• Happy holidays, folks! Thanks to each and every one of you for being part of the Tom's Hardware community!

Anandtech benches dual Magny Cours and Xeon

Page 3 - Seeking answers? Join the Tom's Hardware community: where nearly two million members share solutions and discuss the latest tech.
Status
Not open for further replies.

Your silly interpretations will turn out to be wrong, again.

So what organisation's reporting of the server market share are we going to use as a determinant of market share status?

We need to settle on this before the year is out, less you try and squirm your way out and rely on what those idiots at AMDZone say.
 

How is this any kind of story? :pfff:

This has been known for at least 6 months before this article appeared.

And unless AMD are really late to market with Bulldozer, I would expect Intel will coincide the launch of Sandy Bridge with Bulldozer, so within a month either side of Bulldozer's release.
 


There is no 100%. AMD has yet to show a road map showing Bulldozer for Q1 2011. But even 16 months before its 2011 debut, Intel had SandyBridge all ready to go:

http://www.brightsideofnews.com/news/2009/7/5/intels-anti-amd-fusion-sandy-bridge-cpu-tapes-out.aspx

Pretty interesting stuff.



Fantastic execution? I beg to differ. 2 years ago AMD released their worst CPU since back during their Intel x86 clone days, jumped into horrible debt and was being run like crap. What saved them was a cash infusion from the UAE investment firm, that same firm investing the most into GF and a $1.25 billion from Intel. Without those AMD would have probably slammed face down into the concrete.

MC is meh. I am sorry but in all honesty its not that great. What I have seen only puts it barley above Xeon except in maybe 1 or 2 tasks which is pathetic. For what it is in a server world it should at least offer 50% better performance with 2x the cores.

We shall see if AMD sticks to the socket. Things change. Its just like AM3. I still doubt having a GPU on the CPU wont change the socket at all.

AMD had better hope that Intel doesn't do a 12 core MCM CPU. If the current results are 100% then AMD would hurt big time if Intel did.
 

Intel want to keep making industry high profits for somewhat mainstream markets, that is why Westmere server CPU's are 1/3 the size of MC.

AMD are in desperate survival mode so are hanging on for dear life, hoping that they can make it to Bulldozer and that Bulldozer will be good enough to save them.

Thus AMD are sacrificing profit margins, for what they hope will be a future.

Amazing someone needs to explain this rather obvious series of events to you, but then again, you are JennyH. :lol:
 


LOL - you're wasting time & bandwidth trying to convince any AMD fanbois of the facts. The AMDZone bozos along with chief salesman JF have been touting Mega Corpulent for months now, so their opinions are set in concrete, never mind any facts.

Anyway, Westmere Xeons will thrash Mega Corpulent in small to medium servers and Nehalem EX will thrash Mega Corpulent in medium to large servers. So I doubt Intel will be doing any MCM Westmeres soon because they don't really need it.

Case closed 😀.
 
Same old excuses from the intel crowd. Go do your MCM oh wait that's gonna need a nuclear power plant to run it.

Simple fact is, intel would do it if they could do it. They can't. How is it even possible to throw away a process lead? Is their 32nm so bad it's actually worse than 45nm? 😀

All that matters is here and now and AMD has the cores that count while intel has to rely on cheap tricks to try and keep up vs AMD's superior architecture.

130W for 6 cores vs 115w for 12 cores. That says it all, talking about the size of the chip is just a smokescreen - the real issue is intels inferior 6 cores on a newer process is losing to AMD's 12 cores on an older process.
 
711853A3367A52D66DB0B129AB9734B5_1000x700.jpg


78F5CCA686037C306CA9C870A7660130_1000x700.jpg


18B717A965DF4DF09C08EC1B5C1FE765_1000x700.jpg


DB4479371EABA06EA052084163FF74C0_1000x700.jpg


The other benchmarks are (only) Spec_int_rate, Sungard ACR (Intel showcase benchmark) and Cinebench. AMD is competitive on those, but loses.

Cost of CPU's tested:
Xeon X7560 $3692 (130W a.k.a. 185W)
Opteron 6174 $1165 (80W a.k.a. 115W)

SPECfp_rate2006 SPECfp_rate_base2006
Opteron 2.3 GHz (2s) 318 290
Beckton 2.26 GHz (2s) 283 274

// copied from AMD zone.


So much for the wonder chip. FAIL intel, just FAIL. 😀 😀
 

Of course if Intel wanted to make as little profit from Server CPU sales as AMD is going to, they could.

But the advantage of being the premier CPU maker means they don't have to, so will reap huge profits whilst AMD continues to rack up the losses.

How is it even possible to throw away a process lead?
They haven't done that, so why do you ask?

Is their 32nm so bad it's actually worse than 45nm? 😀
They have added 50% more cores and kept the same clockspeed than their 32nm offerings.

All that matters is here and now and AMD has the cores that count while intel has to rely on cheap tricks to try and keep up vs AMD's superior architecture.
If AMD's architecture was superior, they wouldn't need twice as many cores to be able to survive in a few segments of the server market.

130W for 6 cores vs 115w for 12 cores. That says it all, talking about the size of the chip is just a smokescreen - the real issue is intels inferior 6 cores on a newer process is losing to AMD's 12 cores on an older process.
Clearly you don't understand that power increases quadratically as clockspeed increases, the size of the chip relates massively to profitability(an alien concept to AMD and their supporters), and how can a core be inferior if it's IPC is massively ahead of its rival?

AMD have sacrificed profits for survival, Intel don't need to do that, and you should be grateful that Intel is leaving some crumbs on the table for AMD.
 
You guys act as if AMD is in a much worse situation than they were. As of quarter 4 09 they gained 1.7% marketshare from Intel. At least its a start.
 


And the only reason they do this is so they don't hold enough marketshare to be considered a monopoly.
 


Considering that in 2006 they had around 25% marketshare, and then squandered that all the way down to 17% at the end of 2008, I guess Intel decided to bail them out a bit and bring them up to a comfortable 20% or so...

Point is, Intel could absolutely demolish AMD in a matter of mere months, if they so chose. All they have to do is forgo profitability for several quarters, sell their product at the break-even point (since selling below costs is by definition monopolistic anti-competiveness and sure to land them in court), and they would bankrupt AMD into Chapt. 7 liquidation. AMD is operating on razer-thin margins and barely staying afloat. Intel makes so much money they could afford to pay AMD $1.25B to shut up & go away...
 
Fazers you are really quite clueless.

What is intel without OEM's? Nothing.

Did you read what Acer's CEO said recently? Maybe you should. "Competition is good".


Do you really believe IBM/HP et-al would accept intel as the only supplier of chips, setting whatever prices they wanted?
 
FYI, I posted in the "Tubbo - worlds fattest desktop CPU" thread Bit-tech's comparison today between the MC 6174 2.2GHz 12-core vs. the Westmere Xeon 5650 2.66GHz 6-core, which were chosen because they were closest in price. And of course because Jenny asked for it 😀.

However contrary to her assertion that MC would destroy the Xeon, the latter turned out to be higher ranked in both performance and value! Go figure!! Obviously Bit-tech failed to drink sufficient green Koolaid prior to running the tests:

Conclusion
Intel is in a very strong position in the workstation/server market right now thanks to the performance lead of its Xeon 5500-series CPUs, and AMD is the distinct underdog. However, AMD has used this as a spur to redesign and re-organise its Opteron brand, dropping backwards compatibility with earlier models in order to simplify its range and boost performance. We're particularly pleased to see AMD finally taking the step of combining two multi-core dies - something Intel learned to do long ago. It may not be the most elegant way to get the job done, but performance results are what count to end-users.

Thus, while the Xeon 5600-series builds on the success of the Xeon 5500-series, AMD has considerably upped the ante. The end result is far greater competition between Xeon and Opteron than there has been in recent years. For example, in contrast to when we last compared Xeon and Opteron, in which the Xeons took the lead in every benchmark; the Opteron 6174s did outperform the Xeon X5650s in several tests. This means it’s more important than ever before to choose the right hardware for your software. Complex simulations such as Folding@home take about the same time on both architectures, while CFD calculations are much faster on the Xeons.

That said, if you look at the big picture AMD still has its work cut out of it in the HPC/server application space as its latest Opteron 6174 lags behind the similarly priced Xeon X5650 in many of these applications. This is particularly true when you consider than the Opteron 6174 is the second fastest Opteron 6000-series CPU, while there are five faster Xeon 5600-series than the Xeon X5650s we tested. Thus, if all you want is the best possible performance from a dual-processor workstation/server, then the Xeon 5600-series is still the best choice.

In summary, while the Opteron 6174 and its Magny-Cours design are a great step forward for AMD, it’s still clear that whatever it does, what it really needs is a new core design; something that we’ll only see next year with the first Bulldozer CPUs.

AMD Opteron 6174

Performance
xxxxxxxx--8/10
Value
xxxxxxx---7/10
Overall
xxxxxxx---7/10

Intel Xeon X5650

Performance
xxxxxxxxx-9/10
Value
xxxxxxxx--8/10
Overall
xxxxxxxxx-9/10

So, despite the thunderous proclamations by certain fanbois here, declaring MC the uncontested winner, it's just merely adequate. Or as Jimmy says, "meh" :lol:
 
That's just a very small part of the market. And umm, I didn't count the results but it sure looked to me like MC won more than the Xeon did, regardless of the conclusion :)
 


LOL - why thank you Jenny, since considering the source I'll just take that as a compliment.

However, last time I checked, IBM got out of the PC selling business when they sold to Lenovo. And yes - HP, Dell, and all those small Chinese & other Asian OEMs who account for something like 25% of Intel's sales, would take the cheapest and best-performing CPUs they could get. Do you seriously think that they would prop up AMD financially by forcing Intel to take more $$ for their CPUs?

I'm absolutely certain it costs Intel much less to fab their chips than it does AMD, seeing as how AMD has to pay GF costs plus profit margin, since those arabs ain't gonna take wooden shekels aka AMD IOU's for long. Not to mention 20-30% more expensive SOI wafers as starting material. So considering the fatship - er, flagship Magny Cours 😀, if Intel sold Westmere Xeons at or slightly above costs, AMD would lose money they don't have on every matching sale of MC. And while Acer, HP & other OEMs might go "Tsk tsk" at Intel, they would jump at the chance to sell cheap Xeon servers because if they didn't, their competition would...

The sad fact is, AMD has never been, and is not now, in charge of its own destiny, at least in the CPU biz. They survive only at Intel's behest. The funny part is, most Intel fans wonder why Intel just doesn't polish them off and be done with it. That would at least dry up the shallow end of the gene pool, where the AMD fanbois tend to congregate 😀..

Ya know, 20 years ago when I was a fresh young squirt :kaola:, new to the PC wars, it was Windows NT vs IBM's OS/2. The OS/2 fanbois were even more loud & shrill than AMD fanbois today. When IBM eventually gave up and discontinued it, the silence was deafening. And quite welcome 😀... It would almost be worth it for Intel to do the same for the rabid AMD fanbois - a sort of mercy-killing 😀..
 


Erm, yeah Jenny 😀. That's the ticket - those pesky reviewers didn't even understand their own benchies...

Anyway, that's two reviews from reputable sites and knowledgeable people, vs. your incomprehensible beer-chugging German wienerschnitzel review.

And did you notice that the HPC bench came out in the Xeon's favor??? Add that to the huge advantage in the up&coming cloud computing environment - virtual machine performance as measured by VMmark - and it looks like Xeon is the clear winner. And that's without the Nehalem EX benches which will be forthcoming soon.

Mega Corpulent is just a fat pig with lipstick 😀

Case closed.
 
Status
Not open for further replies.

TRENDING THREADS