Intel's Pentium Extreme Edition 965: The Last of a Dying Breed
by Anand Lal Shimpi on March 22, 2006 1:51 PM EST- Posted in
- CPUs
We were given a pleasant surprise by Intel at IDF just a few weeks ago: a fully functional and benchmark-able system based on Intel's next-generation desktop processor, codenamed Conroe. The performance that we saw was stunning and the power efficiency promised is a welcome change from the Pentium 4's NetBurst micro-architecture. But after leaving sunny California and returning to reality, we found another Intel chip in our labs; it just wasn't Conroe.
With the heatspreader on top of the chip, you could hardly tell it apart from a Conroe. It looked and smelled like one, but that's where the similarities end. While the fastest Conroe based processors will barely exceed 3.0GHz, this chip is clocked at a mighty 3.73GHz. Indeed, what Intel had sent us was no Conroe. It was the new dual core Pentium Extreme Edition 965, a chip that's being announced today, but one that won't actually be shipping in retail systems until next month. And yes, it's another very high clocked, deeply pipelined CPU from Intel. It's not the power efficient, high performing, competitive part that we want from Intel; it's yet another bump in the rocky road of NetBurst.
Needless to say, it's not a chip that we were too excited about, especially after having our appetites whet by Conroe earlier this month. But the new Extreme Edition did manage to surprise us in a number of areas, some of which may surprise you as well. When we last looked at the Pentium Extreme Edition 955, we found its power consumption to be a bit troubling. The move to 65nm didn't seem to do much for the Pentium 4, as AMD was still able to maintain a significant advantage in power consumption. As it turns out, the initial 65nm parts from Intel did not support all of the power management features that were introduced in later versions of Intel's 90nm silicon. Mainly, support for EIST (Enhanced Intel SpeedStep Technology) and the new C1E enhanced halt state, both of which were introduced over a year ago initially with C1E on the 5xxJ series of processors and later adding EIST on the 6xx series of processors. For whatever reason, neither technology made its way into the Presler EE chips (65nm dual core Extreme Edition). With the new Extreme Edition 965, Intel re-added support for C1E, but EIST is still not supported (note that C1E support was added to later steppings of the EE 955, just not the initial stepping). The two technologies vary as follows (taken from our Pentium 4 6xx review):
C1E - Enhanced Halt State
Also, keep in mind that AMD's Cool'n'Quiet is enabled, and the EE 965's C1E support is kicking in to keep its power consumption low at idle as well.
Under load, the comparison is also very close:
In our first look at Intel's Presler core with the Extreme Edition 955, we investigated the benefits of Hyper Threading with a dual core CPU as well as the performance impact of Presler over Smithfield. So, be sure to consult that article if you want a more in-depth look at Intel's 65nm dual core desktop CPU.
With the heatspreader on top of the chip, you could hardly tell it apart from a Conroe. It looked and smelled like one, but that's where the similarities end. While the fastest Conroe based processors will barely exceed 3.0GHz, this chip is clocked at a mighty 3.73GHz. Indeed, what Intel had sent us was no Conroe. It was the new dual core Pentium Extreme Edition 965, a chip that's being announced today, but one that won't actually be shipping in retail systems until next month. And yes, it's another very high clocked, deeply pipelined CPU from Intel. It's not the power efficient, high performing, competitive part that we want from Intel; it's yet another bump in the rocky road of NetBurst.
Needless to say, it's not a chip that we were too excited about, especially after having our appetites whet by Conroe earlier this month. But the new Extreme Edition did manage to surprise us in a number of areas, some of which may surprise you as well. When we last looked at the Pentium Extreme Edition 955, we found its power consumption to be a bit troubling. The move to 65nm didn't seem to do much for the Pentium 4, as AMD was still able to maintain a significant advantage in power consumption. As it turns out, the initial 65nm parts from Intel did not support all of the power management features that were introduced in later versions of Intel's 90nm silicon. Mainly, support for EIST (Enhanced Intel SpeedStep Technology) and the new C1E enhanced halt state, both of which were introduced over a year ago initially with C1E on the 5xxJ series of processors and later adding EIST on the 6xx series of processors. For whatever reason, neither technology made its way into the Presler EE chips (65nm dual core Extreme Edition). With the new Extreme Edition 965, Intel re-added support for C1E, but EIST is still not supported (note that C1E support was added to later steppings of the EE 955, just not the initial stepping). The two technologies vary as follows (taken from our Pentium 4 6xx review):
C1E - Enhanced Halt State
"Whenever the OS executes the halt instruction, the CPU enters what is known as the halt state. Architecturally, what's going on in a halt state is the clock signal is shut off to the CPU for some period of time. With no clock signal, none of the logic in the chip will do anything and thus power consumption is reduced. Performance is also significantly reduced; however, the halt instruction isn't usually called during application usage, so the performance aspects of the halt state aren't very important.EIST:
The problem with the halt state is that it does nothing to reduce voltage, only current draw by stopping clocks from going to the CPU. Since Power varies linearly with both current and voltage (P = I * V), you're effectively only addressing half of the problem. The Enhanced Halt State, as Intel calls it, does two things: it reduces the clock speed of the CPU by decreasing the clock multiplier down to its minimum value (on the EE 965 series, that's 14x, or 2.8GHz), then reducing the voltage. The clock speed is reduced and then the voltage is dropped, to maintain stability.
Intel insists that the enhanced halt state is a significantly lower power state than the conventional halt state, thanks to the reduction in voltage in addition to the reduction in clock speed. While the standard halt state causes a linear reduction in power, Intel's enhanced halt state causes an exponential decrease in power, potentially offering better power savings than the standard halt state. The real world impact obviously depends on how idle your system happens to be."
"What EIST does is very similar to AMD's Cool'n'Quiet. It is demand based reduction in CPU clock speed and voltage. Using the same mechanism of adjusting clock speed and voltage, based on the application demand, the processor will dynamically increase/decrease its clock speed between its minimum clock and its normal operating frequency, as well as voltage, in order to optimize for power consumption.Because of the support for C1E and Intel's 65nm process, power consumption is finally competitive with AMD. Let's have a look at idle power consumption first:
Because of the way EIST (and AMD's Cool'n'Quiet) works, there's inherently a drop in performance. The idea is this: if you're performing a task that's not using 100% of the CPU, the CPU will operate at a slightly reduced frequency in order to conserve power. So, while some tasks will require that the system run at full speed, others will run at lower speeds. "
Also, keep in mind that AMD's Cool'n'Quiet is enabled, and the EE 965's C1E support is kicking in to keep its power consumption low at idle as well.
Under load, the comparison is also very close:
In our first look at Intel's Presler core with the Extreme Edition 955, we investigated the benefits of Hyper Threading with a dual core CPU as well as the performance impact of Presler over Smithfield. So, be sure to consult that article if you want a more in-depth look at Intel's 65nm dual core desktop CPU.
Facebook
Twitter
RSS
41 Comments
View All Comments
TheTrue - Sunday, April 2, 2006 - link
You guys are really Amazing, jealous of others success, to all of the losers here is going to happene what happend to all the ATI Fan boy, now nvidia is back and there they with the mouth on they assess, if Intel make a faster and better chip then we are the one who should be happy because the price will come down for a better chip. Keep dreaming about AMD is better, that is why every server in mission critical task out there for professional business around the globe use AMD?. Let me see, why Intel Xeon not opteron?, I will get a new chip and that will be Intel I don’t give a damn what some no body think about a company just because they are jealous of the success of that company, just like the geek who use apple, now they are using Intel Chip. Before intel was the worse now they are going to use the very product that they said was so bad and slow, that is what is going to happen to all of you who talk so bad about Intel and the time come, you will do what all of the ATI Fan boy are doing, that is using what is better and that is nvidia. so stop talking like that about Intel, because if not because of Intel you losers will be right now in the toilet with your hand on something else and is not a keyboard.TheTrue - Sunday, April 2, 2006 - link
You guys are really Amazing, jealous of others success, to all of the losers here is going to happened to all the ATI fun boy, now nvidia is back and there they with the mouth on they assess, if Intel make a faster better chip then we are the one who should be happy because the price will down for a better chip. Keep dreaming about AMD is better, that is why every server or mission critical task out there on professional business around the globe use AMD. Let me see, why Intel Xeon not opteron?, I will get a new chip and that will be Intel I don’t give a damn what some no body think about a company just because they are jealous of the success of a company, just like the geek who use apple, now they are using Intel Chip. Before intel was the worse now they are going to use the very product that they said was so bad and slow, that is what is going to happen to all of you who talk so bad about Intel.CobraT1 - Monday, March 27, 2006 - link
To complain about a "look ahead" during the wrap-up is totally ridiculous. This is why we read these articles, to be informed. If one is gathering information on a current purchase and is not interested in waiting, then one can easily omit the "look ahead's" inclusion.Here is what was stated in this "highly controversial" look ahead,
If you need more of a reminder of why it will only help to wait, here are a few of the Conroe tests that we were able to run at IDF, which we duplicated on our systems here (same test configuration, test files and hardware):
Conroe is being compared in one test area (encoding), an area which is the P4 true strength. The point being made that the P4 will be a soon to be obsolete, not that it outperformed the FX-60. The P4 already demonstrated that. This comparison "HURTS" Intel. Why would Intel pay for that?
While the 965 has become a lot more competitive with the FX-60, our overall nod still goes to AMD.
For current buyers who must have high-end, AMD is the way to go. Why would Intel pay for a recommendation for an AMD part?
With AMD's Socket-AM2 right around the corner, and Conroe not too far away, we honestly can't recommend anything but a low cost CPU today to avoid virtually immediate obsolescence. And we'll be telling you exactly what low cost CPU that would be sometime next week...
AT is recommending a low cost CPU for current buyers and will be releasing a comparison with the specific recommendations next week. How would this comment be biased one way or the other? What CPU or CPU's do you think that they will recommend? Has someone's confidence been shaken?
Intel would not pay for a review that essentially says that although the latest P4 is an improvement and brings it closer to what is currently offered by AMD, despite it's strengths in a few areas the overall recommendation after comparing these 2 high-end parts in the P4EE review is the FX-60. To assert that Intel paid for such a recommendation is stupid.
The review was balanced and the inclusion of the "look ahead" was appropriate as it supported one of their final recommendations (as there was more than 1) regarding the part under review. They conclude after reviewing the P4EE,
1- The FX-60 is the better overall CPU at this price point.
2- The P4EE is only recommended if it's strengths are the primary requirement.
3- For current buyers, purchase a low cost part and wait for their comparison next week for assistance.
4- If a buyer can wait 3 to 6 months, the Conroe looks to easily outperform the current high-end from both companies at half the cost.
AT has been forthright regarding the Conroe and has misrepresented nothing. It was clearly stated when it is to be released, there was no attempt to mislead. The information known about the Conroe should be included in every CPU review and\or comparison at it's performance level or expected price point. How many times have reviews (not just CPU's) ended with "xxxxx coming out in a few months is not expected to provide much benefit" or "xxxxx is due out in a few months, if you can wait you may be better off". This is a common practice and to NOT have this information for consideration would do all readers as well as prospective buyers a disservice.
These silly accusations against AT as being "paid off" are pathetic and nothing more than a sign that there is fear in hearts of those who have tied themselves to of all things, a corporation. We can all be thankful that these people are not doing the reviews.
Some people really need to grow up.
rallyhard - Friday, March 31, 2006 - link
To complain about a "look ahead" during the wrap-up is totally ridiculous.Some people really need to grow up.
My thoughts exactly.
Reynod - Sunday, March 26, 2006 - link
Lets be clear about the comparisons here - AMD X2 and 64 cpu's currently exist and so do the Intel P4's. Conroe isn't a production part, so why are you making comparison's with it, the FX series and the new 965's when Conroe can't be bought??Why ... well it is clear ... this site has been bought out by Intel just like Toms was a few years back.
Intel obviously payed you very well for the positive feedback, and the constant references in benchmarking since eh??
Reynod - Thursday, March 30, 2006 - link
Thanks for that.I have always preferred to check Anand's views on new technology in the past as I always considered his reviews balanced.
I think this review fell into a serious hole because it essentially isn't of any value, and as a propaganda tool, I feel it has damaged AMD's reputation in the market.
AMD and Intel both have prototype silicon capable of much higher level of function than we currently enjoy today, however, none of it is at mass production spec.
The Conroe review is flawed because it was reviewed without ever being a production chip. This hypes the market up for Intel, and does unneccessary damage to the fragile market AMD has garnered over the past few years where they have enjoyed a small advantage, both in terms of raw cpu power and lower thermal envelope.
AMD is a small company, Intel is huge.
Reviewing an engineering sample like this in isolation therefore does more damage than good.
I only made my previous point to make it clear that I was outraged - I apologise for the comment.
I, like many others, have enjoyed the power that AMD has brought to the PC world with it's competition with Intel.
If AMD were not around, we would still have P3's as Intel would have had no competition ... we would also be paying a lot more money for CPU's.
Competition breeds innovation.
Bias (intentional or otherwsie) places unfair advantage ..
Pino - Thursday, March 23, 2006 - link
Can´t belive Anand is promoting a CPU that will not be launched in next 6 months.I´m not an AMD or Intel fan.
I´m fan of my pocket!
It´s good to see that in the future we´ll have options, because today we only have one choice, AMD.
But until them, I wish Anand to stay against the paper launches, as ever.
stephenbrooks - Thursday, March 23, 2006 - link
--[Can´t belive Anand is promoting a CPU that will not be launched in next 6 months.]--You'd rather he told you to buy the 965 EE? :)
PrinceGaz - Friday, March 24, 2006 - link
No, he would tell us to buy the FX-60 rather than the 965 EE, as the FX-60 is better.If Conroe were going to be available for purchase in the next month or even two months then including verified benchmark results for it would be fine, but it is still half a year away. If AT is going to routinely start including results for parts that we won't be able to buy for half a year, continuous improvements in price/performance means the recommendation on what to buy will always be to wait several more months. That's not much help for someone who wants to upgrade. You should only include products which are either available or will be available very soon.
coldpower27 - Friday, March 24, 2006 - link
Well it varies, some reports say Late June, while the most pessimistic reports say September. So anyware from 3 to 6 months away.It's good to know this as in potentially less then half a years time your going to be getting a CPU on the Intel side that will outperform this processor by a large margin 20% or greater, and which cost half the price.
This is like getting an Athlon 64x2 2.2GHZ/2x1MB for 1000US now and in at most 6 months you can get something like Athlon 64x2 2.8GHZ/2x1MB for 500US, using current performance improvement timetables this typically hasn't occured, and such a grand scale of price cuts or performance enhancement in such a short interval of time for CPU's.