Back in the day, I worked for a major PC manufacturer. When someone would call up and needed some minor part in their computer replaced under warranty, it always made me wince - after covering all of the costs of sending out a technician, a $40 part could easily end up costing us $200 to replace. It only takes one of those to devour the profits on a good number of PC's.
The reason for doing it in hardware is so that Joe Average, who couldn't set up a VPN if his life depended on it, isn't left completely open.
Don't get me wrong, this isn't going to suddenly make every network completely safe. But it's certainly a step up from a completely non-encrypted network, even if only a small or medium step.
As for every protocol handling encryption itself, handling ecryption reliably isn't easy. I'd much rather trust one central, *well designed* security model than fifty that ranged from well-done to half-baked. We see that all the time from people who try to implement their own encryption mechanisms instead of using the libraries that have tens of thousands of man-hours from well-educated people behind them.
Now, whether this is a "well designed" security model, that's another question all together, and one to which the answer very well may be "no".
I haven't looked around for making your own, but Hypertek makes a whole line of N2O motors:
http://www.magnumrockets.com/hypertek.html
There are also some mailing lists just for "experimental" rocketry (meaning anything that's made yourself). Google for "experimental rocketry", and you'll get a whole slew.
If you want to keep your wireless network secure, tie MAC addresses to IP addresses, and presto!
Presto, you're screwed? What keeps a "baddie" from sniffing your traffic, waiting until you're not on, then changing his MAC address to be the same as yours? Oh, gee... I guess that doesn't buy you very much, either.
Even if it did, that still doesn't keep them from *sniffing* your network. Any data you transmit, they have. Just checked your email? Chances are they have your password. And all of those pictures that your girlfriend sent to you in those pictures. And those are just benign examples.
Putting encryption at this level is useless because secure communication with e.g. a webserver still requires that I encrypt over HTTPS
Until *every* protocol that goes over your network has reliable encryption, then this is still useful.
Hey wait, can we hit two birds with one stone and sell the ingredients and instructions on mixing rubber particles and N2O to MAKE model rocket engines, thereby skirting the legal restriction? hmmm. Like a website where you can order both ingredients and a reusable mixing chamber + exhaust for them to combust within
Of course you can. N2O rocket motors aren't uncommon. They require a higher initial outlay for the N20 tank and the charging equipment, but once that's done, they're cheap and easy. In the N2O combustion chamber, just about anything works as fuel - a lot of the "fuel" used in them is nothing more than a plastic rod.
Unless something has changed that I'm not aware of, you can buy a high-power rocket motor at a launch without any permit *if you use it at the launch*. Not the easiest way, but it does work.
Contact your local high-power rocket club. In our area, one of the local vendors got their permits to sell motors, so you can show up at a launch, buy a motor, and fly. Again, not necessarily the easiest or best, but it does work.
Or, you could just use the nitrous-oxide hybrids. No permits required. If your club fronts the money for the initial charging equipment, it's not a bad way to go.
Why, oh why are people who can't even think to use a firewall allowed to submit questions to "Ask Slashdot?"
It doesn't even have to be that fancy of a firewall. Shoot, even just being behind a NAT will protect you sufficiently from incoming attacks that you should be able to update the machine without being exploited - and that's not even a firewall, that's just routing!
Right now, there are dually boards intended for workstation/desktop use where each of the two processers has 4 DIMM sockets associated with it. If these dual-core chips were done ideally, then each chip would have two cores, each having two DIMM sockets. The real estate usage is the same. The total maximum memory is the same - but you'd have twice the potential bandwidth.
On single-socket boards, you'd still have the same 4 DIMM slots you have now - 2 DIMM slots per core. It wouldn't cost any more, and it wouldn't use any more space. Now maybe there's some reason on the pinout that it can't be done, and that would be sad. But if the pinout allowed it, the motherboard cost wouldn't be any greater.
You don't need that much memory
It's not about the amount of memory, it's about the amount of memory bandwidth. Do you need 26+ gigabytes/second of bandwidth for the desktop? No, you don't need it. But if it were possible with little to no increase in cost, then why not?
It wouldn't even force people to use more DIMMs than they use now. Shoot, you could run an 8-way Opteron on two DIMMs if you wanted. It would be kind of a waste, but it could be done. : )
If you're at all familiar with the Opteron architecture, you'd realize that each chip's memory controller does, indeed go to a new memory bank.
As an example, I just bought a 4-way Opteron. It's got four seperate banks of memory on it. Each processer has a 128-bit, DDR400 memory controller, all independent of each other.
If you have a program on each CPU, accessing memory tied to that CPU, the 4-way machine I mentioned would have a theoretical memory throughput of 25.6 gigabytes/second. The theoretical throughput of a dual-Xeon machine is 5.4 gigabytes/second. That's a huge difference.
You're right, it takes some intelligent work to schedule programs on CPUs that are close to the memory the program will access. If you hadn't been in a hole for the past year or two, you'd know that there has been a lot of work put into Linux to make it handle these NUMA architectures more intelligently. IBM has some VERY large NUMA systems, and has been pouring a lot of development into Linux.
As for system costs going up so much that it would be prohibitive for a desktop, think again. AMD's entire desktop line is transistioning to the Opteron architecture. Even the lowly 1xx single-proc Opterons and Athlon64's have nearly all of the features of the highest 8xx 8-way chips. The difference between a 848 and a 148 is just reduced cache, and fewer Hypertransport lines out of the chip.
Because the overall size of the die is a tremendous factor in the cost of a processer. Because of that, die sizes tend to stay relatively constant over the years.
As manufacturers are able to squeeze the transistors in more tightly, then you see more circuitry appearing. As they move to 90-nanometer production, they're going to be able to pack on more transistors, and using dual cores becomes an economic possibility. However, throwing FOUR cores on would make the die large enough to be an economic disaster. (Die size was one of the largest problems with the Pentium Pro.)
Forget dual cores. What about Xeons, with Hyperthreading - where the system "sees" two chips? Nothing like paying a dual-processer license so that you can use a single chip.
If Firefox is rendering a page, you've got Firefox doing the rendering, the GUI working with video drivers, disk drivers looking at/updating your browser's cache, kernel code managing disk cache, kernel code managing network activity, and perhaps even firewall code running.
Whether you use Linux or Windows, there are a LOT of things running that you don't see in normal process list.
Now, will dual CPU's speed up that render time in Firefox? Not to any significant amount. But having used a LOT of dual-CPU systems, I can say that under heavy load, the machine will be much more responsive. If that helps your workload, it might be worth it. If it doesn't, it's not worth it.
As an example, at work I have a dual AthlonMP 1800+. At home, I have a single AthlonXP 3200+. For what I do at work, the single-proc chip would suck rocks. For what I do at home, the 1800+ would not compare to the 3200+. It's all about your usage.
You really can't figure out why they're focusing on CMP? It's not exactly tough. They don't have to design a new architecture. That saves a LOT of money in R&D, and (more importantly) cuts a LOT of time off of time-to-market. It's also VERY easy - especially with the Opterons. Copy the lithograph, connect the HT links, and you're done. To top it all off, it's something that will fetch a good price premium
To summarize, it's easy, fast, and will (supposedly) make them more money. That's a lot more attractive than sinking gobs of money and time into trying to design something new that may or may not pan out to be all that attractive.
The principle reason why the Opterons are kicking the trash out of Intel's Xeon line is the memory bandwidth - with each processor you stick in the board, you're getting another 128-bit memory controller. With a well-designed OS, that equates to enormous potential memory bandwidths.
I've been a little leary of the dual-Opteron stories. Yes, it'll let you pack more CPU's into your board: But will you be able to utilize the additional memory controller in that extra core? If so, it will rock trash. If not, then it's losing the key strength of the Opteron.
Now, it *could* be done. The existing Opteron pinouts provide for four DIMM sockets. With dual-core chips, that same pinout could provide *two* DIMM sockets for each of the two cores. If that's how they go, then AMD is going to continue their incredibly strong showing in the server arena.
(FWIW, I just bought a 4x848 Opteron system, and it is a *screamer* at database work!)
Can you tell the difference? It depends. If you're talking the difference between 20 and 40 FPS, anyone can tell the difference. From 40 to 60 FPS, many people can. Once you get above 85 FPS, the number of people who can tell the difference drops off very steeply. Above 100 or 120 FPS, then it really doesn't make any difference at all.
I'm sure that someone will jump in and say that you can't perceive more than 30 FPS. That's simply bull. I used to have a very nifty demo that simply showed a few moving blocks on the screen - one at 15 FPS, one at 30 FPS, one at 60 FPS, and one at 120 FPS. The difference was immediately obvious to everyone I showed it to.
Now, will that make a difference in your game play? Maybe, maybe not. Even in first-person-shooter games, I don't usually get much (if any) benefit from anything over about 60 FPS. Others argue that they get a benefit. It all depends on the person.
Like all other hardware purchases, it's a compromise between getting hardware that will last at least some time into the future, and actually getting some value for what you buy. If you buy the very latest-and-greatest, you're paying out the nose (and other bodily orifices) for what you get.
For less money, you could get a CRT that has a higher framerate than that LCD. With a 25ms response time, it can only show up to 40 FPS.
Had you bought a CRT instead, you could have (A) saved enough money to buy a MUCH better processer, and (B) been able to actually show the improved framerates.
Now, if having the higher processer and an LCD make you feel good about having spent your money, then that's what counts. I, on the other hand, would have much preferred the CRT/better graphics card route.
Actually, people I know who have tried Doom3 with an 1800-class Athlon and a *good* AGP video card have been pretty pleased with it.
I decided to stop waiting for the upgrade, and bought an AthlonXP-M 2500, running at 3200 speeds. With a better video card, I have no doubt that it'll play Doom3 just fine.
Wow. An AthlonXP-M 2500+ (overclocked, of course), an NForce2 motherboard, some good memory, and a hot video card, and you've got a 3200-class machine w/ brand-new, hot graphics for $1,000, with $400 of that going just to the video card.
Before firing a bullet, your gun will be pointed at a great many things before needing to be fired. But I highlight precious few things without wanting them to be copied!
highlighting text in Linux automatically performs a copy while the middle mouse button performs a paste
I wish. That's the behavior that I prefer. In the past half-year, I've tried about four different distributions, and none of them have had that as the default behavior. It seems like they're intentionally trying to become like Windows.
Slashdot Mirror
Back in the day, I worked for a major PC manufacturer. When someone would call up and needed some minor part in their computer replaced under warranty, it always made me wince - after covering all of the costs of sending out a technician, a $40 part could easily end up costing us $200 to replace. It only takes one of those to devour the profits on a good number of PC's.
steve
You get a lot different mileage at 6,000 feet above sea level than you do at 100 feet above sea level.
steve
The reason for doing it in hardware is so that Joe Average, who couldn't set up a VPN if his life depended on it, isn't left completely open.
Don't get me wrong, this isn't going to suddenly make every network completely safe. But it's certainly a step up from a completely non-encrypted network, even if only a small or medium step.
As for every protocol handling encryption itself, handling ecryption reliably isn't easy. I'd much rather trust one central, *well designed* security model than fifty that ranged from well-done to half-baked. We see that all the time from people who try to implement their own encryption mechanisms instead of using the libraries that have tens of thousands of man-hours from well-educated people behind them.
Now, whether this is a "well designed" security model, that's another question all together, and one to which the answer very well may be "no".
steve
I haven't looked around for making your own, but Hypertek makes a whole line of N2O motors:
http://www.magnumrockets.com/hypertek.html
There are also some mailing lists just for "experimental" rocketry (meaning anything that's made yourself). Google for "experimental rocketry", and you'll get a whole slew.
steve
If you want to keep your wireless network secure, tie MAC addresses to IP addresses, and presto!
Presto, you're screwed? What keeps a "baddie" from sniffing your traffic, waiting until you're not on, then changing his MAC address to be the same as yours? Oh, gee... I guess that doesn't buy you very much, either.
Even if it did, that still doesn't keep them from *sniffing* your network. Any data you transmit, they have. Just checked your email? Chances are they have your password. And all of those pictures that your girlfriend sent to you in those pictures. And those are just benign examples.
Putting encryption at this level is useless because secure communication with e.g. a webserver still requires that I encrypt over HTTPS
Until *every* protocol that goes over your network has reliable encryption, then this is still useful.
steve
Hey wait, can we hit two birds with one stone and sell the ingredients and instructions on mixing rubber particles and N2O to MAKE model rocket engines, thereby skirting the legal restriction? hmmm. Like a website where you can order both ingredients and a reusable mixing chamber + exhaust for them to combust within
Of course you can. N2O rocket motors aren't uncommon. They require a higher initial outlay for the N20 tank and the charging equipment, but once that's done, they're cheap and easy. In the N2O combustion chamber, just about anything works as fuel - a lot of the "fuel" used in them is nothing more than a plastic rod.
steve
Unless something has changed that I'm not aware of, you can buy a high-power rocket motor at a launch without any permit *if you use it at the launch*. Not the easiest way, but it does work.
Contact your local high-power rocket club. In our area, one of the local vendors got their permits to sell motors, so you can show up at a launch, buy a motor, and fly. Again, not necessarily the easiest or best, but it does work.
Or, you could just use the nitrous-oxide hybrids. No permits required. If your club fronts the money for the initial charging equipment, it's not a bad way to go.
steve
Why, oh why are people who can't even think to use a firewall allowed to submit questions to "Ask Slashdot?"
It doesn't even have to be that fancy of a firewall. Shoot, even just being behind a NAT will protect you sufficiently from incoming attacks that you should be able to update the machine without being exploited - and that's not even a firewall, that's just routing!
steve
Right now, there are dually boards intended for workstation/desktop use where each of the two processers has 4 DIMM sockets associated with it. If these dual-core chips were done ideally, then each chip would have two cores, each having two DIMM sockets. The real estate usage is the same. The total maximum memory is the same - but you'd have twice the potential bandwidth.
On single-socket boards, you'd still have the same 4 DIMM slots you have now - 2 DIMM slots per core. It wouldn't cost any more, and it wouldn't use any more space. Now maybe there's some reason on the pinout that it can't be done, and that would be sad. But if the pinout allowed it, the motherboard cost wouldn't be any greater.
You don't need that much memory
It's not about the amount of memory, it's about the amount of memory bandwidth. Do you need 26+ gigabytes/second of bandwidth for the desktop? No, you don't need it. But if it were possible with little to no increase in cost, then why not?
It wouldn't even force people to use more DIMMs than they use now. Shoot, you could run an 8-way Opteron on two DIMMs if you wanted. It would be kind of a waste, but it could be done. : )
steve
No it doesn't
Yes, it does.
If you're at all familiar with the Opteron architecture, you'd realize that each chip's memory controller does, indeed go to a new memory bank.
As an example, I just bought a 4-way Opteron. It's got four seperate banks of memory on it. Each processer has a 128-bit, DDR400 memory controller, all independent of each other.
If you have a program on each CPU, accessing memory tied to that CPU, the 4-way machine I mentioned would have a theoretical memory throughput of 25.6 gigabytes/second. The theoretical throughput of a dual-Xeon machine is 5.4 gigabytes/second. That's a huge difference.
You're right, it takes some intelligent work to schedule programs on CPUs that are close to the memory the program will access. If you hadn't been in a hole for the past year or two, you'd know that there has been a lot of work put into Linux to make it handle these NUMA architectures more intelligently. IBM has some VERY large NUMA systems, and has been pouring a lot of development into Linux.
As for system costs going up so much that it would be prohibitive for a desktop, think again. AMD's entire desktop line is transistioning to the Opteron architecture. Even the lowly 1xx single-proc Opterons and Athlon64's have nearly all of the features of the highest 8xx 8-way chips. The difference between a 848 and a 148 is just reduced cache, and fewer Hypertransport lines out of the chip.
steve
Because the overall size of the die is a tremendous factor in the cost of a processer. Because of that, die sizes tend to stay relatively constant over the years.
As manufacturers are able to squeeze the transistors in more tightly, then you see more circuitry appearing. As they move to 90-nanometer production, they're going to be able to pack on more transistors, and using dual cores becomes an economic possibility. However, throwing FOUR cores on would make the die large enough to be an economic disaster. (Die size was one of the largest problems with the Pentium Pro.)
steve
Forget dual cores. What about Xeons, with Hyperthreading - where the system "sees" two chips? Nothing like paying a dual-processer license so that you can use a single chip.
steve
Multithreaded and multi-process.
If Firefox is rendering a page, you've got Firefox doing the rendering, the GUI working with video drivers, disk drivers looking at/updating your browser's cache, kernel code managing disk cache, kernel code managing network activity, and perhaps even firewall code running.
Whether you use Linux or Windows, there are a LOT of things running that you don't see in normal process list.
Now, will dual CPU's speed up that render time in Firefox? Not to any significant amount. But having used a LOT of dual-CPU systems, I can say that under heavy load, the machine will be much more responsive. If that helps your workload, it might be worth it. If it doesn't, it's not worth it.
As an example, at work I have a dual AthlonMP 1800+. At home, I have a single AthlonXP 3200+. For what I do at work, the single-proc chip would suck rocks. For what I do at home, the 1800+ would not compare to the 3200+. It's all about your usage.
steve
That's still not exactly exhorbitant. The UltraSparc-IV's have about 1400 pins.
steve
You really can't figure out why they're focusing on CMP? It's not exactly tough. They don't have to design a new architecture. That saves a LOT of money in R&D, and (more importantly) cuts a LOT of time off of time-to-market. It's also VERY easy - especially with the Opterons. Copy the lithograph, connect the HT links, and you're done. To top it all off, it's something that will fetch a good price premium
To summarize, it's easy, fast, and will (supposedly) make them more money. That's a lot more attractive than sinking gobs of money and time into trying to design something new that may or may not pan out to be all that attractive.
steve
The principle reason why the Opterons are kicking the trash out of Intel's Xeon line is the memory bandwidth - with each processor you stick in the board, you're getting another 128-bit memory controller. With a well-designed OS, that equates to enormous potential memory bandwidths.
I've been a little leary of the dual-Opteron stories. Yes, it'll let you pack more CPU's into your board: But will you be able to utilize the additional memory controller in that extra core? If so, it will rock trash. If not, then it's losing the key strength of the Opteron.
Now, it *could* be done. The existing Opteron pinouts provide for four DIMM sockets. With dual-core chips, that same pinout could provide *two* DIMM sockets for each of the two cores. If that's how they go, then AMD is going to continue their incredibly strong showing in the server arena.
(FWIW, I just bought a 4x848 Opteron system, and it is a *screamer* at database work!)
steve
Can you tell the difference? It depends. If you're talking the difference between 20 and 40 FPS, anyone can tell the difference. From 40 to 60 FPS, many people can. Once you get above 85 FPS, the number of people who can tell the difference drops off very steeply. Above 100 or 120 FPS, then it really doesn't make any difference at all.
I'm sure that someone will jump in and say that you can't perceive more than 30 FPS. That's simply bull. I used to have a very nifty demo that simply showed a few moving blocks on the screen - one at 15 FPS, one at 30 FPS, one at 60 FPS, and one at 120 FPS. The difference was immediately obvious to everyone I showed it to.
Now, will that make a difference in your game play? Maybe, maybe not. Even in first-person-shooter games, I don't usually get much (if any) benefit from anything over about 60 FPS. Others argue that they get a benefit. It all depends on the person.
Like all other hardware purchases, it's a compromise between getting hardware that will last at least some time into the future, and actually getting some value for what you buy. If you buy the very latest-and-greatest, you're paying out the nose (and other bodily orifices) for what you get.
steve
For less money, you could get a CRT that has a higher framerate than that LCD. With a 25ms response time, it can only show up to 40 FPS.
Had you bought a CRT instead, you could have (A) saved enough money to buy a MUCH better processer, and (B) been able to actually show the improved framerates.
Now, if having the higher processer and an LCD make you feel good about having spent your money, then that's what counts. I, on the other hand, would have much preferred the CRT/better graphics card route.
steve
Actually, people I know who have tried Doom3 with an 1800-class Athlon and a *good* AGP video card have been pretty pleased with it.
I decided to stop waiting for the upgrade, and bought an AthlonXP-M 2500, running at 3200 speeds. With a better video card, I have no doubt that it'll play Doom3 just fine.
steve
Wow. An AthlonXP-M 2500+ (overclocked, of course), an NForce2 motherboard, some good memory, and a hot video card, and you've got a 3200-class machine w/ brand-new, hot graphics for $1,000, with $400 of that going just to the video card.
steve
It is apparently possible to cleanse the body of such toxins.
Actually, it's possible to make money telling people that you can cleanse the body of such toxins.
steve
Before firing a bullet, your gun will be pointed at a great many things before needing to be fired. But I highlight precious few things without wanting them to be copied!
steve
I fail to see how a 100mbit (12.5 megabyte) link is "many times" faster than a 7-10 megabyte CF card.
In fact, add in overhead, and the speeds could be at parity.
steve
highlighting text in Linux automatically performs a copy while the middle mouse button performs a paste
I wish. That's the behavior that I prefer. In the past half-year, I've tried about four different distributions, and none of them have had that as the default behavior. It seems like they're intentionally trying to become like Windows.
steve
Billy-boy can give me one of those dual-core Longhorn-capable machines for free, and Sun can give me a nifty SPARC-powered machine for free.
Then I'll install Linux on them, and forgo the software rental fees.
steve