CPU price/performance graph

[nilepez]

But I would definitely constrain the overclocked figures to be those with stock cooling, since the added expense of aftermarket CPU coolers isn't included in the price part of the equation.

I'm willing to graph so long as I find the data.

I think one way to handle that is to pick a good cooler and track OCing of the various chips that use that cooler.

Now that may be difficult, given the wide variety of coolers out there, but I figure that if you pick a Zalman, Thermalright or Skythe, you're probably set.

The other thing is that coolers can outlast a CPU. For example, I bought a Thermalright XP-90 2 years ago, and when I finally figure out which CPU I'm getting (4300 for $163 or 6400 for $159), I'll move it to the new CPU. It'll cost me $6.00 for 975 adapter, but that's not a big deal. Then again, I bought the cooler at least as much for it ability to quietly cool as it's ability to improve OCs.

 

[HotFoot]

I have to agree that the extra cost for the dual-socket motherboard should be added to the FX-7x series. I'll get right to this. I've also added a price/performance column to the table, and that will be updated soon. What I'm looking for before the next update is a 3DMark06 CPU score for the X2 5200+ processor at stock settings.

 

[HotFoot]

The graphs have been updated to reflect the adjustment of the FX-7x price to include a premium for the motherboard. Also, I have added a price/performance column to the table.

And for halbhh, since you want to see what the graph looks like with the origin showing, here you go. I don't know that it's all that informative, but if you're looking at p/p ratio then this does better highlight the value of the cheaper processors.

 

[thedrake]

anyone else NOT seeing a graph or a link to a graph?

 

[HotFoot]

anyone else NOT seeing a graph or a link to a graph?

For some strange reason, I was having this problem yesterday. I'm running firefox 2.0, and I looked into the problem, but I couldn't figure out what it could have been. It seems that for a lot of places I was visiting, images from 3rd party sites wouldn't load. Now, in older versions of firefox, you had the option to not load 3rd party images, but this is gone in 2.0.

Today, the images are showing for me, so I no longer have to switch computers to be sure my images are uploading properly. What I did yesterday that must have fixed the issue is turn off and then on again the option Tools>>Options>>Content>>Load images automatically.

I had played around disabling adblock, but that didn't do anything for me. I ended up uninstalling adblock and installing adblock plus anyway. That could have fixed it, but it doesn't make sense to me.

I hope this helps you.

 

[zenmaster]

There is no need to include the price of aftermarket coolers depending on how much you OC your system.

Example - The Stock Cooler for the C2Duo is designed to handle the 2.93Ghz of the E6800. So long as you OC the E4300 only to this point it is operating fully within design specs.

So you Get a 1.1 Ghz OC and no need for added cooling costs.

Only when you push the CPU/Cooler beyond design specs do the aftermarket coolers add to the cost.

The aftermarket coolers are as much for noice reduction as they are for OCing.

 

[flasher702]

Good concept and methedology. More data, more processors, more OCed processors, and make the graphs easier to read. Keep it up. Don't disinclude processors to make the graph more readable, that's silly. We're in a digitial environment here, perhaps release the graphs themselves instead of pictures of them? That "Less than $300" range that is so "crowded" is that way because that's where most people shop: fill it up.

Oh, and don't worry about stock cooling for OCed processors. YOu haven't included them in the trendlines and the trendlines don't include motherboard and ram prices either. It's up to the person building the system to do the reasearch and factor in cooling costs for OCing and re-run the price/performance themselves. Just focus on the CPU, less work for you and more data for us. I'd say avoid benchmarks with exotic cooling, but any reputable benchmark using conventional air cooling is fair game to be included. Great idea to not include the OCed data in the trend lines, if you get enough info you might want to make a third trend line just for OCs.

One other idea: don't make Intel vs. AMD trend lines. Just make one trend line. That way it will be easier to see which processors, regardless of brand, fall above and below the line. One trend line for stock, one for OCed (and just assume that OCed systems are probably using extra cooling reletively cancelling the extra cost out and don't worry about it). The p/p graph isn't about Intel p/p vs. AMD p/p, it's about performance period vs. MY bank account. Anyone else out there want to second this? Could you make a quick graph with only one trend line so we can see what it looks like?

It's also great that you included processors in the list and just put "0" in if you didn't have benchmark data for them. You should put even more processors in that list and encourage people to help you find that data or even run the benchmarks you like themselves and get you the results with screenshots and such.

All the the AMD processors listed are dual-core, yes? It should say so. And you should feel free to include a few single-core processors as well for reference.

In genearll I would say don't worry as much about your methodology being perfect and your graph being accurate as with disclosing what your methodology is and presenting more information. You manifesto stated one of your primary reasons for creating you own database was because THG was too slow to update and didn't provide enough info, don't slow yourself down trying to be perfect or you'll end up in the same place (or doing a LOT more work). The graph will never be perfect and it only takes very limited portion of computer performance into account anyway. Present more information and let the users look at the details so they can make adjustments for their specific situation.

Ok, and one more radical idea: The trend line is very smooth, this is not realistic. The price/performance points on processors jump around, so should the trend line. Would it be difficult to calculate a trend in segments so that it went up and down and visually illustrated any "sweet spots". We can easily see single processors that are sweet by seeing how far they are above the trend, but could you make a line that shows the trend of where the sweet spots are? Eh, perhaps this wouldnt be very useful in practice with such a small range of data points and many of the processors coming in close to the trend, just throwing it out there.

Once long ago THG had a giant CPU chart with large varieties of different chipsets, types of ram, and amounts of ram listed. It wasn't as accurate for quickly determining reletive CPU performance if you held all other factors as equal as you could, but it was a hell of a lot more usefull as it included many more processors and also included data on how chipset and RAM affected benchmark scores and the relative performance between a new system and an older system. When you build a system there is a lot more to it then just a CPU so it's kind of silly to try and pretend otherwise when comparing CPUs. You'll end up putting more effort into creating a less useful (although arguable more accurate) guide if you do.

Oh, in your table of CPUs it would be nice to link each processor to the benchmark(s) you pulled the data from since they may be using different test beds. Kind of like citing your sources since you're drawing info from a variety of sources so we can quickly go and compare the raw data between where you put points on the graph.

Ok, and now for a very specific request to add info for
1. OCed e4300 ~@2.4ghz and ~@3ghz
2. OCed x2 3600+ Brisbane ~@2.4ghz and ~@2.8ghz
(this is what I'm currently debating for myself, not many other people seem to be but I think they should!)

 

[halbhh]

The graphs have been updated to reflect the adjustment of the FX-7x price to include a premium for the motherboard. Also, I have added a price/performance column to the table.

And for halbhh, since you want to see what the graph looks like with the origin showing, here you go. I don't know that it's all that informative, but if you're looking at p/p ratio then this does better highlight the value of the cheaper processors.

Yeah, I did enjoy seeing it with the zeroes. Thanks!

The *interesting* thing is.... the 4x4 FXs with the expensive motherboard are *still* a better buy than the dual core extreme.

That's kinda interesting.

 

[HotFoot]

The QFX processors are a better by than the X6800 if you're doing a lot of well-threaded applications. It's not too hard for the four cores to overtake the two. However, in gaming benchmarks, the X6800 beats all of the quad-cores. This is one of the main reasons I think I'll produce a separate "gamers" p/p graph.

 

[halbhh]

The QFX processors are a better by than the X6800 if you're doing a lot of well-threaded applications. It's not too hard for the four cores to overtake the two. However, in gaming benchmarks, the X6800 beats all of the quad-cores. This is one of the main reasons I think I'll produce a separate "gamers" p/p graph.

Yes, just what we should expect. But....unless the x6800 is more than 15% better on the games than a closely priced FX (accounting the $250 MB delta into it), then the FX would be a better buy for a couple of reasons: we do more than games, and that MB will allow upgrade to an 8-core platform with a new arch soon.

I didn't expect to be pointing out any advantages to the 4x4! But considering the new arch drop-in upgrade barcelona....it's a whole different picture!

 

[HotFoot]

You've made quite the post there! There are many good suggestions.

Good concept and methedology. More data, more processors, more OCed processors, and make the graphs easier to read. Keep it up. Don't disinclude processors to make the graph more readable, that's silly. We're in a digitial environment here, perhaps release the graphs themselves instead of pictures of them? That "Less than $300" range that is so "crowded" is that way because that's where most people shop: fill it up.

I try to add a little information each day. Today I tired, but failed, to find a 3DMark06 score for a X2 5200+ processor. I have the other scores I need for that one. As far as releasing the graphs themselves, I believe I can save the figures in a MATLAB format (*.fig). That should allow you to pan/zoom all you want yourself. However, I don't know where I can upload these for sharing. Right now I'm generating .png images and having those hosted on ImageShack, which is a simple enough system. The same goes for my tables of data. The easiest thing for me to do would be to just share my spreadsheet, but it's a matter of how. I'm sure it's simple, I just don't know yet.

[quote}Oh, and don't worry about stock cooling for OCed processors. YOu haven't included them in the trendlines and the trendlines don't include motherboard and ram prices either. It's up to the person building the system to do the reasearch and factor in cooling costs for OCing and re-run the price/performance themselves. Just focus on the CPU, less work for you and more data for us. I'd say avoid benchmarks with exotic cooling, but any reputable benchmark using conventional air cooling is fair game to be included. Great idea to not include the OCed data in the trend lines, if you get enough info you might want to make a third trend line just for OCs.[/quote]

I guess I can agree with that. People who OC are going to be more advanced users anyway. Any OC on air cooling is now fair game.

One other idea: don't make Intel vs. AMD trend lines. Just make one trend line. That way it will be easier to see which processors, regardless of brand, fall above and below the line. One trend line for stock, one for OCed (and just assume that OCed systems are probably using extra cooling reletively cancelling the extra cost out and don't worry about it). The p/p graph isn't about Intel p/p vs. AMD p/p, it's about performance period vs. MY bank account. Anyone else out there want to second this? Could you make a quick graph with only one trend line so we can see what it looks like?

I'm up for this idea. I've always found any discussion of the intersection of the trend lines to be meaningless. Good deals will be self-evident.

It's also great that you included processors in the list and just put "0" in if you didn't have benchmark data for them. You should put even more processors in that list and encourage people to help you find that data or even run the benchmarks you like themselves and get you the results with screenshots and such.

Yes please, people find me the information I'm missing. Regarding the benchmarks I like, well, I'm just using a few common benchmarks. No one has yet suggested anything different than what I'm using, but the hardest part (at least at first) is finding the benchmark data. Updating prices later will be easy.

All the the AMD processors listed are dual-core, yes? It should say so. And you should feel free to include a few single-core processors as well for reference.

Yes, all the AMD processors are either the X2 or FX series. I cut out the "X2" from the AMD chip names because of the amount of clutter. A graph does still need to be readable. I'm looking at trying to make the labels a lighter colour in the background so that the points will stand out better. I'll just add a note to the OP that the processors are all from the Intel Core 2 (desktop) and AMD X2 and FX lines.

Ok, and one more radical idea: The trend line is very smooth, this is not realistic. The price/performance points on processors jump around, so should the trend line. Would it be difficult to calculate a trend in segments so that it went up and down and visually illustrated any "sweet spots". We can easily see single processors that are sweet by seeing how far they are above the trend, but could you make a line that shows the trend of where the sweet spots are? Eh, perhaps this wouldnt be very useful in practice with such a small range of data points and many of the processors coming in close to the trend, just throwing it out there.

It wouldn't take that much work for me to set up what you're describing. Basically I'd do a cubic spline fit on to some tavelling average created from the data. It might not add value to the graph, though. I'll see about giving it a try and posting the result.

Oh, in your table of CPUs it would be nice to link each processor to the benchmark(s) you pulled the data from since they may be using different test beds. Kind of like citing your sources since you're drawing info from a variety of sources so we can quickly go and compare the raw data between where you put points on the graph.

If I just make my spreadsheet available you'll be able to find what you're looking for.

Ok, and now for a very specific request to add info for
1. OCed e4300 ~@2.4ghz and ~@3ghz
2. OCed x2 3600+ Brisbane ~@2.4ghz and ~@2.8ghz
(this is what I'm currently debating for myself, not many other people seem to be but I think they should!)

I'll look for some data. So far, though, I haven't even found enough benchmarks for the X2 3600+ at stock settings to include it. I will keep looking.

 

[HotFoot]

Yes, just what we should expect. But....unless the x6800 is more than 15% better on the games than a closely priced FX (accounting the $250 MB delta into it), then the FX would be a better buy for a couple of reasons: we do more than games, and that MB will allow upgrade to an 8-core platform with a new arch soon.

The X6800 is 23% and 40% faster than the FX-74 and FX-70, respectively, in the Quake 4 benchmark. The FX-62 is faster than the FX-70 and FX-72 in games, and only slightly behind the FX-74 (which it really ought to be considering it's clocked slower). In fact, the X2 6000+ scores higher in Quake 4 than the FX-74.

More on games later...

 

[buckiller]

Since you included the premium for 4x4 mobos, why not include the premium of Intel cpu mobos? They tend to be more expensive.

 

[HotFoot]

More on games later...

And later is now: The OP has been updated with a gaming benchmark graph. The general performance remains the same mix, for now, but the gaming benchmarks are Quake 4 and FarCry (one OpenGL and one DirectX). I hope this better demonstrates what many people are looking for.

 

[HotFoot]

Since you included the premium for 4x4 mobos, why not include the premium of Intel cpu mobos? They tend to be more expensive.

This is a general problem for all of the comparisons, and especially the FX-7x series as you've said. I don't know if there's a simple solution.

For one thing, if you're running an AM2 chip at stock, you can get an extremely cheap motherboard. Budget motherboards for C2Ds tend to be a little more expensive. Motherboards capable of overclocking well tend to be around $110 and up. So, while I've tried to keep my OC data restricted to what should be possible on stock cooling in order to avoid needing to include the cost of an aftermarket cooler, the extra cost of using a motherboard that's good for overclocking isn't taken into account. The situation is even worse for the FX-7x series.

What else needs to be considered is the RAM. The AMD processors need the best possible RAM to maximise their scores, while the C2D can achieve most of its potential on cheaper, slower memory. I would consider that the memory and motherboard factors cancel each other out, but it would take a lot of reasoning to try to prove this in any useful way.

Another point is that two of the benchmarks I'm using, 3DMark06 and LAME, scale well with the number of cores, and only one benchmark, Quake, does not. This makes the graph favor quad-core processors. I'm thinking it might be better for me to split the data into gaming/everything else, since people spending $1000 on a processor are often looking for the highest possible FPS, and the fact that the processor handles LAME well is an bonus.

It would be interesting to consider price/performance at a system level, but seriously things can get out of hand.

 

[HotFoot]

As requested, there is an update including an overclocked e4300. The review is from X-Bit Labs, using a Zalman 9500 cooler. Link.

Also info is now available for the X2 3600+ (stock and overclocked), from X-bit Labs.

 

[halbhh]

couple of questions: 3 links work, but the zoom view link does not.

Is it reliable that 4300s can be overclocked so high? If so, you'd think none of the nearby Intel processors should be bought -- just the 4300 would be worth buying.

 

[halbhh]

Xbit had to increase the voltage to get to that 3.4Ghz, but they did have a 3Ghz without the increase, which would represent a nice overclock anyway. though I'm not an expert, the overvolting should not be on a computer where it would matter much if the cpu fails. If it's only for gaming and you don't care about risking the $170 (or so/w shipping etc), then why not.

 

[flasher702]

Yeah, the zoomed view isn't working.

http://www.filefront.com/ or something similar might be the solution you desire for hosting other files. Or you could set it up for bitorrent or ed2k.

The single trend line looks nice, but it's not what I expected. Did you include the OC data in the trend line?

If that gaming performance graph is at all accurate it's brilliantly eye-opening. Good idea.

Good progress, keep it up. I think I'll try to find some raw data for you a little later today.

 

[halbhh]

This OP deserves to be a sticky. Anyone know how to make that happen?

 

[dasickninja]

You have to PM the mods. But its unlikely.

 

[HotFoot]

http://www.filefront.com/ or something similar might be the solution you desire for hosting other files. Or you could set it up for bitorrent or ed2k.

I've zipped my data/graphing files. If you have MATLAB, you can run grapher.m or just open the *.fig files. Download here.

The single trend line looks nice, but it's not what I expected. Did you include the OC data in the trend line?

The trend line is combined for non-overclocked Intel and AMD processors, not overclocked.

If that gaming performance graph is at all accurate it's brilliantly eye-opening. Good idea.

I pretty much had to make a gaming graph when I saw how disparate the stats were between general, well-threaded benchmarks and standard games. Hopefully the next batch of games will improve things for the quad-core systems.

Good progress, keep it up. I think I'll try to find some raw data for you a little later today.

Thanks for the help! Any luck with the data?[/i]

 

[halbhh]

You have to PM the mods. But its unlikely.

Why do you think it is unlikely? I did just PM the mod (I only found one mod for this forum).

If the "guide" sticky is more than 3 months out of date, why don't they remove it I wonder?

 

[HotFoot]

The graphs have been updated. I expect I'll see about updating the prices on either a weekly or a bi-weekly basis. It's really not that much work to get prices anyway. The changes in prices as of this Sunday are few. Two AMD processors got more expensive: the 6000+ and 5600+, by $80 and $114, respectively. The Intel processors didn't move by much. Those that did were down a few dollars.

As for benchmarks, of the stock CPUs I am missing data for the 5400+ (all) and 4200+ (FarCry only). Other than those I have tracked everything down. I am still very happy to accept new data for overclocked processors, as I haven't gotten nearly so far with data on those.

Cheers!

 

[buckiller]

Since you included the premium for 4x4 mobos, why not include the premium of Intel cpu mobos? They tend to be more expensive.

This is a general problem for all of the comparisons, and especially the FX-7x series as you've said. I don't know if there's a simple solution.

For one thing, if you're running an AM2 chip at stock, you can get an extremely cheap motherboard. Budget motherboards for C2Ds tend to be a little more expensive. Motherboards capable of overclocking well tend to be around $110 and up. So, while I've tried to keep my OC data restricted to what should be possible on stock cooling in order to avoid needing to include the cost of an aftermarket cooler, the extra cost of using a motherboard that's good for overclocking isn't taken into account. The situation is even worse for the FX-7x series.

What else needs to be considered is the RAM. The AMD processors need the best possible RAM to maximise their scores, while the C2D can achieve most of its potential on cheaper, slower memory. I would consider that the memory and motherboard factors cancel each other out, but it would take a lot of reasoning to try to prove this in any useful way.

Another point is that two of the benchmarks I'm using, 3DMark06 and LAME, scale well with the number of cores, and only one benchmark, Quake, does not. This makes the graph favor quad-core processors. I'm thinking it might be better for me to split the data into gaming/everything else, since people spending $1000 on a processor are often looking for the highest possible FPS, and the fact that the processor handles LAME well is an bonus.

It would be interesting to consider price/performance at a system level, but seriously things can get out of hand.

I still don't see why you would include the price of 4x4 mobo and not any other mobos?