> A 1000-thread (simultaneous) chip is a ridiculous idea.
Strong claim. One must ask: Why?
> That means you have to duplicate every transistor in the chip (like registers) 1000 times.
And this is bad... how?
> That makes no sense.
It makes enormous sense when you're running 1000 threads!
> You will never reach the same speed as current single processor chips with a 1000-thread CPU > (at least not right now).
Naturlich, since the latter is a figment. But supposing it were real, one would have to ask: Why not? You can't seriously intend that it would be impossible to run each thread at 4 or 5 MHz, as you seem to be saying, so I can only infer that your meaning is not clear to me.
Since threads block so often, by the way, there is an optimal ratio of register files (thread states) to execution units, which will vary with load characteristics and degree of parallelism. System architectures that allow threads to avoid blocking will get more execution per transistor. One good way to do this is to provide hardware call/cc support, but it fails the goal of reducing register realestate.
Given that Schwarz is calling T1 a "9.6GHz" chip, and each of the 8 cores is a 64-bit wide unit, I wouldn't be surprised to hear him calling it a "512-bit" cpu, not surprised at all.
What Arjuna supports are WS-CAF and WS-TX. These are protocols which abstract the implementation of transactions. They can be supported regardless of the data storage technology used by the application server.
Bringing these technologies into the open source world means that many enterprises will now be newly able to operate entirely without proprietary software technology, if they so choose. Enterprises ranging from webshops to Fortune 500s to national government departments.
It would help if you said what the OS was, or at least specified what APIs were available natively. I would suggest that you should not discount the option of using X11 instead of a browser, at least not without evaluating the pros and cons.
Assuming only a socket API, the easiest thing to do is use a simple text-based protocol, talking to a minimalistic TCP server, probably written in PHP, Perl, or Java, and acting as a FastCGI script. You'll find it much quicker and less error prone, chatty, and code-heavy than any markup-based protocol. It's so trivial that it's not rational to even consider any sort of higher-level helper API, I think.
Now I know your BT headset is going to push a lot less power than the phone it's talking to, but are you really sure you want to microwave your brain, at any power level?
"Wireless" and "headset" are two words that do not go together without inviting "cancer" along for the fun.
Standards produced by commitees of corporate representatives tend not to be well-factored, but rather tend to support a mish-mash of features twisted into a tangle, so that everyone can get their pet feature, and hold it up like a gold star on their report card when they get home to the corporate offices. The resulting complexity also helps to keep out small players, and slows down the inevitable competition from open sources.
Semantic squabbles like this properly hinge upon analysis of terms. But of course it's not really about semantics, is it?
The question itself is disingenuous. The questioner does not care whether games are in a class, "art". It's really about power. If "art" has a power to control people, if "artists" can allocate the resources of other people, and "games" are a subclass of "art", then "game artists" have increased power.
But one essential difference between games and other sound and vision arts is that games put control, put power, in the hands of the consumer. It degrades the power status of the auteur to extend the creative role to the unwashed heathen masses. Thus the auteur social class of the ancien regime will inevitably be opposed on grounds of self-interest to the inclusion of the game auteur in their class.
The correct answer to the question therefore is not "yes, it is art" or "no, it is not art". The correct answer is "fuck you, and your cultural imperialism".
There's a huge gap between someone theorizing that some day something might happen, and someone getting out of their cushy office and making measurements that determine that it is already a third of the way to being a done deal.
The original post provided 3 examples of the supposed utility of programmer-controlled memory management and treated them as opposed to automatic garbage collection, but none of them served the original poster's argument: They were all examples of automatic variables being used with RAII, not to manage heap memory, but to manage non-memory resources by lexical scope. Cluestick sez: Languages with GC still have stacks. *Whack*.
Let me see, we have (1) people who love children, (2) people willing to give their lives for the greater good, and (3) gamers.
Personally, I'd say it's much easier to care about children than to sacrifice your life for the greater good, so I'd peg them (2), (1), (3), but I think there's a big gap between (2) and (3) in this case.
Heroin and cocaine are demonized mercilessly by the ignorant.
While there clearly exist animalistic individuals who are devoid of self-control or rational planning capacities required to use heroin and cocaine responsibly, many of us find that these, like numerous other less vividly painted chemicals, are useful adjuncts in living rich and fulfilling lives, with high productivity, minimum pain, robust mental health, and good social relationships.
But the Cell will be used in a lot more than just the PS3. They'll be putting it in PVRs, TVs, stereos, pretty much everything Sony makes, over time. In the long run, the volumes for the Cell could be superior to even x86-64 commodity chips. That amortizes a whole lot of production cost.
No way am I going to stay on the job long enough to drill even one billion holes in a microscopic piece of silicon. But maybe they can get a phillipino to do it.
While that certainly can be helpful, WindowsXP itself turns to sludge over time -- it does not need spyware or HP printer drivers or Quicktime or Skype or AIM or whathaveyou in order to slow down.
My solution was to install Windows 2000 SP4 instead. That sucker is the Rock of Gibraltar, as long as you don't do anything stupid.
You have reduced yourself to a charicature, and constructed a reductio ad absurdam to defeat your own position. Hopefully you can deal with reality well enough to recognize the fact, and accept the crass immorality and intellectual dishonesty of your position before you embarass yourself further.
You can continue to lie, but it won't improve your image. See this link, which explains that an instruction manual used by the US Army Command and General Staff School (CGSC) at Fort Leavenworth, Kansas, makes clear that white phosphorus (WP) can be used to produce a smoke screen. But it adds: "It is against the law of land warfare to employ WP against personnel targets."
Don't like the monthly pay scheme? It's a business opportunity. Buy a pool of subscriptions, and use them to layer metered accounts. Resell at a mark-up.
Slashdot Mirror
> A 1000-thread (simultaneous) chip is a ridiculous idea.
Strong claim. One must ask: Why?
> That means you have to duplicate every transistor in the chip (like registers) 1000 times.
And this is bad... how?
> That makes no sense.
It makes enormous sense when you're running 1000 threads!
> You will never reach the same speed as current single processor chips with a 1000-thread CPU
> (at least not right now).
Naturlich, since the latter is a figment. But supposing it were real, one would have to ask: Why not? You can't seriously intend that it would be impossible to run each thread at 4 or 5 MHz, as you seem to be saying, so I can only infer that your meaning is not clear to me.
Since threads block so often, by the way, there is an optimal ratio of register files (thread states) to execution units, which will vary with load characteristics and degree of parallelism. System architectures that allow threads to avoid blocking will get more execution per transistor. One good way to do this is to provide hardware call/cc support, but it fails the goal of reducing register realestate.
> Can anyone tell how is the new ?
Sure. The new is how this: It's a press release! Whee! Your life will never be the same!
Given that Schwarz is calling T1 a "9.6GHz" chip, and each of the 8 cores is a 64-bit wide unit, I wouldn't be surprised to hear him calling it a "512-bit" cpu, not surprised at all.
Ooooh, touched a sensitive nerve there, did I? Got too close to the revenue stream and the political support base then?
And any slashdot poster can be expected to be intimately familiar with the pathological deficit of empathy ic understanding found in the readership.
That's just wrong.
What Arjuna supports are WS-CAF and WS-TX. These are protocols which abstract the implementation of transactions. They can be supported regardless of the data storage technology used by the application server.
Bringing these technologies into the open source world means that many enterprises will now be newly able to operate entirely without proprietary software technology, if they so choose. Enterprises ranging from webshops to Fortune 500s to national government departments.
...for me, since my company boycotts Intel, since they started building a 45nm fab in apartheid Israel.
All the Civil War proved is that the central authority is willing to destroy the country in order to perpetuate itself and expand its power.
It would help if you said what the OS was, or at least specified what APIs were available natively. I would suggest that you should not discount the option of using X11 instead of a browser, at least not without evaluating the pros and cons.
Assuming only a socket API, the easiest thing to do is use a simple text-based protocol, talking to a minimalistic TCP server, probably written in PHP, Perl, or Java, and acting as a FastCGI script. You'll find it much quicker and less error prone, chatty, and code-heavy than any markup-based protocol. It's so trivial that it's not rational to even consider any sort of higher-level helper API, I think.
Now I know your BT headset is going to push a lot less power than the phone it's talking to, but are you really sure you want to microwave your brain, at any power level?
"Wireless" and "headset" are two words that do not go together without inviting "cancer" along for the fun.
Standards produced by commitees of corporate representatives tend not to be well-factored, but rather tend to support a mish-mash of features twisted into a tangle, so that everyone can get their pet feature, and hold it up like a gold star on their report card when they get home to the corporate offices. The resulting complexity also helps to keep out small players, and slows down the inevitable competition from open sources.
Semantic squabbles like this properly hinge upon analysis of terms. But of course it's not really about semantics, is it?
The question itself is disingenuous. The questioner does not care whether games are in a class, "art". It's really about power. If "art" has a power to control people, if "artists" can allocate the resources of other people, and "games" are a subclass of "art", then "game artists" have increased power.
But one essential difference between games and other sound and vision arts is that games put control, put power, in the hands of the consumer. It degrades the power status of the auteur to extend the creative role to the unwashed heathen masses. Thus the auteur social class of the ancien regime will inevitably be opposed on grounds of self-interest to the inclusion of the game auteur in their class.
The correct answer to the question therefore is not "yes, it is art" or "no, it is not art".
The correct answer is "fuck you, and your cultural imperialism".
There's a huge gap between someone theorizing that some day something might happen, and someone getting out of their cushy office and making measurements that determine that it is already a third of the way to being a done deal.
Thank you, Clark Kent.
The original post provided 3 examples of the supposed utility of programmer-controlled memory management and treated them as opposed to automatic garbage collection, but none of them served the original poster's argument: They were all examples of automatic variables being used with RAII, not to manage heap memory, but to manage non-memory resources by lexical scope. Cluestick sez: Languages with GC still have stacks. *Whack*.
All of the toilets in my house read "Designed for Windows XP".
Let me see, we have (1) people who love children, (2) people willing to give their lives for the greater good, and (3) gamers.
Personally, I'd say it's much easier to care about children than to sacrifice your life for the greater good, so I'd peg them (2), (1), (3), but I think there's a big gap between (2) and (3) in this case.
Heroin and cocaine are demonized mercilessly by the ignorant.
While there clearly exist animalistic individuals who are devoid of self-control or rational planning capacities required to use heroin and cocaine responsibly, many of us find that these, like numerous other less vividly painted chemicals, are useful adjuncts in living rich and fulfilling lives, with high productivity, minimum pain, robust mental health, and good social relationships.
But the Cell will be used in a lot more than just the PS3. They'll be putting it in PVRs, TVs, stereos, pretty much everything Sony makes, over time. In the long run, the volumes for the Cell could be superior to even x86-64 commodity chips. That amortizes a whole lot of production cost.
> Will it make it possible for your computer to have sex with you tomorrow? No. But it's important nonetheless.
Didnt you just contradict yourself?
No way am I going to stay on the job long enough to drill even one billion holes in a microscopic piece of silicon. But maybe they can get a phillipino to do it.
While that certainly can be helpful, WindowsXP itself turns to sludge over time -- it does not need spyware or HP printer drivers or Quicktime or Skype or AIM or whathaveyou in order to slow down.
My solution was to install Windows 2000 SP4 instead. That sucker is the Rock of Gibraltar,
as long as you don't do anything stupid.
You have reduced yourself to a charicature, and constructed a reductio ad absurdam to defeat your own position. Hopefully you can deal with reality well enough to recognize the fact, and accept the crass immorality and intellectual dishonesty of your position before you embarass yourself further.
You can continue to lie, but it won't improve your image. See this link, which explains that an instruction manual used by the US Army Command and General Staff School (CGSC) at Fort Leavenworth, Kansas, makes clear that white phosphorus (WP) can be used to produce a smoke screen. But it adds: "It is against the law of land warfare to employ WP against personnel targets."
Don't like the monthly pay scheme? It's a business opportunity. Buy a pool of subscriptions, and use them to layer metered accounts. Resell at a mark-up.