Sign in with
Sign up | Sign in
Your question
Closed

CORE Or Boost? AMD's And Intel's Turbo Features Dissected

Last response: in Reviews comments
Share
July 28, 2010 6:29:14 AM

Not as powerful but at least amd is doing some thing to stand up to the monster named i7...
Score
17
July 28, 2010 6:52:50 AM

It would be nice to include i3 530/i5 750/i7 860 so that we can see if a more aggresive speed bump worth its cost.
Score
10
Related resources
July 28, 2010 6:57:58 AM

With manual overclocks being as easy as changing numbers due to unlocked multipliers on both those CPU's, i guess the turbo effect is not that much of a consideration.. Moreover, most of us (IMO) prefer running at single stable clock readings rather than allowing frequent dynamic changes..
Score
3
July 28, 2010 7:11:05 AM

While AMD's implementation is more crude, I think they did okay in this test. I hope they will continue improving their Turbo CORE so it can become more competitive against Intel. After all, Intel had nearly 2 years of head start to perfect their Turbo feature.
Score
12
July 28, 2010 7:56:38 AM

AMD's Turbo CORE is not that good, but I will give it that it came up with a trick that works, at least for single threaded applications.
Score
-1
July 28, 2010 8:22:47 AM

I couldn't tell was Hyper threading on or off for these tests? Also I agree seeing the other i5 and i7 implementations that have more aggressive turbo boost parameters would be good to see in that we could see if the efficiency holds up and what % increase per clock is, like if it is a linear gain or a diminishing returns game.
Score
0
July 28, 2010 8:40:16 AM

When was this article actually written? I'm asking because the Drivers and Software section for the AMD motherboard isn't present and the BIOS on the Asus and Intel boards are old.
I'm not saying that with new bios-es and drivers the outcome would be different(or would it be?) but what I am saying is that if this was written a couple of months ago, why wasn't it published then?
Score
0
Anonymous
July 28, 2010 9:15:27 AM

Quote:
The 800-series even bumps clock speed up by five clock speed bins for a single core. One speed bin equals 133 MHz at stock speed, so we’re effectively talking about a 133 to 533 MHz dynamic increase.

Dousn't 5 times 133Mhz equals 666Mhz ?
Score
2
Anonymous
July 28, 2010 9:30:59 AM

Wow, the benchmark graphs in this article are absolutely nonsensical! What are they calibrated against? Sometimes the Turbo value is at 100%, sometimes the non-turbo value, and it's different for AMD and Intel in the same graph.
Score
2
July 28, 2010 11:04:04 AM

Probably amd's development is hindered by intel's patents.
Score
0
July 28, 2010 11:35:00 AM

wtf? how can you have 100% and 100%+ on others? That makes no sense, and it shouldn't hurt to do a 5min data check would it?
Score
-10
July 28, 2010 12:48:02 PM

Am I reading the graphs correctly?? AMD's 400 mhz overclock is more than 10 percent on half the cores, but performance only increased a few percent at max and in most cases only a percent or two??? Doesnt seem to scale very well with the speed increase. I think intel is the same but their overclock is less so it is hard to say.
Also, I know it has already been published, but I would like to see the absolute performance of the two chips vs one another. The percent increase does not address at all which chip is actually faster. I know that was not the point of the article, but that is still the most inportant factor, after all.

And how about some gaming results??
Score
2
July 28, 2010 1:03:53 PM

Cool article. In the future, when there are cheaper processors available that use these features from both manufacturers, I would like to see a similar article related to games!
Score
0
July 28, 2010 1:16:22 PM

AMD's 300$ processor on par with Intel's 1000$ !! I think this is more than enough to declare AMD as a clear winner here.
Score
-1
July 28, 2010 1:36:30 PM

If on par means taking about 30% longer to complete the same tasks....lol

And it sounds like the authors "ideal turbo" is exactly what the socket 1156 parts all use....an i7 870 should have been included in these tests
Score
0
July 28, 2010 1:39:38 PM

Good to see AMD trading blows with Intel. The main reason i have stuck with AMD is the price/performance. Even with the boosts intel is clearly superior and in most cases really doesnt need the boost.. though it never hurts. Will be interesting to see if Bulldozer come to fruition in early 2011 how much things will change.
Score
4
July 28, 2010 1:41:52 PM

Turbo feature -> retarded. Do old style overclocking!
Score
0
a b À AMD
July 28, 2010 1:48:45 PM

Nice article and doesn't exist a winner here just depends of what do u want to do with the CPU. Intel is much better is somethings and AMD have better results in others.

The price of both Intel and AMD CPUs aren't important here since is a performance chart with stock and turbo features not a price/performance comparative.
Score
0
July 28, 2010 1:52:24 PM

These two write the most boring articles, and come up with a conclusion anyone would have guessed.

The Lynnfield processors already have a more aggressive turbo boost, by the way.

The last statement is really poor. The specifics of the processor should determine how much boost they give it, not a blanket statement of discrete amounts. While I agree the boosting could have been improved on these processors, it's got to be a case by case basis depending on the processors' characteristics, and the companies design goals with that specific unit.
Score
2
July 28, 2010 2:14:51 PM

I liked the article because for me it further justifies why my last CPU purchases made this year were for AMD's 955BE and hexacore 1055T. This article shows that AMD not only can compete with their own version of turbo boost but more importantly, AMD offers better value - $180 for an AMD hexacore versus nearly a grand. $1,000!!, for Intel's hexacore.
Score
-1
July 28, 2010 3:01:54 PM

Intel has had 2 generations to work on their turbo technology, this is AMD's first chip. I say we give them a chance to catch up a bit and we test again.
Score
0
July 28, 2010 4:15:09 PM

just wondering how an OS like windows or linux uses the available cores
Score
0
July 28, 2010 6:00:37 PM

I gotta ask, why didn't you have a Lynnfield here as well? They're the chips that are perfect for it, plenty of thermal headroom and aggressive scaling to use it. 266 MHz on a 3.33 GHz chip is pretty meh (~8%) as the article notes, 533 MHz on a 2.66 GHz chip (20%) is actually significant.

1055T vs. i5-750, turbo battle to the death at $200.
Score
3
July 28, 2010 7:09:03 PM

interesting enough, it also figures as AMD is more realistic in allowing more average users to gain from only using 3 full cores, which would be games, a virus scan, and another app running in the background, while few use 4 or even 6 cores... makes sense.... pricewise, AMD wins hands down....
Score
1
Anonymous
July 29, 2010 12:45:10 AM

The % increase graphs in all the early benchmarks are really misleading. Of course if you pick the Intel processor that is already near it's thermal limit you aren't going to see much improvement with Turbo. Why not compare two CPU near the same price point, or throw in the lowest-end Intel CPU, say the i5 750, which should be one of the highest % increases with Turbo since it has the most thermal headroom.
Score
0
Anonymous
July 29, 2010 12:49:23 AM

not all 3ds max's tasks multithreaded, calculating the particles as example and many others
Score
0
July 29, 2010 1:44:45 AM

Too many AMD haters here... Move on kids.
Score
0
July 29, 2010 3:08:46 AM

how about benching with the proc overclocked and turbo boost disabled??? who cares about a feature they turn off when you overclock???
Score
0
July 29, 2010 4:58:09 AM

Lets put David and Goliath to fight and "wonder" what is the outcome. Still I'd take "David" any day.
Score
-1
July 29, 2010 5:30:12 AM

I don't see that much benefit from having the Intel hexacore chip over AMD. Even those what you call "significant" difference cannot justify the extra royalties that I have to pay for the Intel's chip.
Score
-1
July 29, 2010 3:35:11 PM

Thanks for a very informative article.
Score
-1
July 29, 2010 7:05:11 PM

kikireeki
Absolutly I am thrilled with this results. And specially for what I do, 3D rendering, as they look very even. I like it and $300 is more than good for me. I am going to keep my eye on this processor for my next system.
Score
-1
July 30, 2010 3:41:43 AM

Am I the only one who finds benchmarks to be worthless when every one of them uses the $1000 i7 980x Extreme Edition? No one who isn't retarded even owns that chip, so it really tells us nothing.

Use something competing at the same price point, then get back to us.
Score
0
July 30, 2010 10:29:15 PM

Something is wrong with your article. It does not show Intel completely trouncing AMD in something other then price vs performance. Please try again in the future.
Score
-1
August 1, 2010 2:57:25 AM

While Intel® Turbo Boost Technology availability is independent of the number of active cores, the operation is dependent on having headroom (cores operating under TDP) available in one or more cores. The amount of time the system spends in turbo boost will ultimately depend on workload, operating environment, and platform design.
http://www.intel.com/support/processors/sb/cs-029908.ht...
Score
0
Anonymous
August 1, 2010 4:28:41 PM

amd is win
300$ Vs 1000$

Score
0
Anonymous
August 3, 2010 8:36:42 PM

You have to wonder if many consumers even need this? Its almost like adding 4GB RAM but never using anymore then 2.5GB RAM. You just bought yourself RAM that will never get used. If you want to buy into the notion that Turbo charging a CPU is a needed feature go ahead. To me its a gimmick now that the chip makers have reached a brick wall in actual core speed.
Score
0
Anonymous
August 4, 2010 7:39:17 AM

can i copy this articel to my blog?
Score
0
August 4, 2010 11:13:20 PM

I have a really good idea. Let's take $1,000 CPU and compare it to a CPU that cost less than 1/3 of it's price.

Oh wait, tom already did. Great job. This will really help me decide between these CPU's. I was on the fence :|
Score
0
August 4, 2010 11:13:33 PM

I have a really good idea. Let's take $1,000 CPU and compare it to a CPU that cost less than 1/3 of it's price.

Oh wait, tom already did. Great job. This will really help me decide between these CPU's. I was on the fence :|
Score
0
Anonymous
August 5, 2010 9:55:47 PM

Personally I find it Hilarious that people can justify and 60-75% increase in cost, over a few nanoseconds of processing time. I have built Machines for over 10 years with AMD and the price/performance ratio is much more affordable..
Score
0
August 7, 2010 3:45:01 AM

I build regularly and customers are almost always happier with the price/performance of AMD over Intel. I've got a 1055t @4ghz and for $200, you honestly cannot beat that level of performance. Especially when you factor in the overall system cost associated with a socket 1366 over the AM3. You can buy a nice 890xx AM3 board with usb3/sata6gs for around half of a comparable 1366 board and definitely less than a 1156 board as well.

AMD is the best value for your dollar; if you know core unlocking/overclocking the value offered is even more exceptional.
Score
0
Anonymous
August 10, 2010 5:42:50 PM

go AMD go
Score
0
Anonymous
August 12, 2010 12:48:15 AM

The gulftowns are 32nm and the thubans are 45nm. There will be a difference in the power use due to the die size.
Score
0
August 12, 2010 12:02:20 PM

Watt-hours are a measure of energy, not power. The "total power used during a run" doesn't make any sense, power is a rate not a property.
Score
0
August 12, 2010 7:53:33 PM

I'm happy both camps are staying competitive. For a while it was hard to even recommend AMD. am2 was a joke but am2+ and am3 cpus are impressive if on a budget. Also Intel is really competitive in the 200 dollar range. you can buy a i7 930 @ microcenter for 199.99. That is crazy performance for not too much. I once bought a opteron 165 for 229.99. ouch It is a great time to be in the market.
Score
0
Anonymous
August 13, 2010 11:17:07 AM

Here is an interesting point.I have a 1055T o/clocked to 3.4GHz and use it for Rendering in 3D max.The 6MB level 1 & 2 cache does come into play.Rendering a scene with just 2 cores enabled and then one with all 6 cores enabled does not equate to completing it in 1/3rd of the time of just enabling 2 cores.In fact it completes it in just under 2/3rds of the time of using 2 cores.It means that running with 2 cores use the 6MB cache the chip runs very well indeed.6 cores enabled then have to share the 6MB between them.That in turn constricts the performance somewhat.If it had 12MB then it may scale correctly.Perhaps AMD need to look at this in time for Bulldozer.
Score
0
Anonymous
August 23, 2010 9:59:16 PM

$300 For one Or $1000 for the other, I mean really unless you look forward to handing over thousands of green backs for a gaming rig or your Intel horse is just to big to come down off of, its pretty easy to see that the 980 is just an over priced conversation piece but, one exception would be the mac pro being a creative machine and the only choice you have. I'm just looking from a total cost and value stand point.
Score
0
August 24, 2010 5:34:26 PM

"This is why the feature works better on a CPU with an even core count, such as the Phenom II X4 960T."
"works better on a CPU with an even core count"
"even core count"
"even"

Sorry, is 6 not even enough for you?
Score
0
!