The Penryn Preview - Part I: Wolfdale Performance
by Anand Lal Shimpi on August 21, 2007 12:35 PM EST- Posted in
- CPUs
Final Words
After Intel's price cuts we mentioned that despite Penryn's imminent launch, CPUs had gotten too affordable to pass up building a system now if you needed. Now that we have a general idea of clock-for-clock performance differences between Conroe and Wolfdale, we're not nearly as worried about recommending that you build systems today as we once were. There's no doubt that Wolfdale is faster clock-for-clock, but keep in mind that you won't see Wolfdale until Q1 of next year and the performance advantage simply isn't great enough to justify delaying a purchase by 6+ months if you need a system now.
AMD seems quite confident that Phenom will be able to compete with Conroe/Kentsfield; if the race is really close between those cores, Penryn could be exactly what Intel needs to remain technically ahead in performance. If Phenom is significantly faster than Conroe/Kentsfield, then it doesn't look like Penryn will be able to save Intel. We should know for sure which scenario will pan out in the not too distant future.
We've got more Penryn coverage coming, including a look at Yorkfield vs. Kentsfield so stay tuned.
Facebook
Twitter
RSS
55 Comments
View All Comments
Affectionate-Bed-980 - Thursday, August 23, 2007 - link
My God. Then maybe they should think about reviews when dealing with NDAs. Just because I didnt have to pay for this article doesn't mean people can't complain.Remember those Conroe reviews done by HardOCP or something that were just GPU limited? Of course people have a right to complain about crappy reviews.
Beenthere - Wednesday, August 22, 2007 - link
Nothing here but ad hype for sure. Intel looks desperate.AnnonymousCoward - Saturday, August 25, 2007 - link
Since when does a process node transition mean the company is desperate??fitten - Thursday, August 23, 2007 - link
Why would Intel be despirate? you think 2GHz Barcelona (which isn't the desktop chip) scares them?coldpower27 - Wednesday, August 22, 2007 - link
Assuming that a E6550 consumes 8-10W at idle and 55W at load which shouldn't be too far off from the proper numbers and is a reasonable estimate.
Then your looking at 3-5W for idle and something like 37W for load, very impressive considering the Wolfdale SKU's on the desktop are going to retain their 65W TDP.
n0nsense - Wednesday, August 22, 2007 - link
wtf ?32bit system performance tests on 64bit hardware ?
lets test it on PII.
if you can't find native 64bit soft for MS, look at real OSes.
need new optimizations ? compile open source programs with new flags enabled.
and one more thing.
compilation test will be very good
johnsonx - Wednesday, August 22, 2007 - link
Ever since this:http://www.dailytech.com/article.aspx?newsid=8313&...">http://www.dailytech.com/article.aspx?n...amp;thre...
I can't help but laugh when I see the first chart on page one.
strikeback03 - Wednesday, August 22, 2007 - link
bwahahaPenryn enhancements indeed
TA152H - Tuesday, August 21, 2007 - link
I somehow remember having an argument with all the dolts that were claiming massive IPC improvements for this core and how hopeless the Barcelona was since it would be against the Penryn. It surely does not look to be impossible to me, not even close. Considering the massive improvements AMD gets over time with their process technology, and large improvements vis-a-vis the K8, this looks to be the most competitive the companies have been for quite some time.Not that I am bad mouthing Intel, they did an amazing job not only increasing the size of the cache, but also lowering the latency. The problem is that so many people were expecting the impossible, and now are disappointed because they really don't know anything about microprocessors. It's not Intel's fault, it's still a great product. Lower power, better performance and smaller size compared to a fantastic processor is something they deserve a lot of credit for. But, it's not going to walk away from the Barcelona, especially on servers.
Higher clock speeds would probably show greater improvement, since it's got a larger cache, and going to four cores would as well, but the reality is, it's not going to be a big improvement on most apps. It's also going to be relatively simple for AMD to increase cache sizes, particularly since they added wait states to the L2 cache so it could be bigger if they chose (again illustrating how amazing Intel was for increasing size and speed).
By the time this processor is out though, AMD will not only have corrected the most egregious speed path problems for Barcelona, but they will also be further along on their 65nm process, and if history is any indication (and it normally is), AMD will do a great job in improving their manufacturing on 65nm. All in all, it's not going to be easy for Intel. Or AMD.
AbRASiON - Tuesday, August 21, 2007 - link
I believe those idiots were hopeful of extremely high clocks actually.It doesn't matter how performance is delivered, 10mhz of ultra optimised CPU or 10ghz of poorly optomised, all we want is speed and AMD is yet to show us the money.