http://i245.photobucket.com/albums/g...Nehalem-EP.jpg
http://i245.photobucket.com/albums/g...Bloomfield.jpg
http://i245.photobucket.com/albums/g...oomfield_0.jpg
From www.xfastest.com
http://www.xfastest.com/viewthread.p...a=page%3D1
Printable View
how fast is a 2.4 Ghz wolfie?
Seems wrong...
The time is alot different from what I've heard, further, that clockspeed isnt real..? The models in 2008 wont be at that frequency... Bizar
i sooooo hope 45nm wolf is just as fast in single threaded application...
please god please.
It`s probably an early batch, but it`s real.Quote:
Originally Posted by M.Beier
Knowing AndreYang, he`s prolly had it for a little while now :p:
Perkam
So what's the time of a 2,4GHz Wolfdale or Yorkfield? I don't want to underclock my system to test it :p:
18,7sec on E8400 at 333x7,5 in vista with alot of crap running.
E6600 2.4Ghz.
Source
Metroid.
from what i read somewhere, intel has locked all their nehalem cpus that they send out @ 2.4 gigs?? someone correct me if im wrong??Quote:
Originally Posted by M.Beier
Did anyone else notice the below 1 volt?
Yes!:)Quote:
Originally Posted by MuffinFlavored
Yes! It's in another thread here.Quote:
Originally Posted by tylerw13
My E6600 got 21secs as well, I have not ran it on my Wolfdale.
Damn....
Must... resist....
Too late. :up:
I don't have a 2.4 Ghz clock, but at 2.5 Ghz a Yorkie gets 19.03 seconds, so at 2.4 GHz I am guessing 20-21 second range.Quote:
Originally Posted by STaRGaZeR
EDIT. Yorkie at 2.4 Ghz... added, 19.984 seconds SP1M
wow. This seems to be contrary to what the Anand Results seemed to point towards in singlethreaded performance... any speculation as to the disparity?Quote:
Originally Posted by JumpingJack
I think what you will find is different apps seeing some healthy gains, others seeing none or little to nothing. On the whole I suspect healthy overall but not overwhelming single threaded jumps in performance (similar to K8 to Phenom). There are examples where, clock for clock (IPC), Phenom showed moderate to very slight gains, and in other apps nice 15-20% improvements.Quote:
Originally Posted by villa1n
In this case, SP1M -- there is info on the web that Intel buffed up loop prediction, as SP1M is inherently recursive I would postulate that the benefit we see here is coming some from that architectural improvement. Speculation on my part though....
Just looking at the SP1M, roughly 13% gain clock for clock -- which is healthy for single threaded performance ... not quite a jaw dropping as the Conroe leap over Netburst, but still healthy.
Jack
Quote:
Originally Posted by perkam
you just need to look at his new avatar ;)
Not too bad for an early batch :)
edit: I shall call Bloomfield by another name, BOOMFIELD :D
The Performance/watt is rather good. so it's 17seconds at equal frequenzy, but at a higher performance per watt than 45nm core 2, right?
Speculation of course, but seems fairly grounded ;)Quote:
Originally Posted by JumpingJack
Makes sense, hehe, but 13% on something already impressive is no small feat either. I was worried that these would only have 1-3% improvements on singlethreaded, and shine in the multithreading scenario, but seeing this, is well, very promising indeed :)
Quote:
Originally Posted by JumpingJack
waits for amd fainboys to pick this up and say nehalem is only optimized for benchmarks (just like core2) :rofl:
No offense , but that's dumb.Based on a single test which doesn't touch the improvements of Nehalem , you extrapolated to a 2% gain across all apps?Quote:
Originally Posted by villa1n
16% performance improvement on SPi1M is good. But nobody is looking at the CPUz screen. The OP was using only one module(1GB) of RAM. I guess his mainboard was running the RAM with crappy timings too, like Anand's mainboard. So, we can expect some better numbers with the retail products.
You know very well that Core and especially Penryn ( with its improved latencies for some instructions ) are the pinnacle of single thread performance.Quote:
Originally Posted by JumpingJack
With the advanced prefetchers , very large and extremly low latency L2 they keep the large number of execution units busy and offer superb single thread performance.To improve on that with a completely different cache structure ( inferior IMO for single threaded apps ) and a CPU designed for scalability and multithreading is nothing short of astounding.
People expect Nehalem to improve dramatically over Penryn , but they fail to realize how hard that is as the Core/Penryn uarch simply loves single threaded apps.
AMD K10 has a full 3 pages of improvements over K8 and can't touch Core even with a 10 foot pole in single threaded apps.Imagine what work went into Nehalem to offer even that measly 2% in Cinebench.
why bus 133mhz ?
I will not argue against this.... just in studying the emperical data -- what we have seen so far, I would also speculate that Intel started the Conroe/Penryn design cycle with a philosophy of 'let's amp up single threaded and provide good multithreaded'.... in this approach they addressed the majority of the code base in the current market while providing incentive to start transitioning to multithreaded. The dynamic allocation of shared cache is a huge singlethreaded advantage while maintaining good multithreaded performance (i.e. coherency is not an issue in shared caches).Quote:
Originally Posted by savantu
In fact, I am quite pleased personally at the progress software has made to going multithreaded overall, many apps which 2 years ago were single are now working on more cores... games (recent contemporary games) are also showing that trend. My investment in a quad core was not wasted ;)
As such, the timing for a focus on multithreaded is about right....
In short, it would appear to me that Intel delivered in terms of architecture boosts in areas exactly where they needed it to be successful on the current state of the code base....
This is one of many aspects microarchitects must design for.... i.e. what current and future code will be running on the HW.
Jack