Index: INSTALL =================================================================== --- INSTALL (revision e21c72d5e2c7ca2735fce0ab2c4d00dc249711cc) +++ INSTALL (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) @@ -3,6 +3,6 @@ Cforall is built using GNU Make and the GNU Autoconf system. It also requires -g++ version 4, bison and flex. On systems where GNU Make is the default make -it may suffice to build the system by entering the commands +g++ version >= 4.6, bison and flex. On systems where GNU Make is the default +make, the system is built by entering the commands: ./configure @@ -17,9 +17,9 @@ --prefix=/some/directory controls the path prefix common to all installed - cfa-cc components. Some components will be installed in /some/directory/bin, + cfa-cc components. Some components are installed in /some/directory/bin, others in /some/directory/lib. If unspecified, this defaults to /usr/local. - If you wish to use (a subdirectory of) your home directory, ${HOME}/some/dir - works, but it is important not to put quotes around the directory path; - Cforall may appear to build, but the installed version may not work properly. + To use (a subdirectory of) your home directory, ${HOME}/some/dir works, but + it is important not to put quotes around the directory path; Cforall may + appear to build, but the installed version may not work properly. --with-backend-compiler=PROGRAM specifies the installed path of gcc. It Index: doc/LaTeXmacros/common.tex =================================================================== --- doc/LaTeXmacros/common.tex (revision e21c72d5e2c7ca2735fce0ab2c4d00dc249711cc) +++ doc/LaTeXmacros/common.tex (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) @@ -11,18 +11,16 @@ %% Created On : Sat Apr 9 10:06:17 2016 %% Last Modified By : Peter A. Buhr -%% Last Modified On : Tue Jul 12 20:37:57 2016 -%% Update Count : 206 +%% Last Modified On : Mon Aug 1 09:11:20 2016 +%% Update Count : 225 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% - -%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% \setlength{\textheight}{9in} %\oddsidemargin 0.0in -\renewcommand{\topfraction}{0.8} % float must be greater than X of the page before it is forced onto its own page -\renewcommand{\bottomfraction}{0.8} % float must be greater than X of the page before it is forced onto its own page +\renewcommand{\topfraction}{0.8} % float must be greater than X of the page before it is forced onto its own page +\renewcommand{\bottomfraction}{0.8} % float must be greater than X of the page before it is forced onto its own page \renewcommand{\floatpagefraction}{0.8} % float must be greater than X of the page before it is forced onto its own page -\renewcommand{\textfraction}{0.0} % the entire page maybe devoted to floats with no text on the page at all - -\lefthyphenmin=4 +\renewcommand{\textfraction}{0.0} % the entire page maybe devoted to floats with no text on the page at all + +\lefthyphenmin=4 % hyphen only after 4 characters \righthyphenmin=4 @@ -38,8 +36,9 @@ % Names used in the document. -\newcommand{\CFA}{C$\mathbf\forall$\xspace} % set language symbolic name -\newcommand{\CFL}{Cforall\xspace} % set language text name +\newcommand{\CFA}{C$\mathbf\forall$\xspace} % set language symbolic name +\newcommand{\CFL}{Cforall\xspace} % set language text name \newcommand{\CC}{\rm C\kern-.1em\hbox{+\kern-.25em+}\xspace} % CC symbolic name -\def\c11{ISO/IEC C} % C11 name (cannot have numbers in latex command name) +\newcommand{\CCeleven}{\rm C\kern-.1em\hbox{+\kern-.25em+}11\xspace} % C++11 symbolic name +\def\c11{ISO/IEC C} % C11 name (cannot have numbers in latex command name) %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @@ -51,5 +50,5 @@ \setlength{\parindentlnth}{\parindent} -\newlength{\gcolumnposn} +\newlength{\gcolumnposn} % temporary hack because lstlisting does handle tabs correctly \newlength{\columnposn} \setlength{\gcolumnposn}{2.5in} @@ -62,6 +61,6 @@ %\patchcmd{\lsthk@TextStyle}{\let\lst@DefEsc\@empty}{}{}{\errmessage{failed to patch}} -\usepackage{pslatex} % reduce size of san serif font -\usepackage{relsize} % must be after change to small or selects old size +\usepackage{pslatex} % reduce size of san serif font +\usepackage{relsize} % must be after change to small or selects old size % reduce size of chapter/section titles @@ -119,12 +118,13 @@ % inline text and lowercase index: \Index{inline and lowercase index text} +\newcommand{\Index}{\@ifstar\@sIndex\@Index} % inline text and as-in index: \Index[as-is index text]{inline text} +\newcommand{\@Index}[2][\@empty]{\lowercase{\def\temp{#2}}#2\ifx#1\@empty\index{\temp}\else\index{#1@{\protect#2}}\fi} % inline text but index with different as-is text: \Index[index text]{inline text} -\newcommand{\Index}{\@ifstar\@sIndex\@Index} -\newcommand{\@Index}[2][\@empty]{\lowercase{\def\temp{#2}}#2\ifx#1\@empty\index{\temp}\else\index{#1@{\protect#2}}\fi} \newcommand{\@sIndex}[2][\@empty]{#2\ifx#1\@empty\index{#2}\else\index{#1@{\protect#2}}\fi} -% cannot use © +% inline text and code index (cannot use ©) \newcommand{\Indexc}[1]{\lstinline$#1$\index{#1@\lstinline$#1$}} +% code index (cannot use ©) \newcommand{\indexc}[1]{\index{#1@\lstinline$#1$}} @@ -136,4 +136,21 @@ \newcommand{\@newterm}[2][\@empty]{\lowercase{\def\temp{#2}}{\newtermFontInline{#2}}\ifx#1\@empty\index{\temp}\else\index{#1@{\protect#2}}\fi} \newcommand{\@snewterm}[2][\@empty]{{\newtermFontInline{#2}}\ifx#1\@empty\index{#2}\else\index{#1@{\protect#2}}\fi} + +% Latin abbreviation +\newcommand{\abbrevFont}{\textit} % set empty for no italics +\newcommand*{\eg}{% + \@ifnextchar{,}{\abbrevFont{e}.\abbrevFont{g}.}% + {\@ifnextchar{:}{\abbrevFont{e}.\abbrevFont{g}.}% + {\abbrevFont{e}.\abbrevFont{g}.,\xspace}}% +}% +\newcommand*{\ie}{% + \@ifnextchar{,}{\abbrevFont{i}.\abbrevFont{e}.}% + {\@ifnextchar{:}{\abbrevFont{i}.\abbrevFont{e}.}% + {\abbrevFont{i}.\abbrevFont{e}.,\xspace}}% +}% +\newcommand*{\etc}{% + \@ifnextchar{.}{\abbrevFont{etc}}% + {\abbrevFont{etc}.\xspace}% +}% \makeatother @@ -144,4 +161,5 @@ \endlist }% quote2 + \newenvironment{rationale}{% \begin{quote2}\noindent$\Box$\enspace @@ -187,5 +205,5 @@ \newcommand{\VPageref}[2][page]{\ifx#1\@empty\else{#1}\nobreakspace\fi\pageref{#2}} -% Go programming language +% Go programming language: https://github.com/julienc91/listings-golang/blob/master/listings-golang.sty \lstdefinelanguage{Golang}{ morekeywords=[1]{package,import,func,type,struct,return,defer,panic, recover,select,var,const,iota,},% @@ -203,9 +221,9 @@ } -% CFA programming language, based on ANSI C +% CFA programming language, based on ANSI C (with some gcc additions) \lstdefinelanguage{CFA}[ANSI]{C}{ morekeywords={_Alignas,_Alignof,__alignof,__alignof__,asm,__asm,__asm__,_At,_Atomic,__attribute,__attribute__,auto, _Bool,catch,catchResume,choose,_Complex,__complex,__complex__,__const,__const__,disable,dtype,enable,__extension__, - fallthru,finally,forall,ftype,_Generic,_Imaginary,inline,__label__,lvalue,_Noreturn,otype,restrict,_Static_assert, + fallthrough,fallthru,finally,forall,ftype,_Generic,_Imaginary,inline,__label__,lvalue,_Noreturn,otype,restrict,_Static_assert, _Thread_local,throw,throwResume,trait,try,typeof,__typeof,__typeof__,}, }% @@ -214,18 +232,18 @@ language=CFA, columns=fullflexible, -basicstyle=\linespread{0.9}\sf, -stringstyle=\tt, -tabsize=4, -xleftmargin=\parindentlnth, -extendedchars=true, -escapechar=§, -mathescape=true, -keepspaces=true, -showstringspaces=false, -showlines=true, -aboveskip=4pt, +basicstyle=\linespread{0.9}\sf, % reduce line spacing and use sanserif font +stringstyle=\tt, % use typewriter font +tabsize=4, % 4 space tabbing +xleftmargin=\parindentlnth, % indent code to paragraph indentation +extendedchars=true, % allow ASCII characters in the range 128-255 +escapechar=§, % escape to latex in CFA code +mathescape=true, % allow $...$ LaTeX math escapes in code +%keepspaces=true, % +showstringspaces=false, % do not show spaces with cup +showlines=true, % show blank lines at end of code +aboveskip=4pt, % spacing above/below code block belowskip=3pt, -moredelim=**[is][\color{red}]{®}{®}, % red highlighting -moredelim=**[is][\color{blue}]{ß}{ß}, % blue highlighting +moredelim=**[is][\color{red}]{®}{®}, % red highlighting +moredelim=**[is][\color{blue}]{ß}{ß}, % blue highlighting moredelim=**[is][\color{OliveGreen}]{¢}{¢}, % green highlighting moredelim=[is][\lstset{keywords={}}]{¶}{¶}, % temporarily turn off keywords @@ -241,5 +259,5 @@ \renewcommand\thebibliography[1]{ \Oldthebibliography{#1} - \setlength{\parskip}{0pt} % reduce vertical spacing between references + \setlength{\parskip}{0pt} % reduce vertical spacing between references \setlength{\itemsep}{5pt plus 0.3ex} }% Index: doc/aaron_comp_II/.gitignore =================================================================== --- doc/aaron_comp_II/.gitignore (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) +++ doc/aaron_comp_II/.gitignore (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) @@ -0,0 +1,14 @@ +# generated by latex +*.aux +*.bbl +*.blg +*.brf +*.dvi +*.idx +*.ilg +*.ind +*.log +*.out +*.pdf +*.ps +*.toc Index: doc/aaron_comp_II/Makefile =================================================================== --- doc/aaron_comp_II/Makefile (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) +++ doc/aaron_comp_II/Makefile (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) @@ -0,0 +1,78 @@ +## Define the appropriate configuration variables. + +TeXLIB = .:../LaTeXmacros:../LaTeXmacros/listings:../LaTeXmacros/enumitem:../bibliography/: +LaTeX = TEXINPUTS=${TeXLIB} && export TEXINPUTS && latex -halt-on-error +BibTeX = BIBINPUTS=${TeXLIB} && export BIBINPUTS && bibtex + +## Define the text source files. + +SOURCES = ${addsuffix .tex, \ +comp_II \ +} + +FIGURES = ${addsuffix .tex, \ +} + +PICTURES = ${addsuffix .pstex, \ +} + +PROGRAMS = ${addsuffix .tex, \ +} + +GRAPHS = ${addsuffix .tex, \ +} + +## Define the documents that need to be made. + +DOCUMENT = comp_II.pdf + +# Directives # + +all : ${DOCUMENT} + +clean : + rm -f *.bbl *.aux *.dvi *.idx *.ilg *.ind *.brf *.out *.log *.toc *.blg *.pstex_t *.cf \ + ${FIGURES} ${PICTURES} ${PROGRAMS} ${GRAPHS} ${basename ${DOCUMENT}}.ps ${DOCUMENT} + +# File Dependencies # + +${DOCUMENT} : ${basename ${DOCUMENT}}.ps + ps2pdf $< + +${basename ${DOCUMENT}}.ps : ${basename ${DOCUMENT}}.dvi + dvips $< -o $@ + +${basename ${DOCUMENT}}.dvi : Makefile ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} ${basename ${DOCUMENT}}.tex \ + ../LaTeXmacros/common.tex ../LaTeXmacros/indexstyle ../bibliography/cfa.bib + # Conditionally create an empty *.ind (index) file for inclusion until makeindex is run. + if [ ! -r ${basename $@}.ind ] ; then touch ${basename $@}.ind ; fi + # Must have *.aux file containing citations for bibtex + if [ ! -r ${basename $@}.aux ] ; then ${LaTeX} ${basename $@}.tex ; fi + -${BibTeX} ${basename $@} + # Some citations reference others so run steps again to resolve these citations + ${LaTeX} ${basename $@}.tex + -${BibTeX} ${basename $@} + # Make index from *.aux entries and input index at end of document + makeindex -s ../LaTeXmacros/indexstyle ${basename $@}.idx + ${LaTeX} ${basename $@}.tex + # Run again to get index title into table of contents + ${LaTeX} ${basename $@}.tex + +predefined : + sed -f predefined.sed ${basename ${DOCUMENT}}.tex > ${basename $@}.cf + +## Define the default recipes. + +%.tex : %.fig + fig2dev -L eepic $< > $@ + +%.ps : %.fig + fig2dev -L ps $< > $@ + +%.pstex : %.fig + fig2dev -L pstex $< > $@ + fig2dev -L pstex_t -p $@ $< > $@_t + +# Local Variables: # +# compile-command: "make" # +# End: # Index: doc/aaron_comp_II/comp_II.tex =================================================================== --- doc/aaron_comp_II/comp_II.tex (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) +++ doc/aaron_comp_II/comp_II.tex (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) @@ -0,0 +1,403 @@ +% inline code ©...© (copyright symbol) emacs: C-q M-) +% red highlighting ®...® (registered trademark symbol) emacs: C-q M-. +% blue highlighting ß...ß (sharp s symbol) emacs: C-q M-_ +% green highlighting ¢...¢ (cent symbol) emacs: C-q M-" +% LaTex escape §...§ (section symbol) emacs: C-q M-' +% keyword escape ¶...¶ (pilcrow symbol) emacs: C-q M-^ +% math escape $...$ (dollar symbol) + +\documentclass[twoside,11pt]{article} + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +% Latex packages used in the document (copied from CFA user manual). +\usepackage[T1]{fontenc} % allow Latin1 (extended ASCII) characters +\usepackage{textcomp} +\usepackage[latin1]{inputenc} +\usepackage{fullpage,times,comment} +\usepackage{epic,eepic} +\usepackage{upquote} % switch curled `'" to straight +\usepackage{calc} +\usepackage{xspace} +\usepackage{graphicx} +\usepackage{varioref} % extended references +\usepackage{listings} % format program code +\usepackage[flushmargin]{footmisc} % support label/reference in footnote +\usepackage{latexsym} % \Box glyph +\usepackage{mathptmx} % better math font with "times" +\usepackage[usenames]{color} +\usepackage[pagewise]{lineno} +\renewcommand{\linenumberfont}{\scriptsize\sffamily} +\input{common} % bespoke macros used in the document +\usepackage[dvips,plainpages=false,pdfpagelabels,pdfpagemode=UseNone,colorlinks=true,pagebackref=true,linkcolor=blue,citecolor=blue,urlcolor=blue,pagebackref=true,breaklinks=true]{hyperref} +\usepackage{breakurl} +\renewcommand{\UrlFont}{\small\sf} + +\setlength{\topmargin}{-0.45in} % move running title into header +\setlength{\headsep}{0.25in} + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +\newsavebox{\LstBox} + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +\title{ +\Huge \vspace*{1in} Efficient Type Resolution in \CFA \\ +\huge \vspace*{0.25in} PhD Comprehensive II Research Proposal +\vspace*{1in} +} + +\author{ +\huge Aaron Moss \\ +\Large \vspace*{0.1in} \texttt{a3moss@uwaterloo.ca} \\ +\Large Cheriton School of Computer Science \\ +\Large University of Waterloo +} + +\date{ +\today +} + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +\begin{document} +\pagestyle{headings} +% changed after setting pagestyle +\renewcommand{\sectionmark}[1]{\markboth{\thesection\quad #1}{\thesection\quad #1}} +\renewcommand{\subsectionmark}[1]{\markboth{\thesubsection\quad #1}{\thesubsection\quad #1}} +\pagenumbering{roman} +\linenumbers % comment out to turn off line numbering + +\maketitle +\thispagestyle{empty} + +\clearpage +\thispagestyle{plain} +\pdfbookmark[1]{Contents}{section} +\tableofcontents + +\clearpage +\thispagestyle{plain} +\pagenumbering{arabic} + +\section{Introduction} + +\CFA\footnote{Pronounced ``C-for-all'', and written \CFA, CFA, or \CFL.} is an evolutionary modernization of the C programming language currently being designed and built at the University of Waterloo by a team led by Peter Buhr. +\CFA adds multiple features to C, including name overloading, user-defined operators, parametric-polymorphic routines, and type constructors and destructors, among others. +These features make \CFA significantly more powerful and expressive than C, but impose a significant compile-time cost to support, particularly in the expression resolver, which must evaluate the typing rules of a much more complex type system. +The primary goal of this proposed research project is to develop a sufficiently performant expression resolution algorithm, experimentally validate its performance, and integrate it into \Index*{CFA-CC}, the \CFA reference compiler. +Secondary goals of this project include the development of various new language features for \CFA; parametric-polymorphic (``generic'') types have already been designed and implemented, and reference types and user-defined conversions are under design consideration. +The experimental performance-testing architecture for resolution algorithms will also be used to determine the compile-time cost of adding such new features to the \CFA type system. +More broadly, this research should provide valuable data for implementers of compilers for other programming languages with similarly powerful static type systems. + +\section{\CFA} + +To make the scope of the proposed expression resolution problem more explicit, it is necessary to define the features of both C and \CFA (both current and proposed) which affect this algorithm. +In some cases the interactions of multiple features make expression resolution a significantly more complex problem than any individual feature would; in others a feature which does not by itself add any complexity to expression resolution will trigger previously rare edge cases much more frequently. + +\subsection{Polymorphic Functions} +The most significant feature \CFA adds is parametric-polymorphic functions. +Such functions are written using a ©forall© clause (which gives the language its name): +\begin{lstlisting} +forall(otype T) +T identity(T x) { + return x; +} + +int forty_two = identity(42); // T is bound to int, forty_two == 42 +\end{lstlisting} +The ©identity© function above can be applied to any complete object type (or ``©otype©''). +The type variable ©T© is transformed into a set of additional implicit parameters to ©identity© which encode sufficient information about ©T© to create and return a variable of that type. +The current \CFA implementation passes the size and alignment of the type represented by an ©otype© parameter, as well as an assignment operator, constructor, copy constructor \& destructor. + +Since bare polymorphic types do not provide a great range of available operations, \CFA also provides a \emph{type assertion} mechanism to provide further information about a type: +\begin{lstlisting} +forall(otype T | { T twice(T); }) +T four_times(T x) { + return twice( twice(x) ); +} + +double twice(double d) { return d * 2.0; } // (1) + +double magic = four_times(10.5); // T is bound to double, uses (1) to satisfy type assertion +\end{lstlisting} +These type assertions may be either variable or function declarations which depend on a polymorphic type variable. +©four_times© can only be called with an argument for which there exists a function named ©twice© that can take that argument and return another value of the same type; a pointer to the appropriate ©twice© function will be passed as an additional implicit parameter to the call to ©four_times©. + +Monomorphic specializations of polymorphic functions can themselves be used to satisfy type assertions. +For instance, ©twice© could have been defined as below, using the \CFA syntax for operator overloading: +\begin{lstlisting} +forall(otype S | { S ?+?(S, S); }) +S twice(S x) { return x + x; } // (2) +\end{lstlisting} +This version of ©twice© will work for any type ©S© that has an addition operator defined for it, and it could have been used to satisfy the type assertion on ©four_times©. +The compiler accomplishes this by creating a wrapper function calling ©twice // (2)© with ©S© bound to ©double©, then providing this wrapper function to ©four_times©\footnote{©twice // (2)© could also have had a type parameter named ©T©; \CFA specifies renaming of the type parameters, which would avoid the name conflict with the type variable ©T© of ©four_times©.}. + +Finding appropriate functions to satisfy type assertions is essentially a recursive case of expression resolution, as it takes a name (that of the type assertion) and attempts to match it to a suitable declaration in the current scope. +If a polymorphic function can be used to satisfy one of its own type assertions, this recursion may not terminate, as it is possible that function will be examined as a candidate for its own type assertion unboundedly repeatedly. +To avoid infinite loops, the current \Index*{CFA-CC} compiler imposes a fixed limit on the possible depth of recursion, similar to that employed by most \Index*[C++]{\CC} compilers for template expansion; this restriction means that there are some semantically well-typed expressions which cannot be resolved by {CFA-CC}. +One area of potential improvement this project proposes to investigate is the possibility of using the compiler's knowledge of the current set of declarations to more precicely determine when further type assertion satisfaction recursion will not produce a well-typed expression. + +\subsection{Name Overloading} +In C, no more than one function or variable in the same scope may share the same name, and function or variable declarations in inner scopes with the same name as a declaration in an outer scope hide the outer declaration. +This makes finding the proper declaration to match to a function application or variable expression a simple matter of symbol table lookup, which can be easily and efficiently implemented. +\CFA, on the other hand, allows overloading of variable and function names, so long as the overloaded declarations do not have the same type, avoiding the multiplication of function names for different types common in the C standard library, as in the following example: +\begin{lstlisting} +int three = 3; +double three = 3.0; + +int thrice(int i) { return i * three; } // uses int three +double thrice(double d) { return d * three; } // uses double three + +// thrice(three); // ERROR: ambiguous +int nine = thrice(three); // uses int thrice and three, based on return type +double nine = thrice(three); // uses double thrice and three, based on return type +\end{lstlisting} + +The presence of name overloading in \CFA means that simple table lookup is not sufficient to match identifiers to declarations, and a type matching algorithm must be part of expression resolution. + +\subsection{Implicit Conversions} +In addition to the multiple interpretations of an expression produced by name overloading, \CFA also supports all of the implicit conversions present in C, producing further candidate interpretations for expressions. +C does not have a traditionally-defined inheritance hierarchy of types, but the C standard's rules for the ``usual arithmetic conversions'' define which of the built-in types are implicitly convertable to which other types, and the relative cost of any pair of such conversions from a single source type. +\CFA adds to the usual arithmetic conversions rules for determining the cost of binding a polymorphic type variable in a function call; such bindings are cheaper than any \emph{unsafe} (narrowing) conversion, \eg ©int© to ©char©, but more expensive than any \emph{safe} (widening) conversion, \eg ©int© to ©double©. +The expression resolution problem, then, is to find the unique minimal-cost interpretation of each expression in the program, where all identifiers must be matched to a declaration and implicit conversions or polymorphic bindings of the result of an expression may increase the cost of the expression. +Note that which subexpression interpretation is minimal-cost may require contextual information to disambiguate. + +\subsubsection{User-generated Implicit Conversions} +One possible additional feature to \CFA included in this research proposal is \emph{user-generated implicit conversions}. +Such a conversion system should be simple for user programmers to utilize, and fit naturally with the existing design of implicit conversions in C; ideally it would also be sufficiently powerful to encode C's usual arithmetic conversions itself, so that \CFA only has one set of rules for conversions. + +Ditchfield\cite{Ditchfield:conversions} has laid out a framework for using polymorphic conversion constructor functions to create a directed acyclic graph (DAG) of conversions. +A monomorphic variant of these functions can be used to mark a conversion arc in the DAG as only usable as the final step in a conversion. +With these two types of conversion arcs, separate DAGs can be created for the safe and the unsafe conversions, and conversion cost can be represented as path length through the DAG. +Open research questions on this topic include whether a conversion graph can be generated that represents each allowable conversion in C with a unique minimal-length path, such that the path lengths accurately represent the relative costs of the conversions, whether such a graph representation can be usefully augmented to include user-defined types as well as built-in types, and whether the graph can be efficiently represented and included in the expression resolver. + +\subsection{Constructors \& Destructors} +Rob Shluntz, a current member of the \CFA research team, has added constructors and destructors to \CFA. +Each type has an overridable default-generated zero-argument constructor, copy constructor, assignment operator, and destructor; for struct types these functions each call their equivalents on each field of the struct. +This affects expression resolution because an ©otype© type variable ©T© implicitly adds four type assertions, one for each of these four functions, so assertion resolution is pervasive in \CFA polymorphic functions, even those without any explicit type assertions. + +\subsection{Generic Types} +The author has added a generic type capability to \CFA, designed to efficiently and naturally integrate with \CFA's existing polymorphic functions. +A generic type can be declared by placing a ©forall© specifier on a struct or union declaration, and instantiated using a parenthesized list of types after the type name: +\begin{lstlisting} +forall(otype R, otype S) struct pair { + R first; + S second; +}; + +forall(otype T) +T value( pair(const char*, T) *p ) { return p->second; } + +pair(const char*, int) p = { "magic", 42 }; +int magic = value( &p ); +\end{lstlisting} +For \emph{concrete} generic types, that is, those where none of the type parameters depend on polymorphic type variables (like ©pair(const char*, int)© above), the struct is essentially template expanded to a new struct type; for \emph{polymorphic} generic types (such as ©pair(const char*, T)© above), member access is handled by a runtime calculation of the field offset, based on the size and alignment information of the polymorphic parameter type. +The default-generated constructors, destructor \& assignment operator for a generic type are polymorphic functions with the same list of type parameters as the generic type definition. + +Aside from giving users the ability to create more parameterized types than just the built-in pointer, array \& function types, the combination of generic types with polymorphic functions and implicit conversions makes the edge case where a polymorphic function can match its own assertions much more common, as follows: +\begin{itemize} +\item Given an expression in an untyped context, such as a top-level function call with no assignment of return values, apply a polymorphic implicit conversion to the expression that can produce multiple types (the built-in conversion from ©void*© to any other pointer type is one, but not the only). +\item When attempting to use a generic type with ©otype© parameters (such as ©box© above) for the result type of the expression, the resolver will also need to decide what type to use for the ©otype© parameters on the constructors and related functions, and will have no constraints on what they may be. +\item Attempting to match some yet-to-be-determined specialization of the generic type to this ©otype© parameter will create a recursive case of the default constructor, \etc matching their own type assertions, creating an unboundedly deep nesting of the generic type inside itself. +\end{itemize} +As discussed above, any \CFA expression resolver must handle this possible infinite recursion somehow, but the combination of generic types with other language features makes this particular edge case occur somewhat frequently in user code. + +\subsection{Tuple Types} +\CFA adds \emph{tuple types} to C, a facility for referring to multiple values with a single identifier. +A variable may name a tuple, and a function may return one. +Particularly relevantly for resolution, a tuple may be implicitly \emph{destructured} into a list of values, as in the call to ©swap© below: +\begin{lstlisting} +[char, char] x = [ '!', '?' ]; +int x = 42; + +forall(otype T) [T, T] swap( T a, T b ) { return [b, a]; } + +x = swap( x ); // destructure [char, char] x into two elements of parameter list +// can't use int x for parameter, not enough arguments to swap +\end{lstlisting} +Tuple destructuring means that the mapping from the position of a subexpression in the argument list to the position of a paramter in the function declaration is not straightforward, as some arguments may be expandable to different numbers of parameters, like ©x© above. + +\subsection{Reference Types} +The author, in collaboration with the rest of the \CFA research team, has been designing \emph{reference types} for \CFA. +Given some type ©T©, a ©T&© (``reference to ©T©'') is essentially an automatically dereferenced pointer; with these semantics most of the C standard's discussions of lvalues can be expressed in terms of references instead, with the benefit of being able to express the difference between the reference and non-reference version of a type in user code. +References preserve C's existing qualifier-dropping lvalue-to-rvalue conversion (\eg a ©const volatile int&© can be implicitly converted to a bare ©int©); the reference proposal also adds a rvalue-to-lvalue conversion to \CFA, implemented by storing the value in a new compiler-generated temporary and passing a reference to the temporary. +These two conversions can chain, producing a qualifier-dropping conversion for references, for instance converting a reference to a ©const int© into a reference to a non-©const int© by copying the originally refered to value into a fresh temporary and taking a reference to this temporary. +These reference conversions may also chain with the other implicit type conversions. +The main implication of this for expression resolution is the multiplication of available implicit conversions, though in a restricted context that may be able to be treated efficiently as a special case. + +\subsection{Literal Types} +Another proposal currently under consideration for the \CFA type system is assigning special types to the literal values ©0© and ©1©.%, say ©zero_t© and ©one_t©. +Implicit conversions from these types would allow ©0© and ©1© to be considered as values of many different types, depending on context, allowing expression desugarings like ©if ( x ) {}© $\Rightarrow$ ©if ( x != 0 ) {}© to be implemented efficiently and precicely. +This is a generalization of C's existing behaviour of treating ©0© as either an integer zero or a null pointer constant, and treating either of those values as boolean false. +The main implication for expression resolution is that the frequently encountered expressions ©0© and ©1© may have a significant number of valid interpretations. + +\subsection{Deleted Function Declarations} +One final proposal for \CFA with an impact on the expression resolver is \emph{deleted function declarations}; in \CCeleven, a function declaration can be deleted as below: +\begin{lstlisting} +int somefn(char) = delete; +\end{lstlisting} +To add a similar feature to \CFA would involve including the deleted function declarations in expression resolution along with the normal declarations, but producing a compiler error if the deleted function was the best resolution. +How conflicts should be handled between resolution of an expression to both a deleted and a non-deleted function is a small but open research question. + +\section{Expression Resolution} +The expression resolution problem is essentially to determine an optimal matching between some combination of argument interpretations and the parameter list of some overloaded instance of a function; the argument interpretations are produced by recursive invocations of expression resolution, where the base case is zero-argument functions (which are, for purposes of this discussion, semantically equivalent to named variables or constant literal expressions). +Assuming that the matching between a function's parameter list and a combination of argument interpretations can be done in $O(p^k)$ time, where $p$ is the number of parameters and $k$ is some positive number, if there are $O(i)$ valid interpretations for each subexpression, there will be $O(i)$ candidate functions and $O(i^p)$ possible argument combinations for each expression, so a single recursive call to expression resolution will take $O(i^{p+1} \cdot p^k)$ time if it compares all combinations. +Given this bound, resolution of a single top-level expression tree of depth $d$ takes $O(i^{p+1} \cdot p^{k \cdot d})$ time\footnote{The call tree will have leaves at depth $O(d)$, and each internal node will have $O(p)$ fan-out, producing $O(p^d)$ total recursive calls.}. +Expression resolution is somewhat unavoidably exponential in $p$, the number of function parameters, and $d$, the depth of the expression tree, but these values are fixed by the user programmer, and generally bounded by reasonably small constants. +$k$, on the other hand, is mostly dependent on the representation of types in the system and the efficiency of type assertion checking; if a candidate argument combination can be compared to a function parameter list in linear time in the length of the list (\ie $k = 1$), then the $p^{k \cdot d}$ term is linear in the input size of the source code for the expression, otherwise the resolution algorithm will exibit sub-linear performance scaling on code containing more-deeply nested expressions. +The number of valid interpretations of any subexpression, $i$, is bounded by the number of types in the system, which is possibly infinite, though practical resolution algorithms for \CFA must be able to place some finite bound on $i$, possibly at the expense of type system completeness. + +The research goal of this project is to develop a performant expression resolver for \CFA; this analysis suggests two primary areas of investigation to accomplish that end. +The first is efficient argument-parameter matching; Bilson\cite{Bilson03} mentions significant optimization opportunities available in the current literature to improve on the existing {CFA-CC} compiler. +%TODO: look up and lit review +The second, and likely more fruitful, area of investigation is heuristics and algorithmic approaches to reduce the number of argument interpretations considered in the common case; given the large ($p+1$) exponent on number of interpretations considered in the runtime analysis, even small reductions here could have a significant effect on overall resolver runtime. +The discussion below presents a number of largely orthagonal axes for expression resolution algorithm design to be investigated, noting prior work where applicable. + +\subsection{Argument-Parameter Matching} +The first axis we consider is argument-parameter matching --- whether the type matching for a candidate function to a set of candidate arguments is directed by the argument types or the parameter types. + +\subsubsection{Argument-directed (``Bottom-up'')} +Baker's algorithm for expression resolution\cite{Baker82} pre-computes argument candidates, from the leaves of the expression tree up. +For each candidate function, Baker attempts to match argument types to parameter types in sequence, failing if any parameter cannot be matched. + +Bilson\cite{Bilson03} similarly pre-computes argument candidates in the original \CFA compiler, but then explicitly enumerates all possible argument combinations for a multi-parameter function; these argument combinations are matched to the parameter types of the candidate function as a unit rather than individual arguments. +This is less efficient than Baker's approach, as the same argument may be compared to the same parameter many times, but allows a more straightforward handling of polymorphic type binding and multiple return types. +It is possible the efficiency losses here relative to Baker could be significantly reduced by application of memoization to the argument-parameter type comparisons. + +\subsubsection{Parameter-directed (``Top-down'')} +Unlike Baker and Bilson, Cormack's algorithm\cite{Cormack81} requests argument candidates which match the type of each parameter of each candidate function, from the top-level expression down; memoization of these requests is presented as an optimization. +As presented, this algorithm requires the result of the expression to have a known type, though an algorithm based on Cormack's could reasonably request a candidate set of any return type, though such a set may be quite large. + +\subsubsection{Hybrid} +This proposal includes the investigation of hybrid top-down/bottom-up argument-parameter matching. +A reasonable hybrid approach might be to take a top-down approach when the expression to be matched is known to have a fixed type, and a bottom-up approach in untyped contexts. +This may include switches from one type to another at different levels of the expression tree, for instance: +\begin{lstlisting} +forall(otype T) +int f(T x); // (1) + +void* f(char y); // (2) + +int x = f( f( '!' ) ); +\end{lstlisting} +Here, the outer call to ©f© must have a return type that is (implicitly convertable to) ©int©, so a top-down approach could be used to select \textit{(1)} as the proper interpretation of ©f©. \textit{(1)}'s parameter ©x© here, however, is an unbound type variable, and can thus take a value of any complete type, providing no guidance for the choice of candidate for the inner ©f©. The leaf expression ©'!'©, however, gives us a zero-cost interpretation of the inner ©f© as \textit{(2)}, providing a minimal-cost expression resolution where ©T© is bound to ©void*©. + +Deciding when to switch between bottom-up and top-down resolution in a hybrid algorithm is a necessarily heuristic process, and though finding good heuristics for it is an open question, one reasonable approach might be to switch from top-down to bottom-up when the number of candidate functions exceeds some threshold. + +\subsection{Implicit Conversion Application} +Baker's\cite{Baker82} and Cormack's\cite{Cormack81} algorithms do not account for implicit conversions\footnote{Baker does briefly comment on an approach for handling implicit conversions.}; both assume that there is at most one valid interpretation of a given expression for each distinct type. +Integrating implicit conversion handling into their algorithms provides some choice of implementation approach. + +\subsubsection{On Parameters} +Bilson\cite{Bilson03} did account for implicit conversions in his algorithm, but it is not clear his approach is optimal. +His algorithm integrates checking for valid implicit conversions into the argument-parameter matching step, essentially trading more expensive matching for a smaller number of argument interpretations. +This approach may result in the same subexpression being checked for a type match with the same type multiple times, though again memoization may mitigate this cost, and this approach will not generate implicit conversions that are not useful to match the containing function. + +\subsubsection{On Arguments} +Another approach would be to generate a set of possible implicit conversions for each set of interpretations of a given argument. +This would have the benefit of detecting ambiguous interpretations of arguments at the level of the argument rather than its containing call, would also never find more than one interpretation of the argument with a given type, and would re-use calculation of implicit conversions between function candidates. +On the other hand, this approach may unncessarily generate argument interpretations that will never match a parameter, wasting work. + +\subsection{Candidate Set Generation} +Cormack\cite{Cormack81}, Baker\cite{Baker82} \& Bilson\cite{Bilson03} all generate the complete set of candidate argument interpretations before attempting to match the containing function call expression. +However, given that the top-level expression interpretation that is ultimately chosen will be the minimal-cost valid interpretation, any consideration of non-minimal-cost interpretations is in some sense wasted work. +If we assume that user programmers will generally write function calls with relatively low-cost interpretations, a possible work-saving heuristic is to generate only the lowest-cost argument interpretations first, attempt to find a valid top-level interpretation using them, and only if that fails generate the higher-cost argument interpretations. + +\subsubsection{Eager} +Within the eager approach taken by Cormack, Baker \& Bilson, there are still variants to explore. +Cormack \& Baker do not account for implict conversions, and thus do not account for the possibility of multiple valid interpretations with distinct costs; Bilson, on the other hand, sorts the list of interpretations to aid in finding minimal-cost interpretations. +Sorting the lists of argument or function call interpretations by cost at some point during resolution may provide useful opportunities to short-circuit expression evaluation when a minimal-cost interpretation is found, though it is not clear if this short-circuiting behaviour would justify the cost of the sort. + +\subsubsection{Lazy} +In the presence of implicit conversions, many argument interpretations may match a given parameter by application of an appropriate implicit conversion. +However, if user programmers actually use relatively few implicit conversions, then the ``on arguments'' approach to implicit conversions will generate a large number of high-cost interpretations which may never be used. +The essence of the lazy approach to candidate set generation is to wrap the matching algorithm into the element generator of a lazy list type, only generating as few elements at a time as possible to ensure that the next-smallest-cost interpretation has been generated. +Assuming that argument interpretations are provided to the parameter matching algorithm in sorted order, a sorted list of function call interpretations can be produced by generating combinations of arguments sorted by total cost\footnote{The author has developed a lazy $n$-way combination generation algorithm that can perform this task.}, then generating function call interpretations in the order suggested by this list. +Note that the function call interpretation chosen may have costs of its own, for instance polymorphic type binding, so in some cases a number of argument combinations (any combination whose marginal cost does not exceed the cost of the function call interpretation itself) may need to be considered to determine the next-smallest-cost function call interpretation. +Ideally, this candidate generation approach will lead to very few unused candidates being generated (in the expected case where the user programmer has, in fact, provided a validly-typable program), but this research project will need to determine whether or not the overheads of lazy generation exceed the benefit produced from considering fewer interpretations. + +\subsubsection{Stepwise Lazy} +As a compromise between the trade-offs of the eager and lazy approaches, it would also be interesting to investigate a ``stepwise lazy'' approach, where all the interpretations for some ``step'' are eagerly generated, then the interpretations in the later steps are only generated on demand. +Under this approach the \CFA resolver could, for instance, try expression interpretations in the following order: +\begin{enumerate} +\item Interpretations with no polymorphic type binding or implicit conversions. +\item Interpretations containing no polymorphic type binding and at least one safe implicit conversion. +\item Interpretations containing polymorphic type binding, but only safe implicit conversions. +\item Interpretations containing at least one unsafe implicit conversion. +\end{enumerate} +If a valid expression interpretation is found in one step, it is guaranteed to be lower-cost than any interpretation in a later step (by the structure of \CFA interpretation costs), so no step after the first one where a valid interpretation can be found need be considered. +This may save significant amounts of work, especially given that the first steps avoid potentially expensive handling of implicit conversions and type assertion satisfaction entirely. + +%\subsection{Parameter-Directed} +%\textbf{TODO: Richard's algorithm isn't Baker (Cormack?), disentangle from this section \ldots}. +%The expression resolution algorithm used by the existing iteration of {CFA-CC} is based on Baker's\cite{Baker82} algorithm for overload resolution in Ada. +%The essential idea of this algorithm is to first find the possible interpretations of the most deeply nested subexpressions, then to use these interpretations to recursively generate valid interpretations of their superexpressions. +%To simplify matters, the only expressions considered in this discussion of the algorithm are function application and literal expressions; other expression types can generally be considered to be variants of one of these for the purposes of the resolver, \eg variables are essentially zero-argument functions. +%If we consider expressions as graph nodes with arcs connecting them to their subexpressions, these expressions form a DAG, generated by the algorithm from the bottom up. +%Literal expressions are represented by leaf nodes, annotated with the type of the expression, while a function application will have a reference to the function declaration chosen, as well as arcs to the interpretation nodes for its argument expressions; functions are annotated with their return type (or types, in the case of multiple return values). +% +%\textbf{TODO: Figure} +% +%Baker's algorithm was designed to account for name overloading; Richard Bilson\cite{Bilson03} extended this algorithm to also handle polymorphic functions, implicit conversions \& multiple return types when designing the original \CFA compiler. +%The core of the algorithm is a function which Baker refers to as $gen\_calls$. +%$gen\_calls$ takes as arguments the name of a function $f$ and a list containing the set of possible subexpression interpretations $S_j$ for each argument of the function and returns a set of possible interpretations of calling that function on those arguments. +%The subexpression interpretations are generally either singleton sets generated by the single valid interpretation of a literal expression, or the results of a previous call to $gen\_calls$. +%If there are no valid interpretations of an expression, the set returned by $gen\_calls$ will be empty, at which point resolution can cease, since each subexpression must have at least one valid interpretation to produce an interpretation of the whole expression. +%On the other hand, if for some type $T$ there is more than one valid interpretation of an expression with type $T$, all interpretations of that expression with type $T$ can be collapsed into a single \emph{ambiguous expression} of type $T$, since the only way to disambiguate expressions is by their return types. +%If a subexpression interpretation is ambiguous, than any expression interpretation containing it will also be ambiguous. +%In the variant of this algorithm including implicit conversions, the interpretation of an expression as type $T$ is ambiguous only if there is more than one \emph{minimal-cost} interpretation of the expression as type $T$, as cheaper expressions are always chosen in preference to more expensive ones. +% +%Given this description of the behaviour of $gen\_calls$, its implementation is quite straightforward: for each function declaration $f_i$ matching the name of the function, consider each of the parameter types $p_j$ of $f_i$, attempting to match the type of an element of $S_j$ to $p_j$ (this may include checking of implicit conversions). +%If no such element can be found, there is no valid interpretation of the expression using $f_i$, while if more than one such (minimal-cost) element is found than an ambiguous interpretation with the result type of $f_i$ is produced. +%In the \CFA variant, which includes polymorphic functions, it is possible that a single polymorphic function definition $f_i$ can produce multiple valid interpretations by different choices of type variable bindings; these interpretations are unambiguous so long as the return type of $f_i$ is different for each type binding. +%If all the parameters $p_j$ of $f_i$ can be uniquely matched to a candidate interpretation, then a valid interpretation based on $f_i$ and those $p_j$ is produced. +%$gen\_calls$ collects the produced interpretations for each $f_i$ and returns them; a top level expression is invalid if this list is empty, ambiguous if there is more than one (minimal-cost) result, or if this single result is ambiguous, and valid otherwise. +% +%In this implementation, resolution of a single top-level expression takes time $O(\ldots)$, where \ldots. \textbf{TODO:} \textit{Look at 2.3.1 in Richard's thesis when working out complexity; I think he does get the Baker algorithm wrong on combinations though, maybe\ldots} +% +%\textbf{TODO: Basic Lit Review} \textit{Look at 2.4 in Richard's thesis for any possible more-recent citations of Baker\ldots} \textit{Look back at Baker's related work for other papers that look similar to what you're doing, then check their citations as well\ldots} \textit{Look at Richard's citations in 2.3.2 w.r.t. type data structures\ldots} +%\textit{CormackWright90 seems to describe a solution for the same problem, mostly focused on how to find the implicit parameters} + +\section{Proposal} +Baker\cite{Baker82} discussed various expression resolution algorithms that could handle name overloading, but left experimental comparison of those algorithms to future work; Bilson\cite{Bilson03} described one extension of Baker's algorithm to handle implicit conversions, but did not fully explore the space of algorithmic approaches to handle both overloaded names and implicit conversions. +This project is intended to experimentally test a number of expression resolution algorithms which are powerful enough to handle the \CFA type system, including both name overloading and implicit conversions. +This comparison will close Baker's open research question, as well as potentially improving on Bilson's \CFA compiler. + +Rather than testing all of these algorithms in-place in the \CFA compiler, a resolver prototype will be developed which acts on a simplified input language encapsulating the essential details of the \CFA type system\footnote{Note that this simplified input language is not required to be a usable programming language.}. +Multiple variants of this resolver prototype will be implemented, each encapsulating a different expression resolution variant, sharing as much code as feasible. +These variants will be instrumented to test runtime performance, and run on a variety of input files; the input files may be generated programmatically or from exisiting code in \CFA or similar languages. +These experimental results will allow the research team to determine the algorithm likely to be most performant in practical use, and replace {CFA-CC}'s existing expression resolver with that code. +The experimental results will also provide some empirical sense of the compile-time cost of various language features by comparing the results of the most performant resolver variant that supports the feature with the most performant resolver variant that doesn't, a useful capability to guide language design. + +This proposed project should provide valuable data on how to implement a performant compiler for modern programming languages such as \CFA with powerful static type systems, specifically targeting the feature interaction between name overloading and implicit conversions. + +\appendix +\section{Completion Timeline} +The following is a preliminary estimate of the time necessary to complete the major components of this research project: +\begin{center} +\begin{tabular}{ | r @{--} l | p{4in} | } +\hline May 2015 & April 2016 & Project familiarization and generic types design \& implementation. \\ +\hline May 2016 & April 2017 & Design \& implement resolver prototype and run performance experiments. \\ +\hline May 2017 & August 2017 & Integrate new language features and best-performing resolver prototype into {CFA-CC}. \\ +\hline September 2017 & January 2018 & Thesis writing \& defense. \\ +\hline +\end{tabular} +\end{center} + +\addcontentsline{toc}{section}{\refname} +\bibliographystyle{plain} +\bibliography{cfa} + +%\addcontentsline{toc}{section}{\indexname} % add index name to table of contents +%\begin{theindex} +%Italic page numbers give the location of the main entry for the referenced term. +%Plain page numbers denote uses of the indexed term. +%Entries for grammar non-terminals are italicized. +%A typewriter font is used for grammar terminals and program identifiers. +%\indexspace +%\input{comp_II.ind} +%\end{theindex} + +\end{document} Index: doc/bibliography/cfa.bib =================================================================== --- doc/bibliography/cfa.bib (revision e21c72d5e2c7ca2735fce0ab2c4d00dc249711cc) +++ doc/bibliography/cfa.bib (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) @@ -1623,4 +1623,15 @@ year = 1974, } + +@unpublished{Ditchfield:conversions, + contributer = {a3moss@uwaterloo.ca}, + author = {Glen Ditchfield}, + title = {Conversions for {Cforall}}, + note = {\href{http://plg.uwaterloo.ca/~cforall/Conversions/index.html}{http://\-plg.uwaterloo.ca/\-\textasciitilde cforall/\-Conversions/\-index.html}}, + month = {Nov}, + year = {2002}, + urldate = {28 July 2016}, +} + @techreport{Dijkstra65, Index: doc/user/user.tex =================================================================== --- doc/user/user.tex (revision e21c72d5e2c7ca2735fce0ab2c4d00dc249711cc) +++ doc/user/user.tex (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) @@ -11,6 +11,6 @@ %% Created On : Wed Apr 6 14:53:29 2016 %% Last Modified By : Peter A. Buhr -%% Last Modified On : Wed Jul 13 08:14:39 2016 -%% Update Count : 1247 +%% Last Modified On : Mon Aug 1 09:11:24 2016 +%% Update Count : 1271 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @@ -211,5 +211,5 @@ however, it largely extended the language, and did not address many existing problems.\footnote{% Two important existing problems addressed were changing the type of character literals from ©int© to ©char© and enumerator from ©int© to the type of its enumerators.} -\Index*{Fortran}~\cite{Fortran08}, \Index*{Ada}~\cite{Ada12}, and \Index*{Cobol}~\cite{Cobol14} are examples of programming languages that took an evolutionary approach, where modern language features (e.g., objects, concurrency) are added and problems fixed within the framework of the existing language. +\Index*{Fortran}~\cite{Fortran08}, \Index*{Ada}~\cite{Ada12}, and \Index*{Cobol}~\cite{Cobol14} are examples of programming languages that took an evolutionary approach, where modern language features (\eg objects, concurrency) are added and problems fixed within the framework of the existing language. \Index*{Java}~\cite{Java8}, \Index*{Go}~\cite{Go}, \Index*{Rust}~\cite{Rust} and \Index*{D}~\cite{D} are examples of the revolutionary approach for modernizing C/\CC, resulting in a new language rather than an extension of the descendent. These languages have different syntax and semantics from C, and do not interoperate directly with C, largely because of garbage collection. @@ -265,5 +265,5 @@ \section[Compiling CFA Program]{Compiling \CFA Program} -The command ©cfa© is used to compile \CFA program(s), and is based on the GNU \Indexc{gcc} command, e.g.: +The command ©cfa© is used to compile \CFA program(s), and is based on the GNU \Indexc{gcc} command, \eg: \begin{lstlisting} cfa§\indexc{cfa}\index{compilation!cfa@©cfa©}§ [ gcc-options ] C/§\CFA§-files [ assembler/loader-files ] @@ -350,5 +350,5 @@ \section{Underscores in Constants} -Numeric constants are extended to allow \Index{underscore}s within constants\index{constant!underscore}, e.g.: +Numeric constants are extended to allow \Index{underscore}s within constants\index{constant!underscore}, \eg: \begin{lstlisting} 2®_®147®_®483®_®648; §\C{// decimal constant}§ @@ -366,8 +366,8 @@ \begin{enumerate} \item -A sequence of underscores is disallowed, e.g., ©12__34© is invalid. +A sequence of underscores is disallowed, \eg ©12__34© is invalid. \item Underscores may only appear within a sequence of digits (regardless of the digit radix). -In other words, an underscore cannot start or end a sequence of digits, e.g., ©_1©, ©1_© and ©_1_© are invalid (actually, the 1st and 3rd examples are identifier names). +In other words, an underscore cannot start or end a sequence of digits, \eg ©_1©, ©1_© and ©_1_© are invalid (actually, the 1st and 3rd examples are identifier names). \item A numeric prefix may end with an underscore; @@ -498,5 +498,5 @@ \end{quote2} -All type qualifiers, e.g., ©const©, ©volatile©, etc., are used in the normal way with the new declarations and also appear left to right, e.g.: +All type qualifiers, \eg ©const©, ©volatile©, etc., are used in the normal way with the new declarations and also appear left to right, \eg: \begin{quote2} \begin{tabular}{@{}l@{\hspace{1em}}l@{\hspace{1em}}l@{}} @@ -518,6 +518,6 @@ \end{tabular} \end{quote2} -All declaration qualifiers, e.g., ©extern©, ©static©, etc., are used in the normal way with the new declarations but can only appear at the start of a \CFA routine declaration,\footnote{\label{StorageClassSpecifier} -The placement of a storage-class specifier other than at the beginning of the declaration specifiers in a declaration is an obsolescent feature.~\cite[\S~6.11.5(1)]{C11}} e.g.: +All declaration qualifiers, \eg ©extern©, ©static©, etc., are used in the normal way with the new declarations but can only appear at the start of a \CFA routine declaration,\footnote{\label{StorageClassSpecifier} +The placement of a storage-class specifier other than at the beginning of the declaration specifiers in a declaration is an obsolescent feature.~\cite[\S~6.11.5(1)]{C11}} \eg: \begin{quote2} \begin{tabular}{@{}l@{\hspace{3em}}l@{\hspace{2em}}l@{}} @@ -542,5 +542,5 @@ Unsupported are K\&R C declarations where the base type defaults to ©int©, if no type is specified,\footnote{ At least one type specifier shall be given in the declaration specifiers in each declaration, and in the specifier-qualifier list in each structure declaration and type name~\cite[\S~6.7.2(2)]{C11}} -e.g.: +\eg: \begin{lstlisting} x; §\C{// int x}§ @@ -612,5 +612,5 @@ A \Index{pointer}/\Index{reference} is a generalization of a variable name, i.e., a mutable address that can point to more than one memory location during its lifetime. (Similarly, an integer variable can contain multiple integer literals during its lifetime versus an integer constant representing a single literal during its lifetime and may not occupy storage as the literal is embedded directly into instructions.) -Hence, a pointer occupies memory to store its current address, and the pointer's value is loaded by dereferencing, e.g.: +Hence, a pointer occupies memory to store its current address, and the pointer's value is loaded by dereferencing, \eg: \begin{quote2} \begin{tabular}{@{}ll@{}} @@ -669,5 +669,5 @@ Except for auto-dereferencing by the compiler, this reference example is the same as the previous pointer example. Hence, a reference behaves like the variable name for the current variable it is pointing-to. -The simplest way to understand a reference is to imagine the compiler inserting a dereference operator before the reference variable for each reference qualifier in a declaration, e.g.: +The simplest way to understand a reference is to imagine the compiler inserting a dereference operator before the reference variable for each reference qualifier in a declaration, \eg: \begin{lstlisting} r2 = ((r1 + r2) * (r3 - r1)) / (r3 - 15); @@ -677,5 +677,5 @@ ®*®r2 = ((®*®r1 + ®*®r2) ®*® (®**®r3 - ®*®r1)) / (®**®r3 - 15); \end{lstlisting} -When a reference operation appears beside a dereference operation, e.g., ©&*©, they cancel out.\footnote{ +When a reference operation appears beside a dereference operation, \eg ©&*©, they cancel out.\footnote{ The unary ©&© operator yields the address of its operand. If the operand has type ``type'', the result has type ``pointer to type''. @@ -721,9 +721,27 @@ ®&®crc = &cx; §\C{// error, cannot change crc}§ \end{lstlisting} -Hence, for type ©& const©, there is no pointer assignment, so ©&rc = &x© is disallowed, and \emph{the address value cannot be ©0© unless an arbitrary pointer is assigned to the reference}, e.g.: +Hence, for type ©& const©, there is no pointer assignment, so ©&rc = &x© is disallowed, and \emph{the address value cannot be ©0© unless an arbitrary pointer is assigned to the reference}, \eg: \begin{lstlisting} int & const r = *0; §\C{// where 0 is the int * zero}§ \end{lstlisting} Otherwise, the compiler is managing the addresses for type ©& const© not the programmer, and by a programming discipline of only using references with references, address errors can be prevented. +Finally, the position of the ©const© qualifier \emph{after} the pointer/reference qualifier causes confuse for C programmers. +The ©const© qualifier cannot be moved before the pointer/reference qualifier for C style-declarations; +\CFA-style declarations attempt to address this issue: +\begin{quote2} +\begin{tabular}{@{}l@{\hspace{3em}}l@{}} +\multicolumn{1}{c@{\hspace{3em}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ +\begin{lstlisting} +®const® * ®const® * const int ccp; +®const® & ®const® & const int ccr; +\end{lstlisting} +& +\begin{lstlisting} +const int * ®const® * ®const® ccp; + +\end{lstlisting} +\end{tabular} +\end{quote2} +where the \CFA declaration is read left-to-right (see \VRef{s:Declarations}). \Index{Initialization} is different than \Index{assignment} because initialization occurs on the empty (uninitialized) storage on an object, while assignment occurs on possibly initialized storage of an object. @@ -785,5 +803,5 @@ \section{Type Operators} -The new declaration syntax can be used in other contexts where types are required, e.g., casts and the pseudo-routine ©sizeof©: +The new declaration syntax can be used in other contexts where types are required, \eg casts and the pseudo-routine ©sizeof©: \begin{quote2} \begin{tabular}{@{}l@{\hspace{3em}}l@{}} @@ -805,5 +823,5 @@ \CFA also supports a new syntax for routine definition, as well as ISO C and K\&R routine syntax. -The point of the new syntax is to allow returning multiple values from a routine~\cite{Galletly96,CLU}, e.g.: +The point of the new syntax is to allow returning multiple values from a routine~\cite{Galletly96,CLU}, \eg: \begin{lstlisting} ®[ int o1, int o2, char o3 ]® f( int i1, char i2, char i3 ) { @@ -817,5 +835,5 @@ \Index*{Michael Tiemann}, with help from \Index*{Doug Lea}, provided named return values in g++, circa 1989.} The value of each local return variable is automatically returned at routine termination. -Declaration qualifiers can only appear at the start of a routine definition, e.g.: +Declaration qualifiers can only appear at the start of a routine definition, \eg: \begin{lstlisting} ®extern® [ int x ] g( int y ) {§\,§} @@ -849,5 +867,5 @@ The inability to use \CFA declarations in these two contexts is probably a blessing because it precludes programmers from arbitrarily switching between declarations forms within a declaration contexts. -C-style declarations can be used to declare parameters for \CFA style routine definitions, e.g.: +C-style declarations can be used to declare parameters for \CFA style routine definitions, \eg: \begin{lstlisting} [ int ] f( * int, int * ); §\C{// returns an integer, accepts 2 pointers to integers}§ @@ -898,5 +916,5 @@ The syntax of the new routine prototype declaration follows directly from the new routine definition syntax; -as well, parameter names are optional, e.g.: +as well, parameter names are optional, \eg: \begin{lstlisting} [ int x ] f (); §\C{// returning int with no parameters}§ @@ -906,5 +924,5 @@ \end{lstlisting} This syntax allows a prototype declaration to be created by cutting and pasting source text from the routine definition header (or vice versa). -It is possible to declare multiple routine-prototypes in a single declaration, but the entire type specification is distributed across \emph{all} routine names in the declaration list (see~\VRef{s:Declarations}), e.g.: +It is possible to declare multiple routine-prototypes in a single declaration, but the entire type specification is distributed across \emph{all} routine names in the declaration list (see~\VRef{s:Declarations}), \eg: \begin{quote2} \begin{tabular}{@{}l@{\hspace{3em}}l@{}} @@ -919,5 +937,5 @@ \end{tabular} \end{quote2} -Declaration qualifiers can only appear at the start of a \CFA routine declaration,\footref{StorageClassSpecifier} e.g.: +Declaration qualifiers can only appear at the start of a \CFA routine declaration,\footref{StorageClassSpecifier} \eg: \begin{lstlisting} extern [ int ] f (int); @@ -928,5 +946,5 @@ \section{Routine Pointers} -The syntax for pointers to \CFA routines specifies the pointer name on the right, e.g.: +The syntax for pointers to \CFA routines specifies the pointer name on the right, \eg: \begin{lstlisting} * [ int x ] () fp; §\C{// pointer to routine returning int with no parameters}§ @@ -1046,5 +1064,5 @@ p( /* positional */, /* named */, . . . ); \end{lstlisting} -While it is possible to implement both approaches, the first possibly is more complex than the second, e.g.: +While it is possible to implement both approaches, the first possibly is more complex than the second, \eg: \begin{lstlisting} p( int x, int y, int z, . . . ); @@ -1056,5 +1074,5 @@ In the second call, the named arguments separate the positional and ellipse arguments, making it trivial to read the call. -The problem is exacerbated with default arguments, e.g.: +The problem is exacerbated with default arguments, \eg: \begin{lstlisting} void p( int x, int y = 2, int z = 3. . . ); @@ -1264,5 +1282,5 @@ As mentioned, tuples can appear in contexts requiring a list of value, such as an argument list of a routine call. -In unambiguous situations, the tuple brackets may be omitted, e.g., a tuple that appears as an argument may have its +In unambiguous situations, the tuple brackets may be omitted, \eg a tuple that appears as an argument may have its square brackets omitted for convenience; therefore, the following routine invocations are equivalent: \begin{lstlisting} @@ -1303,5 +1321,5 @@ Type qualifiers, i.e., const and volatile, may modify a tuple type. -The meaning is the same as for a type qualifier modifying an aggregate type [Int99, x 6.5.2.3(7),x 6.7.3(11)], i.e., the qualifier is distributed across all of the types in the tuple, e.g.: +The meaning is the same as for a type qualifier modifying an aggregate type [Int99, x 6.5.2.3(7),x 6.7.3(11)], i.e., the qualifier is distributed across all of the types in the tuple, \eg: \begin{lstlisting} const volatile [ int, float, const int ] x; @@ -1311,5 +1329,5 @@ [ const volatile int, const volatile float, const volatile int ] x; \end{lstlisting} -Declaration qualifiers can only appear at the start of a \CFA tuple declaration4, e.g.: +Declaration qualifiers can only appear at the start of a \CFA tuple declaration4, \eg: \begin{lstlisting} extern [ int, int ] w1; @@ -1319,5 +1337,5 @@ Unfortunately, C's syntax for subscripts precluded treating them as tuples. The C subscript list has the form ©[i][j]...© and not ©[i, j, ...]©. -Therefore, there is no syntactic way for a routine returning multiple values to specify the different subscript values, e.g., ©f[g()]© always means a single subscript value because there is only one set of brackets. +Therefore, there is no syntactic way for a routine returning multiple values to specify the different subscript values, \eg ©f[g()]© always means a single subscript value because there is only one set of brackets. Fixing this requires a major change to C because the syntactic form ©M[i, j, k]© already has a particular meaning: ©i, j, k© is a comma expression. \end{rationale} @@ -1380,5 +1398,5 @@ Clearly, the types of the entities being assigned must be type compatible with the value of the expression. -Mass assignment has parallel semantics, e.g., the statement: +Mass assignment has parallel semantics, \eg the statement: \begin{lstlisting} [ x, y, z ] = 1.5; @@ -1469,21 +1487,21 @@ \section{Unnamed Structure Fields} -C requires each field of a structure to have a name, except for a bit field associated with a basic type, e.g.: +C requires each field of a structure to have a name, except for a bit field associated with a basic type, \eg: \begin{lstlisting} struct { - int f1; // named field - int f2 : 4; // named field with bit field size - int : 3; // unnamed field for basic type with bit field size - int ; // disallowed, unnamed field - int *; // disallowed, unnamed field - int (*)(int); // disallowed, unnamed field + int f1; §\C{// named field}§ + int f2 : 4; §\C{// named field with bit field size}§ + int : 3; §\C{// unnamed field for basic type with bit field size}§ + int ; §\C{// disallowed, unnamed field}§ + int *; §\C{// disallowed, unnamed field}§ + int (*)(int); §\C{// disallowed, unnamed field}§ }; \end{lstlisting} This requirement is relaxed by making the field name optional for all field declarations; therefore, all the field declarations in the example are allowed. As for unnamed bit fields, an unnamed field is used for padding a structure to a particular size. -A list of unnamed fields is also supported, e.g.: +A list of unnamed fields is also supported, \eg: \begin{lstlisting} struct { - int , , ; // 3 unnamed fields + int , , ; §\C{// 3 unnamed fields}§ } \end{lstlisting} @@ -1498,5 +1516,5 @@ §\emph{expr}§ -> [ §\emph{fieldlist}§ ] \end{lstlisting} -\emph{expr} is any expression yielding a value of type record, e.g., ©struct©, ©union©. +\emph{expr} is any expression yielding a value of type record, \eg ©struct©, ©union©. Each element of \emph{ fieldlist} is an element of the record specified by \emph{expr}. A record-field tuple may be used anywhere a tuple can be used. An example of the use of a record-field tuple is @@ -1760,9 +1778,8 @@ } \end{lstlisting} -While the declaration of the local variable ©y© is useful and its scope is across all ©case© clauses, the initialization for such a variable is defined to never be executed because control always transfers over it. -Furthermore, any statements before the first ©case© clause can only be executed if labelled and transferred to using a ©goto©, either from outside or inside of the ©switch©. -As mentioned, transfer into control structures should be forbidden; -transfers from within the ©switch© body using a ©goto© are equally unpalatable. -As well, the declaration of ©z© is cannot occur after the ©case© because a label can only be attached to a statement, and without a fall through to case 3, ©z© is uninitialized. +While the declaration of the local variable ©y© is useful with a scope across all ©case© clauses, the initialization for such a variable is defined to never be executed because control always transfers over it. +Furthermore, any statements before the first ©case© clause can only be executed if labelled and transferred to using a ©goto©, either from outside or inside of the ©switch©, both of which are problematic. +As well, the declaration of ©z© cannot occur after the ©case© because a label can only be attached to a statement, and without a fall through to case 3, ©z© is uninitialized. +The key observation is that the ©switch© statement branches into control structure, i.e., there are multiple entry points into its statement body. \end{enumerate} @@ -1778,15 +1795,19 @@ and there is only a medium amount of fall-through from one ©case© clause to the next, and most of these result from a list of case values executing common code, rather than a sequence of case actions that compound. \end{itemize} -These observations help to put the suggested changes to the ©switch© into perspective. +These observations help to put the \CFA changes to the ©switch© into perspective. \begin{enumerate} \item Eliminating default fall-through has the greatest potential for affecting existing code. -However, even if fall-through is removed, most ©switch© statements would continue to work because of the explicit transfers already present at the end of each ©case© clause, the common placement of the ©default© clause at the end of the case list, and the most common use of fall-through, i.e., a list of ©case© clauses executing common code, e.g.: -\begin{lstlisting} +However, even if fall-through is removed, most ©switch© statements would continue to work because of the explicit transfers already present at the end of each ©case© clause, the common placement of the ©default© clause at the end of the case list, and the most common use of fall-through, i.e., a list of ©case© clauses executing common code, \eg: + \begin{lstlisting} case 1: case 2: case 3: ... \end{lstlisting} still work. Nevertheless, reversing the default action would have a non-trivial effect on case actions that compound, such as the above example of processing shell arguments. -Therefore, to preserve backwards compatibility, it is necessary to introduce a new kind of ©switch© statement, called ©choose©, with no implicit fall-through semantics and an explicit fall-through if the last statement of a case-clause ends with the new keyword ©fallthru©, e.g.: +<<<<<<< HEAD +Therefore, to preserve backwards compatibility, it is necessary to introduce a new kind of ©switch© statement, called ©choose©, with no implicit fall-through semantics and an explicit fall-through if the last statement of a case-clause ends with the new keyword ©fallthru©, \eg: +======= +Therefore, to preserve backwards compatibility, it is necessary to introduce a new kind of ©switch© statement, called ©choose©, with no implicit fall-through semantics and an explicit fall-through if the last statement of a case-clause ends with the new keyword ©fallthrough©/©fallthru©, e.g.: +>>>>>>> 080615890f586cb9954c252b55cab47f52c25758 \begin{lstlisting} ®choose® ( i ) { @@ -1815,16 +1836,16 @@ Therefore, no change is made for this issue. \item -Dealing with unreachable code in a ©switch©/©choose© body is solved by restricting declarations and associated initialization to the start of statement body, which is executed \emph{before} the transfer to the appropriate ©case© clause.\footnote{ -Essentially, these declarations are hoisted before the statement and both declarations and statement are surrounded by a compound statement.} and precluding statements before the first ©case© clause. -Further declaration in the statement body are disallowed. +Dealing with unreachable code in a ©switch©/©choose© body is solved by restricting declarations and associated initialization to the start of statement body, which is executed \emph{before} the transfer to the appropriate ©case© clause\footnote{ +Essentially, these declarations are hoisted before the ©switch©/©choose© statement and both declarations and statement are surrounded by a compound statement.} and precluding statements before the first ©case© clause. +Further declarations at the same nesting level as the statement body are disallowed to ensure every transfer into the body is sound. \begin{lstlisting} switch ( x ) { - ®int i = 0;® §\C{// allowed}§ + ®int i = 0;® §\C{// allowed only at start}§ case 0: ... - ®int i = 0;® §\C{// disallowed}§ + ®int j = 0;® §\C{// disallowed}§ case 1: { - ®int i = 0;® §\C{// allowed in any compound statement}§ + ®int k = 0;® §\C{// allowed at different nesting levels}§ ... } @@ -2707,6 +2728,6 @@ Like the \Index*[C++]{\CC} lexical problem with closing template-syntax, e.g, ©Foo>®©, this issue can be solved with a more powerful lexer/parser. -There are several ambiguous cases with operator identifiers, e.g., ©int *?*?()©, where the string ©*?*?© can be lexed as ©*©/©?*?© or ©*?©/©*?©. -Since it is common practise to put a unary operator juxtaposed to an identifier, e.g., ©*i©, users will be annoyed if they cannot do this with respect to operator identifiers. +There are several ambiguous cases with operator identifiers, \eg ©int *?*?()©, where the string ©*?*?© can be lexed as ©*©/©?*?© or ©*?©/©*?©. +Since it is common practise to put a unary operator juxtaposed to an identifier, \eg ©*i©, users will be annoyed if they cannot do this with respect to operator identifiers. Even with this special hack, there are 5 general cases that cannot be handled. The first case is for the function-call identifier ©?()©: @@ -2773,5 +2794,5 @@ This means that a function requiring mutual exclusion could block if the lock is already held by another thread. Blocking on a monitor lock does not block the kernel thread, it simply blocks the user thread, which yields its kernel thread while waiting to obtain the lock. -If multiple mutex parameters are specified, they will be locked in parameter order (i.e. first parameter is locked first) and unlocked in the +If multiple mutex parameters are specified, they will be locked in parameter order (\ie first parameter is locked first) and unlocked in the reverse order. \begin{lstlisting} @@ -4342,4 +4363,9 @@ +\section{New Keywowrds} + +©catch©, ©catchResume©, ©choose©, \quad ©disable©, ©dtype©, \quad ©enable©, \quad ©fallthrough©, ©fallthru©, ©finally©, ©forall©, ©ftype©, \quad ©lvalue©, \quad ©otype©, \quad ©throw©, ©throwResume©, ©trait©, ©try© + + \section{Incompatible} @@ -4471,5 +4497,5 @@ \CFA is C \emph{incompatible} on this issue, and provides semantics similar to \Index*[C++]{\CC}. Nested types are not hoisted and can be referenced using the field selection operator ``©.©'', unlike the \CC scope-resolution operator ``©::©''. -Given that nested types in C are equivalent to not using them, i.e., they are essentially useless, it is unlikely there are any realistic usages that break because of this incompatibility. +Given that nested types in C are equivalent to not using them, \ie they are essentially useless, it is unlikely there are any realistic usages that break because of this incompatibility. \end{description} @@ -5162,5 +5188,5 @@ \label{s:RationalNumbers} -Rational numbers are numbers written as a ratio, i.e., as a fraction, where the numerator (top number) and the denominator (bottom number) are whole numbers. +Rational numbers are numbers written as a ratio, \ie as a fraction, where the numerator (top number) and the denominator (bottom number) are whole numbers. When creating and computing with rational numbers, results are constantly reduced to keep the numerator and denominator as small as possible. Index: src/CodeGen/CodeGenerator.cc =================================================================== --- src/CodeGen/CodeGenerator.cc (revision e21c72d5e2c7ca2735fce0ab2c4d00dc249711cc) +++ src/CodeGen/CodeGenerator.cc (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) @@ -9,7 +9,7 @@ // Author : Richard C. Bilson // Created On : Mon May 18 07:44:20 2015 -// Last Modified By : Peter A. Buhr -// Last Modified On : Fri Jul 15 15:53:15 2016 -// Update Count : 306 +// Last Modified By : +// Last Modified On : Sun Jul 31 08:42:18 2016 +// Update Count : 345 // @@ -45,5 +45,5 @@ bool wantSpacing( Statement * stmt) { return dynamic_cast< IfStmt * >( stmt ) || dynamic_cast< CompoundStmt * >( stmt ) || - dynamic_cast< WhileStmt * >( stmt ) || dynamic_cast< ForStmt * > ( stmt ) || dynamic_cast< SwitchStmt *>( stmt ); + dynamic_cast< WhileStmt * >( stmt ) || dynamic_cast< ForStmt * >( stmt ) || dynamic_cast< SwitchStmt *>( stmt ); } @@ -83,5 +83,5 @@ } - CodeGenerator::CodeGenerator( std::ostream &os ) : indent( *this), cur_indent( 0 ), insideFunction( false ), output( os ), printLabels( *this ) { } + CodeGenerator::CodeGenerator( std::ostream &os ) : indent( *this), cur_indent( 0 ), insideFunction( false ), output( os ), printLabels( *this ) {} CodeGenerator::CodeGenerator( std::ostream &os, std::string init, int indentation, bool infunp ) @@ -155,4 +155,5 @@ objectDecl->get_init()->accept( *this ); } // if + if ( objectDecl->get_bitfieldWidth() ) { output << ":"; @@ -172,9 +173,9 @@ cur_indent += CodeGenerator::tabsize; - for ( std::list< Declaration* >::iterator i = memb.begin(); i != memb.end(); i++) { + for ( std::list< Declaration* >::iterator i = memb.begin(); i != memb.end(); i++ ) { output << indent; (*i)->accept( *this ); output << ";" << endl; - } + } // for cur_indent -= CodeGenerator::tabsize; @@ -257,6 +258,6 @@ (*iter)->accept( *this ); output << "]"; - } - } + } // if + } // for output << " = "; } @@ -317,5 +318,5 @@ // do nothing ; - } + } // switch switch ( opInfo.type ) { @@ -385,5 +386,5 @@ // there are no intrinsic definitions of 0/1 or label addresses as functions assert( false ); - } + } // switch } else { varExpr->accept( *this ); @@ -417,5 +418,4 @@ case OT_CALL: assert( false ); - case OT_CTOR: @@ -437,5 +437,5 @@ // no constructors with 0 or more than 2 parameters assert( false ); - } + } // if break; @@ -470,10 +470,17 @@ // there are no intrinsic definitions of 0 or 1 as functions assert( false ); - } + } // switch } else { - nameExpr->accept( *this ); - output << "("; - genCommaList( untypedExpr->get_args().begin(), untypedExpr->get_args().end() ); - output << ")"; + if ( nameExpr->get_name() == "Range" ) { // case V1 ... V2 or case V1~V2 + assert( untypedExpr->get_args().size() == 2 ); + (*untypedExpr->get_args().begin())->accept( *this ); + output << " ... "; + (*--untypedExpr->get_args().end())->accept( *this ); + } else { // builtin routines + nameExpr->accept( *this ); + output << "("; + genCommaList( untypedExpr->get_args().begin(), untypedExpr->get_args().end() ); + output << ")"; + } // if } // if } else { @@ -521,5 +528,5 @@ // otherwise, the cast is to an lvalue type, so the cast should be dropped, since the result of a cast is // never an lvalue in C - } + } // if castExpr->get_arg()->accept( *this ); output << ")"; @@ -654,5 +661,5 @@ if ( wantSpacing( *i ) ) { output << endl; - } + } // if } cur_indent -= CodeGenerator::tabsize; @@ -737,5 +744,5 @@ (*i)->accept( *this ); output << endl; - } + } // for cur_indent -= CodeGenerator::tabsize; } @@ -759,5 +766,5 @@ output << "continue"; break; - } + } // switch output << ";"; } @@ -798,5 +805,5 @@ if ( forStmt->get_condition() != 0 ) { forStmt->get_condition()->accept( *this ); - } + } // if output << ";"; @@ -805,5 +812,5 @@ Expression * expr = new CastExpr( forStmt->get_increment() ); expr->accept( *this ); - } + } // if output << ") "; Index: src/CodeGen/CodeGenerator.h =================================================================== --- src/CodeGen/CodeGenerator.h (revision e21c72d5e2c7ca2735fce0ab2c4d00dc249711cc) +++ src/CodeGen/CodeGenerator.h (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) @@ -10,6 +10,6 @@ // Created On : Mon May 18 07:44:20 2015 // Last Modified By : Peter A. Buhr -// Last Modified On : Mon Jul 4 17:12:40 2016 -// Update Count : 34 +// Last Modified On : Sat Jul 30 11:10:42 2016 +// Update Count : 37 // @@ -118,5 +118,5 @@ void handleAggregate( AggregateDecl *aggDecl ); void handleTypedef( NamedTypeDecl *namedType ); - }; + }; // CodeGenerator template< class Iterator > Index: src/ControlStruct/CaseRangeMutator.cc =================================================================== --- src/ControlStruct/CaseRangeMutator.cc (revision e21c72d5e2c7ca2735fce0ab2c4d00dc249711cc) +++ src/ControlStruct/CaseRangeMutator.cc (revision e7b2559bdb7a42cc98e4d8c4949c375932028c3a) @@ -9,7 +9,7 @@ // Author : Rodolfo G. Esteves // Created On : Mon May 18 07:44:20 2015 -// Last Modified By : Peter A. Buhr -// Last Modified On : Tue Jul 12 17:35:13 2016 -// Update Count : 9 +// Last Modified By : +// Last Modified On : Sun Jul 31 12:16:28 2016 +// Update Count : 32 // @@ -34,27 +34,28 @@ std::list< Statement * >::iterator i = cases.begin(); while ( i != cases.end() ) { - (*i )->acceptMutator( *this ); + (*i)->acceptMutator( *this ); if ( ! newCaseLabels.empty() ) { + std::cout << "FRED" << std::endl; std::list< Statement * > newCases; // transform( newCaseLabels.begin(), newCaseLabels.end(), bnd1st( ptr_fun( ctor< CaseStmt, Label, Expression * > ) ) ); - for ( std::list< Expression * >::iterator j = newCaseLabels.begin(); - j != newCaseLabels.end(); j++ ) { - std::list