Overclock.net banner

Sandy Bridge vs Nehalem vs Bulldozer vs Piledriver {BENCHMARKS!!!}

28K views 166 replies 60 participants last post by  devl547  
#1 ·
You now have opened a benchmark thread where 4 different processors will battle each other in various tests. All processors will be clocked at the same speed of 4 GHz - this means that the benchmark is not about CPU vs CPU, but rather architecture vs architecture.

This benchmark came out of my personal need to find out which processor i will be keeping for myself - which CPU fits my needs most, does not bottleneck my gaming experience at 1920X1200 and deals with my programs the fastest!

Representing Sandy Bridge - Core i7 3820

http://imageshack.us/photo/my-images/43/corei73820.jpg/

Representing Nehalem - Xeon W3520 (Core i7 920)

http://imageshack.us/photo/my-images/687/xeonw3520.jpg/

Representing Bulldozer - FX6200

http://imageshack.us/photo/my-images/835/fx6200.jpg/

Representing Piledriver - FX6300

http://imageshack.us/photo/my-images/823/fx6300.jpg/

Why not AMD FX 8 core CPUs? Because in the future i might want to throw the Phenom II X6 and keep it competitive with AMD FX 6 core CPUs.

Most of hardware used for CPU testing was kept the same for all processors:

GeForce GTX670 4 Gb video card .
4 DIMMs of 2 Gb DDR3 1333 MHz CL7 RAM & 4 DIMMs of 2 Gb DDR3 1600 MHz CL8 RAM.
Hitachi Deskstar 1 Tb 7200 rpm sata2 hard drive
Dell 24 inch 1920x1200 resolution monitor

All the software used for testing was identical for all 4 processors:

Windows 7 Pro X64
Forceware 306.97
Passmark 7 X64
Winzip
Irfan View
Adobe Photoshop CS2
Virtual Dub X64
20 games - 20 different engines

Let's start with a synthetic benchmark and see what prognoses does it tell for the processors.

PASSMARK 7 X64 - calculating CPU, all tests, fast

http://imageshack.us/photo/my-images/254/passmark7.jpg/

According to Passmark 7, the new Piledriver will wipe the floor with both Bulldozer and Nehalem, even beat Sandy Bridge...!...

Now let's toss in some real life applications which i myself use!

WINZIP - custom file compression

http://imageshack.us/photo/my-images/37/winzipcompress.jpg/

Looks like the Piledriver is a minor upgrade to the Bulldozer, but both are nowhere close to Intel processors.

Let's now extract that same compressed file!

WINZIP - custom file extraction

http://imageshack.us/photo/my-images/138/winzipextract.jpg/

That was really impressive on AMD part! But most impressive is the consistency in time! I guess here extra cores do matter...

I use Irfan View as my main photo viewing program. For it's small same it is the most powerful program that i could think of. One of the tasks i had to do with it was to convert a massive photo archive from jpeg to gif.

IRFAN VIEW - batch conversion from jpeg to gif

http://imageshack.us/photo/my-images/84/batch.jpg/

Piledriver is a massive upgrade to Bulldozer here, but not really in the league with Intel processors.

I use the good old Adobe Photoshop CS2 for the most difficult photo tasks and it is enough for me. One of the more simple tasks i wrote in Photoshop CS2 for this benchmark was a simple photo editing command, that included filtering to diffuse glow, resizing and rotating the custom photo archive made of 950 photos.

ADOBE PHOTOSHOP CS2 - photo archive editing

http://imageshack.us/photo/my-images/7/editingy.jpg/

The biggest surprise here is the incredible performance of my Nehalem based Xeon, which beated the newer Sandy Bridge CPU considerably. I have repeated this several times to the same result. Finally the Piledriver here is an upgrade to Bulldozer and scores the same as the Sandy Bride.

Most of all programs i use Virtual Dub to compress raw gaming videos. X264 and ffdshow codecs are my top 2. Let's see how the processors deal with this task.

VIRTUAL DUB X64 - compressing raw to X264

http://imageshack.us/photo/my-images/202/x264y.jpg/

Really disappointed with the Piledriver here.. Perhaps it just does not like X264 codec...

Typically for avi i use ffdshow, not X264, so let's see how the processors deal with it. Perhaps Piledriver will redeem itself here?

VIRTUAL DUB X64 - compressing raw to ffdshow

http://imageshack.us/photo/my-images/809/ffdshow.jpg/

There is not really much difference here, though Sandy Bridge is clearly superior to all.

Let's game!
Here are included 20 games and each one of them uses a different engine! Now, typically when you want to find out which processor is the best in gaming, you lower the resolution and disable all effects right? But actually who games at 800X600?.....................
I game on 1920x1200 and since my GTX670 can handle that resolution and all effects easy, my biggest concern (as should be yours) is - will the processors be able to keep up with GTX670 at the resolution and settings i want to play! All games have been tested on max settings, 4X AA, 1920X1200 resolution.

ALIENS VS. PREDATOR 3 (Asura engine)

http://imageshack.us/photo/my-images/836/aliensvspredator3.jpg/

First game is a fluke - there is no real difference between the processors. This is one of the few "equilibrium" exceptions;)

ALAN WAKE (MAX-FX 3.0 engine)

http://imageshack.us/photo/my-images/831/alanwakep.jpg/

The Piledriver offers absolutely no improvement on Bulldozer and both AMD processors get beaten by the 4 year old Nehalem. Even further from the rest sits the Sandy Bridge with it's mighty minimal frame rate!

AVATAR (Dunia engine)

http://imageshack.us/photo/my-images/534/avataroy.jpg/

The Piledriver is a small improvement on Bulldozer, but both AMD processors lie quite further from Intel.

CRYOSTASIS (AtmosFear 4 engine)

http://imageshack.us/photo/my-images/40/cryostasis.jpg/

The Piledriver gains on Bulldozer and keeps up with Intel processors!

CRYSIS 2 (Cry 3 engine)

http://imageshack.us/photo/my-images/854/crysis2pq.jpg/

Bulldozer really suffered in Crysis 2 and Piledriver managed to redeem that shame by keeping up with Intel processors!

DEUS EX HUMAN REVOLUTION (Crystal engine)

http://imageshack.us/photo/my-images/201/deusexhumanrevolutionv.jpg/

Nothing to comment here really.

FEAR 3 (Despair engine)

http://imageshack.us/photo/my-images/145/fear3i.jpg/

Another game that could not care less about CPU

Formula 1 2011 (EGO 2.5 engine)

http://imageshack.us/photo/my-images/90/f12011v.jpg/

The Piledriver is a definitive improvement over Bulldozer, but not quite up with Intel processors.

HAWX 2 (unknown engine)

http://imageshack.us/photo/my-images/29/hawx2u.jpg/

The Piledriver is more than i could have asked for in this game! Unfortunately for AMD this is the only game where the Piledriver manages to beat both Intel processors! Bulldozer is just pathetic here!

HARD RESET (Road Hog engine)

http://imageshack.us/photo/my-images/687/hardreset.jpg/

Not only does the Piledriver offer no improvement over Bulldozer, but it get's totally trashed by both Intel processors.

HOMEFRONT (Unreal 3 engine)

http://imageshack.us/photo/my-images/843/homefrontj.jpg/

Once again the Piledriver offers no improvement over Bulldozer, and once again it get's trashed by both Intel processors. The difference, having in mind that Nehelem is so much older, is just scary!

LOST PLANET 2 (MT Framework engine)

http://imageshack.us/photo/my-images/849/lostplanet2.jpg/

The Piledriver just slightly improves Bulldozer's frame rate, but not in the class of Intel.

METRO 2033 (4A engine)

http://imageshack.us/photo/my-images/837/metro2033j.jpg/

I regret adding this game to the list. Worst benchmark game of all time.

NECROVISION (Pain engine)

http://imageshack.us/photo/my-images/39/necrovisione.jpg/

Older engine games are just fine for testing processors as well!
Piledriver is not much of difference from Intel, but clearly no improvement over Bulldozer.

PORTAL 2 (Source engine)

http://imageshack.us/photo/my-images/717/portal2a.jpg/

Another older engine game makes life easy for both Intel processors with absolute max performance possible out of this engine, yet AMD struggles! At least the Piledriver is an improvement over Bulldozer!

RED FACTION ARMAGEDDON (Geo-Mod 2.5 engine)

http://imageshack.us/photo/my-images/805/redfactionarmageddonz.jpg/

The Piledriver is a small improvement over Bulldozer, yet once gain does not have the steam to push the Intel from the crown.

SERIOUS SAM 3 (Serious 3.5 engine)

http://imageshack.us/photo/my-images/23/serioussam3.jpg/

Piledriver tries hard to get the shame off from it's predecessor by adding at least some extra FPS, but quite far from Intel.

SYNDICATE (Starbreeze engine)

http://imageshack.us/photo/my-images/29/syndicatew.jpg/

Piledriver very well done in this game, being quite far from Bulldozer and not far from Intel!

STALKER CLEAR SKY (X-ray 1.5 engine)

http://imageshack.us/photo/my-images/195/stalkerai.jpg/

The difference between Bulldozer and Piledriver is the difference between unplayable and playable as Piledriver manages to keep that critical minimal FPS where it needs to be!

WORLD IN CONFLICT (MassTech engine)

http://imageshack.us/photo/my-images/838/worldinconflictl.jpg/

Piledriver offers no improvement over Bulldozer and gets trashed by Nehalem in those so so important minimal frame rates. Sandy Bridge is even further ahead!

RELATIVE PERFORMANCE
http://imageshack.us/photo/my-images/38/minpn.jpg/

http://imageshack.us/photo/my-images/16/medhr.jpg/

http://imageshack.us/photo/my-images/812/maxzq.jpg/

Conclusion: in my opinion the Piledriver FX adds way too little improvements to be competitive clock per clock with both Nehalem and Sandy Bridge Core i7 processors, and though it is a must upgrade from a Bulldozer FX CPU, no way in hell should it be an upgrade from Nehalem based Core i7 processors.
 
#2 ·
thumb.gif
 
#4 ·
Very nice and informative test (+rep), tho it wouldve been even better if you had used 8-core FX piledriver and i5-based sandy as well (I know, you wanted to test which cpu needs your needs best), FX-83xx vs i5 is one of the hottest topics these days
smile.gif


Still very nice test all around.
 
#9 ·
I believe the largest factor for anyone that would be looking at this was left out, and that is the cost.

It is easy to say that SBE spanks PD, in the same way it is easy to say a Ferrari spanks a Honda. The Honda is a perfectly fine vehicle that meets the needs of really anyone, but it still isn't going to compete in performance or luxury to a Ferrari. The difference? Cost. Anyone that doesn't truly factor cost into their build isn't going to be looking for reviews. They are going to go to their vendor of choice, click on "CPU's" and then immediately click "Price: High to low" and grab the best.

Considering how inexpensive PD is, I think it performed extremely well.
 
#11 ·
Quote:
Originally Posted by pierowheelz View Post

Maybe I'm just a bit out of it today, but what is the scale on this graph? ie x-axis=?? y-axis=??
horizontal axis stands for what users pay for each chip. considering how close the performance of the amd chips to the higher priced intel chips - the cost - as Arktibot pointed out does not add up. but there are enthusiasts do not care about cost.
 
#12 ·
I personally think Piledriver and especially Bulldozer are both terrible CPU's because of their low IPC and high power consumption.... Almost nobody should be buying them.

But, you are testing the Nehalem at somewhat near it's max 24/7 overclock while the other processors have a much higher overclock ceiling. I think if you set each processor to their highest stable overclock and redid this test you would see the Piledriver almost catch up to the Nehalem and the Sandy bridge pull away by a larger margin.
 
#13 ·
Quote:
Originally Posted by Marshock View Post

Conclusion: in my opinion the Piledriver FX adds way too little improvements to be competitive clock per clock with both Nehalem and Sandy Bridge Core i7 processors, and though it is a must upgrade from a Bulldozer FX CPU, no way in hell should it be an upgrade from Nehalem based Core i7 processors.
The problem with clock-for-clock comparisons like this is that they don't take into account what clock speeds the parts are actually capable of, nor are you factoring in cost.

The average i7 920 will do around 4GHz, but all the other parts can be expected to do 4.4-4.6GHz on air.
Quote:
Originally Posted by rdr09 View Post

you get what you pay for . . .
An i7 920 or equivalent Xeon goes for about 100 dollars currently.

Yes, it may be a dead end platform, but chances are that the lowest end Gulftown will be faster than anything that ever shows up on AM3+.
 
#14 ·
Quote:
Originally Posted by Derp View Post

I personally think Piledriver and especially Bulldozer are both terrible CPU's because of their low IPC and high power consumption.... Almost nobody should be buying them.
But, you are testing the Nehalem at somewhat near it's max 24/7 overclock while the other processors have a much higher overclock ceiling.
This benchmark has nothing to do with processor models or pricing.

When do you people get it in you thick skulls? If you want a fair comparison, go here.

This could have been a test Core i7 960 VS FX 8100 - in this case you would say "But, you are testing the Bulldozer at somewhat near it's max 24/7 overclock while the other processors have a much higher overclock ceiling" see how you don't make sense now?

This was a review about the RELATIVE PERFORMANCE of architecture. If it had been done about MAXIMUM PERFORMANCE. All this is - Intel 4 cores, 8 threads vs AMD 6 cores. Sorry i could not bring in AMD 8 cores, perhaps in the future.
Quote:
Originally Posted by Blameless View Post

The average i7 920 will do around 4GHz, but all the other parts can be expected to do 4.4-4.6GHz on air.
4,5 GHz for both AMD (did a 4,6 GHz, but some games BSOD)
4,75 GHz for Sandy Bridge-E (all stable)
Quote:
Originally Posted by Derp View Post

I think if you set each processor to their highest stable overclock and redid this test you would see the Piledriver almost catch up to the Nehalem and the Sandy bridge pull away by a larger margin.
Yes i have overclocked both AMD chips to the max and Xeon W3520 at it's max still trashed them in many cases. Piledriver almost catch up Nehalem? No chance! Just 4 out of 20 games showed some improvement in FPS when Piledriver was set at 4500 MHz.
 
#16 ·
Well this is a great thread....
I always wondered what will be the differences between these chips at the same clocks...

It's good that Nehalem chips are still chugging along quite nicely even compared to SB-E chips @ 4.0 ghz, although if clocked higher it WILL be a substantial difference between all other chips.

Thanks for this!
Now the question is this, will Haswell be a good upgrade coming from Nehalem or Gulftown or hell even SB-E and Ivy, or should we just sit tight once again?
 
#17 ·
Interesting thread. Thanks for taking the time to do the comparisons!

And a bit of a warning to everyone since it's already starting to get tense: keep your replies professional and leave out the attitude!
 
#18 ·
It's fine arguing about cost, but until someone gets a really significant jump in performance, I'm not going to invest my cash.

4GHz i7 960 here, with a couple of i7 870's and an i5 665K....

Moar Powa PLeez....

( Sorry ! )

dunx
 
#19 ·
Quote:
Originally Posted by 2002dunx View Post

It's fine arguing about cost, but until someone gets a really significant jump in performance, I'm not going to invest my cash.
4GHz i7 960 here, with a couple of i7 870's and an i5 665K....
Moar Powa PLeez....
( Sorry ! )
dunx
I am also in this boat. Jumping from a 1090T and 1100T to a 2600K was a huge performance jump for me. However I held out on IVY and plan on holding out on haswell too. I can't forsee myself jumping again until Broadwell or Skylake. I haven't even OC'd this 2600k and monitoring in windows 8 even during some of the most intense games my CPU hardly ever goes above 2 GHZ.
 
#20 ·
Wait wait wait, I know is about relative performance, but realistically you are comparing high end i7's (four cores with hyper threading) vs a lowend/midrange 6 core (no HT obviously). Even at the same 4ghz I don't really see how this is much of a relative performance benchmark.

-prices are not even in the remotely same league
-different cpu markets completely

I just don't see how this is even good for relavance when not one of these processors was ever even meant to compete with eachother?

On another noyte, I do appreciate the time and effort put into this so I'm not bashing you, just trying to understand the reasoning for choosing a 6 core FX models vs 4c 8t intels?

The 6300 did pretty well considerings it's a $130 cpu going against these two workhorses.
 
#21 ·
Quote:
Originally Posted by SoloCamo View Post

Wait wait wait, I know is about relative performance, but realistically you are comparing high end i7's (four cores with hyper threading) vs a lowend/midrange 6 core (no HT obviously). Even at the same 4ghz I don't really see how this is much of a relative performance benchmark.
-prices are not even in the remotely same league
-different cpu markets completely
I just don't see how this is even good for relavance when not one of these processors was ever even meant to compete with eachother?
On another noyte, I do appreciate the time and effort put into this so I'm not bashing you, just trying to understand the reasoning for choosing a 6 core FX models vs 4c 8t intels?
The 6300 did pretty well considerings it's a $130 cpu going against these two workhorses.
+1
 
#22 ·
Intel FTW but im surprised AMD is catching up Intel is going to have to add some nice instruction sets with haswell to optimize it, but intel is smart with no 8 core as it isn't utilized by software yet and one step ahead with 22nm, Haswell better be promising, personally my next build will be 2014 DDR4 Successor to haswell, Skylake/skymont.
 
#23 ·
+rep, Thanks for all the hard work! I'm happy with spending more for intel!

After how long do you guys think a processor becomes too weak to use compared to newer ones?

I just got a i7 2700K a couple months ago and I was just wondering when I will have to get a new computer to play all the latest games.
 
#24 ·
Quote:
Originally Posted by SoloCamo View Post

Wait wait wait, I know is about relative performance, but realistically you are comparing high end i7's (four cores with hyper threading) vs a lowend/midrange 6 core (no HT obviously). Even at the same 4ghz I don't really see how this is much of a relative performance benchmark.
-prices are not even in the remotely same league
-different cpu markets completely
I just don't see how this is even good for relevance when not one of these processors was ever even meant to compete with eachother?
On another note, I do appreciate the time and effort put into this so I'm not bashing you, just trying to understand the reasoning for choosing a 6 core FX models vs 4c 8t intels?
The 6300 did pretty well considering it's a $130 cpu going against these two workhorses.
Now first I'm going to say awesome on taking the time to do the testing, but I would also like to add that the above quote does bring up some valid points. It would be a better comparison if it was benching/testing CPU's that were all within the same range as each other. Become kinda a no win scenario when your pitting high end against midrange
 
#25 ·
Sure, we all know AMD is behind Intel in terms of performace, however i still do not see your logic in putting a 3 core, 6 thread CPU of lower price, against a 4 core, 8 thread processor

HOWEVER

To everyone complaining, I ask that you go back and actually LOOK at the benchmarks. Of course Intel is ahead. However they are more expensive chips by a great margin.
So are these graphs a bit misleading? Perhaps... Although if you take time to look at them a bit you see that the AMD chips arent that far behind the Intel ones.

I dont think the OP's point of this thread was to bash AMD, just to show the truth. I buy AMD because its fast. If i wanted the fastest, i would obviously buy intel, however my 8320 hasnt ever failed to meet my needs.

In short, i think that the OP's research is very well put together, could be a bit less misleading, but you shouldnt be getting angry over this.
thumb.gif
 
#26 ·
Quote:
Originally Posted by Blameless View Post

The problem with clock-for-clock comparisons like this is that they don't take into account what clock speeds the parts are actually capable of, nor are you factoring in cost.
The average i7 920 will do around 4GHz, but all the other parts can be expected to do 4.4-4.6GHz on air.
An i7 920 or equivalent Xeon goes for about 100 dollars currently.
Yes, it may be a dead end platform, but chances are that the lowest end Gulftown will be faster than anything that ever shows up on AM3+.
Where are the $100 i7 920s? I've been looking for a good deal on a 920 for a while.

Great review op. Thanks for all the hard work.