d0p1/ack
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

fixup commit for tag 'oct-1'

Browse source
This commit is contained in:
cvs2hg 1994-12-06 09:12:22 +00:00
parent 7393f8923c
commit dc2a339e09
8241 changed files with 0 additions and 694108 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
.distr
View file

@ -1,21 +0,0 @@
Action
Copyright
NEW
README
TakeAction
bin
doc
emtest
etc
fast
fcc
first
h
include
modules
lang
lib
mach
man
util
Versions

276
Action
View file

@ -1,276 +0,0 @@
name "System definition"
dir first
action ack_sys
failure "You have to run the shell script first/first"
fatal
end
name "Manual pages"
dir man
end
! name "EM definition"
! dir etc
! end
name "EM definition library"
dir util/data
end
name "C utilities"
dir util/cmisc
end
name "Yacc parser generator"
dir util/byacc
end
name "Flex lexical analyzer generator"
dir util/flex
action "make firstinstall && make clean"
end
name "Include files for modules"
dir modules/h
end
name "Modules"
dir modules/src
indir
end
name "LL(1) Parser generator"
dir util/LLgen
action "make firstinstall && make clean"
end
name "C preprocessor"
dir util/cpp
end
name "Peephole optimizer libraries"
dir modules/src/em_opt
end
name "ACK object utilities"
dir util/amisc
end
name "Encode/Decode"
dir util/misc
end
name "Shell files in bin"
dir util/shf
end
name "EM assembler"
dir util/ass
end
name "EM Peephole optimizer"
dir util/opt
end
name "EM Global optimizer"
dir util/ego
indir
end
name "ACK archiver"
dir util/arch
end
name "Program 'ack'"
dir util/ack
end
name "Bootstrap for backend tables"
dir util/cgg
end
name "Bootstrap for newest form of backend tables"
dir util/ncgg
end
name "Bootstrap for code expanders"
dir util/ceg
indir
end
name "LED link editor"
dir util/led
end
name "TOPGEN target optimizer generator"
dir util/topgen
end
name "C frontend"
dir lang/cem/cemcom
end
name "ANSI-C frontend"
dir lang/cem/cemcom.ansi
end
name "ANSI-C preprocessor"
dir lang/cem/cpp.ansi
end
name "ANSI-C header files"
dir lang/cem/libcc.ansi
end
name "LINT C program checker"
dir lang/cem/lint
end
name "EM definition lint-library"
action "make lintlib"
dir util/data
end
name "Modules lint libraries"
dir modules/src
indir "Action.lint"
end
name "Global optimizer lint libraries"
dir util/ego/share
action "make lintlib"
end
name "Pascal frontend"
dir lang/pc/comp
end
name "Basic frontend"
dir lang/basic/src
end
name "Occam frontend"
dir lang/occam/comp
end
name "Modula-2 frontend"
dir lang/m2/comp
end
name "Modula-2 definition modules"
dir lang/m2/libm2
end
name "Modula-2 makefile generator"
dir lang/m2/m2mm
end
name "Fortran to C compiler"
dir lang/fortran/comp
end
name "EM interpreter in C"
dir util/int
end
name "Symbolic debugger"
dir util/grind
end
name "Intel 8086 support"
dir mach/i86
indir
end
name "Intel 80286 support for Xenix"
dir mach/xenix3
indir
end
name "Intel 80386 support for Xenix 386 System V"
dir mach/i386
indir
end
name "MSC6500 support"
dir mach/6500
indir
end
name "Motorola 6800 support"
dir mach/6800
indir
end
name "Motorola 6805 support"
dir mach/6805
indir
end
name "Motorola 6809 support"
dir mach/6809
indir
end
name "Intel 8080 support"
dir mach/i80
indir
end
name "2-2 Interpreter support"
dir mach/em22
indir
end
name "2-4 Interpreter support"
dir mach/em24
indir
end
name "4-4 Interpreter support"
dir mach/em44
indir
end
name "Motorola 68000 2-4 support"
dir mach/m68k2
indir
end
name "Motorola 68000 4-4 support"
dir mach/m68k4
indir
end
name "NS16032 support"
dir mach/ns
indir
end
name "PDP 11 support"
dir mach/pdp
indir
end
name "PMDS support"
dir mach/pmds
indir
end
name "PMDS 4/4 support"
dir mach/pmds4
indir
end
name "Signetics 2650 support"
dir mach/s2650
indir
end
name "Vax 4-4 support"
dir mach/vax4
indir
end
name "M68020 System V/68 support"
dir mach/m68020
indir
end
name "Sun 3 M68020 support"
dir mach/sun3
indir
end
name "Sun 4 SPARC SunOs 4 support"
dir mach/sparc
system "sparc|sparc_solaris"
indir
end
name "Sun 4 SPARC Solaris support"
dir mach/sparc_solaris
system "sparc_solaris"
indir
end
name "Sun 2 M68000 support"
dir mach/sun2
indir
end
name "Mantra M68000 System V.0 support"
dir mach/mantra
indir
end
name "PC Minix support"
dir mach/minix
indir
end
name "Atari ST Minix support"
dir mach/minixST
indir
end
name "Z80 support"
dir mach/z80
indir
end
name "Zilog Z8000 support"
dir mach/z8000
indir
end
name "Acorn Archimedes support"
dir mach/arm
indir
end
name "Documentation"
dir doc
end
name "Motorola 68000 interpreters"
system "m68*|sun*"
dir mach/mantra/int
end
name "Fast compilers"
system "m68020|sun3|i386|vax*"
dir fast
indir
end
name "Fast cc-compatible C compiler"
system "sun3|vax*"
dir fcc
indir
end

17
Copyright
View file

@ -1,17 +0,0 @@
/*
* A M S T E R D A M C O M P I L E R K I T
*
* Copyright (c) 1987, 1991, 1993 by the Vrije Universiteit, Amsterdam,
* The Netherlands.
*
* Permission to use, sell, duplicate or disclose this software must be
* obtained in writing. Requests for such permissions may be sent to
*
* Dr. Andrew S. Tanenbaum
* Wiskundig Seminarium
* Vrije Universiteit
* De Boelelaan 1081a
* 1081 HV Amsterdam
* The Netherlands
*
*/

3
DistrAction
View file

@ -1,3 +0,0 @@
p=/proj/em/Work
sh TakeAction 'make distr' $p/distr/Action
sh TakeAction 'make distr' $p/distr/Action1

35
Makefile
View file

@ -1,35 +0,0 @@
cmp: # compile everything and compare
(cd etc ; make cmp )
(cd util ; make cmp )
(cd lang ; make cmp )
(cd mach ; make cmp )
install: # compile everything to machine code
(cd etc ; make install )
(cd util ; make install )
(cd lang/cem ; make install )
(cd mach ; make install )
(cd lang/pc ; make install )
clean: # remove all non-sources, except boot-files
(cd doc ; make clean )
(cd man ; make clean )
(cd h ; make clean )
(cd etc ; make clean )
(cd util ; make clean )
(cd lang ; make clean )
(cd mach ; make clean )
opr: # print all sources
make pr | opr
pr: # print all sources
@( pr Makefile ; \
(cd doc ; make pr ) ; \
(cd man ; make pr ) ; \
(cd h ; make pr ) ; \
(cd etc ; make pr ) ; \
(cd lang ; make pr ) ; \
(cd util ; make pr ) ; \
(cd mach ; make pr ) \
)

34
NEW
View file

@ -1,34 +0,0 @@
This is ACK distribution 5.2.
The only addition with respect to the 5th ACK distribution is the support
for Solaris 2 on SPARCs. It also contains many bug fixes.
Notes for the 5th ACK distribution:
It is not wise to mix files created by the previous version of the Kit
with files belonging to this version, although that might sometimes work.
Many problems with the previous distribution have been fixed.
The major additions are:
- an ANSI C compiler
- a LINT C program checker, both non-ansi and ansi
- an Intel 80386 back-end
- a SPARC code expander
- a source level debugger for Pascal, Modula-2, C, and ANSI C
- an Acorn Archimedes back-end
- code-expanders for VAX, Intel 80386 and Motorola M68020 processors,
and very fast Pascal, Modula-2, ANSI C, and C compilers constructed
using these code expanders
- a cc-compatible very fast C compiler for SUN-3 and VAX.
Also added, but not part of the Kit proper are
- flex: a lexical analyzer generator
- byacc: yacc-clone by UCB
- f2c: a Fortran to C compiler by AT&T.
See the ACK installation manual for their copyright notices.
--
Ceriel Jacobs, Dept. of Mathematics and Computer Science, Vrije Universiteit,
De Boelelaan 1081a, 1081 HV Amsterdam, The Netherlands
Email: ceriel@cs.vu.nl Fax: +31 20 6427705

2
README
View file

@ -1,2 +0,0 @@
Before starting installation you should read
the file doc/install.pr

144
TakeAction
View file

@ -1,144 +0,0 @@
case $# in
0) PAR='make install && make clean' ; CMD=Action ;;
1) PAR="$1" ; CMD=Action ;;
2) PAR="$1" ; CMD="$2" ;;
*) echo Syntax: "$0" [command [file]] ; exit 1 ;;
esac
if test -r "$CMD"
then :
else
case "$CMD" in
Action) echo No Action file present ;;
*) echo No Action file "($CMD)" present ;;
esac
fi
case $0 in
/*) THISFILE=$0
;;
*) if [ -f $0 ]
then
THISFILE=`pwd`/$0
else
THISFILE=$0
fi
;;
esac
SYS=
RETC=0
{ while read LINE
do
eval set $LINE
case x"$1" in
x!*) ;;
xname) SYS="$2"
ACTION='$PAR'
DIR=.
FM=no
FAIL='Failed for $SYS, see $DIR/Out'
SUCC='$SYS -- done'
ATYPE=
FATAL=no
DOIT=yes
;;
xfatal) FATAL=yes ;;
xaction|xindir) case x$ATYPE in
x) ACTION=$2 ; ATYPE=$1
case $ATYPE$FM in
indirno) FAIL='Failed for $SYS' ;;
esac
;;
*) echo Already specified an $ATYPE for this name
RETC=65 ;;
esac ;;
xfailure) FM=yes
FAIL="$2" ;;
xsuccess) SUCC="$2" ;;
xdir) DIR="$2" ;;
xsystem) PAT="$2"
oIFS=$IFS
IFS="|"
eval set $2
case x`ack_sys` in
x$1|x$2|x$3|x$4|x$5|x$6|x$7) ;;
*) echo "Sorry, $SYS can only be made on $PAT systems"
DOIT=no
;;
esac
IFS=$oIFS
;;
xend) case $DOIT in
no) continue ;;
esac
case x$SYS in
x) echo Missing name line; RETC=65 ;;
*) if test -d $DIR
then (
cd $DIR
X=
case $ATYPE in
indir)
if $THISFILE "$PAR" $ACTION
then eval echo $SUCC
else RETC=2 ; eval echo $FAIL
fi ;;
*)
case "$ACTION" in
'$PAR')
ACTION="$PAR"
;;
*) ;;
esac
if [ -f No$CMD ]
then
x=`cat No$CMD`
if [ "$ACTION" = "$x" ]
then
ACTION='echo "No actions performed, No$CMD file present"'
SUCC='$SYS -- skipped'
fi
fi
if eval "{ $ACTION ; } >Out 2>&1 </dev/null"
then eval echo $SUCC
if [ "$SUCC" = '$SYS -- skipped' ]
then :
else echo "$ACTION" > No$CMD 2>/dev/null
fi
else RETC=1 ; X=: ; eval echo $FAIL
fi
;;
esac
(echo ------- `pwd`
cat Out
$X rm -f Out
) 2>/dev/null 1>&- 1>&3
exit $RETC
)
case $? in
0) ;;
*) case $RETC in
0) RETC=$? ;;
esac ;;
esac
else
echo Directory $DIR for $SYS is inaccessible
RETC=66
fi ;;
esac
case $FATAL$RETC in
yes0) ;;
yes*) echo Fatal error, installation stopped.
exit $RETC ;;
esac
SYS=
;;
*) echo Unknown keyword "$1"
RETC=67 ;;
esac
done
exit $RETC
} <$CMD
RETX=$?
case $RETX in
0) exit $RETC ;;
*) exit $RETX ;;
esac

9
bin/.distr
View file

@ -1,9 +0,0 @@
cc-and-mkdep.ack
cc-and-mkdep.all
cc-and-mkdep.sun
do_deps
do_resolve
lint-lib.ack
lint-lib.unix
mk_manpage
rm_deps

7
bin/cc-and-mkdep.ack
View file

@ -1,7 +0,0 @@
: '$Id$'
: Compile and make dependencies. First argument is the file on which the
: dependencies must be produced. This version is for ACK.
n=$1
shift
exec $CC -Rcem-A$n -Rcem-m $*

20
bin/cc-and-mkdep.all
View file

@ -1,20 +0,0 @@
: '$Id$'
: Compile and make dependencies. First argument is the file on which the
: dependencies must be produced. This version is a generic one that should
: work for all Unix systems.
n=$1
shift
cpp_args=
for i in $*
do
case $i in
-I*|-D*|-U*) cpp_args="$cpp_args $i"
;;
-*) ;;
*) cpp_args="$cpp_args $i"
;;
esac
done
$UTIL_HOME/lib.bin/cpp -d -m $cpp_args > $n
exec $CC $*

7
bin/cc-and-mkdep.sun
View file

@ -1,7 +0,0 @@
: '$Id$'
: Compile and make dependencies. First argument is the file on which the
: dependencies must be produced. This version is for the SUN cc.
n=$1
shift
exec $CC -Qpath $UTIL_HOME/lib.bin -Qoption cpp -d$n -Qoption cpp -m $*

18
bin/do_deps
View file

@ -1,18 +0,0 @@
: '$Id$'
: Produce dependencies for all argument files
for i in $*
do
n=`basename $i .c`
if [ -f $n.dep ]
then
:
else
echo $n.'$(SUF): '$i > $n.dep
echo " head -5 $n.dep > $n.dp1" >> $n.dep
echo ' CC="$(CC)" UTIL_HOME="$(UTIL_HOME)" $(CC_AND_MKDEP) '$n.dp2 '$(CFLAGS)' -c $i >> $n.dep
echo " cat $n.dp1 $n.dp2 > $n.dep" >> $n.dep
echo " rm -f $n.dp1 $n.dp2" >> $n.dep
fi
done

47
bin/do_resolve
View file

@ -1,47 +0,0 @@
: '$Id$'
: Resolve name clashes in the files on the argument list. If these
: files reside in another directory, a copy is made in the current
: directory. If not, it is overwritten. Never do this in a source
: directory! A list of the new files is produced on standard output.
UTIL_BIN=$UTIL_HOME/bin
trap "rm -f tmp$$ a.out nmclash.* longnames clashes" 0 1 2 3 15
: first find out if we have to resolve problems with identifier significance.
cat > nmclash.c <<'EOF'
/* Accepted if many characters of long names are significant */
abcdefghijklmnopr() { }
abcdefghijklmnopq() { }
main() { }
EOF
if $CC nmclash.c
then : no identifier significance problem
for i in $*
do
echo $i
done
else
$UTIL_BIN/prid -l7 $* > longnames
: remove code generating routines from the clashes list.
: code generating routine names start with C_.
: also remove names starting with flt_.
sed '/^C_/d' < longnames | sed '/^flt_/d' > tmp$$
$UTIL_BIN/cclash -c -l7 tmp$$ > clashes
for i in $*
do
$UTIL_BIN/cid -Fclashes < $i > tmp$$
n=`basename $i .xxx`
if cmp -s $n tmp$$
then
rm -f tmp$$
else
mv tmp$$ $n
fi
echo $n
done
fi

1
bin/em.pascal
View file

@ -1 +0,0 @@
exec /usr/em/doc/em/int/em /usr/em/doc/em/int/tables ${1-e.out} core

12
bin/lint-lib.ack
View file

@ -1,12 +0,0 @@
: '$Id$'
: Create a lint library file. The name of the library file is constructed
: from the first argument. The second argument indicates the directory where
: the result is to be placed. This version is for ACK lint.
n=$1
shift
d=$1
shift
lint -L$n $*
mv $n.llb $d

12
bin/lint-lib.unix
View file

@ -1,12 +0,0 @@
: '$Id$'
: Create a lint library file. The name of the library file is constructed
: from the first argument. The second argument indicates the directory where
: the result is to be placed. This version is for Unix lint.
n=$1
shift
d=$1
shift
/usr/bin/lint -C$n $*
mv llib-l$n.ln $d

18
bin/mk_manpage
View file

@ -1,18 +0,0 @@
num=`expr $1 : '.*\.\([1-8]\)'`
if [ -d $2/man ] ; then : ; else mkdir $2/man ; fi
if [ -f $2/man/head ] ; then : ; else cat > $2/man/head <<'EOF'
.rn TH yy
.de TH
.di zz
.yy "\\$1" "\\$2" "\\$3" "\\$4"
.ds ]W 5th ACK distribution
.ds ]D Amsterdam Compiler Kit
.ds ]L "\\$3
.di
.rm zz
..
EOF
fi
if [ -d $2/man/man$num ] ; then : ; else mkdir $2/man/man$num ; fi
cat $2/man/head $1 > $2/man/man$num/`expr //$1 : '.*/\([^/]*\)'`

8
bin/rm_deps
View file

@ -1,8 +0,0 @@
: $Id$
: remove dependencies from a makefile, write result on standard output.
: we cannot do this directly in a makefile because some make versions
: have # start a comment, always.
sed -e '/^#DEPENDENCIES/,$d' $1
echo '#DEPENDENCIES'

3
distr/Action
View file

@ -1,3 +0,0 @@
name "EM tables"
dir etc
end

16
distr/Action1
View file

@ -1,16 +0,0 @@
name "m68k2/cg bootstrap files"
dir mach/m68k2/cg
action "make EMHOME=/proj/em/Work distr"
end
name "vax4/cg bootstrap files"
dir mach/vax4/cg
action "make EMHOME=/proj/em/Work distr"
end
name "m68020/ncg bootstrap files"
dir mach/m68020/ncg
action "make EMHOME=/proj/em/Work distr"
end
name "m68k4/cg bootstrap files"
dir mach/m68k4/cg
action "make EMHOME=/proj/em/Work distr"
end

20
distr/Exceptions
View file

@ -1,20 +0,0 @@
++ ./doc/proto.make made
++ ./doc/int/.distr made
++ ./h/em_mnem.h not present
++ ./h/em_pseu.h not present
++ ./h/em_spec.h not present
++ ./lang/cem/cemcom.ansi/Version.c made
++ ./lang/cem/libcc.ansi/stdlib/malloc.c made
++ ./lang/cem/cemcom/Version.c made
++ ./lang/pc/comp/Version.c made
++ ./lang/m2/comp/Version.c made
++ ./lang/m2/m2mm/Version.c made
++ ./mach/sparc/ce/EM_table made
++ ./mach/sparc_solaris/libem/LIST made
++ ./util/LLgen/src/LLgen.c.dist made
++ ./util/cpp/Version.c made
++ ./util/data/em_flag.c not present
++ ./util/data/em_mnem.c not present
++ ./util/data/em_pseu.c not present
++ ./util/ego/share/pop_push.h made
++ ./util/grind/ops.c made

65
distr/How_To
View file

@ -1,65 +0,0 @@
How to make a fresh distribution:
For a distribution you need ".distr" files and RCS files.
The EM home directory contains a file called ".distr". It contains
the names of all the files and directories you want to have in the distribution.
The directories should contain .distr files, the other files should
be placed under CVS.
There are files that derive from other files and yet should be placed
in the distribution.
These files should not be placed under RCS or CVS.
The file "Exceptions" in this directory contains the current list of
these files.
When all this is correct, use the shell script mktree the extract
the distribution from the EM tree.
sh mktree destination_tree repository_tree > destination_tree/Versions 2>f.attf
Make sure that the destination tree exists and is empty!
Failing to do that will almost certainly result in a welter of
error messages.
The file f.attf contains mktree error messages and should be compared
to Exceptions.
The actions of mktree are quite complicated. It starts in the current
directory creating a version in the destination directory.
Then it reads the .distr file.
For each file mentioned there it performes certain actions:
1- Directory Change to that directory and call yourself recursively.
2- File
a- Does a file LIST exist in this directory AND
is the first line of LIST equal to the name of the
destination file? If so, try to extract all the files
named in the rest of the LIST file and call the program
arch to create a library "arch cDr `cat LIST`".
In this manner libraries can be distributed whose members
have their own RCS file.
else
b- Try to run 'make distr'
else
c- Try to run 'make <filename>'
else
d- give message that says "not present" (or some such).
Now, the tree contains all the files in the distribution, but it also contains
files that should not be in the distribution, especially the files created
by CVS.
That is why we now give the command:
dtar cdf distr5 .
The file distr5 is the one you should put on tape!
But,.... before doing that: Try it out!
Repeat the process described in the installation manual.
Only if that succeeds you are sure that you included the files needed.
Good Luck,
Ed Keizer, 85/4/15.
Updated for 3rd distribution by Ceriel Jacobs, 87/3/11.
And again,
Good Luck!
Updated for 4th distribution by Ceriel Jacobs, 88/4/08.
And again,
Good Luck!
Updated for 5th distribution by Ceriel Jacobs, 91/19/12.
And again,
Good Luck!
Updated for 1st upgrade to 5th distribution by Ceriel Jacobs, 91/12/11.
And again,
Good Luck!

30
distr/dwalk
View file

@ -1,30 +0,0 @@
: ${CDIR=.}
if [ $# = 1 ]
then
${DD-:} $CDIR $1
else
${DD-:} $CDIR
fi
${DF-:} $CDIR .distr
if test ! -r $DESTDIR/$CDIR/.distr
then
echo ++ no .distr in $CDIR 1>&2
exit 0
fi
for i in `cat $DESTDIR/$CDIR/.distr`
do
if test -d $i
then
( if cd $i
then
CDIR=$CDIR/$i
export CDIR
exec $DDIR/dwalk $*
else
echo ++ Could not access $CDIR/$i 1>&2
fi
)
else
${DF-:} $CDIR $i
fi
done

1
distr/echod
View file

@ -1 +0,0 @@
echo $1

26
distr/f.attf
View file

@ -1,26 +0,0 @@
-- ./doc/install.pr no RCS file
-- ./h/em_mnem.h no RCS file
-- ./h/em_pseu.h no RCS file
-- ./h/em_spec.h no RCS file
-- ./lang/basic/src/y.tab.c no RCS file
-- ./lang/basic/src/y.tab.h no RCS file
-- ./lang/pc/pem/pem22.m no RCS file
-- ./lang/pc/pem/pem24.m no RCS file
-- ./lang/pc/pem/pem44.m no RCS file
-- ./lib/LLgen/incl no RCS file
-- ./lib/LLgen/rec no RCS file
-- ./mach/m68k2/cg/tables1.c no RCS file
-- ./mach/m68k2/cg/tables1.h no RCS file
-- ./mach/m68020/ncg/tables1.c no RCS file
-- ./mach/m68020/ncg/tables1.h no RCS file
-- ./mach/vax4/cg/tables1.c no RCS file
-- ./mach/vax4/cg/tables1.h no RCS file
-- ./util/LLgen/src/parser no RCS file
-- ./util/LLgen/src/LLgen.c no RCS file
-- ./util/LLgen/src/Lpars.c no RCS file
-- ./util/LLgen/src/Lpars.h no RCS file
-- ./util/LLgen/src/tokens.c no RCS file
-- ./util/data/em_flag.c no RCS file
-- ./util/data/em_mnem.c no RCS file
-- ./util/data/em_pseu.c no RCS file
-- ./util/ego/share/pop_push.h no RCS file

10
distr/listall
View file

@ -1,10 +0,0 @@
case $# in
0) DESTDIR=. ;;
1) DESTDIR=$1 ;;
*) echo $0 [directory] ; exit 1 ;;
esac
DD=`pwd`/listall.d
DW=`pwd`/dwalk
export DD DESTDIR
cd $DESTDIR
$DW

2
distr/listall.d
View file

@ -1,2 +0,0 @@
echo "<$1>"
ls -bCdx `cat .distr`

10
distr/listdirs
View file

@ -1,10 +0,0 @@
case $# in
0) DIR=. ;;
1) DIR=$1 ;;
*) echo $0 [directory] ; exit 1 ;;
esac
DD=`pwd`/echod
DW=`pwd`/dwalk
export DD
cd $DIR
$DW

39
distr/mk_distr_syms
View file

@ -1,39 +0,0 @@
: Utility to make a tree of symbolic links to source tree.
: Mount the source tree read-only, use this script, and then try installation.
case $# in
2) ;;
*) echo "Usage: $0 <source-tree> <symlink-tree>" 1>&2
exit 1
;;
esac
if [ -f $1/.distr ]
then
for i in `cat $1/.distr`
do
if [ -d $1/$i ]
then
if mkdir $2/$i && $0 $1/$i $2/$i
then
:
else
exit 2
fi
else
if [ -f $1/$i ]
then
if ln -s $1/$i $2/$i
then
:
else
exit 3
fi
else
echo "Missing file $1/$i" 1>&2
exit 4
fi
fi
done
else
echo "No .distr file in $1" 1>&2
exit 5
fi

9
distr/mka
View file

@ -1,9 +0,0 @@
set -e
for i in `tail +2 $DESTDIR/$1/LIST`
do
${DF-false} $1 $i
done
cd $DESTDIR/$1
arch cDr `cat LIST`
: I do not remove the files constituating the library, because
: they might be present in .distr

27
distr/mkd
View file

@ -1,27 +0,0 @@
case $1 in
.) ;;
*) mkdir $DESTDIR/$1
;;
esac
p=$REPDIR/$1
dir=$1
if [ $# = 2 ]
then
if [ -f $2 ]
then
set `fgrep "$dir " $2`
fi
fi
cd $DESTDIR/$dir
if [ $# = 2 ]
then
RV $p $2 > /dev/null 2>&1
echo "$dir $2"
else
if `CV $p > /dev/null 2>&1`
then
echo "$dir `RC -i`"
else
echo "-- $dir CV failed for some reason" 1>&2
fi
fi

17
distr/mkf
View file

@ -1,17 +0,0 @@
if [ -f $DESTDIR/$1/$2 ]
then
:
elif grep LIST $DESTDIR/$1/.distr >/dev/null 2>&1 &&
(test "$2" = "`head -1 $DESTDIR/$1/LIST`") >/dev/null 2>&1 &&
${DA-false} "$1" "$2"
then
: Fetched library contents one by one and put them together
elif ( cd $DESTDIR/$1 ; make distr ) > /dev/null 2>&1
then
echo ++ $1/$2 made 1>&2
elif ( cd $DESTDIR/$1 ; make $2 ) > /dev/null 2>&1
then
echo ++ $1/$2 made 1>&2
else
echo ++ $1/$2 not present 1>&2
fi

1
distr/mks
View file

@ -1 +0,0 @@
cp .distr $DESTDIR/$1

28
distr/mktree
View file

@ -1,28 +0,0 @@
case $# in
2|3) ;;
*) echo Usage: $0 directory repdir [ SVrecord ] 1>&2 ; exit 1 ;;
esac
case $0 in
/*) DDIR=`dirname $0`
;;
*) DDIR=`pwd`/`dirname $0`
;;
esac
case $1 in
/*) DESTDIR=$1 ;;
*) DESTDIR=`pwd`/$1 ;;
esac
case $2 in
/*) REPDIR=$2 ;;
*) REPDIR=`pwd`/$2 ;;
esac
cd $REPDIR
DD=$DDIR/mkd
DF=$DDIR/mkf
DA=$DDIR/mka
export DDIR DESTDIR DD DF DA REPDIR
$DDIR/dwalk $3
cd $DESTDIR
find . -type d -print | xargs chmod "uog+rx"
chmod -R "og-w,u+w,uog+r" .

26
distr/todistr
View file

@ -1,26 +0,0 @@
REV=
FILE=
while :
do
case $# in
0) break ;;
esac
ARG="$1"
shift
case "$ARG" in
-r*) REV=`echo "$ARG"| sed s/-r//` ;;
-*) FLAGS="$FLAGS $ARG" ;;
*) case x$FILE in
x) FILE="$ARG" ;;
*) echo todistr can only be done on one file at the time
exit 1 ;;
esac
esac
done
case x$REV in
x) REV=`rlog -h "$FILE"|sed -n -e '/head/s/^head:[ ]*//p'` ;;
esac
case x$REV in
x) exit 2 ;;
esac
rcs -ndistr4:$REV $FLAGS $FILE

2
distr/ts
View file

@ -1,2 +0,0 @@
DD=`pwd`/ts
echo OK

32
doc/.distr
View file

@ -1,32 +0,0 @@
READ_ME
Makefile
proto.make
ack.doc
basic.doc
cg.doc
crefman.doc
ansi_C.doc
em
install.doc
install.pr
ncg.doc
pcref.doc
peep.doc
regadd.doc
toolkit.doc
v7bugs.doc
val.doc
LLgen
6500.doc
i80.doc
z80.doc
m68020.doc
m2ref.doc
nopt.doc
top
ego
occam
int
ceg
sparc
lint

1893
doc/6500.doc
View file

File diff suppressed because it is too large Load diff

3
doc/LLgen/.distr
View file

@ -1,3 +0,0 @@
LLgen.n
LLgen.refs
proto.make

1072
doc/LLgen/LLgen.n
View file

File diff suppressed because it is too large Load diff

54
doc/LLgen/LLgen.refs
View file

@ -1,54 +0,0 @@
%T An ALL(1) Compiler Generator
%A D. R. Milton
%A L. W. Kirchhoff
%A B. R. Rowland
%B Proc. of the SIGPLAN '79 Symposium on Compiler Construction
%D August 1979
%J SIGPLAN Notices
%N 8
%P 152-157
%V 14
%T Lex - A Lexical Analyser Generator
%A M. E. Lesk
%I Bell Laboratories
%D October 1975
%C Murray Hill, New Jersey
%R Comp. Sci. Tech. Rep. No. 39
%T Yacc: Yet Another Compiler Compiler
%A S. C. Johnson
%I Bell Laboratories
%D 1975
%C Murray Hill, New Jersey
%R Comp. Sci. Tech. Rep. No. 32
%T The C Programming Language
%A B. W. Kernighan
%A D. M. Ritchie
%I Prentice-Hall, Inc.
%C Englewood Cliffs, New Jersey
%D 1978
%A M. Griffiths
%T LL(1) Grammars and Analysers
%E F. L. Bauer and J. Eickel
%B Compiler Construction, An Advanced Course
%I Springer-Verlag
%C New York, N.Y.
%D 1974
%T Make - A Program for Maintaining Computer Programs
%A S. I. Feldman
%J Software - Practice and Experience
%V 10
%N 8
%P 255-265
%D August 1979
%T Methods for the Automatic Construction of Error Correcting Parsers
%A J. R\*:ohrich
%J Acta Informatica
%V 13
%P 115-139
%D 1980

9
doc/LLgen/Makefile
View file

@ -1,9 +0,0 @@
# $Id$
EQN=eqn
REFER=refer
TBL=tbl
TARGET=-Tlp
../LLgen.doc: LLgen.n LLgen.refs
$(REFER) -sA+T -p LLgen.refs LLgen.n | $(EQN) $(TARGET) | $(TBL) > $@

12
doc/LLgen/proto.make
View file

@ -1,12 +0,0 @@
# $Id$
#PARAMS do not remove this line!
SRC_DIR = $(SRC_HOME)/doc/LLgen
EQN=eqn
REFER=refer
TBL=tbl
$(TARGET_HOME)/doc/LLgen.doc: $(SRC_DIR)/LLgen.n $(SRC_DIR)/LLgen.refs
$(REFER) -sA+T -p $(SRC_DIR)/LLgen.refs $(SRC_DIR)/LLgen.n | $(EQN) | $(TBL) > $@

81
doc/Makefile
View file

@ -1,81 +0,0 @@
# $Id$
# This Makefile is not supposed to be used in the doc source directory.
# Instead, it is supposed to be copied to the target doc directory.
SUF=dit
PRINT=dis
NROFF=troff
MS=-ms
OPR=dip
RESFILES= \
toolkit.$(SUF) install.$(SUF) em.$(SUF) ack.$(SUF) v7bugs.$(SUF) \
peep.$(SUF) cg.$(SUF) ncg.$(SUF) regadd.$(SUF) LLgen.$(SUF) \
basic.$(SUF) crefman.$(SUF) pcref.$(SUF) val.$(SUF) ansi_C.$(SUF) \
6500.$(SUF) i80.$(SUF) z80.$(SUF) top.$(SUF) ego.$(SUF) \
m68020.$(SUF) occam.$(SUF) m2ref.$(SUF) ceg.$(SUF) nopt.$(SUF) \
sparc.$(SUF) int.$(SUF) lint.$(SUF)
.SUFFIXES: .doc .$(SUF) .lpr .out
.doc.$(SUF):
$(NROFF) $(MS) $< > $@
# directly to the printer:
.doc.lpr:
$(NROFF) $(MS) $< | $(OPR)
# to standard output
.doc.out:
@$(NROFF) $(MS) $<
# Exceptions, to be run without -ms
v7bugs.$(SUF): v7bugs.doc
$(NROFF) v7bugs.doc >$@
v7bugs.lpr: v7bugs.doc
$(NROFF) v7bugs.doc | $(OPR)
v7bugs.out: v7bugs.doc
@$(NROFF) v7bugs.doc
pcref.$(SUF): pcref.doc
$(NROFF) pcref.doc >$@
pcref.lpr: pcref.doc
$(NROFF) pcref.doc | $(OPR)
pcref.out: pcref.doc
@$(NROFF) pcref.doc
val.$(SUF): val.doc
$(NROFF) val.doc >$@
val.lpr: val.doc
$(NROFF) val.doc | $(OPR)
val.out: val.doc
@$(NROFF) val.doc
pr:
@make "SUF="$(SUF) "NROFF="$(NROFF) "MS="$(MS) \
$(RESFILES) >make.pr.out 2>&1
@$(PRINT) $(RESFILES)
# The 'opr' entry creates a lot of paper ... but the user must be able
# to write the doc directory. I hope that this limits the users of
# this entry to persons that know what they are doing.
opr:
@make "SUF="$(SUF) "NROFF="$(NROFF) "MS="$(MS) $(RESFILES)
$(OPR) $(RESFILES)
clean:
-rm -f $(RESFILES)
# The distr entry is only used when making a distribution tree.
# It makes a version of the installation manual, suitable for a simple
# line printer.
distr: install.doc
tbl install.doc | nroff -Tlpr $(MS) >install.pr

8
doc/READ_ME
View file

@ -1,8 +0,0 @@
Some of these documents use a font called CW.
If this font is not available, reference to it can be changed with
a sed-script like
s/\.ft CW/.ft yourfont/
s/\\f(CW/\\fyourfont/g
s/^.fp\(.*\)CW$/.fp\1yourfont/
However, the font must be a constant-width font for the documents to look
reasonable.

444
doc/ack.doc
View file

@ -1,444 +0,0 @@
.\" $Id$
.nr PD 1v
.tr ~
.TL
Ack Description File
.br
Reference Manual
.AU
Ed Keizer
.AI
Vakgroep Informatica
Vrije Universiteit
Amsterdam
.NH
Introduction
.PP
The program \fIack\fP(I) internally maintains a table of
possible transformations and a table of string variables.
The transformation table contains one entry for each possible
transformation of a file.
Which transformations are used depends on the suffix of the
source file.
Each transformation table entry tells which input suffixes are
allowed and what suffix/name the output file has.
When the output file does not already satisfy the request of the
user (indicated with the flag \fB\-c.suffix\fP), the table is scanned
starting with the next transformation in the table for another
transformation that has as input suffix the output suffix of
the previous transformation.
A few special transformations are recognized, among them is the
combiner, which is
a program combining several files into one.
When no stop suffix was specified (flag \fB\-c.suffix\fP) \fIack\fP
stops after executing the combiner with as arguments the \-
possibly transformed \- input files and libraries.
\fIAck\fP will only perform the transformations in the order in
which they are presented in the table.
.LP
The string variables are used while creating the argument list
and program call name for
a particular transformation.
.NH
Which descriptions are used
.PP
\fIAck\fP always uses two description files: one to define the
front-end transformations and one for the machine dependent
back-end transformations.
Each description has a name.
First the way of determining
the name of the descriptions needed is described.
.PP
When the shell environment variable ACKFE is set \fIack\fP uses
that to determine the front-end table name, otherwise it uses
\fBfe\fP.
.PP
The way the backend table name is determined is more
convoluted.
.br
First, when the last filename in the program call name is not
one of \fIack\fP or the front-end call-names,
this filename is used as the backend description name.
Second, when the \fB\-m\fP is present the \fB\-m\fP is chopped of this
flag and the rest is used as the backend description name.
Third, when both failed the shell environment variable ACKM is
used.
Last, when also ACKM was not present the default backend is
used, determined by the definition of ACKM in h/local.h.
The presence and value of the definition of ACKM is
determined at compile time of \fIack\fP.
.PP
Now, we have the names, but that is only the first step.
\fIAck\fP stores a few descriptions at compile time.
This descriptions are simply files read in at compile time.
At the moment of writing this document, the descriptions
included are: pdp, fe, i86, m68k2, vax2 and int.
The name of a description is first searched for internally,
then in lib/descr/\fIname\fP, then in
lib/\fIname\fP/descr, and finally in the current
directory of the user.
.NH
Using the description file
.PP
Before starting on a narrative of the description file,
the introduction of a few terms is necessary.
All these terms are used to describe the scanning of zero
terminated strings, thereby producing another string or
sequence of strings.
.IP Backslashing 5
.br
All characters preceded by \e are modified to prevent
recognition at further scanning.
This modification is undone before a string is passed to the
outside world as argument or message.
When reading the description files the
sequences \e\e, \e# and \e<newline> have a special meaning.
\e\e translates to a single \e, \e# translates to a single #
that is not
recognized as the start of comment, but can be used in
recognition and finally, \e<newline> translates to nothing at
all, thereby allowing continuation lines.
.nr PD 0
.IP "Variable replacement"
.br
The scan recognizes the sequences {{, {NAME} and {NAME?text}
Where NAME can be any combination if characters excluding ? and
} and text may be anything excluding }.
(~\e} is allowed of course~)
The first sequence produces an unescaped single {.
The second produces the contents of the NAME, definitions are
done by \fIack\fP and in description files.
When the NAME is not defined an error message is produced on
the diagnostic output.
The last sequence produces the contents of NAME if it is
defined and text otherwise.
.PP
.IP "Expression replacement"
.br
Syntax: (\fIsuffix sequence\fP:\fIsuffix sequence\fP=\fItext\fP)
.br
Example: (.c.p.e:.e=tail_em)
.br
If the two suffix sequences have a common member \-~\&.e in this
case~\- the text is produced.
When no common member is present the empty string is produced.
Thus the example given is a constant expression.
Normally, one of the suffix sequences is produced by variable
replacement.
\fIAck\fP sets three variables while performing the diverse
transformations: HEAD, TAIL and RTS.
All three variables depend on the properties \fIrts\fP and
\fIneed\fP from the transformations used.
Whenever a transformation is used for the first time,
the text following the \fIneed\fP is appended to both the HEAD and
TAIL variable.
The value of the variable RTS is determined by the first
transformation used with a \fIrts\fP property.
.IP
Two runtime flags have effect on the value of one or more of
these variables.
The flag \fB\-.suffix\fP has the same effect on these three variables
as if a file with that \fBsuffix\fP was included in the argument list
and had to be translated.
The flag \fB\-r.suffix\fP only has that effect on the TAIL
variable.
The program call names \fIacc\fP and \fIcc\fP have the effect
of an automatic \fB\-.c\fP flag.
\fIApc\fP and \fIpc\fP have the effect of an automatic \fB\-.p\fP flag.
.IP "Line splitting"
.br
The string is transformed into a sequence of strings by replacing
the blank space by string separators (nulls).
.IP "IO replacement"
.br
The > in the string is replaced by the output file name.
The < in the string is replaced by the input file name.
When multiple input files are present the string is duplicated
for each input file name.
.nr PD 1v
.LP
Each description is a sequence of variable definitions followed
by a sequence of transformation definitions.
Variable definitions use a line each, transformations
definitions consist of a sequence of lines.
Empty lines are discarded, as are lines with nothing but
comment.
Comment is started by a # character, and continues to the end
of the line.
Three special two-characters sequences exist: \e#, \e\e and
\e<newline>.
Their effect is described under 'backslashing' above.
Each \- nonempty \- line starts with a keyword, possibly
preceded by blank space.
The keyword can be followed by a further specification.
The two are separated by blank space.
.PP
Variable definitions use the keyword \fIvar\fP and look like this:
.DS X
var NAME=text
.DE
The name can be any identifier, the text may contain any
character.
Blank space before the equal sign is not part of the NAME.
Blank space after the equal is considered as part of the text.
The text is scanned for variable replacement before it is
associated with the variable name.
.br
.sp 2
The start of a transformation definition is indicated by the
keyword \fIname\fP.
The last line of such a definition contains the keyword
\fIend\fP.
The lines in between associate properties to a transformation
and may be presented in any order.
The identifier after the \fIname\fP keyword determines the name
of the transformation.
This name is used for debugging and by the \fB\-R\fP flag.
The keywords are used to specify which input suffices are
recognized by that transformation,
the program to run, the arguments to be handed to that program
and the name or suffix of the resulting output file.
Two keywords are used to indicate which run-time startoffs and
libraries are needed.
The possible keywords are:
.IP \fIfrom\fP
.br
followed by a sequence of suffices.
Each file with one of these suffices is allowed as input file.
Preprocessor transformations do not need the \fIfrom\fP
keyword. All other transformations do.
.nr PD 0
.IP \fIto\fP
.br
followed by the suffix of the output file name or in the case of a
linker
the output file name.
.IP \fIprogram\fP
.br
followed by name of the load file of the program, a pathname most likely
starts with either a / or {EM}.
This keyword must be
present, the remainder of the line
is subject to backslashing and variable replacement.
.IP \fImapflag\fP
.br
The mapflags are used to grab flags given to \fIack\fP and
pass them on to a specific transformation.
This feature uses a few simple pattern matching and replacement
facilities.
Multiple occurrences of this keyword are allowed.
This text following the keyword is
subjected to backslashing.
The keyword is followed by a match expression and a variable
assignment separated by blank space.
As soon as both description files are read, \fIack\fP looks
at all transformations in these files to find a match for the
flags given to \fIack\fP.
The flags \fB\-m\fP, \fB\-o\fP,
\fB\-O\fP, \fB\-r\fP, \fB\-v\fP, \fB\-g\fP, \-\fB\-c\fP, \fB\-t\fP,
\fB\-k\fP, \fB\-R\fP and \-\fB\-.\fP are specific to \fIack\fP and
not handed down to any transformation.
The matching is performed in the order in which the entries
appear in the definition.
The scanning stops after first match is found.
When a match is found, the variable assignment is executed.
A * in the match expression matches any sequence of characters,
a * in the right hand part of the assignment is
replaced by the characters matched by
the * in the expression.
The right hand part is also subject to variable replacement.
The variable will probably be used in the program arguments.
The \fB\-l\fP flags are special,
the order in which they are presented to \fIack\fP must be
preserved.
The identifier LNAME is used in conjunction with the scanning of
\fB\-l\fP flags.
The value assigned to LNAME is used to replace the flag.
The example further on shows the use of all this.
.IP \fIargs\fP
.br
The keyword is followed by the program call arguments.
It is subject to backslashing, variable replacement, expression
replacement, line splitting and IO replacement.
The variables assigned to by \fImapflags\fP will probably be
used here.
The flags not recognized by \fIack\fP or any of the transformations
are passed to the linker and inserted before all other arguments.
.IP \fIstdin\fP
.br
This keyword indicates that the transformation reads from standard input.
.IP \fIstdout\fP
.br
This keyword indicates that the transformation writes on standard output.
.IP \fIoptimizer\fP
.br
The presence of this keyword indicates that this transformation is an optimizer.
It can be followed by a number, indicating the "level" of the
optimizer (see description of the -O option in the ack(1ACK) manual page).
.IP \fIpriority\fP
.br
This \-~optional~\- keyword is followed by a number. Positive priority means
that the transformation is likely to be used, negative priority means that
the transformation is unlikely to be used.
Priorities can also be set with a ack(1ACK) command line option.
Priorities come in handy when there are several implementations of a
certain transformation. They can then be used to select a default one.
.IP \fIlinker\fP
.br
This keyword indicates that this transformation is the linker.
.IP \fIcombiner\fP
.br
This keyword indicates that this transformation is a combiner. A combiner
is a program combining several files into one, but is not a linker.
An example of a combiner is the global optimizer.
.IP \fIprep\fP
.br
This \-~optional~\- keyword is followed an option indicating its relation
to the preprocessor.
The possible options are:
.DS X
always the input files must be preprocessed
cond the input files must be preprocessed when starting with #
is this transformation is the preprocessor
.DE
.IP \fIrts\fP
.br
This \-~optional~\- keyword indicates that the rest of the line must be
used to set the variable RTS, if it was not already set.
Thus the variable RTS is set by the first transformation
executed which such a property or as a result from \fIack\fP's program
call name (acc, cc, apc or pc) or by the \fB\-.suffix\fP flag.
.IP \fIneed\fP
.br
This \-~optional~\- keyword indicates that the rest of the line must be
concatenated to the HEAD and TAIL variables.
This is done once for every transformation used or indicated
by one of the program call names mentioned above or indicated
by the \fB\-.suffix\fP flag.
.br
.nr PD 1v
.NH
Conventions used in description files
.PP
\fIAck\fP reads two description files.
A few of the variables defined in the machine specific file
are used by the descriptions of the front-ends.
Other variables, set by \fIack\fP, are of use to all
transformations.
.PP
\fIAck\fP sets the variable EM to the home directory of the
Amsterdam Compiler Kit.
The variable SOURCE is set to the name of the argument that is currently
being massaged, this is useful for debugging.
The variable SUFFIX is set to the suffix of the argument that is
currently being massaged.
.br
The variable M indicates the
directory in lib/{M}/tail_..... and NAME is the string to
be defined by the preprocessor with \-D{NAME}.
The definitions of {w}, {s}, {l}, {d}, {f} and {p} indicate
EM_WSIZE, EM_SSIZE, EM_LSIZE, EM_DSIZE, EM_FSIZE and EM_PSIZE
respectively.
.br
The variable INCLUDES is used as the last argument to \fIcpp\fP.
It is used to add directories to
the list of directories containing #include files.
.PP
The variables HEAD, TAIL and RTS are set by \fIack\fP and used
to compose the arguments for the linker.
.NH
Example
.PP
Description for front-end
.DS X
.ta 4n 40n
name cpp # the C-preprocessor
# no from, it's governed by the P property
to .i # result files have suffix i
program {EM}/lib/cpp # pathname of loadfile
mapflag \-I* CPP_F={CPP_F?} \-I* # grab \-I.. \-U.. and
mapflag \-U* CPP_F={CPP_F?} \-U* # \-D.. to use as arguments
mapflag \-D* CPP_F={CPP_F?} \-D* # in the variable CPP_F
args {CPP_F?} {INCLUDES?} \-D{NAME} \-DEM_WSIZE={w} \-DEM_PSIZE={p} \e
\-DEM_SSIZE={s} \-DEM_LSIZE={l} \-DEM_FSIZE={f} \-DEM_DSIZE={d} <
# The arguments are: first the \-[IUD]...
# then the include dir's for this machine
# then the NAME and size values finally
# followed by the input file name
stdout # Output on stdout
prep is # Is preprocessor
end
name cem # the C-compiler proper
from .c # used for files with suffix .c
to .k # produces compact code files
program {EM}/lib/em_cem # pathname of loadfile
mapflag \-p CEM_F={CEM_F?} \-Xp # pass \-p as \-Xp to cem
mapflag \-L CEM_F={CEM_F?} \-l # pass \-L as \-l to cem
args \-Vw{w}i{w}p{p}f{f}s{s}l{l}d{d} {CEM_F?}
# the arguments are the object sizes in
# the \-V... flag and possibly \-l and \-Xp
stdin # input from stdin
stdout # output on stdout
prep always # use cpp
rts .c # use the C run-time system
need .c # use the C libraries
end
name decode # make human readable files from compact code
from .k.m # accept files with suffix .k or .m
to .e # produce .e files
program {EM}/lib/em_decode # pathname of loadfile
args < # the input file name is the only argument
stdout # the output comes on stdout
end
.DE
.DS X
.ta 4n 40n
Example of a backend, in this case the EM assembler/loader.
var w=2 # wordsize 2
var p=2 # pointersize 2
var s=2 # short size 2
var l=4 # long size 4
var f=4 # float size 4
var d=8 # double size 8
var M=em22
var NAME=em22 # for cpp (NAME=em22 results in #define em22 1)
var LIB=lib/{M}/tail_ # part of file name for libraries
var RT=lib/{M}/head_ # part of file name for run-time startoff
var SIZE_FLAG=\-sm # default internal table size flag
var INCLUDES=\-I{EM}/include # use {EM}/include for #include files
name asld # Assembler/loader
from .k.m.a # accepts compact code and archives
to e.out # output file name
program {EM}/lib/em_ass # load file pathname
mapflag \-l* LNAME={EM}/{LIB}* # e.g. \-ly becomes
# {EM}/mach/int/lib/tail_y
mapflag \-+* ASS_F={ASS_F?} \-+* # recognize \-+ and \-\-
mapflag \-\-* ASS_F={ASS_F?} \-\-*
mapflag \-s* SIZE_FLAG=\-s* # overwrite old value of SIZE_FLAG
args {SIZE_FLAG} \e
({RTS}:.c={EM}/{RT}cc) ({RTS}:.p={EM}/{RT}pc) \-o > < \e
(.p:{TAIL}={EM}/{LIB}pc) \e
(.c:{TAIL}={EM}/{LIB}cc.1s {EM}/{LIB}cc.2g) \e
(.c.p:{TAIL}={EM}/{LIB}mon)
# \-s[sml] must be first argument
# the next line contains the choice for head_cc or head_pc
# and the specification of in- and output.
# the last three args lines choose libraries
linker
end
.DE
The command \fIack \-mem22 \-v \-v \-I../h \-L \-ly prog.c\fP
would result in the following
calls (with exec(II)):
.DS X
.ta 4n
1) /lib/cpp \-I../h \-I/usr/em/include \-Dem22 \-DEM_WSIZE=2 \-DEM_PSIZE=2 \e
\-DEM_SSIZE=2 \-DEM_LSIZE=4 \-DEM_FSIZE=4 \-DEM_DSIZE=8 prog.c
2) /usr/em/lib/em_cem \-Vw2i2p2f4s2l4d8 \-l
3) /usr/em/lib/em_ass \-sm /usr/em/lib/em22/head_cc \-o e.out prog.k
/usr/em/lib/em22/tail_y /usr/em/lib/em22/tail_cc.1s
/usr/em/lib/em22/tail_cc.2g /usr/em/lib/em22/tail_mon
.DE

365
doc/ansi_C.doc
View file

@ -1,365 +0,0 @@
.de NS
.sp
.in 0
\\fBANS \\$1:\\fP
..
.TL
Amsterdam Compiler Kit-ANSI C compiler compliance statements
.AU
Hans van Eck
.AI
Dept. of Mathematics and Computer Science
Vrije Universiteit
Amsterdam, The Netherlands
.PP
This document specifies the implementation-defined behaviour of the ANSI-C
front end of the Amsterdam Compiler Kit as required by ANS X3.159-1989. Since
the implementation-defined behaviour sometimes depends on the machine
compiling on or for, some items will be left unspecified in this
document\(dg.
.FS
\(dg when cross-compiling, run-time behaviour may be different from
compile-time behaviour
.FE
The compiler assumes that it runs on a UNIX system.
.NS A.6.3.1
.IP -
Diagnostics are placed on the standard error output. They have the
following specification:
.br
"<file>", line <nr>: [(<class>)] <diagnostic>
.br
There are three classes of diagnostics: "error", "strict" and "warning".
When the class is "error", the <class> is absent.
.br
The class "strict" is used for violations of the standard which are
not severe enough to stop compilation. An example is the the occurrence
of non white-space after an '#else' or '#endif' pre-processing
directive. The class "warning" is used for legal but dubious
constructions. An example is overflow of constant expressions.
.NS A.6.3.2
.IP -
The function 'main' can have two arguments. The first argument is an
integer specifying the number of arguments on the command line. The second
argument is a pointer to an array of pointers to the arguments (as
strings).
.IP -
Interactive devices are terminals.
.NS A.6.3.3
.IP -
The number of significant characters is an option. By default it is 64.
There is a distinction between upper and lower case.
.NS A.6.3.4
.IP -
The compiler assumes ASCII-characters in both the source and execution
character set.
.IP -
There are no multi-byte characters.
.IP -
There 8 bits in a character.
.IP -
Character constants with values that can not be represented in 8 bits
are truncated.
.IP -
Character constants that are more than 1 character wide will have the
first character specified in the least significant byte.
.IP -
The only supported locale is "C".
.IP -
A plain 'char' has the same range of values as 'signed char'.
.NS A.6.3.5
.IP -
The compiler assumes that it works on and compiles for a
2-complement binary-number system. Shorts will use 2 bytes and longs
will use 4 bytes. The size of integers are machine dependent.
.IP -
Converting an integer to a shorter signed integer is implemented by
ignoring the high-order byte(s) of the former.
Converting a unsigned integer to a signed integer of the same type is
only done in administration. This means that the bit-pattern remains
unchanged.
.IP -
The result of bitwise operations on signed integers are what can be
expected on a 2-complement machine.
.IP -
If either operand is negative, whether the result of the / operator is the
largest integer less than or equal to the algebraic quotient or the
smallest integer greater than or equal to the algebraic quotient is machine
dependent, as is the sign of the result of the % operator.
.IP -
The right-shift of a negative value is negative.
.NS A.6.3.6
.IP -
The representation of floating-point values is machine-dependent.
When native floating-point is not present an IEEE-emulation is used.
The compiler uses high-precision floating-point for constant folding.
.IP -
Truncation is always to the nearest floating-point number that can
be represented.
.NS A.6.3.7
.IP -
The type returned by the sizeof-operator (also known as size_t)
is 'unsigned int'. This is done for backward compatibility reasons.
.IP -
Casting an integer to a pointer or vice versa has no effect in
bit-pattern when the sizes are equal. Otherwise the value will be
truncated or zero-extended (depending on the direction of the
conversion and the relative sizes).
.IP -
When a pointer is as large as an integer, the type of a 'ptrdiff_t' will
be 'int'. Otherwise the type will be 'long'.
.NS A.6.3.8
.IP -
Since the front end has only limited control over the registers, it can
only make it more likely that variables that are declared as
registers also end up in registers. The only things that can possibly be
put into registers are : 'int', 'long', 'float', 'double', 'long double'
and pointers.
.NS A.6.3.9
.IP -
When a member of a union object is accessed using a member of a
different type, the resulting value will usually be garbage. The
compiler makes no effort to catch these errors.
.IP -
The alignment of types is a compile-time option. The alignment of
a structure-member is the alignment of its type. Usually, the
alignment is passed on to the compiler by the 'ack' program. When a
user wants to do this manually, he/she should be prepared for trouble.
.IP -
A "plain" 'int' bit-field is taken as a 'signed int'. This means that
a field with a size of 1 bit can only store the values 0 and -1.
.IP -
The order of allocation of bit-fields is a compile-time option. By
default, high-order bits are allocated first.
.IP -
An enum has the same size as a "plain" 'int'.
.NS A.6.3.10
.IP -
An access to a volatile declared variable is done by just mentioning
the variable. E.g. the statement "x;" where x is declared volatile,
constitutes an access.
.S A.6.3.11
.IP -
There is no fixed limit on the number of declarators that may modify an
arithmetic, structure or union type, although specifying too many may
cause the compiler to run out of memory.
.NS A.6.3.12
.IP -
The maximum number of cases in a switch-statement is in the order of
1e9, although the compiler may run out of memory somewhat earlier.
.NS A.6.3.13
.IP -
Since both the pre-processor and the compiler assume ASCII-characters,
a single character constant in a conditional-inclusion directive
matches the same value in the execution character set.
.IP -
The pre-processor recognizes -I... command-line options. The
directories thus specified are searched first. After that, depending on the
command that the preprocessor is called with, machine/system-dependant
directories are searched. After that, ~em/include/_tail_ac and
/usr/include are visited.
.IP -
Quoted names are first looked for in the directory in which the file
which does the include resides.
.IP -
The characters in a h- or q- char-sequence are taken to be UNIX
paths.
.IP -
Neither the compiler nor the preprocessor know any pragmas.
.IP -
Since the compiler runs on UNIX, __DATE__ and __TIME__ will always be
defined.
.NS A.6.3.14
.IP -
NULL is defined as ((void *)0). This in order to flag dubious
constructions like "int x = NULL;".
.IP -
The diagnostic printed by 'assert' is as follows:
.ti +4n
"Assertion "<expr>" failed, file "<file>", line <line>",
.br
where <expr> is the argument to the assert macro, printed as string.
(the <file> and <line> should be clear)
.KS
.IP -
The sets for character test macros.
.TS
l l.
name: set:
isalnum() 0-9A-Za-z
isalpha() A-Za-z
iscntrl() \e000-\e037\e177
islower() a-z
isupper() A-Z
isprint() <space>-~ (== \e040-\e176)
.TE
.KE
As an addition, there is an isascii() macro, which tests whether a character
is an ascii character. Characters in the range from \e000 to \e177 are ascii
characters.
.KS
.IP -
The behaviour of mathematic functions on domain error:
.TS
l c
l n.
name: returns:
asin() 0.0
acos() 0.0
atan2() 0.0
fmod() 0.0
log() -HUGE_VAL
log10() -HUGE_VAL
pow() 0.0
sqrt() 0.0
.TE
.KE
.IP -
Underflow range errors do not cause errno to be set.
.IP -
The function fmod() returns 0.0 and sets errno to EDOM when the second
argument is 0.0.
.IP -
The set of signals for the signal() function depends on the UNIX-system
which the compiler is compiling for. The default handling, semantics
and behaviour of these signals are those specified by the operating
system vendor. The default handling is not reset when SIGILL is
received.
.IP -
A text-stream need not end in a new-line character.
.IP -
White space characters before a new-line appear when read in.
.IP -
There may be any number of null characters appended to a binary
stream.
.IP -
The file position indicator of an append mode stream is initially
positioned at the beginning of the file.
.IP -
A write on a text stream does not cause the associated file to be
truncated beyond that point.
.IP -
The buffering intended by the standard is fully supported.
.IP -
A zero-length file actually exists.
.IP -
A file name can consist of any character, except for the '\e0' and
the '/'.
.IP -
A file can be open multiple times.
.IP -
When a remove() is done on an open file, reading and writing behave
just as can be expected from a non-removed file. When the associated
stream is closed, all written data will be lost.
.IP -
When a file exists prior to a call to rename(), the behaviour is that
of the underlying UNIX system. Normally, the call would fail.
.IP -
The %p conversion in fprintf() has the same effect as %#x or %#lx,
depending on the sizes of pointer and integer.
.IP -
The %p conversion in fscanf() has the same effect as %x or %lx,
depending on the sizes of pointer and integer.
.IP -
A - character that is neither the first nor the last character in the
scanlist for %[ conversion is taken to be a range indicator. When the
first character has a higher ASCII-value than the second, the - will
just be put into the scanlist.
.IP -
The value of errno when fgetpos() or ftell() failed is that of lseek().
This means:
.RS
.IP "EBADF \-" 10
when the stream is not valid
.IP "ESPIPE \-"
when fildes is associated with a pipe (and on some systems: sockets)
.IP "EINVAL \-"
the resulting file pointer would be negative
.RE
.LP
.IP -
The messages generated by perror() depend on the value of errno.
The mapping of errors to strings is done by strerror().
.IP -
When the requested size is zero, malloc(), calloc() and realloc()
return a null-pointer.
.IP -
When abort() is called, output buffers will be flushed. Temporary files
(made with the tmpfile() function) will have disappeared when SIGABRT
is not caught or ignored.
.IP -
The exit() function returns the low-order eight bits of its argument
to the environment.
.IP -
The predefined environment names are controlled by the user.
Setting environment variables is done through the putenv() function.
This function accepts a pointer to char as its argument.
To set f.i. the environment variable TERM to a230 one writes
.ti +4n
putenv("TERM=a230");
.br
The argument to putenv() is stored in an internal table, so malloc'ed
strings can not be freed until another call to putenv() (which sets the
same environment variable) is made. The function returns 1 if it fails,
0 otherwise.
.LP
.IP -
The argument to system is passed as argument to /bin/sh -c.
.IP -
The strings returned by strerror() depend on errno in the following
way:
.TS
l l.
errno string
0 "Error 0",
EPERM "Not owner",
ENOENT "No such file or directory",
ESRCH "No such process",
EINTR "Interrupted system call",
EIO "I/O error",
ENXIO "No such device or address",
E2BIG "Arg list too long",
ENOEXEC "Exec format error",
EBADF "Bad file number",
ECHILD "No children",
EAGAIN "No more processes",
ENOMEM "Not enough core",
EACCES "Permission denied",
EFAULT "Bad address",
ENOTBLK "Block device required",
EBUSY "Mount device busy",
EEXIST "File exists",
EXDEV "Cross-device link",
ENODEV "No such device",
ENOTDIR "Not a directory",
EISDIR "Is a directory",
EINVAL "Invalid argument",
ENFILE "File table overflow",
EMFILE "Too many open files",
ENOTTY "Not a typewriter",
ETXTBSY "Text file busy",
EFBUG "File too large",
ENOSPC "No space left on device",
ESPIPE "Illegal seek",
EROFS "Read-only file system",
EMLINK "Too many links",
EPIPE "Broken pipe",
EDOM "Math argument",
ERANGE "Result too large"
.TE
everything else causes strerror() to return "unknown error"
.IP -
The local time zone is per default MET (GMT + 1:00:00). This can be
changed through the TZ environment variable, or by some changes in the
sources.
.IP -
The clock() function returns the number of ticks since process
startup.
.SH
References
.IP [1]
ANS X3.159-1989
.I
American National Standard for Information Systems -
Programming Language C
.R

949
doc/basic.doc
View file

@ -1,949 +0,0 @@
.\" $Id$
.TL
.de Sy
.LP
.IP \fBsyntax\fR 10
..
.de PU
.IP \fBpurpose\fR 10
..
.de RM
.IP \fBremarks\fR 10
..
The ABC compiler
.AU
Martin L. Kersten
Gert-Jan Akkerman
Marcel Worring
Edo Westerhuis
Frans Kunst
Ronnie Lachniet
.AI
Department of Mathematics and Computer Science.
.br
Free University
.br
Amsterdam
.AB
This manual describes the
programming language BASIC and its compiler
included in the Amsterdam Compiler Kit.
.AE
.SH
INTRODUCTION.
.LP
The BASIC-EM compiler is an extensive implementation of the
programming language BASIC.
The language structure and semantics are modelled after the
BASIC interpreter/compiler of Microsoft (tr), a short comparison
is provided in appendix A.
.LP
The compiler generates code for a virtual machine, the EM machine
[[ACM, etc]].
Using EM as an intermediate machine results in a highly portable
compiler and BASIC code.
.br
The drawback of EM is that it does not directly reflect one particular
hardware design, which means that many of the low level operations available
within BASIC are ill-defined or even inapplicable.
To mention a few, the peek and poke instructions are likely
to be behave errorneous, while line printer and tapedeck
primitives are unknown.
.LP
This manual is divided into three chapters.
.br
Chapter 1 discusses the general language syntax and semantics.
.br
Chapter 2 describes the statements available in BASIC-EM.
.br
Chapter 3 describes the predefined functions, ordered alphabetically.
.LP
Appendix A discusses the differences with Microsoft BASIC.
.br
Appendix B describes all reserved symbols.
.LP
.LP
.SH
SYNTAX NOTATION
.LP
The conventions for syntax presentation are as follows:
.IP CAPS 10
Items are reserved words, must be input as shown.
.IP <> 10
Items in lowercase letters enclosed in angular brackets
are to be supplied by the user.
.IP [] 10
Items are optional.
.IP \.\.\. 10
Items may be repeated any number of times
.IP {} 10
A choice between two or more alternatives. At least one of the entries
must be chosen.
.IP | 10
Vertical bars separate the choices within braces.
.LP
All punctuation must be included where shown.
.bp
.NH 1
GENERAL INFORMATION
.LP
The BASIC-EM compiler is designed for a UNIX based environment.
It accepts a text file with a BASIC program (suffix .b) and generates
an executable file, called a.out.
.NH 2
LINE FORMAT
.LP
A BASIC program consists of a series of lines, starting with a
positive line number in the range 0 to 32767.
A line may consists of more than one physical line on a terminal, but
is limited to 1024 characters.
Multiple BASIC statements may be placed on a single line, provided
they are separated by a colon (:).
.NH 2
CONSTANTS
.LP
The BASIC compiler character set is comprised of alphabetic
characters, numeric characters, and special characters shown below.
.DS
= + - * / ^ ( ) % # $ \\ _
! [ ] , . ; : & ' ? > < \\ (blanc)
.DE
.LP
BASIC uses two different types of constants during processing:
numeric and string constants.
.br
A string constant is a sequence of characters taken from the ASCII
character set enclosed by double quotation marks.
.br
Numeric constants are positive or negative numbers, grouped into
five different classes.
.IP "a) integer constants" 25
.br
Whole numbers in the range of -32768 and 32767. Integer constants do
not contain decimal points.
.IP "b) fixed point constants" 25
.br
Positive or negative real numbers, i.e. numbers with a decimal point.
.IP "c) floating point constants" 25
.br
Real numbers in scientific notation. A floating point constant
consists of an optional signed integer or fixed point number
followed by the letter E (or D) and an optional signed integer
(the exponent).
The allowable range of floating point constants is 10^-38 to 10^+38.
.IP "d) Hex constants" 25
.br
Hexadecimal numbers, denoted by the prefix &H.
.IP "e) Octal constants" 25
.br
Octal numbers, denoted by the prefix &O.
.NH 2
VARIABLES
.LP
Variables are names used to represent values in a BASIC program.
A variable is assigned a value by assigment specified in the program.
Before a variable is assigned its value is assumed to be zero.
.br
Variable names are composed of letters, digits or the decimal point,
starting with a letter. Up to 40 characters are significant.
A variable name can be followed by any of the following type
declaration characters:
.IP % 5
Defines an integer variable
.IP ! 5
Defines a single precision variable (see below)
.IP # 5
Defines a double precision variable
.IP $ 5
Defines a string variable.
.LP
Beside single valued variables, values may be grouped into tables or arrays.
Each element in an array is referenced by the array name and an index,
such a variable is called a subscripted variable.
An array has as many subscripts as there are dimensions in the array,
the maximum of which is 11.
.br
If a variable starts with FN it is assumed to be a call to a user defined
function.
.br
A variable name may not be a reserved word nor the name
of a predefined function.
A list of all reserved identifiers is included as Appendix B.
.LP
NOTES:
.br
Two variables with the same name but different type is
considered illegal.
.br
The type of a variable without typedeclaration-character is set,
at it's first occurence in the program,
to the defaulttype which is (in this implementation) double precision.
.br
Multi-dimensional array's must be declared before use (see
DIM-statement ).
.br
BASIC-EM differs from Microsoft BASIC in supporting floats in one precision
only (due to EM), eg doubles and floats have the same precision.
.NH 2
EXPRESSIONS
.LP
When necessary the compiler will convert a numeric value from
one type to another.
A value is always converted to the precision of the variable it is assigned
to.
When a floating point value is converted to an integer the fractional
portion is rounded.
In an expression all values are converted to the same degree of precision,
i.e. that of the most precise operand.
.br
Division by zero results in the message "Division by zero".
If overflow (or underflow) occurs, the "Overflow (underflow)" message is
displayed and execution is terminated (contrary to Microsoft).
.SH
Arithmetic
.LP
The arithmetic operators in order of precedence,a re:
.DS L
^ Exponentiation
- Negation
*,/,\\\\\\\\,MOD Multiplication, Division, Remainder
+,- Addition, Substraction
.DE
The operator \\\\ denotes integer division, its operands are rounded to
integers before the operator is applied.
Modulus arithmetic is denoted by the operator MOD, which yields the
integer value that is the remainder of an integer division.
.br
The order in which operators are performed can be changed with parentheses.
.SH
Relational
.LP
The relational operators in order of precedence, are:
.DS
= Equality
<> Inequality
< Less than
> Greater than
<= Less than or equal to
>= Greater than or equal to
.DE
The relational operators are used to compare two values and returns
either "true" (-1) or "false" (0) (See IF statement).
The precedence of the relational operators is lower
then the arithmetic operators.
.SH
Logical
.LP
The logical operators performs tests on multiple relations, bit manipulations,
or boolean operations.
The logical operators returns a bitwise result ("true" or "false").
In an expression, logical operators are performed after the relational and
arithmetic operators.
The logical operators work by converting their operands to signed
two-complement integers in the range -32768 to 32767.
.DS
NOT Bitwise negation
AND Bitwise and
OR Bitwise or
XOR Bitwise exclusive or
EQV Bitwise equivalence
IMP Bitwise implies
.DE
.SH
Functional
.LP
A function is used in an expression to call a system or user defined
function.
A list of predefined functions is presented in chapter 3.
.SH
String operations
.LP
Strings can be concatenated by using +. Strings can be compared with
the relational operators. String comparison is performed in lexicographic
order.
.NH 2
ERROR MESSAGES
.LP
The occurence of an error results in termination of the program
unless an ON....ERROR statement has been encountered.
.bp
.NH 1
B-EM STATEMENTS
.LP
This chapter describes the statements available within the BASIC-EM
compiler. Each description is formatted as follows:
.Sy
Shows the correct syntax for the statement. See introduction of
syntax notation above.
.PU
Describes the purpose and details of the instructions.
.RM
Describes special cases, deviation from Microsoft BASIC etc.
.LP
.NH 2
CALL
.Sy
CALL <variable name>[(<argument list>)]
.PU
The CALL statement provides the means to execute procedures
and functions written in another language included in the
Amsterdam Compiler Kit.
The argument list consist of (subscripted) variables.
The BASIC compiler pushes the address of the arguments on the stack in order
of encounter.
.RM
Not yet available.
.NH 2
CLOSE
.Sy
CLOSE [[#]<file number>[,[#]<file number...>]]
.PU
To terminate I/O on a disk file.
<file number> is the number associated with the file
when it was OPENed (See OPEN-statement). Ommission of parameters results in closing
all files.
.sp
The END statement and STOP statement always issue a CLOSE of
all files.
.NH 2
DATA
.Sy
DATA <list of constants>
.PU
DATA statements are used to construct a data bank of values that are
accessed by the program's READ statement.
DATA statements are non-executable,
the data items are assembled in a data file by the BASIC compiler.
This file can be replaced, provided the layout remains
the same (otherwise the RESTORE won't function properly).
.sp
The list of data items consists of numeric and string constants
as discussed in section 1.
Moreover, string constants starting with a letter and not
containing blancs, newlines, commas, colon need not be enclosed with
the string quotes.
.sp
DATA statements can be reread using the RESTORE statement.
.NH 2
DEF FN
.Sy
DEF FN<name> [(<parameterlist>)]=<expression>
.PU
To define and name a function that is written by the user.
<name> must be an identifier and should be preceded by FN,
which is considered integral part of the function name.
<expression> defines the expression to be evaluated upon function call.
.sp
The parameter list is comprised of a comma separated
list of variable names, used within the function definition,
that are to replaced by values upon function call.
The variable names defined in the parameterlist, called formal
parameters, do not affect the definition and use of variables
defined with the same name in the rest of the BASIC program.
.sp
A type declaration character may be suffixed to the function name to
designate the data type of the function result.
.NH 2
DEFINT/SNG/DBL/STR
.Sy
DEF<type> <range of letters>
.PU
Any undefined variable starting with the letter included in the range of
letters is declared of type <type> unless a type declaration character
is appended.
The range of letters is a comma separated list of characters and
character ranges (<letter>-<letter>).
.NH 2
DIM
.Sy
DIM <list of subscripted variable>
.PU
The DIM statement allocates storage for subscripted variables.
If an undefined subscripted variable is used
the maximum value of the array subscript is assumed to be 10.
A subscript out of range is signalled by the program (when ACK works)
The minimum subscript value is 0, unless the OPTION BASE statement has been
encountered.
.sp
All variables in a subscripted variable are initially zero.
.sp
BUGS. Multi-dimensional arrays MUST be defined. Subscript out of range is
left unnotified.
.NH 2
END
.Sy
END
.PU
END terminates a BASIC program and returns to the UNIX shell.
An END statement at the end of the BASIC program is optional.
.NH 2
ERR and ERL
.Sy
<identifier name>= ERR
.br
<identifier name>= ERL
.PU
Whenever an error occurs the variable ERR contains the
error number and ERL the BASIC line where the error occurred.
The variables are usually used in error handling routines
provided by the user.
.NH 2
ERROR
.Sy
ERROR <integer expression>
.PU
To simulate the occurrence of a BASIC error.
To define a private error code a value must be used that is not already in
use by the BASIC runtime system.
The list of error messages currently in use can be found in appendix B.
.NH 2
FIELD
.PU
To be implemented.
.NH 2
FOR...NEXT
.Sy
FOR <variable>= <low>TO<high>[STEP<size>]
.br
......
.br
NEXT [<variable>][,<variable>...]
.PU
The FOR statements allows a series of statements to be performed
repeatedly. <variable> is used as a counter. During the first
execution pass it is assigned the value <low>,
an arithmetic expression. After each pass the counter
is incremented (decremented) with the step size <size>, an expression.
Ommission of the step size is intepreted as an increment of 1.
.br
Execution of the program lines specified between the FOR and the NEXT
statement is terminated as soon as <low> is greater (less) than <high>
.sp
The NEXT statement is labeled with the name(s) of the counter to be
incremented.
.sp
The variables mentioned in the NEXT statement may be ommitted, in which case
the variable of increment the counter of the most recent FOR statement.
If a NEXT statement is encountered before its corresponding FOR statement,
the error message "NEXT without FOR" is generated.
.NH 2
GET
.Sy
GET [#]<file number>[, <record number>]
.PU
To be implemented.
.NH 2
GOSUB...RETURN
.Sy
GOSUB <line number>
...
.br
RETURN
.PU
The GOSUB statement branches to the first statement of a subroutine.
The RETURN statement cause a branch back to the statement following the
most recent GOSUB statement.
A subroutine may contain more than one RETURN statement.
.sp
Subroutines may be called recursively.
Nesting of subroutine calls is limited, upon exceeding the maximum depth
the error message "XXXXX" is displayed.
.NH 2
GOTO
.Sy
GOTO <line number>
.PU
To branch unconditionally to a specified line in the program.
If <line number> does not exists, the compilation error message
"Line not defined" is displayed.
.RM
Microsoft BASIC continues at the first line
equal or greater then the line specified.
.NH 2
IF...THEN
.Sy
.br
IF <expression> THEN {<statements>|<line number>}
[ELSE {<statements>|<line number>}]
.br
.Sy
IF <expression> GOTO <line number>
[ELSE {<statements>|<line number>}]
.PU
The IF statement is used
to make a decision regarding the program flow based on the
result of the expressions.
If the expression is not zero, the THEN or GOTO clause is
executed. If the result of <expression> is zero, the THEN or
GOTO clause is ignored and the ELSE clause, if present is
executed.
.br
IF..THEN..ELSE statements may be nested.
Nesting is limited by the length of the line.
The ELSE clause matches with the closests unmatched THEN.
.sp
When using IF to test equality for a value that is the
result of a floating point expression, remember that the
internal representation of the value may not be exact.
Therefore, the test should be against a range to
handle the relative error.
.RM
Microsoft BASIC allows a comma before THEN.
.NH 2
INPUT
.Sy
INPUT [;][<"prompt string">;]<list of variables>
.PU
An INPUT statement can be used to obtain values from the user at the
terminal.
When an INPUT statement is encountered a question mark is printed
to indicate the program is awaiting data.
IF <"prompt string"> is included, the string is printed before the
the question mark. The question mark is suppressed when the prompt
string is followed by a comma, rather then a semicolon.
.sp
For each variable in the variable a list a value should be supplied.
Data items presented should be separated by a comma.
.sp
The type of the variable in the variable list must aggree with the
type of the data item entered. Responding with too few or too many
data items causes the message "?Redo". No assignment of input values
is made until an acceptable response is given.
.RM
The option to disgard the carriage return with the semicolon after the
input symbol is not yet implemented.
.NH 2
INPUT [#]
.Sy
INPUT #<file number>,<list of variables>
.PU
The purpose of the INPUT# statement is to read data items from a sequential
file and assign them to program variables.
<file number> is the number used to open the file for input.
The variables mentioned are (subscripted) variables.
The type of the data items read should aggree with the type of the variables.
A type mismatch results in the error message "XXXXX".
.sp
The data items on the sequential file are separated by commas and newlines.
In scanning the file, leading spaces, new lines, tabs, and
carriage returns are ignored. The first character encountered
is assumed to be the state of a new item.
String items need not be enclosed with double quotes, provided
it does not contain spaces, tabs, newlines and commas,
.RM
Microsoft BASIC won't assign values until the end of input statement.
This means that the user has to supply all the information.
.NH 2
LET
.Sy
[LET]<variable>=<expression>
.PU
To assign the value of an expression to a (subscribted) variable.
The type convertions as dictated in chapter 1 apply.
.NH 2
LINE INPUT
.Sy
LINE INPUT [;][<"prompt string">;]<string variable>
.PU
An entire line of input is assigned to the string variable.
See INPUT for the meaning of the <"prompt string"> option.
.NH 2
LINE INPUT [#]
.Sy
LINE INPUT #<file number>,<string variable>
.PU
Read an entire line of text from a sequential file <file number>
and assign it to a string variable.
.NH 2
LSET and RSET
.PU
To be implemented
.NH 2
MID$
.Sy
MID$(<string expr1>,n[,m])=<string expr2>
.PU
To replace a portion of a string with another string value.
The characters of <string expr2> replaces characters in <string expr1>
starting at position n. If m is present, at most m characters are copied,
otherwise all characters are copied.
However, the string obtained never exceeds the length of string expr1.
.NH 2
ON ERROR GOTO
.Sy
ON ERROR GOTO <line number>
.PU
To enable error handling within the BASIC program.
An error may result from arithmetic errors, disk problems, interrupts, or
as a result of the ERROR statement.
After printing an error message the program is continued at the
statements associated with <line number>.
.sp
Error handling is disabled using ON ERROR GOTO 0.
Subsequent errors result in an error message and program termination.
.NH 2
ON...GOSUB and ON ...GOTO
.Sy
ON <expression> GOSUB <list of line numbers>
.br
ON <expression> GOTO <list of line numbers>
.PU
To branch to one of several specified line numbers or subroutines, based
on the result of the <expression>. The list of line numbers are considered
the first, second, etc alternative. Branching to the first occurs when
the expression evaluates to one, to the second alternative on two, etc.
If the value of the expression is zero or greater than the number of alternatives, processing continues at the first statement following the ON..GOTO
(ON GOSUB) statement.
.sp
When the expression results in a negative number the
an "Illegal function call" error occurs.
.sp
BUG If the value of the expression is zero or greater than the number of
alternatives, processing does NOT continue at the first statement
following the ON..GOTO (ON GOSUB) statement.
.NH 2
OPEN
.Sy
OPEN {"i" | "o" | "r" } , [#]<file number> , <file-name>
.PU
To open <file-name> (filename should be quoted) for input/reading or output.
If file is not opened for output it has to be existent, otherwise an
"file not found" error will occur.
.NH 2
OPTION BASE
.Sy
OPTION BASE n
.PU
To declare the lower bound of subsequent array subscripts as either
0 or 1. The default lower bound is zero.
.NH 2
POKE
.Sy
POKE <expr1>,<expr2>
.PU
To poke around in memory. The use of this statement is not recommended,
because it requires full understanding of both
the implementation of the Amsterdam
Compiler Kit and the hardware characteristics.
.NH 2
PRINT
.Sy
PRINT <list of variables and/or constants>
.PU
To print constants or the contents of variables on the terminal-device.
If the variables or constants are seperated by comma's the values will
be printed seperated by tabs.
If the variables or constants are seperated by semi-colon's the values
will be printed without spaces in between.
The new-line generated at the end of the print-statement can be suppressed by
a semi-colon at the end of list of variables or constants.
.NH 2
PRINT USING
.PU
To be implemented
.NH 2
PUT
.PU
To be implemented
.NH 2
RANDOMIZE
.Sy
RANDOMIZE [<expression>]
.PU
To reset the random seed. When the expression is ommitted, the system
will ask for a value between -32768 and 32767.
The random number generator returns the same sequence of values provided
the same seed is used.
.NH 2
READ
.Sy
READ <list of variables>
.PU
To read values from the DATA statements and assign them to variables.
The type of the variables should match to the type of the items being read,
otherwise a "Syntax error" occurs. If all data is read the message "Out of
data" will be displayed.
.NH 2
REM
.Sy
REM <remark>
.PU
To include explantory information in a program.
The REM statements are not executed.
A single quote has the same effect as : REM, which
allows for the inclusion of comment at the end of the line.
.RM
Microsoft BASIC does not allow REM statements as part of
DATA lines.
.NH 2
RESTORE
.Sy
RESTORE [<line number>]
.PU
To allow DATA statements to be re-read from a specific line.
After a RESTORE statement is executed, the next READ accesses
the first item of the DATA statements.
If <line number> is specified, the next READ accesses the first
item in the specified line.
.sp
Note that data statements result in a sequential datafile generated
by the compiler, being read by the read statements.
This data file may be replaced using the operating system functions
with a modified version, provided the same layout of items
(same number of lines and items per line) is used.
.NH 2
STOP
.Sy
STOP
.PU
To terminate the execution of a program and return to the operating system
command interpreter. A STOP statement results in the message "Break in line
???"
.NH 2
SWAP
.Sy
SWAP <variable>,<variable>
.PU
To exchange the values of two variables.
.sp
BUG. Strings cannot be swapped !
.NH 2
TRON/TROFF
.Sy
TRON
.Sy
TROFF
.PU
As an aid in debugging the TRON statement results in a program
listing each line being interpreted. TROFF disables generation of
this code.
.NH 2
WHILE...WEND
.Sy
WHILE <expression>
.....
WEND
.PU
To execute a series of BASIC statements as long as a conditional expression
is true. WHILE...WEND loops may be nested.
.NH 2
WRITE
.Sy
WRITE [<list of expressions>]
.PU
To write data at the terminal in DATA statement layout conventions.
The expressions should be separated by commas.
.NH 2
WRITE #
.Sy
WRITE #<file number> ,<list of expressions>
.PU
To write a sequential data file, being opened with the "O" mode.
The values are being writting using the DATA statements layout conventions.
.bp
.NH
FUNCTIONS
.LP
.IP ABS(X) 25
Returns the absolute value of expression X
.IP ASC(X$) 25
Returns the numeric value of the first character of the string.
If X$ is not initialized an "Illegal function call" error
is returned.
.IP ATN(X) 25
Returns the arctangent of X in radians. Result is in the range
of -pi/2 to pi/2.
.IP CDBL(X) 25
Converts X to a double precision number.
.IP CHR$(X) 25
Converts the integer value X to its ASCII character.
X must be in the range of 0 to 257.
It is used for cursor addressing and generating bel signals.
.IP CINT(X) 25
Converts X to an integer by rounding the fractional portion.
If X is not in the range -32768 to 32767 an "Overflow"
error occurs.
.IP COS(X) 25
Returns the cosine of X in radians.
.IP CSNG(X) 25
Converts X to a single precision number.
.IP CVI(<2-bytes>) 25
Convert two byte string value to integer number.
.IP CVS(<4-bytes>) 25
Convert four byte string value to single precision number.
.IP CVD(<8-bytes>) 25
Convert eight byte string value to double precision number.
.IP EOF[(<file-number>)] 25
Returns -1 (true) if the end of a sequential file has been reached.
.IP EXP(X) 25
Returns e(base of natural logarithm) to the power of X.
X should be less then 10000.0.
.IP FIX(X) 25
Returns the truncated integer part of X. FIX(X) is
equivalent to SGN(X)*INT(ABS(X)).
The major difference between FIX and INT is that FIX does not
return the next lower number for negative X.
.IP HEX$(X) 25
Returns the string which represents the hexadecimal value of
the decimal argument. X is rounded to an integer using CINT
before HEX$ is evaluated.
.IP INT(X) 25
Returns the largest integer <= X.
.IP INP$(X[,[#]Y]) 25
Returns the string of X characters read from the terminal or
the designated file.
.IP LEN(X$) 25
Returns the number of characters in the string X$.
Non printable and blancs are counted too.
.IP LOC(<file\ number>) 25
For sequential files LOC returns
position of the read/write head, counted in number of bytes.
For random files the function returns the record number just
read or written from a GET or PUT statement.
If nothing was read or written 0 is returned.
.IP LOG(X) 25
Returns the natural logarithm of X. X must be greater than zero.
.IP MID$(X,I,[J]) 25
Returns first J characters from string X starting at position I in X.
If J is omitted all characters starting of from position I in X are returned.
.IP MKI$(X) 25
Converts an integer expression to a two-byte string.
.IP MKS$(X) 25
Converts a single precision expression to a four-byte string.
.IP MKD$(X) 25
Converts a double precision expression to a eight-byte string.
.IP OCT$(X) 25
Returns the string which represents the octal value of the decimal
argument. X is rounded to an integer using CINT before OCTS is evaluated.
.IP PEEK(I) 25
Returns the byte read from the indicated memory. (Of limited use
in the context of ACK)
.IP POS(I) 25
Returns the current cursor position. To be implemented.
.IP RIGHT$(X$,I)
Returns the right most I characters of string X$.
If I=0 then the empty string is returned.
.IP RND(X) 25
Returns a random number between 0 and 1. X is a dummy argument.
.IP SGN(X) 25
If X>0 , SGN(X) returns 1.
.br
if X=0, SGN(X) returns 0.
.br
if X<0, SGN(X) returns -1.
.IP SIN(X) 25
Returns the sine of X in radians.
.IP SPACE$(X) 25
Returns a string of spaces length X. The expression
X is rounded to an integer using CINT.
.IP STR$(X)
Returns the string representation value of X.
.IP STRING$(I,J) 25
Returns thes string of length Iwhose characters all
have ASCII code J. (or first character when J is a string)
.IP TAB(I) 25
Spaces to position I on the terminal. If the current
print position is already beyond space I,TAB
goes to that position on the next line.
Space 1 is leftmost position, and the rightmost position
is width minus 1. To be used within PRINT statements only.
.IP TAN(X) 25
Returns the tangent of X in radians. If TAN overflows
the "Overflow" message is displayed.
.IP VAL(X$) 25
Returns the numerical value of string X$.
The VAL function strips leading blanks and tabs from the
argument string.
.bp
.SH
APPENDIX A DIFFERENCES WITH MICROSOFT BASIC
.LP
The following list of Microsoft commands and statements are
not recognized by the compiler.
.DS
SPC
USR
VARPTR
AUTO
CHAIN
CLEAR
CLOAD
COMMON
CONT
CSAVE
DELETE
EDIT
ERASE
FRE
KILL
LIST
LLIST
LOAD
LPRINT
MERGE
NAME
NEW
NULL
RENUM
RESUME
RUN
SAVE
WAIT
WIDTH LPRINT
.DE
Some statements are in the current implementation not available,
but will be soon. These include:
.DS
CALL
DEFUSR
FIELD
GET
INKEY
INPUT$
INSTR$
LEFT$
LSET
RSET
PUT
.DE
.bp
.SH
APPENDIX B RESERVED WORDS IN BASIC-EM
.LP
The following list of words/symbols/names/identifiers are reserved, which
means that they can not be used for variable-names.
.DS
ABS AND ASC AS
ATN AUTO BASE CALL
CDBL CHAIN CHR CINT
CLEAR CLOAD CLOSE COMMON
CONT COS CSNG CSAVE
CVI CVS CVD DATA
DEFINT DEFSNG DEFDBL DEFSTR
DEF DELETE DIM EDIT
ELSE END EOF ERASE
ERROR ERR ERL ELSE
EQV EXP FIELD FIX
FOR FRE GET GOSUB
GOTO HEX IF IMP
INKEY INPUT INP INSTR
INT KILL LEFT LEN
LET LINE LIST LLIST
LOAD LOC LOG LPOS
LPRINT LSET MERGE MID
MKI MKS MKD MOD
NAME NEW NEXT NOT
NULL ON OCT OPEN
OPTION OR OUT PEEK
POKE PRINT POS PUT
RANDOMIZE READ REM RENUM
REN RESTORE RESUME RETURN
RIGHT RND RUN SAVE
STEP SGN SIN SPACE
SPC SQR STOP STRING
STR SWAP TAB TAN
THEN TO TRON TROFF
USING USR VAL VARPTR
WAIT WHILE WEND WIDTH
WRITE XOR
.DE

3
doc/ceg/.distr
View file

@ -1,3 +0,0 @@
proto.make
ceg.ref
ceg.tr

6
doc/ceg/Makefile
View file

@ -1,6 +0,0 @@
PIC=pic
TBL=tbl
REFER=refer
../ceg.doc: ceg.tr ceg.ref
$(PIC) ceg.tr | $(REFER) -e -p ceg.ref | $(TBL) > $@

42
doc/ceg/ceg.ref
View file

@ -1,42 +0,0 @@
%T A Practical Toolkit For Making Compilers
%A A.S. Tanenbaum
%A H. v. Staveren
%A E.G. Keizer
%A J.W. Stevenson
%J Communications of the ACM
%V 26
%N 9
%D September 1983
%T Description of a Machine Architecture for Use with Block Structured Languages
%A A.S. Tanenbuum
%A H. v. Staveren
%A E.G. Keizer
%A J.W. Stevenson
%R IR-81
%I Dept. Mathematics and Computer Science, Vrije Universiteit
%C Amsterdam
%D August 1983
%T EM_CODE(3ACK)
%A ACK Documentation
%I Dept. Mathematics and Computer Science, Vrije Universiteit
%C Amsterdam
%T ACK.OUT(5ACK)
%A ACK Documentation
%I Dept. Mathematics and Computer Science, Vrije Universiteit
%C Amsterdam
%K aout
%T PRINT(3ACK)
%A ACK Documentation
%I Dept. Mathematics and Computer Science, Vrije Universiteit
%C Amsterdam
%T The C Programming Language
%A B.W. Kernighan
%A D.M. Ritchie
%I Prentice-Hall Inc.
%C Englewood Cliffs, New Jersey
%D 1978

1587
doc/ceg/ceg.tr
View file

File diff suppressed because it is too large Load diff

284
doc/ceg/proposal.tr
View file

@ -1,284 +0,0 @@
.TL
Code Expander
.br
(proposal)
.SH
Introduction
.LP
The \fBcode expander\fR, \fBce\fR, is a program that translates EM-code to
objectcode. The main goal is to translate very fast. \fBce\fR is an instance
of the EM_CODE(3L)-interface. During execution of \fBce\fR, \fBce\fR will build
in core a machine independent objectfile ( NEW A.OUT(5L)). With \fBcv\fR or
with routines supplied by the user the machine independent objectcode will
be converted to a machine dependent object code. \fBce\fR needs
information about the targetmachine (e.g. the opcode's). We divide the
information into two parts:
.IP
- The description in assembly instructions of EM-code instructions.
.IP
- The description in objectcode of assembly instructions.
.LP
With these two tables we can make a \fBcode expander generator\fR which
generates a \fBce\fR. It is possible to put the information in one table
but that will probably introduce (propable) more bugs in the table. So we
divide and conquer. With this approach it is also possible to generate
assembly code ( rather yhan objectcode), wich is useful for debugging.
There is of course a link between the two tables, the link
consist of a restriction on the assembly format. Every assembly
instruction must have the following format:
.sp
INSTR ::= LABEL : MNEMONIC [ OPERAND ( "," OPERAND)* ]
.sp
.LP
\fBCeg\fR uses the following algorithm:
.IP \0\0a)
The assembly table will be converted to a (C-)routine assemble().
assemble() gets as argument a string, the assembler instruction,
and can use the MNEMONIC to execute the corresponding action in the
assembly table.
.IP \0\0b)
The routine assemble() can now be used to convert the EM-code table to
a set of C-routines, wich together form an instance of the
EM_CODE(3L).
.SH
The EM-instruction table
.LP
We use the following grammar:
.sp
.TS
center box ;
l.
TABLE ::= (ROW)*
ROW ::= C_instr ( SPECIAL | SIMPLE)
SPECIAL ::= ( CONDITION SIMPLE)+ 'default' SIMPLE
SIMPLE ::= '==>' ACTIONLIST | '::=' ACTIONLIST
ACTIONLIST ::= [ ACTION ( ';' ACTION)* ] '.'
ACTION ::= function-call | assembly-instruction
.TE
.LP
An example for the 8086:
.LP
.DS
C_lxl
$arg1 == 0 ==> "push bp".
$arg1 == 1 ==> "push EM_BSIZE(bp)".
default ==> "mov cx, $arg1";
"mov si, bp";
"1: mov si, EM_BSIZE(si);
"loop 1b"
"push si".
.DE
.sp
Some remarks:
.sp
* The C_instr is a function indentifier in the EM_CODE(3L)-interface.
.LP
* CONDITION is a "boolean" C-expression.
.LP
* The arguments of an EM-instruction can be used in CONDITION and in assembly
instructions. They are referred by $arg\fIi\fR. \fBceg\fR modifies the
arguments as follows:
.IP \0\0-
For local variables at positive offsets it increases this offset by EM_BSIZE
.IP \0\0-
It makes names en labels unique. The user must supply the formats (see mach.h).
.LP
* function-call is allowed to implement e.g. push/pop optimization.
For example:
.LP
.DS
C_adi
$arg1 == 2 ==> combine( "pop ax");
combine( "pop bx");
"add ax, bx";
save( "push ax").
default ==> arg_error( "C_adi", $arg1).
.DE
.LP
* The C-functions called in the EM-instructions table have to use the routine
assemble()/gen?(). "assembler-instr" is in fact assemble( "assembler-instr").
.LP
* \fBceg\fR takes care not only about the conversions of arguments but also
about
changes between segments. There are situation when one doesn't want
conversion of arguments. This can be done by using ::= in stead of ==>.
This is usefull when two C_instr are equivalent. For example:
.IP
C_slu ::= C_sli( $arg1)
.LP
* There are EM-CODE instructions wich are machine independent (e.g. C_open()).
For these EM_CODE instructions \fBceg\fR will generate \fIdefault\fR-
instructions. There is one exception: in the case of C_pro() the tablewriter
has to supply a function prolog().
.LP
* Also the EM-pseudoinstructions C_bss_\fIcstp\fR(), C_hol_\fIcstp\fR(),
C_con_\fIcstp\fR() and C_rom_\fIcstp\fR can be translated automaticly.
\fBceg\fR only has to know how to interpretate string-constants:
.DS
\&..icon $arg2 == 1 ==> gen1( (char) atoi( $arg1))
$arg2 == 2 ==> gen2( atoi( $arg1))
$arg2 == 4 ==> gen4( atol( $arg1))
\&..ucon $arg2 == 1 ==> gen1( (char) atoi( $arg1))
$arg2 == 2 ==> gen2( atoi( $arg1))
$arg2 == 4 ==> gen4( atol( $arg1))
\&..fcon ::= not_implemented( "..fcon")
.DE
.LP
* Still, life can be made easier for the tablewriter; For the routines wich
he/she didn't implement \fBceg\fR will generate a default instruction wich
generates an error-message. \fBceg\fR seems to generate :
.IP
C_xxx ::= not_implemented( "C_xxx")
.SH
The assembly table
.LP
How to map assembly on objectcode.
.LP
Each row in the table consists of two fields, one field for the assembly
instruction, the other field for the corresponding objectcode. The tablewriter
can use the following primitives to generate code for the machine
instructions :
.IP "\0\0gen1( b)\0\0:" 17
generates one byte in de machine independent objectfile.
.IP "\0\0gen2( w)\0\0:" 17
generates one word ( = two bytes), the table writer can change the byte
order by setting the flag BYTES_REVERSED.
.IP "\0\0gen4( l)\0\0:" 17
generates two words ( = four bytes), the table writer can change the word
order by setting the flag WORDS_REVERSED.
.IP "\0\0reloc( n, o, r)\0\0:" 17
generates relocation information for a label ( = name + offset +
relocationtype).
.LP
Besides these primitives the table writer may use his self written
C-functions. This allows the table writer e.g. to write functions to set
bitfields within a byte.
.LP
There are more or less two methods to encode the assembly instructions:
.IP \0\0a)
MNEMONIC and OPERAND('s) are encoded independently of each other. This can be
done when the target machine has an orthogonal instruction set (e.g. pdp-11).
.IP \0\0b)
MNEMONIC and OPERAND('s) together determine the opcode. In this case the
assembler often uses overloading: one MNEMONIC is used for several
different machine-instructions. For example : (8086)
.br
mov ax, bx
.br
mov ax, variable
.br
These instructions have different opcodes.
.LP
As the transformation MNEMONIC-OPCODE is not one to
one the table writer must be allowed to put restrictions on the operands.
This can be done with type declarations. For example:
.LP
.DS
mov dst:REG, src:MEM ==>
gen1( 0x8b);
modRM( op2.reg, op1);
.DE
.DS
mov dst:REG, src:REG ==>
gen1( 0x89);
modRM( op2.reg, op1);
.DE
.LP
modRM() is a function written by the tablewriter and is used to encode
the operands. This frees the table writer of endless typing.
.LP
The table writer has to do the "typechecking" by himself. But typechecking
is almost the same as operand decoding. So it's more efficient to do this
in one function. We now have all the tools to describe the function
assemble().
.IP
assemble() first calls the function
decode_operand() ( by the table writer written), with two arguments: a
string ( the operand) and a
pointer to a struct. The struct is declared by the table writer and must
consist of at least a field called type. ( the other fields in the struct can
be used to remember information about the decoded operand.) Now assemble()
fires a row wich is selected by mapping the MNEMONIC and the type of the
operands.
.br
In the second field of a row there may be references to other
fields in the struct (e.g. op2.reg in the example above).
.LP
We ignored one problem. It's possible when the operands are encoded, that
not everything is known. For example $arg\fIi\fR arguments in the
EM-instruction table get their value at runtime. This problem is solved by
introducing a function eval(). eval() has a string as argument and returns
an arith. The string consists of constants and/or $arg\fIi\fR's and the value
returned by eval() is the value of the string. To encode the $arg\fIi\fR's
in as few bytes as possible the table writer can use the statements %if,
%else and %endif. They can be used in the same manner as #if, #else and
#endif in C and result in a runtime test. An example :
.LP
.DS
-- Some rows of the assembly table
mov dst:REG, src:DATA ==>
%if sfit( eval( src), 8) /* does the immediate-data fit in 1 byte? */
R53( 0x16 , op1.reg);
gen1( eval( src));
%else
R53( 0x17 , op1.reg);
gen2( eval( src));
%endif
.LD
mov dst:REG, src:REG ==>
gen1( 0x8b);
modRM( op1.reg, op2);
.DE
.DS
-- The corresponding part in the function assemble() :
case MNEM_mov :
decode_operand( arg1, &op1);
decode_operand( arg2, &op2);
if ( REG( op1.type) && DATA( op2.type)) {
printf( "if ( sfit( %s, 8)) {\\\\n", eval( src));
R53( 0x16 , op1.reg);
printf( "gen1( %s)\\\\n", eval( arg2));
printf( "}\\\\nelse {\\\\n");
R53( 0x17 , op1.reg);
printf( "gen2( %s)\\\\n", eval( arg2));
printf( "}\\\\n");
}
else if ( REG( op1.type) && REG( op2.type)) {
gen1( 0x8b);
modRM( op1.reg, op2);
}
.DE
.DS
-- Some rows of the right part of the EM-instruction table are translated
-- in the following C-functions.
"mov ax, $arg1" ==>
if ( sfit( w, 8)) { /* w is the actual argument of C_xxx( w) */
gen1( 176); /* R53() */
gen1( w);
}
else {
gen1( 184);
gen2( w);
}
.LD
"mov ax, bx" ==>
gen1( 138);
gen1( 99); /* modRM() */
.DE
.SH
Restrictions
.LP
.IP \0\01)
The EM-instructions C_exc() is not implemented.
.IP \0\03)
All messages are ignored.

12
doc/ceg/proto.make
View file

@ -1,12 +0,0 @@
# $Id$
#PARAMS do not remove this line!
SRC_DIR = $(SRC_HOME)/doc/ceg
PIC=pic
TBL=tbl
REFER=refer
$(TARGET_HOME)/doc/ceg.doc: $(SRC_DIR)/ceg.tr $(SRC_DIR)/ceg.ref
$(PIC) $(SRC_DIR)/ceg.tr | $(REFER) -e -p $(SRC_DIR)/ceg.ref | $(TBL) > $@

276
doc/ceg/prototype.tr
View file

@ -1,276 +0,0 @@
.TL
A prototype Code expander
.NH
Introduction
.PP
A program to be compiled with ACK is first fed into the preprocessor.
The output of the preprocessor goes into the appropiate front end,
whose job it is to produce EM. The EM code generated is
fed into the peephole optimizer, wich scans it with a window of few
instructions, replacing certain inefficient code sequences by better
ones. Following the peephole optimizer follows a backend wich produces
good assembly code. The assembly code goes into the assembler and the objectcode
then goes into the loader/linker, the final component in the pipeline.
.PP
For various applications this scheme is too slow. For example for testing
programs; In this case the program has to be translated fast and the
runtime of the objectcode may be slower. A solution is to build a code
expander ( \fBce\fR) wich translates EM code to objectcode. Of course this
has to
be done automaticly by a code expander generator, but to get some feeling
for the problem we started out to build prototypes.
We built two types of ce's. One wich tranlated EM to assembly, one
wich translated EM to objectcode.
.NH
EM to assembly
.PP
We made one for the 8086 and one for the vax4. These ce's are instances of the
EM_CODE(3L)-interface and produce for a single EM instruction a set
of assembly instruction wich are semantic equivalent.
We implemented in the 8086-ce push/pop-optimalization.
.NH
EM to objectcode
.PP
Instead of producing assembly code we tried to produce vax4-objectcode.
During execution of ce, ce builds in core a machine independent
objectfile ( NEW A.OUT(5L)) and just before dumping the tables this
objectfile is converted to a Berkly 4.2BSD a.out-file. We build two versions;
One with static memory allocation and one with dynamic memory allocation.
If the first one runs out of memory it will give an error message and stop,
the second one will allocate more memory and proceed with producing
objectcode.
.PP
The C-frontend calls the EM_CODE-interface. So after linking the frontend
and the ce we have a pipeline in a program saving a lot of i/o.
It is interesting to compare this C-compiler ( called fcemcom) with "cc -c".
fcemcom1 (the dynamic variant of fcemcom) is tuned in such a way, that
alloc() won't be called.
.NH 2
Compile time
.PP
fac.c is a small program that produces n! ( see below). foo.c is small program
that loops a lot.
.TS
center, box, tab(:);
c | c | c | c | c | c
c | c | n | n | n | n.
compiler : program : real : user : sys : object size
=
fcemcom : sort.c : 31.0 : 17.5 : 1.8 : 23824
fcemcom1 : : 59.0 : 21.2 : 3.3 :
cc -c : : 50.0 : 38.0 : 3.5 : 6788
_
fcemcom : ed.c : 37.0 : 23.6 : 2.3 : 41744
fcemcom1 : : 1.16.0 : 28.3 : 4.6 :
cc -c : : 1.19.0 : 54.8 : 4.3 : 11108
_
fcemcom : cp.c : 4.0 : 2.4 : 0.8 : 4652
fcemcom1 : : 9.0 : 3.0 : 1.0 :
cc -c : : 8.0 : 5.2 : 1.6 : 1048
_
fcemcom : uniq.c : 5.0 : 2.5 : 0.8 : 5568
fcemcom1 : : 9.0 : 2.9 : 0.8 :
cc -c : : 13.0 : 5.4 : 2.0 : 3008
_
fcemcom : btlgrep.c : 24.0 : 7.2 : 1.4 : 12968
fcemcom1 : : 23.0 : 8.1 : 1.2 :
cc -c : : 1.20.0 : 15.3 : 3.8 : 2392
_
fcemcom : fac.c : 1.0 : 0.1 : 0.5 : 216
fecmcom1 : : 2.0 : 0.2 : 0.5 :
cc -c : : 3.0 : 0.7 : 1.3 : 92
_
fcemcom : foo.c : 4.0 : 0.2 : 0.5 : 272
fcemcom1 : : 11.0 : 0.3 : 0.5 :
cc -c : : 7.0 : 0.8 : 1.6 : 108
.TE
.NH 2
Run time
.LP
Is the runtime very bad?
.TS
tab(:), box, center;
c | c | c | c | c
c | c | n | n | n.
compiler : program : real : user : system
=
fcem : sort.c : 22.0 : 17.5 : 1.5
cc : : 5.0 : 2.4 : 1.1
_
fcem : btlgrep.c : 1.58.0 : 27.2 : 4.2
cc : : 12.0 : 3.6 : 1.1
_
fcem : foo.c : 1.0 : 0.7 : 0.1
cc : : 1.0 : 0.4 : 0.1
_
fcem : uniq.c : 2.0 : 0.5 : 0.3
cc : : 1.0 : 0.1 : 0.2
.TE
.NH 2
quality object code
.LP
The runtime is very bad so its interesting to have look at the code which is
produced by fcemcom and by cc -c. I took a program which computes recursively
n!.
.DS
long fac();
main()
{
int n;
scanf( "%D", &n);
printf( "fac is %D\\\\n", fac( n));
}
long fac( n)
int n;
{
if ( n == 0)
return( 1);
else
return( n * fac( n-1));
}
.DE
.br
.br
.br
.br
.LP
"cc -c fac.c" produces :
.DS
fac: tstl 4(ap)
bnequ 7f
movl $1, r0
ret
7f: subl3 $1, 4(ap), r0
pushl r0
call $1, fac
movl r0, -4(fp)
mull3 -4(fp), 4(ap), r0
ret
.DE
.br
.br
.LP
"fcem fac.c fac.o" produces :
.DS
_fac: 0
42: jmp be
48: pushl 4(ap)
4e: pushl $0
54: subl2 (sp)+,(sp)
57: tstl (sp)+
59: bnequ 61
5b: jmp 67
61: jmp 79
67: pushl $1
6d: jmp ba
73: jmp b9
79: pushl 4(ap)
7f: pushl $1
85: subl2 (sp)+,(sp)
88: calls $0,_fac
8f: addl2 $4,sp
96: pushl r0
98: pushl 4(ap)
9e: pushl $4
a4: pushl $4
aa: jsb .cii
b0: mull2 (sp)+,(sp)
b3: jmp ba
b9: ret
ba: movl (sp)+,r0
bd: ret
be: jmp 48
.DE
.NH 1
Conclusions
.PP
comparing "cc -c" with "fcemcom"
.LP
.TS
center, box, tab(:);
c | c s | c | c s
^ | c s | ^ | c s
^ | c | c | ^ | c | c
l | n | n | n | n | n.
program : compile time : object size : runtime
:_::_
: user : sys :: user : sys
=
sort.c : 0.47 : 0.5 : 3.5 : 7.3 : 1.4
_
ed.c : 0.46 : 0.5 : 3.8 : : :
_
cp.c : 0.46 : 0.5 : 4.4 : : :
_
uniq.c : 0.46 : 0.4 : 1.8 : : :
_
btlgrep.c : 0.47 : 0.3 : 5.4 : 7.5 : 3.8
_
fac.c : 0.14 : 0.4 : 2.3 : 1.8 : 1.0
_
foo.c : 0.25 : 0.3 : 2.5 : 5.0 : 1.5
.TE
.PP
The results for fcemcom1 are almost identical; The only thing that changes
is that fcemcom1 is 1.2 slower than fcemcom. ( compile time) This is due to
to an another datastructure . In the static version we use huge array's for
the text- and
data-segment, the relocation information, the symboltable and stringarea.
In the dynamic version we use linked lists, wich makes it expensive to get
and to put a byte on a abritrary memory location. So it is probably better
to use realloc(), because in the most cases there will be enough memory.
.PP
The quality of the objectcode is very bad. The reason is that the frontend
generates bad code and expects the peephole-optimizer to improve the code.
This is also one of the main reasons that the runtime is very bad.
(e.g. the expensive "cii" with arguments 4 and 4 could be deleted.)
So its seems a good
idea to put a new peephole-optimizer between the frontend and the ce.
.PP
Using the peephole optimizer the ce would produce :
.DS
_fac: 0
pushl 4(ap)
tstl (sp)+
beqlu 1f
jmp 3f
1 : pushl $1
jmp 2f
3 : pushl 4(ap)
decl (sp)
calls $0,_fac
addl2 $4,sp
pushl r0
pushl 4(ap)
mull2 (sp)+,(sp)
movl (sp)+,r0
2 : ret
.DE
.PP
Bruce McKenzy already implemented it and made some improvements in the
source code of the ce. The compile-time is two to two and a half times better
and the
size of the objectcode is two to three times bigger.(comparing with "cc -c")
Still we could do better.
.PP
Using peephole- and push/pop-optimization ce could produce :
.DS
_fac: 0
tstl 4(ap)
beqlu 1f
jmp 2f
1 : pushl $1
jmp 3f
2 : decl 4(ap)
calls $0,_fac
addl2 $4,sp
mull3 4(ap), r0, -(sp)
movl (sp)+, r0
3 : ret
.DE
.PP
prof doesn't cooperate, so no profile information.
.PP

1864
doc/cg.doc
View file

File diff suppressed because it is too large Load diff

323
doc/cref.doc
View file

@ -1,323 +0,0 @@
.\" $Header$
.nr ID 4
.de hd
'sp 2
'tl ''-%-''
'sp 3
..
.de fo
'bp
..
.tr ~
. TITLE
.de TL
.sp 15
.ce
\\fB\\$1\\fR
..
. AUTHOR
.de AU
.sp 15
.ce
by
.sp 2
.ce
\\$1
..
. DATE
.de DA
.sp 3
.ce
( Dated \\$1 )
..
. INSTITUTE
.de VU
.sp 3
.ce 4
Wiskundig Seminarium
Vrije Universteit
De Boelelaan 1081
Amsterdam
..
. PARAGRAPH
.de PP
.sp
.ti +\n(ID
..
.nr CH 0 1
. CHAPTER
.de CH
.nr SH 0 1
.bp
.in 0
\\fB\\n+(CH.~\\$1\\fR
.PP
..
. SUBCHAPTER
.de SH
.sp 3
.in 0
\\fB\\n(CH.\\n+(SH.~\\$1\\fR
.PP
..
. INDENT START
.de IS
.sp
.in +\n(ID
..
. INDENT END
.de IE
.in -\n(ID
.sp
..
.de PT
.ti -\n(ID
.ta \n(ID
.fc " @
"\\$1@"\c
.fc
..
. DOUBLE INDENT START
.de DS
.sp
.in +\n(ID
.ll -\n(ID
..
. DOUBLE INDENT END
.de DE
.ll +\n(ID
.in -\n(ID
.sp
..
. EQUATION START
.de EQ
.sp
.nf
..
. EQUATION END
.de EN
.fi
.sp
..
. ITEM
.de IT
.sp
.in 0
\\fB~\\$1\\fR
.ti +5
..
.de CS
.br
~-~\\
..
.br
.fi
.TL "Ack-C reference manual"
.AU "Ed Keizer"
.DA "September 12, 1983"
.VU
.wh 0 hd
.wh 60 fo
.CH "Introduction"
The C frontend included in the Amsterdam Compiler Kit
translates UNIX-V7 C into compact EM code [1].
The language accepted is described in [2] and [3].
This document describes which implementation dependent choices were
made in the Ack-C frontend and
some restrictions and additions.
.CH "The language"
.PP
Under the same heading as used in [2] we describe the
properties of the Ack-C frontend.
.IT "2.2 Identifiers"
External identifiers are unique up to 7 characters and allow
both upper and lower case.
.IT "2.3 Keywords"
The word \fBvoid\fP is also reserved as a keyword.
.IT "2.4.3 Character constants"
The ASCII-mapping is used when a character is converted to an
integer.
.IT "2.4.4 Floating constants"
To prevent loss of precision the compiler does not perform
floating point constant folding.
.IT "2.6 Hardware characteristics"
The size of objects of the several arithmetic types and
pointers depend on the EM-implementation used.
The ranges of the arithmetic types depend on the size used,
the C-frontend assumes two's complement representation for the
integral types.
All sizes are multiples of bytes.
The calling program \fIack\fP[4] passes information about the
size of the types to the compiler proper.
.br
However, a few general remarks must be made:
.sp 1
.IS
.PT (a)
The size of pointers is a multiple of
(or equal to) the size of an \fIint\fP.
.PT (b)
The following relations exist for the sizes of the types
mentioned:
.br
.ti +5
\fIchar<=short<=int<=long\fP
.PT (c)
Objects of type \fIchar\fP use one 8-bit byte of storage,
although several bytes are allocated sometimes.
.PT (d)
All sizes are in multiples of bytes.
.PT (e)
Most EM implementations use 4 bytes for floats and 8 bytes
for doubles, but exceptions to this rule occur.
.IE
.IT "4 What's in a name"
The type \fIvoid\fP is added.
Objects of type void do not exist.
Functions declared as returning void, do not return a value at all.
.IT "6.1 Characters and integers"
Objects of type \fIchar\fP are unsigned and do not cause
sign-extension when converted to \fIint\fP.
The range of characters values is from 0 to 255.
.IT "6.3 Floating and integral"
Floating point numbers are truncated towards zero when
converted to the integral types.
.IT "6.4 Pointers and integers"
When a \fIlong\fP is added to or subtracted from a pointer and
longs are larger then pointers the \fIlong\fP is converted to an
\fIint\fP before the operation is performed.
.IT "7.2 Unary operators"
It is allowed to cast any expression to the type \fIvoid\fP.
.IT "8.2 Type specifiers"
One type is added to the type-specifiers:
.br
.IS
void
.IE
.IT "8.5 Structure and union declarations"
The only type allowed for fields is \fIint\fP.
Fields with exactly the size of \fIint\fP are signed,
all other fields are unsigned.
.br
The size of any single structure must be less then 4096 bytes.
.IT "8.6 Initialization"
Initialization of structures containing bit fields is not
allowed.
There is one restriction when using an 'address expression' to initialize
an integral variable.
The integral variable must have the same size as a pointer.
Conversions altering the size of the address expression are not allowed.
.IT "9.10 Return statement"
Return statements of the form:
.IS
return ;
.IE
are the only form of return statement allowed in a function of type
function returning void.
.IT "10.1 External function definitions"
The total amount for storage used for parameters
in any function must be less then 4096 bytes.
The same holds for the total amount of storage occupied by the
automatic variables declared inside any function.
.sp
Using formal parameters whose size is smaller the the size of an int
is less efficient on several machines.
At procedure entry these parameters are converted from integer to the
declared type, because the compiler doesn't know where the least
significant bytes are stored in the int.
.IT "11.2 Scope of externals"
Most C compilers are rather lax in enforcing the restriction
that only one external definition without the keyword
\fIextern\fP is allowed in a program.
The Ack-C frontend is very strict in this.
The only exception is that declarations of arrays with a
missing first array bounds expression are regarded to have an
explicit keyword \fIextern\fP.
.IT "14.4 Explicit pointer conversions"
Pointers may be larger the ints, thus assigning a pointer to an
int and back will not always result in the same pointer.
The process mentioned above works with integrals
of the same size or larger as pointers in all EM implementations
having such integrals.
When converting pointers to an integral type or vice-versa,
the pointers is seen as an unsigned int.
.br
EM guarantees that any object can be placed at a word boundary,
this allows the C-programs to use \fIint\fP pointers
as pointers to objects of any type not smaller than an \fIint\fP.
.CH "Frontend options"
The C-frontend has a few options, these are controlled
by flags:
.IS
.PT -V
This flag is followed by a sequence of letters each followed by
positive integers. Each letter indicates a
certain type, the integer following it specifies the size of
objects of that type. One letter indicates the wordsize used.
.IS
.sp 1
.TS
center tab(:);
l l16 l l.
letter:type:letter:type
w:wordsize:i:int
s:short:l:long
f:float:d:double
p:pointer::
.TE
.sp 1
All existing implementations use an integer size equal to the
wordsize.
.IE
The calling program \fIack\fP[4] provides the frontend with
this flag, with values depending on the machine used.
.sp 1
.PT -l
The frontend normally generates code to keep track of the line
number and source file name at runtime for debugging purposes.
Currently a pointer to a
string containing the filename is stored at a fixed place in
memory at each function
entry and the line number at the start of every expression.
At the return from a function these memory locations are not reset to
the values they had before the call.
Most library routines do not use this feature and thus do not
ruin the current line number and filename when called.
However, you are really unlucky when your program crashes due
to a bug in such a library function, because the line number
and filename do not indicate that something went wrong inside
the library function.
.br
Providing the flag -l to the frontend tells it not to generate
the code updating line number and file name.
This is, for example, used when translating the stdio library.
.br
When the \fIack\fP[4] is called with the -L flag it provides
the frontend with this flag.
.sp 1
.PT -Xp
When this flag is present the frontend generates a call to
the function \fBprocentry\fP at each function entry and a
call to \fBprocexit\fP at each function exit.
Both functions are provided with one parameter,
a pointer to a string containing the function name.
.br
When \fIack\fP is called with the -p flag it provides the
frontend with this flag.
.IE
.CH References
.IS
.PT [1]
A.S. Tanenbaum, Hans van Staveren, Ed Keizer and Johan
Stevenson \fIDescription of a machine architecture for use with
block structured languages\fP Informatica report IR-81.
.sp 1
.PT [2]
B.W. Kernighan and D.M. Ritchie, \fIThe C Programming
language\fP, Prentice-Hall, 1978
.PT [3]
D.M. Ritchie, \fIC Reference Manual\fP
.sp
.PT [4]
UNIX manual ack(I).

629
doc/crefman.doc
View file

@ -1,629 +0,0 @@
\." $Id$
.\" eqn crefman.doc | troff -ms
.EQ
delim $$
.EN
.RP
.TL
ACK/CEM Compiler
.br
Reference Manual
.AU
Erik H. Baalbergen
.AI
Department of Mathematics and Computer Science
Vrije Universiteit
Amsterdam
The Netherlands
.AB no
.AE
.NH
C Language
.PP
This section discusses the extensions to and deviations from the C language,
as described in [1].
The issues are numbered according to the reference manual.
.SH
2.2 Identifiers
.PP
Upper and lower case letters are different.
The number of significant letters
is 32 by default, but may be set to another value using the \fB\-M\fP option.
The identifier length should be set according to the rest of the compilation
programs.
.SH
2.3 Keywords
.SH
\f(CWasm\fP
.PP
The keyword \f(CWasm\fP
is recognized.
However, the statement
.DS
.ft CW
asm(string);
.ft R
.DE
is skipped, while a warning is given.
.SH
\f(CWenum\fP
.PP
The \f(CWenum\fP keyword is recognized and interpreted.
.SH
\f(CWentry\fP, \f(CWfortran\fP
.PP
The words \f(CWentry\fP and \f(CWfortran\fP
are reserved under the restricted option.
The words are not interpreted by the compiler.
.SH
2.4.1 Integer Constants
.PP
The type of an integer constant is the first of the corresponding list
in which its value can be represented. Decimal: \f(CWint, long, unsigned long\fP;
octal or hexadecimal: \f(CWint, unsigned, long, unsigned long\fP; suffixed by
the letter L or l: \f(CWlong, unsigned long\fP.
.SH
2.4.3 Character Constants
.PP
A character constant is a sequence of 1 up to \f(CWsizeof(int)\fP characters
enclosed in single quotes.
The value of a character constant '$c sub 1 c sub 2 ... c sub n$'
is $d sub n + M \(mu d sub {n - 1} + ... + M sup {n - 1} \(mu d sub 2 + M sup n \(mu d sub 1$,
where M is 1 + maximum unsigned number representable in an \f(CWunsigned char\fP,
and $d sub i$ is the signed value (ASCII)
of character $c sub i$.
.SH
2.4.4 Floating Constants
.PP
The compiler does not support compile-time floating point arithmetic.
.SH
2.6 Hardware characteristics
.PP
The compiler is capable of producing EM code for machines with the following
properties
.IP \(bu
a \f(CWchar\fP is 8 bits
.IP \(bu
the size of \f(CWint\fP is equal to the word size
.IP \(bu
the size of \f(CWshort\fP may not exceed the size of \f(CWint\fP
.IP \(bu
the size of \f(CWint\fP may not exceed the size of \f(CWlong\fP
.IP \(bu
the size of pointers is equal to the size of either \f(CWshort\fP, \f(CWint\fP
or \f(CWlong\fP
.LP
.SH
4 What's in a name?
.SH
\f(CWchar\fP
.PP
Objects of type \f(CWchar\fP are taken to be signed.
The combination \f(CWunsigned char\fP is legal.
.SH
\f(CWunsigned\fP
.PP
The type combinations \f(CWunsigned char\fP, \f(CWunsigned short\fP and
\f(CWunsigned long\fP are supported.
.SH
\f(CWenum\fP
.PP
The data type \f(CWenum\fP is implemented as described
in \fIRecent Changes to C\fP (see appendix A).
.I Cem
treats enumeration variables as if they were \f(CWint\fP.
.SH
\f(CWvoid\fP
.PP
Type \f(CWvoid\fP is implemented.
The type specifies an empty set of values, which takes no storage space.
.SH
\fRFundamental types\fP
.PP
The names of the fundamental types can be redefined by the user, using
\f(CWtypedef\fP.
.SH
7 Expressions
.PP
The order of evaluation of expressions depends on the complexity of the
subexpressions.
In case of commutative operations, the most complex subexpression is
evaluated first.
Parameter lists are evaluated from right to left.
.SH
7.2 Unary operators
.PP
The type of a \f(CWsizeof\fP expression is \f(CWunsigned int\fP.
.SH
7.13 Conditional operator
.PP
Both the second and the third expression in a conditional expression may
include assignment operators.
They may be structs or unions.
.SH
7.14 Assignment operators
.PP
Structures may be assigned, passed as arguments to functions, and returned
by functions.
The types of operands taking part must be the same.
.SH
8.2 Type specifiers
.PP
The combinations \f(CWunsigned char\fP, \f(CWunsigned short\fP
and \f(CWunsigned long\fP are implemented.
.SH
8.5 Structure and union declarations
.PP
Fields of any integral type, either signed or unsigned,
are supported, as long as the type fits in a word on the target machine.
.PP
Fields are left adjusted by default; the first field is put into the left
part of a word, the next one on the right side of the first one, etc.
The \f(CW-Vr\fP option in the call of the compiler
causes fields to be right adjusted within a machine word.
.PP
The tags of structs and unions occupy a different name space from that of
variables and that of member names.
.SH
9.7 Switch statement
.PP
The type of \fIexpression\fP in
.DS
.ft CW
\f(CWswitch (\fP\fIexpression\fP\f(CW)\fP \fIstatement\fP
.ft
.DE
must be integral.
A warning is given under the restricted option if the type is \f(CWlong\fP.
.SH
10 External definitions
.PP
See [4] for a discussion on this complicated issue.
.SH
10.1 External function definitions
.PP
Structures may be passed as arguments to functions, and returned
by functions.
.SH
11.1 Lexical scope
.PP
Typedef names may be redeclared like any other variable name; the ice mentioned
in \(sc11.1 is walked correctly.
.SH
12 Compiler control lines
.PP
Lines which do not occur within comment, and with \f(CW#\fP as first
character, are interpreted as compiler control line.
There may be an arbitrary number of spaces, tabs and comments (collectively
referred as \fIwhite space\fP) following the \f(CW#\fP.
Comments may contain newline characters.
Control lines with only white space between the \f(CW#\fP and the line separator
are skipped.
.PP
The #\f(CWinclude\fP, #\f(CWifdef\fP, #\f(CWifndef\fP, #\f(CWundef\fP, #\f(CWelse\fP and
#\f(CWendif\fP control lines and line directives consist of a fixed number of
arguments.
The list of arguments may be followed an arbitrary sequence of characters,
in which comment is interpreted as such.
(I.e., the text between \f(CW/*\fP and \f(CW*/\fP is skipped, regardless of
newlines; note that commented-out lines beginning with \f(CW#\fP are not
considered to be control lines.)
.SH
12.1 Token replacement
.PP
The replacement text of macros is taken to be a string of characters, in which
an identifier may stand for a formal parameter, and in which comment is
interpreted as such.
Comments and newline characters, preceeded by a backslash, in the replacement
text are replaced by a space character.
.PP
The actual parameters of a macro are considered tokens and are
balanced with regard to \f(CW()\fP, \f(CW{}\fP and \f(CW[]\fP.
This prevents the use of macros like
.DS
.ft CW
CTL([)
.ft
.DE
.PP
Formal parameters of a macro must have unique names within the formal-parameter
list of that macro.
.PP
A message is given at the definition of a macro if the macro has
already been #\f(CWdefined\fP, while the number of formal parameters differ or
the replacement texts are not equal (apart from leading and trailing
white space).
.PP
Recursive use of macros is detected by the compiler.
.PP
Standard #\f(CWdefined\fP macros are
.DS
\f(CW__FILE__\fP name of current input file as string constant
\f(CW__DATE__\fP curent date as string constant; e.g. \f(CW"Tue Wed 2 14:45:23 1986"\fP
\f(CW__LINE__\fP current line number as an integer
.DE
.PP
No message is given if \fIidentifier\fP is not known in
.DS
.ft CW
#undef \fIidentifier\fP
.ft
.DE
.SH
12.2 File inclusion
.PP
A newline character is appended to each file which is included.
.SH
12.3 Conditional compilation
.PP
The #\f(CWif\fP, #\f(CWifdef\fP and #\f(CWifndef\fP control lines may be followed
by an arbitrary number of
.DS
.ft CW
#elif \fIconstant-expression\fP
.ft
.DE
control lines, before the corresponding #\f(CWelse\fP or #\f(CWendif\fP
is encountered.
The construct
.DS
.ft CW
#elif \fIconstant-expression\fP
some text
#endif /* corresponding to #elif */
.ft
.DE
is equivalent to
.DS
.ft CW
#else
#if \fIconstant-expression\fP
some text
#endif /* corresponding to #if */
#endif /* corresponding to #else */
.ft
.DE
.PP
The \fIconstant-expression\fP in #\f(CWif\fP and #\f(CWelif\fP control lines
may contain the construction
.DS
.ft CW
defined(\fIidentifier\fP)
.ft
.DE
which is replaced by \f(CW1\fP, if \fIidentifier\fP has been #\f(CWdefined\fP,
and by \f(CW0\fP, if not.
.PP
Comments in skipped lines are interpreted as such.
.SH
12.4 Line control
.PP
Line directives may occur in the following forms:
.DS
.ft CW
#line \fIconstant\fP
#line \fIconstant\fP "\fIfilename\fP"
#\fIconstant\fP
#\fIconstant\fP "\fIfilename\fP"
.ft
.DE
Note that \fIfilename\fP is enclosed in double quotes.
.SH
14.2 Functions
.PP
If a pointer to a function is called, the function the pointer points to
is called instead.
.SH
15 Constant expressions
.PP
The compiler distinguishes the following types of integral constant expressions
.IP \(bu
field-width specifier
.IP \(bu
case-entry specifier
.IP \(bu
array-size specifier
.IP \(bu
global variable initialization value
.IP \(bu
enum-value specifier
.IP \(bu
truth value in \f(CW#if\fP control line
.LP
.PP
Constant integral expressions are compile-time evaluated while an effort
is made to report overflow.
Constant floating expressions are not compile-time evaluated.
.NH
Compiler flags
.IP \fB\-C\fR
Run the preprocessor stand-alone while maintaining the comments.
Line directives are produced whenever needed.
.IP \fB\-D\fP\fIname\fP=\fIstring-of-characters\fP
.br
Define \fIname\fR as macro with \fIstring-of-characters\fR as
replacement text.
.IP \fB\-D\fP\fIname\fP
.br
Equal to \fB\-D\fP\fIname\fP\fB=1\fP.
.IP \fB\-E\fP
Run the preprocessor stand alone, i.e.,
list the sequence of input tokens and delete any comments.
Line directives are produced whenever needed.
.IP \fB\-I\fIpath\fR
.br
Prepend \fIpath\fR to the list of include directories.
To put the directories "include", "sys/h" and "util/h" into the
include directory list in that order, the user has to specify
.DS
.ft CW
-Iinclude -Isys/h -Iutil/h
.ft R
.DE
An empty \fIpath\fP causes the standard include
directory (usually \f(CW/usr/include\fP) to be forgotten.
.IP \fB\-M\fP\fIn\fP
.br
Set maximum significant identifier length to \fIn\fP.
.IP \fB\-n\fP
Suppress EM register messages.
The user-declared variables are not stored into registers on the target
machine.
.IP \fB\-p\fP
Generate the EM \fBfil\fP and \fBlin\fP instructions in order to enable
an interpreter to keep track of the current location in the source code.
.IP \fB\-P\fP
Equivalent with \fB\-E\fP, but without line directives.
.IP \fB\-R\fP
Interpret the input as restricted C (according to the language as
described in [1]).
.IP \fB\-T\fP\fIpath\fP
.br
Create temporary files, if necessary, in directory \fIpath\fP.
.IP \fB\-U\fP\fIname\fP
.br
Get rid of the compiler-predefined macro \fIname\fP, i.e.,
consider
.DS
.ft CW
#undef \fIname\fP
.ft R
.DE
to appear in the beginning of the file.
.IP \fB\-V\fIcm\fR.\fIn\fR,\ \fB\-V\fIcm\fR.\fIncm\fR.\fIn\fR\ ...
.br
Set the size and alignment requirements.
The letter \fIc\fR indicates the simple type, which is one of
\fBs\fR(short), \fBi\fR(int), \fBl\fR(long), \fBf\fR(float), \fBd\fR(double)
or \fBp\fR(pointer).
If \fIc\fR is \fBS\fP or \fBU\fP, then \fIn\fP is taken to be the initial
alignment of structs or unions, respectively.
The effective alignment of a struct or union is the least common multiple
of the initial struct/union alignment and the alignments of its members.
The \fIm\fR parameter can be used to specify the length of the type (in bytes)
and the \fIn\fR parameter for the alignment of that type.
Absence of \fIm\fR or \fIn\fR causes the default value to be retained.
To specify that the bitfields should be right adjusted instead of the
default left adjustment, specify \fBr\fR as \fIc\fR parameter.
.IP \fB\-w\fR
Suppress warning messages
.IP \fB\-\-\fIcharacter\fR
.br
Set debug-flag \fIcharacter\fP.
This enables some special features offered by a debug and develop version of
the compiler.
Some particular flags may be recognized, others may have surprising effects.
.RS
.IP \fBd\fP
Generate a dependency graph, reflecting the calling structure of functions.
Lines of the form
.DS
.ft CW
DFA: \fIcalling-function\fP: \fIcalled-function\fP
.ft
.DE
are generated whenever a function call is encountered.
.IP \fBf\fP
Dump whole identifier table, including macros and reserved words.
.IP \fBh\fP
Supply hash-table statistics.
.IP \fBi\fP
Print names of included files.
.IP \fBm\fP
Supply statistics concerning the memory allocation.
.IP \fBt\fP
Dump table of identifiers.
.IP \fBu\fP
Generate extra statistics concerning the predefined types and identifiers.
Works in combination with \fBf\fP or \fBt\fP.
.IP \fBx\fP
Print expression trees in human-readable format.
.RE
.LP
.SH
References
.IP [1]
Brian W. Kernighan, Dennis M. Ritchie,
.I
The C Programming Language
.R
.IP [2]
L. Rosler,
.I
Draft Proposed Standard - Programming Language C,
.R
ANSI X3J11 Language Subcommittee
.IP [3]
Erik H. Baalbergen, Dick Grune, Maarten Waage,
.I
The CEM Compiler,
.R
Informatica Manual IM-4, Dept. of Mathematics and Computer Science, Vrije
Universiteit, Amsterdam, The Netherlands
.IP [4]
Erik H. Baalbergen,
.I
Modeling global declarations in C,
.R
internal paper
.LP
.bp
.SH
Appendix A - Enumeration Type
.PP
The syntax is
.sp
.RS
.I enum-specifier :
.RS
\&\f(CWenum\fP { \fIenum-list\fP }
.br
\&\f(CWenum\fP \fIidentifier\fP { \fIenum-list\fP }
.br
\&\f(CWenum\fP \fIidentifier\fP
.RE
.sp
\&\fIenum-list\fP :
.RS
\&\fIenumerator\fP
.br
\&\fIenum-list\fP , \fIenumerator\fP
.RE
.sp
\&\fIenumerator\fP :
.RS
\&\fIidentifier\fP
.br
\&\fIidentifier\fP = \fIconstant-expression\fP
.RE
.sp
.RE
The identifier has the same role as the structure tag in a struct specification.
It names a particular enumeration type.
.PP
The identifiers in the enum-list are declared as constants, and may appear
whenever constants are required.
If no enumerators with
.B =
appear, then the values of the constants begin at 0 and increase by 1 as the
declaration is read from left to right.
An enumerator with
.B =
gives the associated identifier the value indicated; subsequent identifiers
continue the progression from the assigned value.
.PP
Enumeration tags and constants must all be distinct, and, unlike structure
tags and members, are drawn from the same set as ordinary identifiers.
.PP
Objects of a given enumeration type are regarded as having a type distinct
from objects of all other types.
.bp
.SH
Appendix B: C grammar in LL(1) form
.PP
The \fBbold-faced\fP and \fIitalicized\fP tokens represent terminal symbols.
.vs 16
.nf
\fBexternal definitions\fP
program: external-definition*
external-definition: ext-decl-specifiers [declarator [function | non-function] | '\fB;\fP'] | asm-statement
ext-decl-specifiers: decl-specifiers?
non-function: initializer? ['\fB,\fP' init-declarator]* '\fB;\fP'
function: declaration* compound-statement
.sp 1
\fBdeclarations\fP
declaration: decl-specifiers init-declarator-list? '\fB;\fP'
decl-specifiers: other-specifier+ [single-type-specifier other-specifier*]? | single-type-specifier other-specifier*
other-specifier: \fBauto\fP | \fBstatic\fP | \fBextern\fP | \fBtypedef\fP | \fBregister\fP | \fBshort\fP | \fBlong\fP | \fBunsigned\fP
type-specifier: decl-specifiers
single-type-specifier: \fItype-identifier\fP | struct-or-union-specifier | enum-specifier
init-declarator-list: init-declarator ['\fB,\fP' init-declarator]*
init-declarator: declarator initializer?
declarator: primary-declarator ['\fB(\fP' formal-list ? '\fB)\fP' | arrayer]* | '\fB*\fP' declarator
primary-declarator: identifier | '\fB(\fP' declarator '\fB)\fP'
arrayer: '\fB[\fP' constant-expression? '\fB]\fP'
formal-list: formal ['\fB,\fP' formal]*
formal: identifier
enum-specifier: \fBenum\fP [enumerator-pack | identifier enumerator-pack?]
enumerator-pack: '\fB{\fP' enumerator ['\fB,\fP' enumerator]* '\fB,\fP'? '\fB}\fP'
enumerator: identifier ['\fB=\fP' constant-expression]?
struct-or-union-specifier: [ \fBstruct\fP | \fBunion\fP] [ struct-declaration-pack | identifier struct-declaration-pack?]
struct-declaration-pack: '\fB{\fP' struct-declaration+ '\fB}\fP'
struct-declaration: type-specifier struct-declarator-list '\fB;\fP'?
struct-declarator-list: struct-declarator ['\fB,\fP' struct-declarator]*
struct-declarator: declarator bit-expression? | bit-expression
bit-expression: '\fB:\fP' constant-expression
initializer: '\fB=\fP'? initial-value
cast: '\fB(\fP' type-specifier abstract-declarator '\fB)\fP'
abstract-declarator: primary-abstract-declarator ['\fB(\fP' '\fB)\fP' | arrayer]* | '\fB*\fP' abstract-declarator
primary-abstract-declarator: ['\fB(\fP' abstract-declarator '\fB)\fP']?
.sp 1
\fBstatements\fP
statement:
expression-statement
| label '\fB:\fP' statement
| compound-statement
| if-statement
| while-statement
| do-statement
| for-statement
| switch-statement
| case-statement
| default-statement
| break-statement
| continue-statement
| return-statement
| jump
| '\fB;\fP'
| asm-statement
;
expression-statement: expression '\fB;\fP'
label: identifier
if-statement: \fBif\fP '\fB(\fP' expression '\fB)\fP' statement [\fBelse\fP statement]?
while-statement: \fBwhile\fP '\fB(\fP' expression '\fB)\fP' statement
do-statement: \fBdo\fP statement \fBwhile\fP '\fB(\fP' expression '\fB)\fP' '\fB;\fP'
for-statement: \fBfor\fP '\fB(\fP' expression? '\fB;\fP' expression? '\fB;\fP' expression? '\fB)\fP' statement
switch-statement: \fBswitch\fP '\fB(\fP' expression '\fB)\fP' statement
case-statement: \fBcase\fP constant-expression '\fB:\fP' statement
default-statement: \fBdefault\fP '\fB:\fP' statement
break-statement: \fBbreak\fP '\fB;\fP'
continue-statement: \fBcontinue\fP '\fB;\fP'
return-statement: \fBreturn\fP expression? '\fB;\fP'
jump: \fBgoto\fP identifier '\fB;\fP'
compound-statement: '\fB{\fP' declaration* statement* '\fB}\fP'
asm-statement: \fBasm\fP '\fB(\fP' \fIstring\fP '\fB)\fP' '\fB;\fP'
.sp 1
\fBexpressions\fP
initial-value: assignment-expression | initial-value-pack
initial-value-pack: '\fB{\fP' initial-value-list '\fB}\fP'
initial-value-list: initial-value ['\fB,\fP' initial-value]* '\fB,\fP'?
primary: \fIidentifier\fP | constant | \fIstring\fP | '\fB(\fP' expression '\fB)\fP'
secundary: primary [index-pack | parameter-pack | selection]*
index-pack: '\fB[\fP' expression '\fB]\fP'
parameter-pack: '\fB(\fP' parameter-list? '\fB)\fP'
selection: ['\fB.\fP' | '\fB\->\fP'] identifier
parameter-list: assignment-expression ['\fB,\fP' assignment-expression]*
postfixed: secundary postop?
unary: cast unary | postfixed | unop unary | size-of
size-of: \fBsizeof\fP [cast | unary]
binary-expression: unary [binop binary-expression]*
conditional-expression: binary-expression ['\fB?\fP' expression '\fB:\fP' assignment-expression]?
assignment-expression: conditional-expression [asgnop assignment-expression]?
expression: assignment-expression ['\fB,\fP' assignment-expression]*
unop: '\fB*\fP' | '\fB&\fP' | '\fB\-\fP' | '\fB!\fP' | '\fB~ \fP' | '\fB++\fP' | '\fB\-\-\fP'
postop: '\fB++\fP' | '\fB\-\-\fP'
multop: '\fB*\fP' | '\fB/\fP' | '\fB%\fP'
addop: '\fB+\fP' | '\fB\-\fP'
shiftop: '\fB<<\fP' | '\fB>>\fP'
relop: '\fB<\fP' | '\fB>\fP' | '\fB<=\fP' | '\fB>=\fP'
eqop: '\fB==\fP' | '\fB!=\fP'
arithop: multop | addop | shiftop | '\fB&\fP' | '\fB^ \fP' | '\fB|\fP'
binop: arithop | relop | eqop | '\fB&&\fP' | '\fB||\fP'
asgnop: '\fB=\fP' | '\fB+\fP' '\fB=\fP' | '\fB\-\fP' '\fB=\fP' | '\fB*\fP' '\fB=\fP' | '\fB/\fP' '\fB=\fP' | '\fB%\fP' '\fB=\fP'
| '\fB<<\fP' '\fB=\fP' | '\fB>>\fP' '\fB=\fP' | '\fB&\fP' '\fB=\fP' | '\fB^ \fP' '\fB=\fP' | '\fB|\fP' '\fB=\fP'
| '\fB+=\fP' | '\fB\-=\fP' | '\fB*=\fP' | '\fB/=\fP' | '\fB%=\fP'
| '\fB<<=\fP' | '\fB>>=\fP' | '\fB&=\fP' | '\fB^=\fP' | '\fB|=\fP'
constant: \fIinteger\fP | \fIfloating\fP
constant-expression: assignment-expression
identifier: \fIidentifier\fP | \fItype-identifier\fP
.fi

18
doc/ego/.distr
View file

@ -1,18 +0,0 @@
proto.make
bo
ca
cf
cj
cs
ic
il
intro
lv
ov
ra
refs.gen
refs.opt
refs.stat
sp
sr
ud

55
doc/ego/Makefile
View file

@ -1,55 +0,0 @@
REFS=-p refs.opt -p refs.stat -p refs.gen
INTRO=intro/intro?
OV=ov/ov?
IC=ic/ic?
CF=cf/cf?
IL=il/il?
SR=sr/sr?
CS=cs/cs?
SP=sp/sp?
UD=ud/ud?
LV=lv/lv?
CJ=cj/cj?
BO=bo/bo?
RA=ra/ra?
CA=ca/ca?
EGO=$(INTRO) $(OV) $(IC) $(CF) $(IL) $(SR) $(CS) $(SP) $(CJ) $(BO) \
$(UD) $(LV) $(RA) $(CA)
REFER=refer
TROFF=troff
TBL=tbl
TARGET=-Tlp
../ego.doc: refs.opt refs.stat refs.gen intro/head intro/tail $(EGO)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(EGO) intro/tail | $(TBL) > ../ego.doc
ego.f: refs.opt refs.stat refs.gen intro/head intro/tail $(EGO)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(EGO) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ego.f
intro.f: refs.opt refs.stat refs.gen intro/head intro/tail $(INTRO)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(INTRO) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > intro.f
ov.f: refs.opt refs.stat refs.gen intro/head intro/tail $(OV)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(OV) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ov.f
ic.f: refs.opt refs.stat refs.gen intro/head intro/tail $(IC)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(IC) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ic.f
cf.f: refs.opt refs.stat refs.gen intro/head intro/tail $(CF)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(CF) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > cf.f
il.f: refs.opt refs.stat refs.gen intro/head intro/tail $(IL)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(IL) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > il.f
sr.f: refs.opt refs.stat refs.gen intro/head intro/tail $(SR)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(SR) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > sr.f
cs.f: refs.opt refs.stat refs.gen intro/head intro/tail $(CS)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(CS) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > cs.f
sp.f: refs.opt refs.stat refs.gen intro/head intro/tail $(SP)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(SP) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > sp.f
cj.f: refs.opt refs.stat refs.gen intro/head intro/tail $(CJ)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(CJ) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > cj.f
bo.f: refs.opt refs.stat refs.gen intro/head intro/tail $(BO)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(BO) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > bo.f
ud.f: refs.opt refs.stat refs.gen intro/head intro/tail $(UD)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(UD) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ud.f
lv.f: refs.opt refs.stat refs.gen intro/head intro/tail $(LV)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(LV) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > lv.f
ra.f: refs.opt refs.stat refs.gen intro/head intro/tail $(RA)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(RA) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ra.f
ca.f: refs.opt refs.stat refs.gen intro/head intro/tail $(CA)
$(REFER) -sA+T -l4,2 $(REFS) intro/head $(CA) intro/tail | $(TBL) | $(TROFF) $(TARGET) -ms > ca.f

1
doc/ego/bo/.distr
View file

@ -1 +0,0 @@
bo1

162
doc/ego/bo/bo1
View file

@ -1,162 +0,0 @@
.bp
.NH 1
Branch Optimization
.NH 2
Introduction
.PP
The Branch Optimization phase (BO) performs two related
(branch) optimizations.
.NH 3
Fusion of basic blocks
.PP
If two basic blocks B1 and B2 have the following properties:
.DS
SUCC(B1) = {B2}
PRED(B2) = {B1}
.DE
then B1 and B2 can be combined into one basic block.
If B1 ends in an unconditional jump to the beginning of B2, this
jump can be eliminated,
hence saving a little execution time and object code size.
This technique can be used to eliminate some deficiencies
introduced by the front ends (for example, the "C" front end
translates switch statements inefficiently due to its one pass nature).
.NH 3
While-loop optimization
.PP
The straightforward way to translate a while loop is to
put the test for loop termination at the beginning of the loop.
.DS
while cond loop \kyLAB1: \kxTest cond
body of the loop --->\h'|\nxu'Branch On False To LAB2
end loop\h'|\nxu'code for body of loop
\h'|\nxu'Branch To LAB1
\h'|\nyu'LAB2:
Fig. 10.1 Example of Branch Optimization
.DE
If the condition fails at the Nth iteration, the following code
gets executed (dynamically):
.DS
.TS
l l l.
N * conditional branch (which fails N-1 times)
N-1 * unconditional branch
N-1 * body of the loop
.TE
.DE
An alternative translation is:
.DS
Branch To LAB2
LAB1:
code for body of loop
LAB2:
Test cond
Branch On True To LAB1
.DE
This translation results in the following profile:
.DS
.TS
l l l.
N * conditional branch (which succeeds N-1 times)
1 * unconditional branch
N-1 * body of the loop
.TE
.DE
So the second translation will be significantly faster if N >> 2.
If N=2, execution time will be slightly increased.
On the average, the program will be speeded up.
Note that the code sizes of the two translations will be the same.
.NH 2
Implementation
.PP
The basic block fusion technique is implemented
by traversing the control flow graph of a procedure,
looking for basic blocks B with only one successor (S).
If one is found, it is checked if S has only one predecessor
(which has to be B).
If so, the two basic blocks can in principle be combined.
However, as one basic block will have to be moved,
the textual order of the basic blocks will be altered.
This reordering causes severe problems in the presence
of conditional jumps.
For example, if S ends in a conditional branch,
the basic block that comes textually next to S must stay
in that position.
So the transformation in Fig. 10.2 is illegal.
.DS
.TS
l l l l l.
LAB1: S1 LAB1: S1
BRA LAB2 S2
... --> BEQ LAB3
LAB2: S2 ...
BEQ LAB3 S3
S3
.TE
Fig. 10.2 An illegal transformation of Branch Optimization
.DE
If B is moved towards S the same problem occurs if the block before B
ends in a conditional jump.
The problem could be solved by adding one extra branch,
but this would reduce the gains of the optimization to zero.
Hence the optimization will only be done if the block that
follows S (in the textual order) is not a successor of S.
This condition assures that S does not end in a conditional branch.
The condition always holds for the code generated by the "C"
front end for a switch statement.
.PP
After the transformation has been performed,
some attributes of the basic blocks involved (such as successor and
predecessor sets and immediate dominator) must be recomputed.
.PP
The while-loop technique is applied to one loop at a time.
The list of basic blocks of the loop is traversed to find
a block B that satisfies the following conditions:
.IP 1.
the textually next block to B is not part of the loop
.IP 2.
the last instruction of B is an unconditional branch;
hence B has only one successor, say S
.IP 3.
the textually next block of B is a successor of S
.IP 4.
the last instruction of S is a conditional branch
.LP
If such a block B is found, the control flow graph is changed
as depicted in Fig. 10.3.
.DS
.ft 5
| |
| v
v |
|-----<------| ----->-----|
____|____ | |
| | | |-------| |
| S1 | | | v |
| Bcc | | | .... |
|--| | | | |
| --------- | | ----|---- |
| | | | | |
| .... ^ | | S2 | |
| | | | | |
| --------- | | | | |
v | | | ^ --------- |
| | S2 | | | | |
| | BRA | | | |-----<-----
| | | | | v
| --------- | | ____|____
| | | | | |
| ------>------ | | S1 |
| | | Bnn |
|-------| | | |
| | ----|----
v | |
|----<--|
|
v
.ft R
Fig. 10.3 Transformation of the CFG by Branch Optimization
.DE

1
doc/ego/ca/.distr
View file

@ -1 +0,0 @@
ca1

65
doc/ego/ca/ca1
View file

@ -1,65 +0,0 @@
.bp
.NH 1
Compact assembly generation
.NH 2
Introduction
.PP
The "Compact Assembly generation phase" (CA) transforms the
intermediate code of the optimizer into EM code in
Compact Assembly Language (CAL) format.
In the intermediate code, all program entities
(such as procedures, labels, global variables)
are denoted by a unique identifying number (see 3.5).
In the CAL output of the optimizer these numbers have to
be replaced by normal identifiers (strings).
The original identifiers of the input program are used whenever possible.
Recall that the IC phase generates two files that can be
used to map unique identifying numbers to procedure names and
global variable names.
For instruction labels CA always generates new names.
The reasons for doing so are:
.IP -
instruction labels are only visible inside one procedure, so they can
not be referenced in other modules
.IP -
the names are not very suggestive anyway, as they must be integer numbers
.IP -
the optimizer considerably changes the control structure of the program,
so there is really no one to one mapping of instruction labels in
the input and the output program.
.LP
As the optimizer combines all input modules into one module,
visibility problems may occur.
Two modules M1 and M2 can both define an identifier X (provided that
X is not externally visible in any of these modules).
If M1 and M2 are combined into one module M, two distinct
entities with the same name would exist in M, which
is not allowed.
.[~[
tanenbaum machine architecture
.], section 11.1.4.3]
In these cases, CA invents a new unique name for one of the entities.
.NH 2
Implementation
.PP
CA first reads the files containing the procedure and global variable names
and stores the names in two tables.
It scans these tables to make sure that all names are different.
Subsequently it reads the EM text, one procedure at a time,
and outputs it in CAL format.
The major part of the code that does the latter transformation
is adapted from the EM Peephole Optimizer.
.PP
The main problem of the implementation of CA is to
assure that the visibility rules are obeyed.
If an identifier must be externally visible (i.e.
it was externally visible in the input program)
and the identifier is defined (in the output program) before
being referenced,
an EXA or EXP pseudo must be generated for it.
(Note that the optimizer may change the order of definitions and
references, so some pseudos may be needed that were not
present in the input program).
On the other hand, an identifier may be only internally visible.
If such an identifier is referenced before being defined,
an INA or INP pseudo must be emitted prior to its first reference.

6
doc/ego/cf/.distr
View file

@ -1,6 +0,0 @@
cf1
cf2
cf3
cf4
cf5
cf6

94
doc/ego/cf/cf1
View file

@ -1,94 +0,0 @@
.bp
.NH
The Control Flow Phase
.PP
In the previous chapter we described the intermediate
code of the global optimizer.
We also specified which part of this code
was constructed by the IC phase of the optimizer.
The Control Flow Phase (\fICF\fR) does
the remainder of the job,
i.e. it determines:
.IP -
the control flow graphs
.IP -
the loop tables
.IP -
the calling, change and use attributes of
the procedure table entries
.LP
CF operates on one procedure at a time.
For every procedure it first reads the EM instructions
from the EM-text file and groups them into basic blocks.
For every basic block, its successors and
predecessors are determined,
resulting in the control flow graph.
Next, the immediate dominator of every basic block
is computed.
Using these dominators, any loop in the
procedure is detected.
Finally, interprocedural analysis is done,
after which we will know the global effects of
every procedure call on its environment.
.sp
CF uses the same internal data structures
for the procedure table and object table as IC.
.NH 2
Partitioning into basic blocks
.PP
With regard to flow of control, we distinguish
three kinds of EM instructions:
jump instructions, instruction label definitions and
normal instructions.
Jump instructions are all conditional or unconditional
branch instructions,
the case instructions (CSA/CSB)
and the RET (return) instruction.
A procedure call (CAL) is not considered to be a jump.
A defining occurrence of an instruction label
is regarded as an EM instruction.
.PP
An instruction starts
a new basic block, in any of the following cases:
.IP 1.
It is the first instruction of a procedure
.IP 2.
It is the first of a list of instruction label
defining occurrences
.IP 3.
It follows a jump
.LP
If there are several consecutive instruction labels
(which is highly unusual),
all of them are put in the same basic block.
Note that several cases may overlap,
e.g. a label definition at the beginning of a procedure
or a label following a jump.
.PP
A simple Finite State Machine is used to model
the above rules.
It also recognizes the end of a procedure,
marked by an END pseudo.
The basic blocks are stored internally as a doubly linked
linear list.
The blocks are linked in textual order.
Every node of this list has the attributes described
in the previous chapter (see syntax rule for
basic_block).
Furthermore, every node contains a pointer to its
EM instructions,
which are represented internally
as a linear, doubly linked list,
just as in the IC phase.
However, instead of one list per procedure (as in IC)
there is now one list per basic block.
.PP
On the fly, a table is build that maps
every label identifier to the label definition
instruction.
This table is used for computing the control flow.
The table is stored as a dynamically allocated array.
The length of the array is the number of labels
of the current procedure;
this value can be found in the procedure table,
where it was stored by IC.

50
doc/ego/cf/cf2
View file

@ -1,50 +0,0 @@
.NH 2
Control Flow
.PP
A \fIsuccessor\fR of a basic block B is a block C
that can be executed immediately after B.
C is said to be a \fIpredecessor\fR of B.
A block ending with a RET instruction
has no successors.
Such a block is called a \fIreturn block\fR.
Any block that has no predecessors cannot be
executed at all (i.e. it is unreachable),
unless it is the first block of a procedure,
called the \fIprocedure entry block\fR.
.PP
Internally, the successor and predecessor
attributes of a basic block are stored as \fIsets\fR.
Alternatively, one may regard all these
sets of all basic blocks as a conceptual \fIgraph\fR,
in which there is an edge from B to C if C
is in the successor set of B.
We call this conceptual graph
the \fIControl Flow Graph\fR.
.PP
The only successor of a basic block ending on an
unconditional branch instruction is the block that
contains the label definition of the target of the jump.
The target instruction can be found via the LAB_ID
that is the operand of the jump instruction,
by using the label-map table mentioned
above.
If the last instruction of a block is a
conditional jump,
the successors are the target block and the textually
next block.
The last instruction can also be a case jump
instruction (CSA or CSB).
We then analyze the case descriptor,
to find all possible target instructions
and their associated blocks.
We require the case descriptor to be allocated in
a ROM, so it cannot be changed dynamically.
A case jump via an alterable descriptor could in principle
go to any label in the program.
In the presence of such an uncontrolled jump,
hardly any optimization can be done.
We do not expect any front end to generate such a descriptor,
however, because of the controlled nature
of case statements in high level languages.
If the basic block does not end in a jump instruction,
its only successor is the textually next block.

53
doc/ego/cf/cf3
View file

@ -1,53 +0,0 @@
.NH 2
Immediate dominators
.PP
A basic block B dominates a block C if every path
in the control flow graph from the procedure entry block
to C goes through B.
The immediate dominator of C is the closest dominator
of C on any path from the entry block.
See also
.[~[
aho compiler design
.], section 13.1.]
.PP
There are a number of algorithms to compute
the immediate dominator relation.
.IP 1.
Purdom and Moore give an algorithm that is
easy to program and easy to describe (although the
description they give is unreadable;
it is given in a very messy Algol60 program full of gotos).
.[
predominators
.]
.IP 2.
Aho and Ullman present a bitvector algorithm, which is also
easy to program and to understand.
(See
.[~[
aho compiler design
.], section 13.1.]).
.IP 3
Lengauer and Tarjan introduce a fast algorithm that is
hard to understand, yet remarkably easy to implement.
.[
lengauer dominators
.]
.LP
The Purdom-Moore algorithm is very slow if the
number of basic blocks in the flow graph is large.
The Aho-Ullman algorithm in fact computes the
dominator relation,
from which the immediate dominator relation can be computed
in time quadratic to the number of basic blocks, worst case.
The storage requirement is also quadratic to the number
of blocks.
The running time of the third algorithm is proportional
to:
.DS
(number of edges in the graph) * log(number of blocks).
.DE
We have chosen this algorithm because it is fast
(as shown by experiments done by Lengauer and Tarjan),
it is easy to program and requires little data space.

93
doc/ego/cf/cf4
View file

@ -1,93 +0,0 @@
.NH 2
Loop detection
.PP
Loops are detected by using the loop construction
algorithm of.
.[~[
aho compiler design
.], section 13.1.]
This algorithm uses \fIback edges\fR.
A back edge is an edge from B to C in the CFG,
whose head (C) dominates its tail (B).
The loop associated with this back edge
consists of C plus all nodes in the CFG
that can reach B without going through C.
.PP
As an example of how the algorithm works,
consider the piece of program of Fig. 4.1.
First just look at the program and try to
see what part of the code constitutes the loop.
.DS
loop
if cond then 1
-- lots of simple
-- assignment
-- statements 2 3
exit; -- exit loop
else
S; -- one statement
end if;
end loop;
Fig. 4.1 A misleading loop
.DE
Although a human being may be easily deceived
by the brackets "loop" and "end loop",
the loop detection algorithm will correctly
reply that only the test for "cond" and
the single statement in the false-part
of the if statement are part of the loop!
The statements in the true-part only get
executed once, so there really is no reason at all
to say they're part of the loop too.
The CFG contains one back edge, "3->1".
As node 3 cannot be reached from node 2,
the latter node is not part of the loop.
.PP
A source of problems with the algorithm is the fact
that different back edges may result in
the same loop.
Such an ill-structured loop is
called a \fImessy\fR loop.
After a loop has been constructed, it is checked
if it is really a new loop.
.PP
Loops can partly overlap, without one being nested
inside the other.
This is the case in the program of Fig. 4.2.
.DS
1: 1
S1;
2:
S2; 2
if cond then
goto 4;
S3; 3 4
goto 1;
4:
S4;
goto 1;
Fig. 4.2 Partly overlapping loops
.DE
There are two back edges "3->1" and "4->1",
resulting in the loops {1,2,3} and {1,2,4}.
With every basic block we associate a set of
all loops it is part of.
It is not sufficient just to record its
most enclosing loop.
.PP
After all loops of a procedure are detected, we determine
the nesting level of every loop.
Finally, we find all strong and firm blocks of the loop.
If the loop has only one back edge (i.e. it is not messy),
the set of firm blocks consists of the
head of this back edge and its dominators
in the loop (including the loop entry block).
A firm block is also strong if it is not a
successor of a block that may exit the loop;
a block may exit a loop if it has an (immediate) successor
that is not part of the loop.
For messy loops we do not determine the strong
and firm blocks. These loops are expected
to occur very rarely.

82
doc/ego/cf/cf5
View file

@ -1,82 +0,0 @@
.NH 2
Interprocedural analysis
.PP
It is often desirable to know the effects
a procedure call may have.
The optimization below is only possible if
we know for sure that the call to P cannot
change A.
.DS
.TS
l l.
A := 10; A:= 10;
P; -- procedure call --> P;
B := A + 2; B := 12;
.TE
.DE
Although it is not possible to predict exactly
all the effects a procedure call has, we may
determine a kind of upper bound for it.
So we compute all variables that may be
changed by P, although they need not be
changed at every invocation of P.
We can get hold of this set by just looking
at all assignment (store) instructions
in the body of P.
EM also has a set of \fIindirect\fR assignment
instructions,
i.e. assignment through a pointer variable.
In general, it is not possible to determine
which variable is affected by such an assignment.
In these cases, we just record the fact that P
does an indirect assignment.
Note that this does not mean that all variables
are potentially affected, as the front ends
may generate messages telling that certain
variables can never be accessed indirectly.
We also set a flag if P does a use (load) indirect.
Note that we only have to look at \fIglobal\fR
variables.
If P changes or uses any of its locals,
this has no effect on its environment.
Local variables of a lexically enclosing
procedure can only be accessed indirectly.
.PP
A procedure P may of course call another procedure.
To determine the effects of a call to P,
we also must know the effects of a call to the second procedure.
This second one may call a third one, and so on.
Effectively, we need to compute the \fItransitive closure\fR
of the effects.
To do this, we determine for every procedure
which other procedures it calls.
This set is the "calling" attribute of a procedure.
One may regard all these sets as a conceptual graph,
in which there is an edge from P to Q
if Q is in the calling set of P. This graph will
be referred to as the \fIcall graph\fR.
(Note the resemblance with the control flow graph).
.PP
We can detect which procedures are called by P
by looking at all CAL instructions in its body.
Unfortunately, a procedure may also be
called indirectly, via a CAI instruction.
Yet, only procedures that are used as operand of an LPI
instruction can be called indirect,
because this is the only way to take the address of a procedure.
We determine for every procedure whether it does
a CAI instruction.
We also build a set of all procedures used as
operand of an LPI.
.sp
After all procedures have been processed (i.e. all CFGs
are constructed, all loops are detected,
all procedures are analyzed to see which variables
they may change, which procedures they call,
whether they do a CAI or are used in an LPI) the
transitive closure of all interprocedural
information is computed.
During the same process,
the calling set of every procedure that uses a CAI
is extended with the above mentioned set of all
procedures that can be called indirect.

21
doc/ego/cf/cf6
View file

@ -1,21 +0,0 @@
.NH 2
Source files
.PP
The sources of CF are in the following files and packages:
.IP cf.h: 14
declarations of global variables and data structures
.IP cf.c:
the routine main; interprocedural analysis;
transitive closure
.IP succ:
control flow (successor and predecessor)
.IP idom:
immediate dominators
.IP loop:
loop detection
.IP get:
read object and procedure table;
read EM text and partition it into basic blocks
.IP put:
write tables, CFGs and EM text
.LP

1
doc/ego/cj/.distr
View file

@ -1 +0,0 @@
cj1

144
doc/ego/cj/cj1
View file

@ -1,144 +0,0 @@
.bp
.NH 1
Cross jumping
.NH 2
Introduction
.PP
The "Cross Jumping" optimization technique (CJ)
.[
wulf design optimizing compiler
.]
is basically a space optimization technique. It looks for pairs of
basic blocks (B1,B2), for which:
.DS
SUCC(B1) = SUCC(B2) = {S}
.DE
(So B1 and B2 both have one and the same successor).
If the last few non-branch instructions are the same for B1 and B2,
one such sequence can be eliminated.
.DS
Pascal:
if cond then
S1
S3
else
S2
S3
(pseudo) EM:
.TS
l l l.
TEST COND TEST COND
BNE *1 BNE *1
S1 S1
S3 ---> BRA *2
BRA *2 1:
1: S2
S2 2:
S3 S3
2:
.TE
Fig. 9.1 An example of Cross Jumping
.DE
As the basic blocks have the same successor,
at least one of them ends in an unconditional branch instruction (BRA).
Hence no extra branch instruction is ever needed, just the target
of an existing branch needs to be changed; neither the program size
nor the execution time will ever increase.
In general, the execution time will remain the same, unless
further optimizations can be applied because of this optimization.
.PP
This optimization is particularly effective,
because it cannot always be done by the programmer at the source level,
as demonstrated by the Fig. 8.2.
.DS
Pascal:
if cond then
x := f(4)
else
x := g(5)
EM:
.TS
l l.
... ...
LOC 4 LOC 5
CAL F CAL G
ASP 2 ASP 2
LFR 2 LFR 2
STL X STL X
.TE
Fig. 9.2 Effectiveness of Cross Jumping
.DE
At the source level there is no common tail,
but at the EM level there is a common tail.
.NH 2
Implementation
.PP
The implementation of cross jumping is rather straightforward.
The technique is applied to one procedure at a time.
The control flow graph of the procedure
is scanned for pairs of basic blocks
with the same (single) successor and with common tails.
Note that there may be more than two such blocks (e.g. as the result
of a case statement).
This is dealt with by repeating the entire process until no
further optimizations can de done for the current procedure.
.sp
If a suitable pair of basic blocks has been found, the control flow
graph must be altered. One of the basic
blocks must be split into two.
The control flow graphs before and after the optimization are shown
in Fig. 9.3 and Fig. 9.4.
.DS
.ft 5
-------- --------
| | | |
| S1 | | S2 |
| S3 | | S3 |
| | | |
-------- --------
| |
|------------------|--------------------|
|
v
.ft R
Fig. 9.3 CFG before optimization
.DE
.DS
.ft 5
-------- --------
| | | |
| S1 | | S2 |
| | | |
-------- --------
| |
|--------------------<------------------|
v
--------
| |
| S3 |
| |
--------
|
v
.ft R
Fig. 9.4 CFG after optimization
.DE
Some attributes of the three resulting blocks (such as immediate dominator)
are updated.
.PP
In some cases, cross jumping might split the computation of an expression
into two, by inserting a branch somewhere in the middle.
Most code generators will generate very poor assembly code when
presented with such EM code.
Therefor, cross jumping is not performed in these cases.

5
doc/ego/cs/.distr
View file

@ -1,5 +0,0 @@
cs1
cs2
cs3
cs4
cs5

45
doc/ego/cs/cs1
View file

@ -1,45 +0,0 @@
.bp
.NH 1
Common subexpression elimination
.NH 2
Introduction
.PP
The Common Subexpression Elimination optimization technique (CS)
tries to eliminate multiple computations of EM expressions
that yield the same result.
It places the result of one such computation
in a temporary variable,
and replaces the other computations by a reference
to this temporary variable.
The primary goal of this technique is to decrease
the execution time of the program,
but in general it will save space too.
.PP
As an example of the application of Common Subexpression Elimination,
consider the piece of program in Fig. 7.1(a).
.DS
.TS
l l l.
x := a * b; TMP := a * b; x := a * b;
CODE; x := TMP; CODE
y := c + a * b; CODE y := x;
y := c + TMP;
(a) (b) (c)
.TE
Fig. 7.1 Examples of Common Subexpression Elimination
.DE
If neither a nor b is changed in CODE,
the instructions can be replaced by those of Fig. 7.1(b),
which saves one multiplication,
but costs an extra store instruction.
If the value of x is not changed in CODE either,
the instructions can be replaced by those of Fig. 7.1(c).
In this case
the extra store is not needed.
.PP
In the following sections we will describe
which transformations are done
by CS and how this phase
was implemented.

86
doc/ego/cs/cs2
View file

@ -1,86 +0,0 @@
.NH 2
Specification of the Common Subexpression Elimination phase
.PP
In this section we will describe
the window
through which CS examines the code,
the expressions recognized by CS,
and finally the changes made to the code.
.NH 3
The working window
.PP
The CS algorithm is applied to the
largest sequence of textually adjacent basic blocks
B1,..,Bn, for which
.DS
PRED(Bj) = {Bj-1}, j = 2,..,n.
.DE
Intuitively, this window consists of straight line code,
with only one entry point (at the beginning); it may
contain jumps, which should all have their targets outside the window.
This is illustrated in Fig. 7.2.
.DS
x := a * b; (1)
if x < 10 then (2)
y := a * b; (3)
Fig. 7.2 The working window of CS
.DE
Line (2) can only be executed after line (1).
Likewise, line (3) can only be executed after
line (2).
Both a and b have the same values at line (1) and at line (3).
.PP
Larger windows were avoided.
In Fig. 7.3, the value of a at line (4) may have been obtained
at more than one point.
.DS
x := a * b; (1)
if x < 10 then (2)
a := 100; (3)
y := a * b; (4)
Fig. 7.3 Several working windows
.DE
.NH 3
Recognized expressions.
.PP
The computations eliminated by CS need not be normal expressions
(like "a * b"),
but can even consist of a single operand that is expensive to access,
such as an array element or a record field.
If an array element is used,
its address is computed implicitly.
CS is able to eliminate either the element itself or its
address, whichever one is most profitable.
A variable of a textually enclosing procedure may also be
expensive to access, depending on the lexical level difference.
.NH 3
Transformations
.PP
CS creates a new temporary local variable (TMP)
for every eliminated expression,
unless it is able to use an existing local variable.
It emits code to initialize this variable with the
result of the expression.
Most recurrences of the expression
can simply be replaced by a reference to TMP.
If the address of an array element is recognized as
a common subexpression,
references to the element itself are replaced by
indirect references through TMP (see Fig. 7.4).
.DS
.TS
l l l.
x := A[i]; TMP := &A[i];
. . . --> x := *TMP;
A[i] := y; . . .
*TMP := y;
.TE
Fig. 7.4 Elimination of an array address computation
.DE
Here, '&' is the 'address of' operator,
and unary '*' is the indirection operator.
(Note that EM actually has different instructions to do
a use-indirect or an assign-indirect.)

250
doc/ego/cs/cs3
View file

@ -1,250 +0,0 @@
.NH 2
Implementation
.PP
.NH 3
The value number method
.PP
To determine whether two expressions have the same result,
there must be some way to determine whether their operands have
the same values.
We use a system of \fIvalue numbers\fP
.[
kennedy data flow analysis
.]
in which each distinct value of whatever type,
created or used within the working window,
receives a unique identifying number, its value number.
Two items have the same value number if and only if,
based only upon information from the instructions in the window,
their values are provably identical.
For example, after processing the statement
.DS
a := 4;
.DE
the variable a and the constant 4 have the same value number.
.PP
The value number of the result of an expression depends only
on the kind of operator and the value number(s) of the operand(s).
The expressions need not be textually equal, as shown in Fig. 7.5.
.DS
.TS
l l.
a := c; (1)
use(a * b); (2)
d := b; (3)
use(c * d); (4)
.TE
Fig. 7.5 Different expressions with the same value number
.DE
At line (1) a receives the same value number as c.
At line (2) d receives the same value number as b.
At line (4) the expression "c * d" receives the same value number
as the expression "a * b" at line (2),
because the value numbers of their left and right operands are the same,
and the operator (*) is the same.
.PP
As another example of the value number method, consider Fig. 7.6.
.DS
.TS
l l.
use(a * b); (1)
a := 123; (2)
use(a * b); (3)
.TE
Fig. 7.6 Identical expressions with the different value numbers
.DE
Although textually the expressions "a * b" in line 1 and line 3 are equal,
a will have different value numbers at line 3 and line 1.
The two expressions will not mistakenly be recognized as equivalent.
.NH 3
Entities
.PP
The Value Number Method distinguishes between operators and operands.
The value numbers of operands are stored in a table,
called the \fIsymbol table\fR.
The value number of a subexpression depends on the
(root) operator of the expression and on the value numbers
of its operands.
A table of "available expressions" is used to do this mapping.
.PP
CS recognizes the following kinds of EM operands, called \fIentities\fR:
.DS
- constant
- local variable
- external variable
- indirectly accessed entity
- offsetted entity
- address of local variable
- address of external variable
- address of offsetted entity
- address of local base
- address of argument base
- array element
- procedure identifier
- floating zero
- local base
- heap pointer
- ignore mask
.DE
.LP
Whenever a new entity is encountered in the working window,
it is entered in the symbol table and given a brand new value number.
Most entities have attributes (e.g. the offset in
the current stackframe for local variables),
which are also stored in the symbol table.
.PP
An entity is called static if its value cannot be changed
(e.g. a constant or an address).
.NH 3
Parsing expressions
.PP
Common subexpressions are recognized by simulating the behaviour
of the EM machine.
The EM code is parsed from left to right;
as EM is postfix code, this is a bottom up parse.
At any point the current state of the EM runtime stack is
reflected by a simulated "fake stack",
containing descriptions of the parsed operands and expressions.
A descriptor consists of:
.DS
(1) the value number of the operand or expression
(2) the size of the operand or expression
(3) a pointer to the first line of EM-code
that constitutes the operand or expression
.DE
Note that operands may consist of several EM instructions.
Whenever an operator is encountered, the
descriptors of its operands are on top of the fake stack.
The operator and the value numbers of the operands
are used as indices in the table of available expressions,
to determine the value number of the expression.
.PP
During the parsing process,
we keep track of the first line of each expression;
we need this information when we decide to eliminate the expression.
.NH 3
Updating entities
.PP
An entity is assigned a value number when it is
used for the first time
in the working window.
If the entity is used as left hand side of an assignment,
it gets the value number of the right hand side.
Sometimes the effects of an instruction on an entity cannot
be determined exactly;
the current value and value number of the entity may become
inconsistent.
Hence the current value number must be forgotten.
This is achieved by giving the entity a new value number
that was not used before.
The entity is said to be \fIkilled\fR.
.PP
As information is lost when an entity is killed,
CS tries to save as many entities as possible.
In case of an indirect assignment through a pointer,
some analysis is done to see which variables cannot be altered.
For a procedure call, the interprocedural information contained
in the procedure table is used to restrict the set of entities that may
be changed by the call.
Local variables for which the front end generated
a register message can never be changed by an indirect assignment
or a procedure call.
.NH 3
Changing the EM text
.PP
When a new expression comes available,
it is checked whether its result is saved in a local
that may go in a register.
The last line of the expression must be followed
by a STL or SDL instruction
(depending on the size of the result)
and a register message must be present for
this local.
If there is such a local,
it is recorded in the available expressions table.
Each time a new occurrence of this expression
is found,
the value number of the local is compared against
the value number of the result.
If they are different the local cannot be used and is forgotten.
.PP
The available expressions are linked in a list.
New expressions are linked at the head of the list.
In this way expressions that are contained within other
expressions appear later in the list,
because EM-expressions are postfix.
The elimination process walks through the list,
starting at the head, to find the largest expressions first.
If an expression is eliminated,
any expression later on in the list, contained in the former expression,
is removed from the list,
as expressions can only be eliminated once.
.PP
A STL or SDL is emitted after the first occurrence of the expression,
unless there was an existing local variable that could hold the result.
.NH 3
Desirability analysis
.PP
Although the global optimizer works on EM code,
the goal is to improve the quality of the object code.
Therefore some machine-dependent information is needed
to decide whether it is desirable to
eliminate a given expression.
Because it is impossible for the CS phase to know
exactly what code will be generated,
some heuristics are used.
CS essentially looks for some special cases
that should not be eliminated.
These special cases can be turned on or off for a given machine,
as indicated in a machine descriptor file.
.PP
Some operators can sometimes be translated
into an addressing mode for the machine at hand.
Such an operator is only eliminated
if its operand is itself expensive,
i.e. it is not just a simple load.
The machine descriptor file contains a set of such operators.
.PP
Eliminating the loading of the Local Base or
the Argument Base by the LXL resp. LXA instruction
is only beneficial if the difference in lexical levels
exceeds a certain threshold.
The machine descriptor file contains this threshold.
.PP
Replacing a SAR or a LAR by an AAR followed by a LOI
may possibly increase the size of the object code.
We assume that this is only possible when the
size of the array element is greater than some limit.
.PP
There are back ends that can very efficiently translate
the index computing instruction sequence LOC SLI ADS.
If this is the case,
the SLI instruction between a LOC
and an ADS is not eliminated.
.PP
To handle unforseen cases, the descriptor file may also contain
a set of operators that should never be eliminated.
.NH 3
The algorithm
.PP
After these preparatory explanations,
the algorithm itself is easy to understand.
For each instruction within the current window,
the following steps are performed in the given order :
.IP 1.
Check if this instruction defines an entity.
If so, the set of entities is updated accordingly.
.IP 2.
Kill all entities that might be affected by this instruction.
.IP 3.
Simulate the instruction on the fake-stack.
If this instruction is an operator,
update the list of available expressions accordingly.
.PP
The result of this process is
a list of available expressions plus the information
needed to eliminate them.
Expressions that are desirable to eliminate are eliminated.
Next, the window is shifted and the process is repeated.

311
doc/ego/cs/cs4
View file

@ -1,311 +0,0 @@
.NH 2
Implementation.
.PP
In this section we will discuss the implementation of the CS phase.
We will first describe the basic actions that are undertaken
by the algorithm, than the algorithm itself.
.NH 3
Partioning the EM instructions
.PP
There are over 100 EM instructions.
For our purpose we partition this huge set into groups of
instructions which can be more or less conveniently handled together.
.PP
There are groups for all sorts of load instructions:
simple loads, expensive loads, loads of an array element.
A load is considered \fIexpensive\fP when more than one EM instructions
are involved in loading it.
The load of a lexical entity is also considered expensive.
For instance: LOF is expensive, LAL is not.
LAR forms a group on its own,
because it is not only an expensive load,
but also implicitly includes the ternary operator AAR,
which computes the address of the array element.
.PP
There are groups for all sorts of operators:
unary, binary, and ternary.
The groups of operators are further partitioned according to the size
of their operand(s) and result.
.\" .PP
.\" The distinction between operators and expensive loads is not always clear.
.\" The ADP instruction for example,
.\" might seem a unary operator because it pops one item
.\" (a pointer) from the stack.
.\" However, two ADP-instructions which pop an item with the same value number
.\" need not have the same result,
.\" because the attributes (an offset, to be added to the pointer)
.\" can be different.
.\" Is it then a binary operator?
.\" That would give rise to the strange, and undesirable,
.\" situation that some binary operators pop two operands
.\" and others pop one.
.\" The conclusion is inevitable:
.\" we have been fooled by the name (ADd Pointer).
.\" The ADP-instruction is an expensive load.
.\" In this context LAF, meaning Load Address of oFfsetted,
.\" would have been a better name,
.\" corresponding to LOF, like LAL,
.\" Load Address of Local, corresponds to LOL.
.PP
There are groups for all sorts of stores:
direct, indirect, array element.
The SAR forms a group on its own for the same reason
as appeared with LAR.
.PP
The effect of the remaining instructions is less clear.
They do not help very much in parsing expressions or
in constructing our pseudo symboltable.
They are partitioned according to the following criteria:
.RS
.IP "-"
They change the value of an entity without using the stack
(e.g. ZRL, DEE).
.IP "-"
They are subroutine calls (CAI, CAL).
.IP "-"
They change the stack in some irreproduceable way (e.g. ASP, LFR, DUP).
.IP "-"
They have no effect whatever on the stack or on the entities.
This does not mean they can be deleted,
but they can be ignored for the moment
(e.g. MES, LIN, NOP).
.IP "-"
Their effect is too complicate too compute,
so we just assume worst case behaviour.
Hopefully, they do not occur very often.
(e.g. MON, STR, BLM).
.IP "-"
They signal the end of the basic block (e.g. BLT, RET, TRP).
.RE
.NH 3
Parsing expressions
.PP
To recognize expressions,
we simulate the behaviour of the EM machine,
by means of a fake-stack.
When we scan the instructions in sequential order,
we first encounter the instructions that load
the operands on the stack,
and then the instruction that indicates the operator,
because EM expressions are postfix.
When we find an instruction to load an operand,
we load on the fake-stack a struct with the following information:
.DS
.TS
l l.
(1) the value number of the operand
(2) the size of the operand
(3) a pointer to the first line of EM-code
that constitutes the operand
.TE
.DE
In most cases, (3) will point to the line
that loaded the operand (e.g. LOL, LOC),
i.e. there is only one line that refers to this operand,
but sometimes some information must be popped
to load the operand (e.g. LOI, LAR).
This information must have been pushed before,
so we also pop a pointer to the first line that pushed
the information.
This line is now the first line that defines the operand.
.PP
When we find the operator instruction,
we pop its operand(s) from the fake-stack.
The first line that defines the first operand is
now the first line of the expression.
We now have all information to determine
whether the just parsed expression has occurred before.
We also know the first and last line of the expression;
we need this when we decide to eliminate it.
Associated with each available expression is a set of
which the elements contains the first and last line of
a recurrence of this expression.
.PP
Not only will the operand(s) be popped from the fake-stack,
but the following will be pushed:
.DS
.TS
l l.
(1) the value number of the result
(2) the size of the result
(3) a pointer to the first line of the expression
.TE
.DE
In this way an item on the fake-stack always contains
the necessary information.
EM expressions are parsed bottum up.
.NH 3
Updating entities
.PP
As said before,
we build our private "symboltable",
while scanning the EM-instructions.
The behaviour of the EM-machine is not only reflected
in the fake-stack,
but also in the entities.
When an entity is created,
we do not yet know its value,
so we assign a brand new value number to it.
Each time a store-instruction is encountered,
we change the value number of the target entity of this store
to the value number of the token that was popped
from the fake-stack.
Because entities may overlap,
we must also "forget" the value numbers of entities
that might be affected by this store.
Each such entity will be \fIkilled\fP,
i.e. assigned a brand new valuenumber.
.PP
Because we lose information when we forget
the value number of an entity,
we try to save as much entities as possible.
When we store into an external,
we don't have to kill locals and vice versa.
Furthermore, we can see whether two locals or
two externals overlap,
because we know the offset from the local base,
resp. the offset within the data block,
and the size.
The situation becomes more complicated when we have
to consider indirection.
The worst case is that we store through an unknown pointer.
In that case we kill all entities except those locals
for which a so-called \fIregister message\fP has been generated;
this register message indicates that this local can never be
accessed indirectly.
If we know this pointer we can be more careful.
If it points to a local then the entity that is accessed through
this pointer can never overlap with an external.
If it points to an external this entity can never overlap with a local.
Furthermore, in the latter case,
we can find the data block this entity belongs to.
Since pointer arithmetic is only defined within a data block,
this entity can never overlap with entities that are known to
belong to another data block.
.PP
Not only after a store-instruction but also after a
subroutine-call it may be necessary to kill entities;
the subroutine may affect global variables or store
through a pointer.
If a subroutine is called that is not available as EM-text,
we assume worst case behaviour,
i.e. we kill all entities without register message.
.NH 3
Additions and replacements.
.PP
When a new expression comes available,
we check whether the result is saved in a local
that may go in a register.
The last line of the expression must be followed
by a STL or SDL instruction,
depending on the size of the result
(resp. WS and 2*WS),
and a register message must be present for
this local.
If we have found such a local,
we store a pointer to it with the available expression.
Each time a new occurrence of this expression
is found,
we compare the value number of the local against
the value number of the result.
When they are different we remove the pointer to it,
because we cannot use it.
.PP
The available expressions are singly linked in a list.
When a new expression comes available,
we link it at the head of the list.
In this way expressions that are contained within other
expressions appear later in the list,
because EM-expressions are postfix.
When we are going to eliminate expressions,
we walk through the list,
starting at the head, to find the largest expressions first.
When we decide to eliminate an expression,
we look at the expressions in the tail of the list,
starting from where we are now,
to delete expressions that are contained within
the chosen one because
we cannot eliminate an expression more than once.
.PP
When we are going to eliminate expressions,
and we do not have a local that holds the result,
we emit a STL or SDL after the line where the expression
was first found.
The other occurrences are simply removed,
unless they contain instructions that not only have
effect on the stack; e.g. messages, stores, calls.
Before each instruction that needs the result on the stack,
we emit a LOL or LDL.
When the expression was an AAR,
but the instruction was a LAR or a SAR,
we append a LOI resp. a STI of the number of bytes
in an array-element after each LOL/LDL.
.NH 3
Desirability analysis
.PP
Although the global optimizer works on EM code,
the goal is to improve the quality of the object code.
Therefore we need some machine dependent information
to decide whether it is desirable to
eliminate a given expression.
Because it is impossible for the CS phase to know
exactly what code will be generated,
we use some heuristics.
In most cases it will save time when we eliminate an
operator, so we just do it.
We only look for some special cases.
.PP
Some operators can in some cases be translated
into an addressing mode for the machine at hand.
We only eliminate such an operator,
when its operand is itself "expensive",
i.e. not just a simple load.
The user of the CS phase has to supply
a set of such operators.
.PP
Eliminating the loading of the Local Base or
the Argument Base by the LXL resp. LXA instruction
is only beneficial when the number of lexical levels
we have to go back exceeds a certain threshold.
This threshold will be different when registers
are saved by the back end.
The user must supply this threshold.
.PP
Replacing a SAR or a LAR by an AAR followed by a LOI
may possibly increase the size of the object code.
We assume that this is only possible when the
size of the array element is greater than some
(user-supplied) limit.
.PP
There are back ends that can very efficiently translate
the index computing instruction sequence LOC SLI ADS.
If this is the case,
we do not eliminate the SLI instruction between a LOC
and an ADS.
.PP
To handle unforeseen cases, the user may also supply
a set of operators that should never be eliminated.
.NH 3
The algorithm
.PP
After these preparatory explanations,
we can be short about the algorithm itself.
For each instruction within our window,
the following steps are performed in the order given:
.IP 1.
We check if this instructin defines an entity.
If this is the case the set of entities is updated accordingly.
.IP 2.
We kill all entities that might be affected by this instruction.
.IP 3.
The instruction is simulated on the fake-stack.
Copy propagation is done.
If this instruction is an operator,
we update the list of available expressions accordingly.
.PP
When we have processed all instructions this way,
we have built a list of available expressions plus the information we
need to eliminate them.
Those expressions of which desirability analysis tells us so,
we eliminate.
The we shift our window and continue.

46
doc/ego/cs/cs5
View file

@ -1,46 +0,0 @@
.NH 2
Source files of CS
.PP
The sources of CS are in the following files and packages:
.IP cs.h 14
declarations of global variables and data structures
.IP cs.c
the routine main;
a driving routine to process
the basic blocks in the right order
.IP vnm
implements a procedure that performs
the value numbering on one basic block
.IP eliminate
implements a procedure that does the
transformations, if desirable
.IP avail
implements a procedure that manipulates the list of available expressions
.IP entity
implements a procedure that manipulates the set of entities
.IP getentity
implements a procedure that extracts the
pseudo symboltable information from EM-instructions;
uses a small table
.IP kill
implements several routines that find the entities
that might be changed by EM-instructions
and kill them
.IP partition
implements several routines that partition the huge set
of EM-instructions into more or less manageable,
more or less logical chunks
.IP profit
implements a procedure that decides whether it
is advantageous to eliminate an expression;
also removes expressions with side-effects
.IP stack
implements the fake-stack and operations on it
.IP alloc
implements several allocation routines
.IP aux
implements several auxiliary routines
.IP debug
implements several routines to provide debugging
and verbose output
.LP

5
doc/ego/ic/.distr
View file

@ -1,5 +0,0 @@
ic1
ic2
ic3
ic4
ic5

57
doc/ego/ic/ic1
View file

@ -1,57 +0,0 @@
.bp
.NH
The Intermediate Code and the IC phase
.PP
In this chapter the intermediate code of the EM global optimizer
will be defined.
The 'Intermediate Code construction' phase (IC),
which builds the initial intermediate code from
EM Compact Assembly Language,
will be described.
.NH 2
Introduction
.PP
The EM global optimizer is a multi pass program,
hence there is a need for an intermediate code.
Usually, programs in the Amsterdam Compiler Kit use the
Compact Assembly Language format
.[~[
keizer architecture
.], section 11.2]
for this purpose.
Although this code has some convenient features,
such as being compact,
it is quite unsuitable in our case,
because of a number of reasons.
At first, the code lacks global information
about whole procedures or whole basic blocks.
Second, it uses identifiers ('names') to bind
defining and applied occurrences of
procedures, data labels and instruction labels.
Although this is usual in high level programming
languages, it is awkward in an intermediate code
that must be read many times.
Each pass of the optimizer would have
to incorporate an identifier look-up mechanism
to associate a defining occurrence with each
applied occurrence of an identifier.
Finally, EM programs are used to declare blocks of bytes,
rather than variables. A 'hol 6' instruction may be used to
declare three 2-byte variables.
Clearly, the optimizer wants to deal with variables, and
not with rows of bytes.
.PP
To overcome these problems, we have developed a new
intermediate code.
This code does not merely consist of the EM instructions,
but also contains global information in the
form of tables and graphs.
Before describing the intermediate code we will
first leap aside to outline
the problems one generally encounters
when trying to store complex data structures such as
graphs outside the program, i.e. in a file.
We trust this will enhance the
comprehensibility of the
intermediate code definition and the design and implementation
of the IC phase.

150
doc/ego/ic/ic2
View file

@ -1,150 +0,0 @@
.NH 2
Representation of complex data structures in a sequential file
.PP
Most programmers are quite used to deal with
complex data structures, such as
arrays, graphs and trees.
There are some particular problems that occur
when storing such a data structure
in a sequential file.
We call data that is kept in
main memory
.UL internal
,as opposed to
.UL external
data
that is kept in a file outside the program.
.sp
We assume a simple data structure of a
scalar type (integer, floating point number)
has some known external representation.
An
.UL array
having elements of a scalar type can be represented
externally easily, by successively
representing its elements.
The external representation may be preceded by a
number, giving the length of the array.
Now, consider a linear, singly linked list,
the elements of which look like:
.DS
record
data: scalar_type;
next: pointer_type;
end;
.DE
It is significant to note that the "next"
fields of the elements only have a meaning within
main memory.
The field contains the address of some location in
main memory.
If a list element is written to a file in
some program,
and read by another program,
the element will be allocated at a different
address in main memory.
Hence this address value is completely
useless outside the program.
.sp
One may represent the list by ignoring these "next" fields
and storing the data items in the order they are linked.
The "next" fields are represented \fIimplicitly\fR.
When the file is read again,
the same list can be reconstructed.
In order to know where the external representation of the
list ends,
it may be useful to put the length of
the list in front of it.
.sp
Note that arrays and linear lists have the
same external representation.
.PP
A doubly linked, linear list,
with elements of the type:
.DS
record
data: scalar_type;
next,
previous: pointer_type;
end
.DE
can be represented in precisely the same way.
Both the "next" and the "previous" fields are represented
implicitly.
.PP
Next, consider a binary tree,
the nodes of which have type:
.DS
record
data: scalar_type;
left,
right: pointer_type;
end
.DE
Such a tree can be represented sequentially,
by storing its nodes in some fixed order, e.g. prefix order.
A special null data item may be used to
denote a missing left or right son.
For example, let the scalar type be integer,
and let the null item be 0.
Then the tree of fig. 3.1(a)
can be represented as in fig. 3.1(b).
.DS
.ft 5
4
/ \e
9 12
/ \e / \e
12 3 4 6
/ \e \e /
8 1 5 1
.ft R
Fig. 3.1(a) A binary tree
.ft 5
4 9 12 0 0 3 8 0 0 1 0 0 12 4 0 5 0 0 6 1 0 0 0
.ft R
Fig. 3.1(b) Its sequential representation
.DE
We are still able to represent the pointer fields ("left"
and "right") implicitly.
.PP
Finally, consider a general
.UL graph
, where each node has a "data" field and
pointer fields,
with no restriction on where they may point to.
Now we're at the end of our tale.
There is no way to represent the pointers implicitly,
like we did with lists and trees.
In order to represent them explicitly,
we use the following scheme.
Every node gets an extra field,
containing some unique number that identifies the node.
We call this number its
.UL id.
A pointer is represented externally as the id of the node
it points to.
When reading the file we use a table that maps
an id to the address of its node.
In general this table will not be completely filled in
until we have read the entire external representation of
the graph and allocated internal memory locations for
every node.
Hence we cannot reconstruct the graph in one scan.
That is, there may be some pointers from node A to B,
where B is placed after A in the sequential file than A.
When we read the node of A we cannot map the id of B
to the address of node B,
as we have not yet allocated node B.
We can overcome this problem if the size
of every node is known in advance.
In this case we can allocate memory for a node
on first reference.
Else, the mapping from id to pointer
cannot be done while reading nodes.
The mapping can be done either in an extra scan
or at every reference to the node.

431
doc/ego/ic/ic3
View file

@ -1,431 +0,0 @@
.NH 2
Definition of the intermediate code
.PP
The intermediate code of the optimizer consists
of several components:
.IP -
the object table
.IP -
the procedure table
.IP -
the em code
.IP -
the control flow graphs
.IP -
the loop table
.LP -
.PP
These components are described in
the next sections.
The syntactic structure of every component
is described by a set of context free syntax rules,
with the following conventions:
.DS
.TS
l l.
x a non-terminal symbol
A a terminal symbol (in capitals)
x: a b c; a grammar rule
a | b a or b
(a)+ 1 or more occurrences of a
{a} 0 or more occurrences of a
.TE
.DE
.NH 3
The object table
.PP
EM programs declare blocks of bytes rather than (global) variables.
A typical program may declare 'HOL 7780'
to allocate space for 8 I/O buffers,
2 large arrays and 10 scalar variables.
The optimizer wants to deal with
.UL objects
like variables, buffers and arrays
and certainly not with huge numbers of bytes.
Therefore the intermediate code contains information
about which global objects are used.
This information can be obtained from an EM program
by just looking at the operands of instruction
such as LOE, LAE, LDE, STE, SDE, INE, DEE and ZRE.
.PP
The object table consists of a list of
.UL datablock
entries.
Each such entry represents a declaration like HOL, BSS,
CON or ROM.
There are five kinds of datablock entries.
The fifth kind,
UNKNOWN, denotes a declaration in a
separately compiled file that is not made
available to the optimizer.
Each datablock entry contains the type of the block,
its size, and a description of the objects that
belong to it.
If it is a rom,
it also contains a list of values given
as arguments to the rom instruction,
provided that this list contains only integer numbers.
An object has an offset (within its datablock)
and a size.
The size need not always be determinable.
Both datablock and object contain a unique
identifying number
(see previous section for their use).
.DS
.UL syntax
.TS
lw(1i) l l.
object_table:
{datablock} ;
datablock:
D_ID -- unique identifying number
PSEUDO -- one of ROM,CON,BSS,HOL,UNKNOWN
SIZE -- # bytes declared
FLAGS
{value} -- contents of rom
{object} ; -- objects of the datablock
object:
O_ID -- unique identifying number
OFFSET -- offset within the datablock
SIZE ; -- size of the object in bytes
value:
argument ;
.TE
.DE
A data block has only one flag: "external", indicating
whether the data label is externally visible.
The syntax for "argument" will be given later on
(see em_text).
.NH 3
The procedure table
.PP
The procedure table contains global information
about all procedures that are made available
to the optimizer
and that are needed by the EM program.
(Library units may not be needed, see section 3.5).
The table has one entry for
every procedure.
.DS
.UL syntax
.TS
lw(1i) l l.
procedure_table:
{procedure}
procedure:
P_ID -- unique identifying number
#LABELS -- number of instruction labels
#LOCALS -- number of bytes for locals
#FORMALS -- number of bytes for formals
FLAGS -- flag bits
calling -- procedures called by this one
change -- info about global variables changed
use ; -- info about global variables used
calling:
{P_ID} ; -- procedures called
change:
ext -- external variables changed
FLAGS ;
use:
FLAGS ;
ext:
{O_ID} ; -- a set of objects
.TE
.DE
.PP
The number of bytes of formal parameters accessed by
a procedure is determined by the front ends and
passed via a message (parameter message) to the optimizer.
If the front end is not able to determine this number
(e.g. the parameter may be an array of dynamic size or
the procedure may have a variable number of arguments) the attribute
contains the value 'UNKNOWN_SIZE'.
.sp 0
A procedure has the following flags:
.IP -
external: true if the proc. is externally visible
.IP -
bodyseen: true if its code is available as EM text
.IP -
calunknown: true if it calls a procedure that has its bodyseen
flag not set
.IP -
environ: true if it uses or changes a (non-global) variable in
a lexically enclosing procedure
.IP -
lpi: true if is used as operand of an lpi instruction, so
it may be called indirect
.LP
The change and use attributes both have one flag: "indirect",
indicating whether the procedure does a 'use indirect'
or a 'store indirect' (indirect means through a pointer).
.NH 3
The EM text
.PP
The EM text contains the EM instructions.
Every EM instruction has an operation code (opcode)
and 0 or 1 operands.
EM pseudo instructions can have more than
1 operand.
The opcode is just a small (8 bit) integer.
.sp
There are several kinds of operands, which we will
refer to as
.UL types.
Many EM instructions can have more than one type of operand.
The types and their encodings in Compact Assembly Language
are discussed extensively in.
.[~[
keizer architecture
.], section 11.2]
Of special interest is the way numeric values
are represented.
Of prime importance is the machine independency of
the representation.
Ultimately, one could store every integer
just as a string of the characters '0' to '9'.
As doing arithmetic on strings is awkward,
Compact Assembly Language allows several alternatives.
The main idea is to look at the value of the integer.
Integers that fit in 16, 32 or 64 bits are
represented as a row of resp. 2, 4 and 8 bytes,
preceded by an indication of how many bytes are used.
Longer integers are represented as strings;
this is only allowed within pseudo instructions, however.
This concept works very well for target machines
with reasonable word sizes.
At present, most ACK software cannot be used for word sizes
higher than 32 bits,
although the handles for using larger word sizes are
present in the design of the EM code.
In the intermediate code we essentially use the
same ideas.
We allow three representations of integers.
.IP -
integers that fit in a short are represented as a short
.IP -
integers that fit in a long but not in a short are represented
as longs
.IP -
all remaining integers are represented as strings
(only allowed in pseudos).
.LP
The terms short and long are defined in
.[~[
ritchie reference manual programming language
.], section 4]
and depend only on the source machine
(i.e. the machine on which ACK runs),
not on the target machines.
For historical reasons a long will often be called an
.UL offset.
.PP
Operands can also be instruction labels,
objects or procedures.
Instruction labels are denoted by a
.UL label
.UL identifier,
which can be distinguished from a normal identifier.
.sp
The operand of a pseudo instruction can be a list of
.UL arguments.
Arguments can have the same type as operands, except
for the type short, which is not used for arguments.
Furthermore, an argument can be a string or
a string representation of a signed integer, unsigned integer
or floating point number.
If the number of arguments is not fully determined by
the pseudo instruction (e.g. a ROM pseudo can have any number
of arguments), then the list is terminated by a special
argument of type CEND.
.DS
.UL syntax
.TS
lw(1i) l l.
em_text:
{line} ;
line:
INSTR -- opcode
OPTYPE -- operand type
operand ;
operand:
empty | -- OPTYPE = NO
SHORT | -- OPTYPE = SHORT
OFFSET | -- OPTYPE = OFFSET
LAB_ID | -- OPTYPE = INSTRLAB
O_ID | -- OPTYPE = OBJECT
P_ID | -- OPTYPE = PROCEDURE
{argument} ; -- OPTYPE = LIST
argument:
ARGTYPE
arg ;
arg:
empty | -- ARGTYPE = CEND
OFFSET |
LAB_ID |
O_ID |
P_ID |
string | -- ARGTYPE = STRING
const ; -- ARGTYPE = ICON,UCON or FCON
string:
LENGTH -- number of characters
{CHARACTER} ;
const:
SIZE -- number of bytes
string ; -- string representation of (un)signed
-- or floating point constant
.TE
.DE
.NH 3
The control flow graphs
.PP
Each procedure can be divided
into a number of basic blocks.
A basic block is a piece of code with
no jumps in, except at the beginning,
and no jumps out, except at the end.
.PP
Every basic block has a set of
.UL successors,
which are basic blocks that can follow it immediately in
the dynamic execution sequence.
The
.UL predecessors
are the basic blocks of which this one
is a successor.
The successor and predecessor attributes
of all basic blocks of a single procedure
are said to form the
.UL control
.UL flow
.UL graph
of that procedure.
.PP
Another important attribute is the
.UL immediate
.UL dominator.
A basic block B dominates a block C if
every path in the graph from the procedure entry block
to C goes through B.
The immediate dominator of C is the closest dominator
of C on any path from the entry block.
(Note that the dominator relation is transitive,
so the immediate dominator is well defined.)
.PP
A basic block also has an attribute containing
the identifiers of every
.UL loop
that the block belongs to (see next section for loops).
.DS
.UL syntax
.TS
lw(1i) l l.
control_flow_graph:
{basic_block} ;
basic_block:
B_ID -- unique identifying number
#INSTR -- number of EM instructions
succ
pred
idom -- immediate dominator
loops -- set of loops
FLAGS ; -- flag bits
succ:
{B_ID} ;
pred:
{B_ID} ;
idom:
B_ID ;
loops:
{LP_ID} ;
.TE
.DE
The flag bits can have the values 'firm' and 'strong',
which are explained below.
.NH 3
The loop tables
.PP
Every procedure has an associated
.UL loop
.UL table
containing information about all the loops
in the procedure.
Loops can be detected by a close inspection of
the control flow graph.
The main idea is to look for two basic blocks,
B and C, for which the following holds:
.IP -
B is a successor of C
.IP -
B is a dominator of C
.LP
B is called the loop
.UL entry
and C is called the loop
.UL end.
Intuitively, C contains a jump backwards to
the beginning of the loop (B).
.PP
A loop L1 is said to be
.UL nested
within loop L2 if all basic blocks of L1
are also part of L2.
It is important to note that loops could
originally be written as a well structured for -or
while loop or as a messy goto loop.
Hence loops may partly overlap without one
being nested inside the other.
The
.UL nesting
.UL level
of a loop is the number of loops in
which it is nested (so it is 0 for
an outermost loop).
The details of loop detection will be discussed later.
.PP
It is often desirable to know whether a
basic block gets executed during every iteration
of a loop.
This leads to the following definitions:
.IP -
A basic block B of a loop L is said to be a \fIfirm\fR block
of L if B is executed on all successive iterations of L,
with the only possible exception of the last iteration.
.IP -
A basic block B of a loop L is said to be a \fIstrong\fR block
of L if B is executed on all successive iterations of L.
.LP
Note that a strong block is also a firm block.
If a block is part of a conditional statement, it is neither
strong nor firm, as it may be skipped during some iterations
(see Fig. 3.2).
.DS
loop
if cond1 then
... \kx-- this code will not
\h'|\nxu'-- result in a firm or strong block
end if;
... -- strong (always executed)
exit when cond2;
... \kx-- firm (not executed on last iteration).
end loop;
Fig. 3.2 Example of firm and strong block
.DE
.DS
.UL syntax
.TS
lw(1i) l l.
looptable:
{loop} ;
loop:
LP_ID -- unique identifying number
LEVEL -- loop nesting level
entry -- loop entry block
end ;
entry:
B_ID ;
end:
B_ID ;
.TE
.DE

83
doc/ego/ic/ic4
View file

@ -1,83 +0,0 @@
.NH 2
External representation of the intermediate code
.PP
The syntax of the intermediate code was given
in the previous section.
In this section we will make some remarks about
the representation of the code in sequential files.
.sp
We use sequential files in order to avoid
the bookkeeping of complex file indices.
As a consequence of this decision
we can't store all components
of the intermediate code
in one file.
If a phase wishes to change some attribute
of a procedure,
or wants to add or delete entire procedures
(inline substitution may do the latter),
the procedure table will only be fully updated
after the entire EM text has been scanned.
Yet, the next phase undoubtedly wants
to read the procedure table before it
starts working on the EM text.
Hence there is an ordering problem, which
can be solved easily by putting the
procedure table in a separate file.
Similarly, the data block table is kept
in a file of its own.
.PP
The control flow graphs (CFGs) could be mixed
with the EM text.
Rather, we have chosen to put them
in a separate file too.
The control flow graph file should be regarded as a
file that imposes some structure on the EM-text file,
just as an overhead sheet containing a picture
of a Flow Chart may be put on an overhead sheet
containing statements.
The loop tables are also put in the CFG file.
A loop imposes an extra structure on the
CFGs and hence on the EM text.
So there are four files:
.IP -
the EM-text file
.IP -
the procedure table file
.IP -
the object table file
.IP -
the CFG and loop tables file
.LP
Every table is preceded by its length, in order to
tell where it ends.
The CFG file also contains the number of instructions of
every basic block,
indicating which part of the EM text belongs
to that block.
.DS
.UL syntax
.TS
lw(1i) l l.
intermediate_code:
object_table_file
proctable_file
em_text_file
cfg_file ;
object_table_file:
LENGTH -- number of objects
object_table ;
proctable_file:
LENGTH -- number of procedures
procedure_table ;
em_text_file:
em_text ;
cfg_file:
{per_proc} ; -- one for every procedure
per_proc:
BLENGTH -- number of basic blocks
LLENGTH -- number of loops
control_flow_graph
looptable ;
.TE
.DE

166
doc/ego/ic/ic5
View file

@ -1,166 +0,0 @@
.NH 2
The Intermediate Code construction phase
.PP
The first phase of the global optimizer,
called
.UL IC,
constructs a major part of the intermediate code.
To be specific, it produces:
.IP -
the EM text
.IP -
the object table
.IP -
part of the procedure table
.LP
The calling, change and use attributes of a procedure
and all its flags except the external and bodyseen flags
are computed by the next phase (Control Flow phase).
.PP
As explained before,
the intermediate code does not contain
any names of variables or procedures.
The normal identifiers are replaced by identifying
numbers.
Yet, the output of the global optimizer must
contain normal identifiers, as this
output is in Compact Assembly Language format.
We certainly want all externally visible names
to be the same in the input as in the output,
because the optimized EM module may be a library unit,
used by other modules.
IC dumps the names of all procedures and data labels
on two files:
.IP -
the procedure dump file, containing tuples (P_ID, procedure name)
.IP -
the data dump file, containing tuples (D_ID, data label name)
.LP
The names of instruction labels are not dumped,
as they are not visible outside the procedure
in which they are defined.
.PP
The input to IC consists of one or more files.
Each file is either an EM module in Compact Assembly Language
format, or a Unix archive file (library) containing such modules.
IC only extracts those modules from a library that are
needed somehow, just as a linker does.
It is advisable to present as much code
of the EM program as possible to the optimizer,
although it is not required to present the whole program.
If a procedure is called somewhere in the EM text,
but its body (text) is not included in the input,
its bodyseen flag in the procedure table will still
be off.
Whenever such a procedure is called,
we assume the worst case for everything;
it will change and use all variables it has access to,
it will call every procedure etc.
.sp
Similarly, if a data label is used
but not defined, the PSEUDO attribute in its data block
will be set to UNKNOWN.
.NH 3
Implementation
.PP
Part of the code for the EM Peephole Optimizer
.[
staveren peephole toplass
.]
has been used for IC.
Especially the routines that read and unravel
Compact Assembly Language and the identifier
lookup mechanism have been used.
New code was added to recognize objects,
build the object and procedure tables and to
output the intermediate code.
.PP
IC uses singly linked linear lists for both the
procedure and object table.
Hence there are no limits on the size of such
a table (except for the trivial fact that it must fit
in main memory).
Both tables are outputted after all EM code has
been processed.
IC reads the EM text of one entire procedure
at a time,
processes it and appends the modified code to
the EM text file.
EM code is represented internally as a doubly linked linear
list of EM instructions.
.PP
Objects are recognized by looking at the operands
of instructions that reference global data.
If we come across the instructions:
.DS
.TS
l l.
LDE X+6 -- Load Double External
LAE X+20 -- Load Address External
.TE
.DE
we conclude that the data block
preceded by the data label X contains an object
at offset 6 of size twice the word size,
and an object at offset 20 of unknown size.
.sp
A data block entry of the object table is allocated
at the first reference to a data label.
If this reference is a defining occurrence
or a INA pseudo instruction,
the label is not externally visible
.[~[
keizer architecture
.], section 11.1.4.3]
In this case, the external flag of the data block
is turned off.
If the first reference is an applied occurrence
or a EXA pseudo instruction, the flag is set.
We record this information, because the
optimizer may change the order of defining and
applied occurrences.
The INA and EXA pseudos are removed from the EM text.
They may be regenerated by the last phase
of the optimizer.
.sp
Similar rules hold for the procedure table
and the INP and EXP pseudos.
.NH 3
Source files of IC
.PP
The source files of IC consist
of the files ic.c, ic.h and several packages.
.UL ic.h
contains type definitions, macros and
variable declarations that may be used by
ic.c and by every package.
.UL ic.c
contains the definitions of these variables,
the procedure
.UL main
and some high level I/O routines used by main.
.sp
Every package xxx consists of two files.
ic_xxx.h contains type definitions,
macros, variable declarations and
procedure declarations that may be used by
every .c file that includes this .h file.
The file ic_xxx.c provides the
definitions of these variables and
the implementation of the declared procedures.
IC uses the following packages:
.IP lookup: 18
procedures that loop up procedure, data label
and instruction label names; procedures to dump
the procedure and data label names.
.IP lib:
one procedure that gets the next useful input module;
while scanning archives, it skips unnecessary modules.
.IP aux:
several auxiliary routines.
.IP io:
low-level I/O routines that unravel the Compact
Assembly Language.
.IP put:
routines that output the intermediate code
.LP

6
doc/ego/il/.distr
View file

@ -1,6 +0,0 @@
il1
il2
il3
il4
il5
il6

112
doc/ego/il/il1
View file

@ -1,112 +0,0 @@
.bp
.NH 1
Inline substitution
.NH 2
Introduction
.PP
The Inline Substitution technique (IL)
tries to decrease the overhead associated
with procedure calls (invocations).
During a procedure call, several actions
must be undertaken to set up the right
environment for the called procedure.
.[
johnson calling sequence
.]
On return from the procedure, most of these
effects must be undone.
This entire process introduces significant
costs in execution time as well as
in object code size.
.PP
The inline substitution technique replaces
some of the calls by the modified body of
the called procedure, hence eliminating
the overhead.
Furthermore, as the calling and called procedure
are now integrated, they can be optimized
together, using other techniques of the optimizer.
This often leads to extra opportunities for
optimization
.[
ball predicting effects
.]
.[
carter code generation cacm
.]
.[
scheifler inline cacm
.]
.PP
An inline substitution of a call to a procedure P increases
the size of the program, unless P is very small or P is
called only once.
In the latter case, P can be eliminated.
In practice, procedures that are called only once occur
quite frequently, due to the
introduction of structured programming.
(Carter
.[
carter umi ann arbor
.]
states that almost 50% of the Pascal procedures
he analyzed were called just once).
.PP
Scheifler
.[
scheifler inline cacm
.]
has a more general view of inline substitution.
In his model, the program under consideration is
allowed to grow by a certain amount,
i.e. code size is sacrificed to speed up the program.
The above two cases are just special cases of
his model, obtained by setting the size-change to
(approximately) zero.
He formulates the substitution problem as follows:
.IP
"Given a program, a subset of all invocations,
a maximum program size, and a maximum procedure size,
find a sequence of substitutions that minimizes
the expected execution time."
.LP
Scheifler shows that this problem is NP-complete
.[~[
aho hopcroft ullman analysis algorithms
.], chapter 10]
by reduction to the Knapsack Problem.
Heuristics will have to be used to find a near-optimal
solution.
.PP
In the following chapters we will extend
Scheifler's view and adapt it to the EM Global Optimizer.
We will first describe the transformations that have
to be applied to the EM text when a call is substituted
in line.
Next we will examine in which cases inline substitution
is not possible or desirable.
Heuristics will be developed for
chosing a good sequence of substitutions.
These heuristics make no demand on the user
(such as making profiles
.[
scheifler inline cacm
.]
or giving pragmats
.[~[
ichbiah ada military standard
.], section 6.3.2]),
although the model could easily be extended
to use such information.
Finally, we will discuss the implementation
of the IL phase of the optimizer.
.PP
We will often use the term inline expansion
as a synonym of inline substitution.
.sp 0
The inverse technique of procedure abstraction
(automatic subroutine generation)
.[
shaffer subroutine generation
.]
will not be discussed in this report.

93
doc/ego/il/il2
View file

@ -1,93 +0,0 @@
.NH 2
Parameters and local variables.
.PP
In the EM calling sequence, the calling procedure
pushes its parameters on the stack
before doing the CAL.
The called routine first saves some
status information on the stack and then
allocates space for its own locals
(also on the stack).
Usually, one special purpose register,
the Local Base (LB) register,
is used to access both the locals and the
parameters.
If memory is highly segmented,
the stack frames of the caller and the callee
may be allocated in different fragments;
an extra Argument Base (AB) register is used
in this case to access the actual parameters.
See 4.2 of
.[
keizer architecture
.]
for further details.
.PP
If a procedure call is expanded in line,
there are two problems:
.IP 1. 3
No stack frame will be allocated for the called procedure;
we must find another place to put its locals.
.IP 2.
The LB register cannot be used to access the actual
parameters;
as the CAL instruction is deleted, the LB will
still point to the local base of the \fIcalling\fR procedure.
.LP
The local variables of the called procedure will
be put in the stack frame of the calling procedure,
just after its own locals.
The size of the stack frame of the
calling procedure will be increased
during its entire lifetime.
Therefore our model will allow a
limit to be set on the number of bytes
for locals that the called procedure may have
(see next section).
.PP
There are several alternatives to access the parameters.
An actual parameter may be any auxiliary expression,
which we will refer to as
the \fIactual parameter expression\fR.
The value of this expression is stored
in a location on the stack (see above),
the \fIparameter location\fR.
.sp 0
The alternatives for accessing parameters are:
.IP -
save the value of the stackpointer at the point of the CAL
in a temporary variable X;
this variable can be used to simulate the AB register, i.e.
parameter locations are accessed via an offset to
the value of X.
.IP -
create a new temporary local variable T for
the parameter (in the stack frame of the caller);
every access to the parameter location must be changed
into an access to T.
.IP -
do not evaluate the actual parameter expression before the call;
instead, substitute this expression for every use of the
parameter location.
.LP
The first method may be expensive if X is not
put in a register.
We will not use this method.
The time required to evaluate and access the
parameters when the second method is used
will not differ much from the normal
calling sequence (i.e. not in line call).
It is not expensive, but there are no
extra savings either.
The third method is essentially the 'by name'
parameter mechanism of Algol60.
If the actual parameter is just a numeric constant,
it is advantageous to use it.
Yet, there are several circumstances
under which it cannot or should not be used.
We will deal with this in the next section.
.sp 0
In general we will use the third method,
if it is possible and desirable.
Such parameters will be called \fIin line parameters\fR.
In all other cases we will use the second method.

164
doc/ego/il/il3
View file

@ -1,164 +0,0 @@
.NH 2
Feasibility and desirability analysis
.PP
Feasibility and desirability analysis
of in line substitution differ
somewhat from most other techniques.
Usually, much effort is needed to find
a feasible opportunity for optimization
(e.g. a redundant subexpression).
Desirability analysis then checks
if it is really advantageous to do
the optimization.
For IL, opportunities are easy to find.
To see if an in line expansion is
desirable will not be hard either.
Yet, the main problem is to find the most
desirable ones.
We will deal with this problem later and
we will first attend feasibility and
desirability analysis.
.PP
There are several reasons why a procedure invocation
cannot or should not be expanded in line.
.sp
A call to a procedure P cannot be expanded in line
in any of the following cases:
.IP 1. 3
The body of P is not available as EM text.
Clearly, there is no way to do the substitution.
.IP 2.
P, or any procedure called by P (transitively),
follows the chain of statically enclosing
procedures (via a LXL or LXA instruction)
or follows the chain of dynamically enclosing
procedures (via a DCH).
If the call were expanded in line,
one level would be removed from the chains,
leading to total chaos.
This chaos could be solved by patching up
every LXL, LXA or DCH in all procedures
that could be part of the chains,
but this is hard to implement.
.IP 3.
P, or any procedure called by P (transitively),
calls a procedure whose body is not
available as EM text.
The unknown procedure may use an LXL, LXA or DCH.
However, in several languages a separately
compiled procedure has no access to the
static or dynamic chain.
In this case
this point does not apply.
.IP 4.
P, or any procedure called by P (transitively),
uses the LPB instruction, which converts a
local base to an argument base;
as the locals and parameters are stored
in a non-standard way (differing from the
normal EM calling sequence) this instruction
would yield incorrect results.
.IP 5.
The total number of bytes of the parameters
of P is not known.
P may be a procedure with a variable number
of parameters or may have an array of dynamic size
as value parameter.
.LP
It is undesirable to expand a call to a procedure P in line
in any of the following cases:
.IP 1. 3
P is large, i.e. the number of EM instructions
of P exceeds some threshold.
The expanded code would be large too.
Furthermore, several programs in ACK,
including the global optimizer itself,
may run out of memory if they they have to run
in a small address space and are provided
very large procedures.
The threshold may be set to infinite,
in which case this point does not apply.
.IP 2.
P has many local variables.
All these variables would have to be allocated
in the stack frame of the calling procedure.
.PP
If a call may be expanded in line, we have to
decide how to access its parameters.
In the previous section we stated that we would
use in line parameters whenever possible and desirable.
There are several reasons why a parameter
cannot or should not be expanded in line.
.sp
No parameter of a procedure P can be expanded in line,
in any of the following cases:
.IP 1. 3
P, or any procedure called by P (transitively),
does a store-indirect or a use-indirect (i.e. through
a pointer).
However, if the front-end has generated messages
telling that certain parameters can not be accessed
indirectly, those parameters may be expanded in line.
.IP 2.
P, or any procedure called by P (transitively),
calls a procedure whose body is not available as EM text.
The unknown procedure may do a store-indirect
or a use-indirect.
However, the same remark about front-end messages
as for 1. holds here.
.IP 3.
The address of a parameter location is taken (via a LAL).
In the normal calling sequence, all parameters
are stored sequentially. If the address of one
parameter location is taken, the address of any
other parameter location can be computed from it.
Hence we must put every parameter in a temporary location;
furthermore, all these locations must be in
the same order as for the normal calling sequence.
.IP 4.
P has overlapping parameters; for example, it uses
the parameter at offset 10 both as a 2 byte and as a 4 byte
parameter.
Such code may be produced by the front ends if
the formal parameter is of some record type
with variants.
.PP
Sometimes a specific parameter must not be expanded in line.
.sp 0
An actual parameter expression cannot be expanded in line
in any of the following cases:
.IP 1. 3
P stores into the parameter location.
Even if the actual parameter expression is a simple
variable, it is incorrect to change the 'store into
formal' into a 'store into actual', because of
the parameter mechanism used.
In Pascal, the following expansion is incorrect:
.DS
procedure p (x:integer);
begin
x := 20;
end;
\&...
a := 10; \kxa := 10;
p(a); ---> \h'|\nxu'a := 20;
write(a); \h'|\nxu'write(a);
.DE
.IP 2.
P changes any of the operands of the
actual parameter expression.
If the expression is expanded and evaluated
after the operand has been changed,
the wrong value will be used.
.IP 3.
The actual parameter expression has side effects.
It must be evaluated only once,
at the place of the call.
.LP
It is undesirable to expand an actual parameter in line
in the following case:
.IP 1. 3
The parameter is used more than once
(dynamically) and the actual parameter expression
is not just a simple variable or constant.
.LP

135
doc/ego/il/il4
View file

@ -1,135 +0,0 @@
.NH 2
Heuristic rules
.PP
Using the information described
in the previous section,
we can find all calls that can
be expanded in line, and for which
this expansion is desirable.
In general, we cannot expand all these calls,
so we have to choose the 'best' ones.
With every CAL instruction
that may be expanded, we associate
a \fIpay off\fR,
which expresses how desirable it is
to expand this specific CAL.
.sp
Let Tc denote the portion of EM text involved
in a specific call, i.e. the pushing of the actual
parameter expressions, the CAL itself,
the popping of the parameters and the
pushing of the result (if any, via an LFR).
Let Te denote the EM text that would be obtained
by expanding the call in line.
Let Pc be the original program and Pe the program
with Te substituted for Tc.
The pay off of the CAL depends on two factors:
.IP -
T = execution_time(Pe) - execution_time(Pc)
.IP -
S = code_size(Pe) - code_size(Pc)
.LP
The change in execution time (T) depends on:
.IP -
T1 = execution_time(Te) - execution_time(Tc)
.IP -
N = number of times Te or Tc get executed.
.LP
We assume that T1 will be the same every
time the code gets executed.
This is a reasonable assumption.
(Note that we are talking about one CAL,
not about different calls to the same procedure).
Hence
.DS
T = N * T1
.DE
T1 can be estimated by a careful analysis
of the transformations that are performed.
Below, we list everything that will be
different when a call is expanded in line:
.IP -
The CAL instruction is not executed.
This saves a subroutine jump.
.IP -
The instructions in the procedure prolog
are not executed.
These instructions, generated from the PRO pseudo,
save some machine registers
(including the old LB), set the new LB and allocate space
for the locals of the called routine.
The savings may be less if there are no
locals to allocate.
.IP -
In line parameters are not evaluated before the call
and are not pushed on the stack.
.IP -
All remaining parameters are stored in local variables,
instead of being pushed on the stack.
.IP -
If the number of parameters is nonzero,
the ASP instruction after the CAL is not executed.
.IP -
Every reference to an in line parameter is
substituted by the parameter expression.
.IP -
RET (return) instructions are replaced by
BRA (branch) instructions.
If the called procedure 'falls through'
(i.e. it has only one RET, at the end of its code),
even the BRA is not needed.
.IP -
The LFR (fetch function result) is not executed
.PP
Besides these changes, which are caused directly by IL,
other changes may occur as IL influences other optimization
techniques, such as Register Allocation and Constant Propagation.
Our heuristic rules do not take into account the quite
inpredictable effects on Register Allocation.
It does, however, favour calls that have numeric \fIconstants\fR
as parameter; especially the constant "0" as an inline
parameter gets high scores,
as further optimizations may often be possible.
.PP
It cannot be determined statically how often a CAL instruction gets
executed.
We will use \fIloop nesting\fR information here.
The nesting level of the loop in which
the CAL appears (if any) will be used as an
indication for the number of times it gets executed.
.PP
Based on all these facts,
the pay off of a call will be computed.
The following model was developed empirically.
Assume procedure P calls procedure Q.
The call takes place in basic block B.
.DS
.TS
l l l.
ZP \&= # zero parameters
CP \&= # constant parameters - ZP
LN \&= Loop Nesting level (0 if outside any loop)
F \&= \fIif\fR # formal parameters of Q > 0 \fIthen\fR 1 \fIelse\fR 0
FT \&= \fIif\fR Q falls through \fIthen\fR 1 \fIelse\fR 0
S \&= size(Q) - 1 - # inline_parameters - F
L \&= \fIif\fR # local variables of P > 0 \fIthen\fR 0 \fIelse\fR -1
A \&= CP + 2 * ZP
N \&= \fIif\fR LN=0 and P is never called from a loop \fIthen\fR 0 \fIelse\fR (LN+1)**2
FM \&= \fIif\fR B is a firm block \fIthen\fR 2 \fIelse\fR 1
pay_off \&= (100/S + FT + F + L + A) * N * FM
.TE
.DE
S stands for the size increase of the program,
which is slightly less than the size of Q.
The size of a procedure is taken to be its number
of (non-pseudo) EM instructions.
The terms "loop nesting level" and "firm" were defined
in the chapter on the Intermediate Code (section "loop tables").
If a call is not inside a loop and the calling procedure
is itself never called from a loop (transitively),
then the call will probably be executed at most once.
Such a call is never expanded in line (its pay off is zero).
If the calling procedure doesn't have local variables, a penalty (L)
is introduced, as it will most likely get local variables if the
call gets expanded.

446
doc/ego/il/il5
View file

@ -1,446 +0,0 @@
.NH 2
Implementation
.PP
A major factor in the implementation
of Inline Substitution is the requirement
not to use an excessive amount of memory.
IL essentially analyzes the entire program;
it makes decisions based on which procedure calls
appear in the whole program.
Yet, because of the memory restriction, it is
not feasible to read the entire program
in main memory.
To solve this problem, the IL phase has been
split up into three subphases that are executed sequentially:
.IP 1.
analyze every procedure; see how it accesses its parameters;
simultaneously collect all calls
appearing in the whole program an put them
in a \fIcall-list\fR.
.IP 2.
use the call-list and decide which calls will be substituted
in line.
.IP 3.
take the decisions of subphase 2 and modify the
program accordingly.
.LP
Subphases 1 and 3 scan the input program; only
subphase 3 modifies it.
It is essential that the decisions can be made
in subphase 2
without using the input program,
provided that subphase 1 puts enough information
in the call-list.
Subphase 2 keeps the entire call-list in main memory
and repeatedly scans it, to
find the next best candidate for expansion.
.PP
We will specify the
data structures used by IL before
describing the subphases.
.NH 3
Data structures
.NH 4
The procedure table
.PP
In subphase 1 information is gathered about every procedure
and added to the procedure table.
This information is used by the heuristic rules.
A proctable entry for procedure p has
the following extra information:
.IP -
is it allowed to substitute an invocation of p in line?
.IP -
is it allowed to put any parameter of such a call in line?
.IP -
the size of p (number of EM instructions)
.IP -
does p 'fall through'?
.IP -
a description of the formal parameters that p accesses; this information
is obtained by looking at the code of p. For every parameter f,
we record:
.RS
.IP -
the offset of f
.IP -
the type of f (word, double word, pointer)
.IP -
may the corresponding actual parameter be put in line?
.IP -
is f ever accessed indirectly?
.IP -
if f used: never, once or more than once?
.RE
.IP -
the number of times p is called (see below)
.IP -
the file address of its call-count information (see below).
.LP
.NH 4
Call-count information
.PP
As a result of Inline Substitution, some procedures may
become useless, because all their invocations have been
substituted in line.
One of the tasks of IL is to keep track which
procedures are no longer called.
Note that IL is especially keen on procedures that are
called only once
(possibly as a result of expanding all other calls to it).
So we want to know how many times a procedure
is called \fIduring\fR Inline Substitution.
It is not good enough to compute this
information afterwards.
The task is rather complex, because
the number of times a procedure is called
varies during the entire process:
.IP 1.
If a call to p is substituted in line,
the number of calls to p gets decremented by 1.
.IP 2.
If a call to p is substituted in line,
and p contains n calls to q, then the number of calls to q
gets incremented by n.
.IP 3.
If a procedure p is removed (because it is no
longer called) and p contains n calls to q,
then the number of calls to q gets decremented by n.
.LP
(Note that p may be the same as q, if p is recursive).
.sp 0
So we actually want to have the following information:
.DS
NRCALL(p,q) = number of call to q appearing in p,
for all procedures p and q that may be put in line.
.DE
This information, called \fIcall-count information\fR is
computed by the first subphase.
It is stored in a file.
It is represented as a number of lists, rather than as
a (very sparse) matrix.
Every procedure has a list of (proc,count) pairs,
telling which procedures it calls, and how many times.
The file address of its call-count list is stored
in its proctable entry.
Whenever this information is needed, it is fetched from
the file, using direct access.
The proctable entry also contains the number of times
a procedure is called, at any moment.
.NH 4
The call-list
.PP
The call-list is the major data structure use by IL.
Every item of the list describes one procedure call.
It contains the following attributes:
.IP -
the calling procedure (caller)
.IP -
the called procedure (callee)
.IP -
identification of the CAL instruction (sequence number)
.IP -
the loop nesting level; our heuristic rules appreciate
calls inside a loop (or even inside a loop nested inside
another loop, etc.) more than other calls
.IP -
the actual parameter expressions involved in the call;
for every actual, we record:
.RS
.IP -
the EM code of the expression
.IP -
the number of bytes of its result (size)
.IP -
an indication if the actual may be put in line
.RE
.LP
The structure of the call-list is rather complex.
Whenever a call is expanded in line, new calls
will suddenly appear in the program,
that were not contained in the original body
of the calling subroutine.
These calls are inherited from the called procedure.
We will refer to these invocations as \fInested calls\fR
(see Fig. 5.1).
.DS
.TS
lw(2.5i) l.
procedure p is
begin .
a(); .
b(); .
end;
.TE
.TS
lw(2.5i) l.
procedure r is procedure r is
begin begin
x(); x();
p(); -- in line a(); -- nested call
y(); b(); -- nested call
end; y();
end;
.TE
Fig. 5.1 Example of nested procedure calls
.DE
Nested calls may subsequently be put in line too
(probably resulting in a yet deeper nesting level, etc.).
So the call-list does not always reflect the source program,
but changes dynamically, as decisions are made.
If a call to p is expanded, all calls appearing in p
will be added to the call-list.
.sp 0
A convenient and elegant way to represent
the call-list is to use a LISP-like list.
.[
poel lisp trac
.]
Calls that appear at the same level
are linked in the CDR direction. If a call C
to a procedure p is expanded,
all calls appearing in p are put in a sub-list
of C, i.e. in its CAR.
In the example above, before the decision
to expand the call to p is made, the
call-list of procedure r looks like:
.DS
(call-to-x, call-to-p, call-to-y)
.DE
After the decision, it looks like:
.DS
(call-to-x, (call-to-p*, call-to-a, call-to-b), call-to-y)
.DE
The call to p is marked, because it has been
substituted.
Whenever IL wants to traverse the call-list of some procedure,
it uses the well-known LISP technique of
recursion in the CAR direction and
iteration in the CDR direction
(see page 1.19-2 of
.[
poel lisp trac
.]
).
All list traversals look like:
.DS
traverse(list)
{
for (c = first(list); c != 0; c = CDR(c)) {
if (c is marked) {
traverse(CAR(c));
} else {
do something with c
}
}
}
.DE
The entire call-list consists of a number of LISP-like lists,
one for every procedure.
The proctable entry of a procedure contains a pointer
to the beginning of the list.
.NH 3
The first subphase: procedure analysis
.PP
The tasks of the first subphase are to determine
several attributes of every procedure
and to construct the basic call-list,
i.e. without nested calls.
The size of a procedure is determined
by simply counting its EM instructions.
Pseudo instructions are skipped.
A procedure does not 'fall through' if its CFG
contains a basic block
that is not the last block of the CFG and
that ends on a RET instruction.
The formal parameters of a procedure are determined
by inspection of
its code.
.PP
The call-list in constructed by looking at all CAL instructions
appearing in the program.
The call-list should only contain calls to procedures
that may be put in line.
This fact is only known if the procedure was
analyzed earlier.
If a call to a procedure p appears in the program
before the body of p,
the call will always be put in the call-list.
If p is later found to be unsuitable,
the call will be removed from the list by the
second subphase.
.PP
An important issue is the recognition
of the actual parameter expressions of the call.
The front ends produces messages telling how many
bytes of formal parameters every procedure accesses.
(If there is no such message for a procedure, it
cannot be put in line).
The actual parameters together must account for
the same number of bytes.A recursive descent parser is used
to parse side-effect free EM expressions.
It uses a table and some
auxiliary routines to determine
how many bytes every EM instruction pops from the stack
and how many bytes it pushes onto the stack.
These numbers depend on the EM instruction, its argument,
and the wordsize and pointersize of the target machine.
Initially, the parser has to recognize the
number of bytes specified in the formals-message,
say N.
Assume the first instruction before the CAL pops S bytes
and pushes R bytes.
If R > N, too many bytes are recognized
and the parser fails.
Else, it calls itself recursively to recognize the
S bytes used as operand of the instruction.
If it succeeds in doing so, it continues with the next instruction,
i.e. the first instruction before the code recognized by
the recursive call, to recognize N-R more bytes.
The result is a number of EM instructions that collectively push N bytes.
If an instruction is come across that has side-effects
(e.g. a store or a procedure call) or of which R and S cannot
be computed statically (e.g. a LOS), it fails.
.sp 0
Note that the parser traverses the code backwards.
As EM code is essentially postfix code, the parser works top down.
.PP
If the parser fails to recognize the parameters, the call will not
be substituted in line.
If the parameters can be determined, they still have to
match the formal parameters of the called procedure.
This check is performed by the second subphase; it cannot be
done here, because it is possible that the called
procedure has not been analyzed yet.
.PP
The entire call-list is written to a file,
to be processed by the second subphase.
.NH 3
The second subphase: making decisions
.PP
The task of the second subphase is quite easy
to understand.
It reads the call-list file,
builds an incore call-list and deletes every
call that may not be expanded in line (either because the called
procedure may not be put in line, or because the actual parameters
of the call do not match the formal parameters of the called procedure).
It assigns a \fIpay-off\fR to every call,
indicating how desirable it is to expand it.
.PP
The subphase repeatedly scans the call-list and takes
the call with the highest ratio.
The chosen one gets marked,
and the call-list is extended with the nested calls,
as described above.
These nested calls are also assigned a ratio,
and will be considered too during the next scans.
.sp 0
After every decision the number of times
every procedure is called is updated, using
the call-count information.
Meanwhile, the subphase keeps track of the amount of space left
available.
If all space is used, or if there are no more calls left to
be expanded, it exits this loop.
Finally, calls to procedures that are called only
once are also chosen.
.PP
The actual parameters of a call are only needed by
this subphase to assign a ratio to a call.
To save some space, these actuals are not kept in main memory.
They are removed after the call has been read and a ratio
has been assigned to it.
So this subphase works with \fIabstracts\fR of calls.
After all work has been done,
the actual parameters of the chosen calls are retrieved
from a file,
as they are needed by the transformation subphase.
.NH 3
The third subphase: doing transformations
.PP
The third subphase makes the actual modifications to
the EM text.
It is directed by the decisions made in the previous subphase,
as expressed via the call-list.
The call-list read by this subphase contains
only calls that were selected for expansion.
The list is ordered in the same way as the EM text,
i.e. if a call C1 appears before a call C2 in the call-list,
C1 also appears before C2 in the EM text.
So the EM text is traversed linearly,
the calls that have to be substituted are determined
and the modifications are made.
If a procedure is come across that is no longer needed,
it is simply not written to the output EM file.
The substitution of a call takes place in distinct steps:
.IP "change the calling sequence" 7
.sp 0
The actual parameter expressions are changed.
Parameters that are put in line are removed.
All remaining ones must store their result in a
temporary local variable, rather than
push it on the stack.
The CAL instruction and any ASP (to pop actual parameters)
or LFR (to fetch the result of a function)
are deleted.
.IP "fetch the text of the called procedure"
.sp 0
Direct disk access is used to to read the text of the
called procedure.
The file offset is obtained from the proctable entry.
.IP "allocate bytes for locals and temporaries"
.sp 0
The local variables of the called procedure will be put in the
stack frame of the calling procedure.
The same applies to any temporary variables
that hold the result of parameters
that were not put in line.
The proctable entry of the caller is updated.
.IP "put a label after the CAL"
.sp 0
If the called procedure contains a RET (return) instruction
somewhere in the middle of its text (i.e. it does
not fall through), the RET must be changed into
a BRA (branch), to jump over the
remainder of the text.
This label is not needed if the called
procedure falls through.
.IP "copy the text of the called procedure and modify it"
.sp 0
References to local variables of the called routine
and to parameters that are not put in line
are changed to refer to the
new local of the caller.
References to in line parameters are replaced
by the actual parameter expression.
Returns (RETs) are either deleted or
replaced by a BRA.
Messages containing information about local
variables or parameters are changed.
Global data declarations and the PRO and END pseudos
are removed.
Instruction labels and references to them are
changed to make sure they do not have the
same identifying number as
labels in the calling procedure.
.IP "insert the modified text"
.sp 0
The pseudos of the called procedure are put after the pseudos
of the calling procedure.
The real text of the callee is put at
the place where the CAL was.
.IP "take care of nested substitutions"
.sp 0
The expanded procedure may contain calls that
have to be expanded too (nested calls).
If the descriptor of this call contains actual
parameter expressions,
the code of the expressions has to be changed
the same way as the code of the callee was changed.
Next, the entire process of finding CALs and doing
the substitutions is repeated recursively.
.LP

27
doc/ego/il/il6
View file

@ -1,27 +0,0 @@
.NH 2
Source files of IL
.PP
The sources of IL are in the following files
and packages (the prefixes 1_, 2_ and 3_ refer to the three subphases):
.IP il.h: 14
declarations of global variables and
data structures
.IP il.c:
the routine main; the driving routines of the three subphases
.IP 1_anal:
contains a subroutine that analyzes a procedure
.IP 1_cal:
contains a subroutine that analyzes a call
.IP 1_aux:
implements auxiliary procedures used by subphase 1
.IP 2_aux:
implements auxiliary procedures used by subphase 2
.IP 3_subst:
the driving routine for doing the substitution
.IP 3_change:
lower level routines that do certain modifications
.IP 3_aux:
implements auxiliary procedures used by subphase 3
.IP aux:
implements auxiliary procedures used by several subphases.
.LP

3
doc/ego/intro/.distr
View file

@ -1,3 +0,0 @@
head
intro1
tail

10
doc/ego/intro/head
View file

@ -1,10 +0,0 @@
.ND
.\".ll 80m
.\".nr LL 80m
.\".nr tl 78m
.tr ~
.ds >. .
.ds >, ,
.ds [. " [
.ds .] ]
.cs 5 22

79
doc/ego/intro/intro1
View file

@ -1,79 +0,0 @@
.TL
The design and implementation of
the EM Global Optimizer
.AU
H.E. Bal
.AI
Vrije Universiteit
Wiskundig Seminarium, Amsterdam
.AB
The EM Global Optimizer is part of the Amsterdam Compiler Kit,
a toolkit for making retargetable compilers.
It optimizes the intermediate code common to all compilers of
the toolkit (EM),
so it can be used for all programming languages and
all processors supported by the kit.
.PP
The optimizer is based on well-understood concepts like
control flow analysis and data flow analysis.
It performs the following optimizations:
Inline Substitution, Strength Reduction, Common Subexpression Elimination,
Stack Pollution, Cross Jumping, Branch Optimization, Copy Propagation,
Constant Propagation, Dead Code Elimination and Register Allocation.
.PP
This report describes the design of the optimizer and several
of its implementation issues.
.AE
.bp
.NH 1
Introduction
.PP
.FS
This work was supported by the
Stichting Technische Wetenschappen (STW)
under grant VWI00.0001.
.FE
The EM Global Optimizer is part of a software toolkit
for making production-quality retargetable compilers.
This toolkit,
called the Amsterdam Compiler Kit
.[
tanenbaum toolkit rapport
.]
.[
tanenbaum toolkit cacm
.]
runs under the Unix*
.FS
*Unix is a Trademark of Bell Laboratories
.FE
operating system.
.sp 0
The main design philosophy of the toolkit is to use
a language- and machine-independent
intermediate code, called EM.
.[
keizer architecture
.]
The basic compilation process can be split up into
two parts.
A language-specific front end translates the source program into EM.
A machine-specific back end transforms EM to assembly code
of the target machine.
.PP
The global optimizer is an optional phase of the
compilation process, and can be used to obtain
machine code of a higher quality.
The optimizer transforms EM-code to better EM-code,
so it comes between the front end and the back end.
It can be used with any combination of languages
and machines, as far as they are supported by
the compiler kit.
.PP
This report describes the design of the
global optimizer and several of its
implementation issues.
Measurements can be found in.
.[
bal tanenbaum global
.]

17
doc/ego/intro/tail
View file

@ -1,17 +0,0 @@
.SH
Acknowledgements
.PP
The author would like to thank Andy Tanenbaum for his guidance,
Duk Bekema for implementing the Common Subexpression Elimination phase
and writing the initial documentation of that phase,
Dick Grune for reading the manuscript of this report
and Ceriel Jacobs, Ed Keizer, Martin Kersten, Hans van Staveren
and the members of the S.T.W. user's group for their
interest and assistance.
.bp
.SH
References
.LP
.[
$LIST$
.]

1
doc/ego/lv/.distr
View file

@ -1 +0,0 @@
lv1

95
doc/ego/lv/lv1
View file

@ -1,95 +0,0 @@
.bp
.NH 1
Live-Variable analysis
.NH 2
Introduction
.PP
The "Live-Variable analysis" optimization technique (LV)
performs some code improvements and computes information that may be
used by subsequent optimizations.
The main task of this phase is the
computation of \fIlive-variable information\fR.
.[~[
aho compiler design
.] section 14.4]
A variable A is said to be \fIdead\fR at some point p of the
program text, if on no path in the control flow graph
from p to a RET (return), A can be used before being changed;
else A is said to be \fIlive\fR.
.PP
A statement of the form
.DS
VARIABLE := EXPRESSION
.DE
is said to be dead if the left hand side variable is dead just after
the statement and the right hand side expression has no
side effects (i.e. it doesn't change any variable).
Such a statement can be eliminated entirely.
Dead code will seldom be present in the original program,
but it may be the result of earlier optimizations,
such as copy propagation.
.PP
Live-variable information is passed to other phases via
messages in the EM code.
Live/dead messages are generated at points in the EM text where
variables become dead or live.
This information is especially useful for the Register
Allocation phase.
.NH 2
Implementation
.PP
The implementation uses algorithm 14.6 of.
.[
aho compiler design
.]
First two sets DEF and USE are computed for every basic block b:
.IP DEF(b) 9
the set of all variables that are assigned a value in b before
being used
.IP USE(b) 9
the set of all variables that may be used in b before being changed.
.LP
(So variables that may, but need not, be used resp. changed via a procedure
call or through a pointer are included in USE but not in DEF).
The next step is to compute the sets IN and OUT :
.IP IN[b] 9
the set of all variables that are live at the beginning of b
.IP OUT[b] 9
the set of all variables that are live at the end of b
.LP
IN and OUT can be computed for all blocks simultaneously by solving the
data flow equations:
.DS
(1) IN[b] = OUT[b] - DEF[b] + USE[b]
[2] OUT[b] = IN[s1] + ... + IN[sn] ;
where SUCC[b] = {s1, ... , sn}
.DE
The equations are solved by a similar algorithm as for
the Use Definition equations (see previous chapter).
.PP
Finally, each basic block is visited in turn to remove its dead code
and to emit the live/dead messages.
Every basic block b is traversed from its last
instruction backwards to the beginning of b.
Initially, all variables that are dead at the end
of b are marked dead. All others are marked live.
If we come across an assignment to a variable X that
was marked live, a live-message is put after the
assignment and X is marked dead;
if X was marked dead, the assignment may be removed, provided that
the right hand side expression contains no side effects.
If we come across a use of a variable X that
was marked dead, a dead-message is put after the
use and X is marked live.
So at any point, the mark of X tells whether X is
live or dead immediately before that point.
A message is also generated at the start of a basic block
for every variable that was live at the end of the (textually)
previous block, but dead at the entry of this block, or v.v.
.PP
Only local variables are considered.
This significantly reduces the memory needed by this phase,
eases the implementation and is hardly less efficient than
considering all variables.
(Note that it is very hard to prove that an assignment to
a global variable is dead).

1
doc/ego/ov/.distr
View file

@ -1 +0,0 @@
ov1

Some files were not shown because too many files have changed in this diff Show more