Thread View: alt.folklore.computers
9 messages
9 total messages
Started by Gareths Downstairs Computer
Wed, 20 Jun 2018 16:48
Which are the dinosaurs, the computers or the computerists?
Author: Gareths Downstairs Computer
Date: Wed, 20 Jun 2018 16:48
Date: Wed, 20 Jun 2018 16:48
21 lines
2442 bytes
2442 bytes
Having cut my teeth on the DEC computers (PDP8/E used as the basis of many aspects of 3rd year electronics at Essex Uni in 1972 and then 10 years as an assembly language programmer on PDP11s in real-time embedded applications), that basic understanding of fundamental instruction set operation has stood me in good stead for nearly 50 years, but times change. Although the essence of programs remains, as it always will, in such instructions operating on a user's data, what has developed around it in the areas of cacheing, pipelining and parallel execution has never really figured in my program designs, although much appreciated in the speed of computation that was on offer. Today, I became aware of the Microsoft E2 EDGE development making me feel as though I could be the prototypical Rip Van Winkle in the world of computing; a dinosaur from yesteryear to accompany the PDP8 that wsa in the Brit Science Museum as long ago as 1999! :-)
Re: Which are the dinosaurs, the computers or the computerists?
Author: Dan Espen
Date: Thu, 21 Jun 2018 13:36
Date: Thu, 21 Jun 2018 13:36
44 lines
3063 bytes
3063 bytes
Gareth's Downstairs Computer <headstone255.but.n...@yahoo.com> writes: > Having cut my teeth on the DEC computers (PDP8/E used as > the basis of many aspects of 3rd year electronics at > Essex Uni in 1972 and then 10 years as an assembly > language programmer on PDP11s in real-time embedded > applications), that basic understanding of fundamental > instruction set operation has stood me in good stead > for nearly 50 years, but times change. > > Although the essence of programs remains, as it > always will, in such instructions operating on > a user's data, what has developed around it in the > areas of cacheing, pipelining and parallel execution > has never really figured in my program designs, although > much appreciated in the speed of computation that was on > offer. > > Today, I became aware of the Microsoft E2 EDGE development > making me feel as though I could be the prototypical > Rip Van Winkle in the world of computing; a dinosaur > from yesteryear to accompany the PDP8 that wsa in the > Brit Science Museum as long ago as 1999! :-) This is one of those cases where links would help: https://web.archive.org/web/20160428161757/http://research.microsoft.com:80/en-us/projects/e2 (deleted page from Microsoft Research’s website) Referring article here: https://fossbytes.com/microsoft-linux-windows-10-e2-edge-cpu/ Microsoft has called E2 “a research project, and there are currently no plans to productize it.” Not sure this will help. I tihnk Z/Architecture has a few instructions along these lines. I don't believe they are actually in use anywhere. -- Dan Espen
Re: Which are the dinosaurs, the computers or the computerists?
Author: d... Dennis Boone
Date: Thu, 21 Jun 2018 14:11
Date: Thu, 21 Jun 2018 14:11
8 lines
1941 bytes
1941 bytes
> https://fossbytes.com/microsoft-linux-windows-10-e2-edge-cpu/ > Microsoft has called E2 ?a research project, and there are currently > no plans to productize it.? This sounds like The Return of the Son of VLIW. De
Re: Which are the dinosaurs, the computers or the computerists?
Author: Gareths Downstairs Computer
Date: Thu, 21 Jun 2018 14:25
Date: Thu, 21 Jun 2018 14:25
47 lines
3476 bytes
3476 bytes
On 21/06/2018 14:36, Dan Espen wrote: > Gareth's Downstairs Computer > <headstone255.but.n...@yahoo.com> writes: > >> Having cut my teeth on the DEC computers (PDP8/E used as >> the basis of many aspects of 3rd year electronics at >> Essex Uni in 1972 and then 10 years as an assembly >> language programmer on PDP11s in real-time embedded >> applications), that basic understanding of fundamental >> instruction set operation has stood me in good stead >> for nearly 50 years, but times change. >> >> Although the essence of programs remains, as it >> always will, in such instructions operating on >> a user's data, what has developed around it in the >> areas of cacheing, pipelining and parallel execution >> has never really figured in my program designs, although >> much appreciated in the speed of computation that was on >> offer. >> >> Today, I became aware of the Microsoft E2 EDGE development >> making me feel as though I could be the prototypical >> Rip Van Winkle in the world of computing; a dinosaur >> from yesteryear to accompany the PDP8 that wsa in the >> Brit Science Museum as long ago as 1999! :-) > > This is one of those cases where links would help: > > https://web.archive.org/web/20160428161757/http://research.microsoft.com:80/en-us/projects/e2 > > (deleted page from Microsoft Research’s website) > > Referring article here: > > https://fossbytes.com/microsoft-linux-windows-10-e2-edge-cpu/ > > Microsoft has called E2 “a research project, and there are currently > no plans to productize it.” > > Not sure this will help. I tihnk Z/Architecture has a few instructions > along these lines. I don't believe they are actually in use > anywhere. > Thanks, can't recall the original sighting but have since been through both of those pages. Must we fear the day when Microsoft comes to own the web archive?
Re: Which are the dinosaurs, the computers or the computerists?
Author: Gareths Downstairs Computer
Date: Thu, 21 Jun 2018 14:27
Date: Thu, 21 Jun 2018 14:27
12 lines
2226 bytes
2226 bytes
On 21/06/2018 15:11, Dennis Boone wrote: > > https://fossbytes.com/microsoft-linux-windows-10-e2-edge-cpu/ > > > Microsoft has called E2 ?a research project, and there are currently > > no plans to productize it.? > > This sounds like The Return of the Son of VLIW. AIUI, the essence of E2/EDGE is that the scheduling is done intelligently by the computer, whereas with VLIW it is done by the compiler, the latter being unable to deal with performance issues caused by programs dynamic behaviours and loadings.
Re: Which are the dinosaurs, the computers or the computerists?
Author: Scott Lurndal
Date: Thu, 21 Jun 2018 15:18
Date: Thu, 21 Jun 2018 15:18
9 lines
1944 bytes
1944 bytes
d...@ihatespam.msu.edu (Dennis Boone) writes: > > https://fossbytes.com/microsoft-linux-windows-10-e2-edge-cpu/ > > > Microsoft has called E2 ?a research project, and there are currently > > no plans to productize it.? > >This sounds like The Return of the Son of VLIW. With a touch of a 'data-flow' architectural bent.
Re: Which are the dinosaurs, the computers or the computerists?
Author: Gareths Downstairs Computer
Date: Thu, 21 Jun 2018 16:38
Date: Thu, 21 Jun 2018 16:38
14 lines
2159 bytes
2159 bytes
On 21/06/2018 16:18, Scott Lurndal wrote: > d...@ihatespam.msu.edu (Dennis Boone) writes: >>> https://fossbytes.com/microsoft-linux-windows-10-e2-edge-cpu/ >> >>> Microsoft has called E2 ?a research project, and there are currently >>> no plans to productize it.? >> >> This sounds like The Return of the Son of VLIW. > > With a touch of a 'data-flow' architectural bent. > At a much much slower speed, the joy of playing with LabView!
Re: Which are the dinosaurs, the computers or the computerists?
Author: Charlie Gibbs
Date: Thu, 21 Jun 2018 19:24
Date: Thu, 21 Jun 2018 19:24
12 lines
1974 bytes
1974 bytes
On 2018-06-21, Gareth's Downstairs Computer <headstone255.but.n...@yahoo.com> wrote: > Must we fear the day when Microsoft comes to own the web archive? Paging Winston Smith... we have a job opportunity for you... -- /~\ cgibbs@kltpzyxm.invalid (Charlie Gibbs) \ / I'm really at ac.dekanfrus if you read it the right way. X Top-posted messages will probably be ignored. See RFC1855. / \ Fight low-contrast text in web pages! http://contrastrebellion.com
Re: Which are the dinosaurs, the computers or the computerists?
Author: Sarr Blumson
Date: Thu, 21 Jun 2018 20:18
Date: Thu, 21 Jun 2018 20:18
21 lines
2212 bytes
2212 bytes
Gareth's Downstairs Computer <headstone255.but.n ot.these....@yahoo.com> Wrote in >> This sounds like The Return of the Son of VLIW. > > AIUI, the essence of E2/EDGE is that the scheduling is done > intelligently by the computer, whereas with VLIW it is done > by the compiler, the latter being unable to deal with performance > issues caused by programs dynamic behaviours and loadings. The identification of blocks that can be executed independently is done by hardware? Wow! Bottom line: having a clue what the hardware actually does will always be useful for understanding why things fail. -- ----Android NewsGroup Reader---- http://usenet.sinaapp.com/
Thread Navigation
This is a paginated view of messages in the thread with full content displayed inline.
Messages are displayed in chronological order, with the original post highlighted in green.
Use pagination controls to navigate through all messages in large threads.
Back to All Threads