Athlon XP 3000+ vs. P4 3.06 GHz

2z

OSNN Gamer
Joined
12 May 2002
Messages
2,439
Quake 3 Arena 1024x768/32/85hz
frames per second

XP 3000+ = 311.2
P4 3.06 = 348.9

All five time-demo runs of Quake 3 Arena point in the same direction. The Athlon CPUs with Barton cores benefit considerably from the double L2 cache. They still don't perform quite as well as the P4 at 3.06 GHz. How important or big the gap is may be a subjective opinion.

Pentium 1
AthlonXP 0

..............................................

3D Mark 2001 SE / ATI Radeon9700pro / 1024x768/32/85hz

XP 3000+ = 15655
P4 3.06 = 15862

The 3D Mark 2001 determines DirectX 8's Direct3D performance under Windows XP. The AMD Athlon XP 3000+ gives the Intel Pentium 4 3066 a run for its money - the P4 manages to beat it by a mere 207 points!

Pentium 2
AthlonXP 0

.............................................

Unreal Tournament 2003 / ATI Radeon9700pro / 1024x768/32/85hz

XP 3000+ = 215.1
P4 3.06 = 212.5

Another blockbuster game that supports DirectX8 is Unreal Tournament 2003. The Athlon XP 3000+ takes first with 215 frames, ahead of the P4 3066 with its 212.5 frames. However, this is the only benchmark in our portfolio where the Athlon XP has a clear lead over its competitors.

Pentium 2
AthlonXP 1

.............................................

mp3 Makers Platinium 178 meg file

XP 3000+ = 185 sec
P4 3.06 = 73 sec

Pentium 3
AthlonXP 1

.............................................

Pinnacle Studio 8.3.18 mpeg2 rendering

XP 3000+ = 243.8 sec
P4 3.06 = 224.9 sec

With 243.8 seconds, the AMD Athlon XP 3000+ was somewhat slower at creating an MPEG-2 film using Pinnacle Studio 8.3.18 The P4 at 3.06 GHz leads the factory-clocked PCs.

Pentium 4
AthlonXP 1

..............................................

Main Concept 1.3

XP 3000+ = 341.0
P4 3.06 = 293.4

The Athlon XP 3000+ is an average performer in encoding DV video (1.2 GB) to MPEG-2 using the Main Concept Encoder. In other words, the enlarged L2 cache doesn't appear to have any impact at all, while encoding speed depends directly on CPU clock speed. The P4 gets a considerable boost from the HT optimizations.

Pentium 5
AthlonXP 1

...............................................

Multimedia Performance: PC Mark 2002 cpu bench

XP 3000+ = 6646
P4 3.06 = 7575

Pentium 6
AthlonXP 1

...............................................

Multimedia Performance: PC Mark 2002 memory bench

XP 3000+ = 5853
P4 3.06 = 7726

Pentium 7
AthlonXP 1

In both benchmark tests, the Pentium 4 3066 is faster than the AMD Athlon XP 3000+. And, yet again, the Athlon XP 3000+ is clearly slower than the XP 2800+.

................................................

SiSoft Sandra 2003 Benchmarks: CPU

XP 3000+ = 3257 - 8074
P4 3.06 = 5803 - 9342

Pentium 8
AthlonXP 1

SiSoft Sandra Benchmark 2003 reveals that the Athlon XP 3000+ is struggling to keep up with the competition. As you know, though, this benchmark does not reflect any realistic performance scores. In CPU Bench, the XP 3000+ has to bow down before the XP 2700+ - the expanded L2 cache doesn't make any difference.

..............................................

Sysmark 2002

XP 3000+ = 251
P4 3.06 = 289

Pentium 9
AthlonXP 1

The Athlon XP 3000+ falls far behind the Pentium 4 3066 in some partial areas. One more thing about all AMD Athlon XP CPUs: compared to Intel's models, the AMD processors lag slightly behind because they lack enhancements. Plus, the integrated HyperThreading functions give the Pentiums a slight advantage.

..............................................

Archiving: Winrar 3.11

XP 3000+ = 69
P4 3.06 = 54

Pentium 10
AthlonXP 1

Archiving is a very practical application. The new Winrar 3.11 archiving software was used under Windows XP to compress a 178 MB WAV file while the clock was running. The Athlon XP 3000+ performed perceptibly better than a model with the same clock speed (XP 2700+) but half the L2 cache. This results in a difference of three seconds.

...............................................

3D Rendering: Newtek Lightwave 7.5

XP 3000+ = 291.8
P4 3.06 = 183.8

Pentium 11
AthlonXP 1

The Lightwave benchmark clearly brought the enhancements of the Pentium 4 processors to light - the Athlon XP 3000+ placed in the center of the pack, trailing the XP 2800+.

...............................................

3D Rendering: Cinema 4D XL 8.001

XP 3000+ = 123
P4 3.06 = 94

Pentium 12
AthlonXP 1

What a scenario - the Athlon XP 3000+ trails the higher-clocked XP 2800+! Their scores differ by six seconds, putting the model rating in a very dubious light. The crème de la crème is the P4 at 3.06 GHz,

...........................................

3D Rendering: 3D Studio Max 5.1

XP 3000+ = 105
P4 3.06 = 94

Pentium 13
AthlonXP 1

The Athlon XP 3000+ is slower than the XP 2800+, while the P4 takes the lead.

........................................

Multitasking: 3D Studio Max 5.1 and Main Concept 1.3

P4 3066 = 126 sec
XP 3000+ = 185 sec

Pentium 14
AthlonXP 1

AMD should revisit its model-numbering system before it loses users' trust.

Toms Hardware

:cool:
 
Disappointing results...

Oh well, still waiting for Hammer than.

And yes, I agree about the CPU model numbering. I was really confused reading that table of AMD CPU:s at Tom's.
 
twozigzag? what is the point of this thread?

different reviewers will point in different directions...

do not forget that THG is hardly regarded as a source for ACCURATE information by many forums :)

I mean they did procliam the gf FX ultra as the 2nd coming... and were the ONLY top site not to post IQ comparisons... :)

try out a few other websites and lets see the figures shall we?

from www.anandtech.com without all those ridiculous oc'd numbers et al...

it is a fairer picture and yes intel does 'win' some benches and so does amd... the performance crown cannot be given to one or the other...

all I have to say is perhaps THG needs to rethink their strategy as a VALID reviewing website... their reviews have been going downhill for some time... and really one only has to look as far as some of their benches earlier this month to see that...

Content Creation Performance
Content Creation Winstone 2003

intel = 49.5
amd = 40.9

Internet Content Creation Performance
Internet Content Creation SYSMark 2002

intel = 419
amd = 334

General Usage/Office Performance
Business Winstone 2002

amd = 39.9
intel = 34.9

General Usage Performance
Office Productivity SYSMark 2002

amd = 215
intel = 213

Gaming Performance
Unreal Tournament 2003 - Flyby Benchmark - 1024x768 Maximum Detail

amd = 214.9
intel = 205.5

Gaming Performance
Unreal Tournament 2003 - Botmatch Benchmark - 1024x768 Maximum Detail

amd = 74.7
intel = 70.4

Gaming Performance
3DMark 2001 SE - 1024x768

intel = 15304
amd = 15243

Gaming Performance
Quke III Arena - 1024x768x32 High Quality

intel = 328.7
amd = 305.9

Gaming Performance
Jedi Knight 2 - jk2ffa - 1024x768x32 High Quality

intel = 173.1
amd = 168.2

Gaming Performance
Comanche 4 - Benchmark Test - 1024x768x32

intel = 59.1
amd = 55.5

MPEG-4 Video Encoding Performance
MPEG-2 to DiVX Conversion using XMpeg 4.5 & DiVX 5.0.2 (Frames per Second - Higher is Better)

intel = 97.9
amd = 71.1

Windows Media 9 Encoding Performance
Converting DVD to 2Mbps VBR - Lower is Better

intel = 8.13
amd = 10.23

Quicktime 6.0 Pro Encoding Performance
Converting DVD to MPEG-4 Internet Stream - Lower is Better

intel = 2.7
amd = 2.93

3D Rendering Performance
3DSMAX R5 - SinglePipe2.max (Render Time in Seconds - Lower is Better

intel = 169
amd = 227

3D Rendering Performance
3DSMAX R5 - Underwater_Environment_Finished.max (Render Time in Seconds - Lower is Better)

intel = 237
amd = 302

3D Rendering Performance
3DSMAX R5 - 3dsmax5_rays.max (Render Time in Seconds - Lower is Better

intel = 18
amd = 22

3D Rendering Performance
3DSMAX R5 - CBALLS2.max (Render Time in Seconds - Lower is Better

intel = 33
amd = 44

3D Rendering Performance
3DSMAX R5 - vol_light2.max (Render Time in Seconds - Lower is Better)

intel = 15
amd = 22

3D Rendering Performance
Maya 4.0.1 - rendertest.ma (Render Time in Seconds - Lower is Better)

intel = 62
amd = 65

3D Rendering Performance
Lightwave 3D 7.5 - raytrace (Render Time in Seconds - Lower is Better)

intel = 101.5
amd = 131.2

3D Rendering Performance
Lightwave 3D 7.5 - sunset (Render Time in Seconds - Lower is Better)

amd = 43.7
intel = 51.2

3D Rendering Performance
Lightwave 3D 7.5 - radiosity_reflective_things (Render Time in Seconds - Lower is Better)

intel = 48.2
amd = 89.8

-------------------------------------------------------------------------------

basically what the figures state is that the amd processor runs quite close to the pentium processor in many apps... it lags behind in certain professional multimedia benches... but it does run faster in other areas...

the one area that amd owns intel is office applications... there is no substitute for that... and in gaming... once an intel strongpoint... amd is keeping up very very well...

overall this is a decent launch for amd... not as crap as some others are pointing out...

for us gamers/website users/programmers... this is a very nice solution... to be able to buy a 2500+ barton for sub 180 dollars is quite nice... plus this device runs cooler than the t'bred B's and should scale on up to the 3200+ part pretty well it would seem...

a few more optimizations and this processor is a very nice stopgap between the t'bred's and the upcoming hammer core that everyone is talking about...

intel's own prescott/prestonia parts will ship soon and keep the pressure on amd... and the 64-bit parts from amd will do the same to intel...

all in all... price cuts galore and everyone happy :)
 
Thanks for those facts, its quite clear that AMD are using the '+' range to its full advantage, 3000+ at some things! :eek:

Well my Q is WHAT ?

From what I can see from the results that Sazar posted, (Render Time in Seconds - Lower is Better) alone the AMD chip takes 3mins 30secs longer than the Intel one.
I think this chip should have been called the '3min+' :D :D :D

Nearly a good post Sazar, but the initial "twozigzag? what is the point of this thread?" is quite harsh. The point of this thread is so ppl like yourself and 2zz can discuss your findings and ppl like myself can look at the results of various benchmarks without having to search the www and wait for all the different pages to load.
 
Originally posted by Goldy
Thanks for those facts, its quite clear that AMD are using the '+' range to its full advantage, 3000+ at some things! :eek:

Well my Q is WHAT ?

From what I can see from the results that Sazar posted, (Render Time in Seconds - Lower is Better) alone the AMD chip takes 3mins 30secs longer than the Intel one.
I think this chip should have been called the '3min+' :D :D :D

Nearly a good post Sazar, but the initial "twozigzag? what is the point of this thread?" is quite harsh. The point of this thread is so ppl like yourself and 2zz can discuss your findings and ppl like myself can look at the results of various benchmarks without having to search the www and wait for all the different pages to load.

the reason I asked the question is that the figures from various websites list different things...

it is generally agreed... even by myself... that the athlon cpu lineup is on its last legs... its a fact... there is no denying it... but it is also a fact that getting blatantly one-sided postings from one site is not sufficient to paint an accurate picture of a product...

I did not present any such picture with my post and tried to be fair and accurate... twozigzg did not do anything of the sort... IMO... which is what my comments were trying to point out...

those who read my posts would have seen my posts on the nvidia gf FX ultra... but even I was not so much of a fanboy as to post all the benches that the card did not do well @ and proclaim one card over another... I proclaimed one to be more of a disappointment for other reasons...

also THG does not understand the naming convention that AMD uses... at least not as well as 'lesser' reviewing websites...

and like I said :) amd is not as optimized as intel for some benchmarks.. the reviewers (even THG) will say the same... hence intel is a better solution for certain apps/fields... and amd more so for others because of the way it does its math processing :)
 
What about the prices? I always liked the AMD's because of the lower costs better OC'ing abblities
 
Sazar - The results are 1 sided enough.

Sazar's benchmarks.....Intel 17 - AMD 5

Tzz's benchmarks.........Intel 14 - AMD 1

That's both THG and Anandtech that think the AMD chip is Garbage.

:D :D :D
 
Originally posted by Kermit
What about the prices? I always liked the AMD's because of the lower costs better OC'ing abblities

@ the mo the prices are subject to change because intel is saying they are going to cut prices and amd will undoubtedly match them...

the best overall deal is the 2500+ probably :) ... the retail price point is around 170-180 bucks... the 3000+ @ the mo is OEM for around 580 though this will likely drop as time progresses and amd tries to stay competitive...
 
Originally posted by Kermit
Thanks Saz


wow $580 huh

Will look into the 2500+ thanks

yup... 580 :)

for some reason amd has chosen a price point for its flagship @ around 30-50 bucks below the competitors pricepoint... it makes sense when considering its office benches... BUT it should probably be retailling around the 500 buck mark not too long from now per projected price cuts... :)
 
Always remember this. Although Intel may be leading, their processors are inefficient. They rely on raw power rather than optimising their architecture. AMD stuffed up something though if their 2800+ is faster than 3000+ (i don't understand how...)

AMD's are more efficient. Intel are faster.

At the moment if a 3.06 Intel is same price as a AMD 3000+ i'd go for the Intel purely because of the benches. But of course if the AMD is cheaper... You know who wins =)

2.2 ghz is only slightly behind a 3.06ghz... hrms... inefficiency is a tad obvious....

hrms... the new Xeon's are looking quite promising... RISC arch instead of CISC... should be worth a look... if only it did 32-bit =P
 
For me in the end, it's price... and not just the chip, but the mobo it goes on.. I'll be looking to upgrade in about a month or so. When that time comes, whatever the better price is, that'll be the deciding factor.

I'm mainly baised towards AMD though, as I know a few people that work at Intel here locally at one thier plants. They don't actually treat their employees very well from what I can tell (and they tell me).

-JG
 
Originally posted by TwoZigzagColt45
Sazar - The results are 1 sided enough.

Sazar's benchmarks.....Intel 17 - AMD 5

Tzz's benchmarks.........Intel 14 - AMD 1

That's both THG and Anandtech that think the AMD chip is Garbage.

:D :D :D

thats pure flame bait twozigzag...

I get accused of being a fanboy all the time but I think you really take the cake m8... at least I back up my 'fanboy' comments with some sort of info about the architecture...

btw there is no comparison in real world tests and there is no question about which processor has the superior architecture...

amd wins out in both cases... and they are running @ my local store @ between 30-50 bucks cheaper for the ultra high end flagships of both... though most people will be inclined to buy the lower clocked parts...

:rolleyes:
 
In recent years the Intel/Other CPU argument is/has become a small issue unless you are at the state of the art end of the spectrum, everyone ease buys on the price/performance ratio, a benchmark yet to be devised correctly (accept in your head).

I have long ago advocated the use of not faster CPU’s but multiple CPU’s yet they still have not arrived to the mainstream market even though they have been in use commercially for over twenty years now. You are being conned by the CPU manufactures to buy their products. Large Companies/Corporations do not buy new products only proven products so you are continuing the myth of faster is better and, propergating the profit margins for these CPU manufactures.

How fast does your (n) brain work compared to (say) as 3Gig Athlon? Answer about 4 billion times the speed even though it can only transmit at a maximum speed of about 16Mhz between components at just about meltdown!!!

There is more to speed than fastness.
 
posting just to make a point as to how bad tom's has gotten :) and why fanboys love using them to illustrate how great their products are...

just look @ the test setups THEY used v/s the test setups for most other websites...

notice anything interesting?

the only common hardware = video card/hard drive/network card/atapi device...

which means there is no common MEMORY... :)

anyone notice that? anyone? hmm?

would it not have been LOGICAL to have everything as similar as possible so comparisons could be made directly between the cpus? is that so hard for these 'uber reviewers' to do ?

THG really is sucking it up big time when it comes to reviews for the past several months...
 

Members online

No members online now.

Latest profile posts

Also Hi EP and people. I found this place again while looking through a oooollllllldddd backup. I have filled over 10TB and was looking at my collection of antiques. Any bids on the 500Mhz Win 95 fix?
Any of the SP crew still out there?
Xie wrote on Electronic Punk's profile.
Impressed you have kept this alive this long EP! So many sites have come and gone. :(

Just did some crude math and I apparently joined almost 18yrs ago, how is that possible???
hello peeps... is been some time since i last came here.
Electronic Punk wrote on Sazar's profile.
Rest in peace my friend, been trying to find you and finally did in the worst way imaginable.

Forum statistics

Threads
62,015
Messages
673,494
Members
5,621
Latest member
naeemsafi
Back