Comparing Performance and Power Use For Vista vs. Windows 7 WIth Clarksfield Chi 119
crazipper writes "Back when Intel launched its Core i5/i7 'Lynnfield' CPUs, Tom's Hardware ran some tests in Windows 7 versus Vista to gauge the benefits of the core parking and ideal core optimizations, said to cut power consumption in the new OS. It turned out that Win7 shifted the Nehalem-based CPUs in and out of Turbo Boost mode faster, resulting in higher power draw under load, while idle power was a slight bit lower. The mobile version of the architecture was claimed (at the time) to show a greater improvement in moving to Win7. Today there's a follow-up with the flagship Clarksfield processor that shows the same aggressive P-state promotion policies giving Win7 a significant performance advantage with Core i7 Mobile. However, power consumption is higher as well."
Windows Update (Score:2, Funny)
We do know that the thrice-daily Windows Updates will consume a startling amount of power, though.
Re: (Score:2, Funny)
We do know that the thrice-daily Windows Updates will consume a startling amount of power, though.
How much power? Since we're talking about Windows with Chi, I'd say over 9000.
Re: (Score:1)
Re: (Score:1)
Re: (Score:2)
Re: (Score:2, Interesting)
Re: (Score:1)
Re:Windows Update (Score:5, Insightful)
I am no Linux fanboi by any stretch of the imagination however I have to agree with the parent. In my personal experience, regardless of hardware configuration, even a brand spanking new build will slow to a dead crawl (for all intents and purposes unuseable) when performing updates.
Re: (Score:2)
My experience has been just the opposite, granted I haven't used Ubuntu for the last major update, but before then the updates would always make doing much else impossible.
Windows updates, however, sit in the background and get data as they can even if it takes three days. It is generally a very low priority task unless you change it.
This is on a low-end laptop that is now a couple years old, so a desktop may not have had a problem with the Ubuntu updates.
Re: (Score:2)
He's talking about the actual installation, not the download process.
Re: (Score:2)
The update process uses 100% of a CPU core while it is waiting on some thread to finish. If the pending thread finishes quickly, then little CPU is used. Or the pending thread can take forever or lock up, and you end up using a significant amount of CPU and energy.
Re: (Score:2)
Hate to reply to my own post, but I wanted to clarify my point.
Because the process will use 100% of a CPU core for a unit of time, a higher powered CPU will expend more energy than a lower powered CPU as they will both be active for the same amount of time, but the higher powered CPU is designed to consumer more power per unit of time. If the process was limited by a complex calculation, then the higher powered CPU would finish faster and spend more time in a sleep state, which would likely use less power
Re: (Score:2, Interesting)
Ya you might actually want to look at the CPU usage during update, because the process doing the updates isn't using 100% while waiting for another process to finish. i've watched cpu usage several times during updates, and the only processes using cpu are the ones doing the actual updates (or the other running processes).
Re: (Score:2)
My observations are pretty consistent across a wide range of XP and 2003 x86/x64 systems. It is one of the SVCHOST.EXE processes that is being used by the update system, not the WAUPDATE process itself. The individual update processes themselves typically use a negligible amount of CPU time.
Re: (Score:1)
Ahh... you're talking about the automatic updates service, which is hosted by the same process as about a dozen other services. That service has a low priority, and I've never seen it bring any system to a halt. Usually I noticed it when the update icon first appears in the task bar saying its finished downloading update.
Are your observations perhaps on machines which are all managed by you?
Re: (Score:2)
I feel as if the conversation has drifted. The point wasn't that it would slow the computer down. The point was that it would use more Watts by keeping a CPU pegged, which would keep it at its highest speed.
I've observed this on machines that I manage, others home machines, and machines that have been freshly installed off of various install media. Trust me, this isn't an incidence of "I forgot to uncheck the 'use all of the CPU all the time for no reason' checkbox.
Re: (Score:1)
Ya, except that as other have pointed out, the "race to idle" actually uses less watts. So pegging the cpu isn't as draining as keeping the process running longer.
Re: (Score:2)
I think you may have missed my point completely. This is about the Windows Update process, and I was pointing out that in my experience, regardless of the speed of the CPU "they will both be active for the same amount of time". So, on a Pentium II and a Core i7, the update process will keep the CPU pegged for 5 minutes.
Obviously if you are trying to complete specific calculations, then it is better to hurry through them at high power and shut down earlier. In this case though, the process in question is
Re: (Score:1)
What exactly do you think CPUs do with their time if not calculating?
Re: (Score:2)
CPUs idle when not doing anything. Processes though can do all sorts of crazy things like, polling something constantly, which keeps the CPU loaded. Why someone would do that is a mystery, but that people do it is not.
Re: (Score:1)
Or perhaps the process is processing the update list, which is what it is doing.
Re: (Score:2)
Although, if the process were processing a list, then a faster CPU would finish the list more quickly, which would be contrary to my stated observations. Or are you implying that the process processes a list repeatedly for a specific amount of time?
Re: (Score:2)
As a shudder runs down my spine (Score:2, Funny)
So you're saying Vista is the better OS?
But what about ECC? (Score:4, Insightful)
On what desktop system do you use ECC? (Score:4, Insightful)
I haven't seen a desktop in a long time that had ECC RAM, or even support for it. In the Core 2 era of chips desktop use normal unbuffered DDR2 or DDR3 DIMMs. For ECC stuff on workstations/servers you use FBDIMMs which are way more expensive.
Same shit with the i7. If you want i7 class hardware with ECC it is called the Xeon 5500. Running on a 5520 chipset, it supports ECC RAM, and lots of it (144GB is the most I've seen thus far).
That's all workstation class stuff. Desktop stuff is not ECC because it is cheaper.
Re:On what desktop system do you use ECC? (Score:5, Informative)
I haven't seen a desktop in a long time that had ECC RAM, or even support for it.
Any moderately recent AMD CPU will support ECC, and it's not hard to find a mainboard that does as well (for example I believe any ASUS mainboard for AMD will support ECC, I know the one I checked a couple days ago does (cheapest ASUS AM3 mainboard on Newegg then, probably still is, only like $5 more than the cheapest other AM3 board)).
In the Core 2 era of chips desktop use normal unbuffered DDR2 or DDR3 DIMMs.
Buffered/unbuffered is separate from ECC/non-ECC. For example I know the AMD desktop chips support unbuffered ECC memory.
Desktop stuff is not ECC because it is cheaper.
Maybe 10% cheaper. And of course it's easy to make things cheaper if they don't have to work correctly.
Re: (Score:3, Insightful)
Re: (Score:3, Insightful)
Sometimes good enough is just that. People are used to restarting their computers and getting random blue screens. If a restart fixes it, they generally don't care. And that's fine by me.
I see it more as a problem that needs to be fixed, because even if most people use their computer for mostly entertainment they still use it for actual productive stuff at least occasionally.
I don't use my machine for super-high precision work where a few bits flipped will cause massively different results. Nor do 99% of people. Why pay the extra 10% more when less than 1% actually might have a use for it?
Because that "10% more" is going to be maybe $20 if you have unusually large amounts of RAM, and more like $5 for a $500 BudgetBox system that only has 2GB? That's probably worth it even for gaming (I'd imagine a bluescreen in the middle of an important raid or something could be rather annoying), let alone using TurboT
Re: (Score:2)
Honestly I have not seen a RAM-based BSOD in a long, long time. The last time was actually, unfortunately, the first time I booted a new laptop that came with Vista a couple years ago. I'm reasonably certain the OEM screwed something up there, it's highly unlikely that it was a RAM error.
RAM BSODs are very rare, because the RAM is very good. You use ECC in "mission critical" applications, not in video games or the occasional turbotax that you only use once a year.
Seriously. If you're worried about it yo
Re: (Score:2)
I built a Phenom II 940 with 8GB of DDR2 ECC on an Asus M3A78-T at the beginning of the year which works great. A system built around the cheapest version of the Xeon i7 at
Re: (Score:2)
more like 50% cheaper http://ncix.com/products/index.php?sku=23482&vpn=OCZ2G8004GK&manufacture=OCZ%20Technology [ncix.com] http://ncix.com/products/index.php?sku=41650&vpn=KTH-XW4400E6%2F2G&manufacture=KINGSTON%20TECHNOLOGY%20-%20MEMORY [ncix.com]
(Those links are $80CAD for 4GB DDR2-800 non-ECC and $80CAD for 2GB DDR2-800 ECC.)
Look over here [newegg.com], I think your example of ECC pricing might not by typical.
Re: (Score:2)
It's better if you just search for DDR-2 800 and pick out the ECC compared to the non. They are pretty much the same price, but the ECC is genearlly slower (due to higher latency) than non-ECC. Whether or not that matters to you or not is personal preference. Clearly since manufacturers don't see the need to include ECC in desktop level PCs there is not exactly a public outcry for this RAM.
Re: (Score:2)
Any latency difference with current DDR2 and DDR3 memory is primarily a function of the memory controller and how cache
Comment removed (Score:5, Informative)
Re:On what desktop system do you use ECC? (Score:5, Informative)
"Intel segments the market intentionally!"
Don't forget virtualization. With AMD, you don't have to pay a premium if you plan to run virtual machines.
Re: (Score:3, Interesting)
"Intel segments the market intentionally!"
Don't forget virtualization. With AMD, you don't have to pay a premium if you plan to run virtual machines.
You no longer have to pay a premium with Intel either. I've noticed that Intel recently began adding their "Virtualization Technology" to all new CPU models, even their entry-level Celeron and Pentium Dual-Core lines. Example: this $53 Celeron E3200 at Newegg [newegg.com].
I think Intel did this in response to Microsoft's announcement of Windows 7's "Windows XP Mode" and its requirement of on-CPU virtualization technology. AMD also recently started adding their "AMD-V" to their previously-excluded Sempron line of CPUs.
Re: (Score:1)
For more info, look up these CPUs on http://ark.intel.com/ [intel.com] or find the PCNs at http://intel.pcnalert.com/Portal/SearchPCNDataBase.aspx [pcnalert.com].
Re: (Score:2)
Is ECC RAM really that important? I've found desktop computers to be extremely reliable these days, and typically any instability to be caused by bad device drivers.
The only time I've used ECC RAM is in a machine I built about nine years ago. I finally checked the Windows minidump files in a debugger and saw memory issues on the stack. But maybe I put the machine together incorrectly, or it was using unreliable components or something. These days I'm quite happy to buy a Dell off-the-shelf... they've al
Re: (Score:2)
Is ECC RAM really that important?
Yes.
Article from nine days ago: Google Finds DRAM Errors More Common than Believed [slashdot.org].
As in, more common than believed by people like yourself.
Re: (Score:2)
Re: (Score:2)
I haven't seen a desktop in a long time that had ECC RAM
You mean like EVERY single AMD AM2/AM2+/AM3 board that ever existed? Thats only half of the market so its quite understandable you missed it.
Re: (Score:2)
He didn't say supported, he said had. HAD. Consumers don't often buy ECC RAM, hence Intel doesn't see the need to include support for it.
Frankly, Intel doesn't seem to care about the half-dozen hobyists who think their nightly WoW session is a "mission critical" application. Maybe if someday that half-dozen turns into a few million they'll change their minds.
Seriously, why the hell do you need ECC RAM?
Re: (Score:2)
Wait, I think I missed part of his post.
He's obviously not an AMD fanboi then. My bad.
Still, otherwise, the point stands.
Re: (Score:2)
Re: (Score:2)
I haven't seen a desktop in a long time that had ECC RAM, or even support for it.
intel 'bad axe 2' (x975) series. I have several of those mobos and I keep them as cheap servers. eepro1000 on board, two 4-port sata2 chips (both linux supported, running 8 md5 raid drives across those 2 controllers), lots of extra pci-e slots and it DOES take ecc ram.
yet its a consumer non-server board.
Re: (Score:1)
Re: (Score:2)
Because Borderlands is going to rawk on it.
What? That's not a good enough reason for you?
Underclocking and P-state? (Score:1, Informative)
Foo2 gives much higher performance and somewhat higher power consumption than Foo1.
Solution: Apply a downwards scalar to Foo2 so that the performance is the same and the power consumption is lower than Foo1.
MacBook Pro (Score:3, Informative)
Isn't that what Apple introduced earlier this year on the MacBook Pros? The ability to switch off the high power GPU when it's not needed and fall back to a lower quality integrated GPU? I realize that Apple used an nVidia solution instead of an Intel, but that still seems a little disingenuous.
PS: Emphasis was mine
Re: (Score:2)
Re: (Score:3, Insightful)
Notebooks have done this for years (my girlfriend's 2-3 years old windows lap-top has that). Im guessing this is just Intel's flavor of it. Unless there's something fancier about Apple or Intel's offering like being able to do it on the fly without any settings to toggle or bios interaction, like CPU stepping.
Re:MacBook Pro (Score:4, Informative)
The Apple GPU switching implementation appears to require the user to restart his or her session (that is, log off and log on again.) Intel's implementation seems to support switching GPUs without logging off or restarting. The Intel solution also has to handle two different display drivers.
Some older laptops supported switching between integrated and discrete graphics as well, but I think they required a reboot to switch.
Re: (Score:2)
You can switch on the ThinkPad T400 without restarting or logging out, as long as you're running Windows Vista or Windows 7.
Re: (Score:3, Interesting)
My vaio has that too.
Unsure as to the actual battery life gains, but it has built in Intel GM965/X3100 and an nVidia 8400M GS. Maybe not using intel's tech?
Re:MacBook Pro (Score:4, Insightful)
So the worst thing you can say about Win7 is that it performs better but uses slightly more power in some rigs?
Desperation sets in...
Re: (Score:1, Troll)
Desperation sets in...
Indeed.
Re: (Score:2)
Good grief (Score:4, Funny)
I've built several high-end PCs from scratch and spec'd several more at component level, during a period of well over a decade and most recently just a couple of years ago, and I still have absolutely no idea what any of the fine summary meant.
Does anyone actually label/number components in any sort of logical way at all any more? Codename this, year that, version.subversion.minorversion.veryminorversion the other (revision C17, of course; the C16s and B17s didn't have the double overclocked doobreeflips in the L7 cache).
It's a wonder anyone can build a PC that runs at any speed at all any more. Sheesh.
Re: (Score:3, Informative)
Lynnfield = the internal name for the new Core i5/Core i7 CPUs for LGA 1156.
Core parking/ideal core = two optimizations from Microsoft in Win7 that are supposed to save power by consolidating background tasks onto as few CPU cores as possible, and then putting the idle cores to sleep.
Clarksfield = Core i7 Mobile; basically, the Lynnfield stuff with a different interface, more aggressive Turbo Boost, etc.
Nehalem = Another Intel internal name referring to the whole family of 45nm CPUs based
Re: (Score:3, Insightful)
They obviously don't. Some cohesive naming might give you at least an indication on what you are dealing with.
My favorite is the nVidia one: GF 6xxx -> GF 7xxx -> GF 8xxx -> GF 9xxx -> GT 2xx .. WTF?
Now don't ask me why. I think it's stupid.
Re: (Score:2)
Isn't this what we want? (Score:5, Insightful)
Re: (Score:2)
Powering the chipset and backlight (Score:5, Insightful)
while under battery power the CPU will do everything it can to conserve power under the same software load conditions.
In many notebooks, the CPU does not dominate battery consumption; the northbridge, southbridge, and LCD backlight draw a significant fraction of the power. So when CPU usage hits 90%, clocking it up to full power is warranted because it gets the work done faster, meaning that the chipset and LCD don't run as long while the user is waiting for the CPU to finish.
Re: (Score:3, Insightful)
... if the goal was to use as little power as possible, we'd just lock the processor in "slow mode".
Not necessarily. You also have to consider that higher performance settings may allow the processor to complete its task(s) and return to a minimal-power idle configuration more quickly, for an overall improvement in average power consumption. It all depends on the power/performance ratios for each performance level and the amount of overhead involved in switching between them. Plus, of course, a bit of clairvoyance in accurately predicting future requirements.
Re: (Score:3, Insightful)
Re: (Score:2)
If you run a 30 W load over 1 second, it will use 30 joules of energy (because a 1 W power draw means it consumes 1 J per second). But if you run a 500 W load over 1/100 sec, you'll only use 5 J of energy.
Idealistic math ... and I get the instinctive thought (because you don't explicitly say wtf you are throwing these numbers out for) that the 30 J run and the 5 J run achieve the same goal. Such thoughts are misleading!
I don't claim to know which power states are the most efficient on a CPU. To speak of a
Re: (Score:2)
You're right. They aren't synonyms. Clairvoyance is "the power or faculty of discerning objects not present to the senses" or "ability to perceive matters beyond the range of ordinary perception", according to Marriam-Webster, whereas precognition is specifically the ability to perceive the future.
However, I never claimed they were synonyms. Future events are among those "matters beyond the range of ordinary perception", so precognition necessarily implies clairvoyance.
Re: (Score:2, Insightful)
That said, Tom's Hardware did make a pretty big blunder on SSDs and battery life before, even having the gall to start that article with "Could To
Re: (Score:3, Insightful)
Actually, that's probably only true if you keep the voltage constant. If you can reduce the voltage to the CPU as you reduce the frequency ("DVFS" - Dyn
How about using XP sp3 for comparison??? (Score:5, Informative)
I cant be the only one who might think xp sp3 might actually win
Re:How about using XP sp3 for comparison??? (Score:4, Informative)
Windows 98 might win.
Re: (Score:2)
ur mom might win
This is slashdot, son, not 4chan. Here we post maturely and intelligently without ever resorting to personal insults and outdated internet memes.
Re: (Score:3, Informative)
Of course it would win. Which is why they won't allow it in the tests.
Situations like this are why I run Intel chips (Score:3, Insightful)
I primarily use Microsoft software (I know, get out the pitchforks) and over the years I have occasionally run AMD chips after being overcome by various AMD biased friends of mine. I've never been able to put my finger on it, but Windows simply doesn't run as well on AMD chips as it does on Intel chips. I always end up switching back to Intel. This article is just an example of why. Intel and Microsoft are in bed with each other, and Microsoft will always be putting out the code to take full advantage of the Intel chips. It wouldn't surprise me if Intel gives Microsoft the heads up on new features far in advance. It wouldn't surprise me if Microsoft works with Intel and encourages them to develop certain features in their processors that will help the Microsoft code base execute faster.
Re:Situations like this are why I run Intel chips (Score:4, Insightful)
What is flame bait about my post? Intel and Microsoft work closely together to optimize the user experience. Must be AMD fans with mod points today.
Re:Situations like this are why I run Intel chips (Score:5, Insightful)
Riiight.
Certainly Intel and Microsoft work closely together, they have many reasons to. But I've used many AMD and Intel systems, and honestly they're pretty interchangeable in terms of user experience.
Claims that Windows only runs right with Intel is at best, inaccurate. Are you forgetting things like the adoption of the AMD64 architecture as The Way Forward for Microsoft in terms of 64bit support, over Intel's offerings..
Re: (Score:2)
Re: (Score:2, Insightful)
My Win7 quad core AMD system that boots in under 10 seconds, is rock solid stable, and runs every game I throw at it blindingly fast would care to disagree with you. :)
Link to my PC build out. I was going more for cosmetics (30 lbs of brushed aluminum, I don't much like the blue LEDs though, I am burnt out on blue LEDs) than for power, I have friends who consider a 10 second boot with Win7 to be slow. Not that I boot very often, more likely I am coming out of Hibernate which I can do in ~3-5 seconds, whic
Re: (Score:1)
I've never been able to put my finger on it, but Windows simply doesn't run as well on AMD chips as it does on Intel chips. I always end up switching back to Intel.
It's real for you because it is in your head - you are seeing what you expect to see.
Re: (Score:1)
What does it mean "doesn't run as well"? Do the AMD CPU behaves obstinate and uncooperative? Started an union? You found high profile political assassination plans on a core-dump? It was going to stab you last night? Bad AMD bad!
Also you say that intel and Microsoft working together as if it's a GOOD thing, what? in 5 year you can run Windows 8 ONLY in intel: chipsets-SSD-CPU-Video Card? Sure THEY would like that.
Any Pheno
still worth the upgrade (Score:2, Insightful)
Re: (Score:1)
Re: (Score:1)
Iv said it several times and Ill say it again.
The only thing wrong with Vista is the system requirements.
My laptop with a 2GHz amd x2 processor and 2GB of RAM ran vista very poorly, even though vista only "requires" 1GB.
I cant imagine running it with 1GB.
But Vista works fine when you have 3+GBs
Not only was it speedy on my desktop powerhouse, but it was stable too. More so than I have found XP to be.
Windows 7 is absolutely great if you have a system that can run Vista decently, and win7 on my laptop actually
Re: (Score:1)
Why not "upgrade" to Windows XP 64-bit? It's faster than Vista and Win7, supports as much RAM as you can throw at it, has the same drivers support as Vista, and less invasive DRM.
Unless you actually like the condescending, childish Fisher-Price interface of Vista?
confused (Score:3, Funny)
Is Clarksfield Chi anything like a Charleston Chew?
Clarksfield Chi (Score:2)
power isn't the problem (Score:2, Funny)
The problem [ducks] is that it's running windows [runs]...
[aw crap, here we go again]
[I hear the sock puppets winding up]
more power, but more energy? (Score:2)
It uses more power, but if it gets the job done more quickly, it could still use less energy. Much like any current computer will get a sizable job done using less power than an Apple ][, even though the power supply and power draws are much bigger on the modern PC.
Also, the article tries to compare the laptops and gives system performance in minutes/mAh. But the article doesn't give the voltage of the battery packs. What is the minutes/mWh?
Test is pointless (Score:1, Insightful)
Windows 7 is an upgrade to Vista, and it performs better. This isn't news.
The problem is that Vista is a HUGE downgrade from XP, and so far everything I've read says that 7 is simply less of an XP downgrade than Vista was. I couldn't care less if it's prettier - it either needs to have some major functionality that XP doesn't (and it doesn't), or it needs to offer a serious performance boost over XP (and it appears to do the opposite.)
Re: (Score:3, Interesting)
Re: (Score:1)
Re: (Score:2)
Re: (Score:1, Troll)
much better drivers for 64-bit 7 then XP
Ah, well at least you're honest about your lying.
Power User? How about begrudging windows users? (Score:2)
For those of us that use Windows in a VM on our primary Linux or Mac OS X desktop, what is the best OS?
For a long time, I stuck with my good old Win2K VM. But, too many apps were not supported on Win2K, so I moved to XP.
There was clearly no reason to go to Vista from XP. But, how about now with Win7? Any advantages to Win7 for basic VM use, office apps & IT tools?
Re: (Score:1)