High-performance computing isn't moving away from out-of-order execution any time soon. Itanic was a failure. The current generation of consoles are in-order, indeed, but keep in mind that they serve a workload niche (rather large niche in terms of deployment, sure, but still a workload niche).
The argument that the compiler can do a reasonable job at scheduling instructions... well, is simply false. Reason #1: The problem is that most applications have rather small basic blocks (spec 2000 integer, for instance, has basic blocks in the 6-10 instruction range). You can do slightly better with hyperblocks, but for that you need rather heavy profiling to figure out which paths are frequently taken. Reason #2: compiler operates on static instructions, the dynamic scheduler - on the dynamic stream. The compiler can't differentiate between instances of the instructions that hit in the cache (with a latency of 3-4 cycles) and those that miss all the way to memory (200+ cycles). The dynamic scheduler can. Why do you think that Itanium has such large caches? Because it doesn't have out-of-order execution, it is slowed down by cache misses to a much larger extent than the out-of-order processors.
I agree that there are always ways to statically improve the code to behave better on in-order machines (hoist loads and make them speculative, add prefetches, etc), but for the vast majority of applications none are as robust as out-of-order execution.
That's a debate that happened more than 20 years ago, at a time when all processors were in-order and could barely fit their L1 on chip, and there were a lot of platforms.
These days:
The transistors budgets are so high that the space taken by instruction decoders aren't an issue anymore (L1, L2 and sometimes even an L3 is on chip).
Execution is out-of-order, and the pipeline stalls are greatly reduced. The out-of-order execution engine runs a RISC-like instruction set to begin with (micro-ops or r-ops).
There is one dominant platform (Wintel) and software costs dominate (compatibility is essential).
One of the real problems with x86-32 was the low number of registers, which resulted in many stack spills. x86-64 added 8 more general purpose registers, and the situation is much better (that's why most people see a 10-20% speedup when migrating to x86-64 - more registers). Sure, it'd be better if we had 32 registers... but again, with 16 registers life is decent.
I've tried GameFly in the states, and had nothing but trouble with them (somehow quite a few games got lost in mail... OTOH I had no trouble with a parallel Netflix subscription. WTF?). Almost all mail-driven rental services in the States have really poor ratings and come with similar horror stories.
And what can I say — their service is getting worse and worse. At the beginning of the year it used to be much better. These days, the clients are buggy, the phone number I got from them no longer works... so, sure, I'm only using it for skype-to-skype calls.
To ebay – get your act together or you'll lose most of your current paying skype customers (and forget about growth)
Obviously IANAL but I don't see how publishing a paper or a piece of source code showing how to circumvent a DRM protection does not fall under "free speech"
Of course, when they drafted the DMCA they did want it enforced.
... which are made by developers, developers, developers.
The main problem with PS3 is not the price, it's the games. There are a few good ones, but certainly not enough. With respect to developers, developers, developers, Sony made a few wrong moves:
The CELL is perhaps the most difficult platform to develop for. Instead of a clean SMP interface, they opted for a two-instruction set asymmetric architecture. They took a relatively complex problem—developing for a multi-processor—and made it much, much, worse. I always hear that current generation games don't fully utilize the PS3... to which I reply "D'oh, if you only knew what it takes to fully utilize it... "
They did not release proper tools and libraries. Our developers are smart people, we'll let them figure it out... That worked out well for the PS2, but it certainly doesn't work for PS3
Their arrogance (most likely) alienated quite a few developers that'd have produced exclusives.
Conclusion: bad moves -> few games -> third place as a console
The Niagra processor is a great idea for (web, db) server workloads, where you have a lot of inherent parallelism and very poor cache behavior. A while back, the Piranha research project figured out that for such types of applications, it's better to have many "wimpy", in-order cores than a few "beefy", out-of-order execution ones. Niagra is doing exactly this. However, outside this application realm Niagra doesn't do that well.
Bottomline: The Niagra microarchitecture is meant for a particular niche.
... there's nothing fundamental about it. Instead, it's a self-fulfilling prophecy. The big players in the silicon world all use the "law" and its corollaries as their business plan. They'll likely discard a feature/product if it falls behind the curve in terms of speed. For the layperson, this "precision" may indeed create the appearance of an actual law, even though it's just an observation (similar to Malthus' "law")
is that it is incredibly expensive to begin with. A week in a hospital can cost as much as 100k$. The result is "drive-through" surgery. WTF?
Also, if I have an insurance policy that the hospital accepts, the cost of a procedure is X$. If I don't have insurance, it'x 2X or even 3X$. Again, WTF?
If food prices are driven up, many poor countries are in fact going to benefit. With their very cheap labor, they could, at least in theory, produce cheap food and even export it. However, food subsidies in the developed world essentially kills their markets. Not only are they not able to export, they end up importing cheaper, subsidized food.
Slashdot Mirror
are they gonna get sexual education?
Jules Verne most likely first imagined it, and Gerard Bull designed it: http://www.astronautix.com/lvs/babongun.htm
The argument that the compiler can do a reasonable job at scheduling instructions ... well, is simply false. Reason #1: The problem is that most applications have rather small basic blocks (spec 2000 integer, for instance, has basic blocks in the 6-10 instruction range). You can do slightly better with hyperblocks, but for that you need rather heavy profiling to figure out which paths are frequently taken. Reason #2: compiler operates on static instructions, the dynamic scheduler - on the dynamic stream. The compiler can't differentiate between instances of the instructions that hit in the cache (with a latency of 3-4 cycles) and those that miss all the way to memory (200+ cycles). The dynamic scheduler can. Why do you think that Itanium has such large caches? Because it doesn't have out-of-order execution, it is slowed down by cache misses to a much larger extent than the out-of-order processors.
I agree that there are always ways to statically improve the code to behave better on in-order machines (hoist loads and make them speculative, add prefetches, etc), but for the vast majority of applications none are as robust as out-of-order execution.
These days:
One of the real problems with x86-32 was the low number of registers, which resulted in many stack spills. x86-64 added 8 more general purpose registers, and the situation is much better (that's why most people see a 10-20% speedup when migrating to x86-64 - more registers). Sure, it'd be better if we had 32 registers ... but again, with 16 registers life is decent.
I've tried GameFly in the states, and had nothing but trouble with them (somehow quite a few games got lost in mail ... OTOH I had no trouble with a parallel Netflix subscription. WTF?). Almost all mail-driven rental services in the States have really poor ratings and come with similar horror stories.
Nifty patch that (among others) adds similar safeguards to the linux kernel. Too bad it's not in the mainstream kernel.
Most of the power (~90%) is still consumed by the processor and screen. Bottomline - these HDDs are pretty much pointless right now.
Of course, dropping the software-based PS2 emulation further shows how clueless they can still be.
(if not complete overlap). Avicenna, Averoes, al-Khwrizm (the "algorithm" guy) all were muslim.
To ebay – get your act together or you'll lose most of your current paying skype customers (and forget about growth)
Of course, when they drafted the DMCA they did want it enforced.
but linux desktop is ... way too many configurations/mixes of libraries/etc. Getting it right is much harder than doing the same thing for Windows/Mac.
... to electronics at least. Gold has high conductivity, malleability, ductility, resistance to oxidation and is also not toxic to humans.
The main problem with PS3 is not the price, it's the games. There are a few good ones, but certainly not enough. With respect to developers, developers, developers, Sony made a few wrong moves:
Conclusion: bad moves -> few games -> third place as a console
with a CD/DVD purchase? It seems to me - a license to play the content, privately, for the lifetime of the physical medium.
Bottomline: The Niagra microarchitecture is meant for a particular niche.
... there's nothing fundamental about it. Instead, it's a self-fulfilling prophecy. The big players in the silicon world all use the "law" and its corollaries as their business plan. They'll likely discard a feature/product if it falls behind the curve in terms of speed. For the layperson, this "precision" may indeed create the appearance of an actual law, even though it's just an observation (similar to Malthus' "law")
Let's donate some money to her defense fund ... Too bad she doesn't have a website for that.
What I do know is that an MRI was 1000$ for the insurance, but would have been 2-3000$ if I requested it myself.
Also, if I have an insurance policy that the hospital accepts, the cost of a procedure is X$. If I don't have insurance, it'x 2X or even 3X$. Again, WTF?
... you're just as moron.
He could patent it within a year of public disclosure.
In particular, the Foreign Corrupt Practices Act. Of course, IANAL.
... has made sure of that for quite a few countries.
If food prices are driven up, many poor countries are in fact going to benefit. With their very cheap labor, they could, at least in theory, produce cheap food and even export it. However, food subsidies in the developed world essentially kills their markets. Not only are they not able to export, they end up importing cheaper, subsidized food.