Prescott's Little Secret

In learning about Prescott and trying to understand just why Intel did what they did, we came to realization: not only is Prescott designed to be ramped in speed, but there was something else hiding under the surface.

When overclocking a processor, we can expect a kind of linear trend in performance. As Northwood's speed increases, its performance increases. The same is true for Prescott , but what is important to look at is increase in performance compared to increase in clock speed.

Prescott 's enhancements actually give it a steeper increase in performance per increase in clock. Not only can Prescott be clocked higher than Northwood, but as its clock speed is increased, it will start to outperform similarly clocked Northwood CPUs.

We can even see this trend apparent in our limited 3 clock speed tests. Most of the time, the 2.8GHz Northwood outperforms the 2.8GHz Prescott, but the percentage by which Prescott is outperformed decreases as clock speed increases, meaning that the performance delta is significantly less at 3.2GHz.

Business Winstone 2004

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
1.48%
3.00GHz
0.00%
3.20GHz
0.46%

Content Creation Winstone 2004

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-3.57%
3.00GHz
-5.67%
3.20GHz
-5.43%

SYSMark 2004

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
1.19%
3.00GHz
2.27%
3.20GHz
2.70%

SYSMark was one of the only applications to show a positive performance improvement for Prescott, and we see that with clock speed that advantage continues to grow over Northwood. Keep on reading, it gets even more interesting...

Aquamark - CPU Score

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-2.87%
3.00GHz
-2.47%
3.20GHz
-0.84%

Halo

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-0.18%
3.00GHz
-0.18%
3.20GHz
0.00%

GunMetal

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-0.29%
3.00GHz
-0.58%
3.20GHz
-0.29%

UT2003 - Flyby

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-2.62%
3.00GHz
-1.46%
3.20GHz
-0.86%

Clock speed goes up, Prescott performs more like Northwood.

UT2003 - Botmatch

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-3.55%
3.00GHz
-3.09%
3.20GHz
-2.05%

Warcraft 3

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
1.96%
3.00GHz
1.12%
3.20GHz
0.72%

We continue to see that as clock speed increases, the gap between Prescott and Northwood decreases as well.

Quake III Arena

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-1.33%
3.00GHz
-0.49%
3.20GHz
1.28%

Quake becomes the textbook case of what should happen to Prescott performance as clock speed increases; although initially it is slightly slower than Northwood at 2.80GHz, by the time we reach 3.2GHz Prescott holds an advantage over a 3.2GHz Northwood. This is exactly the trend we expect to see over time, especially once we get close to 4GHz.

Jedi Knight: Jedi Academy

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-7.63%
3.00GHz
-6.85%
3.20GHz
-7.04%

Wolfeinstein: Enemy Territory

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-5.53%
3.00GHz
-4.94%
3.20GHz
-3.79%

DivX Encoding

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-1.30%
3.00GHz
-0.61%
3.20GHz
-0.38%

3dsmax R5

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-9%
3.00GHz

-9%

3.20GHz
-9%

There will be some scenarios that do not work in Prescott's favor, and in those cases Northwood will still remain faster.

Lightwave 7.5

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-7.7%
3.00GHz

-7.3%

3.20GHz
-6.8%

Although to a much lesser degree, we are seeing the same sort of scaling with clock speed in applications like Lightwave. It looks like our theory about Prescott's performance is correct.

Visual Studio Compile Test

  Percentage Increase in Performance from Northwood to Prescott
2.80GHz
-8.2%
3.00GHz

-5.7%

3.20GHz
-3.8%

Much like Quake, our compile test is another perfect example of what clock scaling will do to the Northwood/Prescott gap. As the clock speed goes up, the performance delta decreases.

Development Workstation Performance Final Words
POST A COMMENT

104 Comments

View All Comments

  • Stlr22 - Sunday, February 1, 2004 - link

    post*
    Reply
  • Stlr22 - Sunday, February 1, 2004 - link

    KristopherKubicki

    Earlier you said that I should read the article.
    What was your point? What was it about my first pot that you disagreed with?
    Reply
  • KristopherKubicki - Sunday, February 1, 2004 - link

    #7:

    I agree 100% with Anand and Derek. This processor will be a non-event until we get in the 3.6GHz range. Similar to Northwood's launch.

    #10:

    Check out our price engine. We have already been listing the processor a week!

    http://www.anandtech.com/guides/priceguide.htm

    http://www.monarchcomputer.com/Merchant2/merchant....

    Reply
  • cliffa3 - Sunday, February 1, 2004 - link

    In the table on page 14 it shows that the 90nm P4@2.8 will have a 533 MHz FSB, but is that the case? I did some quick google research and can't find anything to support that...please confirm or correct, thanks. Reply
  • NFactor - Sunday, February 1, 2004 - link

    Yes, I must agree this is an amazing article, one of the best i have ever read. Thanks. Reply
  • Xentropy - Sunday, February 1, 2004 - link

    VERY interesting article. Thank you Anand and Derek! One of the best I've read on Anandtech, and I consider yours the best hardware site on the net!

    One correction, on page 7, you say, "if you want to multiply a number in binary by 2 you can simply shift the bits of the number to the right by 1 bit," but don't you mean shift to the left one bit (and place a zero at the end)? It's much like multiplying a decimal number by ten for obvious reasons.

    Anyway, it looks like the Prescott is somewhat of a non-event at this time. Just new cores that perform fundamentally the same as the current ones at current speeds. The real news will come later; Intel has just positioned itself for one hell of a speed ramp to come. Northwood was clearly at the end of the line. One analogy, I suppose, would be that Intel didn't fire any shots in the CPU war today, but they loaded their guns in preparation to fire.

    The coming year will be an exciting one for us hardware geeks. I'm interested in seeing how higher clocked Prescotts play out as well as whether anything 64-bit shows up before 2005 to support AMD's stance that we need it NOW.

    Again, thanks for a very thorough article!
    Reply
  • Stlr22 - Sunday, February 1, 2004 - link

    KristopherKubicki

    So what's your take on these new Prescotts?
    Reply
  • KristopherKubicki - Sunday, February 1, 2004 - link

    Anand scolded me for not reading the article :( I only read the conclusion and the graphs. Turns out the decision making isnt as clearcut as it sounds.

    As for the thing with the inquirer. Well, lots of people had prescotts. We had one back in August I believe. The thing is they were horribly slow - 533FSB 2.8GHz. Everyone drew the conclusion that these were purposely slowed processors that were jsut for engineering purposes. While the inq benched this processor, most people didnt just becuase they were under the impression this was not to be the final production model. Hope that clears up some discrepancy about the validity.

    Cheers,

    Kristopher
    Reply
  • wicktron - Sunday, February 1, 2004 - link

    Hehe, I guess the Inq was right about this one. Where are all the Inq bashers and their claim of "fake" benchies? Haha, I laugh. Reply
  • Stlr22 - Sunday, February 1, 2004 - link

    KristopherKubicki - "read the article..."


    lol that might be a good idea, as I only broswed it and read the conclusion. :D
    Reply

Log in

Don't have an account? Sign up now