Intel: Core i7 to Be Up to 52% Faster Compared to Core 2 Quad


Recommended Posts

So how do you interpret the "52% increase in CPU processing power in 3D gaming", considering it's a constantly shifting balance between the CPU and GPU under different environments, resolutions, and effects settings, for different games and game levels? It doesn't make any sense at all in that case :D

It actually makes much more sense if it means playing 3D games in software rendering mode, like those Red Mars CPU benchmarks in 3DMark 06 :laugh:

well the CPU is still working. A benchmark of the game may not be accurate but you can be sure its something Intel looks into when designing the chips. You'd look at the efficiency and time gaming related calculations take to perform. So yeah, I'm not proposing a single benchmark will ultimatly show these gains at all but it certainly doesn't mean the result should be indicating that Intel predicts a 50% overall fps figure in a game.

Yes, GPU, resolution and all that changes too but it'd be the raw calculations regarding games I'm sure this is talking about. You'd need to use a synthetic benchmark to test it anyway likely which everyone knows isn't always a good guide to actual in game gains.

edit: Simply put, if people think its possible that video encoding related calculations are 40% more effiecient why is it unrealistic that calculations related to gaming operations cant be in the same ball park? As I said above, I believe 52% is purely about processing power and not the real world performance of the app overall so it makes sense if encoding can get a huge gain (which some people said isnt unrealistic) then the games calculations too can benefit. It also goes without saying that with larabree in development (or whatever their GPU solution is named atm), then Intel will be looking very closely at ways to optimise anything related to gaming.

Edited by Smigit
When I see something like that I interpret it as 52% CPU processing power, not as a 52% overall performance of FPS. Obviously the overall game won't be boosted by 52%, that goes without saying given most are GPU not CPU dependent. I personally think some people are misinterpreting that 52% figure as meaning FPS.

Even 52 is likely a tall order in relation to pure CPU grunt, but I would expect a fairly considerable improvement.

It specifically says 3D gaming, however. While it may not result in a 52% increase in FPS, it's going to be an increase. Previews of the Nehalem said it's nothing like that at all.

yeah, everybody forget how was Core2Duo vs P4 and latest (in that time) AMD when some games got big increase on fps

remember for ex FEAR that got almost 60fps more? probably will not happen something like that now, they are probably referring to about CPU overload in different directions, will make probably gain many fps but not anything like P4->Core2Duo

but... anything is possible, depends on the optimizations

the new micro-architecture in its first implementation provides roughly 52% more performance at the same clock-speed compared to currently used Core 2 micro-architecture.

Clock speed isn't everything. The technology that makes up the CPU is everything.

I'm currently using an AMD user but I'll probably go back to Intel (Had a Celeron D before) once this is released. Curious as to what the different models are. Is the cheapest going to be 3.20GHz? Or is that the highest?

For Intel to Use a Integrated memory controller (like AMD) that supports DDR3 with three channels of memory. so 6 Slots can be used, Hyper-threading each cores can process two threads so 4Core looks like 8 core on a single CPU. Gaming , PhotoShop and Video Editing will be better on a Intel Core i7 system.

what i am waiting for is Nehalem-EX Server Version Quad channel FB-DIMM2 Memory Controller SkullTrail II will be my next upgrade.

Clock speed isn't everything. The technology that makes up the CPU is everything.

I'm currently using an AMD user but I'll probably go back to Intel (Had a Celeron D before) once this is released. Curious as to what the different models are. Is the cheapest going to be 3.20GHz? Or is that the highest?

lol no , 3.2GHZ is core i7 Extreme edition . i hope if it really was like what you said :woot:

but damn core i7 EE would cost ~14xx$

core i7 945 2.9GHZ ~7xx$

core i7 920 2.6GHZ ~35x$

acourding to this

For Intel to Use a Integrated memory controller (like AMD) that supports DDR3 with three channels of memory. so 6 Slots can be used, Hyper-threading each cores can process two threads so 4Core looks like 8 core on a single CPU. Gaming , PhotoShop and Video Editing will be better on a Intel Core i7 system.

what i am waiting for is Nehalem-EX Server Version Quad channel FB-DIMM2 Memory Controller SkullTrail II will be my next upgrade.

why would you need core i7 Multi-socket(Quad socket/processor ,octo socket/processor ) :| , anyway skulltrail is DP(dual processor ) platform

lol no , 3.2GHZ is core i7 Extreme edition . i hope if it really was like what you said :woot:

but damn core i7 EE would cost ~14xx$

core i7 945 2.9GHZ ~7xx$

core i7 920 2.6GHZ ~35x$

Holy crap. Wayy to expensive. I'll stick to AMD for now... :(

So I've been hearing about these types of speed increases for awhile now, but what I hadn't heard anything about was price. If these things are going to cost a grand, then I sure am happy I bought my computer when I did, because I'll be sticking with my processor for quite awhile now. It isn't the sheer price that phases me to the point where I can say that... it's the fact that, on top of that, I'd be needing to buy a new motherboard, DDR3 memory, and even a new heatsink for the processor, since the socket size switch makes all the stuff I just bought useless.

Don't get me wrong, I am going to upgrade eventually, if maybe only because I love the chance at working on a new build. But I was always thinking my build would be an immediate thing. Now I know I'll at least be waiting for USB 3.0.

lol no , 3.2GHZ is core i7 Extreme edition . i hope if it really was like what you said :woot:

but damn core i7 EE would cost ~14xx$

core i7 945 2.9GHZ ~7xx$

core i7 920 2.6GHZ ~35x$

acourding to this

So I've been hearing about these types of speed increases for awhile now, but what I hadn't heard anything about was price. If these things are going to cost a grand, then I sure am happy I bought my computer when I did, because I'll be sticking with my processor for quite awhile now. It isn't the sheer price that phases me to the point where I can say that... it's the fact that, on top of that, I'd be needing to buy a new motherboard, DDR3 memory, and even a new heatsink for the processor, since the socket size switch makes all the stuff I just bought useless.

Don't get me wrong, I am going to upgrade eventually, if maybe only because I love the chance at working on a new build. But I was always thinking my build would be an immediate thing. Now I know I'll at least be waiting for USB 3.0.

need i to say more ..

According to this, the Intel Core i7-940 (2.93GHz) and Intel Core i7-920 (2.66GHz) are nearly the same, except in clock speed. The i7-940 is only 0.27GHz faster and it's $353 more expensive. That doesn't make sense to me.

Heck, I'll be happy with half of that in improvement, honestly. I'll believe these numbers when I see some real tests done, but I'm already preparing to rebuild my whole rig about a year from now, complete with a mid-range i7 Quad Core, a new mobo, and at least 4GBs of DDR3 RAM. I'll likely be looking at a new video card by then too. Granted, this will probably be delayed a bit by buying Windows 7 next year, but that's ok. My rig will remain fairly solid for at least another 18 months. :)

According to this, the Intel Core i7-940 (2.93GHz) and Intel Core i7-920 (2.66GHz) are nearly the same, except in clock speed. The i7-940 is only 0.27GHz faster and it's $353 more expensive. That doesn't make sense to me.

Hence why I'll get the cheaper one and overclock the heck out of it. :D I managed to overclock my Core 2 Duo E6750 from 2.66GHz to 3.6GHz on air. I plan to run that i7 as hard as I can. ;)

well the CPU is still working. A benchmark of the game may not be accurate but you can be sure its something Intel looks into when designing the chips. You'd look at the efficiency and time gaming related calculations take to perform. So yeah, I'm not proposing a single benchmark will ultimatly show these gains at all but it certainly doesn't mean the result should be indicating that Intel predicts a 50% overall fps figure in a game.

Yes, GPU, resolution and all that changes too but it'd be the raw calculations regarding games I'm sure this is talking about. You'd need to use a synthetic benchmark to test it anyway likely which everyone knows isn't always a good guide to actual in game gains.

heh, you are not making any sense here. There's no way to measure this so-called "CPU processing power in 3D gaming" of yours. What's the "CPU processing power in 3D gaming"? is it AI, physics, data loading, data decoding, or what? That basically covers everything out there, and varies greatly from game to game. In one 3D game it may have complicated AI but simple physics, in another 3D game it may have complicated physics but simple AI, and the "CPU processing power in 3D gaming" are about completely different tasks, favoring completely different CPU architectures. The "raw calculations regarding games" is completely undetermined, so talking about a certain percentage of "performance boost" in "raw calculations regarding games" is completely non-sense. :D

edit: Simply put, if people think its possible that video encoding related calculations are 40% more effiecient why is it unrealistic that calculations related to gaming operations cant be in the same ball park? As I said above, I believe 52% is purely about processing power and not the real world performance of the app overall so it makes sense if encoding can get a huge gain (which some people said isnt unrealistic) then the games calculations too can benefit. It also goes without saying that with larabree in development (or whatever their GPU solution is named atm), then Intel will be looking very closely at ways to optimise anything related to gaming.

Because video encoding is 100% done on the CPU, so we can measure the 40% increase in performance for sure. On the other hand, there's no way to measure the "calculations related to gaming operations" since there's no such fixed set of "calculations related to gaming operations", thus it's unrealistic to talk about "performance boost" percentages regarding "calculations related to gaming operations", and it can't be determined at all. So by your interpretation of that line, Intel must be pulling some random numbers out of their asses :laugh:

Yes it isn't unrealistic for encoding to gain 40%, and it isn't unrealistic for gaming to gain some performance, but it's completely unrealistic and ridiculous to pull out a 52% figure out there, no matter how you look at it. It either can't have that much of increase (52% fps increase with 3D accelerated graphics), or it's absolutely impossible to measure the increase in any determinable manner (your so-called interpreted 52% boost in "calculations related to gaming operations"), or it's just mostly useless (52% fps increase in software rendering mode) :D

And Larrabee is about 3D graphics, so even if Larrabee can have great improvement over nVidia and ATi graphics cards, it has absolutely zero relation to the Core i7 CPU's performance improvement over C2Q's in 3D games.

According to this, the Intel Core i7-940 (2.93GHz) and Intel Core i7-920 (2.66GHz) are nearly the same, except in clock speed. The i7-940 is only 0.27GHz faster and it's $353 more expensive. That doesn't make sense to me.

yea but there are always premium for next to the best cpu

ex.

330$ 570$

Q9550 Vs Q9650 ( next to QX9700)

2.8 3GHZ

on the old days

266 Vs 560$

Q6600 Vs Q6700 (next to QX6850)

2.4 GHZ 2.6GHZ

This topic is now closed to further replies.
  • Recently Browsing   0 members

    • No registered users viewing this page.
  • Posts

    • IBM reveals sub-1nm chip technology, production expected in another 5 years by Pradeep Viswanathan TSMC is now leading the chip manufacturing industry with its 2nm-class process node called N2. Samsung Foundry also has a 2nm-class process node called SF2. TSMC says N2 entered volume production in Q4 2025. Samsung says SF2 started mass production in 2025. Today, IBM announced the world’s first sub-1-nanometer chip technology, marking another major semiconductor research milestone. The new technology is based on a 0.7nm, or 7-angstrom, node and uses a new transistor architecture called “nanostack.” The new design vertically stacks and staggers nanosheet-based transistors so that more components can fit into the same chip area while also improving performance and power efficiency. IBM claims that this new sub-1nm chip can pack nearly 100 billion transistors onto a chip the size of a fingernail. This offers almost twice the density, up to 50 percent higher performance, or 70 percent better energy efficiency when compared to IBM's 2nm node design announced back in 2021. Also, IBM mentioned that this new architecture can deliver 40 percent SRAM scaling. It is important to consider that this announcement from IBM is a research milestone rather than a near-term process node launch. Back in 2021, IBM unveiled the world’s first 2nm chip design, claiming 50 billion transistors on a fingernail-sized chip and major performance and efficiency gains. Five years later, IBM’s 2nm technology has still not entered mainstream commercial production. That is because IBM is no longer a major commercial chip manufacturer. It sold its chip manufacturing business to GlobalFoundries years ago and has since then focused only on semiconductor research, IP development, and partnerships. To productize its 2-nm chip technology, IBM partnered with Japan’s Rapidus, but it has not resulted in anything shipping at scale. IBM says that its new sub-1nm technology can reach production as early as within the next five years. If that happens, it will likely depend on manufacturing partners, advanced EUV tooling, and years of yield improvements.
    • It's funny when thieves accuse other thieves of stealing. Ai companies just blatantly siphoned all the knowledge of the internet without consent and are now selling it with their service... so excuse me if I find this a bit ironic.
  • Recent Achievements

    • Week One Done
      Meta Plast earned a badge
      Week One Done
    • First Post
      kinowa earned a badge
      First Post
    • Rookie
      krychek57 went up a rank
      Rookie
    • Grand Master
      Jaybonaut went up a rank
      Grand Master
    • One Year In
      Philsl earned a badge
      One Year In
  • Popular Contributors

    1. 1
      +primortal
      454
    2. 2
      +Edouard
      170
    3. 3
      PsYcHoKiLLa
      135
    4. 4
      Michael Scrip
      78
    5. 5
      Xenon
      77
  • Tell a friend

    Love Neowin? Tell a friend!