Article: Llano at Hot Chips
By: David Kanter (dkanter.delete@this.realworldtech.com), September 1, 2011 1:52 pm
Room: Moderated Discussions
MS (ms@lostcircuits.com) on 9/1/11 wrote:
---------------------------
>David Kanter (dkanter@realworldtech.com) on 8/31/11 wrote:
>---------------------------
>>MS (ms@lostcircuits.com) on 8/31/11 wrote:
>>---------------------------
>>>David Kanter (dkanter@realworldtech.com) on 8/31/11 wrote:
>>>---------------------------
>>>>AMD’s Hot Chips presentation delved into Llano, the first mainstream Fusion product,
>>>>with details and results for power management. Previous disclosures painted a poor
>>>>picture, which is far from the truth. Given the older CPU and GPU designs and time-to-market
>>>>pressure, the results are quite good. Llano’s power management focuses on the most
>>>>important aspects and is a solid foundation for future generations that will be much more power aware and optimized.
>>>>
>>>>http://www.realworldtech.com/page.cfm?ArticleID=RWT083111130632
>>>>
>>>>As always, we encourage feedback and discussions.
>>>>
>>>>
>>>>Regards,
>>>>
>>>>
>>>>David
>>>
>>>The IPC improvements are mostly myth and Llano is a power >hog compared to SB so
>>>I would argue that all the listed improvements are only >for the purpose of not making it really bad.
>>
>>When you say Llano is a power hog, what do you mean: Active, active/idle or true idle (or perhaps all 3)?
>>
>>AMD's numbers indicated that their battery life should be reasonable, although
>>I wasn't able to really dig into the fine print.
>>
>>David
>
>
>David, here is a listing of all different kinds of scenarios:
>
>http://www.lostcircuits.com/mambo//index.php?option=com_content&task=view&id=101&Itemid=1&limit=1&limitstart=5
>>
>
>Here are more discussions and listings of comparisons for power and IPC performance:
>
>http://www.lostcircuits.com/forum/viewtopic.php?f=3&t=3897&start=220
>
>Bottomline is that testing all different benchmarks Llano came out on average the
>same as any comparable Propus with some improvements in some benchmarks and some
>definite hits in others but AMD appears to have taken a very biased selection of tasks to justify their IPC claims.
You're saying that their desktop parts aren't power gated, right?
David
---------------------------
>David Kanter (dkanter@realworldtech.com) on 8/31/11 wrote:
>---------------------------
>>MS (ms@lostcircuits.com) on 8/31/11 wrote:
>>---------------------------
>>>David Kanter (dkanter@realworldtech.com) on 8/31/11 wrote:
>>>---------------------------
>>>>AMD’s Hot Chips presentation delved into Llano, the first mainstream Fusion product,
>>>>with details and results for power management. Previous disclosures painted a poor
>>>>picture, which is far from the truth. Given the older CPU and GPU designs and time-to-market
>>>>pressure, the results are quite good. Llano’s power management focuses on the most
>>>>important aspects and is a solid foundation for future generations that will be much more power aware and optimized.
>>>>
>>>>http://www.realworldtech.com/page.cfm?ArticleID=RWT083111130632
>>>>
>>>>As always, we encourage feedback and discussions.
>>>>
>>>>
>>>>Regards,
>>>>
>>>>
>>>>David
>>>
>>>The IPC improvements are mostly myth and Llano is a power >hog compared to SB so
>>>I would argue that all the listed improvements are only >for the purpose of not making it really bad.
>>
>>When you say Llano is a power hog, what do you mean: Active, active/idle or true idle (or perhaps all 3)?
>>
>>AMD's numbers indicated that their battery life should be reasonable, although
>>I wasn't able to really dig into the fine print.
>>
>>David
>
>
>David, here is a listing of all different kinds of scenarios:
>
>http://www.lostcircuits.com/mambo//index.php?option=com_content&task=view&id=101&Itemid=1&limit=1&limitstart=5
>>
>
>Here are more discussions and listings of comparisons for power and IPC performance:
>
>http://www.lostcircuits.com/forum/viewtopic.php?f=3&t=3897&start=220
>
>Bottomline is that testing all different benchmarks Llano came out on average the
>same as any comparable Propus with some improvements in some benchmarks and some
>definite hits in others but AMD appears to have taken a very biased selection of tasks to justify their IPC claims.
You're saying that their desktop parts aren't power gated, right?
David
Topic | Posted By | Date |
---|---|---|
Article: Llano Hot Chips Update | David Kanter | 2011/08/31 12:32 PM |
Article: Llano Hot Chips Update | MS | 2011/08/31 01:22 PM |
Article: Llano Hot Chips Update | David Kanter | 2011/08/31 06:07 PM |
Article: Llano Hot Chips Update | MS | 2011/09/01 08:16 AM |
Article: Llano Hot Chips Update | David Kanter | 2011/09/01 01:52 PM |
Article: Llano Hot Chips Update | Gionatan Danti | 2011/09/01 02:53 AM |
Links are ok | David Kanter | 2011/09/01 04:02 AM |
Article: Llano Hot Chips Update | iz | 2011/09/01 02:07 AM |
Article: Llano Hot Chips Update | Gionatan Danti | 2011/09/01 03:01 AM |
Article: Llano Hot Chips Update | David Kanter | 2011/09/01 04:08 AM |
Article: Llano Hot Chips Update | iz | 2011/09/02 01:04 AM |
Article: Llano Hot Chips Update | iz | 2011/09/01 02:08 AM |
More fusion, how? | Moritz | 2011/09/04 12:33 AM |
More fusion, how? | Rohit | 2011/09/04 09:27 AM |