[Techspot] Then and Now: A decade of Intel CPUs compared, from Conroe to Haswell

[escrow4]

Fascinating (and Core 2 gets murdered):

http://www.techspot.com/article/1039-ten-years-intel-cpu-compared/page7.html

"In 2006 the Core 2 Duo E6600 retailed for $316 and in its place today we have the Core i7-4790K for roughly the same price at $339. The 4790K is clocked at almost twice the frequency, features twice as many cores, and four times as many threads.

Actual performance gains are more impressive.

The Core i7-4790K is eleven times faster in Excel 2013 and Hybrid x265, six times faster in 7-Zip, Photoshop CC, and HandBrake. When it came to gaming, the 4790K was twice as fast in BioShock Infinite and Crysis 3, seven times faster in Metro Redux, three times faster when testing with Hitman Absolution and just barely faster in Tomb Raider."

"Although the Core 2 Quad Q9650 performed considerably better than the E6600, it was still worlds slower than the i7-4790K and often found itself outpaced by the Pentium G3220 (Haswell) and even the Celeron G1820.

The Core 2 processors were fine for general usage under Windows 8.1, though it has to be said a 4-10w SoC provides about the same experience."

And look at that 8350 - its a power pig:

Indeed, very interesting . . . .

 

[mrmt]

And look at that 8350 - its a power pig:

Nah, it's just this set of biased, irrelevant benchmarks that make the FX look bad. If you use hardware.fr test suit combined with Mantle games you'll see how efficient the FX really is.

 

[Greenlepricon]

Not really sure what the power consumption of AMD's chips has to do with the wording of the thread, but we all know the 8350 isn't energy star certified at this point. Those graphs don't really mean much to the average user and especially not to the Intel chip comparison out of context.

Regardless, it's pretty interesting to see how quickly performance has grown. Sadly it also shows how performance is slowing. There are a few areas where the most recent chips are doing great, but Sandy Bridge owners are still looking pretty good in retrospect.

 

[Sweepr]

Nah, it's just this set of biased, irrelevant benchmarks that make the FX look bad. If you use hardware.fr test suit combined with Mantle games you'll see how efficient the FX really is.

You can't argue with numbers. No ad hominem will change the basic physics laws.
Jokes aside, crappy Vishera is a power hog. 50-65W more than an old Core 2 Quad.

I wish they include Skylake-S results soon.

 

[inf64]

Well we all know 32nm Piledriver is not a power friendly chip. Power issues aside it does perform solidly in a lot of those benchmarks they used, plus when you realize that most workloads won't last that long then it becomes the comparison in idle power between the platforms (intel again wins of course but the difference is smaller there).

I like this test because it shows us how much more performance we got from both intel and AMD 10 years since Core2 launched. Some of those perf. jumps are crazy, let's hope next 10 years bring similar gains .

 

[Makaveli]

I wish they would have added 6 cores chips to the testing.

Would have loved to see the number from Gulftown, SB-E, Ivy-E, Haswell-E

 

[Fjodor2001]

Since this article had the intention of comparing various Intel CPUs over the last decade, why not include an Intel CPU to illustrate the ones that had high power consumption? There are plenty to choose from, like the Pentium D :

 

[Makaveli]

Since this article had the intention of comparing various Intel CPUs over the last decade, why not include an Intel CPU to illustrate the ones that had high power consumption? There are plenty to choose from, like the Pentium D :

Seems like a very biased article...

And what if they didn't have any p4's or able to get one.

those systems are 10+ years old.

I don't see the problem stopping with conroe I don't know anyone still using a p4 while I know people still on conroe I think you are looking for bias when there isn't any.

 

[mrmt]

Well we all know 32nm Piledriver is not a power friendly chip. Power issues aside it does perform solidly in a lot of those benchmarks they used, plus when you realize that most workloads won't last that long then it becomes the comparison in idle power between the platforms (intel again wins of course but the difference is smaller there).

I think that the performance increases will be even more tied to dedicated hardware than about the processor themselves. I expect this game to become very expensive, and unable to sustain the myriad of small companies that live on the market today.

 

[SlowSpyder]

It's worth mentioning that while it does use a good deal of power, it also performs pretty respectably in those benches. Though, obviously it's performance per watt won't be as good as Intel's offerings.

 

[RaistlinZ]

I think my dad still uses a P4 or Pentium D HP machine on Windows XP.

 

[ShintaiDK]

Core 2 Duo/Quad is just not enough

 

[Makaveli]

I think my dad still uses a P4 or Pentium D HP machine on Windows XP.

lol I was waiting for the first my parents / grand parents still use p4

 

[jpiniero]

Things have now slowed at the top end for sure though. Low power and mobile is where it's at.

 

[Fjodor2001]

And what if they didn't have any p4's or able to get one.

those systems are 10+ years old.

The article's intention was to include Intel CPUs over the last decade. That should include Pentium Ds (some models are from 2006).

And saying it's hard to get hold of a Pentium D is a really poor excuse. They are quite easy to come by, e.g. from eBay or whatever.

I don't see the problem stopping with conroe I don't know anyone still using a p4 while I know people still on conroe I think you are looking for bias when there isn't any.

So you think your personal experiences should determine what CPUs they should include in the test? I know persons using both Pentium 4 and old Conroe models, but not many of either. Still it doesn't matter, since the article's intention was to compare "Intel CPUs over the last decade", not "Intel CPUs over the last decade, that still are being used commonly by the social network of some selected AnandTech forum members".

Finally, if this was a test to compare Intel CPUs, why did they cherry-pick a single AMD CPU that has high power consumption for the only purpose of "winning" the highest power consumption award? Either they should keep it strictly Intel CPUs, or include several other CPUs from AMDs lineup over the years too. Them failing to do so is obviously biased, whether intentional or not.

PS. I noticed that they added an "alibi" 7870K too, but that does not really change much. Not sure what it's doing in their "Intel test" to be begin with, and if it's "Intel and AMD test", then there should be plenty more AMD CPUs included.

 

[MiddleOfTheRoad]

Nah, it's just this set of biased, irrelevant benchmarks that make the FX look bad. If you use hardware.fr test suit combined with Mantle games you'll see how efficient the FX really is.

It does scream bias -- to omit the Core i7 920 which makes the power consumption of the FX-8350 look downright thrifty (Afterall, the i7 920 pulls twice the juice @ 4 Ghz).

FX power consumption is pretty typical for a 32nm chip. But again, the fanboys love to play loose with the actual facts.

 

[ShintaiDK]

Did you just use an OCed chip as an excuse?

 

[mrmt]

It does scream bias -- to omit the Core i7 920 which makes the power consumption of the FX-8350 look downright thrifty (Afterall, the i7 920 pulls twice the juice @ 4 Ghz).

FX power consumption is pretty typical for a 32nm chip. But again, the fanboys love to play loose with the actual facts.

Except that the 920 is a 45nn chip. FX power consumption is not typical when compared to others 32nm chips.

 

[Sweepr]

Did you just use an OCed chip as an excuse?

Not only this but most likely an older stepping, not D0. The fact that he has to pick a 2008 chip to make AMD look better shows how crappy Vishera is.

I'm suprised we made it to 18 posts without Hardware.fr graphs.

 

[Spjut]

Looks like Lynnfield still has plenty of life left!

 

[BigDaveX]

Finally, if this was a test to compare Intel CPUs, why did they cherry-pick a single AMD CPU that has high power consumption for the only purpose of "winning" the highest power consumption award?

If they wanted to do that, they'd have gone with the FX-8150 or an FX-9000 series CPU, both of which are far more power-hungry than the FX-8350.

Not to mention the fact that the FX-8350 is one of the highest-end chips that AMD currently sells, whereas the Pentium D hasn't been part of Intel's line-up for nine years. If anything, reminding people of the fact that you need to go back to the Bush administration to find the last example of a dud Intel chip would make Intel look better, not worse.

As an aside, I'm surprised that the Core 2 Quad line has aged so poorly. When the initial Core i7s were released, they were generally a little slower than the Core 2s in games.

 

[Sweepr]

45nm chip from 2009, 100W less than FX and still solid performance. Lynnfield was a great chip but I ended up going Bloomfield by then.

 

[Sweepr]

As an aside, I'm surprised that the Core 2 Quad line has aged so poorly. When the initial Core i7s were released, they were generally a little slower than the Core 2s in games.

I noticed that too. Bloomfield (first gen Core i7) aged much better than Core 2.

 

[crashtech]

The take away for me is that at this point, Nehalem is still adequate (depending on model/clocks), but Core2 (even quad) is a goner for sure, nothing we didn't already know. I tend to lean a little more forward in my recommendations to my customers, discouraging repairs on anything older than a Sandy Bridge.

 

[frozentundra123456]

I think my dad still uses a P4 or Pentium D HP machine on Windows XP.

A fair number of work machines in my analysis lab still use P4 for HPLC analyis and control software, with XP also. Obviously they arent connected to the internet.