Print
You can’t recompile the world. That’s the lesson Intel learned with the Pentium 4, which kicked ass with optimized code but ran like a Yugo with legacy apps. And even with Intel’s nearly limitless resources, it couldn’t get every developer to update software for the P4.
Intel took those lessons to heart with the stellar Core 2 and continues in that vein with Core i7, which is designed to run even existing code faster. That’s largely due to the Hyper-Threading, massive bandwidth, and low latency in the new chip, but other touches also help.
Loop conditions are common programming techniques that repeat the same task in a CPU. With Core i7, an improved loop detector routine will save power and boost performance by detecting larger loops and caching what the program asks for. Intel also polished its branch prediction algorithms. Branch predictions are those yes/no questions a CPU faces. If the CPU guesses wrong on what the program wants, the assembly-line-like pipeline inside the CPU must be cleared and the process started anew. New SSE4.2 instructions also make their way into Core i7, but they will be of little benefit to desktop users. Since Intel is designing the chip for server use as well, the new instructions are mainly to help speed up supercomputing and server-oriented workloads.
The main takeaway is that while some of the changes are radical, Intel is being pragmatic with its chip design—you won’t have to go out and buy new software to experience the CPU’s performance potential.
With a Hyper-Threaded quad core, even enthusiasts are unlikely to see the need for a multi-processor machine; nevertheless, one of the new features in Core i7 directly addresses a weakness in Intel’s current lineup when it comes to multi-CPU machines. As you know, Intel currently uses a front-side-bus technology to tie its multiprocessor machines together. As you might imagine, problems arise when a single front-side bus is sharing two quad-core CPUs.
With so many cores churning so much data, the front-side bus can become gridlocked. Intel “fixed” this issue by building chipsets with two front-side buses. But what happens when you have a machine with four or eight CPUs? Since Intel couldn’t keep adding front-side buses, it took another page from AMD’s playbook by building in direct point-to-point connections over what it calls a Quick Path Interconnect. Server versions of Core i7 feature two QPI connections (desktop versions get just one), which can each talk at about 25GB/s, or double what a 1,600MHz front-side bus can achieve. AMD fans, of course, will point out that the fastest iteration of AMD’s chip-to-chip conduit, dubbed HyperTransport 3.1, is twice as fast as the current QPI.
QPI combined with the on-die memory controller will also make an Intel server or workstation a NUMA, or non-uniform memory access, design. Since each CPU has a direct link to its own individual memory DIMM, what happens if CPU 1 needs to access something that’s stored in the RAM being controlled by CPU 2? In this case, it must use the QPI link to access the second CPU’s memory controller to the RAM to get the data. This will slow things down a bit, but Intel says its tests indicate that even given this scenario, the memory access is still faster than what is possible with the current front-side-bus multiprocessor design.
It’s a known fact that overclocking can decrease the life of your CPU; thus, Intel has always discouraged end-users from overclocking its CPUs. With Core i7, Intel reverses its stance and actually overclocks the CPU for you! Of course, Intel would not describe its Turbo mode as overclocking, and, technically, it isn’t. While pushing your 2.66GHz Core 2 Quad to 3.2GHz would likely strain its thermal and voltage specs, the new Core i7 CPUs feature an internal power control unit that closely monitors the power and thermals of the individual cores.
This wouldn’t help by itself, though. Intel designed the Core i7 to be very aggressive in power management. With the previous Core 2, power to the CPU could be lowered only so far before the chip would crash. That’s because while you can cut power to large sections of the execution core, the cache can tolerate only so much decrease in power before blowing up. With Core i7, Intel separates the power circuit, so the cache can be run independently. This lets Intel cut power consumption and thermal output even further than before. Furthermore, while the Core 2 CPUs required that all the cores were idle to reduce voltage, with Core i7, individual cores can be turned off if they’re not in use.
Turbo mode exploits the power savings by letting an individual core run at increased frequencies if needed. This again follows Intel’s mantra of improving performance on today’s applications. Since a majority of today’s applications are not threaded to take full advantage of a quad core with Hyper-Threading, Turbo mode’s “overclocking” will make these applications run faster. For more information on how you’ll set up Turbo mode, read our sidebar below.
Turbo mode might sound like a feature left over from the TV series Knight Rider, but it’s more neat than cheesy. You already know that Core i7 CPUs closely monitor the power and thermals of the chip and use any leftover headroom to overclock the individual cores as needed. But just how does it work?
From what we’ve surmised by examining an early BIOS, you will be able to set each type of core scenario based on how far you want to overclock, given the load. For example, with applications that push one thread, you could set the BIOS to overclock, or rather, turbo that single core by perhaps three multipliers over stock. You would do the same for two-, three-, and four-core scenarios.
The good news is that you’ll get fine-grain control over the Turbo mode in the upcoming Core i7 CPUs.
The BIOS will also take into account the thermal rating, or TDP, of the cooling system you’re using. If you’re using, say, a heatsink rated for 150 TDP, the BIOS will overclock to higher levels than it would with a 130 TDP unit. You would manually set the heatsink’s rating in the BIOS, as there’s no way for the heatsink to communicate with the motherboard directly.
So all this CPU goodness and performance will drop right into that $450 LGA775 board you just bought, right? Of course not. Ung’s Law dictates that the minute you buy expensive hardware, something better will arrive that makes what you just bought obsolete.
Intel isn’t doing this just to piss people off (although a history of such behavior has had that result). Since Core i7 moves the memory controller directly into the CPU, Intel added a load of pins that go directly to the memory modules. The new standard bearer for performance boxes is the LGA1366 socket. It looks functionally similar to the LGA775, with the obvious addition of more pins. More pins also means a bigger socket, which means your fancy heatsink is also likely headed to the recycle bin. LGA1366 boards space the heatsink mounts just a tad bit wider, just enough to make your current heatsink incompatible. There’s a chance that some third-party heatsink makers will offer updated mounts to make your current heatsink work, but that’s not known yet.
What will be interesting to heatsink aficionados is Intel’s encouragement that vendors rate the heatsinks using a unified thermal rating that will be tied to the Turbo mode settings. For more information, see the Turbo mode sidebar below.
Intel is adopting more than just AMD’s integrated memory controller with its new Core i7 chips; it’s also adopting AMD’s abandoned Socket 940/754 two-socket philosophy. For the high end, the LGA1366 socket will offer tri-channel RAM and a high-performance QPI interface. For mainstream users, Intel will offer a dual-channel DDR3 design built around a new LGA1066 socket late next year. LGA1066 isn’t just about shedding one channel of DDR3 though; LGA1066-based CPUs will also bring direct-attach PCI Express to the table.
Instead of PCI Express running through the chipset, as it does with existing Core 2 and the new performance Core i7, PCI-E will reside on the die of LGA1066 CPUs. With the PCI-E in the CPU itself, Intel will reuse its fairly slow DMI interface to connect the CPU to a single-chip south bridge. The two chips Intel will introduce are the quad-core Lynnfield and the dual-core Havendale. Havendale CPUs will actually feature a newly designed graphics core inside the heat spreader that will talk to the CPU core via a high-speed QPI interface. Both chips will feature Hyper-Threading on all cores.
Many AMD users got a royal screwing when the company abandoned both Socket 940 and Socket 754 for a unified Socket 939; could Intel do something similar? We asked Intel point blank whether LGA1366 would eventually be abandoned for LGA1066; the company told us it fully intends to support both platforms.
| Core i7-965 Extreme Edition | Core i7-940 | Core i7-920 | |
|---|---|---|---|
| Clock Speed | 3.2GHz | 2.93GHz | 2.66GHz |
| L2 Cache | 1MB | 1MB | 1MB |
| L3 Cache | 8MB | 8MB | 8MB |
| Process | 45nm | 45nm | 45nm |
| Transistors | 731 million | 731 million | 731 million |
| QPI Speed | 6.4GT/s | 4.8GT/s | 4.8GT/s |
| Multiplier Lock | No | Yes | Yes |
| Default Multiplier | 24 | 22 | 20 |
| Volume Pricing | $999 | $562 | $284 |
Comments are closed on this article
jameyscott
May 20, 2009 at 3:12pm
why would i want the i7 it only goes up to 4 cores teh Xeon as demonstated in the top of the line mac pro desktop goes up 2 8 cores at 3.2 ghz some one please explain to me
JohnW
April 17, 2009 at 11:07pm
Please clear something up for me you stated in your article "AMD fans, of course, will point out that the fastest iteration of AMD’s
chip-to-chip conduit, dubbed HyperTransport 3.1, is twice as fast as
the current QPI." But I just read a rather lengthy explanation that seems to make that a false statement. I don't know how to shorten it so I'll just put it in here and let you tell me which is right. Sorry it's long but it says QPI is 78% faster than the fastest Hypertransport Technology.The first version of
the QuickPath Interconnect will work with a clock rate
of 3.2 GHz transferring two data per clock cycle (a technique called
DDR, Double Data Rate), making the bus to work as if it
was using a 6.4 GHz clock rate (Intel uses the GT/s unit – which means
giga transfers per second – to represent this). Since 16 bits are transmitted
per time, we have a maximum theoretical transfer rate
of 12.8 GB/s on each lane (6.4 GHz x 16 bits / 8). You will see some
people saying that the QuickPath Interconnect has a maximum theoretical
transfer rate of 25.6 GB/s because they simple multiply the transfer rate by
two to cover the two datapaths. We don’t agree with this methodology. In brief,
it is as if we said that a highway has a speed limit of 130 MPH just because
there is a speed limit of 65 MPH in each direction. It makes no sense.So compared to the
front side bus QuickPath Interconnect transmits fewer bits per clock cycle but
works at a far higher clock rate. Currently the fastest
front side bus available on Intel processors is of 1,600 MHz (actually
400 MHz transferring four data per clock cycle, so
QuickPath Interconnect works with a base clock eight times higher),
meaning a maximum theoretical transfer rate of 12.8 GB/s, the same as
QuickPath. QPI, however, offers 12.8 GB/s on each
direction, while a 1,600 MHz front side bus provides this bandwidth for both
read and write operations – and both cannot be executed at the same time on the
FSB, limitation not present on QPI. Also since the front side bus
transfers both memory and I/O requests, there are always more data being
transferred on this bus compared to QPI, which carries only I/O requests. So
QPI will work “less busy” and thus having more bandwidth available.QuickPath
Interconnect is also faster than HyperTransport. The maximum transfer rate of
HyperTransport technology
is 10.4 GB/s (which is already slower than QuickPath Interconnect), but current
Phenom processors use a lower transfer rate of 7.2 GB/s. So Intel Core i7 CPU will have an external bus 78% faster than the one
used on AMD Phenom processors. Other CPUs from AMD like Athlon (formerly known as Athlon 64)
and Athlon X2 (formerly known as Athlon 64 X2) use an even lower transfer rate,
4 GB/s – QPI
is 220% faster than that.
Thanks
John W
DragonFangNINE
December 28, 2009 at 3:23pm
HyperTransport 3.1 tops out at 51.2GB/s bidirectional
QPI tops out at half that with 25.6 GB/s bidirectional
And just for those who are still getting into the speed concept, when you are looking at bandwidth (GB/s is a measure of bandwidth) you are looking at a combination of speed plus datasize. To put it into the same analogy that the writer of the previous article iterated so poorly, if you have a highway that has a speedlimit of 60M/h and lets say that you are able to pass 20 cars per second, now add another couple of lanes to double the current width of your highway, with the same speedlimit, you are now passing 40 cars per second. This is the concept of bandwidth.
To wrap things up, HyperTransport is one wide ass highway with a mediocre speedlimit. QPI has a higher speedlimit, but a lot fewer lanes. Or maybe I missed something on QPI's specs and it has a slightly lower speedlimit AND fewer lanes, either way AMD's HyperTransport 3.1 still comes out top dog.
Now don't think that I'm an AMD fanboy because of all of this, I stand on the side of technology and as such I have to go with the i7 all the way!
m1keth3pwn3r
April 17, 2009 at 3:30pm
You AMD fanboys are whining about Intel using a design (IMC) AMD used in the Athlon, but what had AMD done for the year's before this? MOST OF THEIR F***ING PROCS WERE CARBON COPIES OF INTEL CHIPS! So why are you making a big fuss about this? Just live with it. Like Gordon said, it's not Intel's fault they pwned AMD with the Core 2 procs, so just live with it. Sure AMD is good for budget, but the ONLY reason they are so cheap is because they had to market them really cheap to move stock.
In closing, if you love AMD so much, by their sh*t and stop complaining!
JohnW
April 21, 2009 at 12:30pm
Obviously you TOTALLY misunderstood. I bought an I7 920 because it is faster and was just wanting clarification on what was said versus what I read. The only whining I hear is you.
hiremenow
January 03, 2009 at 9:35pm
You Sinorscat you said that you don't want Intel trash but if Intel trashes AMD with there last Gen-chips then where does that leave AMD well if there lucky the AMD Phenom II might be able to beat out a core 2 quad if AMD is lucky. so long story short intel is not trash, intel is the creme of the crop and AMD is the crap of the crop
Silentblaze513
December 11, 2008 at 11:35am
Yes, by looking at the benchmarks the core-i7 lacks in 3dmark, 3dmark vantage and FEAR. However the rest of the benchmarks show that the core-i7 is kick-ass. Maybe you should read them again!?!
ghot
December 07, 2008 at 1:57pm
...I dunno...the Seven Deadly Sins lol
and Silent: the benchmarks dont lie ^^
...and you are correct about the price...NOW it IS 1029.00 ....NOW :)
shadowskate
December 02, 2008 at 6:06am
is this the year of the 7 lol Windows 7 now this Core i7 what's next?
Butterfingers
Silentblaze513
December 01, 2008 at 5:35am
Cry-baby fanboy just won't let up.
btw intel core i7 EE 965 retails for $1000 not $1500; please try not to lie, it makes your argument look weak.
ghot
November 29, 2008 at 9:59am
3dMark06 DOES measure "overall" system performance, by that I mean CPU/GPU working together....if a $1500 dollar i7 cant outrun my very modest syatem in 3dMark06 OVERALL, as well as PCMark05 OVERALL and the various other OVERALL benchs...then there MUST be a problem somewhere. Not to mention the horrid 51fps in FEAR which is an old game now lol. Intel blamed that score on a USB bug....how that computes is beyond me.....wtf would a USB bug have to do with an fps score?
If you look closely at all the XXXXXX OVERALL benches the i7 do'nt cut the mustard...I trust Max PC's benching skills. Further the AMD scores came from a 1066 motherboard running 800mhz RAM...so the OVERALL benches should show even HIGHER scores for the i7, and they just don't.
Sure it'll encode faster...so what..this is the same thing Intel has been doing for years...building CPU's for a singular task at which the DO excel. I wanna see a Intel CPU that excels at the OVERALL benches before I plunk down ANY money for one.
I was running a much faster vid card, but still, I'm only running a AMD 5000 @ 3.2Ghz....so it balances out. The AMD CPU in my rig is definitely the bottleneck.
YES! I AM waiting for Shanghai before I consider a further upgrade. THEN we'll see what a comparable CPU does againt the i7. Comparing it to a Phenom is a joke....even comparing it to Intel's own QX9770 procs showed the same thing....more or less the same scores in all the OVERALL benchmarks.
i7 Phenom 9950 Intel QX9770 AMD 5000+ w/GTX280
PCMark Vantage Overall 6,705 5,299 5,961
3DMark06 overall 12,859 11,639 12,906 12,097
3DMark Vantage 7,516 7,301 7,588
WHERE'S THE BEEF...the $1500 Beef? My 5000+ and the GTX280 cost me $550 total ^^
...and btw 2-3 years ago AMD didn't "poop" they bytch slapped Intel ! Hopefully with the new oil money influx they will do it again with the Shanghai.
Chunkey
November 22, 2008 at 1:17pm
Everything current aside,
Let's say Intel copied AMD's top processor's architecture exactly. They then do their little tweaks and such to it and release it. If it performs this much better than AMD's original, what's the problem? Intel did it right. They're the one's who released the processor with the performance."Ohohoh it's AMD's technology it doesn't counttt they copieeddd" doesn't hold any ground. When AMD used such technology it pooped. When Intel uses a similar technology, it shines.
Sinorscat
November 18, 2008 at 9:05am
If mommy is buying your next computer for ya at crimbo then you better get whining now if you want this intel trash............. Why has no mentiond AM3? Anyone who buys there own equipment will wait for 2009 for AMD's next venture (i.e. the AM3). And as for me and any other conscientious users with there own bank account and trade accounts will wait for AMD's Rev G server platform to arrive in mid 09. If your computer will not last that long then maybe you should be spending a bit more time in school.
You whinney junior schoolies go and buy your 1000$ Intel chips and let me laugh at ya next year.
HaHAHAHAHAHAhahahHAhAhahHhhaaaaa
Better still get yourself a console.... You Idiots
Mommy Mommy I want the new Intel chip for cristmas pleease mommy pleeeese and dont forget my Nike Trainers
Keep up the good work AMD
Silentblaze513
November 20, 2008 at 4:29am
You guys have based your argument on how well AMD does in 3dmark compared to Intel. 3dmark doesn’t measure jack shit when it comes to modeling, animation, texturing, and so on. I agree that if what you do is "play games" then buying this expensive contraption is just dumb. Which is why instead of spending $800-$2500 (still way too pricey for games) I only spend $400 on a perfectly good Xbox 360 and spend the rest on a decent HDTV. They're so cheap it doesn’t matter if they breakdown, just buy the two year replacement warranty and you're good to go. btw I've been in CG for 6 years; don't call me a "junior schoolie"
ghot
November 17, 2008 at 6:19am
Yes I'm an AMD fan, however that doesn't make my previous post wrong or whinning......
Here's MY system components:
Motherboard:
ASUS M2N32 SLI Deluxe, Wireless EditionProcessor:
AMD Athlon 64 X2 5000+ (Black Edition) Brisbane 2.6GHz Dual-Core (Overclocked to 3.2Ghz)CPU Fan/Heatsink:
ZALMAN CNPS9500AT 2 Ball CPU Cooling Fan/HeatsinkMemory:
CORSAIR Dominator 2GB (2 x 1GB) 240-Pin DDR2 1066 (PC2 8500) Dual ChannelVideo Card:
EVGA 01G-P3-1280-AR GeForce GTX 280 1GB 512-bit GDDR3 PCI Express 2.0Hard Drive # 1:
WD 36GB 10,000rpm Raptor SATAHard Drive # 2:
Seagate 80GB 7200rpm SATAOptical Drive # 1:
Lite-On LTR-52246S CD/RWOptical Drive # 2:
Lite-On LH-18A1P CD/DVD BurnerPower Supply:
PC Power & Cooling Silencer 750 Quad (Black) EPS12V 750W Continuous @ 40°C (825W Peak) Power SupplyCase:
Full Tower (Gerneric) 5x 80mm case fans (2 front intake, 2 rear exhaust, 1 sisde exhaust)Sound Card:
noneMonitor:
ViewSonic G90FB Black 19" CRT Monitor
and dude I get 12095 on 3DMark 06 and the almighty i7 gets: 12859 on same test (overall score)
granted I have GTX280, BUT, my CPU cost $89 and is overclocked to 3.2Ghz same as the i7 at stock. To me ENTIRE system benches are the only ones that matter.....and even with an 8800 vid card, 12589 for the i7.....bites! Note: neither my memory or vid card is overclocked. So if you want to rush out and spend $1000 on an i7, feel free. Meanwhile I'll sit here laughing at you with my $1200 comp :)
Sure the i7 runs office, audi conversion and video conversion apps like all get out......and even SOME games....(ooops on the FEAR score) but there is stand alone equipment that does the same job far faster and better than any comp ever could. I agree the i7 is a nice CPU...but all in all it ain't all that! Its just an AMD design made in an INTEL fab. Drop AMD 10 billion dollars or so and watch the repeat of the AMD stomps Intel debacle of a few years ago.
Being a fan of a company doesn't mean I'm wrong lol......AMD makes the best CPU's (architecture wise) nVidia makes the best chipsets...those are facts son, despite what you think :)
Oh, almost forgot, I'm running the GTX280 in a PCI-E 1.0 slot too, even though its a 2.0 card, so you can add that into the 3DMark 06 scores as well.
Silentblaze513
November 17, 2008 at 2:11pm
I forgot to mention that I don't play games, I make them. If AMD can make something for the workstation class that can beat the i7 I'll be happy to look at it; but for now phenom is nothing but a budget proc.
dazza145
November 15, 2008 at 12:03am
yes with the new intel x58 motherboards it supports both nvidia SLI and ATI crossfire
dazza145
November 13, 2008 at 7:33pm
i think if this cpu can perform better than the core 2 extreme it is good value considering it is a fraction of the price
Stockislander
November 09, 2008 at 10:16pm
Looks like Windows 7/ Core i7 will be a smokin' platform around the time my XP/ Q6600 build is driving me crazY... I get to skip Vista AND Penryn!
pcfxer
November 08, 2008 at 8:30am
Of course penryn is great for gaming. I still game on my Athlon64 X2 5000+ BE OC'd to 3.04GHz and it does just fine. Graphics cards are the key component for 99% of games these days anyway.
ghot
November 07, 2008 at 8:34pm
Dear Max PC, you have insulted us with your i7-965 vs. Phenom X4 9950 benchmarks.
1. You used DDR2 800 Patriot memory, when the AM2+ board takes 1066.
2. Further you used Patriot instead of Corsair for the Phenom
3. ...and you used Qimonda rather than Corsiar for the i7
4. then you told a falsehood:
You said: that the resason the i7 did so poorly in FEAR was due to a USB bug in the i7....I'm no....Einstein
but even I can't begin to imagine how a USB bug in the i7 could affect only one out of four game tests
please EXPLAIN that in detail or retract it.
NOW...assuming you had run a FAIR bechmark, which you didn't, there are still a few benchmark scores that you simply "glossed over" without explanation.
The....3DMark 06 overall, PCMark Vantage overall, 3DMark Vantage overall, scores do not in MY opinion justify purchasing a $1000 i7 over a $185Phenom X4...at least without some explantion.
While I realize that the i7 IS a very good chip and that Mac PC "tries" to remain neutral in these tests, I do feel that the i7 is not "quite" the Phenom X4 thrasher you make it out to be. The benchmarks I mentioned above, test how a CPU functions IN a complete system, and since I can't just hook my monitor, mouse and keyboard directly to an i7.....I have to consider the over all system scores. Any of the benchmarks related to memory are totally skewed and therefore not worth consideration at this time. Please use the proper memory all from the same company and all the max stock speed that the CPU/mobo will handle.
That USB bug excuse from Intel is simply ridiculous also. What did you use to play FEAR with a USB DVD player? Even the rest of the scores are at least partially suspect due to the unfair memory choices.
On top of ALL that, you toally neglected the price /performance ratio, not to mention pitting a 65mm AMD against a 45mm i7...(I do realize that at this time there was no other option..so at least in this one area...you may be forgiven)....however...this is NOT the kind of quailty review that I have come to expect from Max PC.....
I would expect, that when you get the chance you will attempt to provide your readers with a more balanced review, and just this once, can be forgiven for the obvious bias. I'm SURE that your memory choice for this review were driven by the lack of "suitable" memory choices, like: the MAX PC lab just didnt have any Corsair 1066 memory laying around :/
lastly, since most of the world is still using Windows XP...I fail to understand (time contraints) why XP benchs were not included. Also I don't understand why you only mentioned which chipset you chose to pair with each CPU, and not which motherboard manufacturer...except of course for the i7 which you paired with a fully named motherboard, specifically designed for the i7.
All in all...... Luuucy, you got some splainin' to do!
P.S. Don't worry...even after this gross miscarriage of benchmarking...I still lub you :)
middiefrosh
August 22, 2009 at 4:42pm
Fanboy. You're just sad that Intel has made something AMD can't compete with and go on with baseless accusations against Intel.
You're gonna have to live with it: Intel is making great hardware, and AMD isn't keeping up.
Silentblaze513
November 16, 2008 at 10:30am
Just shut up and wait for AMD to come out with something that can compete; loser. This is "Maximum PC" there's no room for budget cpus here.
Naw-yi
November 07, 2008 at 5:47am
anyone notice they are using only 800mhz drr2 memory for the phenom and not 1066?
ghot
November 06, 2008 at 1:19am
Funny they never used it.....I guess you could say they didnt need to ....to stay ahead in the CPU wars....but if you recall they got creamed by AMD a few years back and STILL didnt use it. I don't know about you, but after 30 years of watching the CPU wars....I think Intel is full of it, and a bunch of thieves.
Even a few well respected mags have commented on this exact same fact :)
Intel, due to their many fabs and 18 digit bank accounts, really should be able to "come up with a NEW idea" at least once in a while. I can't even begin to count the numerous suits alledging and proving that Intel does just this. They should re-name Intel to: Monkey see, monkey do!
From a bottomline standpoint...Intel makes NO mistakes. But from an (albiet old fashioned) honor standpoint, I've met hookers with more scruples.
mpcrsc562
November 04, 2008 at 12:02pm
How the hell do you take credit for something you never released?
"The company’s response: One: An IMC isn’t an AMD invention and, in
fact, Intel had both an IMC and graphics core planned for its
never-released Timna CPU years before the Athlon 64."Damn-- I way behind! There's all kind of stuff I could have said I started/created and never released but I just kept my mouth shut and didn't say anything. Damn! I guess it's too late to say that I created the internet, huh?
Spider-Mom
November 04, 2008 at 3:34pm
because they didnt steel the idea from AMD. What the hell does it matter if it was ever released. And besides, IBM did it before either of these companies. Whos idea it was is compleatly mute at this point. They didnt keep their mouth shut about Timna. God you make it sound like they just made it up now and it never actually exisited. Intel also had 64bit destop CPU before AMD but they never went to market with it because it was nothing but a waste of money. That goes for what AMD did also. Intel could have put an IMC on their chip along time ago if they wanted but it wouldnt have made a big differance for their procs. Did you even read this article?
mpcrsc562
November 05, 2008 at 1:00pm
whoa! i don't care whose invention it is or it isn't.
your quote: "God you make it sound like they just made it up now and it never actually exisited."
to me, it didn't exist. anything that is PLANNED but never released is vaporware. besides, the text reads: "Intel had both an IMC and graphics core PLANNED [emphasis mine] for its never-released Timna CPU years before the Athlon 64"
to reiterate, i don't care whose invention it is or isn't. intel stated, as the article reads, that they had those things planned for the never released cpu. 1+1=2. One: the items were planned + One: the cpu was never released = never existed. yeah, i'm sure it exists written down on some scroll in the vaults or dungeons of intel, but for all practical purposes, it never existed. cooleo.
you must be an intel employee 'casue it seems it hit a nerve.
srynznfyra
December 07, 2008 at 2:46am
Saying something is 'planned' is not the same as saying it exists. This is how these companies use clever language, which fools some people but doesn't fool others. Generally the more gullible types, or just plain fanboys like you, believe this tosh. Fine, intel had that idea, but they never even said that they actually made it into an actual chip.
AMD and intel are both great. AMD's for one category, ie performance without a huge price, and Intel's for people who need as much performance as they can possibly get, without a budget. I'm building a PC right now, and I've chosen AMD for the mere reason that I found a good cheap amd board, and the X2 5600 2.8GHz isn't expensive. Now, Spider-Mom, can you please give me a proper argument as to why Intel is so much better than AMD in your eyes.
pablok2
November 04, 2008 at 10:28am
well, with the stolen ideas from AMD we can conclude that intel is slacking on innovation, but the shortest distance between two points is a line
ghot
November 03, 2008 at 9:48pm
Gee Intel what are you going to STEAL next? Have you had an orginal thought in the last decade?????
jvc08
November 03, 2008 at 10:47am
i am buying a q9650 proc. for my system. i dont think those scores are that impressive...
digital demon
November 03, 2008 at 9:51am
"You guys should be fans of whoever's giving you your money's worth or whoever's winning the race."
Exactly...to me, it's price/performance over all.
As for the article, it's about what I expected...i7 vaults Intel into an entirely new stratosphere of performance. That gaming bug will get fixed before they are released. I doubt I'll be able to get one any time soon...but I will ASAP.
Skiplives
November 03, 2008 at 8:44am
My biggest concern is the longevity of the pin-out, but it appears that the high end chips will all have this pin-out, and the cheaper, two channel chips and motherboards will have the smaller pin-out.
I guess this is expected, as the i7 is really targetted at the server market and having more memory bandwidth is important there. The budget desktop market can get by with two channel, and power-users are never going to turn down the option of "more".
The only down-side I see, is that I'm not likely to get all the parts I need for this weedend. And cost of course, but that is a given.
_________________
That's my story, and I'm sticking to it.
Catalina588
November 03, 2008 at 10:05am
The pin-out will be around for a couple of years, which is as long as anybody can expect. Next year, it's likely the same socket will house a) an 8-core CPU and b) a CPU-GPU marriage with Larrabee.
Keith E. Whisman
November 03, 2008 at 8:18am
So should I upgrade from my Penryn E8400 Dual core now or wait until the next generation after Nehalem? Is Penryn still going to be fast enough for gaming for a while? I see the numbers but does it really matter for gaming at high resolutions running in SLI with 4gigs of ram? I think I'm going to wait another year but I really want to upgrade but my system is still pretty new.. God Why me......
knexkid
November 03, 2008 at 6:44am
Thank you so much for all these benchmarks! Now can you answer when I can buy this stuff? Lol. I am really really excited to build my new computer soon (around Christmas time...like you answered on the podcast). Also, why on earth did FEAR totally tank on the i7 Extreme? Thanks Max PC and Gordon for doing all this kick ass benchmarking!
Spider-Mom
November 03, 2008 at 3:58am
Am I the only person who noticed that Q4 had wrose performance in dual channel mode compared to single? All in all there is somthing very fishy with the gaming results. Truth be told, if games arnt running allot faster, whats the big deal about memory bandwith? If its not running games faster does that mean its not going to run other 3d apps faster either? Who cares what SiS Sandra says, I dont play that game very often. I was sort of hoping for something better I guess. And what about the future of the intigrated PCI controller? Is that drastically going to change gaming performance? Who knows but it sounds like it might. That might also be enought to prevent me from buying in now. How come the lower end chip is getting this faetur but not the ones with the higher pin count? What since does that make? If its an artifical way of getting more people to buy the other versions then I would be a little angery. Furthermore, if there isnt good overclocking on these chip that already have lousy gaming benafits, why would I upgrade to this? Being forced to buy the 1000$ chip to get respectable over clocking is a total joke, and Im not laughing. Rite now people are getting almost a gigahurt and a half of an OC from 180$ quads on air. There doesnt seem to be any way that a sub 3.0GHz i7 is ever going to beat a 4GHz Core. There is still alot more benchmarking that needs to be done. Im a heavy user of PS3 and soon 4. But 10 seconds off of 2min on a script ill never use is not even remotly as important to me as 10 or 20 frames ever second in a game. I wouldnt call it a turd in gold paint but all in all, it seems to be a little underwhelming given the way it was described in the begining of the article. Its just stupid really. If the Exteme chips prove that these cores are capable of hitting 4GHz but the mortal versions dont just because of the multiplier, I and a hole lot of other people are going to be VERY pissed off. Good job on the new tech Intel. I sure hope it proves to be worth it.
Gailim
November 03, 2008 at 1:13am
interesting, your saying the overspeed protection is simply a locked multiplier. Toms is saying that it's something all together different. they say that the overspeed protection limits the TDP of the chip. if a chip goes over the prescribed wattage the chip resets to stock speed. its unrelated to the locked multiplier. in effect this means that large overclocks on i7 are impossible without the EE version (which lets users adjust the "protection" wattage)
one of you is wrong and it could certainly be Toms, in fact i hope it is, cause otherwise it would suck
here is thier explanation of it http://www.tomshardware.com/reviews/Intel-Core-i7-Nehalem,2057-7.html
Catalina588
November 03, 2008 at 10:35am
http://boinc.bakerlab.org/rosetta/show_host_detail.php?hostid=929192
Currently a 965 is at 2,260 RAC at rosetta@home and climbing. As you know, it takes a month or more to reach maximum RAC. A Skulltrail maxes out over 5,200. This is very much a progress report. I expect this processor to get into the Rosetta Top 10 by Christmas.
Rosetta reports internal benchmark: 3296 Floating point million ops/second and 8945.9 integer million ops/sec.
I haven't done Folding@Home on this proc as I'm an FAH GPU fan.
Overall, the Core i7 model 965 is exactly as reported in the various benchmark reviews out today. It absolutely screams at multi-tasking. Roughly the same performance as a Skulltrail (and sometimes more) for thousands $$$ less.
Hope this helps.
- Pete
knipfty
November 03, 2008 at 10:17am
I was thinking the same thing. You have 8 threads that can be used...
billysundays
November 02, 2008 at 11:30pm
- On page 4, in the first paragraph - "...they can participate in the latest technology trends without feeling like they’re getting a great deal. That’s because Intel’s new 2.66GHz Core i7-920 is a great deal." I think you meant "while feeling like they’re getting a great deal."
- Also, page 4,the second paragraph - "the slightly clock speed advantage of the Q9550" should be "the slightly faster clock speed advantage of the Q9550". I guess I noticed because this was when I really started to pay attention. This is a great deal.
- Third paragraph - "The Core i7,l however, will..."
ha, ha. ;-)
