Athlon XP < P4 < A64
- Thread starter dc5
- Start date
Depends on the speeds you're talking about, but in general, yes.
but, fastest AXP < fastest P4 < fastest A64
Factoring in cost is why the AXP is so popular. Now that A64s are cheaper and the Sempron 3100+ is out, the AXP niche for value is becoming smaller and smaller.
but, fastest AXP < fastest P4 < fastest A64
Factoring in cost is why the AXP is so popular. Now that A64s are cheaper and the Sempron 3100+ is out, the AXP niche for value is becoming smaller and smaller.
"AXP 3200 < P4 2.4C"
!!!!!!!!!!!!!!!!!!!!!!!!!
more like a 2.8C is better or on the same level as a 3200+
!!!!!!!!!!!!!!!!!!!!!!!!!
more like a 2.8C is better or on the same level as a 3200+
It depends on usage type too. If you're gaming then you're right on the money. For other types of activites, programming, simulations, etc. P4's are great. I love hyperthreading at work, could care less about it at home.
Programming? Well I know that my A64 at home compiles my .NET assemblies significantly faster than my PIV at work. I think that's consistent with AT's compilation benchmarks as well. The only thing the P4 seems to have an edge in is some rendering and encoding apps - and on the high end these advantages seem to be eroding pretty quickly.
http://anandtech.com/showdoc.aspx?i=1834&p=1
In this article, it shows that even in games, the performance was similar if not better than the 3200.
And at that time, I don't think the price from the 3200 could beat the 2.4C price by a long shot. Still today the 3200 is 20-30 bucks more expensive.
There are some where the 3200's performance can reach about a 2.6C level, but overall, the 2.4C is still a better buy, especially when you consider how far you can OC it.
That's why my first post says:
"AXP 3200 < P4 2.4C
then I think it's something like
P4 3.2C < A64 3000"
"AXP 3200 < P4 2.4C
then I think it's something like
P4 3.2C < A64 3000"
I dunno VIAN, I have a P4 2.8/i865 system and with the same video card, my mobile barton mops the floor with it at 2.4. I haven't used it at 3200+ speeds very much but I would hazard a guess that at 2.2, the barton and 2.8 would be very similar in most things with the xp winning in games...
As far as the bench's you linked, I see the XP and P4C swapping places from bench to bench...
As far as the bench's you linked, I see the XP and P4C swapping places from bench to bench...
This is the true:
P4C < mobile AXP Barton OC < Athlon 64 OC or not
P4 anything << Athlon 64
Besides AXP barton mobile OC a LOT CHEAPER than P4C.
P4C < mobile AXP Barton OC < Athlon 64 OC or not
P4 anything << Athlon 64
Besides AXP barton mobile OC a LOT CHEAPER than P4C.
Was it a P4C with Dual Channel.
As far as the benches, it means that they are roughly equal in performance, and the P4C at 2.4 is much cheaper than the 3200+.
This is the case, but I didn't take OCing into factor. And I haven't seen any websites with benches like this unfortunately. What a shame. But, in case of the AXP OC, it would probably be something close to the 3.2GHz P4C. I'm just providing an educated guess.
Zebo
Elite Member
- Jul 29, 2001
- 39,398
- 19
- 81
P4's are a joke right now when 2800 A64's overclcok 700Mhz. 1.8 to 2.5 easy on stock HSF.
You need at least a 3.8 pentium to match it.
Cheaper, faster, cooler, less power and 64 bit future what more you want. In fact I can't think of a single advantage of buying any pentium right now over A64.
Then a 2600 mobile barton overclcoked destroys all in price/performance.
Nah
it's more like p4 < A64 < XP-M when you fctor in overclocking, price and performance.
Pure performance it's just like you said. But who does'nt pay attention to price?
You need at least a 3.8 pentium to match it.
Cheaper, faster, cooler, less power and 64 bit future what more you want. In fact I can't think of a single advantage of buying any pentium right now over A64.
Then a 2600 mobile barton overclcoked destroys all in price/performance.
Nah
it's more like p4 < A64 < XP-M when you fctor in overclocking, price and performance.
Pure performance it's just like you said. But who does'nt pay attention to price?
I also payd attention to the price. That's why I said the 2.4C is better than the 3200+. I factored in price. If price is not important, however, you probably wouldn't be making a decision between those anyway.
And I wouldn't buy a AXP for a new system at this point. I would get an A64 2800 at least way before I ever got an AXP. Cheap and fast, much faster than AXPs at stock and almost as fast as the 3.2GHz. OC, if possible to get OC 700MHz, it would kill all.
And I wouldn't buy a AXP for a new system at this point. I would get an A64 2800 at least way before I ever got an AXP. Cheap and fast, much faster than AXPs at stock and almost as fast as the 3.2GHz. OC, if possible to get OC 700MHz, it would kill all.
Yeah, I just looked again at the original post.
That is just for Bandwidth, Intel does have much more bandwidth than AXP and a lot of A64 chips because it needs all that bandwidth, however, a AXP has no need for all the bandwidth to work great unlike Intel. So bandwidth doesn't equal performance.
Another thing you have to understand is that Intel is better than AMD at certain applications. Like AMD is better than Intel at games and general applications and Intel is generally much better at everything else, although AMD is starting to creep up into that area as well. This is on a clock per clock basis taking Instructions per clock into account. This app specific performance means AMD should have been the leading desktop processor as it was cheaper and quicker, but it is still barely known to common people.
Everyone knows Intel and everyone know Nvidia.
Show me at least 5 applications where intel processors are faster( I am talking about the A64 processors). I only have seen one or two, and the differences are very minimal.
Another thing:
I was looking for 3200+ price and found it cost 19 dollars less than P4 2.4C (P4C2.4 US$ 141 and AXP 3200+ US$112, both OEM) , and looking in the benchmarks, I found that in most of the apps AXP3200 beats P4 2.4C, The 3200+ performance is more like P4 2.8C and it's a lot cheaper.
Anyway I woudn't buy a 3200+, because a mobile 2500+ dirty cheap and overclocks beyond the 3200+ beating all the P4C processors.
Another thing:
I was looking for 3200+ price and found it cost 19 dollars less than P4 2.4C (P4C2.4 US$ 141 and AXP 3200+ US$112, both OEM) , and looking in the benchmarks, I found that in most of the apps AXP3200 beats P4 2.4C, The 3200+ performance is more like P4 2.8C and it's a lot cheaper.
Anyway I woudn't buy a 3200+, because a mobile 2500+ dirty cheap and overclocks beyond the 3200+ beating all the P4C processors.
1. http://anandtech.com/showdoc.aspx?i=1956&p=17 - Overall
2. http://anandtech.com/showdoc.aspx?i=1956&p=18 - AquamarkCPU
3. http://anandtech.com/showdoc.aspx?i=1956&p=21 - DIVX
4., 5. http://anandtech.com/showdoc.aspx?i=1956&p=22 - 3dstudio, lightwave
According to Anandtech's Realtime pricing, which is pretty accurate most of the time, the cheapest 3200 is only 178.
Neither are bad CPU's and I think you are giving AMD too much credit.
A 2.4C would have been better anyway, because you can overclock it to fight an A64, but a 3200 or 2500 won't be able to overclock to a decent level to compare to an A64.
2. http://anandtech.com/showdoc.aspx?i=1956&p=18 - AquamarkCPU
3. http://anandtech.com/showdoc.aspx?i=1956&p=21 - DIVX
4., 5. http://anandtech.com/showdoc.aspx?i=1956&p=22 - 3dstudio, lightwave
According to Anandtech's Realtime pricing, which is pretty accurate most of the time, the cheapest 3200 is only 178.
Neither are bad CPU's and I think you are giving AMD too much credit.
A 2.4C would have been better anyway, because you can overclock it to fight an A64, but a 3200 or 2500 won't be able to overclock to a decent level to compare to an A64.
hmmm i've benched my 2.4 ghz axp on my system looks like performance is right around 3.2C to 3.0C
VIAN, in the 1. http://anandtech.com/showdoc.aspx?i=1956&p=17 - Overall test how come the 3.4EE is not against an FX-53 ?
Plus he said he was talking about price, since when did EE'S have a great price to pefromance ratios ?
in Doom 3 a 3000 64 comes within 2 frames on a 3.4EE, says alot about Price/performance.
Plus he said he was talking about price, since when did EE'S have a great price to pefromance ratios ?
in Doom 3 a 3000 64 comes within 2 frames on a 3.4EE, says alot about Price/performance.
VIAN, while for the most part I do agree with the common opinion that on average an A64 is better than a P4C/E and that the AXP performance generally comes in below both the others. On the other hand any one of the 3 can excel in a specific area, so unless you narrow the testing to a specific use there really is no reason to try and say that the speed of one processor is equal to another (as you have).
As for your references, well I just have to say that they seem to be hand picked to show Intel in the BEST light. Come on, do you really think we should use a synthetic benchmark (that even Anandtech said favored Intel) to determine real world performance. I know I don?t. Also the article ?the real slim shady? (your first reference) looks like a good article on the surface, but I believe it was in the two CPU articles prior to that you could see a disturbing trend. The trend shows the AXP using the same setup on some of the same benchmarks gradually dropping, that?s right dropping, in performance, in some cases more than 10%; all this is while the P4 is showing a constant improvement. While I don?t know why the differences occurred or what article to believe I feel that at the time Anandtech was more focused/impressed with the P4 and may not have accurately compared processors in that article.
I don?t expect you to retract your statements based solely on my opinion or recollection of past articles, but I would ask that if you want to compare processors either be a little more specific on the type of usage you are trying to represent, or be more general and don?t use speed grades as a comparison.
As for your references, well I just have to say that they seem to be hand picked to show Intel in the BEST light. Come on, do you really think we should use a synthetic benchmark (that even Anandtech said favored Intel) to determine real world performance. I know I don?t. Also the article ?the real slim shady? (your first reference) looks like a good article on the surface, but I believe it was in the two CPU articles prior to that you could see a disturbing trend. The trend shows the AXP using the same setup on some of the same benchmarks gradually dropping, that?s right dropping, in performance, in some cases more than 10%; all this is while the P4 is showing a constant improvement. While I don?t know why the differences occurred or what article to believe I feel that at the time Anandtech was more focused/impressed with the P4 and may not have accurately compared processors in that article.
I don?t expect you to retract your statements based solely on my opinion or recollection of past articles, but I would ask that if you want to compare processors either be a little more specific on the type of usage you are trying to represent, or be more general and don?t use speed grades as a comparison.
I mostly look in gaming because that's what I care about. As far as genearl usage, which is important, I don't care too much about because I don't care about running Word on a 1GHz processor, it's mostly the same.
The Athlon architecture is superior to the P4 architecture in Gaming and General Usage.
A64 has the same advantages as AXP, only it's quicker because of the Integrated memory controller and other tweaks.
The P4 architecture is superior to the Athlon architecture in the Content Creation and Coding.
That's how it basically is. There can be exceptions.
Yes, I did hand pick them because carlosd asked for them. I'm not a fan of Intel, I love AMD, and I hate Intel for releasing the P4 BS that it is. Meaning, they could have done so much better if it wasn't for their love of money. But, although Intel does suck, there are some things that the P4 are useful for and they can outdo the AXPs. So I don't appreaciate people leaving Intel out in the wind, because they are useful to an extent. Such as a cheap OCing chip, or for someone who is always ripping CDs or Encoding/Decoding movies. The P4 is made for them, I wouldn't recommend an A64.
Synthetic benchmarks are followed by a rainy cloud, but I can't really say anything about them because I don't have enough knowledge about them, unless it's graphics synthetic benches, but they seem different.
That is a very interesting observation, and I will try and look into that.
I use speed grades to identify a processor. I can't say that they entire P4 line destroys the AXP line.
"AXP 3200 < P4 2.4C
then I think it's something like
P4 3.2C < A64 3000"
These are just observations form benchmarks that I made. When I wanted to buy a new processor, I took at look at these benches and I try to decide which company was faster at which price. Since I didn't OC at the time and I couldn't afford something god-like, I settled for something which performed quicker per dollar. Looking back, it wasn't the best choice, but it was decent.
It is difficult to judge something on a clock per clock basis. I said clock per clock many times, but it's incorrect, it should be more like dollar per dollar. All you can do is look at how much the product costs and it's perfomance and find the best ratio. But I always like to go a little more above that cause I feel that's where the sweet spot lies. However taking OCing into consideration is a bit more complicated.
Edit: oh good, most of it is still here. My failing powersupply restarted the comp while I was typing, which sucked ass.
I was saying that the P4Cs fill the performance void between the AXPs and the A64s. In the Gaming section at least. Interesting that according to the Real-time Engine, the P43.2 is 235 bucks at it's cheapest, but the A64 3000 is only about 140 at it's cheapest. That is just amazing considering how good the A64 is in comparison.
really? i see the 2.8C beating the 3200+ in every benchmark except for general usage and serious sam...
VIAN, thanks for the detailed explanation regarding your views. I have to say that I agree with you on all points (I think) except one. That one would be that the ?AXP 3200 < P4 2.4C?. You need to understand that I am not much of a gamer, nor do I have both systems to make direct comparisons with so I can only compare using published benchmarks.
As I have mentioned before, I have reservations about using ?the real slim shady? as a reference, and here is why. In the article ?Intel Pentium 4 3.0C ? The First 800MHz FSB CPU? it shows the AXP 3000+ score of 214.9 fps in UT (flyby) yet 2 months later (using the same configuration and benchmark) in the ?Intel Pentium 4 3.2GHz - The Real Slim Shady? the AXP 3200+ only scores 203.0 fps. If you take the score from the older article and compare against the newer article the AXP 3000+ falls between the P4C 2.8 and the 3.0 instead of the 3200+ being between the P4C 2.4 and 2.6.
While some of the benchmarks indicate a new revision, and the fact that the same processors where not used throughout both articles makes the comparison very time consuming. I think this one example shows that at least one of those articles have to be questioned and by comparing articles from other sites I personally think ?the real slim shady? should be the one in question.
All this aside, I just think your comparison might be a little to pessimistic on how the AXP compares to the P4.
Just to clear things up the P4C performance did go up while the AXP went down, and not all the benchmarks show the same discrepancy in performance. Also I think this benchmark might show the biggest discrepancy, I didn?t check that I just used the first common benchmark that I saw on both articles.
As I have mentioned before, I have reservations about using ?the real slim shady? as a reference, and here is why. In the article ?Intel Pentium 4 3.0C ? The First 800MHz FSB CPU? it shows the AXP 3000+ score of 214.9 fps in UT (flyby) yet 2 months later (using the same configuration and benchmark) in the ?Intel Pentium 4 3.2GHz - The Real Slim Shady? the AXP 3200+ only scores 203.0 fps. If you take the score from the older article and compare against the newer article the AXP 3000+ falls between the P4C 2.8 and the 3.0 instead of the 3200+ being between the P4C 2.4 and 2.6.
While some of the benchmarks indicate a new revision, and the fact that the same processors where not used throughout both articles makes the comparison very time consuming. I think this one example shows that at least one of those articles have to be questioned and by comparing articles from other sites I personally think ?the real slim shady? should be the one in question.
All this aside, I just think your comparison might be a little to pessimistic on how the AXP compares to the P4.
Just to clear things up the P4C performance did go up while the AXP went down, and not all the benchmarks show the same discrepancy in performance. Also I think this benchmark might show the biggest discrepancy, I didn?t check that I just used the first common benchmark that I saw on both articles.
TRENDING THREADS
-
Discussion Zen 5 Speculation (EPYC Turin and Strix Point/Granite Ridge - Ryzen 9000)- Started by DisEnchantment
- Replies: 23K
-
Discussion Intel Meteor, Arrow, Lunar & Panther Lakes Discussion Threads
- Started by Tigerick
- Replies: 18K
-
Discussion Intel current and future Lakes & Rapids thread- Started by TheF34RChannel
- Replies: 23K
-
-
Discussion Speculation: Zen 4 (EPYC 4 "Genoa", Ryzen 7000, etc.)- Started by Vattila
- Replies: 13K
Facebook
Twitter