David Kanter (dkanter@realworldtech.com) on 1/24/12 wrote:
---------------------------
>Wilco (Wilco.Dijkstra@ntlworld.com) on 1/24/12 wrote:
>---------------------------
>>David Kanter (dkanter@realworldtech.com) on 1/24/12 wrote:
>>---------------------------
>>>Wilco (Wilco.Dijkstra@ntlworld.com) on 1/24/12 wrote:
>>>---------------------------
>>>>David Kanter (dkanter@realworldtech.com) on 1/23/12 wrote:
>>>>---------------------------
>>>>
>>>>"Realistically, Medfield will not have a decisive performance advantage over platforms
>>>>like TI’s OMAP5 or the Snapdragon S4. At best, Medfield will be slightly ahead of
>>>>the competition; but in many cases Intel’s performance may >lag by 10-30%."
>>>
>>>Actually, I updated the article...the new language you might find more reasonable.
>>
>>The new version is more accurate, but still suggests that Medfield could be faster
>>than an A15 or Krait. There is no way Medfield would be close, whether you compare
>>at max frequency, equal frequency or equal watts. Unless of course you're talking
>>about Intel marketing numbers, not actual products.
>>
>>>>I can't believe how anyone could seriously suggest that Medfield will be competitive
>>>>or even have a performance advantage over 1.5-2GHz dual core Krait or A15, especially
>>>>given the fact that a 1GHz A9 outperforms an 1.6GHz Atom.
>>>
>>>We've been over this before...there's no way that an A9 has a 30-40% advantage
>>>in terms of effective IPC. Most A9s have a crappy memory hierarchy and lose in a variety of benchmarks.
>>
>>We've seen a few benchmarks showing how well the A9 does vs >1.6GHz netbook Atoms,
>
>I would hesitate to call them benchmarks.
>
>>which may not be perfect, but they tell a different story than what Intel claims.
>>Unless Medfield has significantly improved IPC, I'd expect it to be a little slower
>>than the netbook variants due to a slower memory system in >mobiles.
>
>Again, I place far greater stock in SPECint than the other benchmarks I've seen. You obviously differ in that regard.
>

Here is a research work done by UMich and ARM. How much sense does it make for the conclusion :

"In this paper we have characterized interactive smart phone applications, and shown how they differ significantly from SPEC CPU2006 benchmarks. Smartphones have become the primary consumer computing device. As computer architects work to improve the efficiency and performance of such systems they need to consider benchmarks that better match typical use cases along with their library and system interactions. In particular, the interactive smart phone applications have significantly worse instruction cache, TLB miss statistics and branch misprediction rates, which we attribute to heavy use of high level software abstractions. To this end, we have developed an interactive smartphone benchmark suite that includes a web-browser benchmark, BBench, which is representative of the most ubiquitous smartphone application—the web-browser. BBench provides a fully contained, automated and repeatable web-browser benchmark that exercises not only the web-browser, but the underlying libraries and operating system. While there is a place for CPU-intensive portable benchmarks, computer architects and systems designers will be ill-served relying solely on these benchmarks for performance improvement and characterization in the mobile device arena."

Paper:
http://www.eecs.umich.edu/~tnm/trev_test/papersPDF/2011.10.Full-System%20Analysis%20and%20Characterization%20of%20Interactive%20Smartphone%20Applications.pdf