This post naturally assumes that this description is accurate, which is by no means certain.
As the writer touches on here, AMD has an excellent opportunity here. That opportunity is wasted if they simply make a 64-bit x86 CPU. This was a great idea when moving to the MIPS R10k. It was a great idea when moving from SPARC v8 to v9. These architectures were great to begin with, and have managed to maintain backward source and binary compatibility without adding cruft or useless compatibility logic. The x86 architecture, OTOH, is filled with cruft already. It has dozens of useless instructions, hundreds of artificial restrictions, and about as much non-orthogonality as anyone could want in a cautionary example.
If AMD simply warms over and extends this already much-maligned architecture, they will lose their big change to truly break away from Intel. Why not put out something genuinely creative? A new design? I know AMD can innovate, but I'm puzzled as to why they won't. If everyone is resigned to an architecture change anyway, why not give them something good to change to? AMD seems to be so accustomed to playing follow-the-leader that they don't know how to lead even when given the opportunity.
Get with it, AMD. Nobody is going to buy this processor. The improved FPU performance will be wasted on your market. These are peecee people; they don't care about vagaries like "computation." They want to play gamez and talk in chat rooms. Your puny FPU isn't going to touch the real workstation CPUs; the FPU performances of Alphas, SPARCs, and MIPS are dramatically above anything you can get with only 16-32 registers. So whom are you targeting? Hardcore Quake addicts?
It's time for something new, not the same old thing. If AMD does in fact follow this path, they will flop, and start all over again by reimplementing Itanium three or fours years after Intel, then spend ten more years playing catch-up. I can only hope that there's sufficient confusion to drive people into the arms of the workstation vendors, who have been producing consistently superior products for 10 or 20 years, maintaining or breaking compatibility at the right times and in the right ways. With any luck this will eventually be the death of the peecee.
this is not news. who cares about sun/kingston as linux has totally obliterated sun equipment in the datacenter. just walk into any exodus, globalcenter, or abovenet NOC and notice how 95% of the clientelle are using linux powered rackmounts.
Enjoy your crack, dude. The elimination of Sun equipment, which is probably around 5% not 95% as you claim, has nothing to do with Linux and everything to do with the insane cost of Sun hardware. Despite the serious quality problems with peecees, the extra cost for real computers is hard to justify any more. The availability of Linux is at most a catalyst; most corporate Linux users would be enntee users if Linux did not exist. People aren't switching to peecees so they can run Linux; they're switching to peecees so IT costs don't eat them alive. If they just wanted to run Linux they could do so with the same Sun hardware they would otherwise have run Solaris on. It ain't happening, man. Linux may be better than Solaris, but that's got nothing to do with what's going on here, and your apples to paperclips comparison makes no sense: you're saying an OS has eliminated a (supposedly competing) hardware product. Eh?
I'm also having a real hard time with your terminology. What the f*ck has a datacenter got to do with a NOC??? Have you ever actually been to an example of either? I also find it hard to believe (but will offer no evidence and thus not claim as fact) that any sizable percentage of users have "linux-powered rackmounts." The rackmountable peecee is still a rarity, and an expensive one at that. If we're talking about rackmounted Alpha or SPARC systems, then you've defeated your own argument. If not, then I'm pretty damn sure you're just blowing smoke.
HDs and RAM is where Suns high margin is. I can understand (from a finacial point of view) why they would want to keep their profit center up.
I want what you're smoking. All of Sun's hardware is overpriced if you buy it from them. Priced any UltraSPARCs lately? Hell, a crappy 8-bit framebuffer from spares costs hundreds of dollars. There is no possible way for Sun to keep disk prices artificially high because you can use commodity disks direct from the manufacturer instead of the same disks with a Sun label on them. Sun RAM on the third-party market runs between $2 and $5 per MB, depending on whether it's new or used, and has for quite some time, including during the peecee RAM price spike a few months ago. While this still represents a nice margin for someone, that someone isn't Sun. This is hardly an outrageous price for high-speed ECC RAM.
The truth is, Sun's profits come from all their hardware, especially that purchased by people with also-outrageously-expensive service contracts who have no choice but to buy new equipment directly from them. This is true of pretty much every company that makes quality hardware.
The drawings indicate 200 pins, while most regular SIMMS have 30 or 72 pins.
Really? All of mine have 200 pins. Even more amusingly, whether they are SIMMS, DIMMS, or "QIMMS" depends on what system I put them in. I.e., one such system allows adding them one at a time, one requires pairs, and one requires quads. So in some contexts, these devices are much more like peecee DIMMS than any SIMMS.
--TM, amazed at how much bandwidth a 576-bit memory bus gives you
Mark my words: IA64 will be Intel's biggest failure ever. It's already too late; their competitors have had 64-bit platforms available for years now, and have already gone through the transition annoyances to have mature reliable 64-bit computing options available. Nobody is sitting on their asses waiting for Intel to implement and ship Itanium. Anybody who genuinely cares about 64-bit computing went with Decompaq, Sun, SGI, and friends years ago and isn't about to look back.
The only people excited about Itanium are the ones who think they want to run enntee on it, and they are bound for disappointment because it'll be at least a year before m$ can demo a working 64-bit enntee. Linux on IA64 will help, but it won't save them. People who want to run Linux on a 64-bit platform are already doing so and probably won't buy into the Intel hype. If Intel's 64-bit offering were substantially cheaper than others, they might claim this market anyway, in the same way and for the same reason as they claimed most of the 32-bit market. Alas, Itanium is looking at least as expensive as competing options, and the first versions are unlikely to match up in performance or scalability.
And really, hype is all it is. The hard truth here is that Intel is between two and six years behind its competitors and is trying to make up for it with slick marketing hype. While Intel has called press conferences, their traditional RISC workstation competitors have marched on, crushing Intel's new processor in performance before it's even shipped. Within the next two to three years, we can expect to see more Alpha 21264s, UltraSPARC IIIs, MIPS R14k, and Itanium. As it looks, Itanium will be the weakest of the four. Ironically, they could probably have avoided this if they hadn't made the idiotic decision to ship Itanium with an x86 compatibility mode. That extra die space could have been used to take the performance lead away from their competitors. Instead, they've simply added support for an architecture that everyone agrees should have died 10 years ago.
So let's drink one final toast to Intel. Here's to you for holding back the computing industry for 20 years. Farewell, you shall not be missed.
Whoa! you must have forgotten about feudalism, absolute monarchies, class systems, and all the other ugly blots in western history.
What part of "off-and-on" didn't you understand?
Greek democracy was anything but egalitarian.
No claim to the contrary is made.
Face it, most westerners are descended from powerless peasants who were lorded over for centuries by absolute monarchs and an all-powerful church that would burn you alive if you spoke your mind.
No claim to the contrary is made.
Westerners made the transition to democracy, painfully, with very little in the way of democratic tradition except for in the farthest, remotest past.
Indeed. And during these transitions, what were the philosophers of the day basing their discourse on? That's right, the remotest past. History is replete with examples of the distant past being used to justify or condemn actions of the present. That's why we study it. Every now and then someone dredges up a good idea, works it over a bit, and puts it into action. That happened a lot in the European renaissance, and in many other places at other times as well. The point is that the history is there, and while not entirely continuous, is not at all a new idea.
has always been one uniform "Chinese" way of thinking/acting/being is laughable if not for the fact that you had made your comment in all seriousness, even with genuinely good intentions, as opposed to a sense of irony.
You misinterpret. I do not claim that all Chinese individuals think and act in the same way. To do so would be foolish. When analyzing things that affect and are affected by large groups of people, such as government, it is important to look at what is common to the people in question. Yes there are individual variations and exceptions galore. But those don't explain anything useful. We know people are all a little different. What we don't know is what similarities among large groups of people cause them to act in certain ways. That is the interesting issue here. Stop thinking about this thread as "stupid bigoted American thinks all Chinese are carbon copies of one another" and you might have something to contribute.
According to you, ONLY "the Chinese" apparently fear anarchy.
No. I never made any such claim. It's just a question of how much anarchy is feared relative to other evils.
Your attempt to be insightful thus, in claiming "It's a cultural thing. " is an exercise in cultural determinism; by essentializing China and "the Chinese," you ignore the universal, or at least widespread concerns they shared with other people and groups, outside China.
I am not overlooking this. Note that the examples I offered were not nations in a state of anarchy. But the process of changing governments from the type that the PRC has today and most of today's republics had in the past to a "free" society is lengthy and bloody. A people must decide whether it's worth it.
Your beliefs that China has traditionally been anti-democratic
I hold no such beliefs. Contrast "anti-democratic" with "pro-status-quo."
Not only do you reduce more than one billion people to a cultural stereotype, also unwittingly (I hope) help perpetrate and support the same self-serving arguments given by certain Asian/African authoritarian leaders on why they cannot have democracy-- "Oh, it is not inherent in our culture to have democracy; we have for centuries never practised or believed in freedom and basic human rights therefore, you, the Westerner/Westernized Asian or African cannot tell us to democratized because we just can't do it." Cultural relativism makes for some fantastic arguments that allow the powerful to stay in power in Asia and Africa.
I harbor no illusions about the brutality and evilness of these dictators. The excuses and rationalizations they use to remain in power are their problem, not mine. I am not claiming that democracy in the PRC or elsewhere is impossible, for cultural or any other reasons. I am claiming that it is neither inevitable nor our decision to make.
First no one government/political party/group can speak for hundreds of millions of people.
Of course they can. Whether they should is another matter.
The Chinese"/"Russians" etc are NOT a homogeneous group where supposedly fixed cultural norms and traditions have ensured that there is such a thing as a "Chinese"/"Russian" etc ways of thinking that are inherently different from "American" ways of thinking which apparently stand for freedom and democracy.
No claim of homogeneity is made. Homogeneity is not required for tradition. A trivial example: many Americans are not Christian, in name or in practice. So why is Christmas a federal holiday?
Sorry folks, but "Americans" do not have the monopoly over such essentials as freedom and basic human dignity; others like them too, thank you very much.
Including the right to self-determination. Unlike most Americans, I make no effort to interfere with that right. Anyone here remember the Vietnam War? Tell me, which side stood for these rights: Nguyen "Tyrant" van Thieu, the "commies," or the "imperialist" US? I argue that none of them did. In light of your post, ISTM that you would have supported the actions of the US. Ironically, similar actions in support of Chinese "freedom fighters" in the early 20th century were in retrospect hugely flawed and probably contributed to the current government there. If people want these freedoms and basic rights they must be willing to fight for them, just as every nation which currently enjoys them had to at some point. The severity and length of the fight certainly varied, from short, bloodless political battles to years of anarchy and death. These costs must be considered when discussing "freedom."
Ooh, the Chinese like dim sum and don't like democracy!
You trivialize (not to mention completely distort) my argument and attempt to further protect your belief that I am simply a narrow-minded bigot. It just ain't so.
THE ONLY reason for why some Chinese leaders act they way they do is, plainly stupid.
A discussion of every reason would fill volumes and is quite beyond the capabilites of this forum. I offered one reason in rejection of what has become a bromide. Nothing more.
Slashdot moderators who have given your message a score of 5 clearly agree with your views, as I am afraid, too many others.
I have no control over the moderators, or whether their actions reflect agreement or disagreement versus a genuine belief that my post is worth reading. You are, naturally, entitled to your own opinion independent of the moderators'.
But it completely refutes the claim of cultural affinity for totalitarian rule.
Proof that all statements can and likely will be misinterpreted. The point I was trying to make wasn't that anyone necessarily enjoys or wants a totalitarian state, but that some may find it a lesser evil than anarchy. I don't. If you don't, great. But many people do, and there are strong reasons to believe that one's opinion on this matter, like any other, is heavily influenced by culture and heritage. Get over the idea that I'm a bigot. I'm not. Quite frankly, I'm indifferent on this matter. People get the government they deserve. The "West" is rife with corruption and thinly disguised socialism. The Chinese government is totalitarian. Russia is essentially an anarchy, as is most of Africa. Which of these options appeals to you most or least is not my business or my problem. It's a personal decision, and one that happens to be heavily influenced by the time, place, and circumstances in which you were raised.
But there is no basis for any claim, which is somehow implicit in every argument of this sort, that the subjects or citizens of a nation have no say in the type of government they have. No government can exist without the governed. This is not a principle of democracy, it's an economic fact: bureaucrats and generals aren't productive in any way that helps. Thus if 1.3 billion people, or even a sizable minority of them (see "Taiwan") became genuinely convinced that their current government was more evil than some other, and the associated process necessary to change it, then a revolution would occur and some presumably more desired form of government would be instituted. The existing government simply cannot possibly kill everyone trying to overthrow it, and would be foolish to try. Thus the power to make a change always exists. The question - the important question at the heart of all this - is whether the pain, bloodshed, and anarchy necessary to make that change is worthwhile. It is quite clear historically that most Chinese do not feel that it is. It's not a value judgment; it's a simple observation.
I disagree with the traditional American idea that it's somehow our business what type of governments other nations have. I don't much care what type of government the Chinese choose for themselves, or even their reasons for choosing it. My original post was in rebellion against this idea that we are by definition right about governments. Our successes and failures speak for themselves. If other nations choose to emulate us, we should be honored. If they do not, we should perhaps examine why instead of either going to war in an effort to change that, or blithely asserting that sooner or later, democracy is inevitable. Neither approach properly respects national or individual soverignty and both are flat out wrong.
You are free (living in the US at least) to make whatever statements you like about why the PRC has a totalitarian government. Given your apparent closeness to this matter, you probably have significantly more insight than I do. But that does not imply that my observations are the result of bigotry. It's too complex an issue for such a simple refutation of an important argument.
Anarchy will rule but as compared with a the current situation anything is better...
You don't seem to know your history very well. In the early times of China, there was great turmoil and strife and - yes - anarchy. Much like the hyperinflation in the Weimar days convinced Germans to give the Bundesbank a stranglehold on their economy, the Chinese, at least traditionally, fear anarchy above all else. Hence the dynastic system, which led to long-lasting, powerful governments. And now, the "evil reds," who are not communist at all but simply totalitarian, are free to exert as much control as they desire. It's a cultural thing. Certainly as recent events have shown this does not apply to everyone in China, but the popular support for "anything but anarchy" is still very strong. Whether this is changing and how fast requires telling by someone a bit closer to Chinese culture than I.
You cannot apply your own values and experiences to others and expect them to work. The Chinese people have never been governed by anything even resembling democracy. Never. For that matter, neither had the Russians, and look what difficulties they're having with it. You (assuming you live in Western Europe, the US, Oz, etc.) have something like 2500 years of off-and-on democratic heritage of some kind or other. The Greek republican governments, the aristocrat-democracies of Europe, and the post-revolutionary American and French governments have provided plenty of fodder for your inclinations. But these are culturally insignificant to many people, including the Chinese. There is no certain inevitable victory for the forces of democracy in China. Maybe it'll happen, maybe not. Predicting the future is hard. But everyone needs to get this "inevitable triumph of the forces of democracy" out of their heads, because it just ain't so.
f you can't program you have no business using a pre-release kernel!
Yes and no. Remember that even most kernel hackers aren't familiar with every part of the kernel and can't fix everything that goes wrong. There are kernels that should legitimately be avoided by everybody, and then there are those that pretty much just work. Linus is now aiming explicitly at the latter; the kernels near the end of a development cycle need to get used so that bugs can be found and fixed. With this in mind, it's time for everyone to start using 2.3/2.4pre on all the non-production machines you can find. Bugs won't get fixed if nobody is using these kernels.
In answer to the original question, the best places to look are the Documentation/Changes file, which describes what software you need to build and successfully run the latest kernel, and the mailing list, which is archived at www.kernelnotes.org and other places.
Thank you. I'm glad someone finally said it. Napster is nothing but a great big sack of shit that bogs down any network it's run on. It has zero educational value and I'm damn glad my university blocks it. If I want to steal mp3s I'll do it with my own bandwidth. There's no reason the university should be expected to allow shit like that. The DMCA, evil and disturbing though it is, has not one damn thing to do with it. I seriously wonder whether Katz has ever actually tried using the net at a university. And not Harvard or UIUC, but a normal dirt-poor state university. Here's a free clue, Jon: WE DON'T EVEN HAVE ENOUGH BANDWIDTH FOR RESEARCH, MUCH LESS IDIOTIC BRAINDEAD PUKE MONKEYS WHO THINK THEY'RE FUCKING "LEET" AS HELL BECAUSE THEY HAVE W4R3Z AND CAN STEAL MUSIC AND RUN N4PS73R!!@!@$$!$%!@#!!!!! Jesus, people, get a fucking clue before you open your big mouths. Just because the evil corporatists would love to scare everybody into banning this stuff from their networks doesn't mean that they're actually responsible for doing so.
Yes, but what about when your L2 cache goes into mod zero byte block mode and slags the hell out of your cpu? That could easily lead to multi-megawatt emissions of head-exposion-causing microwave radiation madness! Write to your congressman/MP now, before it's too late! Think of the children!!!
You have missed the point. The objective of overclocking is not to obtain noticeable, or even measurable, speed increases in any task. It is to show how 31337 the 0v3rC10kk3r d00d!!!#!!@!!! is. You are correct, however, when you mention that A 1 GHz chip (or even a 800 MHz one) can, for most tasks, outpace any other componant of the system. This is why real workstations with "slow" 300-500MHz processors can easily outperform peecees with processors clocked twice as fast or faster. It's called balanced design, and has never made an appearance in the peecee world. The great irony is that peecee overclockers are trying to increase the speed of what is already the fastest component in their systems but refuse to spend one extra currency unit on improving the subsystems that are the slowest in the computing world. Instead, they should buy a chip 200-300 MHz behind the state of the "art" and spend the extra dosh on a better mainboard, i/o subsystem, and disks. It's amazing how much better performance such a system can deliver at a similar price point.
rated speed to avoid single-bit errors and the like
SBEs, eh? Well, that implies that you invested in ECC memory. Investing in higher quality components is highly unusual for an overclocker. I can assure you that most of them observe SBEs as a BSOD in their GameOS, because they spent all their cash on a higher-clocked processor and then bought Joe's Factory Thirds "PC92-1/2" Memory from the guy on the corner wearing a trench coat.
Uh, dont you think that companies would be smart enough to have shielding around the processor itself, rather than relying on the case? I think people think retards work in the R&D section of companies, they ARE aware of severe problems like THIS.
Of course they are. They're engineers. And the instant the marketdroids realize they can drop costs and increase profits by forgoing the shielding they will do so. And if past experience is any guide, people will buy it even though it interferes with their tv, radio, and other computer equipment, and cooks their brains. These are peecee buyers we're talking about, not intelligent human beings. If they'll buy aol, they'll buy anything. Now we just need to find a way to sell them a "computer" that is actually just a metal case connected to the appropriate line voltage. Pfffzzzzt, no more peecee luser.
You want to void your warranty and render tech support useless so you can save $40-100? How valuable is your data? Hopefully more than that.
You're in the wrong place. The workstation users are over there ---------->. These are peecee lusers. They've never heard of the service contract. Probably because any vendor who offered them on peecees would go under in five seconds.
I wonder what the chances are that the universities are recieving a little bit of persuasion from the record industry on this one?
In most cases, zero.
It may of course be the case that they are just worried about their bandwidth getting chewed
Bingo.
With respect to research: much of the time research use of education networks tends to take up tiny ammounts of bandwidth so why not use up the rest:)
Perhaps you attend a well-funded small private university or one like Northwestern, which can be heard on CNN complaining about how much of their 622-Mbit connection is being consumed by Napster. (sarcasm) My heart goes out to them (/sarcasm). At most universities, strictly educational/research uses are sufficient to saturate inbound links. Your post indicates that you don't grasp the severity of the problem. In our case at least, the network is UNUSABLE during "business hours." If I can get modem speeds (2-3kB/s), it's a good day. Never attribute to conspiracy what can be adequately explained by poverty.
I'm a student and systems administrator at a state university. I'm not absolutely certain whether we block Napster (I think we may have just started doing so) but if we haven't I sure wish we would. We don't block DeCSS or anything else really, though some types of connections (streaming media in particular) are rate-limited. Let me tell you first that is anything but censorship. As has been pointed out by the network admin, many uses for streaming media are more than legitimate, but we just simply don't have the bandwidth. There are three T1s to the world at our site, to serve something like 12000 students and hundreds of faculty and staff.
Censorship is restricting certain types of content only within a medium for some sort of political or moral goal. I don't believe that the university has any objection to students receiving any certain type of content (the AUP simply specifies that usage should be for educational purposes - I'll get to what this means in a bit). But regardless of the content, as the head admin says, "network bandwidth is a very limited resource." And I wholeheartedly agree to any measures he takes to help relieve the congestion, especially if it impacts only services, like Napster, that cannot possibly be considered to have legitimate educational purposes.
Yes, that's right, educational purposes. That's what university networks are supposed to be for. And I believe in a broad definition of "educational" that includes things like hosting Free Software projects, receiving and playing (non-stolen) music files, and even reading Slashdot. Most organizations, especially for-profit ones, do not even allow these activities because they do not contribute to that organization's mission. You should be thankful that most universities liberally interpret the boundaries of their missions and do not require you to pay for your own bandwidth to use these and other services.
Another issue to consider is that, in a badly oversubscribed environment like ours (100% usage from 8am to 6pm), every byte you get is a byte someone else won't. In a lot of cases, that someone else is trying to do real research, or as in my case, get security fixes and other data crucial to my job as a systems administrator. The conscientious individual recognizes this and self-imposes limits to his network use during congested times. After-hours, in fact, most limits are removed and students and faculty are allowed even freer use of the network. As I've been saying, these restrictions and limits are placed so that everyone has a fair shot at using the network. It would be nice if people would further limit their usage to truly educational material during the day; if they did then restrictions would not even be necessary. Until that happens (ha!) we'll continue to restrict and/or rate-limit certain services.
Unfortunately, decisions must be made as to exactly which services must be limited or cut off, and in general I feel that Napster is an example of a service with no real educational value and high bandwidth usage. Thus it is a good candidate for restriction. Perhaps you disagree, but then it would be your responsibility to decide what else must be limited or cut. Obviously items like DeCSS are not cut for these reasons, and I vehemently disagree with that practice. Ditto for cutting internet long-distance just to prevent competition. There are lots of bad reasons to restrict network usage, but I've yet to see anyone around here bringing them up and I suspect that in most places, decisions are being made for valid reasons, not censorship or to stifle competition. Here we are talking about bandwidth usage, and something has to go. I'm glad it's Napster and not FTP or HTTP. Certainly these protocols can be abused as well, but they are also frequently used for purposes directly related to the stated goals of the university. Think about it. If not Napster, then what?
The kernel http daemon in Linux 2.4 will make reverse http caching obsolete and outmoded.
I hope this is a troll. Just in case it isn't, let's think good and hard about what khttpd does: it's an ultra-fast web server for static content served from the filesystem. It's not a caching product, and never will/can be. It's also marked EXPERIMENTAL and almost certainly will be for 2.4 as well. khttpd is a marginally cool idea (hmmm..whoa, look what I can do!!!) that very few people will be using any time soon. And it certainly won't be for caching.
Re:"It was all I could do, as a woman!". :PPPPPP
on
X-Files FPS Episode
·
· Score: 2
Well, if we're going to talk about gender stereotypes, let's address this one then: *all* the men were portrayed as sex-crazed automotons
Look. I'm a guy. I know plenty of guys, and plenty of girls. Every last one of them, and, I'm pretty certain, almost any human being, male or female, would rather have sex than do anything else. Are there exceptions? Sure. I'm one. Maybe you're another. But this is one stereotype that is really not at all unfair. I would just prefer to see it applied to women as well, because IME it's just as fair in that context. Of course, I'd rather see people change their ways but that seems unlikely at best.
Look, I understand what you're saying, but this isn't a very good argument. It's based on security through obscurity, which most security professionals agree is useless. If there's a buffer overflow, it should be fixed, not ignored because nobody knows what to do with it. I'm not trying to pick a fight here; I certainly understand your argument. I just don't think it's a good one. Let the merits of Linux/390 vs OS/390 stand on their own. If one is actually more secure than the other, fine. But relative obscurity is not a security feature.
I think that a mainframe is largely a thing of the past due to the fact that most of the investment in the money and other factors will obselete the small parts that make the mainframe.
Funny, I've been hearing this for ten years now. "The Mainframe is dead." "Unix is dead." Sure. It's beyond me why people try to predict the future in this industry. I've yet to see someone who can do it without emabarrassing himself horribly.
Running linux on these things I guess would be a waste because I am sure that some crappy mainframe OS would work a little better.
What makes you think so? IBM did the port after all; I would assume they know what they're doing. Besides, if the mainframe OS is crappy (which they aren't) why would it be better???
There were no 100 MHz microsparc[-ii] or turbosparc cpus. 110 perhaps? Also, AFAIK there is no possible way to put 164MB in a SS5. (64+64+32+4??? There were no 4MB modules...) I know I'm nitpicking, but... Now, getting rid of CDE, there's an idea I think we can all agree on.:)
Slashdot Mirror
Spitfire is the name for UltraSPARC-Is and the MMU architechture in the I and II.
/proc/cpuinfo
[wesolows@pimp:~]$ cat
cpu : TI UltraSparc II (BlackBird)
fpu : UltraSparc II integrated FPU
promlib : Version 3 Revision 19
prom : 3.19.0
type : sun4u
ncpus probed : 2
ncpus active : 2
Cpu0Bogo : 398.95
Cpu1Bogo : 399.76
>>>> MMU Type : Spitfire
State:
CPU0: online
CPU1: online
As the writer touches on here, AMD has an excellent opportunity here. That opportunity is wasted if they simply make a 64-bit x86 CPU. This was a great idea when moving to the MIPS R10k. It was a great idea when moving from SPARC v8 to v9. These architectures were great to begin with, and have managed to maintain backward source and binary compatibility without adding cruft or useless compatibility logic. The x86 architecture, OTOH, is filled with cruft already. It has dozens of useless instructions, hundreds of artificial restrictions, and about as much non-orthogonality as anyone could want in a cautionary example.
If AMD simply warms over and extends this already much-maligned architecture, they will lose their big change to truly break away from Intel. Why not put out something genuinely creative? A new design? I know AMD can innovate, but I'm puzzled as to why they won't. If everyone is resigned to an architecture change anyway, why not give them something good to change to? AMD seems to be so accustomed to playing follow-the-leader that they don't know how to lead even when given the opportunity.
Get with it, AMD. Nobody is going to buy this processor. The improved FPU performance will be wasted on your market. These are peecee people; they don't care about vagaries like "computation." They want to play gamez and talk in chat rooms. Your puny FPU isn't going to touch the real workstation CPUs; the FPU performances of Alphas, SPARCs, and MIPS are dramatically above anything you can get with only 16-32 registers. So whom are you targeting? Hardcore Quake addicts?
It's time for something new, not the same old thing. If AMD does in fact follow this path, they will flop, and start all over again by reimplementing Itanium three or fours years after Intel, then spend ten more years playing catch-up. I can only hope that there's sufficient confusion to drive people into the arms of the workstation vendors, who have been producing consistently superior products for 10 or 20 years, maintaining or breaking compatibility at the right times and in the right ways. With any luck this will eventually be the death of the peecee.
Enjoy your crack, dude. The elimination of Sun equipment, which is probably around 5% not 95% as you claim, has nothing to do with Linux and everything to do with the insane cost of Sun hardware. Despite the serious quality problems with peecees, the extra cost for real computers is hard to justify any more. The availability of Linux is at most a catalyst; most corporate Linux users would be enntee users if Linux did not exist. People aren't switching to peecees so they can run Linux; they're switching to peecees so IT costs don't eat them alive. If they just wanted to run Linux they could do so with the same Sun hardware they would otherwise have run Solaris on. It ain't happening, man. Linux may be better than Solaris, but that's got nothing to do with what's going on here, and your apples to paperclips comparison makes no sense: you're saying an OS has eliminated a (supposedly competing) hardware product. Eh?
I'm also having a real hard time with your terminology. What the f*ck has a datacenter got to do with a NOC??? Have you ever actually been to an example of either? I also find it hard to believe (but will offer no evidence and thus not claim as fact) that any sizable percentage of users have "linux-powered rackmounts." The rackmountable peecee is still a rarity, and an expensive one at that. If we're talking about rackmounted Alpha or SPARC systems, then you've defeated your own argument. If not, then I'm pretty damn sure you're just blowing smoke.
I want what you're smoking. All of Sun's hardware is overpriced if you buy it from them. Priced any UltraSPARCs lately? Hell, a crappy 8-bit framebuffer from spares costs hundreds of dollars. There is no possible way for Sun to keep disk prices artificially high because you can use commodity disks direct from the manufacturer instead of the same disks with a Sun label on them. Sun RAM on the third-party market runs between $2 and $5 per MB, depending on whether it's new or used, and has for quite some time, including during the peecee RAM price spike a few months ago. While this still represents a nice margin for someone, that someone isn't Sun. This is hardly an outrageous price for high-speed ECC RAM.
The truth is, Sun's profits come from all their hardware, especially that purchased by people with also-outrageously-expensive service contracts who have no choice but to buy new equipment directly from them. This is true of pretty much every company that makes quality hardware.
Really? All of mine have 200 pins. Even more amusingly, whether they are SIMMS, DIMMS, or "QIMMS" depends on what system I put them in. I.e., one such system allows adding them one at a time, one requires pairs, and one requires quads. So in some contexts, these devices are much more like peecee DIMMS than any SIMMS.
--TM, amazed at how much bandwidth a 576-bit memory bus gives you
The only people excited about Itanium are the ones who think they want to run enntee on it, and they are bound for disappointment because it'll be at least a year before m$ can demo a working 64-bit enntee. Linux on IA64 will help, but it won't save them. People who want to run Linux on a 64-bit platform are already doing so and probably won't buy into the Intel hype. If Intel's 64-bit offering were substantially cheaper than others, they might claim this market anyway, in the same way and for the same reason as they claimed most of the 32-bit market. Alas, Itanium is looking at least as expensive as competing options, and the first versions are unlikely to match up in performance or scalability.
And really, hype is all it is. The hard truth here is that Intel is between two and six years behind its competitors and is trying to make up for it with slick marketing hype. While Intel has called press conferences, their traditional RISC workstation competitors have marched on, crushing Intel's new processor in performance before it's even shipped. Within the next two to three years, we can expect to see more Alpha 21264s, UltraSPARC IIIs, MIPS R14k, and Itanium. As it looks, Itanium will be the weakest of the four. Ironically, they could probably have avoided this if they hadn't made the idiotic decision to ship Itanium with an x86 compatibility mode. That extra die space could have been used to take the performance lead away from their competitors. Instead, they've simply added support for an architecture that everyone agrees should have died 10 years ago.
So let's drink one final toast to Intel. Here's to you for holding back the computing industry for 20 years. Farewell, you shall not be missed.
Somebody moderate this up please. It's an excellent contribution to an important discussion.
What part of "off-and-on" didn't you understand?
Greek democracy was anything but egalitarian.
No claim to the contrary is made.
Face it, most westerners are descended from powerless peasants who were lorded over for centuries by absolute monarchs and an all-powerful church that would burn you alive if you spoke your mind.
No claim to the contrary is made.
Westerners made the transition to democracy, painfully, with very little in the way of democratic tradition except for in the farthest, remotest past.
Indeed. And during these transitions, what were the philosophers of the day basing their discourse on? That's right, the remotest past. History is replete with examples of the distant past being used to justify or condemn actions of the present. That's why we study it. Every now and then someone dredges up a good idea, works it over a bit, and puts it into action. That happened a lot in the European renaissance, and in many other places at other times as well. The point is that the history is there, and while not entirely continuous, is not at all a new idea.
You misinterpret. I do not claim that all Chinese individuals think and act in the same way. To do so would be foolish. When analyzing things that affect and are affected by large groups of people, such as government, it is important to look at what is common to the people in question. Yes there are individual variations and exceptions galore. But those don't explain anything useful. We know people are all a little different. What we don't know is what similarities among large groups of people cause them to act in certain ways. That is the interesting issue here. Stop thinking about this thread as "stupid bigoted American thinks all Chinese are carbon copies of one another" and you might have something to contribute.
According to you, ONLY "the Chinese" apparently fear anarchy.
No. I never made any such claim. It's just a question of how much anarchy is feared relative to other evils.
Your attempt to be insightful thus, in claiming "It's a cultural thing. " is an exercise in cultural determinism; by essentializing China and "the Chinese," you ignore the universal, or at least widespread concerns they shared with other people and groups, outside China.
I am not overlooking this. Note that the examples I offered were not nations in a state of anarchy. But the process of changing governments from the type that the PRC has today and most of today's republics had in the past to a "free" society is lengthy and bloody. A people must decide whether it's worth it.
Your beliefs that China has traditionally been anti-democratic
I hold no such beliefs. Contrast "anti-democratic" with "pro-status-quo."
Not only do you reduce more than one billion people to a cultural stereotype, also unwittingly (I hope) help perpetrate and support the same self-serving arguments given by certain Asian/African authoritarian leaders on why they cannot have democracy-- "Oh, it is not inherent in our culture to have democracy; we have for centuries never practised or believed in freedom and basic human rights therefore, you, the Westerner/Westernized Asian or African cannot tell us to democratized because we just can't do it." Cultural relativism makes for some fantastic arguments that allow the powerful to stay in power in Asia and Africa.
I harbor no illusions about the brutality and evilness of these dictators. The excuses and rationalizations they use to remain in power are their problem, not mine. I am not claiming that democracy in the PRC or elsewhere is impossible, for cultural or any other reasons. I am claiming that it is neither inevitable nor our decision to make.
First no one government/political party/group can speak for hundreds of millions of people.
Of course they can. Whether they should is another matter.
The Chinese"/"Russians" etc are NOT a homogeneous group where supposedly fixed cultural norms and traditions have ensured that there is such a thing as a "Chinese"/"Russian" etc ways of thinking that are inherently different from "American" ways of thinking which apparently stand for freedom and democracy.
No claim of homogeneity is made. Homogeneity is not required for tradition. A trivial example: many Americans are not Christian, in name or in practice. So why is Christmas a federal holiday?
Sorry folks, but "Americans" do not have the monopoly over such essentials as freedom and basic human dignity; others like them too, thank you very much.
Including the right to self-determination. Unlike most Americans, I make no effort to interfere with that right. Anyone here remember the Vietnam War? Tell me, which side stood for these rights: Nguyen "Tyrant" van Thieu, the "commies," or the "imperialist" US? I argue that none of them did. In light of your post, ISTM that you would have supported the actions of the US. Ironically, similar actions in support of Chinese "freedom fighters" in the early 20th century were in retrospect hugely flawed and probably contributed to the current government there. If people want these freedoms and basic rights they must be willing to fight for them, just as every nation which currently enjoys them had to at some point. The severity and length of the fight certainly varied, from short, bloodless political battles to years of anarchy and death. These costs must be considered when discussing "freedom."
Ooh, the Chinese like dim sum and don't like democracy!
You trivialize (not to mention completely distort) my argument and attempt to further protect your belief that I am simply a narrow-minded bigot. It just ain't so.
THE ONLY reason for why some Chinese leaders act they way they do is, plainly stupid.
A discussion of every reason would fill volumes and is quite beyond the capabilites of this forum. I offered one reason in rejection of what has become a bromide. Nothing more.
Slashdot moderators who have given your message a score of 5 clearly agree with your views, as I am afraid, too many others.
I have no control over the moderators, or whether their actions reflect agreement or disagreement versus a genuine belief that my post is worth reading. You are, naturally, entitled to your own opinion independent of the moderators'.
Proof that all statements can and likely will be misinterpreted. The point I was trying to make wasn't that anyone necessarily enjoys or wants a totalitarian state, but that some may find it a lesser evil than anarchy. I don't. If you don't, great. But many people do, and there are strong reasons to believe that one's opinion on this matter, like any other, is heavily influenced by culture and heritage. Get over the idea that I'm a bigot. I'm not. Quite frankly, I'm indifferent on this matter. People get the government they deserve. The "West" is rife with corruption and thinly disguised socialism. The Chinese government is totalitarian. Russia is essentially an anarchy, as is most of Africa. Which of these options appeals to you most or least is not my business or my problem. It's a personal decision, and one that happens to be heavily influenced by the time, place, and circumstances in which you were raised.
But there is no basis for any claim, which is somehow implicit in every argument of this sort, that the subjects or citizens of a nation have no say in the type of government they have. No government can exist without the governed. This is not a principle of democracy, it's an economic fact: bureaucrats and generals aren't productive in any way that helps. Thus if 1.3 billion people, or even a sizable minority of them (see "Taiwan") became genuinely convinced that their current government was more evil than some other, and the associated process necessary to change it, then a revolution would occur and some presumably more desired form of government would be instituted. The existing government simply cannot possibly kill everyone trying to overthrow it, and would be foolish to try. Thus the power to make a change always exists. The question - the important question at the heart of all this - is whether the pain, bloodshed, and anarchy necessary to make that change is worthwhile. It is quite clear historically that most Chinese do not feel that it is. It's not a value judgment; it's a simple observation.
I disagree with the traditional American idea that it's somehow our business what type of governments other nations have. I don't much care what type of government the Chinese choose for themselves, or even their reasons for choosing it. My original post was in rebellion against this idea that we are by definition right about governments. Our successes and failures speak for themselves. If other nations choose to emulate us, we should be honored. If they do not, we should perhaps examine why instead of either going to war in an effort to change that, or blithely asserting that sooner or later, democracy is inevitable. Neither approach properly respects national or individual soverignty and both are flat out wrong.
You are free (living in the US at least) to make whatever statements you like about why the PRC has a totalitarian government. Given your apparent closeness to this matter, you probably have significantly more insight than I do. But that does not imply that my observations are the result of bigotry. It's too complex an issue for such a simple refutation of an important argument.
You don't seem to know your history very well. In the early times of China, there was great turmoil and strife and - yes - anarchy. Much like the hyperinflation in the Weimar days convinced Germans to give the Bundesbank a stranglehold on their economy, the Chinese, at least traditionally, fear anarchy above all else. Hence the dynastic system, which led to long-lasting, powerful governments. And now, the "evil reds," who are not communist at all but simply totalitarian, are free to exert as much control as they desire. It's a cultural thing. Certainly as recent events have shown this does not apply to everyone in China, but the popular support for "anything but anarchy" is still very strong. Whether this is changing and how fast requires telling by someone a bit closer to Chinese culture than I.
You cannot apply your own values and experiences to others and expect them to work. The Chinese people have never been governed by anything even resembling democracy. Never. For that matter, neither had the Russians, and look what difficulties they're having with it. You (assuming you live in Western Europe, the US, Oz, etc.) have something like 2500 years of off-and-on democratic heritage of some kind or other. The Greek republican governments, the aristocrat-democracies of Europe, and the post-revolutionary American and French governments have provided plenty of fodder for your inclinations. But these are culturally insignificant to many people, including the Chinese. There is no certain inevitable victory for the forces of democracy in China. Maybe it'll happen, maybe not. Predicting the future is hard. But everyone needs to get this "inevitable triumph of the forces of democracy" out of their heads, because it just ain't so.
Yes and no. Remember that even most kernel hackers aren't familiar with every part of the kernel and can't fix everything that goes wrong. There are kernels that should legitimately be avoided by everybody, and then there are those that pretty much just work. Linus is now aiming explicitly at the latter; the kernels near the end of a development cycle need to get used so that bugs can be found and fixed. With this in mind, it's time for everyone to start using 2.3/2.4pre on all the non-production machines you can find. Bugs won't get fixed if nobody is using these kernels.
In answer to the original question, the best places to look are the Documentation/Changes file, which describes what software you need to build and successfully run the latest kernel, and the mailing list, which is archived at www.kernelnotes.org and other places.
Thank you. I'm glad someone finally said it. Napster is nothing but a great big sack of shit that bogs down any network it's run on. It has zero educational value and I'm damn glad my university blocks it. If I want to steal mp3s I'll do it with my own bandwidth. There's no reason the university should be expected to allow shit like that. The DMCA, evil and disturbing though it is, has not one damn thing to do with it. I seriously wonder whether Katz has ever actually tried using the net at a university. And not Harvard or UIUC, but a normal dirt-poor state university. Here's a free clue, Jon: WE DON'T EVEN HAVE ENOUGH BANDWIDTH FOR RESEARCH, MUCH LESS IDIOTIC BRAINDEAD PUKE MONKEYS WHO THINK THEY'RE FUCKING "LEET" AS HELL BECAUSE THEY HAVE W4R3Z AND CAN STEAL MUSIC AND RUN N4PS73R!!@!@$$!$%!@#!!!!! Jesus, people, get a fucking clue before you open your big mouths. Just because the evil corporatists would love to scare everybody into banning this stuff from their networks doesn't mean that they're actually responsible for doing so.
Yes, but what about when your L2 cache goes into mod zero byte block mode and slags the hell out of your cpu? That could easily lead to multi-megawatt emissions of head-exposion-causing microwave radiation madness! Write to your congressman/MP now, before it's too late! Think of the children!!!
rated speed to avoid single-bit errors and the like
SBEs, eh? Well, that implies that you invested in ECC memory. Investing in higher quality components is highly unusual for an overclocker. I can assure you that most of them observe SBEs as a BSOD in their GameOS, because they spent all their cash on a higher-clocked processor and then bought Joe's Factory Thirds "PC92-1/2" Memory from the guy on the corner wearing a trench coat.
Of course they are. They're engineers. And the instant the marketdroids realize they can drop costs and increase profits by forgoing the shielding they will do so. And if past experience is any guide, people will buy it even though it interferes with their tv, radio, and other computer equipment, and cooks their brains. These are peecee buyers we're talking about, not intelligent human beings. If they'll buy aol, they'll buy anything. Now we just need to find a way to sell them a "computer" that is actually just a metal case connected to the appropriate line voltage. Pfffzzzzt, no more peecee luser.
You're in the wrong place. The workstation users are over there ---------->. These are peecee lusers. They've never heard of the service contract. Probably because any vendor who offered them on peecees would go under in five seconds.
In most cases, zero.
It may of course be the case that they are just worried about their bandwidth getting chewed
Bingo.
With respect to research: much of the time research use of education networks tends to take up tiny ammounts of bandwidth so why not use up the rest :)
Perhaps you attend a well-funded small private university or one like Northwestern, which can be heard on CNN complaining about how much of their 622-Mbit connection is being consumed by Napster. (sarcasm) My heart goes out to them (/sarcasm). At most universities, strictly educational/research uses are sufficient to saturate inbound links. Your post indicates that you don't grasp the severity of the problem. In our case at least, the network is UNUSABLE during "business hours." If I can get modem speeds (2-3kB/s), it's a good day. Never attribute to conspiracy what can be adequately explained by poverty.
--TM
Censorship is restricting certain types of content only within a medium for some sort of political or moral goal. I don't believe that the university has any objection to students receiving any certain type of content (the AUP simply specifies that usage should be for educational purposes - I'll get to what this means in a bit). But regardless of the content, as the head admin says, "network bandwidth is a very limited resource." And I wholeheartedly agree to any measures he takes to help relieve the congestion, especially if it impacts only services, like Napster, that cannot possibly be considered to have legitimate educational purposes.
Yes, that's right, educational purposes. That's what university networks are supposed to be for. And I believe in a broad definition of "educational" that includes things like hosting Free Software projects, receiving and playing (non-stolen) music files, and even reading Slashdot. Most organizations, especially for-profit ones, do not even allow these activities because they do not contribute to that organization's mission. You should be thankful that most universities liberally interpret the boundaries of their missions and do not require you to pay for your own bandwidth to use these and other services.
Another issue to consider is that, in a badly oversubscribed environment like ours (100% usage from 8am to 6pm), every byte you get is a byte someone else won't. In a lot of cases, that someone else is trying to do real research, or as in my case, get security fixes and other data crucial to my job as a systems administrator. The conscientious individual recognizes this and self-imposes limits to his network use during congested times. After-hours, in fact, most limits are removed and students and faculty are allowed even freer use of the network. As I've been saying, these restrictions and limits are placed so that everyone has a fair shot at using the network. It would be nice if people would further limit their usage to truly educational material during the day; if they did then restrictions would not even be necessary. Until that happens (ha!) we'll continue to restrict and/or rate-limit certain services.
Unfortunately, decisions must be made as to exactly which services must be limited or cut off, and in general I feel that Napster is an example of a service with no real educational value and high bandwidth usage. Thus it is a good candidate for restriction. Perhaps you disagree, but then it would be your responsibility to decide what else must be limited or cut. Obviously items like DeCSS are not cut for these reasons, and I vehemently disagree with that practice. Ditto for cutting internet long-distance just to prevent competition. There are lots of bad reasons to restrict network usage, but I've yet to see anyone around here bringing them up and I suspect that in most places, decisions are being made for valid reasons, not censorship or to stifle competition. Here we are talking about bandwidth usage, and something has to go. I'm glad it's Napster and not FTP or HTTP. Certainly these protocols can be abused as well, but they are also frequently used for purposes directly related to the stated goals of the university. Think about it. If not Napster, then what?
--TM
I hope this is a troll. Just in case it isn't, let's think good and hard about what khttpd does: it's an ultra-fast web server for static content served from the filesystem. It's not a caching product, and never will/can be. It's also marked EXPERIMENTAL and almost certainly will be for 2.4 as well. khttpd is a marginally cool idea (hmmm..whoa, look what I can do!!!) that very few people will be using any time soon. And it certainly won't be for caching.
Look. I'm a guy. I know plenty of guys, and plenty of girls. Every last one of them, and, I'm pretty certain, almost any human being, male or female, would rather have sex than do anything else. Are there exceptions? Sure. I'm one. Maybe you're another. But this is one stereotype that is really not at all unfair. I would just prefer to see it applied to women as well, because IME it's just as fair in that context. Of course, I'd rather see people change their ways but that seems unlikely at best.
Look, I understand what you're saying, but this isn't a very good argument. It's based on security through obscurity, which most security professionals agree is useless. If there's a buffer overflow, it should be fixed, not ignored because nobody knows what to do with it. I'm not trying to pick a fight here; I certainly understand your argument. I just don't think it's a good one. Let the merits of Linux/390 vs OS/390 stand on their own. If one is actually more secure than the other, fine. But relative obscurity is not a security feature.
Funny, I've been hearing this for ten years now. "The Mainframe is dead." "Unix is dead." Sure. It's beyond me why people try to predict the future in this industry. I've yet to see someone who can do it without emabarrassing himself horribly.
Running linux on these things I guess would be a waste because I am sure that some crappy mainframe OS would work a little better.
What makes you think so? IBM did the port after all; I would assume they know what they're doing. Besides, if the mainframe OS is crappy (which they aren't) why would it be better???
Of course not; that's what the groupies are for. (g,d&r)
There were no 100 MHz microsparc[-ii] or turbosparc cpus. 110 perhaps? Also, AFAIK there is no possible way to put 164MB in a SS5. (64+64+32+4??? There were no 4MB modules...) I know I'm nitpicking, but... Now, getting rid of CDE, there's an idea I think we can all agree on. :)