Just to clarify, that will be a 300mm wafer. Intel is already well into mass production of 300mm wafers, and to my knowledge, they are still the only one.
Intel's mantra is to gain a generation on the competition. They seem to be doing just that. It would be impossible without spending a lot of time and money to debug vendor tools.
But then again, it would be impossible to spend those resources to debug vendor tools if you weren't a generation ahead and making a huge margin on your products.
Tell your joke to AMD -- I'm sure they would think it was a hoot.;)
No, it is neither. The "micron" dimension associated with a particular fabrication technology is the average width of a transistor. The smaller transistor, coupled with better design resulting in redundant circuitry and better fabrication processes resulting in fewer faults, allows more transistors to fit on a chip. causing Moore's law to continue to tick forward.
There is another dimension generally provided, which is the wafer size. Recently, Intel became the first to start high-volume production of a 300mm (aka 12") wafer size, versus the previous 200mm (8") wafers that most of the industry still uses. Combined with the.13 micron process that most new P4s are fabricated with, this results in an extremely high die count (number of chips that can be masked onto a single wafer) which is of course offset by the enormous Northwood die size!
The entire digital chip is generally masked using the same process, including the core, L1 memories, L2 memories, and sometimes (e.g. Itanium) even the enormous L3 memories.
It says here that Intel's Fab 24 is now slated to support a.09um/300mm process by end of 2003. Although no dates were indicated for IBM, they may indeed beat Intel to 0.1um. So why is IBM going for.1um when Intel is going to.09um?
Not only are Intel already at.13 micron, but they are also at 300mm. They already have a.1 micron facility in progress, so IBM will be playing catch-up. Luckily for IBM, Intel facility seems delayed.
Intel vice-president of communications Chuck Molloy told the Irish Times that "the current economic climate is a contributing factor" in the company's decision to postpone construction. But Molloy called the delay "normal," noting that the Leixlip plant, once completed, would be the first facility to use the new 0.1-micron technology.
The opinion is not lowering the threshold on what can be considered a "technological protection measure". All these last few paragraphs say is that it is irrelevant whether the mod chips are truly circumvention devices because the access code was not proven to be a protection device that was circumvented.
The main points of the case are as follows: 1) The access code does not protect the copyrighted work from being copied, 2) the access code merely causes the copied work to be unplayable, 3) the mod chip makes the copied work playable, and 4) the key here is that the work is already copied, regardless of the presence of the mod chip.
Even further, the text also supports the notion that even if the access code WERE a technological protection measure, the mod chip may still not have been considered a circumvention device because the protection measure would have also prevented the legal playing of American games and backup copies.
Sony was in fact two hurdles away from winning this case. I don't think this lowers the hurdle on what can be considered "technological protection measures" Rather, it clarifies (according to Australian law, unless they have an appeal process from this level) that mod chips are legal because they are not circumventing a protection device.
Clearly Sony must take additional steps to protect their games.
Living in the south (Texas), AC isn't even an option any more. Toyota/Lexus has the best/coldest/mostpowerful ACs, hands down. Nissan/Infinity ACs are close, but Honda/Acura ACs tend to be poor.
So, does the Prius have a "Toyota AC"? What effect does the AC have on the mileage?
I note that when I drive my (ahem...cough cough4runnercough cough) vehicle I typically get 21mpg with AC off. With AC on, I get about 20mpg.
Hmmm... OK, I admit I almost believed you. Then I read the article you pasted and didn't see the word "American" or "US" used anywhere.
So, maybe it isn't true?
First off, it doesn't take much to achieve a 95% cache hit rate. Second, in order for the majority of instruction accesses to miss L2, you would have to have a very very small cache. I'm talking like 1KB small.
What most non-programmers (and even some "hand-coders" like yourself) don't realize is that most software runs in loops. All you have to do is make your L1 cache big enough to hold a typical inner loop (less than 100 instructions) and you have yourself a 60-80% hit rate. Increase the size of the cache more, and you can enclose the typical outer loop and maybe a few often-called libraries, event handlers, or system calls. From then on, you run into severely diminishing returns. Increasing your cache beyond a hit rate of 95% to 100% (theoretically impossible of course) to compensate for a mere 2-cycle access L2 only buys you an additional ~5% of performance.
Doesn't sound like much of a "tremendous problem" anymore, does it?
From Intel's point of view, approximately 0% of the buyers out there care about the cache size. I'm sure Intel performs due diligence when modeling and selecting an appropriate cache size. When the diminishing returns set in, they know when to draw the line. I don't know about you, but I would prefer Intel spend an appropriate amount of resources on L1 cache and an appropriate amount on L2 cache, then spend the rest of their resources increasing the clock speed and validating the chip to make sure what I buy is bug-free. Surely Intel can better spend those resources on removing speed paths and reducing their cycle time. This has the potential to increase the performance well over the 5% needed to compensate for the additional L1 cache misses.
You couldn't possibly bitch that Intel's Andy Grove and Leslie Vadasz have been THE most vocal tech company in the fight to protect our consumer rights against Disney's Michael Eisner pushing the CBDTPA bullshit and and closing the analog hole: Hollywood vs. High-Tech and EFF Applauds Intel's Stand
As far as marketing and time to market go, I can't think of a more formidable opponent than Intel. Hoping Intel will fail in this arena is futile. And hoping they will fail for ethereal political reasons is absurd. And thinking that a quake demo against a 1.6GHz P4 underclocked to 0.8GHz and memory bandwidth equally underclocked is any indication of "suck ass" performance is pathetic.
You know when you have to tie both hands of your opponent behind their back to give him a fair fight, you've got some serious problems of your own.
Nope. After re-reading the article, I can safely say that nothing later in the article contradicts that statement, although nothing else in the article supports it.
So that essentially leaves me wondering what justifies this completely outrageous decision. As you point out, the article unfortunately does not elaborate further on this. It does not, however, contradict the statement.
I would agree that if the author were to exactly or nearly quote a person's question, then the author should cite the source of the question. Odds are, however, that the author summarized each set of questions from many different people into one clearly-phrased, properly-targetted question that complements the desired answer. Plus, as you said, the questions are "frequently-asked" and as such, they are essentially common knowledge (or lack-of-knowledge in this case). And we all know from writing papers in school that you don't have to cite the source of obvious information.
Compilations of information and the exact expression of that information is definitely copyrightable. Not only that, but the answers to those questions are obviously not common knowledge or else so many people would not be asking them. The fact is, someone put time into creating the document, answering the questions, and publishing the work. There was some thinking involved in selecting the appropriate questions, but also in categorizing and answering them in a way that would convey the information clearly.
One must think about the reason for copyright law in the first place. The laws are created to encourage the sharing of knowledge. Without copyright protection, the company might not want to publish their FAQ. They would be worried that someone would steal their work and claim it as their own. In this case, many obvious questions would inevitably go unanswered.
The court was justified in saying that the format and conventions used in creating a FAQ is simply a standardization on the best known method of representing the answers to commonly-asked questions. Denying that the format is copyrightable was adequate in this case since it addressed the issues that needed to be addressed. That's all they needed to say.
What the court added to this, however, was completely uncalled for. The court said that the particular publication was not copyrightable simply because it was a FAQ. So are you saying that by naming it a FAQ, the author waives all right to copyrighting the document? So the author could just change the name of the document to "Frequently-given-answers" -- would that be sufficient to now be able to copyright the work? Even if so, this would be counterproductive, since people can no longer used the word FAQ as a keyword for searching.
FAQ is simply a convention for naming a type of document with a standardized format. This convention should not be an implicit waiving of copyright priviliges. It's the content that is valuable here, not the format.
The court said exactly that -- and that is what concerns me. Directly from the article:
Taking it a step further, the court held that "a business cannot copyright a Frequently Asked Questions page"
There's nothing unclear about that whatsoever. The "Taking it a step further" part implies that in addition to disallowing copyright of the format or key phrases of typical FAQ questions, the court also disallows copyright of the entire FAQ page.
If you ask me, the court was trying to flex its muscles and make a decision that would have a long lasting effect on the internet. Perhaps the judge is going to retire soon and is worrying about what kind of legacy he leaves behind. But either way, they really overstepped their bounds. Not that I'm a lawyer, but this seems to contradict all forms of copyright law I've ever read about.
By seeking to include "GNU" in the GNU/Linux convention, he is only looking for recognition. For what, you might ask?
You think he's in it for the personal fame and glory? Hell no. Or the money? RMS, I really don't think so. (Yes, ESR seems motivated by fame and money, but then again I don't have the same sort of respect for ESR that I do for RMS.) He isn't looking to call it RMS/Linux; he never called it the rcc compiler or the remacs editor. He wants people to know who provided the huge mass of software surrounding the kernel, who provided the means and methodology to enable the kernel to be developed and supported and used, and most importantly, the infrastructure and enormous amount task of coordinating the individual efforts (particularly the early efforts when risk of failure was highest) and supporting those that keep it all going.
He wants people to recognize that the FSF provided GNU and that the FSF has a specific idealology that has provided you with a tangible benefit. He wants you to use more of their software, to modify and distribute their software, and to contribute to their cause. He realizes that the strength of FSF relies on you and others that believe in his goals and want to see them succeed.
He carefully separates his personal agenda from his FSF agenda. If you don't believe me, look at his web page (stallman.org) and it will become 100% evident to you that he is not in it for selfish motives.
We implemented an echo cancellation algorithm for a GSM phone. It required somewhere around 2-4 MIPS from our 26 MIPS budget. You should be able to find some app notes you can use to implement on a very inexpensive TI or ADI development kit.
DSPs are historically very very slow in frequency when compared to other embedded CPUs (although this is far from true today). Until the past few years, DSPs have been lingering in the 10s of MHz range, while embedded MCUs were venturing into the 100 MHz range.
You can probably implement on any MCU that runs around 20MHz. This should provide you the low latency you need and more than ample MIPS capacity.
I sympathize with you that Moto is not increasing the speeds of the PPC. They did the same with the dragonball that prompted Palm to consider the switch to an ARM architecture.
However, you are significantly underestimating the importance of cache. Cache lowers cost by allowing the significantly larger storage memory to reside off chip. It provides a low latency access to memory to keep up with processor speeds in addition to reducing external accesses which save a very significant amount of power and reduce board noise.
The key here is low latency. A core relies on the highest level of memory to have a latency of typically one core clock cycle. Main memory doesn't even come close to that. A memory transfer rate of 533MHz does NOT mean the access latency of the main memory is 1.88ns (1/533x10^6Hz). In fact, the access latency is actually several bus clock cycles. Since the memory bus clock is 133MHz, we are talking about a latency on the order of perhaps 25ns. When the core clock is close to 1 ns, there is a huge disparity between the core demands and the main memory capabilities. Without cache, the core would need to wait many tens of cycles per memory access. For applications that require heavy memory usage, this would have a devastating effect on your performance.
This doesn't even begin to comment on how expensive the 533MHz QDR DRAM really is. By providing more cache, Moto is reducing the cost of the system, which inevitably impacts the end cost you must pay.
Don't be so quick to second-guess the designers who bring you one of the better-architected PC CPUs and systems out there. We know what we're doing.
CPU cache will only become more important as CPU speeds increase. A hierarchical memory organization is intended to address the disparity between lower levels of memory and the CPU speed. Higher levels of cache run at faster speeds, until you get to the highest which generally runs at or near core speed. The goal is to access memory from cache as much as possible, and there is a lot of memory controller hardware designed to support that goal. CPU speeds still are still increasing at a much faster rate than memory speeds, and as this disparity increases, cache only becomes more important.
It's not just the expandability. There are several reasons.
RAM generates more heat from the same package People will always want more RAM, so you can't reduce the pin count. Increasing die size will decrease yield and drive up costs. Chipset functionality would need to be moved into CPU as well, further adding size. RAM is a high-volume, very low margin commodity. CPU developers don't want to dilute their margins across mere RAM. (i.e. $400 for a P4 + $100 for 256MB RAM = a mere $500 for twice as much silicon)
But, there is hope. Intel and AMD are adding dramatically larger L2 and L3 caches to their CPUs, so you are getting more memory for your money, although it actually provides better memory performance, and not truly a larger physical memory space.
533MHz is not an attempt by anyone to deceive you. It is a genuine number indicative of the throughput the bus provides. Nobody (educated, at least) is claiming the bus clock runs at 533MHz, only that 533 MHz is simply the rate of transfer. The clock rate is effectively multiplied by 4 at each end of the transfer and used to synchronize the transfers. This is analogous to your system clock running at 100MHz, yet your core claims to run at 1GHz.
How can this be? The core has an internal multiplier (called a PLL) that allows the core to run at a higher speed. This allows the board to run at a lower speed which results in less board noise, less switching (so lower power), and also represents a common denominator reference so all devices don't need to run at the same high frequency. For example, the CPU might scale the reference clock by 10, but the chipset might not scale the clock at all.
Hertz (Hz) is merely a rate, and represents an inverse second (1/s) and is commonly used to indicate the rate of periodicity of a clock. However, Hz is used to indicate bandwidth of a modem, for example. A 48K modem transfers 48 kilobits of data, and can be said to transfer bits at a rate of 48KHz. In actuality, there are not 48000 individual bits transferred every second. Instead, there are 8000 individual symbols transferred each second, and each symbol provides 6 bits.
In either case, neither of the clauses from that Blizzard letter describes any of their current claims.
For example, Blizzard is not claiming the defendant modified or altered Blizzard copyrighted software.
And Blizzard is not claiming the defendant bypassed anti-circumvention technology.
Furthermore, since Blizzard used DMCA provisions to demand an immediate delisting of bnetd by their bandwidth provider, at least they appear to me to have abused the DMCA. According to this:
Question: What are the counter-notice and put-back procedures?
there is a penalty for ignorantly or wrongfully using the DMCA to remove material which is clearly not infringing on material protected by DMCA. Unfortunately, it appears the penalty is limited to actual damages, so perhaps would be minimal.
I'm hoping this develops into a counter suit either way. This would be a nice precedent against DMCA abuse.
The whole dual-layer argument becomes moot when someone comes out with a single-layer writable disc with twice the capacity. Sure, it won't run on a standard DVD player *today*, but I'm sure tomorrow's DVD-B (or whatever) drive will be able to play it.
GPL isn't a virus in any sense. Yes, you are not the first to use the term. Rather, you are ignorantly joining the me-too bandwagon and repeating your favorite mantra.
A virus is defined as a bit of code that autonomously finds a host for itself so that when that host is executed it can come to life and wreak havoc or self-replicate. So, by definition, GPL is not a virus.
You might argue the GPL is instead a trojan horse, poised to take advantage of pathetic, unare individuals, that once granted access to the system (i.e. a source distribution) will unleash untold fury upon the poor idiot who added the source code to the project. This is far from the truth. The GPL (you apparently need to read it) mandates that any software that is to be distributed under the license clearly display the abridged license in source files and upon running command-line applications. Because the license information is prominently included in all source files with copyright information, any honest programmer (i.e. one that is not simply trying to steal source code) would note the copyright and exercise his full right to either comply with it by using the code and GPL'ing the resulting work or by not using the code.
Either way, the programmer has a choice. There is no virus-like behavior whatsoever.
If you are a programmer and agree with the GPL, you have been granted full permission to leverage any GPL'd code in your application provided you share the source of the result. If you do not agree with the GPL, take a hike -- don't use GPL code in yours.
What I really don't get is what the hell this KDE guy is really complaining about. If he is using GPL'd code that he obtained for free, he shouldn't be bitching about it (i.e., never look a gift horse in the mouth). If he is GPL'ing his own code, he still owns the copyright (unless he gave it away, doh!) and can sell it all he wants. He apparently chose to incorporate GPL'd code into his software and thought he could make money off of it, but it turns out he was wrong. He made a bad decision. Really, it's not like Mr. GPL came up to him and infiltrated his business and destroyed his entire business model!
. To use it you must sign onto the Borg Collective though
This is the kind of ignorant drivel that gives GPL a bad name. GPL is intended for someone to be able to create source to implement a great idea they want to donate to the rest of the world. They want to make sure that their idea will be used to benefit others, not hidden away in someone's proprietary software to fatten someone else's wallet. That would be absurd.
The permission GPL grants is that others may use and modify for their own use a piece of software freely (no restrictions). For your own purposes, it's that simple -- no borg collective or other FUD. If someone wants to modify and redistribute the software, they must distribute it with the source code.
If I wrote an ingenious new app and wanted to give it to the world, why shouldn't I be able to stipulate that nobody can repackage it and sell it without redistributing the source? If you don't like it, rewrite it so you can resell it! You have every right to do so.
Slashdot Mirror
Just to clarify, that will be a 300mm wafer. Intel is already well into mass production of 300mm wafers, and to my knowledge, they are still the only one.
But then again, it would be impossible to spend those resources to debug vendor tools if you weren't a generation ahead and making a huge margin on your products.
Tell your joke to AMD -- I'm sure they would think it was a hoot. ;)
No, it is neither. The "micron" dimension associated with a particular fabrication technology is the average width of a transistor. The smaller transistor, coupled with better design resulting in redundant circuitry and better fabrication processes resulting in fewer faults, allows more transistors to fit on a chip. causing Moore's law to continue to tick forward.
There is another dimension generally provided, which is the wafer size. Recently, Intel became the first to start high-volume production of a 300mm (aka 12") wafer size, versus the previous 200mm (8") wafers that most of the industry still uses. Combined with the .13 micron process that most new P4s are fabricated with, this results in an extremely high die count (number of chips that can be masked onto a single wafer) which is of course offset by the enormous Northwood die size!
The entire digital chip is generally masked using the same process, including the core, L1 memories, L2 memories, and sometimes (e.g. Itanium) even the enormous L3 memories.
It says here that Intel's Fab 24 is now slated to support a .09um/300mm process by end of 2003. Although no dates were indicated for IBM, they may indeed beat Intel to 0.1um. So why is IBM going for .1um when Intel is going to .09um?
http://www.siliconstrategies.com/story/OEG20020118 S0081
This is an excerpt from http://www.newsfactor.com/perl/story/8205.html:
The opinion is not lowering the threshold on what can be considered a "technological protection measure". All these last few paragraphs say is that it is irrelevant whether the mod chips are truly circumvention devices because the access code was not proven to be a protection device that was circumvented.
The main points of the case are as follows:
1) The access code does not protect the copyrighted work from being copied, 2) the access code merely causes the copied work to be unplayable, 3) the mod chip makes the copied work playable, and 4) the key here is that the work is already copied, regardless of the presence of the mod chip.
Even further, the text also supports the notion that even if the access code WERE a technological protection measure, the mod chip may still not have been considered a circumvention device because the protection measure would have also prevented the legal playing of American games and backup copies.
Sony was in fact two hurdles away from winning this case. I don't think this lowers the hurdle on what can be considered "technological protection measures" Rather, it clarifies (according to Australian law, unless they have an appeal process from this level) that mod chips are legal because they are not circumventing a protection device.
Clearly Sony must take additional steps to protect their games.
Me-three posts are even more frowned-upon, but I am here to say that it was indeed quite a dandy, eloquent post.
Living in the south (Texas), AC isn't even an option any more. Toyota/Lexus has the best/coldest/mostpowerful ACs, hands down. Nissan/Infinity ACs are close, but Honda/Acura ACs tend to be poor.
So, does the Prius have a "Toyota AC"? What effect does the AC have on the mileage?
I note that when I drive my (ahem...cough cough4runnercough cough) vehicle I typically get 21mpg with AC off. With AC on, I get about 20mpg.
Hmmm... OK, I admit I almost believed you. Then I read the article you pasted and didn't see the word "American" or "US" used anywhere. So, maybe it isn't true?
What most non-programmers (and even some "hand-coders" like yourself) don't realize is that most software runs in loops. All you have to do is make your L1 cache big enough to hold a typical inner loop (less than 100 instructions) and you have yourself a 60-80% hit rate. Increase the size of the cache more, and you can enclose the typical outer loop and maybe a few often-called libraries, event handlers, or system calls. From then on, you run into severely diminishing returns. Increasing your cache beyond a hit rate of 95% to 100% (theoretically impossible of course) to compensate for a mere 2-cycle access L2 only buys you an additional ~5% of performance.
Doesn't sound like much of a "tremendous problem" anymore, does it?
From Intel's point of view, approximately 0% of the buyers out there care about the cache size. I'm sure Intel performs due diligence when modeling and selecting an appropriate cache size. When the diminishing returns set in, they know when to draw the line. I don't know about you, but I would prefer Intel spend an appropriate amount of resources on L1 cache and an appropriate amount on L2 cache, then spend the rest of their resources increasing the clock speed and validating the chip to make sure what I buy is bug-free. Surely Intel can better spend those resources on removing speed paths and reducing their cycle time. This has the potential to increase the performance well over the 5% needed to compensate for the additional L1 cache misses.
You couldn't be bitching that Intel is trying to ensure no more copyright extensions for media giants like Disney: Intel's Amicus Brief for Eldred vs. Ashcroft
You couldn't possibly bitch that Intel's Andy Grove and Leslie Vadasz have been THE most vocal tech company in the fight to protect our consumer rights against Disney's Michael Eisner pushing the CBDTPA bullshit and and closing the analog hole: Hollywood vs. High-Tech and EFF Applauds Intel's Stand
Perhaps you are disturbed that Intel didn't whore itself to Microsoft in true AMD's Jerry Sanders fashion to help alleviate Microsoft's legal woes AMD chief testifies in Microsoft's favor followed by the very coincidental Microsoft support for Hammer Microsoft To Support AMD's Hammer
As far as marketing and time to market go, I can't think of a more formidable opponent than Intel. Hoping Intel will fail in this arena is futile. And hoping they will fail for ethereal political reasons is absurd. And thinking that a quake demo against a 1.6GHz P4 underclocked to 0.8GHz and memory bandwidth equally underclocked is any indication of "suck ass" performance is pathetic.
You know when you have to tie both hands of your opponent behind their back to give him a fair fight, you've got some serious problems of your own.
As long as we both agree. ;)
Nope. After re-reading the article, I can safely say that nothing later in the article contradicts that statement, although nothing else in the article supports it.
So that essentially leaves me wondering what justifies this completely outrageous decision. As you point out, the article unfortunately does not elaborate further on this. It does not, however, contradict the statement.
Compilations of information and the exact expression of that information is definitely copyrightable. Not only that, but the answers to those questions are obviously not common knowledge or else so many people would not be asking them. The fact is, someone put time into creating the document, answering the questions, and publishing the work. There was some thinking involved in selecting the appropriate questions, but also in categorizing and answering them in a way that would convey the information clearly.
One must think about the reason for copyright law in the first place. The laws are created to encourage the sharing of knowledge. Without copyright protection, the company might not want to publish their FAQ. They would be worried that someone would steal their work and claim it as their own. In this case, many obvious questions would inevitably go unanswered.
The court was justified in saying that the format and conventions used in creating a FAQ is simply a standardization on the best known method of representing the answers to commonly-asked questions. Denying that the format is copyrightable was adequate in this case since it addressed the issues that needed to be addressed. That's all they needed to say.
What the court added to this, however, was completely uncalled for. The court said that the particular publication was not copyrightable simply because it was a FAQ. So are you saying that by naming it a FAQ, the author waives all right to copyrighting the document? So the author could just change the name of the document to "Frequently-given-answers" -- would that be sufficient to now be able to copyright the work? Even if so, this would be counterproductive, since people can no longer used the word FAQ as a keyword for searching.
FAQ is simply a convention for naming a type of document with a standardized format. This convention should not be an implicit waiving of copyright priviliges. It's the content that is valuable here, not the format.
Taking it a step further, the court held that "a business cannot copyright a Frequently Asked Questions page"
There's nothing unclear about that whatsoever. The "Taking it a step further" part implies that in addition to disallowing copyright of the format or key phrases of typical FAQ questions, the court also disallows copyright of the entire FAQ page.
If you ask me, the court was trying to flex its muscles and make a decision that would have a long lasting effect on the internet. Perhaps the judge is going to retire soon and is worrying about what kind of legacy he leaves behind. But either way, they really overstepped their bounds. Not that I'm a lawyer, but this seems to contradict all forms of copyright law I've ever read about.
By seeking to include "GNU" in the GNU/Linux convention, he is only looking for recognition. For what, you might ask?
You think he's in it for the personal fame and glory? Hell no. Or the money? RMS, I really don't think so. (Yes, ESR seems motivated by fame and money, but then again I don't have the same sort of respect for ESR that I do for RMS.) He isn't looking to call it RMS/Linux; he never called it the rcc compiler or the remacs editor. He wants people to know who provided the huge mass of software surrounding the kernel, who provided the means and methodology to enable the kernel to be developed and supported and used, and most importantly, the infrastructure and enormous amount task of coordinating the individual efforts (particularly the early efforts when risk of failure was highest) and supporting those that keep it all going.
He wants people to recognize that the FSF provided GNU and that the FSF has a specific idealology that has provided you with a tangible benefit. He wants you to use more of their software, to modify and distribute their software, and to contribute to their cause. He realizes that the strength of FSF relies on you and others that believe in his goals and want to see them succeed.
He carefully separates his personal agenda from his FSF agenda. If you don't believe me, look at his web page (stallman.org) and it will become 100% evident to you that he is not in it for selfish motives.
We implemented an echo cancellation algorithm for a GSM phone. It required somewhere around 2-4 MIPS from our 26 MIPS budget. You should be able to find some app notes you can use to implement on a very inexpensive TI or ADI development kit.
DSPs are historically very very slow in frequency when compared to other embedded CPUs (although this is far from true today). Until the past few years, DSPs have been lingering in the 10s of MHz range, while embedded MCUs were venturing into the 100 MHz range.
You can probably implement on any MCU that runs around 20MHz. This should provide you the low latency you need and more than ample MIPS capacity.
best regards,
mega
However, you are significantly underestimating the importance of cache. Cache lowers cost by allowing the significantly larger storage memory to reside off chip. It provides a low latency access to memory to keep up with processor speeds in addition to reducing external accesses which save a very significant amount of power and reduce board noise.
The key here is low latency. A core relies on the highest level of memory to have a latency of typically one core clock cycle. Main memory doesn't even come close to that. A memory transfer rate of 533MHz does NOT mean the access latency of the main memory is 1.88ns (1/533x10^6Hz). In fact, the access latency is actually several bus clock cycles. Since the memory bus clock is 133MHz, we are talking about a latency on the order of perhaps 25ns. When the core clock is close to 1 ns, there is a huge disparity between the core demands and the main memory capabilities. Without cache, the core would need to wait many tens of cycles per memory access. For applications that require heavy memory usage, this would have a devastating effect on your performance.
This doesn't even begin to comment on how expensive the 533MHz QDR DRAM really is. By providing more cache, Moto is reducing the cost of the system, which inevitably impacts the end cost you must pay.
Don't be so quick to second-guess the designers who bring you one of the better-architected PC CPUs and systems out there. We know what we're doing.
CPU cache will only become more important as CPU speeds increase. A hierarchical memory organization is intended to address the disparity between lower levels of memory and the CPU speed. Higher levels of cache run at faster speeds, until you get to the highest which generally runs at or near core speed. The goal is to access memory from cache as much as possible, and there is a lot of memory controller hardware designed to support that goal. CPU speeds still are still increasing at a much faster rate than memory speeds, and as this disparity increases, cache only becomes more important.
best regards,
mega
It's not just the expandability. There are several reasons.
RAM generates more heat from the same package
People will always want more RAM, so you can't reduce the pin count.
Increasing die size will decrease yield and drive up costs.
Chipset functionality would need to be moved into CPU as well, further adding size.
RAM is a high-volume, very low margin commodity. CPU developers don't want to dilute their margins across mere RAM. (i.e. $400 for a P4 + $100 for 256MB RAM = a mere $500 for twice as much silicon)
But, there is hope. Intel and AMD are adding dramatically larger L2 and L3 caches to their CPUs, so you are getting more memory for your money, although it actually provides better memory performance, and not truly a larger physical memory space.
best regards,
mega
533MHz is not an attempt by anyone to deceive you. It is a genuine number indicative of the throughput the bus provides. Nobody (educated, at least) is claiming the bus clock runs at 533MHz, only that 533 MHz is simply the rate of transfer. The clock rate is effectively multiplied by 4 at each end of the transfer and used to synchronize the transfers. This is analogous to your system clock running at 100MHz, yet your core claims to run at 1GHz.
How can this be? The core has an internal multiplier (called a PLL) that allows the core to run at a higher speed. This allows the board to run at a lower speed which results in less board noise, less switching (so lower power), and also represents a common denominator reference so all devices don't need to run at the same high frequency. For example, the CPU might scale the reference clock by 10, but the chipset might not scale the clock at all.
Hertz (Hz) is merely a rate, and represents an inverse second (1/s) and is commonly used to indicate the rate of periodicity of a clock. However, Hz is used to indicate bandwidth of a modem, for example. A 48K modem transfers 48 kilobits of data, and can be said to transfer bits at a rate of 48KHz. In actuality, there are not 48000 individual bits transferred every second. Instead, there are 8000 individual symbols transferred each second, and each symbol provides 6 bits.
Best regards,
mega
For example, Blizzard is not claiming the defendant modified or altered Blizzard copyrighted software.
And Blizzard is not claiming the defendant bypassed anti-circumvention technology. Furthermore, since Blizzard used DMCA provisions to demand an immediate delisting of bnetd by their bandwidth provider, at least they appear to me to have abused the DMCA. According to this: Question: What are the counter-notice and put-back procedures? there is a penalty for ignorantly or wrongfully using the DMCA to remove material which is clearly not infringing on material protected by DMCA. Unfortunately, it appears the penalty is limited to actual damages, so perhaps would be minimal.
I'm hoping this develops into a counter suit either way. This would be a nice precedent against DMCA abuse.
The whole dual-layer argument becomes moot when someone comes out with a single-layer writable disc with twice the capacity. Sure, it won't run on a standard DVD player *today*, but I'm sure tomorrow's DVD-B (or whatever) drive will be able to play it.
GPL isn't a virus in any sense. Yes, you are not the first to use the term. Rather, you are ignorantly joining the me-too bandwagon and repeating your favorite mantra.
A virus is defined as a bit of code that autonomously finds a host for itself so that when that host is executed it can come to life and wreak havoc or self-replicate. So, by definition, GPL is not a virus.
You might argue the GPL is instead a trojan horse, poised to take advantage of pathetic, unare individuals, that once granted access to the system (i.e. a source distribution) will unleash untold fury upon the poor idiot who added the source code to the project. This is far from the truth. The GPL (you apparently need to read it) mandates that any software that is to be distributed under the license clearly display the abridged license in source files and upon running command-line applications. Because the license information is prominently included in all source files with copyright information, any honest programmer (i.e. one that is not simply trying to steal source code) would note the copyright and exercise his full right to either comply with it by using the code and GPL'ing the resulting work or by not using the code.
Either way, the programmer has a choice. There is no virus-like behavior whatsoever.
If you are a programmer and agree with the GPL, you have been granted full permission to leverage any GPL'd code in your application provided you share the source of the result. If you do not agree with the GPL, take a hike -- don't use GPL code in yours.
What I really don't get is what the hell this KDE guy is really complaining about. If he is using GPL'd code that he obtained for free, he shouldn't be bitching about it (i.e., never look a gift horse in the mouth). If he is GPL'ing his own code, he still owns the copyright (unless he gave it away, doh!) and can sell it all he wants. He apparently chose to incorporate GPL'd code into his software and thought he could make money off of it, but it turns out he was wrong. He made a bad decision. Really, it's not like Mr. GPL came up to him and infiltrated his business and destroyed his entire business model!
This is the kind of ignorant drivel that gives GPL a bad name. GPL is intended for someone to be able to create source to implement a great idea they want to donate to the rest of the world. They want to make sure that their idea will be used to benefit others, not hidden away in someone's proprietary software to fatten someone else's wallet. That would be absurd.
The permission GPL grants is that others may use and modify for their own use a piece of software freely (no restrictions). For your own purposes, it's that simple -- no borg collective or other FUD. If someone wants to modify and redistribute the software, they must distribute it with the source code.
If I wrote an ingenious new app and wanted to give it to the world, why shouldn't I be able to stipulate that nobody can repackage it and sell it without redistributing the source? If you don't like it, rewrite it so you can resell it! You have every right to do so.