AMD Athlon XP3200+ CPU 13th May 2003
Before we get started we need to explain the format of our reviews over the past six months. Readers will have noted that an entire review is laid out on one long page instead of 15-20 short pages. While it takes longer for a single page of this length to load we have designed the layout so that text appears first and graphics last so you can start reading before completion of loading. We decided not to split over 15-20 pages as many people find it annoying to have interruptions once they start getting into a review. It also means you can use the search option in the menu bar to go straight to parts that are of interest. We'd like our readers to let us know which method they prefer by providing feedback in our Forums. In any case, by the time you finish reading this paragraph the page should have mostly loaded.
Last year AMD increased the Front Side Bus (FSB) of their Athlon processor range in an effort to better position them against rival processors from Intel. Now they are doing it again in another 66MHz increment to a 400MHz FSB. While this may seem to be only half the speed of Intel's latest CPUs this comparison is unfair as the architecture of the Athlon range is such that it does not benefit as much as the Pentium 4 from this. Nevertheless we will investigate the performance increases to be gained from increase in the tests below.
Visually the CPU is the same as any other Barton chip with the characteristic elongated shape reminding us that there is double the cache of the Thoroughbred chip on its die.
The chip itself runs at 2.2 GHz with a multiplier of 11. There have been numerous reports of good over clocking from the Barton range but we will leave that for another article.
Of interest is the Cooler AMD sent us along with the CPU. We're not familiar with this brand but it is incredibly quiet in operation and much smaller than the behemoths many of us have grown accustomed to.
A standard 60mm fan from Ajigo.
The key seems to be the big copper plate and many thin fins.
We also like the fact that it uses all 6 lugs of the socket - a fact that other manufacturers should take note of. The time of broken center lugs due to heavy heat sinks should be left behind us.
We should also mention the memory used in this test.
These Corsair DIMMs are matched pairs and perform flawlessly at 2-2-2-6 timings.
The ASUS A7N8X Deluxe Motherboard
ASUS have been very quick off the mark with a revised version of the NForce2 chipset that supports the 400MHz FSB of the new Athlons and we used their latest board for this review.
The following are the manufacturer's specifications:
This seems fairly comprehensive so lets take a look at the board itself:
The DIMM slots are well positioned and both channels clearly marked. Details in the instruction manual clearly show how to position memory and under what circumstances the board can operate in dual channel mode. Our benchmarks showed single channel mode to be worse under every test so we will omit those results and concentrate on dual channel performance although it's useful to know that those with only a single DIMM can use the board and upgrade to dual channel performance at a later date.
The ATX power connector is well positioned and will not obstruct the air flow of the CPU although it may be awkward to access the floppy connector. This is not the case with the 12V 4-pin connector which could have been better positioned as it may obstruct exhaust fans on some cases.
While its not apparent from the perspective of the above photo, the fins on the Northbridge heat sink are quite tall. We prefer passive heat sinks because those little 40mm fans used spin at high speed and can create a whine that can be more annoying than the noise of the CPU fan.
We find the usual connectors on the back including the onboard gigabit LAN connector and onboard audio.
Onboard serial is catered to as well as a host of audio connectors.
Readers may be wondering why there is such a push toward Gigabit ethernet when 100Mbps meets their needs. Looking to the future, Gigabit is set to become the standard for networking (and not just for connecting servers but for the home too).
Here's a summary of the system and the reference systems we compared it to:
The above descriptions are accurate with the following exceptions:
The memory used was DDR333 for the DDR machines (DDR400 for this board) and PC1066 for the i850 system. DDR400 was not used (apart from this and the Canterwood D875PBZ board) as it gave worse results due to memory timing issues.
This clearly shows the 400Hz FSB.
Let's start with the synthetic benchmarks.
This test is largely dominated by the CPU bus and so there is very little difference here between the high end Athlons as they operate at roughly the same frequency. The dual CPU bus of the Dual Athlon system leads clearly.
While we see an increase in memory bandwidth as expected, the results are still dwarfed by the P4 systems. We know the Athlon does not need such a high memory bandwidth so we'll see later on how well real-world tasks are handled.
Again little difference between Athlons in a CPU dominated test. Those interested purely in number crunching will no doubt be eyeing the Dual Athlon results.
Same situation here. The most telling sign that FSB makes little difference is the P4 3GHz (800MHz FSB) being beaten by the P4 3.06GHz (533MHz FSB).
PC Mark 2002
This is a series of tests and is more comprehensive than any of the Sandra benchmarks.
And in comparison to other machines:
Here we see an increase from the MP2600 (266MHz FSB) to XP2700 (333MHz FSB) to XP3000 (333MHz FSB with extra cache) to XP3200 (400MHz FSB with extra cache). IT is obvious that not only does the extra FSB make a difference but the increase in cache with the Barton core also provides a boost.
3D Mark 2001
A superb score on a Ti4400 graphics card and wouldn't look out of place on a Radeon 9700 Pro. No doubt gamers will take delight in having an XP3200 Rig.
As good as the score is it cannot beat the outrageous achievement of the P4 3GHz on a Canterwood board..
Unreal Tournament 2003
Now for some real world benchmarks starting with UT2003 Flyby.
The XP3200 is vying for the top spot.
The XP3200 takes the crown now especially at 1024x768 which is the favored resolution of most gamers.
Let's turn to an area where we know that fast CPUs will make a difference - Audio and Video encoding. This is becoming more and more popular and is very computationally intensive with long processing times (relatively speaking that is, this field is not for those that complain about how long their Outlook Express takes to load).
For consistency we will use Jet Li's The One as our test matter. It is not interlaced and contains a mixture of action types and is not too long. There will be three tests all using Divx 5.02. Audio will be encoded separately. I will try and keep my commentary to a minimum as all configuration information is shown in the images below.
and here are the results
The increased FSB makes a huge difference in this bandwidth dominated test, leaping past the 333MHz FSB Athlons despite a similar frequency.
AviSynth and VirtualDub
No serious Divx encoder uses Xmpeg alone and it's just used by the media for benchmarking purposes so let's get serious. We ripped our source material to hard disk and created a DVD2AVI project file using forced film (it was 99% film). Loading this into Gordian Knot we first saved an .avs file with no changes at all (720x480) and no filters of any sort. This was loaded into VirtualDub with the following CODEC parameters :
After encoding we got these results:
This is almost a synthetic test as no-one converts a DVD to Divx without resizing and applying other filters.
This is all good stuff but how about a real-world test? To simulate a realistic test we added a neutral bicubic resize filter in the .avs file and used the following CODEC parameters (including two popular Pro settings) which are designed to total 700MB (when the audio is muxed in):
Which resulted in the following.
The addition of computationally heavy filters put less emphasis on the memory bandwidth and more on raw CPU speed, changing the situation dramatically. The Dual MP2600+ is well in the lead due to the extra processing required for the filters and Pro settings. The XP3200 is significantly ahead of its siblings.
What about audio? We took the AC3 track from the above sample material and used HeadAC3he to convert it into Vorbis format so our final muxed file could have Ogg containment. There isn't space here to go into the advantages of Ogg Vorbis over MP3 and AVI so let's just say that Vorbis sounds about the same as MP3 for half the file size or twice as good for the same file size (that is subjective though).
Since it is more meaningful to show throughput than time taken (which depends on the length of the source) we display the results thus:
This is another test that only uses a single processor and is CPU intensive but the XP3200 scores well here.
AMD refuses to accept second place to Intel and counters every initiative with one of their own. Without this increase in FSB Intel would have a clear lead with their 800MHz FSB CPUs and chipsets. While banking on the Opteron/Athlon-64 for eventual victory AMD has released what is probably the last incarnation of the 32-bit Athlon, giving them some breathing space until their desktop Athlon-64 processors arrive. Recent showings from Microsoft are encouraging and it looks like a 64-bit version of Windows will be ready for the Athlon-64 launch.
Should you buy an XP3200? It all depends on the price. If AMD price it reasonably, it will represent good value for money and allow owners of DDR400 memory to make the most of it. It is definitely good enough to prevent AMD owners who are looking to upgrade from jumping on the Intel bandwagon. First time buyers can be reassured that it will perform on a par with the fastest Intel has to offer.
We would like to thank AMD UK for the review sample XP3200 CPU.
We would like to thank CORSAIR for the review sample Dual Channel DDR Memory Kit.
We would also like to thank MICROSOFT UK for the review sample Windows XP Pro and their technical assistance.
All trademarks are the property of their respective owners.