The Pentium IV's really looong pipeline does allow the P4 to run at higher clockspeeds, but the branch prediction you mentioned is instant death.... a single branch prediction requires up to 20 full clock cycles of work to be discarded.
The situation is not quite as dire due to P4's trace cache (you actually addressed that later in your post). Nevertheless, your point stands.
On Intel SMP setups, even on P4 Xeons (Which, IMO, are inferior to P3 Tualatin chips by the same company) when one CPU accesses main memory, it locks main memory for the other CPUs. All other CPUs have to sit and twiddle their transistors while the main memory is on use by only one CPU.
On AMD SMP setups, ALL processors can simultaneous access memory, merely sharing the bandwidth simultaneously. So, if one CPU is only using 100MB of memory bandwidth, the rest can be used by other CPUs at that time.
P4 Xeons (as well as P3s) have a shared memory bus. That is, multiple CPUs share the bandwidth of the 400MHz or 533MHz bus when accessing memory. However, Athlon has a point-to-point channel for each CPU. That is, each Athlon CPU has the full bandwidth of the 266MHz (soon to be 333MHz) memory bus, regardless of how many CPUs there are in the system. This means that beyond 2-way SMP systems, Athlon has a significant advantage in memory bandwidth over P4.
SPECfp benchmark is highly dependent on the memory bandwidth. P4, with two channels of RDRAM, has more memory bandwidth than Athlon with a single channel of DDR. Thus, P4 gets a free ride here. Show me an apples to apples comparison here: P4 and Athlon with the same memory (be it SDRAM or DDR). I have yet to see one.
For a truly FPU-intensive benchmark that does not depend on memory bandwidth much, check out 3D Sudio rendering (tomshardware & others have it). Athlon simply smokes P4 on that one. Incidentally, on this benchmark P3 1000MHz outperformed P4 1500MHz.
Well, this summer alone, I have seen a fair number of Konqueror security flaws posted
How many? One?
Also, most vendors do not provide CVS packages for things like this. Hell, debian still doesn't even have an official KDE3. And even if there is a CVS version, how many people are going to be quick to hop on it, considering the code in CVS is typically beta at best? And what newbies are even going to know about this?
Some ridiculously stupid mumbles there. Each distribution has an easy way of upgrading the packages. In Debian it's "apt-get updage; apt-get upgrade". In Mandrake & RedHat you just run the GUI updater software. The update icon is right there on the desktop.
Nobody is suggesting that you should install a CVS version of software to get a security fix. The fixes are backported into the stable branches of the software, and vendors package them. Wow, what a concept!
And then your issue on bugfixes. Are you trying to say that OSS patches never break anything?
No, I'm saying that Microsoft breaks stuff more often despite taking months to release a fix.
I pointed out that both Microsoft and the KDE project have a history of poor security
And KDE's history of poor security would be...?
I also mentioned that, just because a fix is in the KDE project's CVS, does not mean that it is available for everyone - that will have to wait until the next release.
Bull shit. Ever heard of Debian's apt-get, Mandrake's urpmi, RedHat's up2date, etc.? It's up to each vendor to make the fix available to the users. You can also install it yourself without waiting for the vendor to catch up.
Microsoft has hundreds of millions of customers across the world, and the systems handle billions of dollars of revenue... this puts a huge responsiblity to get their fixes right and properly tested
Then can you explain why Microsoft releases bugfixes that uhhm break stuff? Despite the fact that Microsoft takes 2-3 months to uhhh "test" stuff, Open Source community has a much better track record in this regard.
Quite frankly, LinuxToday is becoming unreadable by anyone not a) a KDE super-fan b) rabidly anti-Microsoft.
(see subject) 150MB/s is just a gimmick for the people who don't know any better. The real advantage (to me) is hot-pluggability, and (as already mentioned) thinner & longer cables + backwards compatibility with standard IDE.
Microsoft submitted falsified evidence -- and got caught. Microsoft executives lied under oath -- and got caught. Microsoft wrote the testimony for its "expert witnesses" -- and got caught. This one was actually quite funny. One stooge claimed that the states' demands would lead to "balkanization of windows". Problem was that he didn't know what "balkanization" means:-) so he admitted the whole testimony was written by MS lawyers. The last gem I read is that MS lawyers quoted selectively from multiple decisions so as to misrepresent their holdings. The judge did not find that strategy persuasive.
Now, you are an attorney, tell me: why are Microsoft executives not being prosecuted for perjury?
This is actually what I want to do. I want to hook up a spare box to the TV and use it to play DVDs, DivX, etc., as well as used it as a PVR. I know TV capture cards are supported on Linux, but what about TV out?
BTW, are hardware MPEG encoders supported under Linux? Some TV capture cards have them built in. It would be more efficient to encode the stream on the card since it uses up less PCI bandwidth.
This would be a perfect media box for the living room: DVDs, CDs, mp3s, PRV, etc. all in one.
As for the notion of 'needing something to fight against' as a justification for injustice or
corruption, so that the next generation has something to occupy their time, I think the
absurdity of your words stand upon their own.
Ever read 1984?
You'd be surprised how well that works. Not to the benefit of the common people, of course.
by your assumption a*log2(16)^12 + b = 1 ms for simplicity, let's ignore the constant b. then:
a*log2(16)^12 = a * 4^12 = 1 ms (by assumption) a*log2(32)^12 = a * 5^12 = 14.5 ms a*log2(64)^12 = a * 6^12 = 129.75 ms ... a*log2(256)^12 = a * 8^12 = 4096 ms
Either way, Microsoft break their own rules; there's numerous windows on a standard desktop that run as localsystem. Use my shatter tool to verify this - there's a whole load of unnamed windows which might be running as Localsystem, and a few invisible windows (like the DDE server) that definitely are. Security boundary my arse.
The author has addressed Microsoft's response in his writeup. Given that there are numerous windows running as LocalSystem on any desktop, Microsoft's response is a load of tripe.
Remember, it costs Microsoft $300 to make an XBox, but they sell it for $200. That's why:
The problem is that Microsoft already spent $300 to make an xbox. They lose that money no matter what. If you buy an xbox they will get $200 and partially recover their losses.
In short, Microsoft loses $100 on an xbox if you buy it. They lose $300 if you don't buy it.
This is about the stupidest proposition I've herd yet. You obviously have no clue about how Free Software licences (and copyright in general) work, so let me clue you in.
All all of the so-called click-wrap "licenses" (*) start off with the presumption that even though you bought a copy of software, you are not allowed to use it unless you agree to the "license" (and, in effect, give up your rights). Such a presumption, however, is not supported by copyright law. Quite simply, if you own a copy of software, you may do whatever you want with it, as long as you don't distribute copies of it to someone else. Making copies is the exclusive right of the copyright holder (fair use applies, of course).
(*) The "license" is actually a unilateral contract in that it takes away your rights instead of granting them.
Free Software licenses start off with the (correct) presumption that you can use the software in any way you want (thus, unlike proprietary "licenses", they don't attempt to take away your rights). Instead, they grant you more rights than you normally have. (Thus Free Software licenses are indeed licenses). Specifically, you get the right to distribute the software. There are, however, limitations in the ways you are allowed to do so. For example, GPL stipulates that you may not distribute the software under any other license; BSD allows you to relicense the software, but you must give credit to the original author, etc. If you agree to the license, you get the right to distribute the software; if you don't agree you have no such right.
This is how copyright works. All Free Software licenses are besed entirely in copyright law. They do not attempt to take away your rights as a condition to using the software. This makes them stronger than proprietary "licenses".
The only two cases that I'm aware of where a license was ruled unenforcible involve specifically the proprietary click-wrap "licenses". (Step-Saver v. Wyse Technology and ARS v. Software Link).
Re:stop this FUD
on
.NET for Apache
·
· Score: 3, Informative
If you are a software developer and want to leverage a GPL component, you have exactly zero choices as to what license your software will be under.
If you are a software developer and want to leverage a Microsoft component you have no right to do that at all. Or does Microsoft now permit you to take some of its proprietary code and distribute it under a license of your choice? Last I checked you could not distribute their code at all.
You don't expect to have any rights to a proprietary code, yet, just because something is Open Source, you assume that you have a God-given right to do with that code as you please, and GPL takes that right away. Bullshit. You cannot distribute someone else's code unless they grant you permission to do so. In the case of proprietary libraries, that permision comes in exchange for payment. In the case of GPL, such permission comes automatically if you accept the terms of the GPL.(*) If the payment is not acceptible to you, then write the code yourself! And stop repeating the "viral" FUD, it makes you sound like an idiot.
(*)Some GPL developers will also let you use their code in your proprietary product in exchange for monetary payment. Just like proprietary developers.
1) MS never said anything about OpenSource and cancer. It was GPL. GPL != OpenSource. Read the fucking articles and understand MS's point of view. MS is more than thrilled with BSD code and other non-ip-destroying licenses. They are not happy with GPL and they (correctly) point out that GPL infects everything it touches because it is viral in nature. This is not a debatable point, unless you just dont get GPL.
You are obviously a fucking moron since you repeat this blatant Microsoft FUD. 1. Microsoft singled out part of the Open Source in their usual divide and conquer strategy. 2. Microsoft loves BSD because it loves to "borrow" BSD code and incorporate it into its proprietary products. This saves Microsoft quite a bit of money and, many would argue, gives them better quality code too. 3. I see that you have swalloed the "viral" propaganda. Perhaps you can explain to me how exactly GPL "infects" stuff? Maybe you mean the fact that GPL does not permit you to take the code you don't own and incorporate it into your proprietary product? But the same is true of Microsoft's code! You can't take their "shared source" and use it in your product either. With GPL, at least, you can use, modify, and distribute the code all you want as long as you distribute derivative works under GPL. With Microsoft, you have no such option. Why, Microsoft is the virus!
I also want to know how exactly GPL "touches" stuff. Oh what you actually mean is that GPL "touches" the code when the company willingly decides to use GPL code in their proprietary product.
If microsoft has never done anything to help any apache or open source effort, why did they fly a few of the zend people into redmond for a week, having them perf tune php on iis ?
Uhhm, because it helps Microsoft, not Open Source. PHP is the most widely used server-side scripting language. It sure helps to have it run well on your web server.
Why is there a mod_frontpage for apache that microsoft publishes ?
Because it helps them to sell Frontpage and install viral software on Unix.
Oh yeah, you assume a lot of stuff about microsoft that is wrong, which makes you kind of an idiot.
This would require bonding of two network interfaces. As far as I know that was one of the features included in 2.4. Can somebody confirm?
As for failover, that would be really easy to do regardless of the load balancing support. You just need a cronjob that checks if one of the connections is still up, and reconfigures routing & firewall on timeout.
* ACLs! * All journalling file systems merged (XFS, JFS, ext3, ReiserFS) * No more VM stability issues
Anyone know if we can expect that?
On a side note, what are the four FSs above best suited for? I know ReiserFS is really good at working with lots of small files and XFS is excellent at data streaming. Anyone care to add more details?
Slashdot Mirror
The situation is not quite as dire due to P4's trace cache (you actually addressed that later in your post). Nevertheless, your point stands.
On Intel SMP setups, even on P4 Xeons (Which, IMO, are inferior to P3 Tualatin chips by the same company) when one CPU accesses main memory, it locks main memory for the other CPUs. All other CPUs have to sit and twiddle their transistors while the main memory is on use by only one CPU. On AMD SMP setups, ALL processors can simultaneous access memory, merely sharing the bandwidth simultaneously. So, if one CPU is only using 100MB of memory bandwidth, the rest can be used by other CPUs at that time.
P4 Xeons (as well as P3s) have a shared memory bus. That is, multiple CPUs share the bandwidth of the 400MHz or 533MHz bus when accessing memory. However, Athlon has a point-to-point channel for each CPU. That is, each Athlon CPU has the full bandwidth of the 266MHz (soon to be 333MHz) memory bus, regardless of how many CPUs there are in the system. This means that beyond 2-way SMP systems, Athlon has a significant advantage in memory bandwidth over P4.
he's just trolling for his employer. He always does that.
SPECfp benchmark is highly dependent on the memory bandwidth. P4, with two channels of RDRAM, has more memory bandwidth than Athlon with a single channel of DDR. Thus, P4 gets a free ride here. Show me an apples to apples comparison here: P4 and Athlon with the same memory (be it SDRAM or DDR). I have yet to see one.
For a truly FPU-intensive benchmark that does not depend on memory bandwidth much, check out 3D Sudio rendering (tomshardware & others have it). Athlon simply smokes P4 on that one. Incidentally, on this benchmark P3 1000MHz outperformed P4 1500MHz.
How many? One?
Also, most vendors do not provide CVS packages for things like this. Hell, debian still doesn't even have an official KDE3. And even if there is a CVS version, how many people are going to be quick to hop on it, considering the code in CVS is typically beta at best? And what newbies are even going to know about this?
Some ridiculously stupid mumbles there. Each distribution has an easy way of upgrading the packages. In Debian it's "apt-get updage; apt-get upgrade". In Mandrake & RedHat you just run the GUI updater software. The update icon is right there on the desktop.
Nobody is suggesting that you should install a CVS version of software to get a security fix. The fixes are backported into the stable branches of the software, and vendors package them. Wow, what a concept!
And then your issue on bugfixes. Are you trying to say that OSS patches never break anything?
No, I'm saying that Microsoft breaks stuff more often despite taking months to release a fix.
And KDE's history of poor security would be...?
I also mentioned that, just because a fix is in the KDE project's CVS, does not mean that it is available for everyone - that will have to wait until the next release.
Bull shit. Ever heard of Debian's apt-get, Mandrake's urpmi, RedHat's up2date, etc.? It's up to each vendor to make the fix available to the users. You can also install it yourself without waiting for the vendor to catch up.
Microsoft has hundreds of millions of customers across the world, and the systems handle billions of dollars of revenue... this puts a huge responsiblity to get their fixes right and properly tested
Then can you explain why Microsoft releases bugfixes that uhhm break stuff? Despite the fact that Microsoft takes 2-3 months to uhhh "test" stuff, Open Source community has a much better track record in this regard.
Quite frankly, LinuxToday is becoming unreadable by anyone not a) a KDE super-fan b) rabidly anti-Microsoft.
Quite frankly, you are an idiot spreading FUD.
Ian Goldberg
You do know that serial ATA supports only one drive per channel, don't you?
(see subject) 150MB/s is just a gimmick for the people who don't know any better. The real advantage (to me) is hot-pluggability, and (as already mentioned) thinner & longer cables + backwards compatibility with standard IDE.
2x Socket A
2x 64 bit 66 MHz PCI slots
4x 32 bit 33 MHz PCI slots
4x 266MHz DDR slots
Available from Tyan, Asus, Gigabyte, Abit, etc.
(see subject)
Microsoft submitted falsified evidence -- and got caught. :-) so he admitted the whole testimony was written by MS lawyers.
Microsoft executives lied under oath -- and got caught.
Microsoft wrote the testimony for its "expert witnesses" -- and got caught. This one was actually quite funny. One stooge claimed that the states' demands would lead to "balkanization of windows". Problem was that he didn't know what "balkanization" means
The last gem I read is that MS lawyers quoted selectively from multiple decisions so as to misrepresent their holdings. The judge did not find that strategy persuasive.
Now, you are an attorney, tell me: why are Microsoft executives not being prosecuted for perjury?
This is actually what I want to do. I want to hook up a spare box to the TV and use it to play DVDs, DivX, etc., as well as used it as a PVR. I know TV capture cards are supported on Linux, but what about TV out?
BTW, are hardware MPEG encoders supported under Linux? Some TV capture cards have them built in. It would be more efficient to encode the stream on the card since it uses up less PCI bandwidth.
This would be a perfect media box for the living room: DVDs, CDs, mp3s, PRV, etc. all in one.
Ever read 1984?
You'd be surprised how well that works. Not to the benefit of the common people, of course.
log2(16) = 4
...
log2(32) = 5
log2(64) = 6
log2(128) = 7
log2(256) = 8
by your assumption a*log2(16)^12 + b = 1 ms
for simplicity, let's ignore the constant b.
then:
a*log2(16)^12 = a * 4^12 = 1 ms (by assumption)
a*log2(32)^12 = a * 5^12 = 14.5 ms
a*log2(64)^12 = a * 6^12 = 129.75 ms
a*log2(256)^12 = a * 8^12 = 4096 ms
The author has addressed Microsoft's response in his writeup. Given that there are numerous windows running as LocalSystem on any desktop, Microsoft's response is a load of tripe.
Seeing as he runs windows, this is probably a good guess.
The problem is that Microsoft already spent $300 to make an xbox. They lose that money no matter what. If you buy an xbox they will get $200 and partially recover their losses.
In short, Microsoft loses $100 on an xbox if you buy it. They lose $300 if you don't buy it.
In a sane world, yes.
This is about the stupidest proposition I've herd yet. You obviously have no clue about how Free Software licences (and copyright in general) work, so let me clue you in.
:-)
All all of the so-called click-wrap "licenses" (*) start off with the presumption that even though you bought a copy of software, you are not allowed to use it unless you agree to the "license" (and, in effect, give up your rights). Such a presumption, however, is not supported by copyright law. Quite simply, if you own a copy of software, you may do whatever you want with it, as long as you don't distribute copies of it to someone else. Making copies is the exclusive right of the copyright holder (fair use applies, of course).
(*) The "license" is actually a unilateral contract in that it takes away your rights instead of granting them.
Free Software licenses start off with the (correct) presumption that you can use the software in any way you want (thus, unlike proprietary "licenses", they don't attempt to take away your rights). Instead, they grant you more rights than you normally have. (Thus Free Software licenses are indeed licenses). Specifically, you get the right to distribute the software. There are, however, limitations in the ways you are allowed to do so. For example, GPL stipulates that you may not distribute the software under any other license; BSD allows you to relicense the software, but you must give credit to the original author, etc. If you agree to the license, you get the right to distribute the software; if you don't agree you have no such right.
This is how copyright works. All Free Software licenses are besed entirely in copyright law. They do not attempt to take away your rights as a condition to using the software. This makes them stronger than proprietary "licenses".
The only two cases that I'm aware of where a license was ruled unenforcible involve specifically the proprietary click-wrap "licenses". (Step-Saver v. Wyse Technology and ARS v. Software Link).
IANAL (but I play one on TV
GNU doesn't give a damn what license you use if you write something that links to GLIBC.
But really, tell me again how Microsoft fares
If you are a software developer and want to leverage a Microsoft component you have no right to do that at all. Or does Microsoft now permit you to take some of its proprietary code and distribute it under a license of your choice? Last I checked you could not distribute their code at all.
You don't expect to have any rights to a proprietary code, yet, just because something is Open Source, you assume that you have a God-given right to do with that code as you please, and GPL takes that right away. Bullshit. You cannot distribute someone else's code unless they grant you permission to do so. In the case of proprietary libraries, that permision comes in exchange for payment. In the case of GPL, such permission comes automatically if you accept the terms of the GPL.(*) If the payment is not acceptible to you, then write the code yourself! And stop repeating the "viral" FUD, it makes you sound like an idiot.
(*)Some GPL developers will also let you use their code in your proprietary product in exchange for monetary payment. Just like proprietary developers.
You are obviously a fucking moron since you repeat this blatant Microsoft FUD.
1. Microsoft singled out part of the Open Source in their usual divide and conquer strategy.
2. Microsoft loves BSD because it loves to "borrow" BSD code and incorporate it into its proprietary products. This saves Microsoft quite a bit of money and, many would argue, gives them better quality code too.
3. I see that you have swalloed the "viral" propaganda. Perhaps you can explain to me how exactly GPL "infects" stuff? Maybe you mean the fact that GPL does not permit you to take the code you don't own and incorporate it into your proprietary product? But the same is true of Microsoft's code! You can't take their "shared source" and use it in your product either. With GPL, at least, you can use, modify, and distribute the code all you want as long as you distribute derivative works under GPL. With Microsoft, you have no such option. Why, Microsoft is the virus! I also want to know how exactly GPL "touches" stuff. Oh what you actually mean is that GPL "touches" the code when the company willingly decides to use GPL code in their proprietary product.
If microsoft has never done anything to help any apache or open source effort, why did they fly a few of the zend people into redmond for a week, having them perf tune php on iis ?
Uhhm, because it helps Microsoft, not Open Source. PHP is the most widely used server-side scripting language. It sure helps to have it run well on your web server.
Why is there a mod_frontpage for apache that microsoft publishes ?
Because it helps them to sell Frontpage and install viral software on Unix.
Oh yeah, you assume a lot of stuff about microsoft that is wrong, which makes you kind of an idiot.
Can any of the Debian insiders comment on what the future of Debian looks like?
As for failover, that would be really easy to do regardless of the load balancing support. You just need a cronjob that checks if one of the connections is still up, and reconfigures routing & firewall on timeout.
What I especially want to see:
* ACLs!
* All journalling file systems merged (XFS, JFS, ext3, ReiserFS)
* No more VM stability issues
Anyone know if we can expect that?
On a side note, what are the four FSs above best suited for? I know ReiserFS is really good at working with lots of small files and XFS is excellent at data streaming. Anyone care to add more details?