• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

More Northwood Pentium 4 at 2.0 and 2.2 GHz @ Xbit

Damn, the Northwood seems to be scoring nicely in a lot of those benchmarks. The only thing that dissapoints me is the fact that their setup with the 2.2A failed a test. That is something not usually displayed by Intel (Or AMD for that matter) rigs.
 
I wonder why Xbit-Labs used so many SSE/SSE2/P4 specific optimized benches, much more so then they usually do. And they even used Intel's own P4 benchmark suite.
Unless the purpose was specifically to gauge the relative improvement from Willamette to Northwood it didnt seem to me as though many of the benches were very realistic towards the majority of the software.
 
Wow, the 2.0A seemed to do a lot better in these tests winning 20 out of 31 tests over the 2000+. And that was a pretty comprehensive test. Had a ton of benchies.
 
I wonder why Xbit-Labs used so many SSE/SSE2/P4 specific optimized benches, much more so then they usually do. And they even used Intel's own P4 benchmark suite.
Unless the purpose was specifically to gauge the relative improvement from Willamette to Northwood it didnt seem to me as though many of the benches were very realistic towards the majority of the software.

Yes. But its almost the same as doing a test that has a majority of wav conversion,rendering,decoding,etc which is known to be XP's strength
 
Bovinicus, maybe the 2.2 P4 was too fast for the game. It seems that a lot of division by 0 errors are the result of some calculation being performed faster than a program expected.
 
Perhaps the problem is similar to what used to happen with some PII processors when running software created by specific C++ compilers.

What I'm talking about...


This review is very impressive. Especially the benefits found with the SSE2 optimizations. I think the performance crown will definitely be on Intel's processors for the next month or two.
 
I'm not sure there can be such a thing as a performance crown anymore...

It all comes down to what software one decides to run on a computer. For example, the LAME MP3 encoders made the P4 look like a snail, and the eJAY MP3 encoder made the Athlon look like a lame duck.
 
Yes. But its almost the same as doing a test that has a majority of wav conversion,rendering,decoding,etc which is known to be XP's strength

That's not the same thing at all. Xbit used, as Rand said, Intel's own P4 benchmark suite. Some of those tests weren't very realistic. In addition, XBit somehow forgot that AMD released an SSE patch for Content Creation, which is why the P4 rapes and pillages the Athlon XP in that benchmark, among several others.

I'll wait for Anand and company to round out the results.
 
So throw 6 more tests in AMD's favor and you have a split 15/15 for 2 pretty equally priced CPU's.

In all the benchmarks Pentium 4 processors built on Northwood core appeared faster than their competitors from AMD. To tell the truth, this is very sad news for AMD, bearing in mind that Athlon XP used to be the leader in DRV-07 and DX-06 tests before Northwood announcement. However, larger L2 cache and higher clock frequencies of the new Pentium 4 CPUs did a great job having made Athlon XP not so attractive for professional OpenGL applications.

Ofcourse Thoroughbred is just around the corner. Anyway if you only believe Anand's reviews then why read any others? I do agree though Anand's are more reliable.
 
Anyway if you only believe Anand's reviews then why read any others? I do agree though Anand's are more reliable.

I trust the following web sites for reviews:

1. Anandtech
2. HardOCP
3. Aceshardware
4. Tech-Report
5. Tomshardware (minus the terribly bloated and loaded terminology, and even some numerical mistakes lately...).
6. Firingsquad

Among several others that I'm currently blanking out on at the moment. Anandtech is definitely up there though.
 


<< X-Bit must be doing a little more Intel advertising these days 😀 >>



Just to clarify something, I am NOT implying XBit has intentionally biased their suite of benchmarks in ANY way.
I do respect XBit and tpically their reviews are fairly decent.
Nor do I question that their results are indeed accurate.

I merely am curious as to why they used so many SSE2 optimized benchmarks, and benchmarks that are specifically optimized for the Pentium 4, and ignoring the Content Creation patch that allows for the AthlonXP to utilize it's SSE capabilities, along with using Intel's own benchmark suite which is obviously been coded specifically for said processor. I do not doubt there is a valid reason, nor am I saying XBit has intentionally chosen said benchmarks to favor the P4.



<< Yes. But its almost the same as doing a test that has a majority of wav conversion,rendering,decoding,etc which is known to be XP's strength >>



Only if those programs were to contain 3DNow! optimizations, or were specifically coded for the K7 core.
Otherwise they would only be testing something that is in-line with the strengths of the K7 core, which is quite fine as would be testing an application that is inline with the strengths of the P4 core.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top