http://www.ece.uiuc.edu/ece291/mp/mp4/ablit.html should give you a decent idea of what Alpha Blending can do, why you would want to use it, and how you might go about coding it (using MMX even!:)
The similarities are remarkable. A more-advanced better compression takes on an established older, poorer one.
My prediction: OV will be used but will not be mainstream, much like BZ2... and music available in OV will also be available in MP3 (that's not really a suprise, is it?:)
but a breakthrough nonetheless. 48 MB/cm^2.. but 10 GB/cm^2 possible. Desktop units by 2003. Looks like IBM is breaking down the doors of high storage yet again. Their 45-75 GB drives are impressive, but this? Wow. Access rates look pretty nice long-term too.. "a gigabit-per-second data rate appears reasonable for holographic storage".
Non-moving heads were abandoned a long time ago, for a very good reason: track density. Most hard drives today pack 10,000 tracks or more per inch. It is physically impossible to build read heads that small or in that kind of density.
Multiple heads per platter? (eg, 4 or 5 moveable heads). A good idea, but probably the engineering of such a beast is cost-prohibitive.
back in October 1997. It is available online (costs $$ to actually get the article).
One of the things that always seems to me to be a major roadblock for the widespread use of electric/flywheel/non-combustion engines in cars is the heat problem. Not a case of having too much heat, but not enough. How are you going to heat your car efficently in the winter? Combustion-based cars, of course, just route air by the engine to heat it.. but heating coils and the like draw way too much power for use in electric vehicles.
The README for the Linux/ia64 Developer's Release on Cygnus' ftp site (which incidentally is what RedHat's site links to), has some very interesting tidbits:
The entire GNU toolchain has been extended to support IA-64 (this includes binutils, gcc, and gdb).
The compiler generates working code, but does not generated optimized code for the Itanium processor yet. It has some basic optimizations, but no "interesting" optimizations yet.
Binutils is mostly functional, with the exception of shared library support and a few other things.
Gdb has only partial functionality--basic commands work, but most advanced commands are not working.
Speaking as a computer engineer, the IA-64 is one of the few processors that feels truly designed from the ground up.
As such, one of the things Intel did very right was avoiding the craziness when switching between IA-32 and IA-64 code. It looks VERY straightforward: a new instruction in the IA-32 instruction set that jumps to IA-64 code and an IA-64 instruction that jumps to IA-32 code. The IA-32 registers are mapped into the lowest 32 registers on the IA-64 side. This is very much unlike the (IMO) stupid way Intel did protected mode/real mode switching in the IA-32 instruction set, which is complex and downright nasty at times.
As to the other features of the processor (the 128 GP integer registers set up in a processor-managed rotating stack, the 128 FP registers, the 3 different sub-instruction-sets that allow the processor to be seperated into modular pieces, predication, and explicit parallelism), they are shockingly well-designed and make sense from both an engineering and programming viewpoint. I am very much looking forward to running on one!
The crux of the matter is that IA-32 applications should run with no modifications under a properly written IA-64 OS and it should even be possible to run a IA-32 OS with no problems on an IA-64 processor!
Why not implement a bandwidth cap that only is applied to traffic going OUT onto the internet from the dorms? And inside the dorms, have 100 Mb switched ethernet.
At the University of Illinois, Urbana-Champaign, each dorm port (serving 2 computers) has a maximum bandwidth usage of 500 MB/day. That isn't so bad except that the network admins will switch off your port the next day if you go over that limit, and the limit applies to traffic going ANYWHERE, including to the room next door! Also, there is no way to tell how far you are into that 500 megs.
Frankly, the top reason why most people have gone over (and I know at least 30 people who have been shut off), is not something like Napster--it's sending a few hundred megs down the hall to burn a CD (or someone downloading a gig worth of stuff from their local network Windows file share). And the other common reason is that the school gives out hubs to people with multiple computers, so even traffic inside the room gets counted in that 500 Mb/day limit!
Most students hate this policy, especially engineers who have 2-3 computers in their room. The main reason seems to be that people are getting their ports shut off by the overly strict enforcement of a bandwidth policy (send 501 megs, and your port is off the next day) which is undoubtably intended to catch people running giant public warez servers.
I believe that the network admins would have far fewer headaches and the students would be far happier if only outgoing traffic to the internet was limited (and it could even be a stricter limit than 500 MB/day), as this is the major cost to the university--internal bandwidth is basically free once the lines are installed.
Slashdot Mirror
http://www.ece.uiuc.edu/ece291/mp/mp4/ablit.html should give you a decent idea of what Alpha Blending can do, why you would want to use it, and how you might go about coding it (using MMX even! :)
The similarities are remarkable. A more-advanced better compression takes on an established older, poorer one.
:)
My prediction: OV will be used but will not be mainstream, much like BZ2... and music available in OV will also be available in MP3 (that's not really a suprise, is it?
but a breakthrough nonetheless. 48 MB/cm^2.. but 10 GB/cm^2 possible. Desktop units by 2003.
Looks like IBM is breaking down the doors of high storage yet again. Their 45-75 GB drives are impressive, but this? Wow.
Access rates look pretty nice long-term too.. "a gigabit-per-second data rate appears reasonable for holographic storage".
Non-moving heads were abandoned a long time ago, for a very good reason: track density. Most hard drives today pack 10,000 tracks or more per inch. It is physically impossible to build read heads that small or in that kind of density.
Multiple heads per platter? (eg, 4 or 5 moveable heads). A good idea, but probably the engineering of such a beast is cost-prohibitive.
back in October 1997. It is available online (costs $$ to actually get the article).
One of the things that always seems to me to be a major roadblock for the widespread use of electric/flywheel/non-combustion engines in cars is the heat problem. Not a case of having too much heat, but not enough. How are you going to heat your car efficently in the winter? Combustion-based cars, of course, just route air by the engine to heat it.. but heating coils and the like draw way too much power for use in electric vehicles.
The entire GNU toolchain has been extended to support IA-64 (this includes binutils, gcc, and gdb).
The compiler generates working code, but does not generated optimized code for the Itanium processor yet. It has some basic optimizations, but no "interesting" optimizations yet.
Binutils is mostly functional, with the exception of shared library support and a few other things.
Gdb has only partial functionality--basic commands work, but most advanced commands are not working.
Speaking as a computer engineer, the IA-64 is one of the few processors that feels truly designed from the ground up.
As such, one of the things Intel did very right was avoiding the craziness when switching between IA-32 and IA-64 code. It looks VERY straightforward: a new instruction in the IA-32 instruction set that jumps to IA-64 code and an IA-64 instruction that jumps to IA-32 code. The IA-32 registers are mapped into the lowest 32 registers on the IA-64 side. This is very much unlike the (IMO) stupid way Intel did protected mode/real mode switching in the IA-32 instruction set, which is complex and downright nasty at times.
As to the other features of the processor (the 128 GP integer registers set up in a processor-managed rotating stack, the 128 FP registers, the 3 different sub-instruction-sets that allow the processor to be seperated into modular pieces, predication, and explicit parallelism), they are shockingly well-designed and make sense from both an engineering and programming viewpoint. I am very much looking forward to running on one!
The crux of the matter is that IA-32 applications should run with no modifications under a properly written IA-64 OS and it should even be possible to run a IA-32 OS with no problems on an IA-64 processor!
I've got it working under FreeBSD 3.x via a kernel patch.
Do a Deja search for "Promise" in comp.unix.bsd.freebsd.misc.
Also, it will be fully supported via the new ATA driver in 4.0.
Why not implement a bandwidth cap that only is applied to traffic going OUT onto the internet from the dorms? And inside the dorms, have 100 Mb switched ethernet.
At the University of Illinois, Urbana-Champaign, each dorm port (serving 2 computers) has a maximum bandwidth usage of 500 MB/day. That isn't so bad except that the network admins will switch off your port the next day if you go over that limit, and the limit applies to traffic going ANYWHERE, including to the room next door! Also, there is no way to tell how far you are into that 500 megs.
Frankly, the top reason why most people have gone over (and I know at least 30 people who have been shut off), is not something like Napster--it's sending a few hundred megs down the hall to burn a CD (or someone downloading a gig worth of stuff from their local network Windows file share). And the other common reason is that the school gives out hubs to people with multiple computers, so even traffic inside the room gets counted in that 500 Mb/day limit!
Most students hate this policy, especially engineers who have 2-3 computers in their room. The main reason seems to be that people are getting their ports shut off by the overly strict enforcement of a bandwidth policy (send 501 megs, and your port is off the next day) which is undoubtably intended to catch people running giant public warez servers.
I believe that the network admins would have far fewer headaches and the students would be far happier if only outgoing traffic to the internet was limited (and it could even be a stricter limit than 500 MB/day), as this is the major cost to the university--internal bandwidth is basically free once the lines are installed.