Re: Compile HLL to microcode on VLIW - possible?

Scott A. Berg <sberg@camtronics.com> wrote:
>[Is it possible to compile HLL to microcode?]


Yes, see, e.g. [Ebeling 76].


>[These consecutive lines of code don't share and can overlap
> was never taken to the microcode level.]


To the contrary, this was a general area of interest in the 70's, and
continues in the VLSI community for hardware/software cosynthesis,
where they are trying to build a processor around the needs of a
particular application and thus get to choose the machine language to
match the problem at hand.


>[Microcode is embedded in a PROM, but could be in RAM.]


Many older machines put at least some part of the microcode in RAM;
various proposed and a few constructed machines even had caching
and/or virtual memory for the microcode. However, using RAM instead
of ROM tends to increase various costs (both time and money). The
space of tradeoffs is quite large!


>[Does anybody use hardwired logic, or do all use microcode?]


Many desktop computer processors use hardwired logic; arguably, even
machines such as the Intel P6 are straying away from microcode (as I
recall, P96 uses microcode for infrequent operations, hardwired logic
otherwise).


;-D on ( Micro-optimization ) Pardo


Here's some references:


%A John Bayko
%T Great Microprocessors of the Past and Present
%R Version 5.3.1 Available as of September 1995 from
\fChttp://www.cs.uregina.ca:80/~bayko/cpu.html\fP.
%W bayko@cs.uregina.ca
%X Describes Rekusiv; summarizes book.


%A Burd
%T Great Microprocessors of the Past and Present
%R http://infopad.eecs.berkeley.edu/~burd/gpp/archive/cpu_history.html
%X See `Rekursiv' O-O processor w/ writable instruction set.
Instruction set constructed on the fly, can change for different
objects.


%A David R. Ditzel
%A Hubert R. McLellan
%T Branch Folding in the CRISP Microprocessor: Reducing Branch Delay
to Zero
%J Proceedings of the 14th Annual International Symposium on Computer
Architecture; Computer Architecture News
%V 15
%N 2
%D June 1987
%P 2-9


%A David R. Ditzel
%A Hubert R. McLellan
%A Alan D. Berenbaum
%T The Hardware Architecture of the CRISP Microprocessor
%J Proceedings of the 14th Annual International Symposium on Computer
Architecture; Computer Architecture News
%V 15
%N 2
%D June 1987
%P 309-319


%A David R. Ditzel
%A Hubert R. McLellan
%A Alan D. Berenbaum
%T Design Tradeoffs to Support the C Programming Language in the CRISP
Microprocessor
%J Proceedings of the Second International Symposium on Architectural
Support for Programming Languages and Operating Systems (ASPLOS II)
%D 5-8 October 1987
%P 158-163


%A Carl Ebeling
%T A User-oriented Microprogramming Support System
%R Master's Thesis
%I Department of Computers Science, Southern Illinois University
%D December 1976


%A M. J. Flynn
%A C. Neuhauser
%T EMMY -- An Emulation System for User Microprogramming
%J National Computer Conference
%D 1975
%P 85-89


%A Steven Geyer
%A Anthony Lee
%T Development Tools for User Microprogramming
%J Micro 14
%D 1981


%A A Hassitt
%A L. E. Lyon
%T An APL Emulator on System/370
%J IBM Systems Journal
%N 4
%D 1976
%P 358-379


%A E. W. Reigel
%A U. Faber
%A D. A. Fisher
%T The Interpreter \- A Microprogrammable Building Block System
%J Spring Joint Computer Conference
%D 1972
%P 705-723


%A Anthony D. Robbi
%T Microcache: A Buffer Memory for Microprograms
%J CompCon 1972 Digest of Papers
%D September 1972
%P 123-125


%A J. Eric Roskos
%A Robert I. Winner
%T Toward User Sharing of the Microprogramming Level Under Unix on the
Perkin-Elmer 3220
%J IEEE Micro-14
%D 1981
%P 67-73


%A Maurice V. Wilkes
%T The Growth of Interest in Microprogramming: A Literature Survey
%J Computing Surveys
%V 1
%N 3
%D September 1969
%P 62-65


%A W. T. Wilner
%T Design of the Burroughs B1700
%J Fall Joint Compuer Conference
%D 1972
%P 489-497
--

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