Sign in with
Sign up | Sign in
Your question

Anandtech Review => AMD's Quad FX: Technically Quad Core

Last response: in CPUs
Share
a c 447 à CPUs
a c 111 À AMD
November 30, 2006 8:12:12 PM

Didn't see any threads related to Anandtech's Quad FX reveiw so here it is:

AMD's Quad FX: Technically Quad Core

Sorry if it has already been posted.

It seems that using just one dual core CPU is actually faster than using two dual core CPUs in most of the benchmarks. The exceptions are 2D Content Creation and Web Publication.

Quote:

More Sockets, but Lower Performance?

When AMD briefed us on Quad FX, the performance focus was on heavy multitasking (AMD calls this "Megatasking") or very multi-threaded tests. We figured it was an innocent attempt to make sure we didn't run a bunch of single threaded benchmarks on Quad FX and proclaim it a failure. Given that the vast majority of our CPU test suite is multi-threaded to begin with, we didn't think there would be any problems showcasing where four cores is better than two, much like we did in our Kentsfield review.

However when running our SYSMark 2004SE tests we encountered a situation that didn't make total sense to us at first, and somewhat explained AMD's desire for us to strongly focus on megatasking/multithreaded tests. If we pulled one of the CPUs out of the Quad FX system, we actually got higher performance in SYSMark than with both CPUs in place. In other words, four cores was slower than two.


Quote:

Power Consumption

Power consumption of a Quad FX system is simply unreal for a desktop, as it should be because this is effectively a workstation platform with un-buffered memory. At idle our Quad FX test bed consumed nearly 400W, partially because we couldn't get Cool 'n Quiet running on the system, but also because the CPUs and motherboard simply draw an incredible amount of power.

Looking at power consumption under full load, Cool 'n Quiet would have no chance to even make an impact as all cores are being utilized at full speed. Under load the Quad FX system pulled 456W on average, a full 73% more than our Kentsfield testbed.


Quote:

Final Words
AMD is going to have a very tough sell with Quad FX; although the CPUs are priced competitively, if the ASUS L1N64-SLI WS ends up just shy of the $400 mark it's a platform that is simply too expensive at no benefit to the end user. When only running one or two CPU intensive threads, Quad FX ends up being slower than an identically clocked dual core system, and when running more threads it's no faster than Intel's Core 2 Extreme QX6700. But it's more expensive than the alternatives and consumes as much power as both, combined.

.
.
.

Prepare to revisit this discussion in less than a year's time, and next time AMD will hopefully be much better prepared, armed with a new architecture and a cooler, smaller 65nm process. Until then, there's always Quad FX but you're better off with Kentsfield.


I think this paints a bleak picture for AMD until they can finally release their next gen CPU.
November 30, 2006 9:11:23 PM

Quote:
I think this paints a bleak picture for AMD until they can finally release their next gen CPU.


I had been looking forward to the release of the 4x4 machines with hope that they would do well. Whether its a review from Anandtech, Tom's, or someone else, the 4x4 turns out bad. I wonder how many heads will roll at AMD? I think I'll probably stay with my old 939 machine for a bit longer, as AM2 didn't show any real benifit and this 4x4 is worse yet.

The only possible good thing I've seen for AMD is that with Vista, it might perform better than with XP, but that's a big MIGHT, and I'm not betting on it. Guess my Intel stocks will do good, while my AMD stocks will continue to suffer.
November 30, 2006 9:33:12 PM

I don’t mean to sound like a pretentious Intel fanboy but the release of the AMD 4x4 smacks of desperate measures from a desperate company. The power requirements are simply unreal. At PC watch under full load this thing can draw 589 watts, if you ran that with GeForce 8800GTX SLI (321 watt full load per card) you will need a 1.2 Kw PSU just to run this, and that doesn’t included motherboard, ram, hard drives etc.
Related resources
November 30, 2006 10:40:45 PM

Guess no one told AMD that one of the 4's in 4x4 is for 4 PSUs...

In all seriousness, Quad FX is going to be picked up by a select few. Its just not worth it when there's a C2Q that is cheaper, faster, and destroys 4x4 in performance per watt.

Its like intel releasing the Pentium D chips when the X2's were out - pretty useless, but at least the P-D's were cheaper... :?

Talk about leaving a bitter taste in one's mouth.
a b à CPUs
November 30, 2006 11:03:45 PM

Good article. Thanks for the link. But, Anandtech has lost credibility in my book ever since the Core Duo vs AthlonFX benches. I've come to take Anand with a grain of salt.

Give it some time to mature and as the native quad cores are released, 4x4 will show itself not be the power hungry waste of money it's being made out to be.
November 30, 2006 11:05:12 PM

I fail to see how. With two sockets, two 68W quad core chips are still going to be 146W.
a b à CPUs
November 30, 2006 11:07:11 PM

Quote:
I don’t mean to sound like a pretentious Intel fanboy but...


Lesson learned here is, anytime you feel the need to preface a post with a disclaimer like this, that's exactly what you are going to sound like.
November 30, 2006 11:10:46 PM

Quote:
I fail to see how. With two sockets, two 68W quad core chips are still going to be 146W.


That's still a lot better than the situation now. Another thing is that if its run with Vista, it might run better because all the cores can be addressed, in addition to future programs that will take advantage of multiple cores. Would have been nice if Anandtech had tried the comparisons using Vista.

At the same time, I don't hold much hope in the 4x4 platform. I can see Intel in my future machine.
a b à CPUs
November 30, 2006 11:11:05 PM

Quote:
I fail to see how. With two sockets, two 68W quad core chips are still going to be 146W.


Check your math before attempting to sound intelligent.

68 + 68 = 136

I'm not surprised you fail to see how...
November 30, 2006 11:12:57 PM

Removed, counter flame way too strong.
a b à CPUs
November 30, 2006 11:25:24 PM

whatever...just don't hurt yourself with any big numbers, ok...
November 30, 2006 11:28:49 PM

Ack, knee jerked on an (interpreted) flame :( 
I do this a lot to BaronMatrix, but you aren't as antagonizing.
a b à CPUs
November 30, 2006 11:31:55 PM

Quote:
I don’t mean to sound like a pretentious Intel fanboy but...


Lesson learned here is, anytime you feel the need to preface a post with a disclaimer like this, that's exactly what you are going to sound like.

No offense dude but you sound like one big AMD fanboy in denial that 4x4 is crap. You see as it matures.. it will be called 4x4+. Not the same platform.

As it stands 4x4 is utter and total crap. Admit it and go on with your life. No sense in trying to pick on a maybe/possibility as a reasoning to claim it to be any different.
a c 447 à CPUs
a c 111 À AMD
December 1, 2006 1:45:06 AM

Quote:
Guess my Intel stocks will do good, while my AMD stocks will continue to suffer.


I see you're hedging your bets.
a c 447 à CPUs
a c 111 À AMD
December 1, 2006 1:56:21 AM

Quote:
I don’t mean to sound like a pretentious Intel fanboy but the release of the AMD 4x4 smacks of desperate measures from a desperate company. The power requirements are simply unreal.


While it is a depeserate attempt to draw attention away from C2D and C2Q, I don't think AMD is in a desperate situation yet. They held the performance crown for quite some time beating Intel's Pentium 4 over the head with the Athlon XP first, and then the Athlon 64.

The introduction of the C2D merely marks the transition of the performance crown back to Intel. AMD can still compete fairly well in the value segment of the market and having Dell sell PCs with Athlons in them is a major milestone.

However, if K8L fails to provide competitive performance then AMD will be in dire straights since they will need to rely on K10 to level the playing field at the very least.
December 1, 2006 8:09:08 AM

Quote:
I don’t mean to sound like a pretentious Intel fanboy but the release of the AMD 4x4 smacks of desperate measures from a desperate company. The power requirements are simply unreal.


While it is a depeserate attempt to draw attention away from C2D and C2Q, I don't think AMD is in a desperate situation yet. They held the performance crown for quite some time beating Intel's Pentium 4 over the head with the Athlon XP first, and then the Athlon 64.

The introduction of the C2D merely marks the transition of the performance crown back to Intel. AMD can still compete fairly well in the value segment of the market and having Dell sell PCs with Athlons in them is a major milestone.

I believe when Intel releases the E4400 and E4300 and then follows on with the E2xx series of processors based on the Core 2 architechure then they will own the value segment. Not to mention I remember reading that Intel is planning to drop their Netburst processor prices down the well in January.

This does not bode well for AMD. The only place left that AMD has the advantage will be in the 4P and higher and super computers.

However, if K8L fails to provide competitive performance then AMD will be in dire straights since they will need to rely on K10 to level the playing field at the very least.
December 1, 2006 8:55:08 AM

What I'd like to see is a quad 8800GTS/GTX setup... unfortunately the current AMD aren't the best CPU to feed these monsters, but the interconnect seems to be there.

Why didn't they put the second 680a on the other processor ? They are selling the cpus in pair anyway, woudn't need to have both crossbars buzy for nothing ? I know there is enough BW in the crossbar itself, but there is still contention and latency.
December 1, 2006 9:49:27 AM

Here is a more trusted site :


Quote:
Performance Summary: Throughout our entire suite of benchmarks, a system powered by Intel's quad-core Core 2 Extreme QX6700 processor outpaced all of the QuadFX-based systems. The Intel-powered system also generally scaled better moving from two to four cores in the multi-threaded benchmarks. Our in-game tests and PCMark05's memory performance module put the QuadFX platform at a disadvantage versus AMD's own socket AM2 dual-core platform, but in all of the multi-threaded application and rendering tests, QuadFX was significantly faster than a similarly equipped system powered by an Athlon 64 FX-62.



Quote:
AMD is clearly laying the foundation for the future with the QuadFX platform. In its current state, a QuadFX machine powered by a pair of AMD's fastest FX-74 processors can't quite keep pace with the QX6700 strictly from a performance standpoint. The overall feature-set of the QuadFX is impressive, however, thanks in part to NVIDIA's nForce 680a SLI chipset and the dual-socket nature of the platform. Twelve SATA ports, quad PCI Express X16 graphics slots, the potential for quad gigabit Ethernet, and SLI support put the QuadFX in a league of its own from a feature standpoint. And that doesn't account for potential future innovations that could make use of the second CPU socket.



Quote:
AMD will be selling Athlon 64 FX-70, FX-72, and FX-74 processors in pairs with heatsinks for prices of $599, $799, and $999 respectively. That's two 3.0GHz dual-core processors for just under a grand. The Asus QuadFX L1N64-SLI WS motherboard will sell for upwards of $300. And for maximum performance, QuadFX will also require four DIMMs, which will be marginally more expensive than two DIMMs of a similar total capacity. Overall, the pricing structure makes configuring the fastest QuadFX system more expensive than the fastest quad-core Intel-based system, but QuadFX does offer more features, so pricing isn't out of line in our opinion



http://www.hothardware.com/viewarticle.aspx
December 1, 2006 11:13:31 AM

Too expensive (Mobo+CPUs+PSU+RAM) for the performances offered.
Let's wait for the next AMD step (and Intels too...).

Sounds great to keep your house warm in winter though.
December 2, 2006 7:33:49 AM

Quote:
Again, shining example of NUMA in action.... Vista will help, but not that much --- Desktop work loads just do not play nice with NUMA. I think you are right, for now this does not bode well for AMD.


Has anybody had Linux running on this platform yet? I'd be interested to see how well its able to work on it and if it offered any advantage over XP/Vista. I could see this working for developers running environments such as VMWare or for some of the graphics niche areas where Linux has a good foothold.
December 2, 2006 10:56:03 AM

Quote:
I fail to see how. With two sockets, two 68W quad core chips are still going to be 146W.



Barcelona 4x4 = 68+68 =136W for 8 cores.

Current 4x4 = 125W+125W = 250W for 4 cores

Kentsfield = 130W for 4 cores

Right now its double the power for the same number of cores as Intel. And AMD who laugh at intel for their "glued" design have basically glued two Dual Cores together here, except that on 90nm they cant fir in one package so there are two....

After Barcelona, it will be double the cores for about the same power.

That is, unless Intel is producing 45nm quad cores by then...

Personally I think nVidia should have taken this opportunity to say "screw you" to AMD for buying ATi and refused to put a platform together for it... leaving AMD with a long chipset lead time on releasing 4x4 still.
December 2, 2006 11:23:36 AM

yes, but at it's intro it will be a top performer and I think most people vill opt for lower clock, 68W parts.
December 2, 2006 11:36:10 AM

Quote:
I fail to see how. With two sockets, two 68W quad core chips are still going to be 146W.



Barcelona 4x4 = 68+68 =136W for 8 cores.

Current 4x4 = 125W+125W = 250W for 4 cores

Kentsfield = 130W for 4 cores

Right now its double the power for the same number of cores as Intel. And AMD who laugh at intel for their "glued" design have basically glued two Dual Cores together here, except that on 90nm they cant fir in one package so there are two....

After Barcelona, it will be double the cores for about the same power.

That is, unless Intel is producing 45nm quad cores by then...

Personally I think nVidia should have taken this opportunity to say "screw you" to AMD for buying ATi and refused to put a platform together for it... leaving AMD with a long chipset lead time on releasing 4x4 still.

Projecting from today's current products, to AMD products of tomorrow then this is correct --- however, we are not aware of any Intel's 45 nm quad products just yet. Word on the street is that the TDP will be lowered to 50 watts at 3.5-3.7 GHz.

The 68 watt quad part that is being thrown in this thread will not give nut busting performance either, as AMD will likely need to bin this out at lower clocks and lower voltages to hit this envelop. AMD's full range of power specs (leaked albiet) is 68, 89, and 120 Watts for their future quad cores. The FX-line is certain to be the top bin parts which means we are back to the same 120 Watt x2 for the 8x4.

While you will get 8 cores and good performance, the power will still be 500+ for this platform.

Jack

Oh I agree Jack, and my only source for the 68W thing was this thread :)  its pretty sad but I've just about lost interest in AMDs roadmaps now, just as I had with Intel's before Core 2 Duo.

I said in my original post that Intel could be producing 45nm by then (or soon after).

Its pretty sad when the only "cool" thing about a new CPU is the chipset.

56 PCIe lanes, 20 USB2, 12 SATA, 4 GbE. Thats way more exciting than a 3.0GHz A64 with NO overclocking headroom.
December 2, 2006 9:40:03 PM

Quote:
yes, but at it's intro it will be a top performer and I think most people vill opt for lower clock, 68W parts.


I don't know to be certain, but I don't think the 68W parts will be top performers, Q6600 (when it launches) will likely out perform the 68 Watt barcelona (on performance only), perf/watt hard to tell. The 68 watt parts will likely clock 30-50% below the high performance parts which will come in at 120 Watts. My guess anyway based on AMDs historical segmentation along this vector.
I intended the top performer in dual socket ?8X4? configuration; don't forget that it will still be multiplied by the 2X factor. I don't have an exact idea on how barcelona will perform and most probably intel will have an edge on power consumption but if AMD keeps 8cores within the 136W envelope, they will most likely outperform intel's 4 cores by at least 50% (K8 arch already does it with a 500W envelope 8O :lol:  ) and nobody will care about the 20-30W+ or $400-500+ when they build a top performing $2000-3000 machine.
December 2, 2006 10:02:02 PM

Well, your hypothesis is based on the strong fact that intel is going to introduce 45nm chips after mid 2007, however, you also asume that intel will still have the clock/clock lead, about which I'd not bet.
However, one thing is sure; when intel gets on 45nm, it won't take them much longer to build a dual die octo core, that is why AMD has to rush the 65nm quads as soon as possible if they want to have some guaranteed months of performance lead and a more balanced image.
December 2, 2006 10:13:58 PM

I know; it's all about how well will the 45nm scale, and if they ship 45nm C2Ds by this time, for sure they will ship dual die octos in Q4 2007 like they're doing with kentsfield now, it took them less than 3 months to launch the Quad from the release of the Duo, they're not kidding any more.
December 3, 2006 2:15:09 AM

Quote:
I fail to see how. With two sockets, two 68W quad core chips are still going to be 146W.



Barcelona 4x4 = 68+68 =136W for 8 cores.

Current 4x4 = 125W+125W = 250W for 4 cores

Kentsfield = 130W for 4 cores

Right now its double the power for the same number of cores as Intel. And AMD who laugh at intel for their "glued" design have basically glued two Dual Cores together here, except that on 90nm they cant fir in one package so there are two....

After Barcelona, it will be double the cores for about the same power.

That is, unless Intel is producing 45nm quad cores by then...

Personally I think nVidia should have taken this opportunity to say "screw you" to AMD for buying ATi and refused to put a platform together for it... leaving AMD with a long chipset lead time on releasing 4x4 still.

Projecting from today's current products, to AMD products of tomorrow then this is correct --- however, we are not aware of any Intel's 45 nm quad products just yet. Word on the street is that the TDP will be lowered to 50 watts at 3.5-3.7 GHz.

The 68 watt quad part that is being thrown in this thread will not give nut busting performance either, as AMD will likely need to bin this out at lower clocks and lower voltages to hit this envelop. AMD's full range of power specs (leaked albiet) is 68, 89, and 120 Watts for their future quad cores. The FX-line is certain to be the top bin parts which means we are back to the same 120 Watt x2 for the 8x4.

While you will get 8 cores and good performance, the power will still be 500+ for this platform.

Jack

If I recall it's supossed to be that only the top bin of AMD chips only will work with 4x4 an 8x4, so do you really guys expect that the lower bins (68watt parts) they will let them to work with this plattaform?

Personally I think that the target for this 4x4 8x4 it's The FX chips, so If the FX are the top of AMD you should expect that ONLY the 120watt chips are going to work.

Just my 2 cents....

Cheers

SAM
December 3, 2006 4:21:47 AM

Quote:
4x4 is a joke unless your building a server.
The real quad core due out next year will be very competative.


Woooowwwaaaa, step back .... everyone, hold onto something as the earth is about to stop spinning for a few moments.... did I read this right, MrsBytch (MMM) called the 4x4 a joke????

Now I have seen everyting.... :) 
In other (unrelated) news, Hell froze over, Castro and Chavez love the US, Bush learns how to say "Nuclear" and the Cubs win the World Series. On the same day.
December 3, 2006 7:12:59 AM

Quote:
I know; it's all about how well will the 45nm scale, and if they ship 45nm C2Ds by this time, for sure they will ship dual die octos in Q4 2007 like they're doing with kentsfield now, it took them less than 3 months to launch the Quad from the release of the Duo, they're not kidding any more.


I did an edit above, you may want to read that....


Yeah, I was quite shocked at how quickly the pulled in the quad core offering.... this is the one advantage the FSB has, time to market and lower costs for doing this kind of trick.... glued together or not, it did perform tremendously well.
Yes, the high-k is not yet that mature because they'd not play with SOI if it was.
AMD has to pull out its quads well before mid 2007 if they want to breathe for some time. However, in all our discussion, there is one large variable, that is Barvelona's performance, which may range from +15% to -15% that of core2 and once we nail this by the first benchmarks, a much clearer view throughout 2007 will be possible.
P.S: another thing to consider, is that 45nm at the very eginning will not reach top clock rates, even if it's straightforward die shrink. The northwood was just that but the NSDS proved it was immature to be pushed at the beginning.
December 3, 2006 7:50:15 AM

After reading almost all the specs, and thinking about it for a fortnight I am strongly of the opinion that AMD K8L / 65 nm / Quad-Core on a die systems at 3.4 GHz (which will need mature 65 nm to reach) will offer about 95% (91% to 99%)* the performance of Intel Core 2 Quad / Xeon 5300 systems clocked at just 2.67 GHz.

The only variable I haven't really considered is cache, as I don't know what Intel will want to offer, and the 'exact' difference having 4 x 512 KB L2 caches and a shared L3 cache per die on AMD will make.

However, I am sure these figures are accurate to +/- 4% - which is damn near close enough considering the parts will not be out for months, maybe even a year.

*(It'll be nipping at its heals, but not outperforming it very often)

8) - Tabris:D arkPeace
December 3, 2006 7:54:26 AM

There wont be a 8x4
Because 8x4 is:
December 3, 2006 8:34:00 AM

Quote:
4x4 is a joke unless your building a server.
The real quad core due out next year will be very competative.


Woooowwwaaaa, step back .... everyone, hold onto something as the earth is about to stop spinning for a few moments.... did I read this right, MrsBytch (MMM) called the 4x4 a joke????

Now I have seen everyting.... :) 

Speaking of jokes, wheres Baron Matrices inputs to this thread?
December 3, 2006 12:13:08 PM

Quote:
4x4 is a joke unless your building a server.
The real quad core due out next year will be very competative.


Woooowwwaaaa, step back .... everyone, hold onto something as the earth is about to stop spinning for a few moments.... did I read this right, MrsBytch (MMM) called the 4x4 a joke????

Now I have seen everyting.... :) 
Not so fast Jack, what about Shakira?
December 3, 2006 12:41:36 PM

I have read other your 'calculations' lately and I tell you one thing; the greatest mistake inthis field is taking a calculator and making divisions to estimate percentage gains.Despite the name, K8L is qualitatively different from K8 and o many aspects, substantially different from Core2, so you'd better not assume K8L is K8 because it simply IS NOT!
December 3, 2006 4:16:55 PM

Lets just say AMD goes to 65mn and smacks a 8MB cache directly ondie just like Intel has done in the past to try and squeeze performance out of thier P4's i wionder what this will do for performance, besides its not good that people expected AMD to do what they did with the Athlon 64 bit again.
Just a thought
December 3, 2006 6:04:51 PM

I guess someone's got to put up some defense for QuadFX, if for no other reason than to have it...

http://www.legitreviews.com/article/425/1/

They tested everything with NUMA support (via XP Pro 64bit), and the Quad FX rig shows quite respectable results, beating the QX in a number of benchmarks. Most other benchmarkers failed to use an OS that is properly capable of using a dual-socket configuration with split memory. XP64 and Vista, on the other hand, are far more apt in this respect, and thus the performance increased drastically in almost every benchmark over XP Pro tests.

Since the people buying these systems are enthusiasts and in most cases will know these things, saying that no one uses XP64 and that Vista is not released to the mainstream market yet isn't the most watertight way to try and call the NUMA issue...well...a major issue. In about two months Vista will be out, and despite what many people claim, most people buying a new performance rig will be putting Vista on it, and Vista will perform better on the QuadFX platform than the 32-bit variety of XP.

As usual, the differing architectures have their own areas of exceptional performance over the competitor, and it seems K8 still has a little bite left in it in some of the benchmarks, though it's clear that it's about reached the end of its run and AMD is having issues pushing the clock speed higher (or can, but the energy and cooling requirements are just too ridiculous). QUICK maturation of 65nm is needed for AMD to scale the clock speed up, so they don't have to rely solely on architectural improvements.

With results like these, it really seems to me that anyone that expects Intel to be able to beat AMD's "K8L" systems by the end of next year are kidding themselves. If four K8 cores can almost come to parity with four Intel, what does it seem like four (if AMD releases the dual-core K8s for the QuadFX platform) or eight "K8L" (it won't be the named Barcelona core for the QuadFX platform, I believe, as that is reserved more especially for server only purposes, but it will be a derivative, clearly) will be able to do? The Intel bias here is really staggering, as the Barcelona improvements aren't that small.

The only significant drawbacks I can find with buying a QuadFX system over a QX6700 system are the power requirements, price (which essentially falls back on the need for two 2GB dual-channel RAM kits and the expensive motherboard, which there is only one of for the QuadFX platform at this time. The FX-74 processors aren't any more expensive than a QX6700, and with the FX-70 pair running at $599, one could build a "quad-core" system with $599 spent on the processors), and the high level of noise. If someone told me they were going to buy a QuadFX system now with FX-70s (rather than FX-74s) with the intent of upgrading to whatever Barcelona derivative finds its way to the QuadFX name, I would have to warn them about the downfalls, but wouldn't really push them away from it. If nothing else, it'd be nice knowing someone who could do it to see firsthand how well the new chips perform in a performance HT1.0 system (as opposed to HT3.0), which I might feel a little bad about, but wouldn't lose sleep about :lol:  .

Bottom line: Intel is still unquestionably superior at the moment, but the QuadFX isn't as lame-duck as people are making it out to be.

edit - edited for spelling errors.
December 3, 2006 7:26:03 PM

Quote:
Lets just say AMD goes to 65mn and smacks a 8MB cache directly ondie just like Intel has done in the past to try and squeeze performance out of thier P4's i wionder what this will do for performance, besides its not good that people expected AMD to do what they did with the Athlon 64 bit again.
Just a thought

Benchmarks show that a K8 core moving from 512k to 1024k L2 benefits almost nothing, too few performance to justify the added cost and correctly, AMD will equip it;s future chips (FX and Opterons apart) with 512K or less.
December 3, 2006 7:30:21 PM

Quote:
case in point,the elusive sempron x2 3600 benches,nearly identicle to full fledged 64 chips at that clock.

thats rumored to change with k8l
.

I love the 3600+, had they thought about it before they'd have put that cache amoount on all the athlos and got some decent cost cut maintaining a healthy performance.
BTW, what are these rumours about?
December 3, 2006 7:41:24 PM

Well, if K8L benefits from larger cache, than it means it can use the extra information on it and thus, means it's efficiency and IPC might have grown quite a bit. It has totally redesigned SSE units and internal busses widened and still many people insist it's performance will be considerably inferior to C2D (most of them talf about actual K8 numbers).
December 3, 2006 8:39:18 PM

Quote:
I guess someone's got to put up some defense for QuadFX, if for no other reason than to have it...

http://www.legitreviews.com/article/425/1/

They tested everything with NUMA support (via XP Pro 64bit), and the Quad FX rig shows quite respectable results, beating the QX in a number of benchmarks. Most other benchmarkers failed to use an OS that is properly capable of using a dual-socket configuration with split memory. XP64 and Vista, on the other hand, are far more apt in this respect, and thus the performance increased drastically in almost every benchmark over XP Pro tests.

Since the people buying these systems are enthusiasts and in most cases will know these things, saying that no one uses XP64 and that Vista is not released to the mainstream market yet isn't the most watertight way to try and call the NUMA issue...well...a major issue. In about two months Vista will be out, and despite what many people claim, most people buying a new performance rig will be putting Vista on it, and Vista will perform better on the QuadFX platform than the 32-bit variety of XP.

As usual, the differing architectures have their own areas of exceptional performance over the competitor, and it seems K8 still has a little bite left in it in some of the benchmarks, though it's clear that it's about reached the end of its run and AMD is having issues pushing the clock speed higher (or can, but the energy and cooling requirements are just too ridiculous). QUICK maturation of 65nm is needed for AMD to scale the clock speed up, so they don't have to rely solely on architectural improvements.

With results like these, it really seems to me that anyone that expects Intel to be able to beat AMD's "K8L" systems by the end of next year are kidding themselves. If four K8 cores can almost come to parity with four Intel, what does it seem like four (if AMD releases the dual-core K8s for the QuadFX platform) or eight "K8L" (it won't be the named Barcelona core for the QuadFX platform, I believe, as that is reserved more especially for server only purposes, but it will be a derivative, clearly) will be able to do? The Intel bias here is really staggering, as the Barcelona improvements aren't that small.

The only significant drawbacks I can find with buying a QuadFX system over a QX6700 system are the power requirements, price (which essentially falls back on the need for two 2GB dual-channel RAM kits and the expensive motherboard, which there is only one of for the QuadFX platform at this time. The FX-74 processors aren't any more expensive than a QX6700, and with the FX-70 pair running at $599, one could build a "quad-core" system with $599 spent on the processors), and the high level of noise. If someone told me they were going to buy a QuadFX system now with FX-70s (rather than FX-74s) with the intent of upgrading to whatever Barcelona derivative finds its way to the QuadFX name, I would have to warn them about the downfalls, but wouldn't really push them away from it. If nothing else, it'd be nice knowing someone who could do it to see firsthand how well the new chips perform in a performance HT1.0 system (as opposed to HT3.0), which I might feel a little bad about, but wouldn't lose sleep about :lol:  .

Bottom line: Intel is still unquestionably superior at the moment, but the QuadFX isn't as lame-duck as people are making it out to be.

edit - edited for spelling errors.



To interject, the site link shows that neither of these platforms with 8800 SLI is easy on power.






As is shown, both of these systems are amazingly power-hungry though C2Q tends to tame it slightly being on a 65nm process. These may end up as the first FX EEs by the time Agena FX ships. 700W load. 8O

C2Q at nearly 600W load. 8O


ANd amazingly enough the power difference is almost exactly the difference of 1 FX74. Well, I guess that isn't amazing.
December 3, 2006 9:28:03 PM

Quote:
with early bragging about barcelona,i think we are in for a great chip.

it will be then that we can dissect the core.Amd doesnt brag,and if tey started pumping hype like intel with prescott,it would hurt them immeasurably.
I'd have to disagree about that. They were pretty cocky while K8 was beating down Netburst. Remember who issued the dual-core challenge? :wink:
December 3, 2006 9:30:03 PM

Quote:
Point taken, those 8800 while screamers are really sucking down the electrons.


I guess the next nVidia shrink won't be far off, especialy since they're sayign a FASTER G80 is in the works. Hopefully R600 @ 80nm will help. I mean, buying DX9 cards right now is crazy.
I did hear that nVidia ready to do 65nm also as UMC and TSMC have gotten to 45nm SRAM.
A 65nm G80 will definitely cut power a lot.
December 3, 2006 9:44:03 PM

http://www.tgdaily.com/2006/09/25/amd_idf-2006/
AMD sends "Multi-Core Processing for Dummies" to IDF

http://digitimes.com/bits_chips/a20060313PR201.html
"We've seen, at least in a couple of areas, Intel acknowledge that AMD was right."
"Then their new-generation micro-architecture (NGMA), is, quite frankly, a quick fix on the front-side bus."

And in general, it's never a pretty sight when AMD talks about Intel in interviews :D 

Oh yeah..
www.amd.com/duel
Quote:
Intel did not Participate in the Dual-Core Duel
10.Tried to follow their own roadmap to get to the duel
9.Decided to take the "front-side bus" to the duel; got stuck in a bottleneck
8.The "Intel Inside" stickers they used to package the cores together keep melting
7.Too busy rearranging the deck chairs on the Itanic
6."Hey, we don't expect anyone to actually buy these things!“
5.Didn't want to compete when they realized that the duel would involve actual "rules" of fair competition
4.They couldn't get a permit from the fire department to emit thatmuch heat
3.No systems available yet --protective clothing used by manufacturers only safe for up to 149 watts
2. Dell told them they weren't allowed to participate
And the number one reason Intel didn’t accept the dual-core duel:
1. Moore's Law has been replaced by "Paul's Paradox": the number of canceled products per year at Intel will double every year after the introduction of the AMD Opteron™processor.

:lol: 
December 3, 2006 10:04:52 PM

I would have to say AMD was bragging, but at the time, they needed to, since they were trying to pull themselves up from the underdog position (which, I would say, they did with incredible effectiveness).
December 3, 2006 10:06:39 PM

I don't think bragging gets you anywhere, it just makes you look silly. Apple's been ragging on Windows for forever.. Look where they are :lol: 
December 3, 2006 10:07:20 PM

Quote:
I don't think bragging gets you anywhere, it just makes you look silly. Apple's been ragging on Windows for forever.. Look where they are :lol: 


Point taken! :) 
December 3, 2006 10:57:42 PM

Quote:
I would have to say AMD was bragging, but at the time, they needed to, since they were trying to pull themselves up from the underdog position (which, I would say, they did with incredible effectiveness).


well there is a difference between bragging and saying it for what it is.i think AMD is stating the truth,but it comes off as a boast because we cat see the benches.

I think its real.I dont care if i am proved wrong,because if AMD is talking out their butts;they will loose more customers back to intel.
And they know it.

I agree only to a point. In terms of marketing, they HAVE to say that their new processors rock, even if they don't.

But I agree, they probably will.
December 4, 2006 2:35:45 AM

Quote:
this was just a "preview release" so to speak.Just a luxury look at things to come.with its issues AMD is not expecting to sell alot of these,and the purpose was to put their next great idea in the hands of us whiny enthusiasts regardless of polish ,just to shut us up.

of course it has enraged us in lieu of am2 and c2d :lol:  :lol:  :lol: 
and I think that was expected as well.When the time comes the platform will rock.Until the it gives intel nothing interms of a reason to up the anty,it gives enthusiasts something to whine about,and buys them alot more time .


QuadFX is more of a stopgap, with the somewhat-intended consequence of being a platform that, in the future, could entirely dominate the high-end market.
December 4, 2006 8:15:43 AM

Quote:
I have read other your 'calculations' lately and I tell you one thing; the greatest mistake in this field is taking a calculator and making divisions to estimate percentage gains. Despite the name, K8L is qualitatively different from K8 and o many aspects, substantially different from Core2, so you'd better not assume K8L is K8 because it simply IS NOT!


I already bought all that into account (that K8L is not the same as K8, and will be made on a smaller die, with better pre-fetching and load/store enhancements - K8L (Quad single socket) at 3.4x GHz will give approx 95% (91% to 99% in most benchmarks) when compared to Core 2 Quad at just 2.67 GHz in the majority of software.

In some tasks it might be 2-3% faster (3.4 vs 2.67) but in the majority of tasks it'll be 5-9% slower.

Of course if a K8L (desktop variant) at 3.4x GHz only costs 85% of what a Core 2 Quad at 2.67 GHz costs while offering more than 85% of the performance (overall), then they'll have better price/performance, which is historically AMDs key enabler in tough times.
December 4, 2006 1:47:37 PM

Quote:
I have read other your 'calculations' lately and I tell you one thing; the greatest mistake in this field is taking a calculator and making divisions to estimate percentage gains. Despite the name, K8L is qualitatively different from K8 and o many aspects, substantially different from Core2, so you'd better not assume K8L is K8 because it simply IS NOT!


I already bought all that into account (that K8L is not the same as K8, and will be made on a smaller die, with better pre-fetching and load/store enhancements - K8L (Quad single socket) at 3.4x GHz will give approx 95% (91% to 99% in most benchmarks) when compared to Core 2 Quad at just 2.67 GHz in the majority of software.

In some tasks it might be 2-3% faster (3.4 vs 2.67) but in the majority of tasks it'll be 5-9% slower.

Of course if a K8L (desktop variant) at 3.4x GHz only costs 85% of what a Core 2 Quad at 2.67 GHz costs while offering more than 85% of the performance (overall), then they'll have better price/performance, which is historically AMDs key enabler in tough times.

You do realize that that statement is absolutely ludicrous, since a regular 3.4Ghz K8 would be almost equal in performance (in most areas) to a 2.67Ghz Core 2.

I hate to be really rude, but whatever math you did is shite.
!