Forgot your password?
Cyhist Jan 24 1997 A
Document Actions
Date: Fri, 24 Jan 1997 02:34:17 EST
Reply-To: "CYHIST Community Memory: Discussion list on the History of
Cyberspace" <CYHIST@SJUVM.STJOHNS.EDU>
Sender: "CYHIST Community Memory: Discussion list on the History of
Cyberspace" <CYHIST@SJUVM.STJOHNS.EDU>
From: "Peter G. Capek" <capek@watson.ibm.com>
Subject: Emulation
______________________________________________________________________
Community Memory: Discussion List on the History of Cyberspace ______________________________________________________________________
I'm a bit surprised at some of the comments about the invention of emulation which have been made here recently. The IBM System/360 line was one of the most well known, if not one of the first, uses of emulation in a commercial system: different models of System/360 emulated various of the earlier IBM systems, and I believe that in at least one case a later version of 360 emulated a competitive machine. All but one of the originally announced models of System/360 (30, 40, 50, 60; the model 70 wasn't) were in fact microcoded and included emulators for other architectures. For example, the model 30 could emulate the 1401 (and perhaps other machines), and the model 60 (later named the model 65 with slight modifications) could emulate the 7090/94.
However, at least in IBM, the story is much older than that. There were emulators for Stretch on earlier machines, although due to memory constraints, I doubt they were very useful for any serious work. Someone commented on a modification to ENIAC which effectively caused it to emulate a different architecture to make it easier to program. I believe the place where this is described, albeit briefly, is in Goldstine's The Computer From Pascal to Von Neumann. This is one of the earliest pieces of work that I know of which intentionally trades off performance for ease of programming.
Peter Capek
______________________________________________________________________
Reply-To: "CYHIST Community Memory: Discussion list on the History of
Cyberspace" <CYHIST@SJUVM.STJOHNS.EDU>
Sender: "CYHIST Community Memory: Discussion list on the History of
Cyberspace" <CYHIST@SJUVM.STJOHNS.EDU>
From: "Peter G. Capek" <capek@watson.ibm.com>
Subject: Emulation
______________________________________________________________________
Community Memory: Discussion List on the History of Cyberspace ______________________________________________________________________
I'm a bit surprised at some of the comments about the invention of emulation which have been made here recently. The IBM System/360 line was one of the most well known, if not one of the first, uses of emulation in a commercial system: different models of System/360 emulated various of the earlier IBM systems, and I believe that in at least one case a later version of 360 emulated a competitive machine. All but one of the originally announced models of System/360 (30, 40, 50, 60; the model 70 wasn't) were in fact microcoded and included emulators for other architectures. For example, the model 30 could emulate the 1401 (and perhaps other machines), and the model 60 (later named the model 65 with slight modifications) could emulate the 7090/94.
However, at least in IBM, the story is much older than that. There were emulators for Stretch on earlier machines, although due to memory constraints, I doubt they were very useful for any serious work. Someone commented on a modification to ENIAC which effectively caused it to emulate a different architecture to make it easier to program. I believe the place where this is described, albeit briefly, is in Goldstine's The Computer From Pascal to Von Neumann. This is one of the earliest pieces of work that I know of which intentionally trades off performance for ease of programming.
Peter Capek
______________________________________________________________________
