AMD Launches Counterstrike Against Core 2 Duo

DigitalDame2 writes to mention a PC Magazine article about the AMD 4x4 enthusiast platform, which is meant to counter Core 2 Duo. The article observes that AMD is now facing many of the same business practices it used in its war against Intel. From the article: "While imitation may be the sincerest form of flattery, improvement can often be a slap in the face. Intel's C2D was designed with both low power and performance per watt in mind, two key design metrics that helped AMD cut into Intel's market share with the Athlon 64 and Athlon 64 X2. And, as preliminary numbers have indicated and final performance reviews now show, the C2D has learned its lesson well: its performance now tops AMD's Athlon 64 architecture by a substantial margin."

4X4 is more a marketing ploy than anything else

[Harry Balls]

4X4 sounds more like a marketing ploy to me than like a feasible solution for Joe Average or even Joe Gamer.

Why?

Consider the cost of Athlon X2 processors:
http://www.pricewatch.com/cpu/442067-1.htm [pricewatch.com]
The least expensive Athlon X2 costs a cool 300 bucks, while the mid-range Core 2 Duo (Conroe) E6600 costs $315 (projected wholesale price).

Now factor in a more expensive (because of 2 processor sockets) 4X4 motherboard, two Athlon X2 chips at $300, and you wind up with a $350 to $400 surcharge for being an AMD fanboy.

The situation gets worse if you want a high-end system:
Two FX-62 will set you back $1045 + $1045 = $2090
http://www.pricewatch.com/cpu/992212-1.htm [pricewatch.com]
and while this combination is expected to outperform a single Core 2 Duo at $1057
http://froogle.google.com/froogle?q=E6800&btnG=Sea rch+Froogle&lmode=online&scoring=p [google.com]
factoring in the more expensive two-socket motherboard expect to pay a cool $1100 more than for the E6800 system.

Personally, I'll probably buy an E6600 ($315) or an E6400 ($240) as soon as they become available.

umm? comparison to Intel please...

[sofar]

but does it perform better than core 2 duo? I fail to see any performance test between them, and it's also AMD having the bigger market share right now, not intel. Seems like a lot of AMD FUD nowadays... AMD is no longer the underdog here.

Performance improvement?

[Atroxodisse]

Not if you ask hard OCP http://enthusiast.hardocp.com/article.html?art=MTE wOCwxLCxobmV3cw==/ [hardocp.com]

Re:Part of the vicious cycle in Tech

[andrewman327]

I don't see why we're talking about flattery and being slapped in the face. It seems that AMD and Intel are competing more directly than in the past, which could ultimately be good news for consumers. By reducing power (/. reported on congress' urge to reduce power consumption earlier) these chips save money and run very quickly. Now that both parties are fighting for efficiency and other similar things, they will have to pull out some amazing science to directly compete instead of simply bosting that their paradigm is superior.

Performance number?

[Soybean47]

FTFA:

AMD also plans to push a sort of "performance number" into the market to redefine how consumers should think about power, they said.

Doesn't AMD already label their processors with a relatively meaningless number designed to... say... redefine how consumers think about processor speed?

Was that a highly effective marketing technique? I mean, I guess it did get people to think about speed, and it helped convince many people that GHz isn't the be-all and end-all of processor comparison. But at some point won't people just be annoyed by the mess of pretend numbers AMD is throwing around to "make us think?"

Re:Part of the vicious cycle in Tech

[Uryene]

...A cycle I learned my lesson about many, many moons ago.

At home, I keep a $640 check I wrote back in 1990 for a 486 CPU.
It's framed and visible on top of a bookcase to serve as a reminder.

At the time, I thought it was a great deal; screaming processors were
never going to get much cheaper than that!

These days, last years tech (or even two years ago tech) is usually
MORE than sufficient. Except for games, which always seem to
need NEXT years processor in order to be playable... ;-)

Ah, but you can fudge the number of cores...

[Dr. Zowie]

... as did Intel with their previous round of patched-up dual-core machines. The reason AMD's multicore is so much better than Intel's is because AMD provided a much better caching architecture. Intel's 64-bit multicores could be compared to a large V-8 engine stuck behind a tiny VW carburetor -- totally starved for data. AMD's multicores effectively shared one anothers' L2 caches (a big win), and achieved lower latency on RAM fetches (another big win).

If the two giants start to compete on core count, you can bet your family farm that there will be fudging going on over cross-communication, latency, and RAM bandwidth.

Re:Intel leading with heat and watts

[C_Kode]

You noted how you changed (3) Intel servers with (4) GBs of ram for a single AMD server yet you left out a TON of information about the AMD. What and how are the disk connected compared to the Intel boxen. Secondly, how much ram does this 64-bit AMD have? (16GB?)

We had (2) IBM servers (Dual AMD 64-bit Opteron) with 12GB ram each running 32-bit RHEL3 and Oracle 10g. Because it was 32-bit RH it was only using 4GB in each server. We upgraded the RHEL3-64 and Oracle 10g 64-bit (using all 12GB of memory in each box) and we got about 140% improvement on the same hardware.

What was the difference? 8 more GB of ram each. The fact that a single server has 12GB of ram and all queries happen on a single server makes a HUGE difference than have (3) servers with only 4GB of ram as the database can cache more data in memory.

While I don't know your *true* setup, I can say that a single server with a TON of ram will kill many servers with only a little bit of ram on simple select statements. CPU doesn't do a whole lot on select statements compared to what it will do on say stored procs or all kinds of subselects/joins/aggregate functions in your select statements.

Re:"well.. my dad can beat up your dad!"

[uop]

Well, having the strongest offering usually does count for something (especially if you ask the marketeers).
The 4x4 initiative basically looks like DP for the desktop, which Intel offers as well (although Xeon only).

imho, the really interesting thing about 4x4 is the possibility of plugging in a coprocessor in the future.
For example, you may settle for a single Athlon64 X2 in a 4x4 board for now, and add a physics/video/dsp/whatever coprocessor in the future.
That's wild speculation, of course, but it does make the 4x4 setup intriguing as a future-proof product.

--

65nm

[Azarael]

My question is, how would the comparison stackup once AMD finally releases 65nm chips? Everyone knows that Intel has the best fabs, but I'm curious to see what happens when AMD catches up further in that area.

Re:65nm

[Aadain2001]

About the time AMD does, Intel will be moving towards their 45nm or 40nm or whatever their next smallest size is. Intel has the best fabs for a reason: they invested a LOT of money into fab R&D just after the bubble burst. They called is their One Generation Ahead strategy. While everyone else was trying to cope with the loss of capital and drop in stock prices, Intel want to make sure that they came out one generation of silicon manufacturing ahead and stayed that way. While they have in some respects (physical size of transisters) they have missed some advances in some other areas (SOI). In the end, Intel will probably stay ahead of AMD until they hit the physical wall on the size of transistors (can't go smaller than an atom!).

Re:4X4 is more a marketing ploy than anything else

[TTK Ciar]

I am a software engineer working at The Internet Archive, and I write parallel software every day (sometimes with PVM for "real" applications, but more often as throwaway perl slammed out on the command line, using open3() to open several simultaneous subprocesses, sometimes fed data by the parent but more often each reading from a different data file). Much of what I do is "trivially parallelizable", meaning it's pretty easy to make scale across multiple processors or machines. It is my impression that most real-life problems seen by most businesses are trivially parallelizable, with the rare exceptions hogging all the attention by dint of being more interesting.

My workstation is a single-processor machine, but I have at my exclusive disposal a dual-xeon machine and two AMD dual-core machines. I'm always scp'ing my work up to them from my workstation so I can take advantage of their multi-process goodness. (Developing while ssh'd into those machines is usually not a good idea, since the network likes to go down or slow down a lot between Archive HQ and our datacenters, and our HQ firewall blocks PVM so I can't just make my workstation the PVM master node with the other three machines slaves.)

When I read this article, my initial reaction was "Enthusiasts, hell! I want as many of these as I can get for servers!" (assuming this 4x4 product is significantly cheaper than current dual-opteron products -- we're a non-profit, without a lot to spend on hardware, and we're always running on the edge of starvation. But maybe that's a bad assumption and these will be prohibitively pricey).

If someone offered me a 4x4 or 8x8 for my desktop, though, I'd accept it gladly, and make good use of it, parsing/analyzing Archive metadata, processing multiple simultaneous http streams (we use a lot of http-rpc here, and xml data representation which means each http-rpc stream can suck down a lot of processing power), md5'ing multiple files in parallel, and the like. I'd probably also make more extensive use of bzip2 than I do currently :-)

My datasets commonly consist of hundreds or thousands of files, each of which can be processed in parallel, so I can keep throwing cores at the problem with near-linear scalability until I grind against disk or bus bandwidth limits (at which point the data needs to start out distributed in order to keep scaling).

Just my $0.02

-- TTK

Re:4X4 is more a marketing ploy than anything else

[Surt]

I'm going to run video editing, 3d rendering, and various custom software all of which scales to at least 4 cores, often at the same time (even with a quad processor box with all 4 procs maxed, i'm too often waiting on hour long renders). I have a lot of software that will likely scale just fine to 32+ procs (I'd love to find out .. the current biggest box i've been able to run on is only 4x).

Writing parallel software is not that hard. By the time you've written a couple of enterprise applications, you know the basics, because there your software has to sync across multiple boxes. Syncing on one box is all the easier. Parallel software is really close to trivial, you need only know how to a) synchronize and b) partition workloads. A is very easy, and B is only hard some of the time (for many media tasks, B is utterly trivial).

Re:Wake me up when it's really a 4x4.

[TheRaven64]

Look, the name is perfectly simple to understand. It's 2 AMD Althlon 64 X2 CPUs. Put that together, and you get...uhhh...

Anyway, ummm, I'm sure it does make sense really...

Re:65nm

[chrisinsocalif]

That is incorrect, Okay, let's nail down the transition to 45nm. AMD will have 65nm chips available Decmember 2006. Intel claims that they will have 45nm at the end of 2007. What this really means is that they will have 45nm chips available at the beginning of 2008. AMD will have 45nm chips available mid 2008. FAB 38 will be online at the end of 2008. This will give AMD the capacity for 30-40% of the market. Intel finally released a fast CPU that is only 20% of their CPU production, the rest is Netburst. Intels Advantage will fall when 65nm K8L is released and the K8L should take the performance crown back from Intel. Also Intel has a problem scaling up do more than 2 processors due to their FSB. Also when people say Intels FABs are superior to AMD's that is also incorrect. Intel is about a few months ahead in terms of 65nm. In all other areas AMD is ahead. For example, AMD is moving to second generation SOI while Intel still doesn't use SOI, AMD is moving to 3rd generation Strained Silicon while Intel is at 2nd. Intel still doesn't have the capabilities of APM. If AMD runs a good test the chip can move into production that day. If Intel does a good test it takes 2 months to duplicate it in a manufacturing FAB.

Everyone not getting it

[charnov]

Okay, I'll give it the Slashdot norm, but nobody gets what this is. It a hypertransport socket for not just another CPU, but ANYTHING you would want to connect directly to memory and CPU. No PCI or other slow bus.

There are already Xilinx cards available because this has been used in Cray supercomputers for a while (the Opteron ones anyways). This means AMD can counter ANYTHING Intel puts out because you can just slap a $20 speciality DSP on the mobo which could easily be 100x faster than that Intel chip at whatever small set of functions it needs. Video cards are already in the works for this along with all kinds of audio and video stuff. I seem to remember one manufacturer has a RAID processor. The possibilities are endless.

Re:You are Right: AMD may Die

[Bobsledboy]

AMD uses silicon on insulator technology in their fabs, Intel doesn't. SOI provides better performance for a given size, hence AMD 65nm is "better" than Intel 65nm, this is also why Sony, Nintendo and Microsoft are all using it in their next gen consoles.