developers mailing list
[hidden email]         http://llvm.cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
Reply | Threaded
Open this post in threaded view
|

Re: LLVM performance test

Torvald Riegel-3
In reply to this post by Lauro Ramos Venancio
Hi,

I have two related questions: Are there LLVM developers on this list that are
interested in improving LLVM performance? I have examples in which LLVM is
slower than gcc (e.g., STM linked list microbenchmark, 1.8 (gcc) vs. 1.3
(llvm), more is better). I've never done compiler performance tuning, so I
don't know how much effort is required.

Second question: does anyone keep track of performance results?

Thanks,
Torvald

On Tuesday 14 August 2007 01:10, Lauro Ramos Venancio wrote:

> Hi all,
>
> I did a performance test of two real applications (FFMPEG and GTK) on
> ARM. For more details see:
> http://laurovenancio.wordpress.com/2007/08/07/llvm-perf-tests/
>
> Lauro
> _______________________________________________
> LLVM Developers mailing list
> [hidden email]         http://llvm.cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
_______________________________________________
LLVM Developers mailing list
[hidden email]         http://llvm.cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
Reply | Threaded
Open this post in threaded view
|

Re: LLVM performance test

Gordon Henriksen-3
On 2007-08-19, at 14:53, Torvald Riegel wrote:

does anyone keep track of performance results?

Benchmark info is submitted by the nightly testers.


— Gordon


_______________________________________________
LLVM Developers mailing list
[hidden email]         http://llvm.cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
Reply | Threaded
Open this post in threaded view
|

Re: LLVM performance test

Anton Korobeynikov
In reply to this post by Lauro Ramos Venancio
Hello, Torvald.

> I have two related questions: Are there LLVM developers on this list that are
> interested in improving LLVM performance?
Yes, surely.

> I have examples in which LLVM is slower than gcc (e.g., STM linked list microbenchmark,
>  1.8 (gcc) vs. 1.3 (llvm), more is better).
Please provide link to benchmark.

> Second question: does anyone keep track of performance results?
This is usually done via nightly tests.

--
With best regards, Anton Korobeynikov.

Faculty of Mathematics & Mechanics, Saint Petersburg State University.


_______________________________________________
LLVM Developers mailing list
[hidden email]         http://llvm.cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
Reply | Threaded
Open this post in threaded view
|

Re: LLVM performance test

Chris Lattner
In reply to this post by Torvald Riegel-3
On Aug 19, 2007, at 11:53 AM, Torvald Riegel wrote:
> I have two related questions: Are there LLVM developers on this  
> list that are
> interested in improving LLVM performance? I have examples in which  
> LLVM is
> slower than gcc (e.g., STM linked list microbenchmark, 1.8 (gcc)  
> vs. 1.3
> (llvm), more is better).

Yes absolutely.  If you can narrow down the example to a simple  
testcase and attach that to a bugzilla, that would be wonderful.

-Chris
_______________________________________________
LLVM Developers mailing list
[hidden email]         http://llvm.cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
Reply | Threaded
Open this post in threaded view
|

Re: LLVM performance test

Holger Schurig-2
In reply to this post by Gordon Henriksen-3
> Benchmark info is submitted by the nightly testers.
>
> http://llvm.org/nightlytest/

Hmm, I could not really see benchmark info there. For example,
when I look at
http://llvm.org/nightlytest/machine.php?machine=153, where is
this info?

Maybe it's implicitly in the column "dejagnu time wall", because
this amount has decreased from 2007-08-09 to 2007-08-19 from 200
seconds to 180 seconds. But that would be a lousy benchmark ...
_______________________________________________
LLVM Developers mailing list
[hidden email]         http://llvm.cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
Reply | Threaded
Open this post in threaded view
|

Re: LLVM performance test

Gordon Henriksen-3
On Aug 20, 2007, at 02:54, Holger Schurig wrote:

Benchmark info is submitted by the nightly testers.


Hmm, I could not really see benchmark info there. For example, when I look at http://llvm.org/nightlytest/machine.php?machine=153, where is this info?

Raw data is here:

"Significant" changes are hilighted on this page:

Be patient; they take a while to load.

— Gordon


_______________________________________________
LLVM Developers mailing list
[hidden email]         http://llvm.cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev