Comment Re:We're heading back to the '80s (Score 1) 113
Speaking as another geeky types with college degrees and bad hair who works on things like this (distributed data storage/high end computing) I'd agree with point 1 & disagree with point two.
There was a revolution to put computing power on the desk, we did it, it's been done, it's time to move on to more interesting things. A century or two ago the commoners knew nothing about medicine leaving everything to the *professionals*. Now adays most of my dept can do CPR, basic first aid, diagnosise of common ailments. This doesn't make them doctors - just as using Office doesn't make people Computer Scientists.
Point 2. Computers are now getting bigger and more mainframe-y The defining point of the mainframes was their fixed location for processing, with requests being sent from essentailly dumb terminals.
The current research interest is in tying high end systems together as a utility Grid like resource where lots of mainframes are tied together to either provide a specific service or to do the job in the quickest time possible. This deviates from the mainframe concept in the eighties in the idea that there is no one central point for the system and that processing, storage etc can be done wherever is easist/cheapest without having to spend money on redundant resources.
Cases to prove my point are: IBMs investment of $4 billion for server farms/grid archietcture for businesses, the dutch governments four location grid, the Uk governments £120 million investment in a National Grid with lots of nice new supercomputers & data storage all linked together, NSFs $53 million investment in a Teraflop+ processing grid shared between SDSC, NSCA & two other sites.
There was a revolution to put computing power on the desk, we did it, it's been done, it's time to move on to more interesting things. A century or two ago the commoners knew nothing about medicine leaving everything to the *professionals*. Now adays most of my dept can do CPR, basic first aid, diagnosise of common ailments. This doesn't make them doctors - just as using Office doesn't make people Computer Scientists.
Point 2. Computers are now getting bigger and more mainframe-y The defining point of the mainframes was their fixed location for processing, with requests being sent from essentailly dumb terminals.
The current research interest is in tying high end systems together as a utility Grid like resource where lots of mainframes are tied together to either provide a specific service or to do the job in the quickest time possible. This deviates from the mainframe concept in the eighties in the idea that there is no one central point for the system and that processing, storage etc can be done wherever is easist/cheapest without having to spend money on redundant resources.
Cases to prove my point are: IBMs investment of $4 billion for server farms/grid archietcture for businesses, the dutch governments four location grid, the Uk governments £120 million investment in a National Grid with lots of nice new supercomputers & data storage all linked together, NSFs $53 million investment in a Teraflop+ processing grid shared between SDSC, NSCA & two other sites.
