Hi Mike,

The regression is using bzip2_source with lgred, which I think means the
argument is already 1 :-(

Someone more familiar with the cpu2000.py script can perhaps have a look?

Andreas

On 29/07/2015 21:30, "gem5-dev on behalf of mike upton"
<[email protected] on behalf of [email protected]> wrote:

>for me, the test version of 401.bzip2 in cpu2006 runs:
>
><bzip_exe> dryer.jpg 2
>
>The final number appears to be the size of the input data in MB.
>Since dryer.jpg is less than 2MB, it replicates the data.
>
>Running this on my laptop takes abt 3 seconds.
>
>If I change the params to:
><bzip_exe> dryer.jpg 1
>
>it takes about 1.4 sec
>
>so you should be able to cut the runtime in half.
>
>
>On Wed, Jul 29, 2015 at 3:03 AM, Andreas Hansson <[email protected]>
>wrote:
>
>> Hi all,
>>
>> bzip2 accounts for almost 30% of our regression CPU time, and there is
>>no
>> obvious way of reducing the dataset (like the other benchmarks). I
>>believe
>> Mike mentioned something at the ISCA workshop, but I cannot remember
>> exactly what it was. Anyone got an idea? Mike?
>>
>> Thanks,
>>
>> Andreas
>>
>> -- IMPORTANT NOTICE: The contents of this email and any attachments are
>> confidential and may also be privileged. If you are not the intended
>> recipient, please notify the sender immediately and do not disclose the
>> contents to any other person, use it for any purpose, or store or copy
>>the
>> information in any medium. Thank you.
>>
>> ARM Limited, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ,
>> Registered in England & Wales, Company No: 2557590
>> ARM Holdings plc, Registered office 110 Fulbourn Road, Cambridge CB1
>>9NJ,
>> Registered in England & Wales, Company No: 2548782
>> _______________________________________________
>> gem5-dev mailing list
>> [email protected]
>> http://m5sim.org/mailman/listinfo/gem5-dev
>>
>_______________________________________________
>gem5-dev mailing list
>[email protected]
>http://m5sim.org/mailman/listinfo/gem5-dev


-- IMPORTANT NOTICE: The contents of this email and any attachments are 
confidential and may also be privileged. If you are not the intended recipient, 
please notify the sender immediately and do not disclose the contents to any 
other person, use it for any purpose, or store or copy the information in any 
medium.  Thank you.

ARM Limited, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ, Registered 
in England & Wales, Company No:  2557590
ARM Holdings plc, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ, 
Registered in England & Wales, Company No:  2548782
_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev

Reply via email to