Re: Optimizing stack access for a stack based VM

Hans-Peter Diettrich <DrDiettrich1@aol.com>
Thu, 13 Sep 2007 22:45:45 +0200

          From comp.compilers
Related articles
Optimizing stack access for a stack based VM jirik.svoboda@seznam.cz (Jiri Svoboda) (2007-09-11)
Re: Optimizing stack access for a stack based VM DrDiettrich1@aol.com (Hans-Peter Diettrich) (2007-09-13)
Re: Optimizing stack access for a stack based VM blog@rivadpm.com (Alex McDonald) (2007-09-13)
Re: Optimizing stack access for a stack based VM lkrupp@pssw.com (Louis Krupp) (2007-09-13)
Re: Optimizing stack access for a stack based VM DrDiettrich1@aol.com (Hans-Peter Diettrich) (2007-09-13)
Re: Optimizing stack access for a stack based VM DrDiettrich1@aol.com (Hans-Peter Diettrich) (2007-09-13)
Re: Optimizing stack access for a stack based VM jvorbrueggen@not-mediasec.de (=?ISO-8859-1?Q?Jan_Vorbr=FCggen?=) (2007-09-14)
Re: Optimizing stack access for a stack based VM blog@rivadpm.com (Alex McDonald) (2007-09-14)
Re: Optimizing stack access for a stack based VM kenney@cix.compulink.co.uk (2007-09-14)
Re: Optimizing stack access for a stack based VM jeffrey.kenton@comcast.net (Jeff Kenton) (2007-09-16)
Re: Optimizing stack access for a stack based VM dot@dotat.at (Tony Finch) (2007-09-16)
Re: Optimizing stack access for a stack based VM anton@mips.complang.tuwien.ac.at (2007-10-01)
| List of all articles for this month |
From: Hans-Peter Diettrich <DrDiettrich1@aol.com>
Newsgroups: comp.compilers
Date: Thu, 13 Sep 2007 22:45:45 +0200
Organization: Compilers Central
References: 07-09-030 07-09-043
Keywords: storage, optimize, comment
Posted-Date: 13 Sep 2007 22:54:34 EDT

Louis Krupp wrote:


> I do know that the earlier machines in this series (Burroughs B6700)
> kept the top two words of the stack (and their double precision
> extensions) in registers and the rest of the stack in memory. Later
> machines cached the top n words of the stack, which made stack access
> faster.


AFAIR a 16 bit TI microprocessor also used the top 16 entries on the
stack as registers. Perhaps this architecture reflected the Burroughs
machine?


DoDi
[That seems to be pretty typical. The HP3000 kept the top several elements
of the stack in registers as well. -John]

Post a followup to this message

Return to the comp.compilers page.
Search the comp.compilers archives again.