Related articles |
---|
Register Allocation and Aliasing aglew@oberon.crhc.uiuc.edu (1990-07-05) |
Re: Register Allocation and Aliasing rfg@ncd.com (1990-07-06) |
Re: Register Allocation and Aliasing preston@rice.edu (Preston Briggs) (1990-07-14) |
Re: Register Allocation and Aliasing pur-ee!hankd@dynamo.ecn.purdue.edu (1990-07-14) |
Re: Register Allocation and Aliasing torbenm@diku.dk (1990-07-14) |
Re: Register Allocation and Aliasing mike@vlsivie.at (1990-07-15) |
Re: Register Allocation and Aliasing aglew@dwarfs.crhc.uiuc.edu (1990-07-16) |
Re: Register Allocation and Aliasing phorgan@cup.portal.com (Patrick Horgan) (1990-07-17) |
Re: Register Allocation and Aliasing heggy@cs.pitt.edu (1990-07-17) |
Re: Register Allocation and Aliasing aglew@oberon.crhc.uiuc.edu (1990-07-17) |
Re: Register Allocation and Aliasing lupine!rfg@uunet.UU.NET (1990-07-19) |
Re: Register Allocation and Aliasing lupine!rfg@uunet.UU.NET (1990-07-19) |
Re: Register Allocation and Aliasing vestal@src.honeywell.com (1990-07-19) |
Newsgroups: | comp.arch,comp.compilers |
From: | aglew@dwarfs.crhc.uiuc.edu (Andy Glew) |
In-Reply-To: | mike@vlsivie.at's message of 15 Jul 90 20:56:06 GMT |
Followup-To: | comp.arch,comp.compilers |
Keywords: | optimize, code |
Organization: | University of Illinois, Computer Systems Group |
References: | <1990Jul06.194618.4957@esegue.segue.boston.ma.us> <1990Jul15.205606.19343@esegue.segue.boston.ma.us> |
Date: | Mon, 16 Jul 90 15:05:53 GMT |
>IT EVEN HAS A NAME: it's called ``cache memory''. Access times are short
>and if integrated on the chip can be as fast as a register access.
As I am sure Mr. Gschwind knows, cache implemented on-chip is not as
fast as register access, chiefly because cache is seldom multiported,
as well as for other reasons such as loading, and the number of
addresses that can be specified in an instruction.
If you will, we are talking about the space formed by the
cross-product of the following parameters:
ADDRESSING = by memory address and/or by register number
MULTIPORTING = 1r/w .. 2r/1w ...
SIZE/SPEED = large/slow .. small/fast
The standard configurations are
CACHE = addressed by memory address (associatively)
single-ported
large/slow (at least wrt. registers)
REGISTER = addressed by number
multiported
small/fast
What I was asking about, and what Hank Dietz et al, and others, have
explored, is whether there are other configurations between these two
extremes that might be useful.
--
Andy Glew, aglew@uiuc.edu
--
Return to the
comp.compilers page.
Search the
comp.compilers archives again.