×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Core Duo Reaches the Desktop

Zonk posted more than 7 years ago | from the back-in-the-race dept.

299

rtt writes "AMD has long reigned the desktop CPU market due to Intel's offerings struggling to keep up in terms of performance and power consumption. Yonah is the predecessor to the Core architecture and is predominantly a mobile chip, and is used at the heart of Intel's Viiv technology. Bit-tech has an article about Yonah beating the top of the range desktop AMD chip, the FX60, clock for clock. From the article" 'When Yonah is running at the same clock speed as AMD's Athlon 64 FX-60, we found that it beat it into a corner in just about every situation.'"

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered

299 comments

Lies! Lies and slander! (2, Funny)

generic-man (33649) | more than 7 years ago | (#15367072)

I'm sure AMD would beg to differ. [slashdot.org]

Re:Lies! Lies and slander! (2, Interesting)

pimpimpim (811140) | more than 7 years ago | (#15367258)

I was hoping that your link would lead to some statement of AMD on this comparison on the slashdot venders site, but there doesn't seem to be one. Or at least, none that I can find. Can you give the exact link, I would be happy to read an other side of the story. Or where you just trying to make some vague statement on how AMD supports slashdot and we should be pro-AMD even when they are not in front of intel concerning CPU power.

In any case, I don't know how much this new intel is better or not, but I wouldn't mind that much. When any of those two manufacturers make a chip that's "better" than the other's, well, then let the other manufacturer improve their product! All good for us in the end, it's at least a good thing to know that AMD can't just stop developing now, because they have intel's breath in their neck. That means more fancy stuff to be expected, yay!

Personally I'll just buy the one with the best performance/price and performance/power-usage ratio.

PRICE:PERFORMANCE, THE RATIO & YOU (2, Interesting)

DRAGONWEEZEL (125809) | more than 7 years ago | (#15367488)

It's how I have obtained everything I have on a meager income. (1> meager 100000)
For instance when I bought my car, I spent about 10 hours researching. I saved over $4000 off of sticker, and 70000 miles later I am still a happy camper! that was between 12-18% off the price. My time was worth $400 /hr. 5x what I bill my clients, and 17x what I make hourly.

How to buy anything.
1. Set a realistic budget for the item you wish to purchase & save money for it
2. Do research on the best Price:Performance
        a. Look up your options, consider items that are similar, look at diferent brands.
        b. Compare reviews
        c. Don't spend so much time researching that your savings is no longer worth it. (don't spend tons of time looking how to save 10 cents on dryer sheets!)

3. Look for a reputable vendor for said product.
4. Make purchase, and enjoy without feeling guilty about what you spent!

Thats why I purchased an AMD x2 4400
and an nvida geforce 7900 gt. Great games performance / Excellent multitasking

Smokin like the tires on my car!
   

Re:Lies! Lies and slander! (1)

geekoid (135745) | more than 7 years ago | (#15367546)

I think he was joking, and that you were just itching for an excuse to post that.

Already on the desktop (4, Informative)

daveschroeder (516195) | more than 7 years ago | (#15367074)

Apple is aready using the Intel Core Duo T2500 in the iMac [apple.com], and the Core Duo and Core Solo in the Mac mini [apple.com].

Based on these and other benchmarks it would appear that Merom ("Core 2 Duo", the next generation portable processor, Conroe (the next generation desktop/workstation processor), and Woodcrest (the next generation workstation/server processor) will have quite a bit to offer.

Re:Already on the desktop (0)

Anonymous Coward | more than 7 years ago | (#15367145)

The Core Duo is also in the MacBook / MacBook Pro - my understanding is that they're not actually using the 'laptop-oriented' Yonah, but the 'desktop-oriented' Core processors in their laptops.

Re:Already on the desktop (0)

Anonymous Coward | more than 7 years ago | (#15367356)

Yonah == Core.

Re:Already on the desktop (1)

Guy Harris (3803) | more than 7 years ago | (#15367405)

The Core Duo is also in the MacBook / MacBook Pro - my understanding is that they're not actually using the 'laptop-oriented' Yonah, but the 'desktop-oriented' Core processors in their laptops.

Your understanding is incorrect. The only Core processor currently available is Yonah - Intel Core Duo and Intel Core Solo. (There's also a Yonah derivative, Sossaman, called the Dual-Core Xeon LV, but that's not used in any Apple machines.) Conroe is to be the "desktop-oriented" processor, but it's not out yet, and it - like the "laptop-oriented" Merom - will be called Intel Core 2 (Duo and, perhaps, Solo).

Re:Already on the desktop (1)

chrismcdirty (677039) | more than 7 years ago | (#15367459)

I believe the dual core desktop Intel chips are Pentium D, Celeron D, and (maybe) Xeon D.

Re:Already on the desktop (1)

Trepalium (109107) | more than 7 years ago | (#15367583)

The Celeron D isn't dual core. It's just a Prescott core Celeron with 256KB of L2 cache. The dual core Xeon variant is the Xeon 7000-series. Rather idiotic marketing in my opinion, unless their goal was to hopelessly confuse potential buyers.

Re:Already on the desktop (0)

Anonymous Coward | more than 7 years ago | (#15367434)

What's the going rate for being a shill these days? To think that you being so passionately in love with a company that would sue you in a heartbeat is pretty funny.

Apple astroturf fanboys (0)

Anonymous Coward | more than 7 years ago | (#15367572)

They just re-work Steve Jobs' talking points for the day.
Others on the payroll come by later and mod them up.
Bottom line is "Intel and Apple beats AMD and Unix" is bullshit.

AMD kicks Intels ass.

Just ask Dell.

every situation? (4, Insightful)

Anonymous Coward | more than 7 years ago | (#15367123)

mp3 encoding and other floating point workloads are quite common. AMD wins hands down there.

Re:every situation? (2, Interesting)

flobberchops (971724) | more than 7 years ago | (#15367555)

Since most MP3's are downloaded, this is not an issue :) AMD lost the consumer (ie., non geek brand fanbois) market to Intel. I always used AMD now after my AMD laptop is a hairdryer , opening a browser turns the AMD fan on non stop. They are a joke in the power consumption efficiency market. Merom beats AMD into a pulp. Im going Core 2 Duo on my laptops in the near future, not AMD.

Wake me up when it supports 64-bit (4, Insightful)

RelliK (4466) | more than 7 years ago | (#15367125)

When it supports AMD64 instruction set, it will be worth a look. Until then who cares?

Re:Wake me up when it supports 64-bit (-1, Troll)

Anonymous Coward | more than 7 years ago | (#15367164)

Exactly what kind of 64 bit processing are you doing? You'd have to be a complete idiot to be using 64 bit on anything other than a server.

Re:Wake me up when it supports 64-bit (4, Funny)

MarkByers (770551) | more than 7 years ago | (#15367184)

You'd have to be a complete idiot to be using 64 bit on anything other than a server.

32 bits should be enough for anyone.

Re:Wake me up when it supports 64-bit (0)

Anonymous Coward | more than 7 years ago | (#15367238)

'You'd have to be a complete idiot to be using 64 bit on anything other than a server.'

32 bits should be enough for anyone.


I completely agree! And you'll never need more than a few megabytes of harddrive storage!

Re:Wake me up when it supports 64-bit (0)

Anonymous Coward | more than 7 years ago | (#15367266)

Other than e-penis, why would anyone (today) with the status of 64 bit software as it stands want to use a 64 bit OS / drivers / programs. ?? I think people like 64 bit because the number is twice as big as 32 and because they are AMD fanboys. Maybe in a year or two 64 bit will be feasible on the desktop

Re:Wake me up when it supports 64-bit (1)

ebyrob (165903) | more than 7 years ago | (#15367369)

Other than e-penis, why would anyone (today) with the status of 64 bit software as it stands want to use a 64 bit OS / drivers / programs.

Because they're faster.

Several parallelizeable operations can be done faster using a 64-bit architecture than a 32-bit architecture. While it is a bit silly to run 32-bit programs on a 64-bit architecture or to buy a 64-bit architecture and forever run it on a 32-bit OS, 64-bit programs on a 64-bit OS will outperform their counterparts in several important instances. Once we have [pcstats.com] 64-bit optimized programs it'll be silly not to be running a 64-bit processor...

Yeah. (1)

Penguin Follower (576525) | more than 7 years ago | (#15367481)

On my Athlon64 3700+, I decided to try out 32 vs 64 bit in their current state using Gentoo Linux. I setup two hard drives, one had everything compiled 32bit, and the other hard drive I had 64bit. I didn't think there would be any difference for everyday desktop use, but the system did feel a tad more responsive over all. I would like to do that again, this time as a server. Like SQL maybe. That's where the biggest difference would be as of right now.

Re:Wake me up when it supports 64-bit (1)

tomstdenis (446163) | more than 7 years ago | (#15367602)

I currently have 4GB of memory. Along with the 1GB of PCI space that's 5GB of addressable memory. I also plan to add another 2GB to the system.

This is in a 2P workstation in my house [and yes I use it fairly well]. I run windows in a QEMU environment [that's 1GB of memory] and do a lot of parallel builds (e.g. make -j5) which can suck back the memory.

On top of that there are architectural benefits to 64-bit mode. You basically do away with segments [it's all done through paging]. You get 8 more GPRs and XMM registers which despite the lame troll-fud are actually useful.

I run Gentoo, so all my software is compiled with the latest C compiler on my box. I'm not running 64-bit Linux and 32-bit userland tools like you might in the Windows world.

I'm not exactly a millionaire here, even though I got the CPUs for free I still had to buy a mobo/ram/case/etc. If I can put something like this together I imagine a lot others could do something with 270s in their own systems.

Tom

Re:Wake me up when it supports 64-bit (0)

Anonymous Coward | more than 7 years ago | (#15367406)

This is a legitimate argument, but I generally buy my PCs knowing what I'll plan on using my computer for the next 2-3 years, 64-bit is not going to be making waves on the desktop any time soon.. People who need high powered workstations, I could see some applications start going 64 bit (CAD, etc.), but really, its nothing to care about right now.

When the time is right and it comes time to make that decision, I'll look at 64-bit processors.

The PC you have now will never "be enough" at all times. Eventually it will go obsolete. There were times when 640k of memory was indeed enough for everybody. Eventually, as time goes on, you'll upgrade when you need to.

Re:Wake me up when it supports 64-bit (2, Informative)

WhiteWolf666 (145211) | more than 7 years ago | (#15367300)

MP3 Decoding and Encoding, as well as Video Decoding and Encoding, are significantly faster in AMD64 mode than i386.

Of course, if you want proper end-to-end AMD64 software you'll need Linux.

AMD64's performance improvements are a reality on Linux, today.

Some benchmarks:
http://enterprise.linux.com/enterprise/05/06/09/14 13209.shtml?tid=121 [linux.com]

Some more benchmarks, on XP!:
http://www.pcstats.com/articleview.cfm?articleid=1 665&page=6 [pcstats.com]

There are many, many, many more out there. If you're doing math-intensive things, AMD64 out performs i386. It's irrelevant whether its the larger address space or greater number of registers; either way, it works better.

Re:Wake me up when it supports 64-bit (0)

Anonymous Coward | more than 7 years ago | (#15367466)

That's a silly thing to say. Running in 64-bit mode gives more registers, and the 64-bit extensions include the NX bit. There are benefits to 64-bit mode other than addressing more than 4GB of memory space.

Re:Wake me up when it supports 64-bit (0)

Anonymous Coward | more than 7 years ago | (#15367552)

Real-world bioimaging. We (the people in my lab who do the gooky work) can generate data sets much larger than a 32-bit address space can handle. A single mouse, imaged at 10 microns/voxel can run > 30GB. Be nice to load the entire set at full res, rather than have to do funky paging of the voxels.

Re:Wake me up when it supports 64-bit (2, Insightful)

myurr (468709) | more than 7 years ago | (#15367211)

Not only is this chip 32bit only, it's also dual core as opposed to the FX60's single core, its been built on a 65nm process unlike the FX60's 90nm, and the FX60 is actually starting to show it's age a little bit. I big giant "Duh" springs to mind at this point.

Re:Wake me up when it supports 64-bit (2, Informative)

cixelsyd (239) | more than 7 years ago | (#15367255)

FX-60 is a dual core processor, just for the record.

That would be the Conroe (3, Informative)

Sycraft-fu (314770) | more than 7 years ago | (#15367230)

AKA Core 2 Duo. Not sure on offical launch date, November I think. At any rate it's their high performance chip based on the Core design, targeted at desktops. Faster and has EMT64 (Intel's name for the x86 64-bit extensions). Limited testing on it at this point, since it's still engineering samples only, but AnandTech found it to be about 10-30% faster than a 2.8GHz Athlon X2 (http://www.anandtech.com/showdoc.aspx?i=2713&p=1) .

Re:That would be the Conroe (1)

Guy Harris (3803) | more than 7 years ago | (#15367461)

At any rate it's their high performance chip based on the Core design

Confusingly, Intel's using "Core" in products using both the Pentium M microarchitecture (Yonah, a/k/a Intel Core Duo/Solo) and using the new Intel Core Microarchitecture (Conroe and Merom, a/k/a Intel Core 2 Duo and perhaps Solo).

I.e., Conroe's and Merom's microarchitecture is significantly different from Yonah's, even though they both have "Core" in their names.

Here's who cares: (1)

Chordonblue (585047) | more than 7 years ago | (#15367268)

Vendors that are tired of AMD's focus on the high end of everything. Go ahead, look for a low end AMD processor. You won't find one anymore. AMD is all about Opterons and X2's now. My local and loyal AMD computer shop here just went to Intel for their low end machines. The prices Intel is offering low end chips for is a real bargain and hard to pass up no matter how big a fan you are of AMD.

You might think that the low end isn't all that important, but remember, it's how AMD got it's foot in the door.

Re:Here's who cares: (1)

jsoderba (105512) | more than 7 years ago | (#15367312)

I'm guessing AMD is still limited by manufacturing capacity. Building new cutting edge manufacturing fabs is very expensive, and it takes a while for AMD to save up for new ones. If they can't play in both the low and high ends, the more profitable high end is obviously preferable.

Re:Here's who cares: (1)

Chordonblue (585047) | more than 7 years ago | (#15367370)

Oh I don't doubt that at all, and I actually agree with AMD's position on this! But that's not going to help those who need those lower end processors. They will go elsewhere - even the most dedicated AMD shops will eventually need to do something to fill in their low end machines. AMD simply cannot match the enormous capacity Intel has at it's disposal. Even if their processors aren't better, they are cheaper and with most PC purchases that's all the customer seems to care about.

Re:Here's who cares: (1)

tomstdenis (446163) | more than 7 years ago | (#15367559)

This is bullshit. AMD still sells Sempron processors of all sorts. While it's true it seems focus is on dual-core that doesn't mean cost will always go up. As transistors get smaller the cost of doing dual-core goes down.

Generally the power of dual-core parts is actually not higher than single core parts. A 65W chip is a 65W chip.

Tom

Re:Wake me up when it supports 64-bit (1)

DrXym (126579) | more than 7 years ago | (#15367364)

Until Linux rules the world or Microsoft produce a 64-bit version of Windows that actually works seamlessly, I think 64-bit instruction sets are overrated. I say this as someone posting this message on an Athlon 64 X2 3800+.

I really, really hope that Microsoft intends to allow XP32 to be upgraded to Vista64.

Wake me up when software supports 64-bit (1)

flyweight_of_fury (972871) | more than 7 years ago | (#15367387)

When OTS software supports 64-bit processors, they'll be worth a look. Until then who cares? --see I can play too...

Re:Wake me up when software supports 64-bit (1)

tomstdenis (446163) | more than 7 years ago | (#15367535)

ALL of my software is 64-bit. (Except openoffice)

Did I mention I run Gentoo? :-)

So yes, all my software can use the extra registers and is in a proper flat memory model. ... and yes my box has more than 4GB of addressable memory...

Tom

It's a play on words. (4, Insightful)

insomniac8400 (590226) | more than 7 years ago | (#15367129)

"When Yonah is running at the same clock speed as AMD's Athlon 64 FX-60, we found that it beat it into a corner in just about every situation." If this is true, it would be the first time intel made anything better than amd. But in the end, all that matters is that AMD's $200 chip outperforms intel's $200 chip.

Re:It's a play on words. (5, Insightful)

anagama (611277) | more than 7 years ago | (#15367181)

It's worth noting that the comparison is between the FX-60 running at factory speed, and a Core Duo running overclocked.

Re:It's a play on words. (1)

anagama (611277) | more than 7 years ago | (#15367398)

Here is an article with an overclocked FX-60 [xbitlabs.com]. It's hard to make direct comparisons between the articles but look at the quake results. In the Bit-Tech Core Duo article linked in the summary, Quake 4 1280x1024 high quality: FX60 gets 119.5 fps and overclocked T2600 gets 124.4.

In the article I linked to, quake 4 at 1024x768 high quality, base FX60=162 and when overclocked, 173.6. In other words, overclocking the FX60 gives 106.8% the performace over factory settings on this test.

Going back to the article cited in the summary, multiplying the FX60's score from the Bit-tech article by the overclocking boost from the overclocking article suggests that an overclocked FX60 could be expected to score 127.6 fps.

Obviously, it's not all so simple, but there is an obvious bias in an article that fails to compare overclocked chips to overclocked chips.

Re:It's a play on words. (3, Insightful)

spleck (312109) | more than 7 years ago | (#15367413)

It's worth nothing that the comparison is between the FX-60 running at 2.6 GHz, and a Core Duo running at 2.6 GHz. Hence the clock-for-clock comparison. I think they were trying to compare architectures, for which I thought the article did a good job. I learned that the Yonah is nice, but can't do 64-bit or FPU operations well.

Actually, I already knew that, but I still looked at the benchmarks.

Re:It's a play on words. (1)

Senjutsu (614542) | more than 7 years ago | (#15367415)

It's also worth noting that the Core Duo, over-clocked, was still running at a slower frequency than the FX-60 at stock speeds.

Ergo, it beat the tar out of the Athlon, clock-for-clock.

Re:It's a play on words. (1)

drinkypoo (153816) | more than 7 years ago | (#15367474)

Get back to me when it can beat the tar out of the Athlon dollar-for-dollar and I'll be impressed. As we know, clock speeds mean precisely jack shit. All I care about is performance per dollar, and performance per watt.

Re:It's a play on words. (2, Interesting)

Anonymous Coward | more than 7 years ago | (#15367185)

Thats the thing, the FX60 is AMD's highest FX chip, and it starts at $990 on pricewatch and over $1000 on froogle. Pricewatch isnt listing core duos yet, but froogle has this model (duo T2600) startng at $640.

If you dont need the 64 bit stuff, this looks like a pretty good deal.

Re:It's a play on words. (1)

EdipisReks (770738) | more than 7 years ago | (#15367327)

"If this is true, it would be the first time intel made anything better than amd" hardly. the Pentium was better than the K5, the Pentium 2 was better than the K6 and K6-2, the Katmai Pentium 3 was better than the K6-3, the Coppermine Pentium 3 was better than the original Athlon, and the Northwood Pentium IV was better than the Athlon XP. remember that it is only very recently that AMD has come out on top, Intel generally made faster chips than AMD for the majority of their shared history.

Re:It's a play on words. (0)

Anonymous Coward | more than 7 years ago | (#15367360)

Faster in Ghz, but not in benchmarks.

Re:It's a play on words. (0)

Anonymous Coward | more than 7 years ago | (#15367517)

I can't speak for all of those claims but I can speak for most of them. AMD did not start getting their foot into the door until they came out with the K7 series (Athlon). Intel really was king for quite a long time.

Re:It's a play on words. (0)

Anonymous Coward | more than 7 years ago | (#15367565)

Yes, I know before the thunderbird chips, AMD lagged a bit behind. I have older AMD cpus, their 486s, K-6s and K6-2. Back then, they were just cheaper, not better performing. At about the 1Ghz range, they were equal performers for cheaper, and when the XPs came out, they were ahead, then Intel would put out a faster processor, then AMD would beat it, and it was a constant game of catchup for both companies. Then 64bit cpus came about, and intel just hasn't been able to grab hold of the lead again. Maybe these future chips will do it, and force more innovation from both companies.

Re:It's a play on words. (1)

Falkentyne (760418) | more than 7 years ago | (#15367487)

Apparently you weren't around when the 486 was brand spankin new. AMD was NOT the choice if you wanted a good chip. Course.. that shit was expensive - even after the pentium came out my brother picked this beauty up: Micron Intel 486DX4-100 8MB RAM 800MB HD 4X CDROM 14" CRT (1024X768) 1MB Video All this for only $1700!

TCPA watch? (0)

Anonymous Coward | more than 7 years ago | (#15367141)

So does this thing come with a TCPA trusted computing module / treacherous computing module / terrorist computing module, or not? It seems to be almost impossible to figure out which computers these days do and don't have TPM...

Over the top (5, Insightful)

Rorian (88503) | more than 7 years ago | (#15367152)

I think they go just a bit overboard in saying that Yonah beats the FX-60 "into a corner".. Most benchmarks had it either infront or behind by around 2-3%. Is it really worth forking out a few hundred dollars for such a dismal gain in performance? Does it have better performance-per-watt? That's what really seems to count these days anyway.

Re:Over the top (1, Insightful)

jsoderba (105512) | more than 7 years ago | (#15367383)

Is it really worth forking out a few hundred dollars for such a dismal gain in performance?
The Core Duo is expensive, but have you looked at what AMD is charging for the FX series? Intel wins on price/performance by a mile. On the other hand, they're overclocking the Intel CPU a hell of a lot and running the AMD CPU at stock speed, so it's not exactly a fair comparison. Still says a lot about what we can expect from Core 2, though.

Does it have better performance-per-watt?
What? We are talking about the Core Duo here, the most efficent x86 CPU on the market.

Match on Desktop perhaps but not as a workstation (3, Interesting)

HighOrbit (631451) | more than 7 years ago | (#15367187)

From TFA:

Core Duo solves a lot of the short comings, but there is one major feature omission from Yonah's architecture: it doesn't support Intel's EM64T 64-bit extensions

and later:
The lack of 64-bit extensions may be a worry for some, as will the poor FPU performance - the latter showed up in our MP3 encoding test.

So if you are doing anything with a 64-bit, high memory, or FPU requirement, AMD still wins.

Until Conroe (2, Insightful)

SuperKendall (25149) | more than 7 years ago | (#15367252)

Yes, until Conroe arrives later this year.

Until then the consumer space really doesn't need 64-bit processors for most work people do.

Re:Until Conroe (1)

drinkypoo (153816) | more than 7 years ago | (#15367449)

What happens later this year that makes people need 64 bit processors, just in time for intel's new processor release?

Why did they overclock the Core Duo? (2, Interesting)

WhiteWolf666 (145211) | more than 7 years ago | (#15367214)

I don't understand the articles' conclusions.

Athlon X2 4800+ stock > Core Duo at stock clocks, in 32-bit mode.
Athlon X2 4800+ stock Core Duo at stock, in 32-bit mode.
Athlon FX-60 stock http://www.pcstats.com/articleview.cfm?articleid=1 845&page=2 , it is possible to run the Athlon X2 4800+ at 3.14 ghz , which is a 30% overclock, albeit with a very serious cooling solution. I'm wagering that at that speed it would flatten the overclock Core Duo, especially if you permit 64-bit optimizations, which DO noticeably increase speed on several programs in Linux. Please don't whine about not having a 64-bit OS; those of us in the Linux world can choose 64-bit or 32-bit at will.

Now, I'll admit that the Intel's Performance per Watt is significantly better. But it ain't faster.

Re:Why did they overclock the Core Duo? (0)

Anonymous Coward | more than 7 years ago | (#15367311)

64 bit in Linux is not the performance boost you think it is. It's compiling properly to use the CPU's extra registers that makes the difference!

Re:Why did they overclock the Core Duo? (1)

WhiteWolf666 (145211) | more than 7 years ago | (#15367320)

Wow slashdot kills brackets.

AMD X2 Stock Faster than Core Duo Stock.
AMD X2 Stock Slower than Core Duo Overclocked.
AMD FX-60 Stock Faster than Core Duo Stock.
AMD FX-60 Stock Slower than Core Duo Overclocked.

Re:Why did they overclock the Core Duo? (0)

Anonymous Coward | more than 7 years ago | (#15367682)

You missed the important part of their conclusion which explains why it was overclocked:

"When Yonah is running at the same clock speed as AMD's Athlon 64 FX-60, we found that it beat it into a corner in just about every situation."

In other words, they weren't trying to compare the performance of specific processor models agains each other. Rather, they were trying to compare the performance efficiency of the architectures in general.

I'm not sure how fair the comparison is...whether any of the buses were overclocked in the process or anything, but that was their logic.

Dubious Test (3, Insightful)

cait56 (677299) | more than 7 years ago | (#15367224)

As near as I can determine from reading the article, it proves that a Core Duo *slightly* outperforms an Athlon 64 XP2 when doing heavy number crunching with a 32-bit Windows application.

Comparing the same application build for 64-bit on Linux vs. 32-bit on Linux (or BSD) would have been a far more meaningful comparison.

Re:Dubious Test (0)

Anonymous Coward | more than 7 years ago | (#15367464)

Why?
Heavy number crunching is heavy number crunching, regardless of the platform. As such it is compiler and hardware limited, not OS limited.

Re:Dubious Test (1)

Broken Bottle (84695) | more than 7 years ago | (#15367468)

Whether or not the test is dubious is debatable, but the test you suggest doesn't have much application to the average user. How many FPS Far Cry turns out on a Core Duo on Windows XP is much more meaningful to Joe Six Pack when he wants to see which gives him more bang for his buck.

Re:Dubious Test (0)

Anonymous Coward | more than 7 years ago | (#15367571)

Waaa! Waaa! The test isn't fair! AMD rulez!!!11

I wondered when the fanboys would start discrediting the test. AMD's days of having the best performance are over. Face it.

Wait a minute... (4, Informative)

thebdj (768618) | more than 7 years ago | (#15367236)

First, I would hardly say it is beating it. The numbers are all close, but most the processes they are running are almost running into other limits beyond processing speed at this point. The differences are not that great and the chip still loses (and much more then it whens other tests) in anything that is single threaded.

The other thing we need to remember is pricing. I was checking prices the other day for 4200+ processors and D950 processors. While almost exactly the same price, right now the AMD would still be much cheaper because of RAM price differences (especially if you get large RAM sticks, I am looking for 2x 1GB) and motherboards. Find motherboards for AMD and Intel that I believe were equal in features had the Intel motherboard almost $20 more then the AMD one.

Now, while I cannot attest for the power consumption on Intel right off, AMD is releasing more energy efficient processors with the AM2 release, due in just a few weeks. There should also be a slight (5-10%) performance increase based off of information from reviews of the processors and boards while still in development (improvements may be better in production models), so I would not call this a win for Intel yet.

I am glad that Intel finally seems to be catching up with AMD, which hopefully will only lead to better competition between the two over time. I really do not like these speculative reviews (remember those Opteron 64-bit reviews before the first Athlon64s hit), so someone wake me up when Socket AM2 and its processor are out and the new line of Intel chips is actually available and not just a ramped up Yonah. Especially since the cost of the motherboard they used makes you want to cringe. (I have yet to have to break $100 on my motherboards.)

Just shows how selective statistics can lie (5, Insightful)

jmorris42 (1458) | more than 7 years ago | (#15367267)

Ok, Intel is getting some game, 'bout freaking time. But this isn't an "AMD killer" by any means.

Notice how they only included ONE FPU intensive task and AMD (and several of the Intel products) schooled this mobile offering? Most reviews include a lot more balanced set of tests, this one obviously had their storyline written for them and was tailoring the tests to fit the plot.

And also, let us not forget that the STOCK benchmark numbers for this chip were anything but impressive, so they played up the overclocked numbers. However, while this chip does have some seriously intersting overclock potential it isn't the first chip to be massively overclocked. Just last week we were salivating over a budgie Intel chip that somebody overclocked into the world's fastest CPU. So why not include THAT firebreathing monster's numbers on the chart along with some seriously overclocked AMD parts? Perhaps that would't have had such a dramatic narrative? Ah.

Meanwhile, I'll keep comparing parts running at factory spec and waiting to see what AMD drops next week to compare current gen parts to current gen parts.

Re:Just shows how selective statistics can lie (1)

Ignignot (782335) | more than 7 years ago | (#15367501)

It is relatively easy to improve FP performance with a small investment of die space and power. The reason it isn't so good is that this is a mobile computer, so it doesn't really need high peformace FPU's. A desktop version would probably have comparable performance, but probably not significantly better than AMD's.

I thought the real issue with overclocking the Intel chip is that overclocking it was very easy given a stock heatsink and fan - that means that intel can sell the chips at a higher speed with literally no difference other than the voltage the cpu operates at.

And I know the slashdot crowd loves AMD - and I loved their chips for the last few years - but it looks like now the value / performance is strongly in intel's favor, or will be by this fall.

Re:Just shows how selective statistics can lie (1)

HoboMaster (639861) | more than 7 years ago | (#15367589)

I want to see how the overclocked Core Duo compares to a stably overclocked FX-60, which can also be easily done with the stock heatsink and fan. Seems if you're overclocking one, you should overclock teh other a comparable amount.

Re:Just shows how selective statistics can lie (0)

Anonymous Coward | more than 7 years ago | (#15367540)

Notice how they only included ONE FPU intensive task and AMD (and several of the Intel products) schooled this mobile offering? Most reviews include a lot more balanced set of tests, this one obviously had their storyline written for them and was tailoring the tests to fit the plot.

It's ironic that now folks are saying FPU isn't as important... when they were saying the complete opposite at the start of the Pentium line (and AMD's FPU sucked then).

Re:Just shows how selective statistics can lie (0)

Anonymous Coward | more than 7 years ago | (#15367712)

Looks to mee that many still says that FPU is important, because they now have to defend AMD. I don't think FPU is important, but it was to some degree important for Quake at the time Pentium got good FPU performance.

What the heck is "Intel's ViiV technology?" (5, Funny)

dpbsmith (263124) | more than 7 years ago | (#15367285)

It seems to be one of those mysterious things like IBM's "SAA" or Microsoft's ".NET" or Vitalis' "V7..." .

It's a secret miracle ingredient about which all that is clear is that you're supposed to think it's good without needing to know what it is, exactly, or what it does, or why it's good.

Intel says: With Intel Viiv technology, you control a highly integrated Intel platform designed for digital entertainment. That means you can: Take charge of your media. Share experiences with movies, photos, and music with your friends and family. Simplify your digital life.

It's sort of like saying "Texaco gasoline has CleanSystem3, which will help you score with hot chicks."

Will somebody please explain to me what technical characteristics of a processor allow you to "share experiences with movies, photos, and music with your friends and family?"

Unless that means it doesn't support DRM?

Re:What the heck is "Intel's ViiV technology?" (1)

Tibor the Hun (143056) | more than 7 years ago | (#15367455)

Will somebody please explain to me what technical characteristics of a processor allow you to "share experiences with movies, photos, and music with your friends and family?"

Think of Viiv as a loose certification standard. If the system meets certain specs (Fast HD, fast ram, certain processor speed) then the system gets the Viiv designation, and you can be fairly certain that you can take advantage of your digicam toys you've spent a small fortune on.

So, Viiv is not a CPU name, it's like a standards designation. (I think that all started with Centrino -- it wasn't just the CPU, it was the CPU and wireless and such stuff.)

I think it's a good effort. Takes the focus off the MHz war, and steers it on the useability of the PC.

But then again, I use a Mac, and don't really concern myself with not being able to burn home movies, or organize my images, since my 1.4GHz G4 excels at those tasks. (At the same time. And then some.)

Re:What the heck is "Intel's ViiV technology?" (4, Insightful)

mrchaotica (681592) | more than 7 years ago | (#15367724)

Unless that means it doesn't support DRM?
On the contrary, it means that it does support DRM. And not just DRM, but Treacherous Computing. In hardware.

That marketing blurb should read:
Intel says: With Intel Viiv technology, we control a highly locked-down Intel platform designed for protecting publishers' "Intellectual Property". That means you can: Let us take charge of "your" media. Share experiences with movies, photos, and music with your friends and family if we let you. Complicate your digital life.
It's 1984-style DoubleSpeak.

hrm (2, Insightful)

Silicon Mike (611992) | more than 7 years ago | (#15367309)

So.. What they are saying is Intel's latest and greatest CPU is finally gonna beat something AMD released, what, 5 or 6 months ago? Intel is STILL playing catch-up.

Re:hrm (0)

Anonymous Coward | more than 7 years ago | (#15367653)

Core duos have been out for sometime. Notice that Core 2 is the one that's coming out. It's supposed to be a better version of Core Duo.

And yes, I can't say I'm surprised by all the Intel bashing that goes on. If it ain't AMD it has to suck, right?

And before I get bashed as an Intel fanboy, I am running on an X2 3800+ that's overclocked. It's true Intel didn't have much to offer over the last good while. But now that they do, I don't think it should be automatically poo-pooed.

Sham (5, Interesting)

Short Circuit (52384) | more than 7 years ago | (#15367336)

You know, I like the Core Duo, and would love to have one in a laptop or on a desktop. (If Debian isn't ready for x86-64, then x86-64 isn't ready for me.)

Probably the most impressive thing is that the T2600 out-guns Intel's flagship Pentium Extreme Edition 965 processor, even with the massive clock speed deficit. After effortlessly overclocking our Core Duo to 2.6GHz, it beats AMD's flagship Athlon 64 FX-60 into a pulp.


As others have pointed out, the Core Duo only beat out the Athlon64 FX-60 when overclocked. If the chip, when overclocked, was safe for production environments, then the chip would have shipped at a higher default clock speed.

The whole tone of the article is wrong...it seems more interested in Intel than in technology. Notice that the "most impressive thing" is that the Core Duo chip does better than a high-end Intel chip. The only negative thing they mention in the article is a reminder that AMD's AM2 architecture is supposed to come out next week.

They're misrepresenting the product. I have to wonder if they were paid for this review.

Re:Sham (0)

Anonymous Coward | more than 7 years ago | (#15367640)

"They're misrepresenting the product."

I don't think so. They clearly state what the purpose of the test is. It shows that Intels Yonah have higher IPC than AMDs CPUs. And since Merom/Conroe/Woodcrest will have even higher IPC than Yonah and will ship at up to 3Ghz this fall, things are very interesting. We will see a major leap in performance which we haven't seen since the P6 architecture was introduced in the 90s.

Re:Sham, but don't forget it's mobile (0, Flamebait)

WillAffleckUW (858324) | more than 7 years ago | (#15367684)

one should also point out that it's designed as a mobile chip, but for some reason they used as a desktop chip.

My question is: what's the bottom line in Power Usage, Heat Usage (have to run those fans or add weight for heatsinks), Price (Intel is generally more expensive), etc.

[caveat - I own Intel shares and don't own AMD shares]

Core Duo Speeds (3, Funny)

digitaldc (879047) | more than 7 years ago | (#15367349)

When Yonah is running at the same clock speed as AMD's Athlon 64 FX-60, we found that it beat it into a corner in just about every situation.

In other words, the Athlon 64 ran fine - it just needed a bit more time to cache up to it.

Re:Core Duo Speeds (2, Funny)

geekoid (135745) | more than 7 years ago | (#15367502)

You know, /. mod system has always been screwy, but that post getting marked up insightfull, and not funny, is obsurd.

Overclocked (0)

Anonymous Coward | more than 7 years ago | (#15367465)

The authors of TFA had to overclock the Intel chip for it to beat the FX-60 or even the 4800+. For a fair comparison, if they overclock one vendor's chips, they should overclock the other vendor's. Based on stock performance, AMD would have won then. This is even in 32-bit where only the Intel chips can use all of their abilities.

This is ridiculous. Core Duo is a great processor, but it by no way tops AMD's highend offerings as far as speed goes.

If you want to argue power management or performance per watt, that's another story, but TFA was a pure speed benchmark.

AMD has long reigned the desktop CPU market due (1)

geekoid (135745) | more than 7 years ago | (#15367469)

if by 'long' you mean 'the past few years' then yeah.
If you are comparing it to the history of the desktop CPU, then no it ahs not been long. Looking at some market factors, I would guess temporary might even be a better word.

Don't get me wrong, I like the competition in the market. This mean AMD helps keep the price of the good chips^H^H^H^H^H^H^H^H^H^H Intel chips down.

Enter obligatory comment (5, Insightful)

Temujin_12 (832986) | more than 7 years ago | (#15367479)

Entry obligatory AMD zealot, "intel can't possibly make something better then AMD" comments here _______.

Seriously, I'm sick of the overly zealous statements when it comes to "OS vs. OS" "Company vs. Company" etc. debates. Why is it so threatening when another companies/organizations happen to produce something better than your favorite company/organization?

Sometimes intel will get it right and sometimes AMD will. Deal with it.

Ya, I know. This is probably eligible for flaimbait and/or troll mod points. Oh well, I just needed to get this off my chest.

Re:Enter obligatory comment (1)

tomstdenis (446163) | more than 7 years ago | (#15367630)

The only problem I have with these stories is that they assume the competition is asleep at the wheel.

Intel may be catching up and beating AMD in certain areas today but to then extrapolate and say Conroe will beat AMD assumes that AMD is not going to release any new product.

Tom

Re:Enter obligatory comment (1)

WinterSolstice (223271) | more than 7 years ago | (#15367664)

It's probably because most geeks aren't really into sports. You'll see these same discussion with football fans - sometimes to an absurd degree. It's just a "team" or "side" thing.

Me? I like stuff that works, doesn't cost too much, and is likely to keep doing what I bought it for long into the future. Right now I have Apple machines, an XBox 360, a PS2 and a Nintendo 64. Obviously consoles have always switched around for me - I don't play "teams" with them. Desktops are similar, but Apple has held my interest long enough for my PCs to have all found better homes. (4 years now). Don't worry - at some point Linux/MS/NewOS will come along and I'll switch to them. After all, I came to Apple from Debian/RedHat/Windows, and to that from FreeBSD/OS2/DOS, and to that from VMS/Irix.

-WS

Let's Get A Few Things Straight about Yonah (4, Informative)

Shuh (13578) | more than 7 years ago | (#15367541)



Yonah = "Core Duo/Solo"

Conroe, Merom = "Core 2 Duo/Solo"

The Woodcrest, who knows?

Conroe, Merom, Woodcrest = "Next Generation Architecture" = "Core Architecture"

Although Yonah is the "Core Duo/Solo," it is not actually part of the "Core Architecture."

Capisci?

When is it enough? (1)

shummer_mc (903125) | more than 7 years ago | (#15367759)

I'm not a gamer. My computer runs fine with my XP2100+. I may upgrade to the 35W dual core 3800+. Not for performance, but for power usage/heat dissipation. However, I'll wait until the Core 2 Duo is released so that the prices will be lower :)

Unless something crazy happens, I don't think that I'll need anything faster (ever). My machine is already faster than me in all but network bandwidth and file IO.

The server market is where it's at...

Slightly tilted conclusions... (0)

Anonymous Coward | more than 7 years ago | (#15367766)

Hold on. The Core Duo "creams" the Athlon64 FX by 2%-3% when overclocked? First off, last I checked this is within the margin of error of most benchmarks. Once again, I would like to plug the notion of better statistical validity in benchmarking. Rather than just giving us a single number, they should be giving us the average AND the standard deviation range, because if one part isn't beating another by at least a std dev unit, it just isn't accurate to say one part "beats" another. In fact, the difference will hardly be noticable at all until you get at least a couple of std dev units out.

Anyway, leaving that off, the other issue is that, last I checked, the only way to overclock an Intel processor is to overclock the FSB (and hence memory). So is this performance gain (assuming it's real) really due to CPU architecture, or is it because of the bus overclock? Because when the "real" part running at these speeds is released, you can bet it wont be on an overclocked bus! 2%-3% performance difference could easily be achieved by overclocking the Athlon's memory/HTT and lowering the multiplier to keep the CPU frequency the same.

Wake me when the clock for clock performance delta is > 5%-10%, then I'll buy one processor is "creaming" another. Early indications are this will indeed be the case with Conroe. On the bright side, a competative Intel can only be beneficial, because it'll force AMD to stop resting on the laurels of their K8 architecture and start making real improvements again. In the end, we as consumers can only benefit.
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Sign up for Slashdot Newsletters
Create a Slashdot Account

Loading...