Re: [rvm-research] Researching the Jikes RVM

Since Dacapo Benchmark Suite [1] is a FOSS benchmark (used as the
clients benchmark, by the authors), it seems a good start. I will let
you know, if I made some progress on this, or if I need some
assistance.

[1] http://www.dacapobench.org/

On Sat, Mar 30, 2013 at 10:58 AM, Kathiravelu Pradeeban
<[email protected]> wrote:
> Hi,
> I feel, testing the non-concurrent implementation would be the first
> step in this project, to confirm that the improvements are fair enough
> to make the implementation merged with the trunk.
>
> I notice that we require to purchase the benchmark (both SPECjbb2013
> and the retired SPECjbb2000). Can I obtain a copy of (or a pointer to)
> the benchmark that is used by the Jikes RVM, to test the initial
> implementation (probably, at a latter stage of the development)?
>
> Thank you.
> Regards,
> Pradeeban.
>
> On Sat, Mar 30, 2013 at 10:44 AM, Kathiravelu Pradeeban
> <[email protected]> wrote:
>> Thank you. I find SPECjbb2013 [1] suitable to benchmark the
>> implementation. SPECjbb2000 used by the authors of the paper is
>> currently retired.
>>
>> [1] http://www.spec.org/jbb2013/
>>
>> Regards,
>> Pradeeban.
>>
>> On Wed, Mar 20, 2013 at 7:06 PM, Erik Brangs <[email protected]> wrote:
>>> Hi,
>>>
>>> On 20.03.2013 09:56, Kathiravelu Pradeeban wrote:
>>>> Hi,
>>>> Can I have a pointer to the known improvements/limitations (if any) or
>>>> status of the current stop-the-world variant from Michael, that
>>>> prevents the code to be merged to the trunk (as indicated in the ideas
>>>> page [1])?
>>>
>>> IIRC the compressor implementation was still suffering from frequent
>>> crashes. I'm afraid I can't give you any detailed information on the
>>> status of the Compressor implementation - garbage collection is not my
>>> area of expertise.
>>>
>>> My personal opinion is that a new collector shouldn't be more unstable
>>> than the collectors that are tested in the sanity and sanity-tier2 runs.
>>> It's been a while since I looked at the regression reports in detail but
>>> from memory I'd say that this translates to one failure per multiple
>>> weeks of test runs.
>>>
>>>
>>> Kind regards,
>>>
>>> Erik Brangs
>>>
>>> ------------------------------------------------------------------------------
>>> Everyone hates slow websites. So do we.
>>> Make your web apps faster with AppDynamics
>>> Download AppDynamics Lite for free today:
>>> http://p.sf.net/sfu/appdyn_d2d_mar
>>> _______________________________________________
>>> Jikesrvm-researchers mailing list
>>> [email protected]
>>> https://lists.sourceforge.net/lists/listinfo/jikesrvm-researchers
>>
>>
>>
>> --
>> Kathiravelu Pradeeban.
>> Postgraduate Student,
>> Erasmus Mundus European Master in Distributed Computing,
>> Instituto Superior Técnico, Lisbon, Portugal.
>>
>> Blog: [Llovizna] http://kkpradeeban.blogspot.com/
>
>
>
> --
> Kathiravelu Pradeeban.
> Postgraduate Student,
> Erasmus Mundus European Master in Distributed Computing,
> Instituto Superior Técnico, Lisbon, Portugal.
>
> Blog: [Llovizna] http://kkpradeeban.blogspot.com/



-- 
Kathiravelu Pradeeban.
Postgraduate Student,
Erasmus Mundus European Master in Distributed Computing,
Instituto Superior Técnico, Lisbon, Portugal.

Blog: [Llovizna] http://kkpradeeban.blogspot.com/

------------------------------------------------------------------------------
Own the Future-Intel(R) Level Up Game Demo Contest 2013
Rise to greatness in Intel's independent game demo contest. Compete 
for recognition, cash, and the chance to get your game on Steam. 
$5K grand prize plus 10 genre and skill prizes. Submit your demo 
by 6/6/13. http://altfarm.mediaplex.com/ad/ck/12124-176961-30367-2