Slashdot Mirror
AMD Announces 65-nm Chips, Touts Power Savings
Several readers wrote in about AMD's entry into the 65-nm manufacturing generation. The company introduced four chips to be manufactured with 65-nm process in the first quarter of 2007 to replace existing 90-nm chips in their lineup. AMD is playing up the power economy of its line, claiming that even its existing 90-nm parts consume less than 50% the power of Intel's Core 2 Duo, averaged over a typical day's usage, while the new 65-nm chips will be even stingier with power. Next stop, 45-nm. The article says that AMD has a goal of catching up within 18 months to Intel's lead on the way to 45-nm technology.
Dang.... nice.
:) (when my current laptop dies or just looks old).
Looking forward to my next laptop being a 65nm Turion X2 in about 2-3 years
Tom
Someday, I'll have a real sig.
It will probably drive down the costs of the Core 2 so many of us can justify buying one.
Check out the cave on the east side of lake Hylia. Strange and wonderful things live in it.
I'm way ahead of the game, my transistors are -30nm. I had to do some funny things with space time, but they work. Until you observe them anyways. Next up, I'm going for inm chips.
When do we say enough is enough and just stop this cancerous shrinkage? How small do transistors really have to be?!
We can say enough is enough when I have more processing power than I know what to do with it in a laptop that is small, lightweight and has 18 hours of battery life. Ultimately, I think we'll get there in 10 to 15 years.
when gates are a few atoms wide.. when to make it smaller they need to use sub atomic particals as building blocks.. even at 45 nm the interconnects are only a few atoms wide.. when they get to 1 atom wide.. i think that will be a safe stopping point.. but till then.. the smaller the better.
'...if only "Jumping to a Conclusion" was an event in the Olympics.'
I went from a pair of 2.8ghz xeons to a pair of Opteron 250HEs and its a world of diference.
"Have you ever thought about just turning off the TV, sitting down with your kids, and hitting them?"
Res publica non dominetur
So if AMD doesn't catch up with Intel by that timeframe, they'd be pretty much screwed, wouldn't they?
Hopefully we can see some Socket AM2 65nm stuff in the retail channel soon.
You see? You see? Your stupid minds! Stupid! Stupid!
Why don't you just borrow Time Lord technology and use it?
Please, for the good of Humanity, vote Obama.
You might change your behavior if your laptop's battery lasted longer. What if it could go 12 hours without plugging in?
I have the reverse problem; HP made a few laptops with full-power Pentium 4 CPUs a couple of years ago, and I got one. It's nice and fast, but its battery life is roughly 23 seconds.
Intel will be holding still for 18 months while AMD catches up.
That if you actually use it as a laptop, you won't have a problem with it burning your, er, "parts".
The nano-transistor uncertainty principle anyone? They are very fast and power efficient when processing... but when you process you won't know what the answer will be?
-- I ignore anonymous replies to my comments and postings.
until then we get to read about AMD fanboys talking about how much better this is then Intels current line up. Completly ignoring that fact that Intel has plans for the next 18 months as well.
Wait and see what happens, in the mean time buy the chip that you need now.
The Kruger Dunning explains most post on
At 23 seconds I would call you lucky. With my Sony, the battery only lasted 16 seconds before it exploded! Now THAT is poor battery life.
Just stay away from (-30+i)nm chips. They're way too complex.
It will give you every answer possible, except that one your looking for.
The Kruger Dunning explains most post on
Keep in mind, though that 1 atom wide for Si is 111pm (that's 0.111nm for those who dont know their units), so we're talking about ~400 atoms wide at 45nm. We've still got a little breathing room. I'm still waiting for Carbon Nanotubes to replace the Si interconnects.
AMD fanboi much?
The Kruger Dunning explains most post on
"nansistor"
Patrick Doyle
I mod down every jackass who puts his moderation policy in his sig. Oh, wait a sec....
Is anyone as tired of software companies eating up the gain in hardware performance as me? And for what? How about someone writing better software, not just new software. I got sick of buying new hardware just to open the same document because the O/S or new Office suite was bloated/full of shit/required way more horsepower just to do the same task. No Vista for me. I'll stay will XP and Linux on my (older) machines. And if MS forces people to go Vista, I'll go Linux or BSD. If I get new hardware, it will be to make these systems faster, not make new software, doing the same job, run the same speed.
-- I ignore anonymous replies to my comments and postings.
Quite frankly, on a level playing field I think we're going to find out that Intel's Cores are not quite as good as a lot of people have been raving. AMD's architectures are just a whole lot better.
You know, that's what a lot of people said before the Core Duo came out, and they were proven quite wrong. I was as surprised as anyone, but I learned the lesson: wait for the actual chips to be tested.
Once Intel puts the memory controller on-die like AMD has, it's going to *really* hurt AMD. HyperTransport doesn't seem to have any advantage at all on the desktop, so AMD's only real tech advantage right now is that on-die mem controller. Perhaps once we all have 8+ core chips on our desktops, you might see some HT advantages, but I believe I read somewhere that Intel has plans for on-die memory controllers and an answer to HT in the wings for 2008, though obviously that's just rumour at this point.
Fanboi alert. Have you checked Pricewatch in the past six months? Intel is kicking AMD's ass in price, performance, and price/performance at almost every price level.
Um, no, you really need to check your facts. You are quite simply misinformed.
I'm way ahead of the game, my transistors are -30nm. I had to do some funny things with space time, but they work. Until you observe them anyways. Next up, I'm going for inm chips.
Great! This guy has Schroeder's Notebook!
There is no "I disagree" mod for a reason. Flamebait, Troll, and Overrated are not substitutes.
HT also shines as memory sizes grow larger. One of the problems with the current generation of workstations is that few have enough (and fast enough) memory and memory bandwidth to keep a single core, let alone several, at 100% utilization all of the time. A dual core duo system with four cores, however, would benefit immensely with something like HT and multiple banks of memory.
Obviously you haven't read anything about Core2. Core2 is, on average, 20% faster at the same clockspeed as AMD's Athlon64. If you liked the fact that AMD's Athlon64 was comparable to the Pentium4 at 2/3 the clock speed, then you simply must like Core2's being faster at ~80% of the clock speed of the Athlon64... while still being on the obsolete, much maligned FSB architecture that AMD spends so much time and money poo-pooing over their obviously-so-much-better IMC+HT technology.
Well... when you can't lead in performance, you try to lead somewhere else. Yes, the launch of Core2 parts drove AMD to cut the prices of their processors by 50% or more in order to stay competitive. Had they not done that, they would be selling nothing right now because even a fanboi couldn't justify buying AMD at the complete destruction that equal priced CPUs from AMD would get compared to the Intel parts. So, AMD dropped back to attempt to remain king of the bargain market until they could release something that would put them back into the performance game, which Intel currently owns (not counting the obviously boutique, one-off 4x4 deadend attempt to save face that AMD marketing released).
I have three Athlon XP and four Athlon64 machines at home (and no Intel other than two laptops). This migration of socket requiring a new CPU and all has bitten me already. My S939 parts barely lived a year (two years given the entire lifetime) and already AMD is requiring me to buy a new motherboard *and* CPU if I wish to upgrade because they're already killing off S939. Many of the already existing S775 boards for Intel will upgrade the CPU to Core2 (perhaps with a BIOS flash). It makes me kind of wonder how long Socket AM2 is going to last given that they're already talking about S1207 and some future move to DDR3 (yet another socket change?) Currently, for me to upgrade my AMD machines, I have to buy a CPU + motherboard because even the S939 X2s are EOL'd. I've thought about buying some upgrade AMD CPUs but I'm not going to do it. Core2 offers too much performance increase with the promise of socket compatible quad core very (very) soon. I believe AMD is requiring S1207 for quad core, so if you bought AM2, you're already EOL'd because of the change for DDR3 and quad core. AM2 was dead before it was released, it seems.
Like adding a massive parallel vector coprocessor with the Fusion ?
up, that'll definitely differenciate them from Intel. And that's also why they need to catch-up with 45nm soon, in order to be able to cram all this on a single die.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
Great. Smaller manufacturing processes are the root of all good. Well, in microchip land, anyway.
Please correct me if I got my facts wrong.
It doesn't matter, eventually linux will be the same.
I have a 500MHz Pentium III laptop I use, which was fine with Windows 2000. After they EOL'ed it, I switched to Linux. I am currently running Xubuntu (Ubuntu with Xfce), but as even Firefox and Thunderbird are getting bloated, it's sluggish. I even maxed out the ram (576MB), which helped a little, but I'm going to have to replace it soon.
Any suggestions on laptops with decent linux driver support that wouldn't crap out after 3 years? I'm spoiled by these old Thinkpads.
Will the War in Iraq get better or worse in 2007? Vote here
FTFA:
``AMD's 90-nm/65 watt Athlon 64 X2 chips consumed 47.6 percent the power of a 65-nm Core 2 Duo chip, the company said. A 35-watt X2 consumes 73.3 percent of the power of the same Core 2 Duo.''
So the 35-Watt X2 consumes 1.53 times as much power as the 65-Watt X2? Something is wrong there...
Please correct me if I got my facts wrong.
Amen.
I've purchased AMDs ever since I got rid of a Pentium 133 (aside from "donated" machines). But over my Thanksgiving break (took some vaca) I put together a Core2Duo; upgrading from an Athlon XP 2800+/Geforce 6600gt.
I put together 3 lists of items. A single core AMD 4000+ s939, a dual core 4800+ AM2 and an Intel e6600. Single core price was 1000$; both duals were just under 1300$ (with GeForce7950gtko)
I went with the Intel. From what I can tell, it's been a good buy; however, I'm kind of kicking myself for not buying a Raptor to go with it - I can tell that disk access is a majority of what holds back anything on this system... and upgrading the 2800+ just didn't make sense...
Karnal
here's an activity for you. get an athlon64 x2 and a core 2 duo, run them at the same mhz speed with the same ddr2 speed/timings, and compare how much faster the core2duo is clock for clock.
it's faster. it does more work per mhz. it's more efficient.
this has nothing to do with 90nm or 65nm. amd isn't changing anything about their cpus, they're just shrinking them.
Trollish, fanboish, but Ill bite anyway. DUH! AMD is slower MHz to MHz, they dont claim otherwise! Thats why they went to CPU ratings as opposed to raw MHz on their model names. They did that years ago. Get over it. AMD's architecture allows them to run on much less power (thus cooler) than the equivalent Intel. They might not always have THE FASTEST CPU EVAR!! but neither does Intel, the lead swaps back and forth. As for "just shrinking them", isnt that all that intel is doing too? Oh yeh, they are also cramming another peice of silicon into the same package to add cores... AMD is putting all the cores on the same piece. They also have the memory controller on board, something that Intel is probably working towards since it dramatically increases memory bandwidth to the CPU. Evaluate the CPUs based on how they perform for your specific needs at the prices you can get them for, and you end up with "The Best CPU" for you. Thats what I do, and sometimes Intel wins, sometime AMD does. I currently run an older P4 as my desktop, and a dual AMD MX as a workstation, and a few multi-cpu/core Opteron based SUN servers.
blah
tm
Support TBI Research: http://www.raisinhope.org
Well the good news is that the 65nm processors will not cost more than their siblings. For example, the Athlon 64 X2 5000+ in both 90nm and 65nm will sell for $301 in quantities of 1000.
When it stops being profitable to continue scaling transistors. The reason we scale is because it makes chips cheaper, faster, just plain better, meaning Intel and AMD (and others) can sell it for lots of money. If scaling no longer achieves that goal, you'll see it end in a heartbeat (just like you saw clock speed ramping come to a halt once it wasn't selling like it used to).
In what way are these new 65-nm chips behind? I feel that, now that AMD's and Intel's chips are on the same scale, we can finally compare the cores on an equal footing. My feeling is that AMD's might win. At any rate, given that Core 2 was just a little ahead of AMD's 90-mm CPUs, Intel's certainly won't lead by far.
Please correct me if I got my facts wrong.
Obviously you haven't read anything about Core2. Core2 is, on average, 20% faster at the same clockspeed as AMD's Athlon64.
No it isn't. consider this....
The Core 2 Duo has caught up, and in certain applications beat the AMD64 design, but in terms of IPC it's not really better. Where the C2D shines is power efficiency. My E6600 (2.4GHz) is running happily at 3.42GHz without overvolting or other fooling around. At this speeds I can compile, and run any crypto test I throw at it through my daily chores faster than any AMDX2 on the market. For a hell of a lot less than what the AMDFX series cost.
I imagine the AMD 65nm part is suitable for overclocking and in 2007 we'll see 3+GHz high IPC parts be standard in retail.
Tom
Someday, I'll have a real sig.
"Next up, I'm going for inm chips."
Feh, those are imaginary.
The enemies of Democracy are
This is Slashdot, not Santa Claus. Please stay on topic.
One minor correction--the memory controller does not increase memory bandwidth per se, but it does significantly reduce latency, as well as the complexity and power consumption of the Northbridge.
Help find a cure for cancer. Join the [H]orde
"What Andy [Grove] giveth, Bill [Gates] taketh away."
This is my signature. There are many like it but this one is mine.
Yeah, but extremely lightweight.
Yeah, I got one of those too... first laptop model I could find with a built in 10-key. Works great when I can leave it plugged in, but when traveling... can't even get half of a movie finished before I run out of juice.
I think while being smartassy and all you completely forgot that the atomic radius is not equivalent to lattice spacing in crystals.
Your numbers are way off.
I feel your pain, I still have mine and its definitely a powerhouse machine but useless while mobile. Initially my zd7140us got 2.5hours of battery life, lately it struggles to go 1.75 hours, mostly 1.5 or less with wifi on.
Now I have a work-provided Dell Latitude D620 with dual core intel and 2 gigs o delicious ram and it has a decent 3.5 hour battery and still runs circles around my old hp in performance. Plus I can go the 2nd battery route with this one if needed.
Cheers.
This is my sig. There are many like it, but this one is mine.
But other than that, I pretty much agree. As has been said for many eyars, brand loyalty is a socially acceptable version of battered spouse syndrome. Products should always be objectively evaluated for suitability to a task. Sometimes one chip is better for a certain task. Sometimes another chip is better. Sometimes the CPU doesn't really matter at all.
Features or efficiency. That's just how it goes. If you want software that does more nifty shit, you have to be willing to throw more horsepower at it. Lynx uses less memory, disk, etc than Firefox, however you certainly aren't going to see me switching. It's not like there is some magic programmers could use but don't to write fast, feature rich software.
Now maybe you long for the days of spartan computing, maybe you want to do nothing but scroll text really fast. That's fine, there's stuff out there to accommodate you. However that's not what most of us want. I want a feature rich system, I want my computer to be everything, do everything. Well for that I need hardware, and I'm willing to pay for it.
It would be like trying to compare frame rates between Ultima 1 and ES4: Oblivion. When you get down to it, Ultima 1 probably has a frame rate as fast or faster than Oblivion. Ultima 1 wouldn't have any trouble running at 30fps or more, even on 286 hardware. Oblivion can run under 30fps, even on an 8800GTX. However you are dealing with a totally different level of graphics. Ultima 1 was made to run in CGA which is 2D, 2-bit (4 colour), 320x200. Oblivion is full 3D with amazingly high geometry, 128-bit FP colour, 2560x1600 with anti-aliasing. Despite the speed being around the same, there is a difference.
While games are teh most pronounced difference, it's still there with other apps. Comparing Office to an old text mode Wordperfect app is meaningless. Ok, maybe for what you do you don't notice any difference, but many of us do. As a simple example, take a highly accurate, learning, in-line spell checker. I love that feature. Well, guess what? That takes resources. You couldn't do that on a really old computer, it just lacks the resources.
So if you are happy with what you have now, great, stick with it, but don't get mad that people want to find ways to use the new power. I do not buy a new graphics card to get higher and higher frame rates, 60fps is enough thanks that's all my screen does. I buy it for more an more features, at the same framerate. Likewise with processing in my computer. Everything is plenty fast now, my computer responds near instantaneously for normal tasks. So what I want is for my computer to do more. I want it capable of doing more complex things. In 1996 my computer played little postage-stamp sized videos, and used nearly 100% CPU to do it. Now it plays fullscreen HD videos and uses nearly 100% CPU (well ok, of one of the cores) to do it. I'm not pissed that it hasn't changed, I'm pleased with the increase in quality, the increase in features.
I take it those 2.8GHz Xeons were based on the old Netburst Architecture (P4). ;-)
AMD did better with the Opteron, but the new Xeon 5100 are Conroe-based.
Conroe vs. Netburst = massive improvement
C - the footgun of programming languages
Not really, in nature (-30+i)nm cores always appear along side (-30-i)nm cores in what we call conjugate pair processors.
The good stuff is AM2-only: 65nm and virtualization extensions.
When do we say enough is enough and just stop this cancerous shrinkage? How small do transistors really have to be?!
At roughly the 10nm mark (if I recall correctly), at which point a MOSFET will no longer exhibit transistor-like behaviour due to quantum tunneling across the body.
That's actually not true... As Intel introduced new CPUs going into the 775 socket, they started using more and more of the pins that were originally "reserved" -- so, in order to support a new CPU, certain additional pins would have to be tied high, low, to calibration resistors, etc. What that means is that while *older* 775 CPUs will run fine on new motherboards, the new 775 CPUs will not run on old motherboards, even with a BIOS flash.
For example, my 775 board running a P4 3GHz will only take P4s up to 3.4GHz or so, since the faster ones were new 65nm cores with slight pin changes. Pentium D, and newer Cores are also in the excluded category..
Never underestimate the bandwidth of a 747 filled with CD-ROMs.
I'd rather see less dense microprocessors. The problem is this big chip manufactuerers make these super dense mammoth race car processors, it concentrates heat in one place, requiring a CPU fan, which is a mechanical component that can and will eventually fail.
I would rather have a motherboard with a CPU design distributed, where the surface area is spread out in such a way, that is completely solid state without any moving parts to fail, namely, a CPU does no require active cooling.
The future lies in completly 100% solid state devices. What does this philosophy mean?
No CPU fans, no power supply fans, no harddrives (flash memory instead), no noise, no moving parts whatsoever. Distributed or minimized waste heat.
Reliability and shock resistance skyrocket. You can seal them inside waterproof and dust proof and fire proof boxes.
I've implemented these kind of computers, at critical network points, and literally you can plug them in FOR YEARS and forget about them.
They are absolutely silent. And absolutely low powered. And totally reliable. All of which, is a very beautiful thing from an engineering standpoint.
These guys need to hire me on their team, because the definition of what is going to be expected in computers is going to radically change in the near future. Computers are going to go under, they are going to become *embedded* in everything with no expectaions of mainenance to them at all and installed in harsh environments. They either work or they fail after decades of use (or preferably, never), and then you replace them.
Reliability is CORE, and to achieve it, computers are going to have to abandon all cruches and become purely solid state devices entombed in indestructible plastic modules.
How often have you ever reformated the drive on your wrist watch? Had to reinstall an OS on your cellphone? Had to replace the CPU fan on your calculator?
I often wondered, why in heck weren't motherboards encased in protective plastic casing, and the same for ISA / PCI / AGP / PCI-x cards. Putting a comptuer together today has become like putting together lego blocks. And each component should be as equally durable and interchangable based on standards as a lego block.
Einstein
http://anarchy-tv.com/
I was EXTREMELY pleased and happy when Intel finally took over the CPU market again with the claim of most powerful consumer CPU. AMD had been at the top for a slight bit too long...after all, what good is competition in a free market if one side is ALWAYS better?
This means AMD is trying even HARDER to make a better chip...it will release, and in a way I am hoping that it STILL isn't better than Intel. Intel continues down it's path and continues to hold the crown for the next couple years.
Then, AMD reclaims it, pushing innovation and the need to claim to have "the fastest" will be reheated again. And next time, who knows...maybe ANOTHER upstart will come around (although I doubt that) that will challenge BOTH Intel and AMD.
I am an AMD fanboi. I have bought nothing but AMD CPU's since the days of the K6, regardless of the power of other procs on the market. And yet I am still very happy Intel is holding the crown. Nothing breeds innovation like having the knowledge that the OTHER guy took the number one spot from you.
Living With a Nerd
While it would be nice to think this is correct, the fact is after looking over a period of weeks, I can't find /any/ benchmarks other than yours that support this claim. (Yes, before some ninny points out the obvious, I'd been researching before you posted this, in preparation for a new laptop purchase -- otherwise it couldn't have been weeks.)
This migration of socket requiring a new CPU and all has bitten me already. My S939 parts barely lived a year (two years given the entire lifetime) and already AMD is requiring me to buy a new motherboard *and* CPU if I wish to upgrade because they're already killing off S939.
Which is funny, because for years this was a commonly cited problem with Intel's platform, while AMD's Socket A was long-lived and stable. One would expect a company to copy their competitor's successes, but to copy their mistakes? I'd wager that this is a temporary glitch in AMD's roadmap and that they are going to try to re-stabilize. I bet they were just flummoxed trying to work out their socket strategy in the face of having to address several markets they weren't serious competitors in prior to K8 and of having to deal with their changing memory interface needs -- Socket 939, for example, only existed because they realized they wanted dual-channel memory in the client space, but the 940-pin Opteron package wouldn't support unbuffered DIMMs. Oops! So 939 was a hack, and I'm not surprised it's short lived, though certainly it sucks for those hoping to upgrade -- a.k.a. the do-it-yourself hobbyists that have been AMD's main supporters since K7. Double oops!
The enemies of Democracy are
::tries to remember what a one of the drawers in his workstation looks like:: Let's see...got a GeForce MX440, a Voodoo 5500, a Monster 3D(!), a Canopus Pure3D(!!!), an ATI 9800 PRO, and a BFG 6800.
Anyone care to donate a couple mobos? We could have a killer Warcaft II LanParty (the 9800 and 6800 could EASILY do WarIII...the others? Most likely not...)
Living With a Nerd
It's amazing that you think most benchmarks aren't skewed by corporate greed or rampant fanboy loyalty.
Also vector optimizations are not well suited to most crypto tasks. Raw ALU power is which is why there is a huge diff from the Pentium 4 to any of the other chips.
If you're really that naive, get yourself an AM2 and C2D setup and time shit yourself.
Tom
Someday, I'll have a real sig.
That's exactly what you would expect in a demand-driven market: the price is based on actual performance. Maybe buyers really do know what they're doing after all. I guess most chips are bought by either OEMs or computer nerds and neither group is going to be fooled by marketing terms or misleading specs.
Prov 9:8 Do not rebuke mockers or they will hate you; rebuke the wise and they will love you.
I own all of those boxes. [well the E6300 is an E6600 now].
The Core 2 Duo *is* a nice chip, but in terms of raw ALU performance it's no better than an Opteron (hint: it's a similar 3-pipe ALU). The FPU is a bit faster because it's natively 128-bit, but that's about it. The extra cache mostly makes up for the lack of a memory controller.
Where the C2D *does* shine is power consumption. Compared to the 90nm parts from AMD the C2D parts are much cooler, take less power, and are way easier to overclock.
Most benchmarks today are fabrications designed to peddle people over to highly advertised ladden web pages. I seriously doubt if more than half of all published benchmarks ever took place.
Tom
Someday, I'll have a real sig.
if (UID>100000) { print "Don't make two slashdot jokes in one post"; } else { print "ahahaha"; }
To expand... when speaking of single cpu, yeh, it doesnt make much difference (even with multiple cores) since there is still only one controller, but when looking at multiple CPU's on the same board, you effectively have now 4 memory controllers, giving each CPU full bandwidth to the ram, while a multi-cpu Intel system has to share the same bus/controller. When comparing something like a Dell Xeon quad to a Sun quad Opteron (with dual-core option on each cpu) this becomes a rather important feature, specially when looking for a good database server (and damn are these SUNs fast!).
tm
Support TBI Research: http://www.raisinhope.org
Unfortunately, since my best box is an X2 4800, I can't answer any of that directly. All I (and most people) have to go by are the various published benchmarks. And unfortunately, stating that they're fabrications doesn't prove the fact. I would be interested in seeing something that supports that.
What are the right numbers Mr. Even-Smartassier?
I love when AMD has to invent specific test conditions to win via marketing.
"Testing all day."
"Typical usage model."
*yawn*
Get back to us when you have a better design, and not a better marketing department.
https://www.accountkiller.com/removal-requested
Support? Sure => http://libtomcrypt.com/ltc113.html
... hmmm ...
...
... Also keep in mind the scale. Often you'll see huge differences in the bars and it could amounts to a 1% difference in performance (which any stats class would tell you could be lost in the noise).
Oh wait... you saw that already
Look sparkles!!! Believe what you want. Just keep in mind the "diversity" of tests they run, like "Content Creation" and "Multimedia" and
It's been QUITE a while since the last benchmark included things like thread creation, compile times, crypto operations, etc.... I wonder why that is
I'm not saying all benchmarks are shite, just that most aren't very thorough or scientific. They just run [or claim to] a suite of boxed tests and post the results. They don't actually crack out the standard deviation and other stats to tell you what the results actually mean.
And if you're "best box" is an X2 4800+ then shut your gob, that's a decent processor. What are you doing where you're really hurting for more performance anyways?
Tom
Someday, I'll have a real sig.
we _had_ laptops that had 18+ hours of battery life, then we threw out the battery life for more processing power.
Luxury. My laptop would run out of power 45 minutes before I started it, explode, stab me to death with bread knives and then dance about on my grave singing Hallelujah. And that was if we were lucky!
I drank what? -- Socrates
Gosh! What about -40?
I drank what? -- Socrates
Your mom looked in my shorts!
I drank what? -- Socrates
oohhh nooo.... he reversed the polarity!!!!!!!!!!!!
I wish S939 had a longer lifespan but hey, AMD engineered the Athlon64 well enough that at least I was able to upgrade my Athlon64 3800+ to a X2 4800+ by just replacing the chip. I'd say AMD's platforms are twice as long lived as Intel's. AM2 platforms are supposed to be able to accept AM2 and AM3 CPUs. That's good platform longevity!!
Wood you stop needling him?
I drank what? -- Socrates
- Intel puts twice as much L2 cache on their dies as does AMD for their high-end parts. The high-end Intel part has 4MB, the high-end AMD part as 1MB per core for a total of 2M.
- Intel's L2 cache architecture is "shared", meaning that when you're running a single-thread benchmark, the single core on which the benchmark is running basically has access to the entire 4M L2. This is significant because it now means the single core running on an Intel part has 4M of L2, whereas on AMD it has 1M. This is quite a nice feature for Intel's single-thread performance.
- In 32-bit x86 mode, there are 8 general purpose registers (GPRs). That means spill/fill code (which certainly hits in L2 and almost certainly hits in L1) is a lot more common. In other words, memory ops are more common. Intel, with the C2D, introduced a more aggressive out-of-order memory architecture, basically allowing any memory op, even with an unresolved address, to execute out of order, fixing it up later if there was a problem. This really, really helps with memory ops, especially the common spill/fill ones going to the (cached) stack. In 64-bit AMD64/EM64T code, there are more GPRs for the compiler to play with, so you have less spill/fill code and fewer memory ops, which mitigates C2D's advantage here. That's one of my theories on why 64-bit performance of AMD vs. Intel chips is closer (the other, which isn't a theory, is Intel's lack of a 64-bit-capable IOMMU, causing the OS to use bounce buffers for DMA to high-addressed main memory).
What I'm basically saying here is, C2D's larger cache and more-aggressive load/store architecture are really helping it for certain apps. My guess is that the libtomcrypt benchmarks are run in 64-bit mode (mitigating Intel advantage point #3 above) and either a) fit entirely in the L1 or L2 of both processors, nullifying any cache advantage C2D has, or b) fit in *neither* of the L2 caches, and is significantly larger than 4MB, which lets AMD's faster on-die memory controller make up for its lack of L2.Socket 939 is not totally dead. Check out the 939 based opteron x2's. The you can get a new opteron 165 x2 for about $150 and it screams after a little overclocking. I just picked one up from newegg and could not be happier.
T or X series Thinkpads still rock. My T40 is almost 4 years old, has taken a lot of abuse and I have no intention to replace it.
[an error occurred while processing this directive]
The best example I can think of is (on Solaris, but it applies to Linux and Windows as well) is the web. NCSA Mosaic (yes I used it) was a nice, clean browser, that had very few features. No tabs, no flash, no java, no javascript, etc. It was great at displaying hypertext though, and even supported some simple features like inline graphics and various fonts etc. (And could use helper applications for things like audio, postscript, etc.) Back in 1993 this configuration ran comfortably on a Solaris machine with as little as 16 MB. (On Linux, even as little as 8 MB.)
... and... etc. So now firefox typically is consuming ~1GB RAM, and I periodically have to restart it just to convince it to give me back some memory.
... it crashes fairly consistently for me.)
.... and all that stuff sucks up machine resources like crazy. :-)
Fast forward to today. Now we have tables, flash, java, and that "goodness" (for some value of "goodness"). Oh yeah, and caching, lets add that to boost speed up. And alpha blended PNGs, and
Is this annoying, hell yes!
Do I want to go back to using NCSA Mosiac? Hell no! (There is Opera, but well, that's another issue
A lot of these features add little value beyond aesthetic appeal, but we've become used to them, and frankly, most users are unwilling to go backwards to get them.
I will remind everyone that FreeDOS 1.0 is available, and you can download older versions of Linux and such, so that you can run your ancient software on the latest platforms, and see it go blazingly fast. But even so, most people won't like the result -- the masses want eye-candy, and ease of use, and
FWIW, I think some of my "largest" contributions to projects I've worked with have been "negative lines of code". I.e. by simplifying a project or removing redundant/duplicate code, I've probably removed many thousands of lines of code from the operating systems projects I've worked on. But program managers and marketdroids dont' care about that -- they can't sell "runs in 20% less memory than the last version" as easily as they can sell whatever new feature they're hyping.
Intel introduced the Pentium Extreme Edition 955 chip on the 65 nm process in December of 2005, and in a volume processor, the Core Duo, in January 2006. If AMD will have their 65 nm processor in Q1 '07, that puts them 12-15 months behind.
If they're 18 months behind on 45 nm, then they have a real problem... That actually puts them farther behind Intel than they are now.
Unless they mean they plan on being at 45 nm within 18 months of TODAY. Which, if Intel's roadmaps holds accurate as well, would have AMD only about 6 months behind Intel.
Unfortunately for AMD, Intel is not only getting their 45 nm process done, they're also working on their next-generation core, Nehalem. Which means that by the time AMD comes out with 45 nm of their current architecture, Intel might already be onto a more efficient core.
Another non-functioning site was "uncertainty.microsoft.com."
The purpose of that site was not known.
That's funny, cause 2 years ago I got a 2.2Ghz A64 3400+ in a 15.4in lappy, and it gets over 2 hours of battery life. Then again, it underclocks to 800MHz when unplugged because the manufacturer said so.
I have a Dell Inspiron 9100. Full P4 hyperthreaded. I'm not sure what Dell claimed, but I can't make it through a single DVD movie before it's gone, and that's with the upgraded battery.
Learn to love Alaska
Only if you cripple the AMD chip, and run it in 32-bit mode. In 64-bit mode, it performs FAR better.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
When Intel can sell me a Core chip for the price of a Sempron, give me a call.
You're upgrade ability will depend on what you want to upgrade. AM3 will use DDR3 RAM so current AM2 processors will not work in this socket (which is pin compatible if I recall correctly). You will however be able to plug AM3 processors into an AM2 board. The processor memory controller works with both DDR2 and DDR3.
intel chips are running cooler and faster than amd's. desktop and server.
Better performance? By a lot of benchmarks yes, but it's not as big a gap as a lot of people want to make out. Cooler? No evidence for that whatsoever, unless you read Intel's marketing literature. Their Pentiums alone took down the National Grid.
Once Intel puts the memory controller on-die like AMD has, it's going to *really* hurt AMD.
Like I said. AMD has a better architecture.
Perhaps once we all have 8+ core chips on our desktops, you might see some HT advantages, but I believe I read somewhere that Intel has plans for on-die memory controllers and an answer to HT
Like I said. Better architecture. HT works much better as memory sizes grow, and guess which way memory sizes are going?
Sure, performance per watt can be better, but i tend to look at absolute values instead when i measure current.
I have an "old" athlon 64 3400, which handles my current load fine. How much power does it consume at idle and under full load? My guess is that it consumes less than these new chips, or very close. If someone has found out these values, please post them.
Open Source Java Web Forum with LDAP authentication
fact: intel runs faster than amd, mhz for mhz
Many benchmarks show just how Intel have improved in terms of performance, and have a slight lead in what those benchmarks show. However, Intel still has no memory controller on the die. They still have nothing to rival HT. But megahertz for megahertz. Sorry, no facts there.
fact: intel runs cooler than amd, mhz for mhz
No evidence for that either, unless you read Intel's marketing literature. The fact is, considering that Intel had such a poor reputation for this (deserved) they had to make it look good.
AMD has a better architecture for somethings, less so for others, and for right now, and for probably the next 12-24 months, Intel has better performance (on the desktop). AMD's architectural superiority will go away once Intel gets an on-die memory controller and something to compete with HT - which is very conveniently timed by Intel to be around the time that advantage would actually come into play (on the desktop). For now, AMD may have architectural supriority, but it lacks the actual real-world performance advantage (in a big way). AMD is going to have to do a hell of a lot more than just a die-shrink to surpass Intel again, and Intel isn't sitting still. By the time AMD's 65nm process is mature, Intel will start to churn out 45nm chips, so it'll start all over again, and by then, Intel will be looking at on-die memory controller and their own HT tech. AMD is going to have to some up with something HUGE, and K8L ain't it.
The chips aren't behind. AMD is behind. The semiconductor manufacturers keep scaling down based off the leader which has always been way ahead of AMD. (NOTE: we are speaking of manufacturing leadership based on the smallest feature in the chip (not necessarily the performance of the CPU (and it matters even if there isn't a performance imporvement (which there usually is) because you can make more for the same amount of money and if they are better, then you can sell them for more too))). AMD is behind because Intel sold more than 40 million microprocessors on the 65 nm manufacturing nade before AMD sold even one. So they are little behind.
I'm running a 14", Core 2 Duo T7400 with 2GB of RAM, everything (including OpenGL/Beryl and wireless, bluetooth is detected but I haven't tested it) running perfectly and natively under Kubuntu 6.10 on a Compal HGL-30 from powernotebooks.com.
My blog. Good stuff (when I remember to update it). Read it.
I got sick of buying new hardware just to open the same document because the O/S or new Office suite was bloated/full of shit/required way more horsepower just to do the same task. No Vista for me. I'll stay will XP and Linux on my (older) machines. And if MS forces people to go Vista, I'll go Linux or BSD. If I get new hardware, it will be to make these systems faster, not make new software, doing the same job, run the same speed.
Golly shucks, I sure agree with you! All this newfangled crap is sooooo worthless. Why, my 80486 SX/33 with 8 MB of RAM runs MS Windows 3.11 and WordPerfect just dandy, thank you! I've stayed away from them overpriced Pent - eh, what's that again?
What is this "Vista" you speak of?
I have no problem with your religion until you decide it's reason to deprive others of the truth.
I 'wood'n't know about that. Oops, time to clock out; I have to 'leaves'.
I drank what? -- Socrates
Why would you make veiled personal attacks on my intelligence when I make the point that new programs should be coded in a way to not only add benefit, but do it efficiently so as to not require a more powerful system? Or another way, programmers should not always rely on better and faster hardware in order to release new code.
Or did I miss something? Are you really running Windows 3.1 still? No no, I get it. You were being clever! Now wasn't that cute of you.
-- I ignore anonymous replies to my comments and postings.
You try and tell the young people of today that... and they'll never believe you.
Gravity is a contributing factor in nearly 73 percent of all accidents involving falling objects. -Dave Barry
Same for AMD.
Meanwhile, a price drop was announced by AMD around July 14 specifically stating the following:
So when AMD was trouncing Intel in 32-bit (and 64-bit) mode, it was AMD's strength... Now it is their weakness? Also, running 64-bit programs doesn't automatically mean massive performance increases... it isn't like it runs 2x as fast because 64 = 32 * 2. For reasons why, there are numerous discussions on the 'net as to why.
Intel puts twice as much L2 cache on their dies as does AMD for their high-end parts. The high-end Intel part has 4MB, the high-end AMD part as 1MB per core for a total of 2M.
Back when Itanium was sporting both impressive SpecFP scores and also gigantic caches, I wondered what would happen if you put a cache that size on a mainstream x86 part -- specfp is really more about cache size and memory bandwidth than it is about the floating point execution units, so I never bought the specfp rating as being due to an inherent advantage of itanium. Well, now we know.
While not very exciting architecturally, big caches are certainly a good way to boost performance. Intel gets those huge caches because of two things: First, they have the fab tech and fab capacity to produce gigantic chips with good yield and still make money. Second, Intel has the smallest cache cell size in the industry. So they are uniquely positioned to put big caches on mainstream parts, and they are taking advantage of it.
Intel, with the C2D, introduced a more aggressive out-of-order memory architecture, basically allowing any memory op, even with an unresolved address, to execute out of order, fixing it up later if there was a problem.
Slight correction on a very fine post: Memory ops that have their address are allowed to go out-of-order even if there are older ops which do not have their address (meaning in the case of an out of order load and a store without its address a possible forwarding case that will have to be fixed once the store gets its address). It doesn't make any sense to have a memory op go without its address, because you couldn't really do anything with it (without something like an address predictor).
The enemies of Democracy are
No, I don't want any bloody Jelly Babies! Stop offering them to me!
For #3, you are certainly correct about the IOMMU issue. There is a good reason why they suffer more so in 64-bit mode, the Core 2 Duo chips support "macro-op fusion" (I think, something like that anyway!) in 32-bit mode ONLY, so this performance advantage is lost in 64-bit mode which further degrades performance.
Seriously, google it, I have an M6811, and when I unplug it it magically turns into an 800MHz box, cpufreq be damned, lol.. I can still play quake3 or watch movies when it's like that though :)
What are you talking about? 32-bit was never faster than 64-bit mode.
There are never any guarantees. However, the VAST MAJORITY of programs benefit, and CPU-intensive applications in particular almost always benefit from it.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
consumption is a much larger issue this time around for my nue laptop. I just got a new HP Turion X2 that has a battery life of about 2 hours. If i am working, less then a hour. -Not even a full movie i bet..
My last HP notebook about 7 years ago got about 4.5 or 5 hours even with the modem running~~
A recent review i read noted the Panasonic Toughbooks being one of the best (i agree, dope machines in deed) They were getting about 4 hours. All the other duel core get approx. 2 hrs or worse. -Now i'm finding myself tethered by a power cord more than a network cable, and that is just fuct./ (!) -very interested in the wireless power info these days.
also solar/inverter manual crank/peddle/pump push/pop whatever...
Kill your TV
My point is this:
Do you remember when Windows 2000 was "good enough"?
Do you remember when Windows 95 was "good enough"?
Do you remember when Windows 3.x was "good enough"?
Do you remember when DOS 5.0 was "good enough"?
I remember all of these stages. The point is not that older software is more or less efficient, or that you are mentally deficient. (I don't actually think you are, BTW) The point is that the bar is constantly changing.
In a year or two, you'll probably be using Windows Vista. Just like you'll probably be driving a different car, and the jacket that you have today that's "good enough" will fall prey to newer stock.
It IS stupid to declare that the newer thingy represents no improvements - what you are really saying is that "Windows XP meets the bar" without acknowledging that the bar will change. New games come out that require DirectX upgrades. Office documents require newer versions of Office. Browsers come out that no longer work with your "old" Windows XP. Printer drivers come out that no longer support Windows XP.
Over time, the utility of your O/S becomes mitigated by a thousand minor factors, as it had long ago with Windows 3.11.
I have no problem with your religion until you decide it's reason to deprive others of the truth.
That's no laptop, it's a piano.
https://www.eff.org/https-everywhere
It depends on the chipset. nForce4 boards aren't forward compatible, but AFAIK, all 865 and 875 chipset motherboards will accept a 4 core. I can't get the Asus page to load right now, but I'm pretty sure I remember seeing that all of their Core 2 Duo motherboards will support the Core 2 Quad.
https://www.eff.org/https-everywhere
AMD is supposed to ship 45nm in 18 months...and if Intel ships 45nm towards end of '07, that leaves AMD roughly 6 months behind. AMD has been used to lagging Intel in process technology, so I don't see how this is anything new.
It was very interesting that despite Intel moving to 65nm earlier (i.e. Presler, Pentium D), AMD still held the performance crown for quite a while afterwards, despite the fact that it was a 90nm implementation...the K8 design was simply that much better. Now that Intel finally got off their ass, they've got the better design with C2D. Needless to say, '07 will be an interesting year for microprocessors.
S939 was killed because of the shift to DDR2. A downside of having the memory controller on the CPU.
Pretty sure the next-gen quad-core AMD CPUs will be compatible with the AM2 socket. At least, they've said so as recently as Sep 2006 interviews.
Wolde you bothe eate your cake, and have your cake?
Let me guess, you work in the auto industry where the same design with MINOR changes is pushed out year after year with no improvements. In the computer industry, progress is being made, and process technology advances are a part of that.
The key is that by shrinking, the amount of power required goes down, which means you can either add more features, cache, or you can increase the speed of the chip.
A Tech Report article on AM2 chipsets shows that the nForce 590 chipset consumes about 20 watts more than the ATI RD580 (CrossFire XPress 3200) chipset at load. However, the power-hungry nForce 590 chipset has more integrated features: 2 gigabit ethernet chips (RD580 has none), 6 SATA ports (RD580 has 4), and more RAID options. That's probably why most high-end CPU reviews I've seen have used the nForce 590 chipset.
An Anandtech article shows that the Intel 975X chipset consumes about 3-5 watts more than the more current P965 chipset for certain apps, but unfortunately they don't have "load" comparisons. The P965 chipset lacks SLI support, so that's probably why reviewers are using 975X.
So a comparison of platforms that "most people buy" should probably use the Intel P965 chipset and the nForce 570 Ultra chipset. It's too bad review sites tend to use the SLI uber-chipsets.
TO START
PRESS ANY KEY
Where's the 'ANY' key? I see Esk, Kitarl, and Pig-Up...
Most disappointing to me is that the heat dissipation of the E6300 really isn't better than AMD, despite the 65nm and the Pentium M heritage. I suspect that this is because SOI prevents a lot of electon leakage. This makes me think AMD's SOI 65nm will be a whole lot more efficient than Intel's non-SOI.
But for someone who needs a low-end dual-core, the 4200 and the E6300 are about the same on every apples-to-apples comparison, so take a look at motherboards and let that make the decision for you. If you go with Intel, make sure you get a mobo that can overclock. The 6300 can take it.
You must have a less recent model than I do. My laptop's batteries last until a rootkit is successfully installed allowing hackers access to my machine, then the batteries explode, destroying the game system that I paid four digits and got mugged for.
I don't believe you
All this is a big yawn. Two important metrics: Frame rates and http://www.spec.org/cpu2006/results/ / http://www.spec.org/cpu2000/results/ .
Also, you want to save big on power, try making mass storage solid state or holographic. Who cares about faster CPUs at the moment when memory needs to get faster and less latent and less reliant on pipelining and more geared towards faster random access and throughput along with faster mass storage without moving parts.
AMD: Losing in SPEC after having a huge lead and having the superior HyperTransport architecture (direct descendant of the EV7 bus from Alpha's glue-less SMP).
AMD is now a partner with WildTangent, what a joke. http://www.theinquirer.net/default.aspx?article=3
Also, AMD bought ATI and is seriously de-focused - I'm deeply saddened that Intel wont be getting the same level of competition as before because it seems to me AMD/ATI are not headed in the right direction.
PS: Ever notice Intel "VIIV" is VI IV or 6 4 in roman numerals? Lol, right.
I'm no Intel shill, but these new Conroe/Woodcrest CPUs, well, try them out. You'll see.
Legalize the constitution. Think for yourself question authority.
Oxymoron Alert !
Maybe he does, but he'd be better off with Schrödinger's notebook.
t es/1933/schrodinger-bio.html
a t
http://nobelprize.org/nobel_prizes/physics/laurea
http://en.wikipedia.org/wiki/Schr%C3%B6dinger's_c
The tyrant will always find a pretext for his tyranny - Aesop
Nothing Intel does with regards to marketing is different in kind than AMD's approach. They may differ in the extent to which they push a specific strategy, but they both have the same sorts of plans on the table.
The history of the general purpose CPU marketplace has shown time and again that sometimes next generation processors aren't all they're made out to be. Itanic, anyone?
So... is certainly a false statement (not to mention, that I've seen 32-bit faster on the same code and can easily construct samples of (non pathological) code which demonstrate 32-bit compiled x86 code that runs faster than the same code compiled in x86-64 mode.
I've written (and helped write) and profiled a number of 32-bit/64-bit applications and have compared the performance in each mode. Sometimes it's a win, sometimes it's about equal, sometimes the 32-bit compiled version wins. Most of the time, the benefit is less than 10% except in specific cases where lots of temps are being used, where you can take advantage of the increased number of registers (but that would also help in 32-bit mode if they were available, unfortunately they aren't) or where you're actually using 64-bit integers (remember, the FPU has been 64-bit for a long time already so don't much of a gain there unless you can use the extra registers).
Writers of applications like Cinebench9.5 have already stated that their gains were as much as being able to "throw away" all the 'compatibility' code (SSE vs FPU and having to support both and such), because x86-64 doesn't support it, so that the x86-64 code is much more clean plus the benefits of using the additional number of registers for calculations. Granted, this *is* an inherent benefit on the x86 systems from moving from x86 to x86-64 but it isn't necessarily a generality that you can extend to all 64-bit environments.
OK, you've got me here... a 1% to 10% speed improvement *is* most certainly showing that many programs do benefit from the x86-64 architecture over the x86 architecture.
Similarly, I found my workload to be dominated by a few intensive applications (some of which I was writing) which made my single-core Athlon64 cry out in pain. I upgraded to an AMD X2 and saw an almost doubling in my productivity in such situations... not that I'm unfamiliar with SMP (and some large SMP machines and how they give benefits)... it's just the first time I've actually decided to buy one for my personal use at home.
Thanx for the correction. I guess that's what I get for relying on a quick Google search to confirm the name.
There is no "I disagree" mod for a reason. Flamebait, Troll, and Overrated are not substitutes.
Itanic was certainly marketed as a next generation chip. But rather than argue whether it was or not, I'll just point out that aside from the example you yourself listed there are many others as listed in my subject line. Those are the ones I can think off the top of my head.
You had it easy. In my day, we didn't have batteries, so I had to do all of that myself. And play Taps at the funeral.
--
Promoting critical thinking since 1994.
According to your informative post below, we've only got connects 200 atoms wide, not "a few" as the GP was asserting. The point still stands, the atoms are not *that* constrained.
Well... when you can't lead in performance, you try to lead somewhere else. Yes, the launch of Core2 parts drove AMD to cut the prices of their processors by 50% or more in order to stay competitive. Had they not done that, they would be selling nothing right now because even a fanboi couldn't justify buying AMD at the complete destruction that equal priced CPUs from AMD would get compared to the Intel parts. So, AMD dropped back to attempt to remain king of the bargain market until they could release something that would put them back into the performance game, which Intel currently owns (not counting the obviously boutique, one-off 4x4 deadend attempt to save face that AMD marketing released).
I don't think that you understand "bargain market". At the moment, Intel is still trying to push Pentium 4's and Prescott based Celerons against AMD's Sempron and Sempron 64. AMD has nothing to worry about here.