...I guess that: a) kernel.org doesn't think the 'enterprise readiness' of RH Enterprise Linux is that great, (vs what Fedora offers) even in what should be considered one of the most mission-critical sites in the Linux ecosystem (or that the difference with Fedora is worth paying for) b) No one at RH is bright enough to be embarassed by this and offer kernel.org some free licenses...
Intel manufacturing cost us much better than AMD
on
Dell Might do AMD
·
· Score: 5, Insightful
Look at the published % margins of Intel and AMD and realize that this is much greater gap than you would get simply from Intel's ability ot command a price premium -compared to AMD, Intel's manufacturing costs per die are LESS, so it's not "so expensive".
Say what you want about AMD's microprocessor design prowess, they are definately not in Intel's league in terms of wafer yield and other areas of manufacturing prowess that dictate cost to produce.
Many clueless/.ers are infuriated that the stock market doesn't reward AMD stock price like that of Intel stock price, but if they understood that share value is determined by the ability to make money, not just pump out cool stuff, they'd understand. Making money means keeping your cost-to-selling-price ratio healthy and AMD doesn't manufacture at lowest price and doesn't sell for a premium price.
(BTW, please don't assume this represents some kind of consumer-friendly behaviour for AMD - if they could charge a big premium over Intel's product, they would in a heartbeat. And of course, the poster that said this is a price negotiation tool on Dell's part is correct)
The problem (and I've had Microsoft technical people agree with me on this) is that Microsoft made it possible to to a really half-assed installation that actually works (sort of). This doesn't happen because Windows admins are lazy - the point is economic - many smaller and even mid-size companies have a lot of infrastructure run by partially or totally untrained (self-taught) individuals who, because they were able to bring up a 'working' installation probably THINK they're up to the job. Linux admins tend to be either formally trained or enthousiasts who are have done much better self training and at least are a lot more self-aware of their limitations. In big corporate enterprises the natural breeding ground for Linux staff is UNIX staff that want to move into new ground. When ever I have a discussion with a big IT org that says they can't support another OS, I just ask them to poll their Sun technical staff and see how many have Linux boxes at home (vs how many have a SPARC/Solaris box or even Solaris x86). The answer invariably is that they already have a semi-trained Linux staff ready for more formal learning.
Anyway, the main point is that Windows can be made to run generally as well as UNIXes if the same level of MANAGEMENT DISCIPLINE is employed. The problem is that Windows can be run shoddly, whereas you can't bring up UNIX in production environment without a certain level of expertise. Whoa onto us all if RH and SuSe succeed in making Linux as easy to install and start going as Windows is, because we'll create a whole another class of cheap clueless help that maintain awful installations.
If you realize that a cache transistor uses about 10% of the power consumed (and hence, heat generated) by a logic transistor, you see why the power/thermals issue IS EXACTLY why Intel is shifting a high percentage of die to cache since it generates excellent performance-per-watt compared to logic. Itanium, by the way lives in a much more disciplined thermal-design-point than most modern 'big' chips (eg. 160 watt Power 5) being 130 / 99 / 62 watt (depending on model) - which is actually better than most Xeons, Pentium 4s and other Prescott-core designs
BTW, Another poster (later on) also correctly mentions that Moore's Law simply talks about number of transistors on a chip - not which type and what they're used for - stigmatize cache when you get your own law:-).
1) All distros clearly say that their disro ver X is LSB ver Y compliant and stand behind that.
2) LSB mandates a sufficiently detailed configuration and fileset that a developer can build an app under any LSB ver Y.Z and expect it to install and run (with no missing libaries, re-configuration, config file editing etc) on any other LSB Y.Z compliant disro installation.
3) Oracle ver nn runs under LSB ver Y.Z NOT ONLY RH AS3.x and Suse EL 9.x (or whatever).
4) There's an automated validation that can determine if an initial distro install is (or is still) valid LSB ver Y.Z configuration.
He isn't looking for a new way to do KVM, he wants to be able to give Keyboard/Mouse/Video INPUT to the laptop so it can be the console to a KVM.
Yes, software solutions exist, but that makes assumptions about compatibility between the console application and the OS on the laptop. The perfect solution is something (probably a PCMCIA card) that has input dongles to attach into the console KVM ports on the KVM unit AND a switch that toggles the laptop between KVM mode and laptop mode.
Having said that, the poster that indicated earlier that anything only 20 geeks want will cost $10,000 is right, so I'm not holding my breath for the PCMCIA card.
I would say, though, that it would be really nice if someone could come up with some cheap hardware with keyboard/mouse/VGA connectors that protocol converted to VNC APIs over IP over ethernet. There's a lot of people that could use a cheap KVM over IP solution like this...
8 cores with 4 threads per core does NOT equal 32 cpus. If so - WOW! - my Hyperthreaded Pentium 4 just became a dual-cpu - Which it is not.
HT, or other kinds of Symmetric Multi-Threading DO not give you the benefit of a fully cpu core, as the threads share some resources. Conceptual hint: If you put a full set of all cpu resources (ALUs, etc) for each of N threads - you don't bother to talk about multi-threading anymore, you simply have an N-core processor.
Jonathon would be really talking about a 32-core processor, if that's what Niagra was.
She didnt say she didn't have a boyfriend, she said she wanted to know where you could get one that would care where she was. Clearly she has a boyfriend whose trust in her she interprets as indifference.
Let me get this straight. When you said Itanium doesn't have this, you didn't mean the capability to mark memory non-executable, you meant Itanium didn't have a feature named NX - which of course it doesn't. Sorry Intel failed to use the same marketing terms that AMD used -I really thought most people would expect that you were wrong about Itanium being able to DO something virtually identical. Silly me...
Well. since lots of Intel processors (everything before 386s) had primary clocks much less than 33MHz. Early 8088 (original IBM PC gen) systems DID have a clock of 4MHZ. I seem to recall that, in that ancient era, All Computers actually marked an upgrade board that used an 8MHz (double clocked) processor upgrade board. I think I actually installed one or two back then. If this seems like a small perf gain, look at it as about a 100% improvement in perf.
I can't think of a single gov't that let's it's business people engage in world trade with our trying to even out the "unfair advantages all the rest of the world gets".
Lovely sentiment, but the US is not even the least-worst offender here.
This appears to be a kind of unit common in Toronto and now, I assume, Montreal. You put a certain amount of cash (or creditcard -hence the connectivity need) and it issues a ticket showing your time of expiration for the amount of time you bought that you put on your dashboard. Also, since these have remote management and reporting, the municipality can make very good parking control planning. Why put dumb hardware on a stick (parking meter) in front of each vehicle?
Slashdot Mirror
...I guess that:
a) kernel.org doesn't think the 'enterprise readiness' of RH Enterprise Linux is that great, (vs what Fedora offers) even in what should be considered one of the most mission-critical sites in the Linux ecosystem (or that the difference with Fedora is worth paying for)
b) No one at RH is bright enough to be embarassed by this and offer kernel.org some free licenses...
Look at the published % margins of Intel and AMD and realize that this is much greater gap than you would get simply from Intel's ability ot command a price premium -compared to AMD, Intel's manufacturing costs per die are LESS, so it's not "so expensive".
/.ers are infuriated that the stock market doesn't reward AMD stock price like that of Intel stock price, but if they understood that share value is determined by the ability to make money, not just pump out cool stuff, they'd understand. Making money means keeping your cost-to-selling-price ratio healthy and AMD doesn't manufacture at lowest price and doesn't sell for a premium price.
Say what you want about AMD's microprocessor design prowess, they are definately not in Intel's league in terms of wafer yield and other areas of manufacturing prowess that dictate cost to produce.
Many clueless
(BTW, please don't assume this represents some kind of consumer-friendly behaviour for AMD - if they could charge a big premium over Intel's product, they would in a heartbeat. And of course, the poster that said this is a price negotiation tool on Dell's part is correct)
The problem (and I've had Microsoft technical people agree with me on this) is that Microsoft made it possible to to a really half-assed installation that actually works (sort of).
This doesn't happen because Windows admins are lazy - the point is economic - many smaller and even mid-size companies have a lot of infrastructure run by partially or totally untrained (self-taught) individuals who, because they were able to bring up a 'working' installation probably THINK they're up to the job. Linux admins tend to be either formally trained or enthousiasts who are have done much better self training and at least are a lot more self-aware of their limitations. In big corporate enterprises the natural breeding ground for Linux staff is UNIX staff that want to move into new ground.
When ever I have a discussion with a big IT org that says they can't support another OS, I just ask them to poll their Sun technical staff and see how many have Linux boxes at home (vs how many have a SPARC/Solaris box or even Solaris x86). The answer invariably is that they already have a semi-trained Linux staff ready for more formal learning.
Anyway, the main point is that Windows can be made to run generally as well as UNIXes if the same level of MANAGEMENT DISCIPLINE is employed. The problem is that Windows can be run shoddly, whereas you can't bring up UNIX in production environment without a certain level of expertise. Whoa onto us all if RH and SuSe succeed in making Linux as easy to install and start going as Windows is, because we'll create a whole another class of cheap clueless help that maintain awful installations.
If you realize that a cache transistor uses about 10% of the power consumed (and hence, heat generated) by a logic transistor, you see why the power/thermals issue IS EXACTLY why Intel is shifting a high percentage of die to cache since it generates excellent performance-per-watt compared to logic. Itanium, by the way lives in a much more disciplined thermal-design-point than most modern 'big' chips (eg. 160 watt Power 5) being 130 / 99 / 62 watt (depending on model) - which is actually better than most Xeons, Pentium 4s and other Prescott-core designs :-).
BTW, Another poster (later on) also correctly mentions that Moore's Law simply talks about number of transistors on a chip - not which type and what they're used for - stigmatize cache when you get your own law
...I bet you thought he meant pledges....
1) All distros clearly say that their disro ver X is LSB ver Y compliant and stand behind that.
2) LSB mandates a sufficiently detailed configuration and fileset that a developer can build an app under any LSB ver Y.Z and expect it to install and run (with no missing libaries, re-configuration, config file editing etc) on any other LSB Y.Z compliant disro installation.
3) Oracle ver nn runs under LSB ver Y.Z NOT ONLY RH AS3.x and Suse EL 9.x (or whatever).
4) There's an automated validation that can determine if an initial distro install is (or is still) valid LSB ver Y.Z configuration.
He isn't looking for a new way to do KVM, he wants to be able to give Keyboard/Mouse/Video INPUT to the laptop so it can be the console to a KVM. Yes, software solutions exist, but that makes assumptions about compatibility between the console application and the OS on the laptop. The perfect solution is something (probably a PCMCIA card) that has input dongles to attach into the console KVM ports on the KVM unit AND a switch that toggles the laptop between KVM mode and laptop mode.
Having said that, the poster that indicated earlier that anything only 20 geeks want will cost $10,000 is right, so I'm not holding my breath for the PCMCIA card.
I would say, though, that it would be really nice if someone could come up with some cheap hardware with keyboard/mouse/VGA connectors that protocol converted to VNC APIs over IP over ethernet. There's a lot of people that could use a cheap KVM over IP solution like this...
8 cores with 4 threads per core does NOT equal 32 cpus. If so - WOW! - my Hyperthreaded Pentium 4 just became a dual-cpu - Which it is not.
HT, or other kinds of Symmetric Multi-Threading DO not give you the benefit of a fully cpu core, as the threads share some resources. Conceptual hint: If you put a full set of all cpu resources (ALUs, etc) for each of N threads - you don't bother to talk about multi-threading anymore, you simply have an N-core processor.
Jonathon would be really talking about a 32-core processor, if that's what Niagra was.
... since AMD (unlike Intel) doesn't encrypt microcode updates, a virus CAN do real damage to the physical cpu. Check out this for more details...
She didnt say she didn't have a boyfriend, she said she wanted to know where you could get one that would care where she was. Clearly she has a boyfriend whose trust in her she interprets as indifference.
Too bad.
That's assuming they like Blue. They may be 'EX' guys, Canajun drinkers or their one of those pussies drinkin american shit like Bud.
( Old Cdn joke: Why drinking american beer like making love in a canoe? They're both fuck'n near water! )
...the "Pentium M" processor in Centrino is not a Celeron or any other Pentium 4 Willamette or Northwood or Prescott core derivative.
It was designed from the ground up to perform well at lower clock speeds to lower power consumption and increase battery life.
Didn't somebody already point out the irony of dupe comments on a dupe post? You, sir, are redundant.
Let me get this straight. When you said Itanium doesn't have this, you didn't mean the capability to mark memory non-executable, you meant Itanium didn't have a feature named NX - which of course it doesn't. Sorry Intel failed to use the same marketing terms that AMD used -I really thought most people would expect that you were wrong about Itanium being able to DO something virtually identical. Silly me...
...or Execute Disable. Check out Table 4-6 for more details.
;).
As for the ("waekly" -is that Welsh or what?) IA-32e processors since they aren't shipping yet, you don't know whether they'll have it
Well. since lots of Intel processors
(everything before 386s) had primary clocks much less than 33MHz. Early 8088 (original IBM PC gen) systems DID have a clock of 4MHZ. I seem to recall that, in that ancient era, All Computers actually marked an upgrade board that used an 8MHz (double clocked) processor upgrade board. I think I actually installed one or two back then. If this seems like a small perf gain, look at it as about a 100% improvement in perf.
Intel already implements something similar in Itanium. Extended 32-bit architectures get it next.
(end of msg)
...due to simple arithmetic: if a std 42U rack was full of 1U, dual proc systems (42) that's 84, not 88 cpus AND CERTAINLY not 88 DPs (196 cpus).
Now normally you don't fill all 42U with systems either -for thermal and other logistic reasons.
Probably, your 899 racks (assuming you're right about THAT) would really hold about 35 systems so you're at about 31465 systems (62930 cpus).
US Gov't provides massive farm tax relief, subsidies and tariff protection. (almost as bad as the EU)
Especially with implict subsidies like the Export-Import Bank , it's hardly the US that has clean hands here.
I can't think of a single gov't that let's it's business people engage in world trade with our trying to even out the "unfair advantages all the rest of the world gets".
Lovely sentiment, but the US is not even the least-worst offender here.
...properly or capitalize properly.
This appears to be a kind of unit common in Toronto and now, I assume, Montreal. You put a certain amount of cash (or creditcard -hence the connectivity need) and it issues a ticket showing your time of expiration for the amount of time you bought that you put on your dashboard. Also, since these have remote management and reporting, the municipality can make very good parking control planning. Why put dumb hardware on a stick (parking meter) in front of each vehicle?
BYW, this is an Intel ARM processor
for me too - I'd love $384k per year too...
Gee, Scott, why would you want to work well with a "hairball"?
...after discovering that GNU applications are being used on Windows.