Wouldn't it be nice of the Operating System helped you protect it from intrusive applications? No, you don't get to silently spam half baked crap into/etc/rc.d/init.d just because the you actually need sufficient privilege to do some other thing on install. No, my registry is NOT a free-for-all; you get to put just what you need in there and not go on a fishing expedition or 'fix' stuff you're not compatible with. No, the BIOS isn't for you because you're just a VOIP app and have no business whatsoever mucking around with the nonvolatile CMOS I need to boot. No, I don't need a fourth JVM crammed into my PATH, thanks.
Vendors would be forced to detail the mucking around they do, probably leading to much less mucking around in general. Indifferent users could just do what they always do and bang on the 'accept/yes/ok' widgets. Those of us who know enough to care (or get paid to) would then have an actual chance.
You know, the Blu-ray/HD DVD squabble is not actually important. You rights aren't being trampled on. Most people couldn't care less about it; they're happy with their DVDs and don't mind letting you *philes hash it out with your disposable income.
All "the enemy" on a shoestring budget needs to do is launch a bunch of duds along with the real missile
Won't it cost your proverbial enemy far more money to produce a barrage of dummies? The launcher isn't free just because it's not armed with a warhead. If the enemy can afford such extravagance, why wouldn't they simply arm all the missiles and count on the ones that get through? Either the enemy can afford to launch enough missiles to defeat the defense or they can't. Which is it?
Will it be easier to detect the launch of a salvo of missiles, as opposed to one? What number of lives will be spared by the successful intercepts? What more retaliatory capacity will be preserved by the successful intercepts? What number of either will not be harmed due to the preponderance of dummies? Aren't cruise missiles far more sophisticated than ballistics?
Only a fool would claim ABM can achieve perfect defense. Only detractors attempt to use perfect defense as the standard. Rational people observe that the presence of ABM raises the bar, perhaps enough to matter.
There has always been a boogy man. There will always be a boogy man. No 'better foreign policy' is going to change that. Sometimes the boogy man fades away and were left astounded that we should ever have been concerned. What fools we were! Sometimes the boogy man attacks. Those parts go in the history books, over and over. THAAD is just the modern incarnation of a slightly higher castle wall.
You and I have had the good fortune to be born in a place that can afford to keep the boogy man away. Perhaps you loath yourself and those around you enough to wish it were otherwise. The rest of us don't need to experience actual shrapnel to learn just how fast that attitude can vanish.
This is at the expense of all that extra storage area.
The people for whom these high end disks are intended aren't concerned with the "storage area" of individual devices. They care about the ratio of storage to spindles and arms. They buy things like this.
Why is this front page news?
Because it's a site about stuff geeks want to read. It's actually rather nice to hit the page and find some news about the latest incremental change in storage, as opposed to more move-slash, dot-on politics.
I'm arguing for the side that doesn't feel the need to employ the political class to 'moderate' media. Now, if we attempt to map that to contemporary political parties two things stand out; < 1994 and > 2006. Prior to '94, the 'fairness doctrine' trial balloon was floating around and suddenly vanished when the Right swept the House. It has stayed gone, coincidentally, for 12 years. Post right wing government and it suddenly reappears in the hands of the Left. In short, I'm arguing for the Right on this one.
Corporate control of most media is bad. That doesn't make Government control of media good.
Personally, I'd like a return to the now ancient and forgotten conservative principle that Big is bad. Big in all things, not just Government. I think we would be better served if media ownership was split among vast numbers of small organizations limited, by regulation, to a certain size. $200 billion/year Walmarts are bad. Murdocks and Turners are bad. It used to be illegal for corporations to cross State lines in the US. Imagine if editors and producers of our contemporary media only had to answer to the agendas of small, limited bosses, with lots of potential other bosses in play if necessary.
You'd think with their constant complaints about the liberal media, Republicans would be all in favor of a law requiring CNN et all to present their side fairly.
Bzzt, wrong. Nice uninformed try, however.
Repeal of the "fairness" doctrine basically made conservative talk radio. Limbaugh has been pointing this out for years. Prior to the repeal, AM was good for commodity price reports (cattle, wheat, etc.,) NPR and not much else. After, hundreds of radio shows ranging from psycho wackjob militia types to mainstream conservatives (yes, there are differences) appeared across the US.
Clinton et al tried the same thing in the early 90's. The Right labeled it the 'Hush Rush' bill. It died on the vine after the '94 sweep of Congress. They're back I guess, and for the same reason.
Legislating "fairness" in political discourse is bad. It doesn't matter which side is doing it, mkay? It's just wrong. If DeLay had tried to pull this you'd be apoplectic with hysteria about fascism. It isn't OK because it's coming from some left wing incumbent like Kucinich.
Michalis Bletsas, chief connectivity officer for the project, told the BBC that the industry should be thinking less about pushing technology designed for the Western world on the rest of the planet, and more about developing technologies specifically for the developing world. "The way to do it is not to try and deploy tried and trusted technology but to try and develop technology specifically targeted to the developing world,"
This is misguided. If the "Western" world has no contact with the platform because the "Western" world has been arbitrarily prevented from sharing the platform, what the heck is the third world going do with it? How much digital content has emerged from the third world? It's not like a $100 device is going to also come with a communications infrastructure and host high load Wikipedias. These things are strickly clients! Clients of whom?
Selling the device to "Western" consumers will multiply production volume. I'd buy one in a heartbeat at enough of a premium to fund the units they give away. Higher volume means more bargaining power negotiating component prices and, therefore, lower cost per unit. It doesn't matter if my demand drives up the price; as long as I pay more than the production cost I'm paying for the discounted units. The fact that the brilliant thinking behind this has pegged some arbitrary figure to the units ($100) is boneheaded; the only thing that matters is whether the intended third world beneficiaries can afford their share of the price, damn the cost. I guess when your busy de-Westernizing your product you can't be bothered with economics.
If you're really hard up for one of these things there is nothing to worry about. Most of the hardware will be stolen by third world dictators and funneled right back to the "Western" world via Ebay. No doubt it will then become necessary to criminalize it. Fixing reality is difficult.
for smaller databases, but limiting the tablespace to a single file per database/schema doesn't sound very flexible, and won't allow DBAs to maximize their disk throughput.
That isn't necessarily the case. Recently it has become popular to aggregate spindles into single stripe/mirror volumes with large stripe widths. This spreads I/O operations uniformly across disks. All disks contribute their IOPS capacity to all operations. Large stripe widths attempt to leverage high sequential IO bandwidth.
Oracle calls this policy SAME; Stripe and Mirror Everything. Their Automatic Storage Management (ASM) is an implementation of SAME, and it is recommended for use with both OLTP and OLAP applications.
If I had to make a MySQL Falcon instance fast I would build a large stripe/mirror volume for the (single) tablespace file. The point is that isolating high load tables on separate spindles isn't necessarily the best policy, according to current thinking. Of course there are other reasons for isolating parts of a database, but you only mentioned throughput.
Speed and efficiency of *development*, maybe. Which is the problem. Modern software is so dependent on toolkits and compiler optimizations and...
I wondered where all those vulnerabilities were coming from. It's not humans misusing memory references and overrunning ad hoc fixed length buffers, etc. It's the toolkits, libraries and compilers! Glad we got that figured out.
From the post:
Our computers have thousands times more memory than 20 years ago. Still, programmers are privileging speed and efficiency over security...
This implies is that because memory is larger less attention can be paid to efficiency, but the hapless programmers don't know better. I used to use quicksort when I had 640 KiB of RAM, but now that I have 8 GiB, I'll just use bubble sort. Brilliant.
End users routinely use multiples of bits per second. Some examples; modems 1200/2400/9600/56k b/s, SATA 1.5/3.0 Gb/s, USB 480 Mb/s, Firewire 400/800 Mb/s, Ethernet 10/100/1000 Mb/s, 802.11b 11 Mb/s, etc.
Using bytes introduces too much ambiguity when discussing line capacity. In real communications bytes are often encoded (8B/10B) or are accompanied by (a possibly configurable number of) error correction bits. Higher level protocols add effectively arbitrary amounts of overhead. People who sell capacity aren't going to attempt to promise some number of JPEGs/s via HTTP; they can't know how your use case will actually perform. Siemens labs are certainly not going to deviate from the well characterized and correct practice when promoting their latest work.
It is convenient to convert between line rates and amounts of storage. An easy rule of thumb; 1Gb/s is good for about 100MiB/s. The math says more MiB/s, but usually the people who have to care are dealing with protocols that rob ~15% of this capacity for framing, error correction, security, etc. 1Gb/s -> 100MiB/s errors on the safe side.
While you may have a point, it doesn't really apply in the case of OSDL. OSDL isn't a business in the sense of cost vs. revenue. It is a non-profit organization, funded by sponsors. So, unless the sponsors cut funding and/or OSDL mismanaged itself into a hole, this shouldn't be happening. The sponsors supply a budget and, assuming you have the ability to forecast costs with at least some competence, there should be no dramatic shortfalls.
I'm confident the sponsors haven't cut funding or it would have been news here at/. and elsewhere. How would you keep people that work on open source software from leaking that Intel or HP have walked away? Not likely. That means OSDL is being run poorly by the powers that be.
OSDL is 'funded' by a collection of corporations. As far as I know they don't actually sell anything. So, either their funding was cut, or they have mismanaged themselves into a deficit. Which is it? Anyone actually know? I suppose their recent IP projects have led to high legal costs, but I'll bet someone reading/. knows the truth.
That 'puttering' characterization caught my eye also. There are a lot of CEOs that would be quite proud of 11% annual growth, even on an order of magnitude less revenue. There are investors that won't consider a stock that isn't growing 20% annually. Then there are mutual funds, pension plans, municipalities and wealthy investors that appreciate consistent, secure returns. This BusinessWeek ditty is intended for the former.
locked me down with this software to a specific experience regarding its UI. I cant change the size of icons, nor the position of toolbars etc. Why not MS??
The mostly unmovable toolbars is the first thing I noticed. The second thing is that the/. main page doesn't render correctly.
It's a mess. Firefox et al have nothing to worry about.
Both the US and Russian Navy have plenty of reactors online
Naval reactors have a different design than civilian power reactors. They are smaller and require less frequent refueling events because they burn enriched Uranium and produce less average power. The safety record of US naval reactors is good primarily due to a high degree of training and discipline, and design uniformity over long periods. The Soviet navy experienced a number of serious failures.
A floating civilian reactor will probably not burn enriched Uranium, resulting is a much larger core that must be refueled frequently. That it's mounted on a barge will probably mean it has less containment than a traditional civilian power reactor. It will probably not enjoy the same level of discipline of operation.
I don't think one can extrapolate naval reactor safety to these large floating civilian reactors. Apples and oranges.
AJAX and Java EE are orthogonal. Servlets and EJB serve AJAX clients just fine. Some large fraction of all AJAX clients use Java containers as successfully as any other back end.
If what is meant is Java EE needs some of the AJAX hype... well Java EE has the tools, libraries and maturity to continue thriving with or without AJAX.
I find this inevitable push to bury Hibernate and Spring as throwing a lot of very good tools down the drain in order to continue the Sun monarchy and JCP worship.
Monarchy, worship. Like Java EE doesn't have competitors. Go pop a zit Brandon.
Remember the Enron "Why" campaign? When corporations have so much dead wood wandering the halls that this sort of stuff begins to emerge, you should expect mass layoffs. I don't like being the pessimist, but I'll need this on the record when I say I told you so.
Wake me up when AMD has 65 nm scale cores. The vast majority of Dou Core 2 Duo Conroe Core whatever performance and efficiency gains are due to the differences between 90 and 65 nm features. Smaller scale means more execution units and more sophisticated cache logic on the same die. Until AMD does 65 nm their products will be either too hot or too slow.
We've been at 90 nm for so long people almost forgot what a massive improvement a smaller node size can make. Various AMD 65 nm engineering samples are floating around Asia and AMD has made announcements about various 65 nm models appearing Q4 06, early 2007. This is the real battle. However, no mention of what these quad-core parts are supposed to be using...
Java bytecode is interpreted on a virtual stack based processor. Most bytecode gets JITed into native register based instructions, but the model JVM processor is a stack processor.
Some previous poster noted that CLI is also a stack based model. I can't verify that myself but it wouldn't surprise me; Microsoft is, after all, highly 'innovative' or something.
"Customs" can rifle through your anus without probable cause or even reasonable suspicion. Why anyone would suspect that laptops are somehow sacred and take it up with the courts mystifies me.
I imagine that an array with vertical bays and a pull-out shelf type arrangement could comfortably handle about 80 2.5" SAS drives in 3U of space. Power and cooling issues abound, however.
LSI and others have 36 port expander ICs arriving in the pipe now. HP recently unveiled a few new server models that house more than a dozen drives (Proliant ML570 G4 with 18x drives.) 2.5" SAS is going to make a big impact. DBAs love spindles and 2.5" drives make lots of spindles easy.
Slashdot Mirror
Anybody know how that compares to other forms of energy production, say, fossil fuels or nuclear?
Pretty well, actually. Especially since all those other forms of energy production are limited by the laws of physics.
Wouldn't it be nice of the Operating System helped you protect it from intrusive applications? No, you don't get to silently spam half baked crap into /etc/rc.d/init.d just because the you actually need sufficient privilege to do some other thing on install. No, my registry is NOT a free-for-all; you get to put just what you need in there and not go on a fishing expedition or 'fix' stuff you're not compatible with. No, the BIOS isn't for you because you're just a VOIP app and have no business whatsoever mucking around with the nonvolatile CMOS I need to boot. No, I don't need a fourth JVM crammed into my PATH, thanks.
Vendors would be forced to detail the mucking around they do, probably leading to much less mucking around in general. Indifferent users could just do what they always do and bang on the 'accept/yes/ok' widgets. Those of us who know enough to care (or get paid to) would then have an actual chance.
Too much to ask I guess.
Help! Help! I'm being oppressed!
You know, the Blu-ray/HD DVD squabble is not actually important. You rights aren't being trampled on. Most people couldn't care less about it; they're happy with their DVDs and don't mind letting you *philes hash it out with your disposable income.
Get a grip.
All "the enemy" on a shoestring budget needs to do is launch a bunch of duds along with the real missile
Won't it cost your proverbial enemy far more money to produce a barrage of dummies? The launcher isn't free just because it's not armed with a warhead. If the enemy can afford such extravagance, why wouldn't they simply arm all the missiles and count on the ones that get through? Either the enemy can afford to launch enough missiles to defeat the defense or they can't. Which is it?
Will it be easier to detect the launch of a salvo of missiles, as opposed to one? What number of lives will be spared by the successful intercepts? What more retaliatory capacity will be preserved by the successful intercepts? What number of either will not be harmed due to the preponderance of dummies? Aren't cruise missiles far more sophisticated than ballistics?
Only a fool would claim ABM can achieve perfect defense. Only detractors attempt to use perfect defense as the standard. Rational people observe that the presence of ABM raises the bar, perhaps enough to matter.
There has always been a boogy man. There will always be a boogy man. No 'better foreign policy' is going to change that. Sometimes the boogy man fades away and were left astounded that we should ever have been concerned. What fools we were! Sometimes the boogy man attacks. Those parts go in the history books, over and over. THAAD is just the modern incarnation of a slightly higher castle wall.
You and I have had the good fortune to be born in a place that can afford to keep the boogy man away. Perhaps you loath yourself and those around you enough to wish it were otherwise. The rest of us don't need to experience actual shrapnel to learn just how fast that attitude can vanish.
Give the summary credit for stating the following: "100 gigabits per square centimeter." That is a fine way to measure storage density.
Some NPR page has the volume of an M&M at 0.636cm^3. So this new ditty will store 7.95 GB in the space of an M&M.
Plain.
Because this place gradually evolving into SlashTruth. The people who use to contribute have moved on and been replaced with basement activist types.
This is at the expense of all that extra storage area.
The people for whom these high end disks are intended aren't concerned with the "storage area" of individual devices. They care about the ratio of storage to spindles and arms. They buy things like this.
Why is this front page news?
Because it's a site about stuff geeks want to read. It's actually rather nice to hit the page and find some news about the latest incremental change in storage, as opposed to more move-slash, dot-on politics.
Which side are you arguing for?
:)
That's a great question. I'm glad you asked!
I'm arguing for the side that doesn't feel the need to employ the political class to 'moderate' media. Now, if we attempt to map that to contemporary political parties two things stand out; < 1994 and > 2006. Prior to '94, the 'fairness doctrine' trial balloon was floating around and suddenly vanished when the Right swept the House. It has stayed gone, coincidentally, for 12 years. Post right wing government and it suddenly reappears in the hands of the Left. In short, I'm arguing for the Right on this one.
Corporate control of most media is bad. That doesn't make Government control of media good.
Personally, I'd like a return to the now ancient and forgotten conservative principle that Big is bad. Big in all things, not just Government. I think we would be better served if media ownership was split among vast numbers of small organizations limited, by regulation, to a certain size. $200 billion/year Walmarts are bad. Murdocks and Turners are bad. It used to be illegal for corporations to cross State lines in the US. Imagine if editors and producers of our contemporary media only had to answer to the agendas of small, limited bosses, with lots of potential other bosses in play if necessary.
Or is that too scary?
You'd think with their constant complaints about the liberal media, Republicans would be all in favor of a law requiring CNN et all to present their side fairly.
Bzzt, wrong. Nice uninformed try, however.
Repeal of the "fairness" doctrine basically made conservative talk radio. Limbaugh has been pointing this out for years. Prior to the repeal, AM was good for commodity price reports (cattle, wheat, etc.,) NPR and not much else. After, hundreds of radio shows ranging from psycho wackjob militia types to mainstream conservatives (yes, there are differences) appeared across the US.
Clinton et al tried the same thing in the early 90's. The Right labeled it the 'Hush Rush' bill. It died on the vine after the '94 sweep of Congress. They're back I guess, and for the same reason.
Legislating "fairness" in political discourse is bad. It doesn't matter which side is doing it, mkay? It's just wrong. If DeLay had tried to pull this you'd be apoplectic with hysteria about fascism. It isn't OK because it's coming from some left wing incumbent like Kucinich.
Michalis Bletsas, chief connectivity officer for the project, told the BBC that the industry should be thinking less about pushing technology designed for the Western world on the rest of the planet, and more about developing technologies specifically for the developing world. "The way to do it is not to try and deploy tried and trusted technology but to try and develop technology specifically targeted to the developing world,"
This is misguided. If the "Western" world has no contact with the platform because the "Western" world has been arbitrarily prevented from sharing the platform, what the heck is the third world going do with it? How much digital content has emerged from the third world? It's not like a $100 device is going to also come with a communications infrastructure and host high load Wikipedias. These things are strickly clients! Clients of whom?
Selling the device to "Western" consumers will multiply production volume. I'd buy one in a heartbeat at enough of a premium to fund the units they give away. Higher volume means more bargaining power negotiating component prices and, therefore, lower cost per unit. It doesn't matter if my demand drives up the price; as long as I pay more than the production cost I'm paying for the discounted units. The fact that the brilliant thinking behind this has pegged some arbitrary figure to the units ($100) is boneheaded; the only thing that matters is whether the intended third world beneficiaries can afford their share of the price, damn the cost. I guess when your busy de-Westernizing your product you can't be bothered with economics.
If you're really hard up for one of these things there is nothing to worry about. Most of the hardware will be stolen by third world dictators and funneled right back to the "Western" world via Ebay. No doubt it will then become necessary to criminalize it. Fixing reality is difficult.
for smaller databases, but limiting the tablespace to a single file per database/schema doesn't sound very flexible, and won't allow DBAs to maximize their disk throughput.
That isn't necessarily the case. Recently it has become popular to aggregate spindles into single stripe/mirror volumes with large stripe widths. This spreads I/O operations uniformly across disks. All disks contribute their IOPS capacity to all operations. Large stripe widths attempt to leverage high sequential IO bandwidth.
Oracle calls this policy SAME; Stripe and Mirror Everything. Their Automatic Storage Management (ASM) is an implementation of SAME, and it is recommended for use with both OLTP and OLAP applications.
If I had to make a MySQL Falcon instance fast I would build a large stripe/mirror volume for the (single) tablespace file. The point is that isolating high load tables on separate spindles isn't necessarily the best policy, according to current thinking. Of course there are other reasons for isolating parts of a database, but you only mentioned throughput.
Speed and efficiency of *development*, maybe. Which is the problem. Modern software is so dependent on toolkits and compiler optimizations and...
I wondered where all those vulnerabilities were coming from. It's not humans misusing memory references and overrunning ad hoc fixed length buffers, etc. It's the toolkits, libraries and compilers! Glad we got that figured out.
From the post:
Our computers have thousands times more memory than 20 years ago. Still, programmers are privileging speed and efficiency over security...
This implies is that because memory is larger less attention can be paid to efficiency, but the hapless programmers don't know better. I used to use quicksort when I had 640 KiB of RAM, but now that I have 8 GiB, I'll just use bubble sort. Brilliant.
End users do not
End users routinely use multiples of bits per second. Some examples; modems 1200/2400/9600/56k b/s, SATA 1.5/3.0 Gb/s, USB 480 Mb/s, Firewire 400/800 Mb/s, Ethernet 10/100/1000 Mb/s, 802.11b 11 Mb/s, etc.
Using bytes introduces too much ambiguity when discussing line capacity. In real communications bytes are often encoded (8B/10B) or are accompanied by (a possibly configurable number of) error correction bits. Higher level protocols add effectively arbitrary amounts of overhead. People who sell capacity aren't going to attempt to promise some number of JPEGs/s via HTTP; they can't know how your use case will actually perform. Siemens labs are certainly not going to deviate from the well characterized and correct practice when promoting their latest work.
It is convenient to convert between line rates and amounts of storage. An easy rule of thumb; 1Gb/s is good for about 100MiB/s. The math says more MiB/s, but usually the people who have to care are dealing with protocols that rob ~15% of this capacity for framing, error correction, security, etc. 1Gb/s -> 100MiB/s errors on the safe side.
While you may have a point, it doesn't really apply in the case of OSDL. OSDL isn't a business in the sense of cost vs. revenue. It is a non-profit organization, funded by sponsors. So, unless the sponsors cut funding and/or OSDL mismanaged itself into a hole, this shouldn't be happening. The sponsors supply a budget and, assuming you have the ability to forecast costs with at least some competence, there should be no dramatic shortfalls.
/. and elsewhere. How would you keep people that work on open source software from leaking that Intel or HP have walked away? Not likely. That means OSDL is being run poorly by the powers that be.
I'm confident the sponsors haven't cut funding or it would have been news here at
OSDL is 'funded' by a collection of corporations. As far as I know they don't actually sell anything. So, either their funding was cut, or they have mismanaged themselves into a deficit. Which is it? Anyone actually know? I suppose their recent IP projects have led to high legal costs, but I'll bet someone reading /. knows the truth.
That 'puttering' characterization caught my eye also. There are a lot of CEOs that would be quite proud of 11% annual growth, even on an order of magnitude less revenue. There are investors that won't consider a stock that isn't growing 20% annually. Then there are mutual funds, pension plans, municipalities and wealthy investors that appreciate consistent, secure returns. This BusinessWeek ditty is intended for the former.
locked me down with this software to a specific experience regarding its UI. I cant change the size of icons, nor the position of toolbars etc. Why not MS??
/. main page doesn't render correctly.
The mostly unmovable toolbars is the first thing I noticed. The second thing is that the
It's a mess. Firefox et al have nothing to worry about.
Both the US and Russian Navy have plenty of reactors online
Naval reactors have a different design than civilian power reactors. They are smaller and require less frequent refueling events because they burn enriched Uranium and produce less average power. The safety record of US naval reactors is good primarily due to a high degree of training and discipline, and design uniformity over long periods. The Soviet navy experienced a number of serious failures.
A floating civilian reactor will probably not burn enriched Uranium, resulting is a much larger core that must be refueled frequently. That it's mounted on a barge will probably mean it has less containment than a traditional civilian power reactor. It will probably not enjoy the same level of discipline of operation.
I don't think one can extrapolate naval reactor safety to these large floating civilian reactors. Apples and oranges.
AJAX and Java EE are orthogonal. Servlets and EJB serve AJAX clients just fine. Some large fraction of all AJAX clients use Java containers as successfully as any other back end.
If what is meant is Java EE needs some of the AJAX hype... well Java EE has the tools, libraries and maturity to continue thriving with or without AJAX.
I find this inevitable push to bury Hibernate and Spring as throwing a lot of very good tools down the drain in order to continue the Sun monarchy and JCP worship.
Monarchy, worship. Like Java EE doesn't have competitors. Go pop a zit Brandon.
Remember the Enron "Why" campaign? When corporations have so much dead wood wandering the halls that this sort of stuff begins to emerge, you should expect mass layoffs. I don't like being the pessimist, but I'll need this on the record when I say I told you so.
Wake me up when AMD has 65 nm scale cores. The vast majority of Dou Core 2 Duo Conroe Core whatever performance and efficiency gains are due to the differences between 90 and 65 nm features. Smaller scale means more execution units and more sophisticated cache logic on the same die. Until AMD does 65 nm their products will be either too hot or too slow.
We've been at 90 nm for so long people almost forgot what a massive improvement a smaller node size can make. Various AMD 65 nm engineering samples are floating around Asia and AMD has made announcements about various 65 nm models appearing Q4 06, early 2007. This is the real battle. However, no mention of what these quad-core parts are supposed to be using...
Java bytecode is interpreted on a virtual stack based processor. Most bytecode gets JITed into native register based instructions, but the model JVM processor is a stack processor.
Some previous poster noted that CLI is also a stack based model. I can't verify that myself but it wouldn't surprise me; Microsoft is, after all, highly 'innovative' or something.
"Customs" can rifle through your anus without probable cause or even reasonable suspicion. Why anyone would suspect that laptops are somehow sacred and take it up with the courts mystifies me.
Here is a link to the NASA page on the AD-1
8x 2.5" SAS drives in 2x 5.25" bays, available now from Supermicro.
Xtore has a 2U 24x SAS JBOD here
I imagine that an array with vertical bays and a pull-out shelf type arrangement could comfortably handle about 80 2.5" SAS drives in 3U of space. Power and cooling issues abound, however.
LSI and others have 36 port expander ICs arriving in the pipe now. HP recently unveiled a few new server models that house more than a dozen drives (Proliant ML570 G4 with 18x drives.) 2.5" SAS is going to make a big impact. DBAs love spindles and 2.5" drives make lots of spindles easy.