AMD Athlon XP2700 7th December 2002
Although the Athlon XP2700 was officially released several weeks ago supplies in the UK have been difficult to obtain with most retailers showing long lead times. This situation is beginning to change and it seems likely that there will be plenty of systems using this processor in stores in time for Christmas. We received one of these last week from AMD along with an ASUS A7N8X Deluxe motherboard which is an NForce2 design and should allow a thorough evaluation of the improvements we will get from the new 333MHz front side bus on the XP2700.
One of the first things that struck us about the CPU was the small size of the core and its rectangular shape which is no doubt due to 0.13 micron shrink. Here's a glimpse of the ASUS motherboard, of particular note is the colour coded DIMM slots. We used two sticks of Crucial DDR333 PC2700 memory to take advantage of the dual channel memory controller.
The board didn't allow us to change multipliers so we could only increase the FSB speed. 183MHz were reached without problem but we are sure we could have gone higher with DDR400 memory and the right AGP and PCI dividers. Tests are conducted at stock speed but there does seem to be considerable room for overclocking.
The system is shown running slightly higher than spec but the difference is miniscule.
Here's a summary of the system and the reference systems we compared it to:
The last two are primarily used for Desktop Video and so have weak 3D graphics so we will not be comparing them for some benchmarks. This leaves the Athlon XP2700 up against Intel's flagship P4 3.06GHz with Hyper-Threading.
As expected the NForce2 board is no match for the PC1066 memory in the P4 system.
Again the bandwidth of the P4 system shines through in this synthetic benchmark.
Things are getting closer now.
Hyper-Threading appears to give the P4 a big boost and the Athlon XP2700 struggles to keep up
PC Mark 2002
The hard disk scores are not relevent as two completely different drives were used. The CPU score show the Athlon to be almost as good as the P4 despite the latter running almost 50% faster.
3D Mark 2001
There is only a 5% difference between the rival systems.
Unreal Tournament 2003
Now for some real world benchmarks starting with UT2003 Flyby.
The Athlon is right up there with the P4 across all resolutions and actually manages to pull ahead at the higher ones. Let's examine the Botmatch scores.
Here we see something completely unexpected - the Athlon leaves the P4 behind and shoots ahead, especially at the higher resolutions. We repeated this test several times with the same results. Looks like the 333MHz FSB Athlons are going to be highly sought after by games players.
Let's turn to an area where we know that fast Dual 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 only thing that save Intel's flagship P4 from being shamed is Hyper-Threading. The Athlon XP2700 is even faster than our Dual Athlon MP1800 rig - no doubt largely due to the increased FSB speed.
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:
Here we see the P4 pull ahead again mainly due to the P4 optimisations in VirtualDub. The XP2700 is still on a par with the Dual Athlon MP1800 rig.
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.
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:
We can see another impressive performance from the Athlon XP2700.
AMD have a winner on their hands with the XP2700 and the increased front side bus has given them some breathing room until their Hammer series of processors is made available. Rumours of Barton sporting a 200MHz FSB abound and if true will allow AMD to continue challenging Intel in the value segments for some time to come. In many practical benchmarks the Athlon was alongside or even ahead of the P4 3.06GHz. Given the fact that this CPU can be picked up for a street price of under £300 (inclusive of UK sales tax) it is unquestionably a winner in the price/performance stakes and as volumes increase we should see that price fall further in the near future.
All trademarks are the property of their respective owners.