It doesn't favor ARM, but I wouldn't say that it specifically disfavors them either. The problem isn't ARM's business model, but rather that going forward, no one but Intel (and to some extent Samsung and IBM) will have access to modern fabs with sufficient capacity. And the chip sizes don't...
The basic problem is that despite that ARM has a lot of wind in its back, TSMC (which supplies Apple, Qualcomm, Nvidia and TI (?)) can't even provide enough wafers for its customers. At the same time, Intel has released an at least somewhat competitive smartphone SoC at 32nm and will move to a...
That makes sense. I wonder if IBM's existing x86 license coupled with AMD's ISA extension-sharing agreements with Intel could somehow render IBM with an x86-64 license in the event of an IBM buyout of AMD, but I'm really speculating wildly at this point. I also think there is a clause in the...
I can't really say that they do need AMD (whatever direction they take), but I figure that if demand for POWER systems really becomes so small that IBM can't justify continuing development on them (which, admittedly, is unlikely, if for no other reason that IBM in any case would have to continue...
That's exactly why IBM wants to sell you their hardware and is ready to cut prices substantially to make sure you do. The amount of maintenance they can sell you (and the amount of control they exert over the future of computing and the computer market as a whole) grows less when their customers...
Exactly. Software and services is without a doubt the primary business of IBM these days, but their software division would be weaker without their hardware division.
Discounting systems is standard practice in this industry, and has to do with the scale and breadth of your hardware purchases, your history as a customer and what software and support contracts you buy with your hardware. In fact, paying list price for large-scale enterprise servers is rare. I...
That's true in a limited sense, but for a systems company like IBM there is more to selling hardware than the profits you make on hardware sales directly (which is just a function of the price tag you choose to set on your systems anyway). Just ask Larry Ellison why Oracle is so keen on...
Do you seriously think that an Intel monopoly on server CPUs is a good position for IBM to be in, whether strategically (control over platforms, programming models etc.) or purely economically (prices of Intel CPUs that go into IBM x86 servers)? That the RISC CPU market is shrinking (albeit with...
Apple will never fab their own chips. Anyone who understands the slightest bit about Apple's business model (maximal profits with a minimum of capital expenditures, and minimal risk in the manufacturing chain) can figure out why.
I can imagine that Qualcomm would, since they are already making...
No wonder that Google has partnered with Intel through Motorola over the future of the Android ecosystem, and made such an effort to optimize Android for x86. They might have seen this coming.
Also, this is just so damn funny. The ARM party is over before it even started.
That's not accurate. Real World Technologies puts the SB pipeline length at 2 stages more than that of Nehalem in case of a micro-op cache miss, which would make the number 18. For reference, the original NetBurst had a 20 stage pipeline.
HMC is a new way of making DRAM chips, not integrated memory. It could (and probably will) be added to CPUs as a separate layer of silicon, but so could the standard DRAM that we have today. The main application for HMC memory will probably be traditional DIMM sticks.
There's also no real...
Intel has already stated repeatedly that Haswell will have upgraded GTxxx graphics just like Sandy Bridge. Further down the road they are bound to use either LRBni or AVX2 software rendering though.
Stock performance is disappointing but overclocked performance looks excellent. Stock clock frequencies may be too conservative but with a maturing 28nm process AMD will probably release higher-clocked SKUs. Also it's a new architecture so we can actually expect significant improvements from...
No, that's really not accurate. It's actually Intel and AMD that have a vested interest in the continued market dominance of x86. Microsoft has always been, or at least tried to be, platform independent and have offered their Windows NT operating systems for MIPS, PowerPC, Alpha and Itanium in...
Yeah, this would be the Xeon E5-2687W at $1885 and with a TDP of 150W. And I want one so bad... :(
http://www.cpu-world.com/news_2011/2011102701_Prices_of_Xeon_E5-2600-series_CPUs.html
First of all, increased transistor performance does not directly translate into higher clock frequency of the entire CPU. Second of all, higher clocks enabled by the process does not require Intel to implement them in the SKU's they sell. With AMD, as you say, offering no competition at all in...
The basic problem is that even with ever increasing GPU power, we have talented and very experienced game designers like John Carmack and Tim Sweeney saying that they don't really know what to do with it because they're limited by the APIs. We've had a development toward more programmable GPUs...
You can always trust Hiroshige Goto for insightful, albeit speculative and cutting edge, CPU roadmaps and diagrams that no one else seems to be able to deliver. I'm impressed (pun somewhat intended).
I'm not sure what your concern is, but what you would need to run DirectX and OpenGL...
What's with all the worthless channer scum popping up here lately? We should burn some crosses to show them that they aren't welcome around these parts.
Yeah, but that's just normal performance scaling, just like what we have today.
You're right that VRM power consumption does scale with output, but it's still not a signifcant source of heat delta. Remember that not everything involved in voltage regulation is moved from the motherboard to the...
Yeah, we know, since that's what you keep repeating on and on and as loudly as you can. What you apparently want everyone to forget is that while the present Atoms aren't at all optimized for ultramobiles (they suck, to put it bluntly, and everyone agrees on that), Medfield, really as the first...
Those two design features will apply (and I would say more or less equally) to the 35W, 45W and 65W SKUs and their TDP rating as well, so it's safe to say that they are not a deciding factor behind (increased) TDP. If they were, performance/power scaling like that with the same die would not be...
x86 designers didn't beat RISC with "good enough" performance and lower prices, they beat them with significantly higher performance, similar RAS features and much lower prices. That's the kind of advantage that you need to displace any architecture that carries with it an enormous legacy and...
Because 4 fat cores (especially with improved SMT) are better than 8 weak cores. In the Haswell-E family there will definitely be an 8 core SKU, but that will be with a larger die, higher costs, somewhat lower clock frequency and higher TDP than in the mainstream line. Those are trade-offs that...
I'm happy to see there will be a 95W desktop SKU. That means they won't be completely focused on scaling down for power efficiency improvements. For 6 and 8 cores we will probably have to wait for the enthusiast/performance server lines, which I also think is the right way to go.
Also keep in...
I know that ripping on the gamer/enthusiast market, with or without any basis in fact, is all the rage here (I've probably seen the same tirade repated 20-30 times on these forums) but when someone adds that the real money is in research and education it just looks ridiculous. I promise you that...
If AMD exits the high-end x86 space including server processors (which I find unlikely), I suspect that IBM will enter it one way or another (either by purchasing the AMD server division or starting to design x86 CPUs themselves). As far as I understand it they still have a valid x86 license...
That's all very true. However there was the MiG-25 as an example of a fighter (or more accurately an interceptor) that could fly at Mach 3+, and which used titanium on the leading edge of the wings to withstand the temperatures created at those speeds, although if it went much faster than that...
That's a ridiculous analogy. The reason that modern fighter jets aren't faster than fighters were 40-50 years ago isn't that they are fast enough, it's that we can't make them any faster with respect to maneuverability and fuel consumption even with modern technology.
And we have the same...
Lol, what an ironic post. When I made an exactly identical description of the binning process on these forums a couple of months ago, I remember you making a response to the effect that I didn't know what I was talking about. Which means that either you are way off in your post here or you were...
I understand that was the intention, however regardless of the disclaimers you add to your signature, you have to understand that when you write under your real name as a director of a company the information you give out and the attitude you display reflects on your company. That's the reality...
I think the interesting question going forward is whether we can expect better server performance from the Bulldozer architecture (and specifically the Orochi dies) than in the client space. I fully believed that right up until the launch when Bulldozer was shown to have abysmal performance...
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.