Comments Locked

70 Comments

Back to Article

  • Teloy - Friday, March 26, 2010 - link

    "It's GPU still only runs at 733MHz though"... "It's" is not quite right... Take care.
  • 8steve8 - Thursday, March 25, 2010 - link

    why was the G45 omitted on pg2 in the graph of power consumption under load with integrated graphics?

    I was keen to see how much more efficient HD graphics were than g45.

    -stephen
  • bpdski - Thursday, March 25, 2010 - link

    It would have been nice to see the benchmarks run with the overclocked G6950 also.

    - Brian
  • Taft12 - Thursday, March 25, 2010 - link

    I have a hard time comprehending what Intel/AMD's TDP ratings mean in light of the "Load Power Consumption" graph.

    How is it that Intel CPUs with higher TDP ratings consume MUCH LESS power at load than AMD CPUs with lower TDP ratings. Just looks at the results -- all of the Intel core i3/5 CPUs are 73W TDP but the Athlon X2 255 is rated at 65W yet consumes 20 more watts at load. Is the 790FX motherboard that inefficient? WTF???

    Lower idle consumption for Intel I understand due to the smaller process and excellent design, but do the TDP ratings truly mean nothing? This is a disastrous result for AMD.
  • strikeback03 - Friday, March 26, 2010 - link

    Both companies rate their TDP differently, and in either case it is not designed to be a measure of power consumption.
  • Nickel020 - Thursday, March 25, 2010 - link

    It would be nice if you could include the 661 in the power consumption charts. Does its higher TDP actually lead to higehr power consumption?
  • Sunburn74 - Thursday, March 25, 2010 - link

    If you're gonna talk about the value of a 4.4 ghz overclocked processor, you gotta include it the benchmarks. Duh!
  • crochat - Thursday, March 25, 2010 - link

    Why the hell is it necessary to always put discrete graphics card in systems with integrated graphics and do power consumption tests with it? Is the benchmark used for power independent from the graphics card?

    I understand that it is much simpler to measure watts only, but what is important is the resulting task energy consumption, taking into account the efficiency of the processor..
  • strikeback03 - Friday, March 26, 2010 - link

    Because some of the tested systems don't have integrated graphics. So for the application performance comparisons shown to be valid, the discrete GPU has to be kept in there. Wouldn't want someone thinking they could get 69.1 FPS in Crysis Warhead with the power consumption of only the integrated graphics.
  • Taft12 - Thursday, March 25, 2010 - link

    It's necessary to save many hours of work the testers could spend on more articles. What counts is the delta in power consumption between CPUs/platforms at idle and load.

    I'm an AMD fan, but the bottom line is Intel systems are more power efficient, period.
  • know of fence - Friday, April 9, 2010 - link

    Unlike to the apologists above, it should be obvious to most readers that testing power consumption with discrete graphics further dilutes results, especially regarding power savings.

    Even if Anandtech absolutely cannot do those tests (because of bench), at least a mention of the EVGA Graphics card's idle power consumption (~ 25W ?) in the description would be really helpful. So readers who care about absolute watt power could then subtract it from benched measurements, to get a meaningful power consumption estimate for a non-gaming- PC.
  • ReaM - Thursday, March 25, 2010 - link

    Qimonda DDR3-1066 4 x 1GB (7-7-7-20)
    Corsair DDR3-1333 4 x 1GB (7-7-7-20)
    Patriot Viper DDR3-1333 2 x 2GB (7-7-7-20)


    Which one is used for O'Clocking?

    I need a good OC ram! :P I dont know which company


    Thank you!
  • Calin - Thursday, March 25, 2010 - link

    Try to post in the forums, you might be luckier
  • ReaM - Thursday, March 25, 2010 - link

    yeah, but these were used here in that test setup
  • ekul - Thursday, March 25, 2010 - link

    I don't think anyone is going to buy this chip at their local computer shop. Even for a cheap HTPC you'd be much better off to get a full clarkdale for the hyperthreading and turbo mode.

    This chip was built so OEMs like Dell and HP can keep the base price of their H55-based systems low to entice buyers. It's also as much CPU as any CSR or assistant is going to need in the corporate world.
  • arnd - Thursday, March 25, 2010 - link

    It appears that there are two more Clarkdale processors, the Celeron G1101 (with just 2 MB L3 cache) and the Xeon L3406 (with 30 W TDP but graphics disabled).
  • xpax - Thursday, March 25, 2010 - link

    Good job, Anand, as usual.

    I don't keep up on the hardware front as much as I used to, and having just built a new i5-750 system I was concerned for a moment as I hadn't heard about these new chips before doing my build.

    After seeing the numbers though, I'm 100% sure I made the right choice.
  • iwodo - Wednesday, March 24, 2010 - link

    I want SandyBridge, i dont know why i never liked this generation architecture. I still have the perception ( no matter how much benchmark i read ) that it simple doesn't offer any performance improvement over C2D or those previous cheap Core2 Quad.

    Spending $100+ ( or $200+ since you need to upgrade your MB ) simple doesn't make sense. I would rather buy a Fermi / 58xx or Sandforce Based SSD.
  • kaleun - Wednesday, March 24, 2010 - link

    As a C2D owner I also don't see much reason to upgrade to an i3. but if I needed more performance, the i5/i7 would be worthwhile. and many people might upgrade from something older than C2D. If I started a PC from scratch, the i3 for $ 120 is really really good compared to everything else in that price range if one considers power consumption and overclocking.

    Obviously, someone who buys an i3/i5/i7 today won't see much reason to upgrade to Sandy Bridge either. But starting from an older platform (even C2Q), Sandy Bridge will be worthwhile. I almost think, unless you are power user, one always is best off skipping every other CPU generation.

    the thing I wonder, for someone who builds a new platform today, why would anyone buy a new C2D is beyond me. My E7400 still costs $ 120 like over a year ago when I bought it. No way I'd buy that over an i3.
  • Calin - Thursday, March 25, 2010 - link

    You could buy an C2D for common installed base (with similar mainboards as other PCs you have installed). Or you might buy one for the perfect last-generation board you buy for a new computer.
    There might be other reasons, but I don't have one of them right away
  • larson0699 - Thursday, March 25, 2010 - link

    @GP(iwodo)-- I like the architecture just fine, but (in the case of i3/i5) to hand the memory controller over to the IGP (when, in Nehalem, it was on-die to begin with) is a shot in the foot. What gives? A lot of us use these chips with discrete GPUs, and even the ones who don't aren't seeing the potential of the architecture because of this stupidity in design--simpler or not (than going monolithic out of the gate). It's a step backward, but even so, still marginally superior to Conroe/Penryn in performance alone. Performance per Watt is definitely more of a win here for those like myself who care how productively any given amount of energy was used.

    @P(kaleun)-- Sandy Bridge doesn't look like much of an upgrade to i7 anyway. The roadmap suggests that the performance CPUs will remain independent of GPUs as they logically should. I don't know anyone (including "power users") who upgrades at every tick and tock. And perhaps it hadn't occurred to you that LGA775 is and will be an upgrade path for those on a budget tighter than LGA1156 can entertain *until* the day it does. We're really scraping the bucket here, but (after just looking) one could put together a quality G41 board, 4 gigs 6400, and an E3300 (with hope to overclock the piss out of it) for $174. Naturally, the next "tick" (Sandy Bridge) will be the final nail in the coffin, but in the meantime, 775's fair game.
  • kevinqian - Wednesday, March 24, 2010 - link

    I think the recommendation for it as HTPC is nullified because bitstreaming is not supported on the Pentium G series! I'm not even sure if it supports 8ch LPCM.
  • larson0699 - Wednesday, March 24, 2010 - link

    [quote]The Core i5 660 is just like the 661 we reviewed in January but with a 733MHz GPU clock instead of 900MHz.[/quote]

    Anand,

    I feel it is also worth mentioning here that the 661 lacks VT, as the quoted statement suggests that GPU clock is the only difference.

    But great article.

    I'm just uncomfortable with the choice of a 3.33GHz dual/HT vs. 2.66 quad at the same price point. I find their clock speed selection a little obvious considering that and HT create such a linear product path:
    Quad/HT+Turbo > Quad > (high clock) Dual/HT+Turbo > Dual

    Is it possible that the G6950 could outperform an i3 simply because each core handles a single thread? I knew better than to think, for instance, that the 660 is logically four 1.66GHz cores... But I don't know exactly how HT allocates processor time, if it does dynamically (again, not thinking it simply splits the core down the middle, always leaving a core half idle if running 1 thread).. Would a kind soul please link me to reference? (I'm looking too)
  • yuhong - Thursday, March 25, 2010 - link

    The 661 lacks VT*-d*, not VT*-x*, which even the G9650 have.
  • larson0699 - Friday, March 26, 2010 - link

    I stand corrected. A difference nonetheless.
  • kaleun - Wednesday, March 24, 2010 - link

    considering overall cost of the platform (at minimum board + RAM + CPU) plus maybe case, PSU, HDDs, monitor, graphics, OS etc. I think saving $ 25 to get the Pentium over the i3 530 is silly. Maybe in the future one uses more multi-threaded applications, then HT comes in handy.

    People always compare CPU prices and are happy to save $ 25 or so. But a CPU alone is worthless. A decent PC costs $ 500 + with quality equipment that is fast and has a long life. (don't come me with those $ 25 case + PSU combos!!!).

    After the purchase I have never heard anyone saying: "I wish I had saved $ 25 and would have a slower CPU." the same way no one ever wished to have less memory.
  • larson0699 - Thursday, March 25, 2010 - link

    Agreed. The Pentium would be a hit if it were priced against the i3 for everything it _doesn't_ have, instead of against C2D for all that it _does_. I'm thinking $75 wouldn't have meant a catastrophic loss for Intel, considering most are buying left and right of it anyway.

    HT, 166MHz of GPU, the meg of L3, and the RAM speed discrepancy just aren't worth saving $25. And since it's the most crippled Pentium ever, it should've been a Celeron.
  • KaarlisK - Thursday, March 25, 2010 - link

    The 25$ does matter when your buying 20PCs - and, in my case, it's not 25$ but 25€. And for those 25€x20 I can buy two-three more PCs, meaning two more teachers with a new computer on their desks.

    Also, I will regret saving $25 on a motherboard (getting a G41 instead of a H55 means losing AHCI and GMA HD Graphics), I will regret not spending money on an SSD (roaming profiles, so all I need is a boot drive), I will regret not spending money on a quality case (have had far too many PSU/PSU fan failures), and I might regret choosing 2GB instead of 4GB RAM (might impact performance with future OSes/apps).

    I don't see how I will regret not buying an i3 530. Nobody will be using Photoshop/x264/Blender/RAR/etc much in the future anyway. So even though there is no reason to choose the G6950 from a price/perf perspective, it's the one saving I can afford to make, so I will.
  • larson0699 - Friday, March 26, 2010 - link

    That is absurd.

    Assuming your teachers actually need HD decode in hardware, step up to G43/G45, a board with X4500HD, and you still save measurably against H55. You're going to retard the CPU in favor of SSD--seriously?? And who buys "quality" cases (= no PSU, a sure bet) in bulk? Three words: Antec. Coolermaster. Silverstone. Bundle it up, man, you've got way better options before you. My example included 4 gigs, as I wouldn't run any less with Vista/7. Of course, you'll need every byte of it when you let the background processes, Search/Indexing, and Superfetch run rampant on an out-of-box registry--as I'm under the impression you'd also regret the manual overhead of deploying a tailored system through RIS or whatever it is now. And I can guarantee you that a two-thread processor will be at the mercy of the next OS by indication of trends. Forget it. If you don't wind up with a whole new platform by that time (let's see, because you chose the PENTIUM from the get-go) you'll be forfeiting that savings with the purchase of 20+ i3's or better.

    In my IT experience with school systems Stateside, NEVER have I walked into a school whose staff decided, "Who needs a preconfigured PC when we can instead BUILD a thousand machines?". And you know why it isn't practical? Education discounts. Volume discounts. Contracts and affiliations. Now show me that those cheap Pentiums are actually cheaper than i3 Lenovos or Dells in bulk, WITH warranty. Busted.
  • KaarlisK - Thursday, March 25, 2010 - link

    Oh, and I'll overclock the GPU to 733/900MHz anyway ;)
  • larson0699 - Thursday, March 25, 2010 - link

    Oops. 200MHz of GPU (was thinking 700 rather than 733).

    If I didn't correct me, I'd have been corrected. Done.
  • juampavalverde - Wednesday, March 24, 2010 - link

    Anand, as soon as i started to read, imho, noticed the lack of the most close match por the g6950, an athlon II 250 paired with a value chipset 785g (not close in price, amd is cheap, but they look similar in tech), and also for a price match there a 785g board with an athlon II x3 or x4. ¿There are chances of getting such information in this review? Specifically the 785g to compare the value side of this new pentium against an amd platform.
  • kaleun - Wednesday, March 24, 2010 - link

    true, there should be a platform price comparison. whoever is cheap enough to buy the Pentium also would buy a cheaper AM3 board. This could create a more serious price gap for similar performance.
  • Rick83 - Wednesday, March 24, 2010 - link

    Thorough article - but there's something that's bugging me lately.
    There are almost no benchmarks regarding dm-crypt performance on the web.
    With dm-crypt/truecrypt/bitlocker being the mainstay in personal encryption, and encryption-assist x86 extensions making their way into mainstream CPUs (and being used as distinctive feature), I'd like to see some data gleaned from testing.
    It's important to know after all, whether the CPUs these days are fast enough to maintain a bit of headroom while keeping the IO-buffers full.
    I'd be grateful if you were to consider that as an addition to your benchmark line-up.
  • Calin - Thursday, March 25, 2010 - link

    The VIA Nano processors had support for hardware-accelerated encryption more than a couple of years ago.
  • Rick83 - Thursday, March 25, 2010 - link

    I'm aware of that.
    But I'm not aware of anyone actually using VIA CPU's, hence my use of the word "mainstream". i5 6xx's will be sold in retail like hotcakes, on the other hand - they' probably already shifted near as many units as an entire run of VIA cpus consisted of...
  • yuhong - Wednesday, March 24, 2010 - link

    Yep, the Core i5 600 series have support for AES and PCLMULQDQ instructions, and it is sad to see they didn't bother to benchmark that. Luckily Tom's Hardware did and has the results.
  • Anand Lal Shimpi - Wednesday, March 24, 2010 - link

    We actually tested AES-NI in our Clarkdale review back in January:

    http://www.anandtech.com/cpuchipsets/showdoc.aspx?...">http://www.anandtech.com/cpuchipsets/showdoc.aspx?...

    Take care,
    Anand
  • Rick83 - Thursday, March 25, 2010 - link

    Yes, that sort of test is what I did/do find in heaps around the net.

    But I'd rather prefer to see a more in-depth benchmark of encryption. This test doesn't show me how well a similarly priced Phenom would fare, or how well AES-NI scales with regard to clock speed and cores (hopefully linearly in both cases - but there are no hard numbers).

    Additionally, Bitlocker is only one part of the equation; I'm not sure about market penetration, but dm-crypt should be considered a major player. This could also be relevant for the IT section of the site, as the Clarkdale based Xeons (and Gulftown in the future) all have different throughput available, and probably make an encrypted RAID far more transparent than an "old" Nehalem.

    This is probably also quite relevant, as one can expect AMD to implement those extensions themselves, for their next hardware.

    Thanks for reading,

    Rick
  • Perisphetic - Tuesday, March 30, 2010 - link

    speaking of the devil,
    are we going to see also some of the Intel vPro marchitecture benchmarks here too?
    I'd like to see how this hardware accelerated encryption alleviates the workload on these CPUs compared to more traditional software solutions and/or other hardware based encryption concoctions.
  • geok1ng - Wednesday, March 24, 2010 - link

    and once again i request side-by-side screenshot comparison of these integrated graphics, to remove any reasonable doubt that Intel is not cheating (again ) on image quality to push FPS higher.
  • vol7ron - Wednesday, March 24, 2010 - link

    I know there's been debate in the past about i3 vs i5, but would i5 be a better buy if you can't overclock? Say for instance you get a laptop that has a locked bios. Even though the i5 is more expensive, wouldn't it still be a better performer in all things not batter/Intel HD?
  • KaarlisK - Wednesday, March 24, 2010 - link

    If I really care about performance, I'm buying a quad core. The Athlon II X4 is cheap anyway - so I really can't imagine a situation where I'd take an Athlon II X3. It's basically either a cheap(ish) dualcore or a good quadcore for me.

    Also, it's possible to see that the i3 530 REALLY is a lower bin - it has much higher power consumption at load than any other bin. So it would be interesting to compare how an i3 530, 540 and an i5-6xx overclock, and how their power consumption curve looks (with the same multiplier&fsb of course).
  • qwertymac93 - Wednesday, March 24, 2010 - link

    will someone please explain how a crippled, handicaped, bastard child of a cpu that is the g6950 can score higher in sysmark 2007 then a high end, QUAD CORE cpu(pII 955) that has more features, bigger cache, higher clockspeed, and twice as many cores. I mean, all of clarkdale's advantages have been taken out and it STILL outscores everything. no turbo, no hyperthreading, lower clockspeed in the core, uncore, AND memory, and no virtualization! That's it, sysmark will forever be ignored in my mind as its clearly biased somehow. this is not because it outscored an amd cpu, its because it outscored ALL the other cpus on the chart, core2, core2quad, aII, pII, everything!
  • Jamahl - Wednesday, March 24, 2010 - link

    You are right, sysmark is a joke of a benchmark and the sooner AT gets rid of it the better for everyone.
  • qwertymac93 - Wednesday, March 24, 2010 - link

    correction, it doesn't outscore the 955, but its damn close...
  • Anand Lal Shimpi - Wednesday, March 24, 2010 - link

    SYSMark is definitely showing its age, but lots of corporations rely on its data to make purchasing decisions. SYSMark doesn't scale very well beyond 2 cores, which is why the Phenom II X4 doesn't get much credit for its extra 2 cores.

    Keep in mind that clock for clock the Phenom II is slower than Core 2 and Nehalem/Westmere (http://www.anandtech.com/cpuchipsets/showdoc.aspx?...">http://www.anandtech.com/cpuchipsets/showdoc.aspx?....

    An ultra low latency L2 plus a pair of high IPC cores (HT doesn't matter as much in a benchmark that mostly uses 2 cores) mean that even the G6950 does well here.

    AMD does a lot better in the other tests because most of our other benchmarks do show more of an advantage from more than 2 cores among other things.

    The benchmark is getting old, but it is a good representation of a lighter workload by today's standards. For heavier threaded workloads we offer everything from the x264 test to the par2 data recovery test.

    We never recommend relying on just a single benchmark but rather letting each one tell their piece of the story and then making a decision based on the benchmarks that represent your workloads.

    Take care,
    Anand
  • KaarlisK - Wednesday, March 24, 2010 - link

    It does show one thing. The value of G6950 & Core i3.

    For my school, where I'm buying computers for the teachers' desktops, the G6950 is more than adequate - and in most productivity tasks (browsing + word/powerpoint) it won't be much slower. The benchmarks also show that if I need a bit more power for this combination - mostly lightly threaded, some photoshop/video - I can safely choose a dual-core,four-thread Core i3/i5, instead of going for a quadcore i5 that requires external graphics and consumes more power.

    And I'm not touching AMD builds with a bargepole. They don't have AHCI for my cheap SSD's, they are usually slower booting and in other similar everyday tasks (as shown by laptop reviews on Anandtech), and they consume more power, while the new Intel graphics core has removed my reservations about G45.

    And I do have an AMD build at home as a cheap gaming/rendering computer, as it's the best way to obtain that specific goal - but there, I don't have to worry about keeping everything shipshape.
  • qwertymac93 - Wednesday, March 24, 2010 - link

    im pretty sure amd cpus support ahci(which has more to do with the chipset really...), either that or both my bios, my ears, and windows are all lying to me. when i enable AHCI in my bios(foxconn a7gm-s) windows shows my two sata drives as removable scsi drives, weird but whatever.
  • KaarlisK - Thursday, March 25, 2010 - link

    But AHCI with AMD chipsets is broken (or maybe the driver is) and SATA performance is lower.
    Of course, it is cheaper to get AMD's sometimes-broken AHCI (usually, it works with Microsoft's driver, but not with AMD's driver, and the performance is lower) than to get Intel's working AHCI (G41 boards don't have it, even the cheapest AMD boards do); on the other hand, sometimes I just CANNOT install Win7 on boards with AMD's AHCI and specific hard drives.
  • Taft12 - Thursday, March 25, 2010 - link

    Citation needed? I've worked with many Intel and AMD systems (mostly Linux however) and never ran into a problem with AHCI. Also, is SATA performance truly impacted assuming you are using mechanical hard drives?
  • KaarlisK - Thursday, March 25, 2010 - link

    A citation regarding the performance:
    http://techreport.com/articles.x/18539/8">http://techreport.com/articles.x/18539/8
    http://techreport.com/articles.x/18539/7">http://techreport.com/articles.x/18539/7

    And USB/PCI/PCIe performance (or CPU usage) is also worse:
    http://techreport.com/articles.x/18539/9">http://techreport.com/articles.x/18539/9

    And a direct quote from TechReport:
    "Unfortunately, AMD's longstanding issues with AHCI Serial ATA controller configurations persist in the SB750, all but forcing users to run the south bridge in plain old IDE mode. That's not the end of the world, but IDE mode doesn't support Serial ATA perks like hot swapping and Native Command Queuing."

    As for problems getting it to work at all, the views are conflicting: http://techreport.com/forums/viewtopic.php?f=36&am...">http://techreport.com/forums/viewtopic.php?f=36&am...

    But the fact is, I've had problems installing Win7 in AHCI mode on SB700, then tried the same drive with the ICH7MDH in AHCI mode, and it worked flawlessly.
  • CSMR - Wednesday, March 24, 2010 - link

    Advice: If you're going to measure power consumption you should use more appropriate components. People have been getting <25W system idle with some of the Clarkdales.

    Question: are video acceleration features available for all the Clarkdale processors here?
  • AtenRa - Wednesday, March 24, 2010 - link

    The numbers at Idle are with the GTX280 (i guess) and not with the intergraded Graphics. ;)
  • clarkn0va - Wednesday, March 24, 2010 - link

    You seem to have missed a couple distinguishing features of the new LGA1156 Pentium. First, it supports ECC when paired with Intel's 3450 chipset. I'm still trying to figure out why (or why Intel doesn't include ECC support on all their CPUs, like AMD does).

    Second would be the "Embedded" designation. I'm not exactly sure what Intel is trying to denote with that, as this is no Atom or Geode with a TDP of 73 Watts.

    http://download.intel.com/pressroom/kits/embedded/...">http://download.intel.com/pressroom/kits/embedded/...
  • Perisphetic - Wednesday, March 24, 2010 - link

    I think the major reason is the FUD of how well would the server CPUs fare if Intel did release ECC for the desktop family of CPUs. The problem is that LGA 1156 slots everything from i3, i5, i7 to Xeons. With the proper BIOS you can run a server board with an i7 or vice versa a Xeon in a desktop motherboard. If i7 did have ECC who would buy the Xeons at twice the price. Sure the Xeons have some fancy server features but if you could buy an ECC enabled i7 at half the cost no one would even consider the Xeons.
  • clarkn0va - Thursday, March 25, 2010 - link

    "if you could buy an ECC enabled i7 at half the cost no one would even consider the Xeons."

    Right. Which makes me wonder why this pentium has ECC enabled. It's not an i7, but it's enough of a CPU to fit the bill on many servers, and will take some business away from the higher-priced low-end Xeons.
  • has407 - Wednesday, March 24, 2010 - link

    Embedded means Intel will continue to ship the product for 7+ years. That designation is applied to many different products from CPU's to chipsets, and includes (some) high-power parts.
  • SgtSpoon - Wednesday, March 24, 2010 - link

    How can the G6950 outperform the i3 530 in fallout 3?
  • SgtSpoon - Wednesday, March 24, 2010 - link

    Also : "As a gaming CPU the Petnium G6950 is on par with the Athlon II X3 440 in our Fallout 3 test"

    Petnium? :)
  • Anand Lal Shimpi - Wednesday, March 24, 2010 - link

    Fixed and fixed :)
  • hyvonen - Wednesday, March 24, 2010 - link

    Anand,
    Looks like i5-670 was dropped from idle power plot... Care to add it? :)
  • FlameDeer - Thursday, March 25, 2010 - link

    Yes, i5-670 idle power is missing at http://www.anandtech.com/cpuchipsets/showdoc.aspx?...">page 8.

    We can find the results as 73.1W at CPU Bench here:
    http://www.anandtech.com/bench/default.aspx?b=51&a...">http://www.anandtech.com/bench/default.aspx?b=51&a...

    But the results of i5-660 & Atom D510 are really missing at CPU Bench.
    Example of Atom D510 vs Athlon II X2 255, which showing no results:
    http://www.anandtech.com/bench/default.aspx?p=110&...">http://www.anandtech.com/bench/default.aspx?p=110&...
  • Anand Lal Shimpi - Thursday, March 25, 2010 - link

    Fixed and fixed :)

    Intel's Atom D510 is now included in Bench :)

    Do you believe there's a need for the i5-660 in Bench even though we have a 661 in there? They provide the same application performance and we have no integrated graphics tests in Bench.

    Take care,
    Anand
  • FlameDeer - Thursday, March 25, 2010 - link

    Hi Anand, thanks for all the fixed. :)

    I agree with you about i5-660 & i5-661 both having same application performance (because no integrated graphics tests), they also having same price too.

    Only power consumption will have some different, but i5-660 & i5-661 are using different OS & GPU here:
    http://www.anandtech.com/cpuchipsets/showdoc.aspx?...">i5-660 Power Consumption - Windows Vista + GeForce GTX 280
    http://www.anandtech.com/cpuchipsets/showdoc.aspx?...">i5-661 Power Consumption - Windows 7 + Radeon HD 5870

    If not taking much time, adding i5-660 data will make Bench even more complete & will definitely benefits readers who specifically choose 660 for some reasons.

    You have really done a great job by building up this Bench function for all readers, with so much of hard works & efforts in running all the tests! Please help me remove my first reply at above which contain link code error to save the precious comments space here. Thanks & take care. :)
  • hyvonen - Friday, March 26, 2010 - link

    Thanks for adding the i5-670 idle power here!

    This may be a bit too much to ask, but I would really like to see the i5-6xx series idle powers measured without the high-power graphics card.

    Many HTPC rigs use in-package graphics to reduce heat generation and noise, and might get left on for extended periods of time... So idle power with integrated graphics only would be a useful metric.
  • FlameDeer - Thursday, March 25, 2010 - link

    Yes, i5-670 idle power is missing at http://www.anandtech.com/cpuchipsets/showdoc.aspx?...">page 8.

    We can find the results as 73.1W at CPU Bench here:
    [L]http://www.anandtech.com/bench/default.aspx?b=51&a...[/L]

    But the results of i5-660 & Atom D510 are really missing at CPU Bench.
    Example of Atom D510 vs Athlon II X2 255, which showing no results:
    [L]http://www.anandtech.com/bench/default.aspx?p=110&...[/L]
  • Kibbles - Wednesday, March 24, 2010 - link

    "To paragraph a short, wise, green man"

    I think you meant paraphrase :)
  • Anand Lal Shimpi - Wednesday, March 24, 2010 - link

    haha woops! fixed :)

    Take care,
    Anand
  • bombacan - Monday, April 5, 2010 - link

    these cpus has vtd support, diffent from i3a and i5 750, i5 661.
    as far as i know vtd needs also mobo support. so youll need a Q chipset.

    for general use i dont think these cpus are preferable to any 4 core att similar price

    gpu on the cpu is bullshit (not the idea, but the gpus are and will be), get a i3 or i5 750 and a standalone cheap card. it is obvious that these cpus are made for companies etc.

Log in

Don't have an account? Sign up now