I was asked to evaluate several distributed computing projects last year. The company wanted to do something other than just waste electricity with idle CPUs. However, I wasn't asked to investigate only client machine performance so much as I was asked for data on bandwidth consumption.
My company is moderately sized (~140 employees) and uses a large amount of bandwidth on a near constant basis. While our data does not need to flow in real time, any disruption in our network can cause quite an uproar directed at the IT department, of which I am a member.
While the data transfers involved with projects like SETI@Home and Folding@Home are small in comparison to our normal traffic, my superiors were concerned that if many connections were made to the central server simultaneously, there would be a noticable drop in performance.
I think this bandwidth issue, and not client performance, stands as the major roadblock to more corporate participantion.
What I meant was that if mini-subs are introduced, the people they're replacing (submarine crews) aren't adrenaline junkies like USAF fighter pilots. I probably should have made that more clear.
In the US Air Force and part of the Army, pilots of traditional fighter/bomber aircraft are none too thrilled with the unmanned aerial vehicles. You go from putting it all on the line everytime you strap on the flight suit to sitting in a nice air-conditioned office playing what amounts to a fancy (and amazingly lifelike) video game. There is intense pressure from the pilots to scale this program down immensely.
The Navy however, has no figher pilot equivalent. The billion dollar war platforms that make up the submarine force are already very unglamorous to work in. The price tag of these ships brings in a whole new player to this battle. Congressmen and women LOVE to see high-priced defense contracts being given to shipyards in their districts.
If these mini-subs are truly effective and the demand for hugely expensive nuclear powered subs begins to drop, it will be interesting to see which senators favor the modernization of our military vs. those who want more pork barrel projects pumping fuel into their local economies.
Wouldn't it be far simpler to put a half dozen IR-emitting devices behind/around the movie screen? We all know that the IR flashes given off by simple remote control devices show up on camera, why not simply arange a highly annoying pattern with those? Its not harmful, else they wouldn't be in consumer electronics, and its got to be cheaper than the method they're talking about.
From the sounds of the article, he wants to make register mappings more logical than virtual. My knowledge of assembly level programming is pretty basic, but I do agree that adding more GP registers would probably increase performance measureably.
His second proposal, the RegisterMap field strikes me as the incredibly complex part of this idea. He sounds like he's suggesting an idea that will turn x86 achitecture into a simplified emulator by allowing you logically map any register address to any physical address you choose. While there are probably some benefits to this, it sounds like the complexity of programming an already exceptionally complex chipset could go through the roof!
I read somewhere in a previous article (last year sometime, can't find a link) that the way most compilers treated x86 was already done with so many pseduo instructions as to basically be an emulator. Now this was before I had any knowledge of assembly level programming, so maybe someone with more knoweldge could clarify this?
Lets see here. This story is about big pulse lasers that will be used by the military to blow stuff up. The previous story was about a Battletech fan who built a 'Mech (albeit a fake one) in his back yard.
If this isn't just an awesome Slashdot engineering project waiting to happen, I don't know what is!
PS - If someone has already beat me to it and is already forming the engineering team, count me in!!
Microsoft will NOT be able to convince any computer professional to use this "Palladium" crap for a server. They won't even try.
Just like they were never able to convince any companies to use that crap IIS server, right?
Until we get better trained and more experienced Sys/Network Admins in the work force, MS servers will remain a player in the field.
This may be a kind of radical idea, but how about we not derail ANY trains? Sabotage is sabotage and just because the information is targeted at one specific train doesn't mean it couldn't be applied to a different train. I prefer riding the rails without having to worry if some lunatic figured out how many stacked pennies on the tracks it takes to derail it.
Slashdot Mirror
My company is moderately sized (~140 employees) and uses a large amount of bandwidth on a near constant basis. While our data does not need to flow in real time, any disruption in our network can cause quite an uproar directed at the IT department, of which I am a member.
While the data transfers involved with projects like SETI@Home and Folding@Home are small in comparison to our normal traffic, my superiors were concerned that if many connections were made to the central server simultaneously, there would be a noticable drop in performance.
I think this bandwidth issue, and not client performance, stands as the major roadblock to more corporate participantion.
-Shadow
-Shadow
For a 4 year enlistment who just wants a way to get school paid for it can be a real drag.
-Shadow
The Navy however, has no figher pilot equivalent. The billion dollar war platforms that make up the submarine force are already very unglamorous to work in. The price tag of these ships brings in a whole new player to this battle. Congressmen and women LOVE to see high-priced defense contracts being given to shipyards in their districts.
If these mini-subs are truly effective and the demand for hugely expensive nuclear powered subs begins to drop, it will be interesting to see which senators favor the modernization of our military vs. those who want more pork barrel projects pumping fuel into their local economies.
-Shadow
Shadow
His second proposal, the RegisterMap field strikes me as the incredibly complex part of this idea. He sounds like he's suggesting an idea that will turn x86 achitecture into a simplified emulator by allowing you logically map any register address to any physical address you choose. While there are probably some benefits to this, it sounds like the complexity of programming an already exceptionally complex chipset could go through the roof!
I read somewhere in a previous article (last year sometime, can't find a link) that the way most compilers treated x86 was already done with so many pseduo instructions as to basically be an emulator. Now this was before I had any knowledge of assembly level programming, so maybe someone with more knoweldge could clarify this?
-Shadow
Lets see here. This story is about big pulse lasers that will be used by the military to blow stuff up. The previous story was about a Battletech fan who built a 'Mech (albeit a fake one) in his back yard. If this isn't just an awesome Slashdot engineering project waiting to happen, I don't know what is! PS - If someone has already beat me to it and is already forming the engineering team, count me in!!
Microsoft will NOT be able to convince any computer professional to use this "Palladium" crap for a server. They won't even try.
Just like they were never able to convince any companies to use that crap IIS server, right?
Until we get better trained and more experienced Sys/Network Admins in the work force, MS servers will remain a player in the field.
This may be a kind of radical idea, but how about we not derail ANY trains? Sabotage is sabotage and just because the information is targeted at one specific train doesn't mean it couldn't be applied to a different train. I prefer riding the rails without having to worry if some lunatic figured out how many stacked pennies on the tracks it takes to derail it.