Processor benchmarks: Intel versus AMD

Processor benchmarks: Intel versus AMD

Summary: Processors are now called upon to handle everything from simple text and graphics, through 3D games, to serious tasks like video rendering. We put Intel and AMD's desktop CPUs through the labs to see how they cope.

SHARE:
TOPICS: Hardware, Reviews
48

This evaluation of current desktop processors utilises over 60 benchmark tests including office and multimedia software, 3D games, Internet applications, video rendering and compression. We have used benchmarks that are relevant to a range of market sectors in order to get a balanced view of CPU performance. However, in an ideal world, you should also run your own mission-critical applications on any processor that you're considering.

Of course, performance is only one aspect of a processor purchase decision. For example, the Athlon 64's support for the NX (No Execute) feature safeguards it from certain virus attacks, and could be reason enough to choose an AMD processor. And if you're after a quiet PC, then AMD's chips have clear advantages over Intel's latest 'Prescott' Pentium 4. The power consumption of the Athlon 64 is lower than that of the Pentium 4 thanks to AMD's use of Silicon-on-Insulator (SOI) technology. The Athlon's 64's 64-bit capability is also a potential advantage, although this feature remains largely unused because of the missing operating system support -- 64-bit Windows XP has now been delayed until 2005.

Power consumption

System
Idle
Max

Athlon 64 3800+ (Nforce 3) 91W 172W
Athlon 64 3800+ (KT800 Pro) 82W 162W
Pentium 4 560 (925X) 155W 258W

Note: The power consumption figures quoted in the table above refer to a complete system with otherwise identical components.

 

Topics: Hardware, Reviews

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.

Talkback

48 comments
Log in or register to join the discussion
  • Folks:

    The slide and the text don't match on all of the charts. In at least 2 cases, the text indicates Intel is the winner while the charts show that AMD is clearly superior. Which is correct?
    anonymous
  • Great review! I appreciate the input as do others I'm sure. I'm about to build a pc and have had a hard time deciding Intel or AMD.Your article will be a definetly be a factor!
    anonymous
  • Good review, although I'd like to see a Visual C++ compilation benchmark or something. I spend a lot of time compiling software and I want to be able to point to a benchmark which compiles several different types of code (heavily templated code, STL, MFC, the effect of compiling with optimisations etc)
    anonymous
  • Strange how you hide the benchmarks from view unless you click on the link. Could this be because if you check them out, they don't match the conclusion? From what I could see AMD won the MAJORITY of the tests, while Intel won a few. Unless you are doing the few things that the Intel chip is better at, the AMD chip is the best choice by far.
    anonymous
  • Whose computers are not needing to multitask all the time? Email, web, antivirus and applicatiions software, not to mention database software are usually running on machines concurrently. Software using threading would also have an impact on requiring multitasking.

    Tests that remove multitasking do not seem very valid in today's world.
    anonymous
  • Why do the Charts not match the review. I see AMD out performing Intel in almost all of the test and the review says the reverse. For someone to get a true review, you should at least make the chart match the text in the review.
    anonymous
  • Multi-tasking means USING multiple programs at the same time (i.e. using outlook while encoding an MP3), not just having multiple programs open. HT is over-hyped! The value is limited for the majority of users. (Think about it, how often do you actually actively use 2 programs at the same time??)
    anonymous
  • FX53 is the fastest AMD workstation cpu.
    anonymous
  • Text and Graphics do match, you need to look at the scale indicator, as it reads more is better in some cases and more is worse is others.
    anonymous
  • This review is clearly flawed. Chips that are clocked higher of the same brand and design underperform their lower clocked cousins on many tests. This is not possible.
    anonymous
  • Just to confirm: some of the test metrics are 'bigger is better' (e.g. frames per second); others are 'smaller is better' (e.g. seconds). This should explain any confusion over text/chart correspondence.
    anonymous
  • Hi, I have a AMD Athlon 2400 (2.0)ghz XP processor with 512MB of RAM ; I use it everyday and playgames. I bought it for $2200 CN in 2003 and now if i sell it i don't even get $1500 CN. Thats the difference you get after buying a AMD processor. So what i think is that you should but a Pentium4 processor :D
    anonymous
  • Although windows is not 64 bit, you can run 64bit linux right now.

    Why are you so focused on windows. Athlon64 is an excellent processor for running 64bit linux. Nvidia has fixed 64bit drivers for their gfx cards also.

    Suse, Gentoo, Mandrake, Fedora and probably many more all have AMD X86_64 distros ready.
    anonymous
  • If you overclock a cpu, you may create imbalance in the delicate cache and instruction hierarchy, this may result in a timing problem and cache miss having to wait for next cycle.

    That's why often celerons with little cache are the best to overclock.

    If you try overclocking an itanium2 it wont even work.
    anonymous
  • how do those compare with the Apple G5?
    anonymous
  • AMD's Athlon 64 CPUs clearly outperform Intel's Pentium 4 even though they are clocked 1.2 GHz less, use DDR and not DDR2 SDRAM, they don't don't have Hyper Threading and have half the cache of Prescotts. This shows that AMD's theory of performance based on Work done per clock cycle multiplied by clock speed stands correct. Also look at the massive power consumption and heat generation of the Prescotts. Their fans make so much noise!!! Wake up guys... Prescott sucks.... absolutely, AMD64 is gr8.
    anonymous
  • NOTHING! depreciates faster than a computer. If you can get 66% of your original price on a year old computer you're doing really well. The only difference here between a P4 and an AMD is the P4 would have cost more originally, so you'd lose even more on depreciation. Sounds to me like you don't know very much about computers, or computer pricing.
    anonymous
  • The article says the Prescott wins on apps that are optimised for SSE2, however I was sure the Hammer was ment to support SSE2? Is this not true?
    anonymous
  • This benchmark clearly shows that a chips Core Speed is NOT everything. with a chip that clocks slower than another AMD can still compete Equally if not better at some of the Benchmarks.
    anonymous
  • Hi Folks: Just an observation here which is, that many people are reading this review and not understanding what is being said. Yes, some of the charts are marked incorrectly, but the comments by the reviewer set that straight. Yes you lose money when you try to sell a computer a year after you buy it. That's why it would be classed as "Used", and why people will not pay the "new" price, because it's "used", and so is worth less than "new". As for who is the better chip maker, well the reviewer said it well. It depends on your particular situation. Gaming, AMD wins. Video editing, Intel wins. power consumption, AMD wins. Multitasking, Intel wins, and so on and so on. In technology, it's more important to keep an open mind, than it is to be "brand loyal", which is a 'consumer' perspective which can lead to heartache and financial ruin (I exagerate....lol). The people who are technical (engineers, technicians, etceteras) try to be as objective as possible, because they want the best product for the job (I fall into this category). It's also important to understand what you read about a product, or if you don't, then to seek the advice of someone who does, and then listen to what they tell you, and act on it.
    cheers
    anonymous