Changeset b21c77a

Jenkins/TestRegen

-                      r97397a26
+                      rb21c77a
                         email()
+                }
+        }
+        }
         catch (Exception caughtError) {
                 email_error()
 …
         def install_dir = pwd tmp: true
         //Configure the conpilation (Output is not relevant)
         //Use the current directory as the installation target so nothing
 …
                 def email_subject = "[cforall dashboard][TEST REGEN# ${env.BUILD_NUMBER}] - Result"
                 def email_body = """This is an automated email from the Jenkins build machine. It was
 generated http://plg2:8082/dashboard.
+generated https://cforall.uwaterloo.ca:8082/dashboard.html.
 Please apply the required changes using the following method :
 …
         def email_subject = "[cforall dashboard][TEST REGEN# ${env.BUILD_NUMBER}] - FAILURE"
         def email_body = """This is an automated email from the Jenkins build machine. It was
 generated http://plg2:8082/dashboard.
+generated https://cforall.uwaterloo.ca:8082/dashboard.html.
 Test generation encoutered an error please see attached logs

Jenkinsfile

r97397a26	rb21c77a
174	174
175	175	def notify_server(int wait) {
176		sh """curl --data "wait=${wait}" -X POST http~~://plg2~~:8082/jenkins/notify > /dev/null \|\| true"""
	176	sh """curl --data "wait=${wait}" -X POST https://cforall.uwaterloo.ca:8082/jenkins/notify > /dev/null \|\| true"""
177	177	return
178	178	}
…	…
329	329
330	330	//Then publish the results
331		sh 'curl -H \'Content-Type: application/json\' --data @bench.json http~~://plg2~~:8082/jenkins/publish > /dev/null \|\| true'
	331	sh 'curl -H \'Content-Type: application/json\' --data @bench.json https://cforall.uwaterloo.ca:8082/jenkins/publish > /dev/null \|\| true'
332	332	}
333	333	}

README

-                      r97397a26
+                      rb21c77a
 - the implicit coercion of structure types to the type of their first member is
   not implemented
 Who is responsible for cfa-cc?
 ------------------------------
 …
 The Cforall project maintains a web page:
         http://plg.uwaterloo.ca/~cforall
+        https://cforall.uwaterloo.ca

doc/papers/OOPSLA17/Makefile

-                      r97397a26
+                      rb21c77a
 DOCUMENT = generic_types.pdf
+BASE = ${basename ${DOCUMENT}}
 # Directives #
 …
 clean :
         @rm -frv ${DOCUMENT} ${basename ${DOCUMENT}}.ps ${Build}
+        @rm -frv ${DOCUMENT} ${BASE}.ps ${Build}
 # File Dependencies #
 ${DOCUMENT} : ${basename ${DOCUMENT}}.ps
+${DOCUMENT} : ${BASE}.ps
         ps2pdf $<
 ${basename ${DOCUMENT}}.ps : ${basename ${DOCUMENT}}.dvi
+${BASE}.ps : ${BASE}.dvi
         dvips ${Build}/$< -o $@
+${basename ${DOCUMENT}}.dvi : Makefile ${Build} ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} ../../bibliography/pl.bib
+${BASE}.dvi : Makefile ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
+                ../../bibliography/pl.bib | ${Build}
         # Must have *.aux file containing citations for bibtex
         if [ ! -r ${basename $@}.aux ] ; then ${LaTeX} ${basename $@}.tex ; fi
 …
 ## Define the default recipes.
 ${Build}:
+${Build} :
         mkdir -p ${Build}
 …
         gnuplot -e Build="'${Build}/'" evaluation/timing.gp
 %.tex : %.fig
+%.tex : %.fig | ${Build}
         fig2dev -L eepic $< > ${Build}/$@
 %.ps : %.fig
+%.ps : %.fig | ${Build}
         fig2dev -L ps $< > ${Build}/$@
 %.pstex : %.fig
+%.pstex : %.fig | ${Build}
         fig2dev -L pstex $< > ${Build}/$@
         fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t

doc/papers/concurrency/Makefile

-                      r97397a26
+                      rb21c77a
 FIGURES = ${addsuffix .tex, \
-monitor \
-ext_monitor \
 int_monitor \
 dependency \
 …
 PICTURES = ${addsuffix .pstex, \
+monitor \
+ext_monitor \
 system \
 monitor_structs \
 …
         dvips ${Build}/$< -o $@
 ${BASE}.dvi : Makefile ${Build} ${BASE}.out.ps WileyNJD-AMA.bst ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
                 annex/local.bib ../../bibliography/pl.bib
+${BASE}.dvi : Makefile ${BASE}.out.ps WileyNJD-AMA.bst ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
+                annex/local.bib ../../bibliography/pl.bib | ${Build}
         # Must have *.aux file containing citations for bibtex
         if [ ! -r ${basename $@}.aux ] ; then ${LaTeX} ${basename $@}.tex ; fi
         ${BibTeX} ${Build}/${basename $@}
+        -${BibTeX} ${Build}/${basename $@}
         # Some citations reference others so run again to resolve these citations
         ${LaTeX} ${basename $@}.tex
         ${BibTeX} ${Build}/${basename $@}
+        -${BibTeX} ${Build}/${basename $@}
         # Run again to finish citations
         ${LaTeX} ${basename $@}.tex
 …
 ## Define the default recipes.
 ${Build}:
+${Build} :
         mkdir -p ${Build}
 ${BASE}.out.ps: ${Build}
+${BASE}.out.ps : | ${Build}
         ln -fs ${Build}/Paper.out.ps .
 WileyNJD-AMA.bst:
+WileyNJD-AMA.bst :
         ln -fs ../AMA/AMA-stix/ama/WileyNJD-AMA.bst .
 %.tex : %.fig ${Build}
+%.tex : %.fig | ${Build}
         fig2dev -L eepic $< > ${Build}/$@
 %.ps : %.fig ${Build}
+%.ps : %.fig | ${Build}
         fig2dev -L ps $< > ${Build}/$@
 %.pstex : %.fig ${Build}
+%.pstex : %.fig | ${Build}
         fig2dev -L pstex $< > ${Build}/$@
         fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t

doc/papers/concurrency/Paper.tex

-                      r97397a26
+                      rb21c77a
 \newcommand{\Textbf}[2][red]{{\color{#1}{\textbf{#2}}}}
 \newcommand{\Emph}[2][red]{{\color{#1}\textbf{\emph{#2}}}}
-\newcommand{\R}[1]{\Textbf{#1}}
-\newcommand{\B}[1]{{\Textbf[blue]{#1}}}
-\newcommand{\G}[1]{{\Textbf[OliveGreen]{#1}}}
 \newcommand{\uC}{$\mu$\CC}
+\newcommand{\cit}{\textsuperscript{[Citation Needed]}\xspace}
+\newcommand{\TODO}{{\Textbf{TODO}}}
+\newcommand{\TODO}[1]{{\Textbf{#1}}}
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 …
 \section{Introduction}
 This paper provides a minimal concurrency \newterm{Abstract Program Interface} (API) that is simple, efficient and can be used to build other concurrency features.
+This paper provides a minimal concurrency \newterm{Application Program Interface} (API) that is simple, efficient and can be used to build other concurrency features.
 While the simplest concurrency system is a thread and a lock, this low-level approach is hard to master.
 An easier approach for programmers is to support higher-level constructs as the basis of concurrency.
 …
 Hence, there are two problems to be solved: concurrency and parallelism.
 While these two concepts are often combined, they are distinct, requiring different tools~\cite[\S~2]{Buhr05a}.
 Concurrency tools handle synchronization and mutual exclusion, while parallelism tools handle performance, cost and resource utilization.
+Concurrency tools handle mutual exclusion and synchronization, while parallelism tools handle performance, cost, and resource utilization.
 The proposed concurrency API is implemented in a dialect of C, called \CFA.
 …
 Extended versions and explanation of the following code examples are available at the \CFA website~\cite{Cforall} or in Moss~\etal~\cite{Moss18}.
 \CFA is an extension of ISO-C, and hence, supports all C paradigms.
+\CFA is a non-object-oriented extension of ISO-C, and hence, supports all C paradigms.
 %It is a non-object-oriented system-language, meaning most of the major abstractions have either no runtime overhead or can be opted out easily.
 Like C, the basics of \CFA revolve around structures and functions.
+Like C, the building blocks of \CFA are structures and routines.
 Virtually all of the code generated by the \CFA translator respects C memory layouts and calling conventions.
 While \CFA is not an object-oriented language, lacking the concept of a receiver (\eg @this@) and nominal inheritance-relationships, C does have a notion of objects: ``region of data storage in the execution environment, the contents of which can represent values''~\cite[3.15]{C11}.
 …
 int x = 1, y = 2, z = 3;
 int * p1 = &x, ** p2 = &p1,  *** p3 = &p2,      $\C{// pointers to x}$
         `&` r1 = x,  `&&` r2 = r1,  `&&&` r3 = r2;      $\C{// references to x}$
+    `&` r1 = x,   `&&` r2 = r1,   `&&&` r3 = r2;        $\C{// references to x}$
 int * p4 = &z, `&` r4 = z;
 …
         'with' '(' $\emph{expression-list}$ ')' $\emph{compound-statement}$
 \end{cfa}
 and may appear as the body of a function or nested within a function body.
+and may appear as the body of a routine or nested within a routine body.
 Each expression in the expression-list provides a type and object.
 The type must be an aggregate type.
 …
 \CFA maximizes the ability to reuse names via overloading to aggressively address the naming problem.
 Both variables and functions may be overloaded, where selection is based on types, and number of returns (as in Ada~\cite{Ada}) and arguments.
+Both variables and routines may be overloaded, where selection is based on types, and number of returns (as in Ada~\cite{Ada}) and arguments.
 \begin{cquote}
 \vspace*{-\baselineskip}%???
 …
 \end{cquote}
 Overloading is important for \CFA concurrency since the runtime system relies on creating different types to represent concurrency objects.
+Therefore, overloading is necessary to prevent the need for long prefixes and other naming conventions to prevent name clashes.
+As seen in Section~\ref{basics}, function @main@ is heavily overloaded.
+Variable overloading is useful in the parallel semantics of the @with@ statement for fields with the same name:
+Therefore, overloading eliminates long prefixes and other naming conventions to prevent name clashes.
+As seen in Section~\ref{basics}, routine @main@ is heavily overloaded.
+For example, variable overloading is useful in the parallel semantics of the @with@ statement for fields with the same name:
 \begin{cfa}
 struct S { int `i`; int j; double m; } s;
 …
+}
 \end{cfa}
 For parallel semantics, both @s.i@ and @t.i@ are visible the same type, so only @i@ is ambiguous without qualification.
+For parallel semantics, both @s.i@ and @t.i@ are visible with the same type, so only @i@ is ambiguous without qualification.
 …
 Overloading also extends to operators.
 Operator-overloading syntax names a routine with the operator symbol and question marks for the operands:
+Operator-overloading syntax creates a routine name with an operator symbol and question marks for the operands:
 \begin{cquote}
 \lstDeleteShortInline@%
 …
 \end{cquote}
 While concurrency does not use operator overloading directly, it provides an introduction for the syntax of constructors.
-\subsection{Parametric Polymorphism}
-\label{s:ParametricPolymorphism}
-The signature feature of \CFA is parametric-polymorphic functions~\cite{} with functions generalized using a @forall@ clause (giving the language its name), which allow separately compiled routines to support generic usage over multiple types.
-For example, the following sum function works for any type that supports construction from 0 and addition:
-\begin{cfa}
-forall( otype T | { void `?{}`( T *, zero_t ); T `?+?`( T, T ); } ) // constraint type, 0 and +
-T sum( T a[$\,$], size_t size ) {
-        `T` total = { `0` };                                    $\C{// initialize by 0 constructor}$
-        for ( size_t i = 0; i < size; i += 1 )
-                total = total `+` a[i];                         $\C{// select appropriate +}$
-        return total;
+}
-S sa[5];
-int i = sum( sa, 5 );                                           $\C{// use S's 0 construction and +}$
-\end{cfa}
-\CFA provides \newterm{traits} to name a group of type assertions, where the trait name allows specifying the same set of assertions in multiple locations, preventing repetition mistakes at each function declaration:
-\begin{cfa}
-trait `sumable`( otype T ) {
-        void `?{}`( T &, zero_t );                              $\C{// 0 literal constructor}$
-        T `?+?`( T, T );                                                $\C{// assortment of additions}$
-        T ?+=?( T &, T );
-        T ++?( T & );
-        T ?++( T & );
-};
-forall( otype T `| sumable( T )` )                      $\C{// use trait}$
-T sum( T a[$\,$], size_t size );
-\end{cfa}
-Assertions can be @otype@ or @dtype@.
-@otype@ refers to a ``complete'' object, \ie an object has a size, default constructor, copy constructor, destructor and an assignment operator.
-@dtype@ only guarantees an object has a size and alignment.
-Using the return type for discrimination, it is possible to write a type-safe @alloc@ based on the C @malloc@:
-\begin{cfa}
-forall( dtype T | sized(T) ) T * alloc( void ) { return (T *)malloc( sizeof(T) ); }
-int * ip = alloc();                                                     $\C{// select type and size from left-hand side}$
-double * dp = alloc();
-struct S {...} * sp = alloc();
-\end{cfa}
-where the return type supplies the type/size of the allocation, which is impossible in most type systems.
 …
 \CFA also provides @new@ and @delete@, which behave like @malloc@ and @free@, in addition to constructing and destructing objects:
 \begin{cfa}
 {       struct S s = {10};                                              $\C{// allocation, call constructor}$
         ...
+{
+        ... struct S s = {10}; ...                              $\C{// allocation, call constructor}$
 }                                                                                       $\C{// deallocation, call destructor}$
 struct S * s = new();                                           $\C{// allocation, call constructor}$
 …
 delete( s );                                                            $\C{// deallocation, call destructor}$
 \end{cfa}
+\CFA concurrency uses object lifetime as a means of synchronization and/or mutual exclusion.
+\CFA concurrency uses object lifetime as a means of mutual exclusion and/or synchronization.
+\subsection{Parametric Polymorphism}
+\label{s:ParametricPolymorphism}
+The signature feature of \CFA is parametric-polymorphic routines~\cite{} with routines generalized using a @forall@ clause (giving the language its name), which allow separately compiled routines to support generic usage over multiple types.
+For example, the following sum routine works for any type that supports construction from 0 and addition:
+\begin{cfa}
+forall( otype T | { void `?{}`( T *, zero_t ); T `?+?`( T, T ); } ) // constraint type, 0 and +
+T sum( T a[$\,$], size_t size ) {
+        `T` total = { `0` };                                    $\C{// initialize by 0 constructor}$
+        for ( size_t i = 0; i < size; i += 1 )
+                total = total `+` a[i];                         $\C{// select appropriate +}$
+        return total;
+}
+S sa[5];
+int i = sum( sa, 5 );                                           $\C{// use S's 0 construction and +}$
+\end{cfa}
+The builtin type @zero_t@ (and @one_t@) overload constant 0 (and 1) for a new types, where both 0 and 1 have special meaning in C.
+\CFA provides \newterm{traits} to name a group of type assertions, where the trait name allows specifying the same set of assertions in multiple locations, preventing repetition mistakes at each routine declaration:
+\begin{cfa}
+trait `sumable`( otype T ) {
+        void `?{}`( T &, zero_t );                              $\C{// 0 literal constructor}$
+        T `?+?`( T, T );                                                $\C{// assortment of additions}$
+        T ?+=?( T &, T );
+        T ++?( T & );
+        T ?++( T & );
+};
+forall( otype T `| sumable( T )` )                      $\C{// use trait}$
+T sum( T a[$\,$], size_t size );
+\end{cfa}
+Assertions can be @otype@ or @dtype@.
+@otype@ refers to a ``complete'' object, \ie an object has a size, default constructor, copy constructor, destructor and an assignment operator.
+@dtype@ only guarantees an object has a size and alignment.
+Using the return type for discrimination, it is possible to write a type-safe @alloc@ based on the C @malloc@:
+\begin{cfa}
+forall( dtype T | sized(T) ) T * alloc( void ) { return (T *)malloc( sizeof(T) ); }
+int * ip = alloc();                                                     $\C{// select type and size from left-hand side}$
+double * dp = alloc();
+struct S {...} * sp = alloc();
+\end{cfa}
+where the return type supplies the type/size of the allocation, which is impossible in most type systems.
 …
 \subsection{\protect\CFA's Thread Building Blocks}
 An important missing feature in C is threading\footnote{While the C11 standard defines a ``threads.h'' header, it is minimal and defined as optional.
+An important missing feature in C is threading\footnote{While the C11 standard defines a \protect\lstinline@threads.h@ header, it is minimal and defined as optional.
 As such, library support for threading is far from widespread.
 At the time of writing the paper, neither \protect\lstinline|gcc| nor \protect\lstinline|clang| support ``threads.h'' in their standard libraries.}.
 On modern architectures, a lack of threading is unacceptable~\cite{Sutter05, Sutter05b}, and therefore existing and new programming languages must have tools for writing efficient concurrent programs to take advantage of parallelism.
+At the time of writing the paper, neither \protect\lstinline@gcc@ nor \protect\lstinline@clang@ support \protect\lstinline@threads.h@ in their standard libraries.}.
+In modern programming languages, a lack of threading is unacceptable~\cite{Sutter05, Sutter05b}, and therefore existing and new programming languages must have tools for writing efficient concurrent programs to take advantage of parallelism.
 As an extension of C, \CFA needs to express these concepts in a way that is as natural as possible to programmers familiar with imperative languages.
 Furthermore, because C is a system-level language, programmers expect to choose precisely which features they need and which cost they are willing to pay.
 …
 \newbox\myboxA
 \begin{lrbox}{\myboxA}
 \begin{lstlisting}[aboveskip=0pt,belowskip=0pt]
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
 `int f1, f2, state = 1;`   // single global variables
 int fib() {
 …
+        }
+}
 \end{lstlisting}
+\end{cfa}
 \end{lrbox}
 \newbox\myboxB
 \begin{lrbox}{\myboxB}
 \begin{lstlisting}[aboveskip=0pt,belowskip=0pt]
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
 #define FIB_INIT `{ 0, 1 }`
 typedef struct { int f2, f1; } Fib;
 …
+        }
+}
 \end{lstlisting}
+\end{cfa}
 \end{lrbox}
 …
 \newbox\myboxA
 \begin{lrbox}{\myboxA}
 \begin{lstlisting}[aboveskip=0pt,belowskip=0pt]
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
 `coroutine` Fib { int fn; };
 void main( Fib & fib ) with( fib ) {
 …
+        }
+}
 \end{lstlisting}
+\end{cfa}
 \end{lrbox}
 \newbox\myboxB
 \begin{lrbox}{\myboxB}
 \begin{lstlisting}[aboveskip=0pt,belowskip=0pt]
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
 `coroutine` Fib { int ret; };
 void main( Fib & f ) with( fib ) {
 …
 \end{lstlisting}
+\end{cfa}
 \end{lrbox}
 \subfloat[3 States, internal variables]{\label{f:Coroutine3States}\usebox\myboxA}
 …
 Using a coroutine, it is possible to express the Fibonacci formula directly without any of the C problems.
+Figure~\ref{f:Coroutine3States} creates a @coroutine@ type:
+\begin{cfa}
+`coroutine` Fib { int fn; };
+\end{cfa}
+which provides communication, @fn@, for the \newterm{coroutine main}, @main@, which runs on the coroutine stack, and possibly multiple interface functions, @next@.
+Figure~\ref{f:Coroutine3States} creates a @coroutine@ type, @`coroutine` Fib { int fn; }@, which provides communication, @fn@, for the \newterm{coroutine main}, @main@, which runs on the coroutine stack, and possibly multiple interface routines, \eg @next@.
 Like the structure in Figure~\ref{f:ExternalState}, the coroutine type allows multiple instances, where instances of this type are passed to the (overloaded) coroutine main.
 The coroutine main's stack holds the state for the next generation, @f1@ and @f2@, and the code has the three suspend points, representing the three states in the Fibonacci formula, to context switch back to the caller's resume.
 The interface function, @next@, takes a Fibonacci instance and context switches to it using @resume@;
+The coroutine main's stack holds the state for the next generation, @f1@ and @f2@, and the code has the three suspend points, representing the three states in the Fibonacci formula, to context switch back to the caller's @resume@.
+The interface routine @next@, takes a Fibonacci instance and context switches to it using @resume@;
 on restart, the Fibonacci field, @fn@, contains the next value in the sequence, which is returned.
 The first @resume@ is special because it cocalls the coroutine at its coroutine main and allocates the stack;
 …
 \newbox\myboxA
 \begin{lrbox}{\myboxA}
 \begin{lstlisting}[aboveskip=0pt,belowskip=0pt]
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
 `coroutine` Format {
         char ch;   // used for communication
 …
+        }
+}
 \end{lstlisting}
+\end{cfa}
 \end{lrbox}
 \newbox\myboxB
 \begin{lrbox}{\myboxB}
 \begin{lstlisting}[aboveskip=0pt,belowskip=0pt]
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
 struct Format {
         char ch;
 …
         format( &fmt );
+}
 \end{lstlisting}
+\end{cfa}
 \end{lrbox}
 \subfloat[\CFA Coroutine]{\label{f:CFAFmt}\usebox\myboxA}
 …
 \end{figure}
 The previous examples are \newterm{asymmetric (semi) coroutine}s because one coroutine always calls a resuming function for another coroutine, and the resumed coroutine always suspends back to its last resumer, similar to call/return for normal functions.
 However, there is no stack growth because @resume@/@suspend@ context switch to existing stack-frames rather than create new ones.
 \newterm{Symmetric (full) coroutine}s have a coroutine call a resuming function for another coroutine, which eventually forms a resuming-call cycle.
+The previous examples are \newterm{asymmetric (semi) coroutine}s because one coroutine always calls a resuming routine for another coroutine, and the resumed coroutine always suspends back to its last resumer, similar to call/return for normal routines.
+However,@resume@/@suspend@ context switch to existing stack-frames rather than create new ones so there is no stack growth.
+\newterm{Symmetric (full) coroutine}s have a coroutine call a resuming routine for another coroutine, which eventually forms a resuming-call cycle.
 (The trivial cycle is a coroutine resuming itself.)
 This control flow is similar to recursion for normal routines, but again there is no stack growth from the context switch.
 …
 Figure~\ref{f:ProdCons} shows a producer/consumer symmetric-coroutine performing bi-directional communication.
 Since the solution involves a full-coroutining cycle, the program main creates one coroutine in isolation, passes this coroutine to its partner, and closes the cycle at the call to @start@.
 The @start@ function communicates both the number of elements to be produced and the consumer into the producer's coroutine structure.
+The @start@ routine communicates both the number of elements to be produced and the consumer into the producer's coroutine structure.
 Then the @resume@ to @prod@ creates @prod@'s stack with a frame for @prod@'s coroutine main at the top, and context switches to it.
 @prod@'s coroutine main starts, creates local variables that are retained between coroutine activations, and executes $N$ iterations, each generating two random values, calling the consumer to deliver the values, and printing the status returned from the consumer.
 …
 The producer call to @delivery@ transfers values into the consumer's communication variables, resumes the consumer, and returns the consumer status.
 For the first resume, @cons@'s stack is initialized, creating local variables retained between subsequent activations of the coroutine.
 The consumer iterates until the @done@ flag is set, prints, increments status, and calls back to the producer via @payment@, and on return from @payment@, prints the receipt from the producer and increments @money@ (inflation).
+The consumer iterates until the @done@ flag is set, prints the values delivered by the producer, increments status, and calls back to the producer via @payment@, and on return from @payment@, prints the receipt from the producer and increments @money@ (inflation).
 The call from the consumer to the @payment@ introduces the cycle between producer and consumer.
 When @payment@ is called, the consumer copies values into the producer's communication variable and a resume is executed.
 …
 \end{cfa}
 and the programming language (and possibly its tool set, \eg debugger) may need to understand @baseCoroutine@ because of the stack.
 Furthermore, the execution of constructs/destructors is in the wrong order for certain operations, \eg for threads;
 \eg, if the thread is implicitly started, it must start \emph{after} all constructors, because the thread relies on a completely initialized object, but the inherited constructor runs \emph{before} the derived.
+Furthermore, the execution of constructs/destructors is in the wrong order for certain operations.
+For example, for threads if the thread is implicitly started, it must start \emph{after} all constructors, because the thread relies on a completely initialized object, but the inherited constructor runs \emph{before} the derived.
 An alternatively is composition:
 …
 However, there is nothing preventing wrong placement or multiple declarations.
 For coroutines as for threads, many implementations are based on routine pointers or function objects~\cite{Butenhof97, C++14, MS:VisualC++, BoostCoroutines15}.
+For coroutines as for threads, many implementations are based on routine pointers or routine objects~\cite{Butenhof97, C++14, MS:VisualC++, BoostCoroutines15}.
 For example, Boost implements coroutines in terms of four functor object-types:
 \begin{cfa}
 …
 symmetric_coroutine<>::yield_type
 \end{cfa}
 Similarly, the canonical threading paradigm is often based on function pointers, \eg @pthread@~\cite{pthreads}, \Csharp~\cite{Csharp}, Go~\cite{Go}, and Scala~\cite{Scala}.
+Similarly, the canonical threading paradigm is often based on routine pointers, \eg @pthreads@~\cite{pthreads}, \Csharp~\cite{Csharp}, Go~\cite{Go}, and Scala~\cite{Scala}.
 However, the generic thread-handle (identifier) is limited (few operations), unless it is wrapped in a custom type.
 \begin{cfa}
 …
 \end{cfa}
 Since the custom type is simple to write in \CFA and solves several issues, added support for routine/lambda-based coroutines adds very little.
+Note, the type @coroutine_t@ must be an abstract handle to the coroutine, because the coroutine descriptor and its stack are non-copyable.
+Copying the coroutine descriptor results in copies being out of date with the current state of the stack.
+Correspondingly, copying the stack results is copies being out of date with the coroutine descriptor, and pointers in the stack being out of date to data on the stack.
+(There is no mechanism in C to find all stack-specific pointers and update them as part of a copy.)
 The selected approach is to use language support by introducing a new kind of aggregate (structure):
 …
 Furthermore, implementing coroutines without language supports also displays the power of a programming language.
 While this is ultimately the option used for idiomatic \CFA code, coroutines and threads can still be constructed without using the language support.
 The reserved keyword eases use for the common cases.
 Part of the mechanism to generalize coroutines is using a \CFA trait, which defines a coroutine as anything satisfying the trait @is_coroutine@, and this trait is used to restrict coroutine-manipulation functions:
 \begin{cfa}
 trait is_coroutine( dtype T ) {
       void main( T & this );
       coroutine_desc * get_coroutine( T & this );
+The reserved keyword simply eases use for the common cases.
+Part of the mechanism to generalize coroutines is using a \CFA trait, which defines a coroutine as anything satisfying the trait @is_coroutine@, and this trait is used to restrict coroutine-manipulation routines:
+\begin{cfa}
+trait is_coroutine( `dtype` T ) {
+        void main( T & );
+        coroutine_desc * get_coroutine( T & );
 };
 forall( dtype T | is_coroutine(T) ) void get_coroutine( T & );
 forall( dtype T | is_coroutine(T) ) void suspend( T & );
+forall( dtype T | is_coroutine(T) ) void resume( T & );
+\end{cfa}
 This definition ensures there is a statically-typed @main@ function that is the starting point (first stack frame) of a coroutine.
 No return value or additional parameters are necessary for this function, because the coroutine type allows an arbitrary number of interface functions with corresponding arbitrary typed input/output values.
 As well, any object passed to @suspend@ and @resume@ is a coroutine since it must satisfy the @is_coroutine@ trait to compile.
 The advantage of this approach is that users can easily create different types of coroutines, for example, changing the memory layout of a coroutine is trivial when implementing the @get_coroutine@ routine.
+forall( `dtype` T | is_coroutine(T) ) void suspend( T & );
+forall( `dtype` T | is_coroutine(T) ) void resume( T & );
+\end{cfa}
+The @dtype@ property of the trait ensures the coroutine descriptor is non-copyable, so all coroutines must be passed by reference (pointer).
+The routine definitions ensures there is a statically-typed @main@ routine that is the starting point (first stack frame) of a coroutine, and a mechanism to get (read) the currently executing coroutine handle.
+The @main@ routine has no return value or additional parameters because the coroutine type allows an arbitrary number of interface routines with corresponding arbitrary typed input/output values versus fixed ones.
+The generic routines @suspend@ and @resume@ can be redefined, but any object passed to them is a coroutine since it must satisfy the @is_coroutine@ trait to compile.
+The advantage of this approach is that users can easily create different types of coroutines, \eg changing the memory layout of a coroutine is trivial when implementing the @get_coroutine@ routine, and possibly redefining @suspend@ and @resume@.
 The \CFA keyword @coroutine@ implicitly implements the getter and forward declarations required for implementing the coroutine main:
 \begin{cquote}
 …
 };
 \end{cfa}
+& {\Large $\Rightarrow$} &
+&
+{\Large $\Rightarrow$}
+&
 \begin{tabular}{@{}ccc@{}}
 \begin{cfa}
 …
 Like coroutines and for the same design reasons, the selected approach for user threads is to use language support by introducing a new kind of aggregate (structure) and a \CFA trait:
 \begin{cquote}
 \begin{tabular}{@{}c@{\hspace{2\parindentlnth}}c@{}}
+\begin{tabular}{@{}c@{\hspace{3\parindentlnth}}c@{}}
 \begin{cfa}
 thread myThread {
 …
+&
 \begin{cfa}
 trait is_thread( dtype T ) {
       void main( T & this );
       thread_desc * get_thread( T & this );
       void ^?{}( T & `mutex` this );
+trait is_thread( `dtype` T ) {
+      void main( T & );
+      thread_desc * get_thread( T & );
+      void ^?{}( T & `mutex` );
 };
 \end{cfa}
 …
 \end{cquote}
 (The qualifier @mutex@ for the destructor parameter is discussed in Section~\ref{s:Monitors}.)
 Like a coroutine, the statically-typed @main@ function is the starting point (first stack frame) of a user thread.
+Like a coroutine, the statically-typed @main@ routine is the starting point (first stack frame) of a user thread.
 The difference is that a coroutine borrows a thread from its caller, so the first thread resuming a coroutine creates an instance of @main@;
 whereas, a user thread receives its own thread from the runtime system, which starts in @main@ as some point after the thread constructor is run.\footnote{
 The \lstinline@main@ function is already a special routine in C (where the program begins), so it is a natural extension of the semantics to use overloading to declare mains for different coroutines/threads (the normal main being the main of the initial thread).}
 No return value or additional parameters are necessary for this function, because the task type allows an arbitrary number of interface functions with corresponding arbitrary typed input/output values.
+The \lstinline@main@ routine is already a special routine in C, \ie where the program's initial thread begins, so it is a natural extension of this semantics to use overloading to declare \lstinline@main@s for user coroutines and threads.}
+No return value or additional parameters are necessary for this routine because the task type allows an arbitrary number of interface routines with corresponding arbitrary typed input/output values.
 \begin{comment} % put in appendix with coroutine version ???
 …
 In this example, threads of type @foo@ start execution in the @void main(foo &)@ routine, which prints @"Hello World!".@ While this paper encourages this approach to enforce strongly typed programming, users may prefer to use the routine-based thread semantics for the sake of simplicity.
 With the static semantics it is trivial to write a thread type that takes a function pointer as a parameter and executes it on its stack asynchronously.
 \begin{cfa}
 typedef void (*voidFunc)(int);
 thread FuncRunner {
         voidFunc func;
+With the static semantics it is trivial to write a thread type that takes a routine pointer as a parameter and executes it on its stack asynchronously.
+\begin{cfa}
+typedef void (*voidRtn)(int);
+thread RtnRunner {
+        voidRtn func;
         int arg;
 };
 void ?{}(FuncRunner & this, voidFunc inFunc, int arg) {
         this.func = inFunc;
+void ?{}(RtnRunner & this, voidRtn inRtn, int arg) {
+        this.func = inRtn;
         this.arg  = arg;
+}
 void main(FuncRunner & this) {
         // thread starts here and runs the function
+void main(RtnRunner & this) {
+        // thread starts here and runs the routine
         this.func( this.arg );
+}
 …
 int main() {
         FuncRunner f = {hello, 42};
+        RtnRunner f = {hello, 42};
         return 0?
+}
 \end{cfa}
 A consequence of the strongly typed approach to main is that memory layout of parameters and return values to/from a thread are now explicitly specified in the \textbf{api}.
+A consequence of the strongly typed approach to main is that memory layout of parameters and return values to/from a thread are now explicitly specified in the \textbf{API}.
 \end{comment}
 …
 void main( Adder & adder ) with( adder ) {
     subtotal = 0;
+    for ( int c = 0; c < cols; c += 1 ) {
+                subtotal += row[c];
+    }
+    for ( int c = 0; c < cols; c += 1 ) { subtotal += row[c]; }
+}
 int main() {
 …
 \section{Synchronization / Mutual Exclusion}
+\section{Mutual Exclusion / Synchronization}
 Uncontrolled non-deterministic execution is meaningless.
 To reestablish meaningful execution requires mechanisms to reintroduce determinism (control non-determinism), called synchronization and mutual exclusion, where synchronization is a timing relationship among threads and mutual exclusion is an access-control mechanism on data shared by threads.
 Since many deterministic challenges appear with the use of mutable shared state, some languages/libraries disallow it (Erlang~\cite{Erlang}, Haskell~\cite{Haskell}, Akka~\cite{Akka} (Scala)).
 In these paradigms, interaction among concurrent objects is performed by stateless message-passing~\cite{Thoth,Harmony,V-Kernel} or other paradigms closely relate to networking concepts (\eg channels~\cite{CSP,Go}).
 However, in call/return-based languages, these approaches force a clear distinction (\ie introduce a new programming paradigm) between non-concurrent and concurrent computation (\ie function call versus message passing).
 This distinction means a programmers needs to learn two sets of design patterns.
+To reestablish meaningful execution requires mechanisms to reintroduce determinism, \ie restrict non-determinism, called mutual exclusion and synchronization, where mutual exclusion is an access-control mechanism on data shared by threads, and synchronization is a timing relationship among threads~\cite[\S~4]{Buhr05a}.
+Since many deterministic challenges appear with the use of mutable shared state, some languages/libraries disallow it, \eg Erlang~\cite{Erlang}, Haskell~\cite{Haskell}, Akka~\cite{Akka} (Scala).
+In these paradigms, interaction among concurrent objects is performed by stateless message-passing~\cite{Thoth,Harmony,V-Kernel} or other paradigms closely relate to networking concepts, \eg channels~\cite{CSP,Go}.
+However, in call/return-based languages, these approaches force a clear distinction, \ie introduce a new programming paradigm, between regular and concurrent computation, \eg routine call versus message passing.
+Hence, a programmer must learn and manipulate two sets of design patterns.
 While this distinction can be hidden away in library code, effective use of the library still has to take both paradigms into account.
 In contrast, approaches based on statefull models more closely resemble the standard call/return programming-model, resulting in a single programming paradigm.
 At the lowest level, concurrent control is implemented as atomic operations, upon which different kinds of locks mechanism are constructed, \eg semaphores~\cite{Dijkstra68b} and path expressions~\cite{Campbell74}.
+At the lowest level, concurrent control is implemented by atomic operations, upon which different kinds of locks mechanism are constructed, \eg semaphores~\cite{Dijkstra68b}, barriers, and path expressions~\cite{Campbell74}.
 However, for productivity it is always desirable to use the highest-level construct that provides the necessary efficiency~\cite{Hochstein05}.
 A newer approach is transactional memory~\cite{Herlihy93}.
+A newer approach for restricting non-determinism is transactional memory~\cite{Herlihy93}.
 While this approach is pursued in hardware~\cite{Nakaike15} and system languages, like \CC~\cite{Cpp-Transactions}, the performance and feature set is still too restrictive to be the main concurrency paradigm for system languages, which is why it was rejected as the core paradigm for concurrency in \CFA.
+One of the most natural, elegant, and efficient mechanisms for synchronization and mutual exclusion for shared-memory systems is the \emph{monitor}.
+Monitors were first proposed by Brinch Hansen~\cite{Hansen73} and later described and extended by C.A.R.~Hoare~\cite{Hoare74}.
+Many programming languages -- \eg Concurrent Pascal~\cite{ConcurrentPascal}, Mesa~\cite{Mesa}, Modula~\cite{Modula-2}, Turing~\cite{Turing:old}, Modula-3~\cite{Modula-3}, NeWS~\cite{NeWS}, Emerald~\cite{Emerald}, \uC~\cite{Buhr92a} and Java~\cite{Java} -- provide monitors as explicit language constructs.
+In addition, operating-system kernels and device drivers have a monitor-like structure, although they often use lower-level primitives such as semaphores or locks to simulate monitors.
+For these reasons, this project proposes monitors as the core concurrency construct, upon which even higher-level approaches can be easily constructed..
+One of the most natural, elegant, and efficient mechanisms for mutual exclusion and synchronization for shared-memory systems is the \emph{monitor}.
+First proposed by Brinch Hansen~\cite{Hansen73} and later described and extended by C.A.R.~Hoare~\cite{Hoare74}, many concurrent programming-languages provide monitors as an explicit language construct: \eg Concurrent Pascal~\cite{ConcurrentPascal}, Mesa~\cite{Mesa}, Modula~\cite{Modula-2}, Turing~\cite{Turing:old}, Modula-3~\cite{Modula-3}, NeWS~\cite{NeWS}, Emerald~\cite{Emerald}, \uC~\cite{Buhr92a} and Java~\cite{Java}.
+In addition, operating-system kernels and device drivers have a monitor-like structure, although they often use lower-level primitives such as mutex locks or semaphores to simulate monitors.
+For these reasons, \CFA selected monitors as the core high-level concurrency-construct, upon which higher-level approaches can be easily constructed.
 …
 A group of instructions manipulating a specific instance of shared data that must be performed atomically is called an (individual) \newterm{critical-section}~\cite{Dijkstra65}.
 A generalization is a \newterm{group critical-section}~\cite{Joung00}, where multiple tasks with the same session may use the resource simultaneously, but different sessions may not use the resource simultaneously.
+The generalization is called a \newterm{group critical-section}~\cite{Joung00}, where multiple tasks with the same session may use the resource simultaneously, but different sessions may not use the resource simultaneously.
 The readers/writer problem~\cite{Courtois71} is an instance of a group critical-section, where readers have the same session and all writers have a unique session.
 \newterm{Mutual exclusion} enforces the correction number of threads are using a critical section at the same time.
+\newterm{Mutual exclusion} enforces that the correct kind and number of threads are using a critical section.
 However, many solutions exist for mutual exclusion, which vary in terms of performance, flexibility and ease of use.
 Methods range from low-level locks, which are fast and flexible but require significant attention for correctness, to higher-level concurrency techniques, which sacrifice some performance to improve ease of use.
 Ease of use comes by either guaranteeing some problems cannot occur (\eg deadlock free), or by offering a more explicit coupling between shared data and critical section.
 For example, the \CC @std::atomic<T>@ offers an easy way to express mutual-exclusion on a restricted set of operations (\eg reading/writing large types atomically).
 However, a significant challenge with (low-level) locks is composability because it takes careful organization for multiple locks to be used while preventing deadlock.
 Easing composability is another feature higher-level mutual-exclusion mechanisms offer.
+Ease of use comes by either guaranteeing some problems cannot occur, \eg deadlock free, or by offering a more explicit coupling between shared data and critical section.
+For example, the \CC @std::atomic<T>@ offers an easy way to express mutual-exclusion on a restricted set of operations, \eg reading/writing, for numerical types.
+However, a significant challenge with locks is composability because it takes careful organization for multiple locks to be used while preventing deadlock.
+Easing composability is another feature higher-level mutual-exclusion mechanisms can offer.
 …
 Synchronization enforces relative ordering of execution, and synchronization tools provide numerous mechanisms to establish these timing relationships.
+Low-level synchronization primitives offer good performance and flexibility at the cost of ease of use.
+Higher-level mechanisms often simplify usage by adding better coupling between synchronization and data (\eg message passing), or offering a simpler solution to otherwise involved challenges, \eg barrier lock.
+As mentioned above, synchronization can be expressed as guaranteeing that event \textit{X} always happens before \textit{Y}.
+Often synchronization is used to order access to a critical section, \eg ensuring the next kind of thread to enter a critical section is a reader thread
+If a writer thread is scheduled for next access, but another reader thread acquires the critical section first, the reader has \newterm{barged}.
+Barging can result in staleness/freshness problems, where a reader barges ahead of a write and reads temporally stale data, or a writer barges ahead of another writer overwriting data with a fresh value preventing the previous value from having an opportunity to be read.
+Low-level synchronization primitives offer good performance and flexibility at the cost of ease of use;
+higher-level mechanisms often simplify usage by adding better coupling between synchronization and data, \eg message passing, or offering a simpler solution to otherwise involved challenges, \eg barrier lock.
+Often synchronization is used to order access to a critical section, \eg ensuring a reader thread is the next kind of thread to enter a critical section.
+If a writer thread is scheduled for next access, but another reader thread acquires the critical section first, that reader has \newterm{barged}.
+Barging can result in staleness/freshness problems, where a reader barges ahead of a writer and reads temporally stale data, or a writer barges ahead of another writer overwriting data with a fresh value preventing the previous value from ever being read (lost computation).
 Preventing or detecting barging is an involved challenge with low-level locks, which can be made much easier by higher-level constructs.
+This challenge is often split into two different approaches, barging avoidance and barging prevention.
+Algorithms that allow a barger but divert it until later are avoiding the barger, while algorithms that preclude a barger from entering during synchronization in the critical section prevent the barger completely.
+baton-pass locks~\cite{Andrews89} between threads instead of releasing the locks are said to be using barging prevention.
+This challenge is often split into two different approaches: barging avoidance and barging prevention.
+Algorithms that allow a barger, but divert it until later using current synchronization state (flags), are avoiding the barger;
+algorithms that preclude a barger from entering during synchronization in the critical section prevent barging completely.
+Techniques like baton-pass locks~\cite{Andrews89} between threads instead of unconditionally releasing locks is an example of barging prevention.
 …
 \label{s:Monitors}
+A \textbf{monitor} is a set of routines that ensure mutual-exclusion when accessing shared state.
+More precisely, a monitor is a programming technique that associates mutual-exclusion to routine scopes, as opposed to mutex locks, where mutual-exclusion is defined by lock/release calls independently of any scoping of the calling routine.
+This strong association eases readability and maintainability, at the cost of flexibility.
+Note that both monitors and mutex locks, require an abstract handle to identify them.
+This concept is generally associated with object-oriented languages like Java~\cite{Java} or \uC~\cite{uC++book} but does not strictly require OO semantics.
+The only requirement is the ability to declare a handle to a shared object and a set of routines that act on it:
+\begin{cfa}
+typedef /*some monitor type*/ monitor;
+int f(monitor & m);
+int main() {
+        monitor m;  // Handle m
+        f(m);       // Routine using handle
+}
+\end{cfa}
+% ======================================================================
+% ======================================================================
+\subsection{Call Semantics} \label{call}
+% ======================================================================
+% ======================================================================
+The above monitor example displays some of the intrinsic characteristics.
+First, it is necessary to use pass-by-reference over pass-by-value for monitor routines.
+This semantics is important, because at their core, monitors are implicit mutual-exclusion objects (locks), and these objects cannot be copied.
+Therefore, monitors are non-copy-able objects (@dtype@).
+Another aspect to consider is when a monitor acquires its mutual exclusion.
+For example, a monitor may need to be passed through multiple helper routines that do not acquire the monitor mutual-exclusion on entry.
+Passthrough can occur for generic helper routines (@swap@, @sort@, \etc) or specific helper routines like the following to implement an atomic counter:
+\begin{cfa}
+monitor counter_t { /*...see section $\ref{data}$...*/ };
+void ?{}(counter_t & nomutex this); // constructor
+size_t ++?(counter_t & mutex this); // increment
+// need for mutex is platform dependent
+void ?{}(size_t * this, counter_t & mutex cnt); // conversion
+\end{cfa}
+This counter is used as follows:
+\begin{center}
+\begin{tabular}{c @{\hskip 0.35in} c @{\hskip 0.35in} c}
+\begin{cfa}
+// shared counter
+counter_t cnt1, cnt2;
+// multiple threads access counter
+thread 1 : cnt1++; cnt2++;
+thread 2 : cnt1++; cnt2++;
+thread 3 : cnt1++; cnt2++;
+        ...
+thread N : cnt1++; cnt2++;
+\end{cfa}
+\end{tabular}
+\end{center}
+Notice how the counter is used without any explicit synchronization and yet supports thread-safe semantics for both reading and writing, which is similar in usage to the \CC template @std::atomic@.
+Here, the constructor (@?{}@) uses the @nomutex@ keyword to signify that it does not acquire the monitor mutual-exclusion when constructing.
+This semantics is because an object not yet constructed should never be shared and therefore does not require mutual exclusion.
+Furthermore, it allows the implementation greater freedom when it initializes the monitor locking.
+The prefix increment operator uses @mutex@ to protect the incrementing process from race conditions.
+Finally, there is a conversion operator from @counter_t@ to @size_t@.
+This conversion may or may not require the @mutex@ keyword depending on whether or not reading a @size_t@ is an atomic operation.
+For maximum usability, monitors use \textbf{multi-acq} semantics, which means a single thread can acquire the same monitor multiple times without deadlock.
+For example, listing \ref{fig:search} uses recursion and \textbf{multi-acq} to print values inside a binary tree.
+\begin{figure}
+\begin{cfa}[caption={Recursive printing algorithm using \textbf{multi-acq}.},label={fig:search}]
+monitor printer { ... };
+struct tree {
+        tree * left, right;
+        char * value;
+A \textbf{monitor} is a set of routines that ensure mutual exclusion when accessing shared state.
+More precisely, a monitor is a programming technique that binds mutual exclusion to routine scope, as opposed to locks, where mutual-exclusion is defined by acquire/release calls, independent of lexical context (analogous to block and heap storage allocation).
+The strong association with the call/return paradigm eases programmability, readability and maintainability, at a slight cost in flexibility and efficiency.
+Note, like coroutines/threads, both locks and monitors require an abstract handle to reference them, because at their core, both mechanisms are manipulating non-copyable shared-state.
+Copying a lock is insecure because it is possible to copy an open lock and then use the open copy when the original lock is closed to simultaneously access the shared data.
+Copying a monitor is secure because both the lock and shared data are copies, but copying the shared data is meaningless because it no longer represents a unique entity.
+As for coroutines/tasks, a non-copyable (@dtype@) trait is used to capture this requirement, so all locks/monitors must be passed by reference (pointer).
+\begin{cfa}
+trait is_monitor( `dtype` T ) {
+        monitor_desc * get_monitor( T & );
+        void ^?{}( T & mutex );
 };
+void print(printer & mutex p, char * v);
+void print(printer & mutex p, tree * t) {
+        print(p, t->value);
+        print(p, t->left );
+        print(p, t->right);
+}
+\end{cfa}
+\end{figure}
+Having both @mutex@ and @nomutex@ keywords can be redundant, depending on the meaning of a routine having neither of these keywords.
+For example, it is reasonable that it should default to the safest option (@mutex@) when given a routine without qualifiers @void foo(counter_t & this)@, whereas assuming @nomutex@ is unsafe and may cause subtle errors.
+On the other hand, @nomutex@ is the ``normal'' parameter behaviour, it effectively states explicitly that ``this routine is not special''.
+Another alternative is making exactly one of these keywords mandatory, which provides the same semantics but without the ambiguity of supporting routines with neither keyword.
+Mandatory keywords would also have the added benefit of being self-documented but at the cost of extra typing.
+While there are several benefits to mandatory keywords, they do bring a few challenges.
+Mandatory keywords in \CFA would imply that the compiler must know without doubt whether or not a parameter is a monitor or not.
+\end{cfa}
+\subsection{Mutex Acquisition}
+\label{s:MutexAcquisition}
+While correctness implicitly implies a monitor's mutual exclusion is acquired and released, there are implementation options about when and where the locking/unlocking occurs.
+(Much of this discussion also applies to basic locks.)
+For example, a monitor may need to be passed through multiple helper routines before it becomes necessary to acquire the monitor mutual-exclusion.
+\begin{cfa}[morekeywords=nomutex]
+monitor Aint { int cnt; };                                      $\C{// atomic integer counter}$
+void ?{}( Aint & `nomutex` this ) with( this ) { cnt = 0; } $\C{// constructor}$
+int ?=?( Aint & `mutex`$\(_{opt}\)$ lhs, int rhs ) with( lhs ) { cnt = rhs; } $\C{// conversions}$
+void ?{}( int & this, Aint & `mutex`$\(_{opt}\)$ v ) { this = v.cnt; }
+int ?=?( int & lhs, Aint & `mutex`$\(_{opt}\)$ rhs ) with( rhs ) { lhs = cnt; }
+int ++?( Aint & `mutex`$\(_{opt}\)$ this ) with( this ) { return ++cnt; } $\C{// increment}$
+\end{cfa}
+The @Aint@ constructor, @?{}@, uses the \lstinline[morekeywords=nomutex]@nomutex@ qualifier indicating mutual exclusion is unnecessary during construction because an object is inaccessible (private) until after it is initialized.
+(While a constructor may publish its address into a global variable, doing so generates a race-condition.)
+The conversion operators for initializing and assigning with a normal integer only need @mutex@, if reading/writing the implementation type is not atomic.
+Finally, the prefix increment operato, @++?@, is normally @mutex@ to protect the incrementing from race conditions, unless there is an atomic increment instruction for the implementation type.
+The atomic counter is used without any explicit mutual-exclusion and provides thread-safe semantics, which is similar to the \CC template @std::atomic@.
+\begin{cfa}
+Aint x, y, z;
+++x; ++y; ++z;                                                          $\C{// safe increment by multiple threads}$
+x = 2; y = 2; z = 2;                                            $\C{// conversions}$
+int i = x, j = y, k = z;
+i = x; j = y; k = z;
+\end{cfa}
+For maximum usability, monitors have \newterm{multi-acquire} semantics allowing a thread to acquire it multiple times without deadlock.
+For example, atomically printing the contents of a binary tree:
+\begin{cfa}
+monitor Tree {
+        Tree * left, right;
+        // value
+};
+void print( Tree & mutex tree ) {                       $\C{// prefix traversal}$
+        // write value
+        print( tree->left );                                    $\C{// multiply acquire monitor lock on each recursion}$
+        print( tree->right );
+}
+\end{cfa}
+Mandatory monitor qualifiers have the benefit of being self-documented, but requiring both @mutex@ and \lstinline[morekeywords=nomutex]@nomutex@ for all monitor parameter is redundant.
+Instead, one of qualifier semantics can be the default, and the other required.
+For example, assume the safe @mutex@ option for a monitor parameter because assuming \lstinline[morekeywords=nomutex]@nomutex@ may cause subtle errors.
+On the other hand, assuming \lstinline[morekeywords=nomutex]@nomutex@ is the \emph{normal} parameter behaviour, stating explicitly ``this parameter is not special''.
+Providing a default qualifier implies knowing whether a parameter is a monitor.
 Since \CFA relies heavily on traits as an abstraction mechanism, the distinction between a type that is a monitor and a type that looks like a monitor can become blurred.
 For this reason, \CFA only has the @mutex@ keyword and uses no keyword to mean @nomutex@.
 The next semantic decision is to establish when @mutex@ may be used as a type qualifier.
 Consider the following declarations:
 \begin{cfa}
+int f1(monitor & mutex m);
 int f2(const monitor & mutex m);
 int f3(monitor ** mutex m);
 int f4(monitor * mutex m []);
 int f5(graph(monitor *) & mutex m);
 \end{cfa}
 The problem is to identify which object(s) should be acquired.
 Furthermore, each object needs to be acquired only once.
 In the case of simple routines like @f1@ and @f2@ it is easy to identify an exhaustive list of objects to acquire on entry.
 Adding indirections (@f3@) still allows the compiler and programmer to identify which object is acquired.
+However, adding in arrays (@f4@) makes it much harder.
 Array lengths are not necessarily known in C, and even then, making sure objects are only acquired once becomes none-trivial.
 This problem can be extended to absurd limits like @f5@, which uses a graph of monitors.
+To make the issue tractable, this project imposes the requirement that a routine may only acquire one monitor per parameter and it must be the type of the parameter with at most one level of indirection (ignoring potential qualifiers).
 Also note that while routine @f3@ can be supported, meaning that monitor @**m@ is acquired, passing an array to this routine would be type-safe and yet result in undefined behaviour because only the first element of the array is acquired.
 However, this ambiguity is part of the C type-system with respects to arrays.
+For this reason, @mutex@ is disallowed in the context where arrays may be passed:
+\begin{cfa}
+int f1(monitor & mutex m);    // Okay : recommended case
+int f2(monitor * mutex m);    // Not Okay : Could be an array
 int f3(monitor mutex m []);  // Not Okay : Array of unknown length
 int f4(monitor ** mutex m);   // Not Okay : Could be an array
 int f5(monitor * mutex m []); // Not Okay : Array of unknown length
+\end{cfa}
+Note that not all array functions are actually distinct in the type system.
+However, even if the code generation could tell the difference, the extra information is still not sufficient to extend meaningfully the monitor call semantic.
 Unlike object-oriented monitors, where calling a mutex member \emph{implicitly} acquires mutual-exclusion of the receiver object, \CFA uses an explicit mechanism to specify the object that acquires mutual-exclusion.
+A consequence of this approach is that it extends naturally to multi-monitor calls.
+\begin{cfa}
+int f(MonitorA & mutex a, MonitorB & mutex b);
+MonitorA a;
+MonitorB b;
 f(a,b);
+\end{cfa}
+While OO monitors could be extended with a mutex qualifier for multiple-monitor calls, no example of this feature could be found.
+The capability to acquire multiple locks before entering a critical section is called \emph{\textbf{bulk-acq}}.
 In practice, writing multi-locking routines that do not lead to deadlocks is tricky.
+For this reason, \CFA requires programmers to identify the kind of parameter with the @mutex@ keyword and uses no keyword to mean \lstinline[morekeywords=nomutex]@nomutex@.
+The next semantic decision is establishing which parameter \emph{types} may be qualified with @mutex@.
+Given:
+\begin{cfa}
+monitor M { ... }
+int f1( M & mutex m );
+int f2( M * mutex m );
+int f3( M * mutex m[] );
+int f4( stack( M * ) & mutex m );
+\end{cfa}
+the issue is that some of these parameter types are composed of multiple objects.
+For @f1@, there is only a single parameter object.
+Adding indirection in @f2@ still identifies a single object.
+However, the matrix in @f3@ introduces multiple objects.
+While shown shortly, multiple acquisition is possible;
+however array lengths are often unknown in C.
+This issue is exacerbated in @f4@, where the data structure must be safely traversed to acquire all of its elements.
+To make the issue tractable, \CFA only acquires one monitor per parameter with at most one level of indirection.
+However, the C type-system has an ambiguity with respects to arrays.
+Is the argument for @f2@ a single object or an array of objects?
+If it is an array, only the first element of the array is acquired, which seems unsafe;
+hence, @mutex@ is disallowed for array parameters.
+\begin{cfa}
+int f1( M & mutex m );                                          $\C{// allowed: recommended case}$
+int f2( M * mutex m );                                          $\C{// disallowed: could be an array}$
+int f3( M mutex m[$\,$] );                                      $\C{// disallowed: array length unknown}$
+int f4( M ** mutex m );                                         $\C{// disallowed: could be an array}$
+int f5( M * mutex m[$\,$] );                            $\C{// disallowed: array length unknown}$
+\end{cfa}
+% Note, not all array routines have distinct types: @f2@ and @f3@ have the same type, as do @f4@ and @f5@.
+% However, even if the code generation could tell the difference, the extra information is still not sufficient to extend meaningfully the monitor call semantic.
+For object-oriented monitors, calling a mutex member \emph{implicitly} acquires mutual exclusion of the receiver object, @`rec`.foo(...)@.
+\CFA has no receiver, and hence, must use an explicit mechanism to specify which object has mutual exclusion acquired.
+A positive consequence of this design decision is the ability to support multi-monitor routines.
+\begin{cfa}
+int f( M & mutex x, M & mutex y );              $\C{// multiple monitor parameter of any type}$
+M m1, m2;
+f( m1, m2 );
+\end{cfa}
+(While object-oriented monitors can be extended with a mutex qualifier for multiple-monitor members, no prior example of this feature could be found.)
+In practice, writing multi-locking routines that do not deadlock is tricky.
 Having language support for such a feature is therefore a significant asset for \CFA.
+In the case presented above, \CFA guarantees that the order of acquisition is consistent across calls to different routines using the same monitors as arguments.
+This consistent ordering means acquiring multiple monitors is safe from deadlock when using \textbf{bulk-acq}.
+However, users can still force the acquiring order.
+For example, notice which routines use @mutex@/@nomutex@ and how this affects acquiring order:
+\begin{cfa}
+void foo(A& mutex a, B& mutex b) { // acquire a & b
+        ...
+}
+void bar(A& mutex a, B& /*nomutex*/ b) { // acquire a
+        ... foo(a, b); ... // acquire b
+}
+void baz(A& /*nomutex*/ a, B& mutex b) { // acquire b
+        ... foo(a, b); ... // acquire a
+}
+\end{cfa}
+The \textbf{multi-acq} monitor lock allows a monitor lock to be acquired by both @bar@ or @baz@ and acquired again in @foo@.
+In the calls to @bar@ and @baz@ the monitors are acquired in opposite order.
+However, such use leads to lock acquiring order problems.
+In the example above, the user uses implicit ordering in the case of function @foo@ but explicit ordering in the case of @bar@ and @baz@.
+This subtle difference means that calling these routines concurrently may lead to deadlock and is therefore undefined behaviour.
+As shown~\cite{Lister77}, solving this problem requires:
+\begin{enumerate}
+        \item Dynamically tracking the monitor-call order.
+        \item Implement rollback semantics.
+\end{enumerate}
+While the first requirement is already a significant constraint on the system, implementing a general rollback semantics in a C-like language is still prohibitively complex~\cite{Dice10}.
+In \CFA, users simply need to be careful when acquiring multiple monitors at the same time or only use \textbf{bulk-acq} of all the monitors.
+While \CFA provides only a partial solution, most systems provide no solution and the \CFA partial solution handles many useful cases.
+For example, \textbf{multi-acq} and \textbf{bulk-acq} can be used together in interesting ways:
+\begin{cfa}
+monitor bank { ... };
+void deposit( bank & mutex b, int deposit );
+void transfer( bank & mutex mybank, bank & mutex yourbank, int me2you) {
+        deposit( mybank, -me2you );
+        deposit( yourbank, me2you );
+The capability to acquire multiple locks before entering a critical section is called \newterm{bulk acquire}.
+In the previous example, \CFA guarantees the order of acquisition is consistent across calls to different routines using the same monitors as arguments.
+This consistent ordering means acquiring multiple monitors is safe from deadlock.
+However, users can force the acquiring order.
+For example, notice the use of @mutex@/\lstinline[morekeywords=nomutex]@nomutex@ and how this affects the acquiring order:
+\begin{cfa}
+void foo( M & mutex m1, M & mutex m2 );         $\C{// acquire m1 and m2}$
+void bar( M & mutex m1, M & /* nomutex */ m2 ) { $\C{// acquire m1}$
+        ... foo( m1, m2 ); ...                                  $\C{// acquire m2}$
+}
+void baz( M & /* nomutex */ m1, M & mutex m2 ) { $\C{// acquire m2}$
+        ... foo( m1, m2 ); ...                                  $\C{// acquire m1}$
+}
+\end{cfa}
+The multi-acquire semantics allows @bar@ or @baz@ to acquire a monitor lock and reacquire it in @foo@.
+In the calls to @bar@ and @baz@, the monitors are acquired in opposite order.
+However, such use leads to lock acquiring order problems resulting in deadlock~\cite{Lister77}, where detecting it requires dynamically tracking of monitor calls, and dealing with it requires rollback semantics~\cite{Dice10}.
+In \CFA, safety is guaranteed by using bulk acquire of all monitors to shared objects, whereas other monitor systems provide no aid.
+While \CFA provides only a partial solution, the \CFA partial solution handles many useful cases.
+\begin{cfa}
+monitor Bank { ... };
+void deposit( Bank & `mutex` b, int deposit );
+void transfer( Bank & `mutex` mybank, Bank & `mutex` yourbank, int me2you) {
+        deposit( mybank, `-`me2you );                   $\C{// debit}$
+        deposit( yourbank, me2you );                    $\C{// credit}$
+}
 \end{cfa}
 This example shows a trivial solution to the bank-account transfer problem~\cite{BankTransfer}.
 Without \textbf{multi-acq} and \textbf{bulk-acq}, the solution to this problem is much more involved and requires careful engineering.
+Without multi- and bulk acquire, the solution to this problem requires careful engineering.
 \subsection{\protect\lstinline|mutex| statement} \label{mutex-stmt}
+The call semantics discussed above have one software engineering issue: only a routine can acquire the mutual-exclusion of a set of monitor. \CFA offers the @mutex@ statement to work around the need for unnecessary names, avoiding a major software engineering problem~\cite{2FTwoHardThings}.
+Table \ref{f:mutex-stmt} shows an example of the @mutex@ statement, which introduces a new scope in which the mutual-exclusion of a set of monitor is acquired.
+Beyond naming, the @mutex@ statement has no semantic difference from a routine call with @mutex@ parameters.
+\begin{table}
+\begin{center}
+\begin{tabular}{|c|c|}
+function call & @mutex@ statement \\
+\hline
+\begin{cfa}[tabsize=3]
+The monitor call-semantics associate all locking semantics to routines.
+Like Java, \CFA offers an alternative @mutex@ statement to reduce refactoring and naming.
+\begin{cquote}
+\begin{tabular}{@{}c|@{\hspace{\parindentlnth}}c@{}}
+routine call & @mutex@ statement \\
+\begin{cfa}
 monitor M {};
 void foo( M & mutex m1, M & mutex m2 ) {
         // critical section
+}
 void bar( M & m1, M & m2 ) {
         foo( m1, m2 );
+}
+\end{cfa}&\begin{cfa}[tabsize=3]
+monitor M {};
+\end{cfa}
+&
+\begin{cfa}
 void bar( M & m1, M & m2 ) {
         mutex(m1, m2) {
+        mutex( m1, m2 ) {       // remove refactoring and naming
                 // critical section
+        }
+}
 \end{cfa}
 \end{tabular}
+\end{center}
+\caption{Regular call semantics vs. \protect\lstinline|mutex| statement}
+\label{f:mutex-stmt}
+\end{table}
+% ======================================================================
+% ======================================================================
+\subsection{Data semantics} \label{data}
+% ======================================================================
+% ======================================================================
+Once the call semantics are established, the next step is to establish data semantics.
+Indeed, until now a monitor is used simply as a generic handle but in most cases monitors contain shared data.
+This data should be intrinsic to the monitor declaration to prevent any accidental use of data without its appropriate protection.
+For example, here is a complete version of the counter shown in section \ref{call}:
+\begin{cfa}
+monitor counter_t {
+        int value;
+\end{cquote}
+\section{Scheduling}
+\label{s:Scheduling}
+While monitor mutual-exclusion provides safe access to shared data, the monitor data may indicate that a thread accessing it cannot proceed.
+For example, Figure~\ref{f:GenericBoundedBuffer} shows a bounded buffer that may be full/empty so produce/consumer threads must block.
+Leaving the monitor and trying again (busy waiting) is impractical for high-level programming.
+Monitors eliminate busy waiting by providing internal synchronization to schedule threads needing access to the shared data, where the synchronization is blocking (threads are parked) versus spinning.
+Synchronization is generally achieved with internal~\cite{Hoare74} or external~\cite[\S~2.9.2]{uC++} scheduling, where \newterm{scheduling} defines which thread acquires the critical section next.
+\newterm{Internal scheduling} is characterized by each thread entering the monitor and making an individual decision about proceeding or blocking, while \newterm{external scheduling} is characterized by an entering thread making a decision about proceeding for itself and on behalf of other threads attempting entry.
+Figure~\ref{f:BBInt} shows a \CFA bounded-buffer with internal scheduling, where producers/consumers enter the monitor, see the buffer is full/empty, and block on an appropriate condition lock, @full@/@empty@.
+The @wait@ routine atomically blocks the calling thread and implicitly releases the monitor lock(s) for all monitors in the routine's parameter list.
+The appropriate condition lock is signalled to unblock an opposite kind of thread after an element is inserted/removed from the buffer.
+Signalling is unconditional, because signalling an empty condition lock does nothing.
+Signalling semantics cannot have the signaller and signalled thread in the monitor simultaneously, which means:
+\begin{enumerate}
+\item
+The signalling thread returns immediately, and the signalled thread continues.
+\item
+The signalling thread continues and the signalled thread is marked for urgent unblocking at the next scheduling point (exit/wait).
+\item
+The signalling thread blocks but is marked for urgrent unblocking at the next scheduling point and the signalled thread continues.
+\end{enumerate}
+The first approach is too restrictive, as it precludes solving a reasonable class of problems, \eg dating service.
+\CFA supports the next two semantics as both are useful.
+Finally, while it is common to store a @condition@ as a field of the monitor, in \CFA, a @condition@ variable can be created/stored independently.
+Furthermore, a condition variable is tied to a \emph{group} of monitors on first use (called \newterm{branding}), which means that using internal scheduling with distinct sets of monitors requires one condition variable per set of monitors.
+\begin{figure}
+\centering
+\newbox\myboxA
+\begin{lrbox}{\myboxA}
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
+forall( otype T ) { // distribute forall
+        monitor Buffer {
+                `condition` full, empty;
+                int front, back, count;
+                T elements[10];
+        };
+        void ?{}( Buffer(T) & buffer ) with(buffer) {
+                [front, back, count] = 0;
+        }
+        void insert( Buffer(T) & mutex buffer, T elem )
+                                with(buffer) {
+                if ( count == 10 ) `wait( empty )`;
+                // insert elem into buffer
+                `signal( full )`;
+        }
+        T remove( Buffer(T) & mutex buffer ) with(buffer) {
+                if ( count == 0 ) `wait( full )`;
+                // remove elem from buffer
+                `signal( empty )`;
+                return elem;
+        }
+}
+\end{cfa}
+\end{lrbox}
+\newbox\myboxB
+\begin{lrbox}{\myboxB}
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
+forall( otype T ) { // distribute forall
+        monitor Buffer {
+                int front, back, count;
+                T elements[10];
+        };
+        void ?{}( Buffer(T) & buffer ) with(buffer) {
+                [front, back, count] = 0;
+        }
+        T remove( Buffer(T) & mutex buffer ); // forward
+        void insert( Buffer(T) & mutex buffer, T elem )
+                                with(buffer) {
+                if ( count == 10 ) `waitfor( remove, buffer )`;
+                // insert elem into buffer
+        }
+        T remove( Buffer(T) & mutex buffer ) with(buffer) {
+                if ( count == 0 ) `waitfor( insert, buffer )`;
+                // remove elem from buffer
+                return elem;
+        }
+}
+\end{cfa}
+\end{lrbox}
+\subfloat[Internal Scheduling]{\label{f:BBInt}\usebox\myboxA}
+%\qquad
+\subfloat[External Scheduling]{\label{f:BBExt}\usebox\myboxB}
+\caption{Generic Bounded-Buffer}
+\label{f:GenericBoundedBuffer}
+\end{figure}
+Figure~\ref{f:BBExt} shows a \CFA bounded-buffer with external scheduling, where producers/consumers detecting a full/empty buffer block and prevent more producers/consumers from entering the monitor until the buffer has a free/empty slot.
+External scheduling is controlled by the @waitfor@ statement, which atomically blocks the calling thread, releases the monitor lock, and restricts the routine calls that can next acquire mutual exclusion.
+If the buffer is full, only calls to @remove@ can acquire the buffer, and if the buffer is empty, only calls to @insert@ can acquire the buffer.
+Threads making calls to routines that are currently excluded block outside (external) of the monitor on a calling queue, versus blocking on condition queues inside (internal) of the monitor.
+% External scheduling is more constrained and explicit, which helps programmers reduce the non-deterministic nature of concurrency.
+External scheduling allows users to wait for events from other threads without concern of unrelated events occurring.
+The mechnaism can be done in terms of control flow, \eg Ada @accept@ or \uC @_Accept@, or in terms of data, \eg Go channels.
+While both mechanisms have strengths and weaknesses, this project uses a control-flow mechanism to stay consistent with other language semantics.
+Two challenges specific to \CFA for external scheduling are loose object-definitions (see Section~\ref{s:LooseObjectDefinitions}) and multiple-monitor routines (see Section~\ref{s:Multi-MonitorScheduling}).
+For internal scheduling, non-blocking signalling (as in the producer/consumer example) is used when the signaller is providing the cooperation for a waiting thread;
+the signaller enters the monitor and changes state, detects a waiting threads that can use the state, performs a non-blocking signal on the condition queue for the waiting thread, and exits the monitor to run concurrently.
+The waiter unblocks next, uses/takes the state, and exits the monitor.
+Blocking signalling is the reverse, where the waiter is providing the cooperation for the signalling thread;
+the signaller enters the monitor, detects a waiting thread providing the necessary state, performs a blocking signal to place it on the urgent queue and unblock the waiter.
+The waiter changes state and exits the monitor, and the signaller unblocks next from the urgent queue to use/take the state.
+Figure~\ref{f:DatingService} shows a dating service demonstrating the two forms of signalling: non-blocking and blocking.
+The dating service matches girl and boy threads with matching compatibility codes so they can exchange phone numbers.
+A thread blocks until an appropriate partner arrives.
+The complexity is exchanging phone number in the monitor because the monitor mutual-exclusion property prevents exchanging numbers.
+For internal scheduling, the @exchange@ condition is necessary to block the thread finding the match, while the matcher unblocks to take the oppose number, post its phone number, and unblock the partner.
+For external scheduling, the implicit urgent-condition replaces the explict @exchange@-condition and @signal_block@ puts the finding thread on the urgent condition and unblocks the matcher..
+The dating service is an example of a monitor that cannot be written using external scheduling because it requires knowledge of calling parameters to make scheduling decisions, and parameters of waiting threads are unavailable;
+as well, an arriving thread may not find a partner and must wait, which requires a condition variable, and condition variables imply internal scheduling.
+\begin{figure}
+\centering
+\newbox\myboxA
+\begin{lrbox}{\myboxA}
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
+enum { CCodes = 20 };
+monitor DS {
+        int GirlPhNo, BoyPhNo;
+        condition Girls[CCodes], Boys[CCodes];
+        condition exchange;
 };
+void ?{}(counter_t & this) {
+        this.cnt = 0;
+}
+int ?++(counter_t & mutex this) {
+        return ++this.value;
+}
+// need for mutex is platform dependent here
+void ?{}(int * this, counter_t & mutex cnt) {
+        *this = (int)cnt;
+}
+\end{cfa}
+Like threads and coroutines, monitors are defined in terms of traits with some additional language support in the form of the @monitor@ keyword.
+The monitor trait is:
+\begin{cfa}
+trait is_monitor(dtype T) {
+        monitor_desc * get_monitor( T & );
+        void ^?{}( T & mutex );
+int girl( DS & mutex ds, int phNo, int ccode ) {
+        if ( is_empty( Boys[ccode] ) ) {
+                wait( Girls[ccode] );
+                GirlPhNo = phNo;
+                exchange.signal();
+        } else {
+                GirlPhNo = phNo;
+                signal( Boys[ccode] );
+                exchange.wait();
+        } // if
+        return BoyPhNo;
+}
+int boy( DS & mutex ds, int phNo, int ccode ) {
+        // as above with boy/girl interchanged
+}
+\end{cfa}
+\end{lrbox}
+\newbox\myboxB
+\begin{lrbox}{\myboxB}
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
+monitor DS {
+        int GirlPhNo, BoyPhNo;
+        condition Girls[CCodes], Boys[CCodes];
 };
+\end{cfa}
+Note that the destructor of a monitor must be a @mutex@ routine to prevent deallocation while a thread is accessing the monitor.
+As with any object, calls to a monitor, using @mutex@ or otherwise, is undefined behaviour after the destructor has run.
+% ======================================================================
+% ======================================================================
+\section{Internal Scheduling} \label{intsched}
+% ======================================================================
+% ======================================================================
+In addition to mutual exclusion, the monitors at the core of \CFA's concurrency can also be used to achieve synchronization.
+With monitors, this capability is generally achieved with internal or external scheduling as in~\cite{Hoare74}.
+With \textbf{scheduling} loosely defined as deciding which thread acquires the critical section next, \textbf{internal scheduling} means making the decision from inside the critical section (\ie with access to the shared state), while \textbf{external scheduling} means making the decision when entering the critical section (\ie without access to the shared state).
+Since internal scheduling within a single monitor is mostly a solved problem, this paper concentrates on extending internal scheduling to multiple monitors.
+Indeed, like the \textbf{bulk-acq} semantics, internal scheduling extends to multiple monitors in a way that is natural to the user but requires additional complexity on the implementation side.
+First, here is a simple example of internal scheduling:
+\begin{cfa}
+monitor A {
+        condition e;
+}
+void foo(A& mutex a1, A& mutex a2) {
+int girl( DS & mutex ds, int phNo, int ccode ) {
+        if ( is_empty( Boys[ccode] ) ) { // no compatible
+                wait( Girls[ccode] ); // wait for boy
+                GirlPhNo = phNo; // make phone number available
+        } else {
+                GirlPhNo = phNo; // make phone number available
+                signal_block( Boys[ccode] ); // restart boy
+        } // if
+        return BoyPhNo;
+}
+int boy( DS & mutex ds, int phNo, int ccode ) {
+        // as above with boy/girl interchanged
+}
+\end{cfa}
+\end{lrbox}
+\subfloat[\lstinline@signal@]{\label{f:DatingSignal}\usebox\myboxA}
+\qquad
+\subfloat[\lstinline@signal_block@]{\label{f:DatingSignalBlock}\usebox\myboxB}
+\caption{Dating service. }
+\label{f:DatingService}
+\end{figure}
+Both internal and external scheduling extend to multiple monitors in a natural way.
+\begin{cquote}
+\begin{tabular}{@{}l@{\hspace{3\parindentlnth}}l@{}}
+\begin{cfa}
+monitor M { `condition e`; ... };
+void foo( M & mutex m1, M & mutex m2 ) {
+        ... wait( `e` ); ...   // wait( e, m1, m2 )
+        ... wait( `e, m1` ); ...
+        ... wait( `e, m2` ); ...
+}
+\end{cfa}
+&
+\begin{cfa}
+void rtn$\(_1\)$( M & mutex m1, M & mutex m2 );
+void rtn$\(_2\)$( M & mutex m1 );
+void bar( M & mutex m1, M & mutex m2 ) {
+        ... waitfor( `rtn` ); ...       // $\LstCommentStyle{waitfor( rtn\(_1\), m1, m2 )}$
+        ... waitfor( `rtn, m1` ); ... // $\LstCommentStyle{waitfor( rtn\(_2\), m1 )}$
+}
+\end{cfa}
+\end{tabular}
+\end{cquote}
+For @wait( e )@, the default semantics is to atomically block the signaller and release all acquired mutex types in the parameter list, \ie @wait( e, m1, m2 )@.
+To override the implicit multi-monitor wait, specific mutex parameter(s) can be specified, \eg @wait( e, m1 )@.
+Wait statically verifies the released monitors are the acquired mutex-parameters so unconditional release is safe.
+Finally, a signaller,
+\begin{cfa}
+void baz( M & mutex m1, M & mutex m2 ) {
+        ... signal( e ); ...
+}
+\end{cfa}
+must have acquired monitor locks that are greater than or equal to the number of locks for the waiting thread signalled from the condition queue.
+Similarly, for @waitfor( rtn )@, the default semantics is to atomically block the acceptor and release all acquired mutex types in the parameter list, \ie @waitfor( rtn, m1, m2 )@.
+To override the implicit multi-monitor wait, specific mutex parameter(s) can be specified, \eg @waitfor( rtn, m1 )@.
+Waitfor statically verifies the released monitors are the same as the acquired mutex-parameters of the given routine or routine pointer.
+To statically verify the released monitors match with the accepted routine's mutex parameters, the routine (pointer) prototype must be accessible.
+Given the ability to release a subset of acquired monitors can result in a \newterm{nested monitor}~\cite{Lister77} deadlock.
+\begin{cfa}
+void foo( M & mutex m1, M & mutex m2 ) {
+        ... wait( `e, m1` ); ...                                $\C{// release m1, keeping m2 acquired )}$
+void bar( M & mutex m1, M & mutex m2 ) {        $\C{// must acquire m1 and m2 )}$
+        ... signal( `e` ); ...
+\end{cfa}
+The @wait@ only releases @m1@ so the signalling thread cannot acquire both @m1@ and @m2@ to  enter @bar@ to get to the @signal@.
+While deadlock issues can occur with multiple/nesting acquisition, this issue results from the fact that locks, and by extension monitors, are not perfectly composable.
+Finally, an important aspect of monitor implementation is barging, \ie can calling threads barge ahead of signalled threads?
+If barging is allowed, synchronization between a singller and signallee is difficult, often requiring multiple unblock/block cycles (looping around a wait rechecking if a condition is met).
+\begin{quote}
+However, we decree that a signal operation be followed immediately by resumption of a waiting program, without possibility of an intervening procedure call from yet a third program.
+It is only in this way that a waiting program has an absolute guarantee that it can acquire the resource just released by the signalling program without any danger that a third program will interpose a monitor entry and seize the resource instead.~\cite[p.~550]{Hoare74}
+\end{quote}
+\CFA scheduling \emph{precludes} barging, which simplifies synchronization among threads in the monitor and increases correctness.
+For example, there are no loops in either bounded buffer solution in Figure~\ref{f:GenericBoundedBuffer}.
+Supporting barging prevention as well as extending internal scheduling to multiple monitors is the main source of complexity in the design and implementation of \CFA concurrency.
+\subsection{Barging Prevention}
+Figure~\ref{f:BargingPrevention} shows \CFA code where bulk acquire adds complexity to the internal-signalling semantics.
+The complexity begins at the end of the inner @mutex@ statement, where the semantics of internal scheduling need to be extended for multiple monitors.
+The problem is that bulk acquire is used in the inner @mutex@ statement where one of the monitors is already acquired.
+When the signalling thread reaches the end of the inner @mutex@ statement, it should transfer ownership of @m1@ and @m2@ to the waiting threads to prevent barging into the outer @mutex@ statement by another thread.
+However, both the signalling and waiting thread W1 still need monitor @m1@.
+\begin{figure}
+\newbox\myboxA
+\begin{lrbox}{\myboxA}
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
+monitor M m1, m2;
+condition c;
+mutex( m1 ) { // $\LstCommentStyle{\color{red}outer}$
         ...
+        // Wait for cooperation from bar()
+        wait(a1.e);
+        mutex( m1, m2 ) { // $\LstCommentStyle{\color{red}inner}$
+                ... `signal( c )`; ...
+                // m1, m2 acquired
+        } // $\LstCommentStyle{\color{red}release m2}$
+        // m1 acquired
+} // release m1
+\end{cfa}
+\end{lrbox}
+\newbox\myboxB
+\begin{lrbox}{\myboxB}
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
+mutex( m1 ) {
         ...
+}
+void bar(A& mutex a1, A& mutex a2) {
+        // Provide cooperation for foo()
+        ...
+        // Unblock foo
+        signal(a1.e);
+}
+\end{cfa}
+There are two details to note here.
+First, @signal@ is a delayed operation; it only unblocks the waiting thread when it reaches the end of the critical section.
+This semantics is needed to respect mutual-exclusion, \ie the signaller and signalled thread cannot be in the monitor simultaneously.
+The alternative is to return immediately after the call to @signal@, which is significantly more restrictive.
+Second, in \CFA, while it is common to store a @condition@ as a field of the monitor, a @condition@ variable can be stored/created independently of a monitor.
+Here routine @foo@ waits for the @signal@ from @bar@ before making further progress, ensuring a basic ordering.
+An important aspect of the implementation is that \CFA does not allow barging, which means that once function @bar@ releases the monitor, @foo@ is guaranteed to be the next thread to acquire the monitor (unless some other thread waited on the same condition).
+This guarantee offers the benefit of not having to loop around waits to recheck that a condition is met.
+The main reason \CFA offers this guarantee is that users can easily introduce barging if it becomes a necessity but adding barging prevention or barging avoidance is more involved without language support.
+Supporting barging prevention as well as extending internal scheduling to multiple monitors is the main source of complexity in the design and implementation of \CFA concurrency.
+% ======================================================================
+% ======================================================================
+\subsection{Internal Scheduling - Multi-Monitor}
+% ======================================================================
+% ======================================================================
+It is easy to understand the problem of multi-monitor scheduling using a series of pseudo-code examples.
+Note that for simplicity in the following snippets of pseudo-code, waiting and signalling is done using an implicit condition variable, like Java built-in monitors.
+Indeed, @wait@ statements always use the implicit condition variable as parameters and explicitly name the monitors (A and B) associated with the condition.
+Note that in \CFA, condition variables are tied to a \emph{group} of monitors on first use (called branding), which means that using internal scheduling with distinct sets of monitors requires one condition variable per set of monitors.
+The example below shows the simple case of having two threads (one for each column) and a single monitor A.
+\begin{multicols}{2}
+thread 1
+\begin{cfa}
+acquire A
+        wait A
+release A
+\end{cfa}
+\columnbreak
+thread 2
+\begin{cfa}
+acquire A
+        signal A
+release A
+\end{cfa}
+\end{multicols}
+One thread acquires before waiting (atomically blocking and releasing A) and the other acquires before signalling.
+It is important to note here that both @wait@ and @signal@ must be called with the proper monitor(s) already acquired.
+This semantic is a logical requirement for barging prevention.
+A direct extension of the previous example is a \textbf{bulk-acq} version:
+\begin{multicols}{2}
+\begin{cfa}
+acquire A & B
+        wait A & B
+release A & B
+\end{cfa}
+\columnbreak
+\begin{cfa}
+acquire A & B
+        signal A & B
+release A & B
+\end{cfa}
+\end{multicols}
+\noindent This version uses \textbf{bulk-acq} (denoted using the {\sf\&} symbol), but the presence of multiple monitors does not add a particularly new meaning.
+Synchronization happens between the two threads in exactly the same way and order.
+The only difference is that mutual exclusion covers a group of monitors.
+On the implementation side, handling multiple monitors does add a degree of complexity as the next few examples demonstrate.
+While deadlock issues can occur when nesting monitors, these issues are only a symptom of the fact that locks, and by extension monitors, are not perfectly composable.
+For monitors, a well-known deadlock problem is the Nested Monitor Problem~\cite{Lister77}, which occurs when a @wait@ is made by a thread that holds more than one monitor.
+For example, the following cfa-code runs into the nested-monitor problem:
+\begin{multicols}{2}
+\begin{cfa}
+acquire A
+        acquire B
+                wait B
+        release B
+release A
+\end{cfa}
+\columnbreak
+\begin{cfa}
+acquire A
+        acquire B
+                signal B
+        release B
+release A
+\end{cfa}
+\end{multicols}
+\noindent The @wait@ only releases monitor @B@ so the signalling thread cannot acquire monitor @A@ to get to the @signal@.
+Attempting release of all acquired monitors at the @wait@ introduces a different set of problems, such as releasing monitor @C@, which has nothing to do with the @signal@.
+However, for monitors as for locks, it is possible to write a program using nesting without encountering any problems if nesting is done correctly.
+For example, the next cfa-code snippet acquires monitors {\sf A} then {\sf B} before waiting, while only acquiring {\sf B} when signalling, effectively avoiding the Nested Monitor Problem~\cite{Lister77}.
+\begin{multicols}{2}
+\begin{cfa}
+acquire A
+        acquire B
+                wait B
+        release B
+release A
+\end{cfa}
+\columnbreak
+\begin{cfa}
+acquire B
+        signal B
+release B
+\end{cfa}
+\end{multicols}
+\noindent However, this simple refactoring may not be possible, forcing more complex restructuring.
+% ======================================================================
+% ======================================================================
+\subsection{Internal Scheduling - In Depth}
+% ======================================================================
+% ======================================================================
+A larger example is presented to show complex issues for \textbf{bulk-acq} and its implementation options are analyzed.
+Figure~\ref{f:int-bulk-cfa} shows an example where \textbf{bulk-acq} adds a significant layer of complexity to the internal signalling semantics, and listing \ref{f:int-bulk-cfa} shows the corresponding \CFA code to implement the cfa-code in listing \ref{f:int-bulk-cfa}.
+For the purpose of translating the given cfa-code into \CFA-code, any method of introducing a monitor is acceptable, \eg @mutex@ parameters, global variables, pointer parameters, or using locals with the @mutex@ statement.
+\begin{figure}
+\begin{multicols}{2}
+Waiting thread
+\begin{cfa}[numbers=left]
+acquire A
+        // Code Section 1
+        acquire A & B
+                // Code Section 2
+                wait A & B
+                // Code Section 3
+        release A & B
+        // Code Section 4
+release A
+\end{cfa}
+\columnbreak
+Signalling thread
+\begin{cfa}[numbers=left, firstnumber=10,escapechar=|]
+acquire A
+        // Code Section 5
+        acquire A & B
+                // Code Section 6
+                |\label{line:signal1}|signal A & B
+                // Code Section 7
+        |\label{line:releaseFirst}|release A & B
+        // Code Section 8
+|\label{line:lastRelease}|release A
+\end{cfa}
+\end{multicols}
+\begin{cfa}[caption={Internal scheduling with \textbf{bulk-acq}},label={f:int-bulk-cfa}]
+\end{cfa}
+\begin{center}
+\begin{cfa}[xleftmargin=.4\textwidth]
+monitor A a;
+monitor B b;
+condition c;
+\end{cfa}
+\end{center}
+\begin{multicols}{2}
+Waiting thread
+\begin{cfa}
+mutex(a) {
+        // Code Section 1
+        mutex(a, b) {
+                // Code Section 2
+                wait(c);
+                // Code Section 3
+        }
+        // Code Section 4
+}
+\end{cfa}
+\columnbreak
+Signalling thread
+\begin{cfa}
+mutex(a) {
+        // Code Section 5
+        mutex(a, b) {
+                // Code Section 6
+                signal(c);
+                // Code Section 7
+        }
+        // Code Section 8
+}
+\end{cfa}
+\end{multicols}
+\begin{cfa}[caption={Equivalent \CFA code for listing \ref{f:int-bulk-cfa}},label={f:int-bulk-cfa}]
+\end{cfa}
+\begin{multicols}{2}
+Waiter
+\begin{cfa}[numbers=left]
+acquire A
+        acquire A & B
+                wait A & B
+        release A & B
+release A
+\end{cfa}
+\columnbreak
+Signaller
+\begin{cfa}[numbers=left, firstnumber=6,escapechar=|]
+acquire A
+        acquire A & B
+                signal A & B
+        release A & B
+        |\label{line:secret}|// Secretly keep B here
+release A
+// Wakeup waiter and transfer A & B
+\end{cfa}
+\end{multicols}
+\begin{cfa}[caption={Figure~\ref{f:int-bulk-cfa}, with delayed signalling comments},label={f:int-secret}]
+\end{cfa}
+        mutex( m1, m2 ) {
+                ... `wait( c )`; // block and release m1, m2
+                // m1, m2 acquired
+        } // $\LstCommentStyle{\color{red}release m2}$
+        // m1 acquired
+} // release m1
+\end{cfa}
+\end{lrbox}
+\newbox\myboxC
+\begin{lrbox}{\myboxC}
+\begin{cfa}[aboveskip=0pt,belowskip=0pt]
+mutex( m2 ) {
+        ... `wait( c )`; ...
+        // m2 acquired
+} // $\LstCommentStyle{\color{red}release m2}$
+\end{cfa}
+\end{lrbox}
+\begin{cquote}
+\subfloat[Signalling Thread]{\label{f:SignallingThread}\usebox\myboxA}
+\hspace{2\parindentlnth}
+\subfloat[Waiting Thread (W1)]{\label{f:WaitingThread}\usebox\myboxB}
+\hspace{2\parindentlnth}
+\subfloat[Waiting Thread (W2)]{\label{f:OtherWaitingThread}\usebox\myboxC}
+\end{cquote}
+\caption{Barging Prevention}
+\label{f:BargingPrevention}
 \end{figure}
+The complexity begins at code sections 4 and 8 in listing \ref{f:int-bulk-cfa}, which are where the existing semantics of internal scheduling needs to be extended for multiple monitors.
+The root of the problem is that \textbf{bulk-acq} is used in a context where one of the monitors is already acquired, which is why it is important to define the behaviour of the previous cfa-code.
+When the signaller thread reaches the location where it should ``release @A & B@'' (listing \ref{f:int-bulk-cfa} line \ref{line:releaseFirst}), it must actually transfer ownership of monitor @B@ to the waiting thread.
+This ownership transfer is required in order to prevent barging into @B@ by another thread, since both the signalling and signalled threads still need monitor @A@.
+There are three options:
+\subsubsection{Delaying Signals}
+The obvious solution to the problem of multi-monitor scheduling is to keep ownership of all locks until the last lock is ready to be transferred.
+It can be argued that that moment is when the last lock is no longer needed, because this semantics fits most closely to the behaviour of single-monitor scheduling.
+This solution has the main benefit of transferring ownership of groups of monitors, which simplifies the semantics from multiple objects to a single group of objects, effectively making the existing single-monitor semantic viable by simply changing monitors to monitor groups.
+This solution releases the monitors once every monitor in a group can be released.
+However, since some monitors are never released (\eg the monitor of a thread), this interpretation means a group might never be released.
+A more interesting interpretation is to transfer the group until all its monitors are released, which means the group is not passed further and a thread can retain its locks.
+However, listing \ref{f:int-secret} shows this solution can become much more complicated depending on what is executed while secretly holding B at line \ref{line:secret}, while avoiding the need to transfer ownership of a subset of the condition monitors.
+One scheduling solution is for the signaller to keep ownership of all locks until the last lock is ready to be transferred, because this semantics fits most closely to the behaviour of single-monitor scheduling.
+However, Figure~\ref{f:OtherWaitingThread} shows this solution is complex depending on other waiters, resulting is choices when the signaller finishes the inner mutex-statement.
+The singaller can retain @m2@ until completion of the outer mutex statement and pass the locks to waiter W1, or it can pass @m2@ to waiter W2 after completing the inner mutex-statement, while continuing to hold @m1@.
+In the latter case, waiter W2 must eventually pass @m2@ to waiter W1, which is complex because W1 may have waited before W2, so W2 is unaware of it.
+Furthermore, there is an execution sequence where the signaller always finds waiter W2, and hence, waiter W1 starves.
+While a number of approaches were examined~\cite[\S~4.3]{Delisle18}, the solution chosen for \CFA is a novel techique called \newterm{partial signalling}.
+Signalled threads are moved to an urgent queue and the waiter at the front defines the set of monitors necessary for it to unblock.
+Partial signalling transfers ownership of monitors to the front waiter.
+When the signaller thread exits or waits in the monitor the front waiter is unblocked if all its monitors are released.
+This solution has the benefit that complexity is encapsulated into only two actions: passing monitors to the next owner when they should be released and conditionally waking threads if all conditions are met.
+\begin{comment}
 Figure~\ref{f:dependency} shows a slightly different example where a third thread is waiting on monitor @A@, using a different condition variable.
 Because the third thread is signalled when secretly holding @B@, the goal  becomes unreachable.
 …
 In both cases, the threads need to be able to distinguish, on a per monitor basis, which ones need to be released and which ones need to be transferred, which means knowing when to release a group becomes complex and inefficient (see next section) and therefore effectively precludes this approach.
 \subsubsection{Dependency graphs}
 \begin{figure}
 …
 The extra challenge is that this dependency graph is effectively post-mortem, but the runtime system needs to be able to build and solve these graphs as the dependencies unfold.
 Resolving dependency graphs being a complex and expensive endeavour, this solution is not the preferred one.
+\subsubsection{Partial Signalling} \label{partial-sig}
+Finally, the solution that is chosen for \CFA is to use partial signalling.
+Again using listing \ref{f:int-bulk-cfa}, the partial signalling solution transfers ownership of monitor @B@ at lines \ref{line:signal1} to the waiter but does not wake the waiting thread since it is still using monitor @A@.
+Only when it reaches line \ref{line:lastRelease} does it actually wake up the waiting thread.
+This solution has the benefit that complexity is encapsulated into only two actions: passing monitors to the next owner when they should be released and conditionally waking threads if all conditions are met.
+This solution has a much simpler implementation than a dependency graph solving algorithms, which is why it was chosen.
+Furthermore, after being fully implemented, this solution does not appear to have any significant downsides.
+Using partial signalling, listing \ref{f:dependency} can be solved easily:
+\begin{itemize}
+        \item When thread $\gamma$ reaches line \ref{line:release-ab} it transfers monitor @B@ to thread $\alpha$ and continues to hold monitor @A@.
+        \item When thread $\gamma$ reaches line \ref{line:release-a}  it transfers monitor @A@ to thread $\beta$  and wakes it up.
+        \item When thread $\beta$  reaches line \ref{line:release-aa} it transfers monitor @A@ to thread $\alpha$ and wakes it up.
+\end{itemize}
+% ======================================================================
+% ======================================================================
+\subsection{Signalling: Now or Later}
+% ======================================================================
+% ======================================================================
+\begin{table}
+\begin{tabular}{|c|c|}
+@signal@ & @signal_block@ \\
+\hline
+\begin{cfa}[tabsize=3]
+monitor DatingService {
+        // compatibility codes
+        enum{ CCodes = 20 };
+        int girlPhoneNo
+        int boyPhoneNo;
+};
+condition girls[CCodes];
+condition boys [CCodes];
+condition exchange;
+int girl(int phoneNo, int cfa) {
+        // no compatible boy ?
+        if(empty(boys[cfa])) {
+                wait(girls[cfa]);               // wait for boy
+                girlPhoneNo = phoneNo;          // make phone number available
+                signal(exchange);               // wake boy from chair
+        } else {
+                girlPhoneNo = phoneNo;          // make phone number available
+                signal(boys[cfa]);              // wake boy
+                wait(exchange);         // sit in chair
+        }
+        return boyPhoneNo;
+}
+int boy(int phoneNo, int cfa) {
+        // same as above
+        // with boy/girl interchanged
+}
+\end{cfa}&\begin{cfa}[tabsize=3]
+monitor DatingService {
+        enum{ CCodes = 20 };    // compatibility codes
+        int girlPhoneNo;
+        int boyPhoneNo;
+};
+condition girls[CCodes];
+condition boys [CCodes];
+// exchange is not needed
+int girl(int phoneNo, int cfa) {
+        // no compatible boy ?
+        if(empty(boys[cfa])) {
+                wait(girls[cfa]);               // wait for boy
+                girlPhoneNo = phoneNo;          // make phone number available
+                signal(exchange);               // wake boy from chair
+        } else {
+                girlPhoneNo = phoneNo;          // make phone number available
+                signal_block(boys[cfa]);                // wake boy
+                // second handshake unnecessary
+        }
+        return boyPhoneNo;
+}
+int boy(int phoneNo, int cfa) {
+        // same as above
+        // with boy/girl interchanged
+}
+\end{cfa}
+\end{tabular}
+\caption{Dating service example using \protect\lstinline|signal| and \protect\lstinline|signal_block|. }
+\label{tbl:datingservice}
+\end{table}
+An important note is that, until now, signalling a monitor was a delayed operation.
+The ownership of the monitor is transferred only when the monitor would have otherwise been released, not at the point of the @signal@ statement.
+However, in some cases, it may be more convenient for users to immediately transfer ownership to the thread that is waiting for cooperation, which is achieved using the @signal_block@ routine.
+The example in table \ref{tbl:datingservice} highlights the difference in behaviour.
+As mentioned, @signal@ only transfers ownership once the current critical section exits; this behaviour requires additional synchronization when a two-way handshake is needed.
+To avoid this explicit synchronization, the @condition@ type offers the @signal_block@ routine, which handles the two-way handshake as shown in the example.
+This feature removes the need for a second condition variables and simplifies programming.
+Like every other monitor semantic, @signal_block@ uses barging prevention, which means mutual-exclusion is baton-passed both on the front end and the back end of the call to @signal_block@, meaning no other thread can acquire the monitor either before or after the call.
+% ======================================================================
+% ======================================================================
+\end{comment}
+\begin{comment}
 \section{External scheduling} \label{extsched}
+% ======================================================================
+% ======================================================================
+An alternative to internal scheduling is external scheduling (see Table~\ref{tbl:sched}).
 \begin{table}
 \begin{tabular}{|c|c|c|}
 …
 \label{tbl:sched}
 \end{table}
-This method is more constrained and explicit, which helps users reduce the non-deterministic nature of concurrency.
-Indeed, as the following examples demonstrate, external scheduling allows users to wait for events from other threads without the concern of unrelated events occurring.
-External scheduling can generally be done either in terms of control flow (\eg Ada with @accept@, \uC with @_Accept@) or in terms of data (\eg Go with channels).
-Of course, both of these paradigms have their own strengths and weaknesses, but for this project, control-flow semantics was chosen to stay consistent with the rest of the languages semantics.
-Two challenges specific to \CFA arise when trying to add external scheduling with loose object definitions and multiple-monitor routines.
-The previous example shows a simple use @_Accept@ versus @wait@/@signal@ and its advantages.
-Note that while other languages often use @accept@/@select@ as the core external scheduling keyword, \CFA uses @waitfor@ to prevent name collisions with existing socket \textbf{api}s.
 For the @P@ member above using internal scheduling, the call to @wait@ only guarantees that @V@ is the last routine to access the monitor, allowing a third routine, say @isInUse()@, acquire mutual exclusion several times while routine @P@ is waiting.
 On the other hand, external scheduling guarantees that while routine @P@ is waiting, no other routine than @V@ can acquire the monitor.
+% ======================================================================
+% ======================================================================
+\end{comment}
 \subsection{Loose Object Definitions}
+% ======================================================================
+% ======================================================================
+In \uC, a monitor class declaration includes an exhaustive list of monitor operations.
+Since \CFA is not object oriented, monitors become both more difficult to implement and less clear for a user:
+\begin{cfa}
+monitor A {};
+void f(A & mutex a);
+void g(A & mutex a) {
+        waitfor(f); // Obvious which f() to wait for
+}
+void f(A & mutex a, int); // New different F added in scope
+void h(A & mutex a) {
+        waitfor(f); // Less obvious which f() to wait for
+}
+\end{cfa}
+Furthermore, external scheduling is an example where implementation constraints become visible from the interface.
+Here is the cfa-code for the entering phase of a monitor:
+\begin{center}
+\begin{tabular}{l}
+\begin{cfa}
+        if monitor is free
+                enter
+        elif already own the monitor
+                continue
+        elif monitor accepts me
+                enter
+        else
+                block
+\end{cfa}
+\end{tabular}
+\end{center}
+\label{s:LooseObjectDefinitions}
+In an object-oriented programming-language, a class includes an exhaustive list of operations.
+However, new members can be added via static inheritance or dynaic members, \eg JavaScript~\cite{JavaScript}.
+Similarly, monitor routines can be added at any time in \CFA, making it less clear for programmers and more difficult to implement.
+\begin{cfa}
+monitor M {};
+void `f`( M & mutex m );
+void g( M & mutex m ) { waitfor( `f` ); }       $\C{// clear which f}$
+void `f`( M & mutex m, int );                           $\C{// different f}$
+void h( M & mutex m ) { waitfor( `f` ); }       $\C{// unclear which f}$
+\end{cfa}
+Hence, the cfa-code for the entering a monitor looks like:
+\begin{cfa}
+if ( $\textrm{\textit{monitor is free}}$ ) $\LstCommentStyle{// \color{red}enter}$
+else if ( $\textrm{\textit{already own monitor}}$ ) $\LstCommentStyle{// \color{red}continue}$
+else if ( $\textrm{\textit{monitor accepts me}}$ ) $\LstCommentStyle{// \color{red}enter}$
+else $\LstCommentStyle{// \color{red}block}$
+\end{cfa}
 For the first two conditions, it is easy to implement a check that can evaluate the condition in a few instructions.
 However, a fast check for @monitor accepts me@ is much harder to implement depending on the constraints put on the monitors.
 Indeed, monitors are often expressed as an entry queue and some acceptor queue as in Figure~\ref{fig:ClassicalMonitor}.
+However, a fast check for \emph{monitor accepts me} is much harder to implement depending on the constraints put on the monitors.
+Figure~\ref{fig:ClassicalMonitor} shows monitors are often expressed as an entry (calling) queue, some acceptor queues, and an urgent stack/queue.
 \begin{figure}
 \centering
 \subfloat[Classical Monitor] {
+\subfloat[Classical monitor] {
 \label{fig:ClassicalMonitor}
 {\resizebox{0.45\textwidth}{!}{\input{monitor}}}
+{\resizebox{0.45\textwidth}{!}{\input{monitor.pstex_t}}}
 }% subfloat
 \qquad
 \subfloat[\textbf{bulk-acq} Monitor] {
+\quad
+\subfloat[Bulk acquire monitor] {
 \label{fig:BulkMonitor}
 {\resizebox{0.45\textwidth}{!}{\input{ext_monitor}}}
+{\resizebox{0.45\textwidth}{!}{\input{ext_monitor.pstex_t}}}
 }% subfloat
+\caption{External Scheduling Monitor}
+\caption{Monitor Implementation}
+\label{f:MonitorImplementation}
 \end{figure}
+There are other alternatives to these pictures, but in the case of the left picture, implementing a fast accept check is relatively easy.
+Restricted to a fixed number of mutex members, N, the accept check reduces to updating a bitmask when the acceptor queue changes, a check that executes in a single instruction even with a fairly large number (\eg 128) of mutex members.
+This approach requires a unique dense ordering of routines with an upper-bound and that ordering must be consistent across translation units.
+For OO languages these constraints are common, since objects only offer adding member routines consistently across translation units via inheritance.
+However, in \CFA users can extend objects with mutex routines that are only visible in certain translation unit.
+This means that establishing a program-wide dense-ordering among mutex routines can only be done in the program linking phase, and still could have issues when using dynamically shared objects.
+The alternative is to alter the implementation as in Figure~\ref{fig:BulkMonitor}.
+Here, the mutex routine called is associated with a thread on the entry queue while a list of acceptable routines is kept separate.
+Generating a mask dynamically means that the storage for the mask information can vary between calls to @waitfor@, allowing for more flexibility and extensions.
+Storing an array of accepted function pointers replaces the single instruction bitmask comparison with dereferencing a pointer followed by a linear search.
+Furthermore, supporting nested external scheduling (\eg listing \ref{f:nest-ext}) may now require additional searches for the @waitfor@ statement to check if a routine is already queued.
+For a fixed (small) number of mutex routines (\eg 128), the accept check reduces to a bitmask of allowed callers, which can be checked with a single instruction.
+This approach requires a unique dense ordering of routines with a small upper-bound and the ordering must be consistent across translation units.
+For object-oriented languages these constraints are common, but \CFA mutex routines can be added in any scope and are only visible in certain translation unit, precluding program-wide dense-ordering among mutex routines.
+Figure~\ref{fig:BulkMonitor} shows the \CFA monitor implementation.
+The mutex routine called is associated with each thread on the entry queue, while a list of acceptable routines is kept separately.
+The accepted list is a variable-sized array of accepted routine pointers, so the single instruction bitmask comparison is replaced by dereferencing a pointer followed by a linear search.
+\begin{comment}
 \begin{figure}
 \begin{cfa}[caption={Example of nested external scheduling},label={f:nest-ext}]
 …
 \end{figure}
 Note that in the right picture, tasks need to always keep track of the monitors associated with mutex routines, and the routine mask needs to have both a function pointer and a set of monitors, as is discussed in the next section.
+Note that in the right picture, tasks need to always keep track of the monitors associated with mutex routines, and the routine mask needs to have both a routine pointer and a set of monitors, as is discussed in the next section.
 These details are omitted from the picture for the sake of simplicity.
 …
 In the end, the most flexible approach has been chosen since it allows users to write programs that would otherwise be  hard to write.
 This decision is based on the assumption that writing fast but inflexible locks is closer to a solved problem than writing locks that are as flexible as external scheduling in \CFA.
+% ======================================================================
+% ======================================================================
+\end{comment}
 \subsection{Multi-Monitor Scheduling}
+% ======================================================================
+% ======================================================================
+\label{s:Multi-MonitorScheduling}
 External scheduling, like internal scheduling, becomes significantly more complex when introducing multi-monitor syntax.
 Even in the simplest possible case, some new semantics needs to be established:
+Even in the simplest possible case, new semantics needs to be established:
 \begin{cfa}
 monitor M {};
+void f(M & mutex a);
+void g(M & mutex b, M & mutex c) {
+        waitfor(f); // two monitors M => unknown which to pass to f(M & mutex)
+}
+\end{cfa}
+The obvious solution is to specify the correct monitor as follows:
+void f( M & mutex m1 );
+void g( M & mutex m1, M & mutex m2 ) {
+        waitfor( f );                                                   $\C{// pass m1 or m2 to f?}$
+}
+\end{cfa}
+The solution is for the programmer to disambiguate:
+\begin{cfa}
+        waitfor( f, m2 );                                               $\C{// wait for call to f with argument m2}$
+\end{cfa}
+Routine @g@ has acquired both locks, so when routine @f@ is called, the lock for monitor @m2@ is passed from @g@ to @f@ (while @g@ still holds lock @m1@).
+This behaviour can be extended to the multi-monitor @waitfor@ statement.
 \begin{cfa}
 monitor M {};
+void f(M & mutex a);
+void g(M & mutex a, M & mutex b) {
+        // wait for call to f with argument b
+        waitfor(f, b);
+}
+\end{cfa}
+This syntax is unambiguous.
+Both locks are acquired and kept by @g@.
+When routine @f@ is called, the lock for monitor @b@ is temporarily transferred from @g@ to @f@ (while @g@ still holds lock @a@).
+This behaviour can be extended to the multi-monitor @waitfor@ statement as follows.
+\begin{cfa}
+monitor M {};
+void f(M & mutex a, M & mutex b);
+void g(M & mutex a, M & mutex b) {
+        // wait for call to f with arguments a and b
+        waitfor(f, a, b);
+}
+\end{cfa}
+Note that the set of monitors passed to the @waitfor@ statement must be entirely contained in the set of monitors already acquired in the routine. @waitfor@ used in any other context is undefined behaviour.
+void f( M & mutex m1, M & mutex m2 );
+void g( M & mutex m1, M & mutex m2 ) {
+        waitfor( f, m1, m2 );                                   $\C{// wait for call to f with arguments m1 and m2}$
+}
+\end{cfa}
+Again, the set of monitors passed to the @waitfor@ statement must be entirely contained in the set of monitors already acquired by accepting routine.
 An important behaviour to note is when a set of monitors only match partially:
 \begin{cfa}
 mutex struct A {};
 mutex struct B {};
+void g(A & mutex a, B & mutex b) {
+        waitfor(f, a, b);
+}
+void g( A & mutex m1, B & mutex m2 ) {
+        waitfor( f, m1, m2 );
+}
 A a1, a2;
 B b;
 void foo() {
+        g(a1, b); // block on accept
+}
+        g( a1, b ); // block on accept
+}
 void bar() {
         f(a2, b); // fulfill cooperation
+        f( a2, b ); // fulfill cooperation
+}
 \end{cfa}
 …
 It is also important to note that in the case of external scheduling the order of parameters is irrelevant; @waitfor(f,a,b)@ and @waitfor(f,b,a)@ are indistinguishable waiting condition.
+% ======================================================================
+% ======================================================================
 \subsection{\protect\lstinline|waitfor| Semantics}
+% ======================================================================
+% ======================================================================
+Syntactically, the @waitfor@ statement takes a function identifier and a set of monitors.
+While the set of monitors can be any list of expressions, the function name is more restricted because the compiler validates at compile time the validity of the function type and the parameters used with the @waitfor@ statement.
+It checks that the set of monitors passed in matches the requirements for a function call.
+Syntactically, the @waitfor@ statement takes a routine identifier and a set of monitors.
+While the set of monitors can be any list of expressions, the routine name is more restricted because the compiler validates at compile time the validity of the routine type and the parameters used with the @waitfor@ statement.
+It checks that the set of monitors passed in matches the requirements for a routine call.
 Figure~\ref{f:waitfor} shows various usages of the waitfor statement and which are acceptable.
 The choice of the function type is made ignoring any non-@mutex@ parameter.
+The choice of the routine type is made ignoring any non-@mutex@ parameter.
 One limitation of the current implementation is that it does not handle overloading, but overloading is possible.
 \begin{figure}
 …
         waitfor(f2, a1, a2); // Incorrect : Mutex arguments don't match
         waitfor(f1, 1);      // Incorrect : 1 not a mutex argument
         waitfor(f9, a1);     // Incorrect : f9 function does not exist
+        waitfor(f9, a1);     // Incorrect : f9 routine does not exist
         waitfor(*fp, a1 );   // Incorrect : fp not an identifier
         waitfor(f4, a1);     // Incorrect : f4 ambiguous
 …
 Finally, for added flexibility, \CFA supports constructing a complex @waitfor@ statement using the @or@, @timeout@ and @else@.
 Indeed, multiple @waitfor@ clauses can be chained together using @or@; this chain forms a single statement that uses baton pass to any function that fits one of the function+monitor set passed in.
 To enable users to tell which accepted function executed, @waitfor@s are followed by a statement (including the null statement @;@) or a compound statement, which is executed after the clause is triggered.
 A @waitfor@ chain can also be followed by a @timeout@, to signify an upper bound on the wait, or an @else@, to signify that the call should be non-blocking, which checks for a matching function call already arrived and otherwise continues.
+Indeed, multiple @waitfor@ clauses can be chained together using @or@; this chain forms a single statement that uses baton pass to any routine that fits one of the routine+monitor set passed in.
+To enable users to tell which accepted routine executed, @waitfor@s are followed by a statement (including the null statement @;@) or a compound statement, which is executed after the clause is triggered.
+A @waitfor@ chain can also be followed by a @timeout@, to signify an upper bound on the wait, or an @else@, to signify that the call should be non-blocking, which checks for a matching routine call already arrived and otherwise continues.
 Any and all of these clauses can be preceded by a @when@ condition to dynamically toggle the accept clauses on or off based on some current state.
 Figure~\ref{f:waitfor2} demonstrates several complex masks and some incorrect ones.
 …
 \end{figure}
+% ======================================================================
+% ======================================================================
 \subsection{Waiting For The Destructor}
+% ======================================================================
+% ======================================================================
 An interesting use for the @waitfor@ statement is destructor semantics.
 Indeed, the @waitfor@ statement can accept any @mutex@ routine, which includes the destructor (see section \ref{data}).
 …
-% ######     #    ######     #    #       #       ####### #       ###  #####  #     #
-% #     #   # #   #     #   # #   #       #       #       #        #  #     # ##   ##
-% #     #  #   #  #     #  #   #  #       #       #       #        #  #       # # # #
-% ######  #     # ######  #     # #       #       #####   #        #   #####  #  #  #
-% #       ####### #   #   ####### #       #       #       #        #        # #     #
-% #       #     # #    #  #     # #       #       #       #        #  #     # #     #
-% #       #     # #     # #     # ####### ####### ####### ####### ###  #####  #     #
 \section{Parallelism}
 Historically, computer performance was about processor speeds and instruction counts.
 However, with heat dissipation being a direct consequence of speed increase, parallelism has become the new source for increased performance~\cite{Sutter05, Sutter05b}.
 …
 While there are many variations of the presented paradigms, most of these variations do not actually change the guarantees or the semantics, they simply move costs in order to achieve better performance for certain workloads.
 \section{Paradigms}
 \subsection{User-Level Threads}
 A direct improvement on the \textbf{kthread} approach is to use \textbf{uthread}.
 These threads offer most of the same features that the operating system already provides but can be used on a much larger scale.
 …
 Examples of languages that support \textbf{uthread} are Erlang~\cite{Erlang} and \uC~\cite{uC++book}.
 \subsection{Fibers : User-Level Threads Without Preemption} \label{fibers}
 A popular variant of \textbf{uthread} is what is often referred to as \textbf{fiber}.
 However, \textbf{fiber} do not present meaningful semantic differences with \textbf{uthread}.
 …
 An example of a language that uses fibers is Go~\cite{Go}
 \subsection{Jobs and Thread Pools}
 An approach on the opposite end of the spectrum is to base parallelism on \textbf{pool}.
 Indeed, \textbf{pool} offer limited flexibility but at the benefit of a simpler user interface.
 …
 The gold standard of this implementation is Intel's TBB library~\cite{TBB}.
 \subsection{Paradigm Performance}
 While the choice between the three paradigms listed above may have significant performance implications, it is difficult to pin down the performance implications of choosing a model at the language level.
 Indeed, in many situations one of these paradigms may show better performance but it all strongly depends on the workload.
 …
 Finally, if the units of uninterrupted work are large, enough the paradigm choice is largely amortized by the actual work done.
 \section{The \protect\CFA\ Kernel : Processors, Clusters and Threads}\label{kernel}
 A \textbf{cfacluster} is a group of \textbf{kthread} executed in isolation. \textbf{uthread} are scheduled on the \textbf{kthread} of a given \textbf{cfacluster}, allowing organization between \textbf{uthread} and \textbf{kthread}.
 It is important that \textbf{kthread} belonging to a same \textbf{cfacluster} have homogeneous settings, otherwise migrating a \textbf{uthread} from one \textbf{kthread} to the other can cause issues.
 …
 Currently \CFA only supports one \textbf{cfacluster}, the initial one.
 \subsection{Future Work: Machine Setup}\label{machine}
 While this was not done in the context of this paper, another important aspect of clusters is affinity.
 While many common desktop and laptop PCs have homogeneous CPUs, other devices often have more heterogeneous setups.
 …
 OS support for CPU affinity is now common~\cite{affinityLinux, affinityWindows, affinityFreebsd, affinityNetbsd, affinityMacosx}, which means it is both possible and desirable for \CFA to offer an abstraction mechanism for portable CPU affinity.
 \subsection{Paradigms}\label{cfaparadigms}
 Given these building blocks, it is possible to reproduce all three of the popular paradigms.
 Indeed, \textbf{uthread} is the default paradigm in \CFA.
 …
 \section{Behind the Scenes}
 There are several challenges specific to \CFA when implementing concurrency.
 These challenges are a direct result of \textbf{bulk-acq} and loose object definitions.
+These challenges are a direct result of bulk acquire and loose object definitions.
 These two constraints are the root cause of most design decisions in the implementation.
 Furthermore, to avoid contention from dynamically allocating memory in a concurrent environment, the internal-scheduling design is (almost) entirely free of mallocs.
 …
 The main memory concern for concurrency is queues.
 All blocking operations are made by parking threads onto queues and all queues are designed with intrusive nodes, where each node has pre-allocated link fields for chaining, to avoid the need for memory allocation.
 Since several concurrency operations can use an unbound amount of memory (depending on \textbf{bulk-acq}), statically defining information in the intrusive fields of threads is insufficient.The only way to use a variable amount of memory without requiring memory allocation is to pre-allocate large buffers of memory eagerly and store the information in these buffers.
+Since several concurrency operations can use an unbound amount of memory (depending on bulk acquire), statically defining information in the intrusive fields of threads is insufficient.The only way to use a variable amount of memory without requiring memory allocation is to pre-allocate large buffers of memory eagerly and store the information in these buffers.
 Conveniently, the call stack fits that description and is easy to use, which is why it is used heavily in the implementation of internal scheduling, particularly variable-length arrays.
 Since stack allocation is based on scopes, the first step of the implementation is to identify the scopes that are available to store the information, and which of these can have a variable-length array.
 The threads and the condition both have a fixed amount of memory, while @mutex@ routines and blocking calls allow for an unbound amount, within the stack size.
+Note that since the major contributions of this paper are extending monitor semantics to \textbf{bulk-acq} and loose object definitions, any challenges that are not resulting of these characteristics of \CFA are considered as solved problems and therefore not discussed.
+% ======================================================================
+% ======================================================================
+Note that since the major contributions of this paper are extending monitor semantics to bulk acquire and loose object definitions, any challenges that are not resulting of these characteristics of \CFA are considered as solved problems and therefore not discussed.
 \section{Mutex Routines}
-% ======================================================================
-% ======================================================================
 The first step towards the monitor implementation is simple @mutex@ routines.
 …
 \end{figure}
 \subsection{Details: Interaction with polymorphism}
 Depending on the choice of semantics for when monitor locks are acquired, interaction between monitors and \CFA's concept of polymorphism can be more complex to support.
 However, it is shown that entry-point locking solves most of the issues.
 …
 void foo(T * mutex t);
 // Correct: this function only works on monitors (any monitor)
+// Correct: this routine only works on monitors (any monitor)
 forall(dtype T | is_monitor(T))
 void bar(T * mutex t));
 …
 Both entry point and \textbf{callsite-locking} are feasible implementations.
 The current \CFA implementation uses entry-point locking because it requires less work when using \textbf{raii}, effectively transferring the burden of implementation to object construction/destruction.
 It is harder to use \textbf{raii} for call-site locking, as it does not necessarily have an existing scope that matches exactly the scope of the mutual exclusion, \ie the function body.
+It is harder to use \textbf{raii} for call-site locking, as it does not necessarily have an existing scope that matches exactly the scope of the mutual exclusion, \ie the routine body.
 For example, the monitor call can appear in the middle of an expression.
 Furthermore, entry-point locking requires less code generation since any useful routine is called multiple times but there is only one entry point for many call sites.
+% ======================================================================
+% ======================================================================
 \section{Threading} \label{impl:thread}
-% ======================================================================
-% ======================================================================
 Figure \ref{fig:system1} shows a high-level picture if the \CFA runtime system in regards to concurrency.
 …
 \end{figure}
 \subsection{Processors}
 Parallelism in \CFA is built around using processors to specify how much parallelism is desired. \CFA processors are object wrappers around kernel threads, specifically @pthread@s in the current implementation of \CFA.
 Indeed, any parallelism must go through operating-system libraries.
 …
 Processors internally use coroutines to take advantage of the existing context-switching semantics.
 \subsection{Stack Management}
 One of the challenges of this system is to reduce the footprint as much as possible.
 Specifically, all @pthread@s created also have a stack created with them, which should be used as much as possible.
 …
 In order to respect C user expectations, the stack of the initial kernel thread, the main stack of the program, is used by the main user thread rather than the main processor, which can grow very large.
 \subsection{Context Switching}
 As mentioned in section \ref{coroutine}, coroutines are a stepping stone for implementing threading, because they share the same mechanism for context-switching between different stacks.
 To improve performance and simplicity, context-switching is implemented using the following assumption: all context-switches happen inside a specific function call.
+To improve performance and simplicity, context-switching is implemented using the following assumption: all context-switches happen inside a specific routine call.
 This assumption means that the context-switch only has to copy the callee-saved registers onto the stack and then switch the stack registers with the ones of the target coroutine/thread.
 Note that the instruction pointer can be left untouched since the context-switch is always inside the same function.
+Note that the instruction pointer can be left untouched since the context-switch is always inside the same routine
 Threads, however, do not context-switch between each other directly.
 They context-switch to the scheduler.
 …
 This option is not currently present in \CFA, but the changes required to add it are strictly additive.
 \subsection{Preemption} \label{preemption}
 Finally, an important aspect for any complete threading system is preemption.
 As mentioned in section \ref{basics}, preemption introduces an extra degree of uncertainty, which enables users to have multiple threads interleave transparently, rather than having to cooperate among threads for proper scheduling and CPU distribution.
 …
 As a result, a signal handler can start on one kernel thread and terminate on a second kernel thread (but the same user thread).
 It is important to note that signal handlers save and restore signal masks because user-thread migration can cause a signal mask to migrate from one kernel thread to another.
 This behaviour is only a problem if all kernel threads, among which a user thread can migrate, differ in terms of signal masks\footnote{Sadly, official POSIX documentation is silent on what distinguishes ``async-signal-safe'' functions from other functions.}.
+This behaviour is only a problem if all kernel threads, among which a user thread can migrate, differ in terms of signal masks\footnote{Sadly, official POSIX documentation is silent on what distinguishes ``async-signal-safe'' routines from other routines}.
 However, since the kernel thread handling preemption requires a different signal mask, executing user threads on the kernel-alarm thread can cause deadlocks.
 For this reason, the alarm thread is in a tight loop around a system call to @sigwaitinfo@, requiring very little CPU time for preemption.
 …
 Indeed, @sigwait@ can differentiate signals sent from @pthread_sigqueue@ from signals sent from alarms or the kernel.
 \subsection{Scheduler}
 Finally, an aspect that was not mentioned yet is the scheduling algorithm.
 …
 Further discussion on scheduling is present in section \ref{futur:sched}.
+% ======================================================================
+% ======================================================================
 \section{Internal Scheduling} \label{impl:intsched}
+% ======================================================================
+% ======================================================================
 The following figure is the traditional illustration of a monitor (repeated from page~\pageref{fig:ClassicalMonitor} for convenience):
 \begin{figure}
 \begin{center}
 {\resizebox{0.4\textwidth}{!}{\input{monitor}}}
+{\resizebox{0.4\textwidth}{!}{\input{monitor.pstex_t}}}
 \end{center}
 \caption{Traditional illustration of a monitor}
 …
 For \CFA, this picture does not have support for blocking multiple monitors on a single condition.
 To support \textbf{bulk-acq} two changes to this picture are required.
+To support bulk acquire two changes to this picture are required.
 First, it is no longer helpful to attach the condition to \emph{a single} monitor.
 Secondly, the thread waiting on the condition has to be separated across multiple monitors, seen in figure \ref{fig:monitor_cfa}.
 …
 \end{figure}
 The solution discussed in \ref{intsched} can be seen in the exit routine of listing \ref{f:entry2}.
+The solution discussed in \ref{s:InternalScheduling} can be seen in the exit routine of listing \ref{f:entry2}.
 Basically, the solution boils down to having a separate data structure for the condition queue and the AS-stack, and unconditionally transferring ownership of the monitors but only unblocking the thread when the last monitor has transferred ownership.
 This solution is deadlock safe as well as preventing any potential barging.
 …
+}
 \end{cfa}
 This function is called by the kernel to fetch the default preemption rate, where 0 signifies an infinite time-slice, \ie no preemption.
+This routine is called by the kernel to fetch the default preemption rate, where 0 signifies an infinite time-slice, \ie no preemption.
 However, once clusters are fully implemented, it will be possible to create fibers and \textbf{uthread} in the same system, as in listing \ref{f:fiber-uthread}
 \begin{figure}
 …
 For monitors, the simplest approach is to measure how long it takes to enter and leave a monitor routine.
 Figure~\ref{f:mutex} shows the code for \CFA.
 To put the results in context, the cost of entering a non-inline function and the cost of acquiring and releasing a @pthread_mutex@ lock is also measured.
+To put the results in context, the cost of entering a non-inline routine and the cost of acquiring and releasing a @pthread_mutex@ lock is also measured.
 The results can be shown in table \ref{tab:mutex}.
 …
 Therefore, there is still significant work to improve performance.
 Many of the data structures and algorithms may change in the future to more efficient versions.
 For example, the number of monitors in a single \textbf{bulk-acq} is only bound by the stack size, this is probably unnecessarily generous.
+For example, the number of monitors in a single bulk acquire is only bound by the stack size, this is probably unnecessarily generous.
 It may be possible that limiting the number helps increase performance.
 However, it is not obvious that the benefit would be significant.

doc/papers/concurrency/figures/ext_monitor.fig

-                      r97397a26
+                      rb21c77a
 -2
 2
 1 0 1 -1 -1 0 0 -1 0.000 0 1 0 0 3150.000 3450.000 3150 3150 2850 3450 3150 3750
 1 0 1 -1 -1 0 0 -1 0.000 0 1 0 0 3150.000 4350.000 3150 4050 2850 4350 3150 4650
 5850 1950 6150 2250
 3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 6000 2100 105 105 6000 2100 6105 2205
 1 -1 0 0 0 10 0.0000 2 105 90 6000 2160 d\001
+1 0 1 -1 -1 0 0 -1 0.000 0 1 0 0 1575.000 3450.000 1575 3150 1275 3450 1575 3750
+1 0 1 -1 -1 0 0 -1 0.000 0 1 0 0 1575.000 4350.000 1575 4050 1275 4350 1575 4650
+4275 1950 4575 2250
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 4425 2100 105 105 4425 2100 4530 2205
+1 -1 0 0 0 10 0.0000 2 105 90 4425 2160 d\001
 -6
 5100 2100 5400 2400
 3 0 1 -1 -1 1 0 4 0.000 1 0.0000 5250 2250 105 105 5250 2250 5355 2250
 1 -1 0 0 0 10 0.0000 2 105 120 5250 2295 X\001
+4275 1650 4575 1950
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 4425 1800 105 105 4425 1800 4530 1905
+1 -1 0 0 0 10 0.0000 2 105 90 4425 1860 b\001
 -6
+5100 1800 5400 2100
+3 0 1 -1 -1 1 0 4 0.000 1 0.0000 5250 1950 105 105 5250 1950 5355 1950
+1 -1 0 0 0 10 0.0000 2 105 120 5250 2010 Y\001
+1495 5445 5700 5655
+3 0 1 -1 -1 0 0 20 0.000 1 0.0000 1575 5550 80 80 1575 5550 1655 5630
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 2925 5550 105 105 2925 5550 3030 5655
+3 0 1 -1 -1 0 0 4 0.000 1 0.0000 4425 5550 105 105 4425 5550 4530 5655
+0 -1 0 0 0 12 0.0000 2 135 1035 3150 5625 blocked task\001
+0 -1 0 0 0 12 0.0000 2 135 870 1725 5625 active task\001
+0 -1 0 0 0 12 0.0000 2 135 1050 4650 5625 routine mask\001
 -6
+5850 1650 6150 1950
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 6000 1800 105 105 6000 1800 6105 1905
+1 -1 0 0 0 10 0.0000 2 105 90 6000 1860 b\001
+3525 1800 3825 2400
+3 0 1 -1 -1 1 0 4 0.000 1 0.0000 3675 1950 105 105 3675 1950 3780 1950
+2 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+1800 3825 1800 3825 2400 3525 2400 3525 1800
+1 4 0 0 0 10 0.0000 2 105 120 3675 2010 Y\001
 -6
+3070 5445 7275 5655
+3 0 1 -1 -1 0 0 20 0.000 1 0.0000 3150 5550 80 80 3150 5550 3230 5630
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 4500 5550 105 105 4500 5550 4605 5655
+3 0 1 -1 -1 0 0 4 0.000 1 0.0000 6000 5550 105 105 6000 5550 6105 5655
+0 -1 0 0 0 12 0.0000 2 135 1035 4725 5625 blocked task\001
+0 -1 0 0 0 12 0.0000 2 135 870 3300 5625 active task\001
+0 -1 0 0 0 12 0.0000 2 135 1050 6225 5625 routine mask\001
+3525 2100 3825 2400
+3 0 1 -1 -1 1 0 4 0.000 1 0.0000 3675 2250 105 105 3675 2250 3780 2250
+1 4 0 0 0 10 0.0000 2 105 120 3675 2295 X\001
 -6
 3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 3300 3600 105 105 3300 3600 3405 3705
 3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 3600 3600 105 105 3600 3600 3705 3705
 3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 6600 3900 105 105 6600 3900 6705 4005
 3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 6900 3900 105 105 6900 3900 7005 4005
 3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 6000 2700 105 105 6000 2700 6105 2805
 3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 6000 2400 105 105 6000 2400 6105 2505
 3 0 1 -1 -1 0 0 20 0.000 1 0.0000 5100 4575 80 80 5100 4575 5180 4655
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 1725 3600 105 105 1725 3600 1830 3705
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 2025 3600 105 105 2025 3600 2130 3705
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 5025 3900 105 105 5025 3900 5130 4005
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 5325 3900 105 105 5325 3900 5430 4005
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 4425 2700 105 105 4425 2700 4530 2805
+3 0 1 -1 -1 0 0 -1 0.000 1 0.0000 4425 2400 105 105 4425 2400 4530 2505
+3 0 1 -1 -1 0 0 20 0.000 1 0.0000 3525 4575 80 80 3525 4575 3605 4655
 2 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
 2925 5475 2925 5475 3225 4050 3225 4050 2925
+2925 3900 2925 3900 3225 2475 3225 2475 2925
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 4
 3750 3750 3750 3750 4050 3150 4050
+3750 2175 3750 2175 4050 1575 4050
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 3
 3450 3750 3450 3900 3675
+3450 2175 3450 2325 3675
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 2
 3150 3600 3375
+3150 2025 3375
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 3
 4350 3750 4350 3900 4575
+4350 2175 4350 2325 4575
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 2
 4050 3600 4275
+4050 2025 4275
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 4
 4650 3750 4650 3750 4950 4950 4950
+4650 2175 4650 2175 4950 3375 4950
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 2
 3750 6300 3975
+3750 4725 3975
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 2
 4950 5175 5100
+4950 3600 5100
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 9
 4950 6450 4950 6450 4050 7050 4050 7050 3750 6450 3750
 2850 6150 2850 6150 1650
+4950 4875 4950 4875 4050 5475 4050 5475 3750 4875 3750
+2850 4575 2850 4575 1650
 2 1 1 -1 -1 0 0 -1 4.000 0 0 0 0 0 5
 4200 5850 3300 4350 3300 4350 4200 5850 4200
 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 1 1 2
+4200 4275 3300 2775 3300 2775 4200 4275 4200
+1 0 1 0 7 50 -1 -1 0.000 0 0 -1 1 0 2
 1 1.00 60.00 120.00
+1 1.00 60.00 120.00
+3150 5250 2400
+3075 3675 2400
+1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
+2850 4575 3000
 1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+3150 3750 3150 3750 2850 5700 2850 5700 1650
+1 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 2
+2850 6150 3000
+2 0 1 0 7 50 -1 -1 0.000 0 0 -1 0 0 5
+1800 5400 1800 5400 2400 5100 2400 5100 1800
+1 -1 0 0 0 10 0.0000 2 75 75 6000 2745 a\001
+1 -1 0 0 0 10 0.0000 2 75 75 6000 2445 c\001
+1 -1 0 0 0 12 0.0000 2 135 315 5100 5325 exit\001
+1 -1 0 0 0 12 0.0000 2 135 135 3300 3075 A\001
+1 -1 0 0 0 12 0.0000 2 135 795 3300 4875 condition\001
+1 -1 0 0 0 12 0.0000 2 135 135 3300 5100 B\001
+0 -1 0 0 0 12 0.0000 2 135 420 6600 3675 stack\001
+0 -1 0 0 0 12 0.0000 2 180 750 6600 3225 acceptor/\001
+0 -1 0 0 0 12 0.0000 2 180 750 6600 3450 signalled\001
+1 -1 0 0 0 12 0.0000 2 135 795 3300 2850 condition\001
+1 -1 0 0 0 12 0.0000 2 165 420 6000 1350 entry\001
+1 -1 0 0 0 12 0.0000 2 135 495 6000 1575 queue\001
+0 -1 0 0 0 12 0.0000 2 135 525 6300 2400 arrival\001
+0 -1 0 0 0 12 0.0000 2 135 630 6300 2175 order of\001
+1 -1 0 0 0 12 0.0000 2 135 525 5100 3675 shared\001
+1 -1 0 0 0 12 0.0000 2 135 735 5100 3975 variables\001
+0 0 50 -1 0 11 0.0000 2 165 855 4275 3150 Acceptables\001
+0 0 50 -1 0 11 0.0000 2 120 165 5775 2700 W\001
+0 0 50 -1 0 11 0.0000 2 120 135 5775 2400 X\001
+0 0 50 -1 0 11 0.0000 2 120 105 5775 2100 Z\001
+0 0 50 -1 0 11 0.0000 2 120 135 5775 1800 Y\001
+3150 2175 3150 2175 2850 4125 2850 4125 1650
+1 -1 0 0 0 10 0.0000 2 75 75 4425 2745 a\001
+1 -1 0 0 0 10 0.0000 2 75 75 4425 2445 c\001
+1 -1 0 0 0 12 0.0000 2 135 315 3525 5325 exit\001
+1 -1 0 0 0 12 0.0000 2 135 135 1725 3075 A\001
+1 -1 0 0 0 12 0.0000 2 135 795 1725 4875 condition\001
+1 -1 0 0 0 12 0.0000 2 135 135 1725 5100 B\001
+0 -1 0 0 0 12 0.0000 2 135 420 5025 3675 stack\001
+0 -1 0 0 0 12 0.0000 2 180 750 5025 3225 acceptor/\001
+0 -1 0 0 0 12 0.0000 2 180 750 5025 3450 signalled\001
+1 -1 0 0 0 12 0.0000 2 135 795 1725 2850 condition\001
+1 -1 0 0 0 12 0.0000 2 165 420 4425 1350 entry\001
+1 -1 0 0 0 12 0.0000 2 135 495 4425 1575 queue\001
+0 -1 0 0 0 12 0.0000 2 135 525 4725 2400 arrival\001
+0 -1 0 0 0 12 0.0000 2 135 630 4725 2175 order of\001
+1 -1 0 0 0 12 0.0000 2 135 525 3525 3675 shared\001
+1 -1 0 0 0 12 0.0000 2 135 735 3525 3975 variables\001
+0 4 50 -1 0 11 0.0000 2 120 135 4150 1875 Y\001
+0 4 50 -1 0 11 0.0000 2 120 105 4150 2175 Z\001
+0 4 50 -1 0 11 0.0000 2 120 135 4150 2475 X\001
+0 4 50 -1 0 11 0.0000 2 120 165 4150 2775 W\001
+0 -1 0 0 3 12 0.0000 2 150 540 5025 4275 urgent\001
+1 0 50 -1 0 11 0.0000 2 165 600 3150 3150 accepted\001

doc/papers/concurrency/figures/monitor.fig

-                      r97397a26
+                      rb21c77a
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 4
 1500 3600 2100 4200 2100 4200 900
-1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 4
-1500 2700 2100 3300 2100 3300 1500
 1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 9
 4200 4800 4200 4800 3300 5400 3300 5400 3000 4800 3000
 …
 2 1 1 -1 -1 0 0 -1 4.000 0 0 0 0 0 5
 3450 4200 2550 2700 2550 2700 3450 4200 3450
+1 0 1 -1 -1 0 0 -1 0.000 0 0 -1 0 0 4
+1500 2700 2100 3300 2100 3300 1500
 1 -1 0 0 0 10 0.0000 2 75 75 4350 1995 a\001
 1 -1 0 0 0 10 0.0000 2 75 75 4350 1695 c\001
 …
 0 -1 0 0 0 12 0.0000 2 180 750 4950 2700 signalled\001
 1 -1 0 0 0 12 0.0000 2 135 795 1650 2100 condition\001
 1 -1 0 0 0 12 0.0000 2 135 135 2550 1425 X\001
 1 -1 0 0 0 12 0.0000 2 135 135 3450 1425 Y\001
+1 4 0 0 0 12 0.0000 2 135 135 2550 1425 X\001
+1 4 0 0 0 12 0.0000 2 135 135 3450 1425 Y\001
 1 -1 0 0 0 12 0.0000 2 165 420 4350 600 entry\001
 1 -1 0 0 0 12 0.0000 2 135 495 4350 825 queue\001
 …
 1 -1 0 0 0 10 0.0000 2 75 75 3450 1995 c\001
 1 -1 0 0 0 12 0.0000 2 135 570 3000 1200 queues\001
+0 -1 0 0 3 12 0.0000 2 150 540 4950 3525 urgent\001

doc/papers/general/Makefile

-                      r97397a26
+                      rb21c77a
         dvips ${Build}/$< -o $@
 ${BASE}.dvi : Makefile ${Build} ${BASE}.out.ps WileyNJD-AMA.bst ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
                 ../../bibliography/pl.bib
+${BASE}.dvi : Makefile ${BASE}.out.ps WileyNJD-AMA.bst ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
+                ../../bibliography/pl.bib | ${Build}
         # Must have *.aux file containing citations for bibtex
         if [ ! -r ${basename $@}.aux ] ; then ${LaTeX} ${basename $@}.tex ; fi
 …
         mkdir -p ${Build}
 ${BASE}.out.ps : ${Build}
+${BASE}.out.ps : | ${Build}
         ln -fs ${Build}/Paper.out.ps .
 …
         gnuplot -e Build="'${Build}/'" evaluation/timing.gp
 %.tex : %.fig ${Build}
+%.tex : %.fig | ${Build}
         fig2dev -L eepic $< > ${Build}/$@
 %.ps : %.fig ${Build}
+%.ps : %.fig | ${Build}
         fig2dev -L ps $< > ${Build}/$@
 %.pstex : %.fig ${Build}
+%.pstex : %.fig | ${Build}
         fig2dev -L pstex $< > ${Build}/$@
         fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t

doc/papers/general/Paper.tex

-                      r97397a26
+                      rb21c77a
 \abstract[Summary]{
 The C programming language is a foundational technology for modern computing with millions of lines of code implementing everything from commercial operating-systems to hobby projects.
+The C programming language is a foundational technology for modern computing with millions of lines of code implementing everything from hobby projects to commercial operating-systems.
 This installation base and the programmers producing it represent a massive software-engineering investment spanning decades and likely to continue for decades more.
 Nevertheless, C, first standardized almost forty years ago, lacks many features that make programming in more modern languages safer and more productive.
 …
 \section{Introduction}
 The C programming language is a foundational technology for modern computing with millions of lines of code implementing everything from commercial operating-systems to hobby projects.
+The C programming language is a foundational technology for modern computing with millions of lines of code implementing everything from hobby projects to commercial operating-systems.
 This installation base and the programmers producing it represent a massive software-engineering investment spanning decades and likely to continue for decades more.
 The TIOBE~\cite{TIOBE} ranks the top 5 most \emph{popular} programming languages as: Java 15\%, \Textbf{C 12\%}, \Textbf{\CC 5.5\%}, Python 5\%, \Csharp 4.5\% = 42\%, where the next 50 languages are less than 4\% each with a long tail.

doc/proposals/ctordtor/Makefile

-                      r97397a26
+                      rb21c77a
 ## Define the appropriate configuration variables.
+## Define the configuration variables.
+MACROS = ../../LaTeXmacros
+BIB = ../../bibliography
+Build = build
+Figures = figures
+Macros = ../../LaTeXmacros
+Bib = ../../bibliography
 TeXLIB = .:$(MACROS):$(MACROS)/listings:$(MACROS)/enumitem:$(BIB)/:
 LaTeX  = TEXINPUTS=${TeXLIB} && export TEXINPUTS && latex -halt-on-error
+TeXLIB = .:${Macros}:${MACROS}/listings:${MACROS}/enumitem:${Bib}/:
+LaTeX  = TEXINPUTS=${TeXLIB} && export TEXINPUTS && latex -halt-on-error -output-directory=${Build}
 BibTeX = BIBINPUTS=${TeXLIB} && export BIBINPUTS && bibtex
+MAKEFLAGS = --no-print-directory # --silent
+VPATH = ${Build} ${Figures}
 ## Define the text source files.
 …
 DOCUMENT = ctor.pdf
+BASE = ${basename ${DOCUMENT}}
 # Directives #
+.PHONY : all clean                                      # not file names
 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}
+        @rm -frv ${DOCUMENT} ${BASE}.ps ${Build}
 # File Dependencies #
 ${DOCUMENT} : ${basename ${DOCUMENT}}.ps
+${DOCUMENT} : ${BASE}.ps
         ps2pdf $<
 ${basename ${DOCUMENT}}.ps : ${basename ${DOCUMENT}}.dvi
         dvips $< -o $@
+${BASE}.ps : ${BASE}.dvi
+        dvips ${Build}/$< -o $@
 ${basename ${DOCUMENT}}.dvi : Makefile ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} ${basename ${DOCUMENT}}.tex \
                 $(MACROS)/common.tex $(MACROS)/indexstyle $(BIB)/cfa.bib
+${BASE}.dvi : Makefile ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
+                ${Macros}/common.tex ${Macros}/indexstyle ${Bib}/pl.bib | ${Build}
         # Conditionally create an empty *.ind (index) file for inclusion until makeindex is run.
         if [ ! -r ${basename $@}.ind ] ; then touch ${basename $@}.ind ; fi
+        #if [ ! -r ${basename $@}.ind ] ; then touch ${Build}/${basename $@}.ind ; fi
         # Must have *.aux file containing citations for bibtex
         if [ ! -r ${basename $@}.aux ] ; then ${LaTeX} ${basename $@}.tex ; fi
         -${BibTeX} ${basename $@}
         # Some citations reference others so run steps again to resolve these citations
+        -${BibTeX} ${Build}/${basename $@}
+        # Some citations reference others so run again to resolve these citations
         ${LaTeX} ${basename $@}.tex
         -${BibTeX} ${basename $@}
+        -${BibTeX} ${Build}/${basename $@}
         # Make index from *.aux entries and input index at end of document
+        makeindex -s $(MACROS)/indexstyle ${basename $@}.idx
+        #makeindex -s ${Macros}/indexstyle ${Build}/${basename $@}.idx
+        # Run again to finish citations
         ${LaTeX} ${basename $@}.tex
         # Run again to get index title into table of contents
 …
 ## Define the default recipes.
+%.tex : %.fig
         fig2dev -L eepic $< > $@
+${Build}:
+        mkdir -p ${Build}
 %.ps : %.fig
         fig2dev -L ps $< > $@
+%.tex : %.fig | ${Build}
+        fig2dev -L eepic $< > ${Build}/$@
+%.pstex : %.fig
+        fig2dev -L pstex $< > $@
+        fig2dev -L pstex_t -p $@ $< > $@_t
+%.ps : %.fig | ${Build}
+        fig2dev -L ps $< > ${Build}/$@
+%.pstex : %.fig | ${Build}
+        fig2dev -L pstex $< > ${Build}/$@
+        fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t
 # Local Variables: #

doc/proposals/ctordtor/ctor.tex

-                      r97397a26
+                      rb21c77a
-% 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}
 …
 \usepackage{textcomp}
 \usepackage[latin1]{inputenc}
 \usepackage{fullpage,times,comment}
 \usepackage{epic,eepic}
 \usepackage{upquote}                                                                    % switch curled `'" to straight
+\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{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"
 …
 \renewcommand{\UrlFont}{\small\sf}
 \setlength{\topmargin}{-0.45in}                                                 % move running title into header
+\setlength{\topmargin}{-0.45in}                         % move running title into header
 \setlength{\headsep}{0.25in}
 …
 \interfootnotelinepenalty=10000
+\CFAStyle                                               % use default CFA format-style
+% 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)
 \title{
 …
 \thispagestyle{plain}
 \pagenumbering{arabic}

doc/proposals/tuples/Makefile

-                      r97397a26
+                      rb21c77a
 ## Define the appropriate configuration variables.
+## Define the configuration variables.
+MACROS = ../../LaTeXmacros
+BIB = ../../bibliography
+Build = build
+Figures = figures
+Macros = ../../LaTeXmacros
+Bib = ../../bibliography
 TeXLIB = .:$(MACROS):$(MACROS)/listings:$(MACROS)/enumitem:$(BIB)/:
 LaTeX  = TEXINPUTS=${TeXLIB} && export TEXINPUTS && latex -halt-on-error
+TeXLIB = .:${Macros}:${MACROS}/listings:${MACROS}/enumitem:${Bib}/:
+LaTeX  = TEXINPUTS=${TeXLIB} && export TEXINPUTS && latex -halt-on-error -output-directory=${Build}
 BibTeX = BIBINPUTS=${TeXLIB} && export BIBINPUTS && bibtex
+MAKEFLAGS = --no-print-directory --silent #
+VPATH = ${Build} ${Figures}
 ## Define the text source files.
 …
 DOCUMENT = tuples.pdf
+BASE = ${basename ${DOCUMENT}}
 # Directives #
+.PHONY : all clean                                      # not file names
 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}
+        @rm -frv ${DOCUMENT} ${BASE}.ps ${Build}
 # File Dependencies #
 ${DOCUMENT} : ${basename ${DOCUMENT}}.ps
+${DOCUMENT} : ${BASE}.ps
         ps2pdf $<
 ${basename ${DOCUMENT}}.ps : ${basename ${DOCUMENT}}.dvi
         dvips $< -o $@
+${BASE}.ps : ${BASE}.dvi
+        dvips ${Build}/$< -o $@
 ${basename ${DOCUMENT}}.dvi : Makefile ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} ${basename ${DOCUMENT}}.tex \
                 $(MACROS)/common.tex $(MACROS)/indexstyle $(BIB)/cfa.bib
+${BASE}.dvi : Makefile ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
+                ${Macros}/common.tex ${Macros}/indexstyle ${Bib}/pl.bib | ${Build}
         # Conditionally create an empty *.ind (index) file for inclusion until makeindex is run.
         if [ ! -r ${basename $@}.ind ] ; then touch ${basename $@}.ind ; fi
+        #if [ ! -r ${basename $@}.ind ] ; then touch ${Build}/${basename $@}.ind ; fi
         # Must have *.aux file containing citations for bibtex
         if [ ! -r ${basename $@}.aux ] ; then ${LaTeX} ${basename $@}.tex ; fi
         -${BibTeX} ${basename $@}
         # Some citations reference others so run steps again to resolve these citations
+        -${BibTeX} ${Build}/${basename $@}
+        # Some citations reference others so run again to resolve these citations
         ${LaTeX} ${basename $@}.tex
         -${BibTeX} ${basename $@}
+        -${BibTeX} ${Build}/${basename $@}
         # Make index from *.aux entries and input index at end of document
+        makeindex -s $(MACROS)/indexstyle ${basename $@}.idx
+        #makeindex -s ${Macros}/indexstyle ${Build}/${basename $@}.idx
+        # Run again to finish citations
         ${LaTeX} ${basename $@}.tex
         # Run again to get index title into table of contents
 …
 ## Define the default recipes.
+%.tex : %.fig
         fig2dev -L eepic $< > $@
+${Build}:
+        mkdir -p ${Build}
 %.ps : %.fig
         fig2dev -L ps $< > $@
+%.tex : %.fig | ${Build}
+        fig2dev -L eepic $< > ${Build}/$@
+%.pstex : %.fig
+        fig2dev -L pstex $< > $@
+        fig2dev -L pstex_t -p $@ $< > $@_t
+%.ps : %.fig | ${Build}
+        fig2dev -L ps $< > ${Build}/$@
+%.pstex : %.fig | ${Build}
+        fig2dev -L pstex $< > ${Build}/$@
+        fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t
 # Local Variables: #

doc/proposals/tuples/tuples.tex

-                      r97397a26
+                      rb21c77a
-% 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}
 …
 \usepackage{textcomp}
 \usepackage[latin1]{inputenc}
 \usepackage{fullpage,times,comment}
 \usepackage{epic,eepic}
 \usepackage{upquote}                                                                    % switch curled `'" to straight
+\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{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"
 …
 \renewcommand{\UrlFont}{\small\sf}
 \setlength{\topmargin}{-0.45in}                                                 % move running title into header
+\setlength{\topmargin}{-0.45in}                         % move running title into header
 \setlength{\headsep}{0.25in}
 …
 \interfootnotelinepenalty=10000
+\CFAStyle                                               % use default CFA format-style
+% 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)
 \title{

doc/proposals/user_conversions.md

-                      r97397a26
+                      rb21c77a
 There is also a set of _explicit_ conversions that are only allowed through a
 cast expression.
+Based on Glen's notes on conversions [1], I propose that safe and unsafe
+conversions be expressed as constructor variants, though I make explicit
+(cast) conversions a constructor variant as well rather than a dedicated
+operator.
+I propose that safe, unsafe, and explicit (cast) conversions be expressed as
+constructor variants.
 Throughout this article, I will use the following operator names for
 constructors and conversion functions from `From` to `To`:
+        void ?{} ( To*, To );            // copy constructor
+        void ?{} ( To*, From );          // explicit constructor
+        void ?{explicit} ( To*, From );  // explicit cast conversion
+        void ?{safe} ( To*, From );      // implicit safe conversion
+        void ?{unsafe} ( To*, From );    // implicit unsafe conversion
+[1] http://plg.uwaterloo.ca/~cforall/Conversions/index.html
+Glen's design made no distinction between constructors and unsafe implicit
+        void ?{} ( To&, To );            // copy constructor
+        void ?{} ( To&, From );          // explicit constructor
+        void ?{explicit} ( To&, From );  // explicit cast conversion
+        void ?{safe} ( To&, From );      // implicit safe conversion
+        void ?{unsafe} ( To&, From );    // implicit unsafe conversion
+It has been suggested that all constructors would define unsafe implicit
 conversions; this is elegant, but interacts poorly with tuples.
 Essentially, without making this distinction, a constructor like the following
 …
 multiplying the space of possible interpretations of all functions:
         void ?{}( Coord *this, int x, int y );
+        void ?{}( Coord& this, int x, int y );
 That said, it would certainly be possible to make a multiple-argument implicit
 …
 used infrequently:
         void ?{unsafe}( Coord *this, int x, int y );
+        void ?{unsafe}( Coord& this, int x, int y );
 An alternate possibility would be to only count two-arg constructors
 `void ?{} ( To*, From )` as unsafe conversions; under this semantics, safe and
+`void ?{} ( To&, From )` as unsafe conversions; under this semantics, safe and
 explicit conversions should also have a compiler-enforced restriction to
 ensure that they are two-arg functions (this restriction may be valuable
 …
 is convertable to `To`.
 If user-defined conversions are not added to the language,
 `void ?{} ( To*, From )` may be a suitable representation, relying on
+`void ?{} ( To&, From )` may be a suitable representation, relying on
 conversions on the argument types to account for transitivity.
+On the other hand, `To*` should perhaps match its target type exactly, so
+another assertion syntax specific to conversions may be required, e.g.
+`From -> To`.
+Since `To&` should be an exact match on `To`, this should put all the implicit
+conversions on the RHS.
+On the other hand, under some models (like [1]), implicit conversions are not
+allowed in assertion parameters, so another assertion syntax specific to
+conversions may be required, e.g. `From -> To`.
+It has also been suggested that, for programmer control, no implicit
+conversions (except, possibly, for polymorphic specialization) should be
+allowed in resolution of cast operators.
+[1] ../working/assertion_resolution.md
 ### Constructor Idiom ###
 …
 that we can use the full range of Cforall features for conversions, including
 polymorphism.
+Glen [1] defines a _constructor idiom_ that can be used to create chains of
+safe conversions without duplicating code; given a type `Safe` which members
+of another type `From` can be directly converted to, the constructor idiom
+allows us to write a conversion for any type `To` which `Safe` converts to:
+        forall(otype To | { void ?{safe}( To*, Safe ) })
+        void ?{safe}( To *this, From that ) {
+In an earlier version of this proposal, Glen Ditchfield defines a
+_constructor idiom_ that can be used to create chains of safe conversions
+without duplicating code; given a type `Safe` which members of another type
+`From` can be directly converted to, the constructor idiom allows us to write
+a conversion for any type `To` which `Safe` converts to:
+        forall(otype To | { void ?{safe}( To&, Safe ) })
+        void ?{safe}( To& this, From that ) {
                 Safe tmp = /* some expression involving that */;
                 *this = tmp; // uses assertion parameter
+                this{ tmp }; // initialize from assertion parameter
+        }
 …
 unsafe conversions.
+Glen's original suggestion said the copy constructor for `To` should also be
+accepted as a resolution for `void ?{safe}( To&, Safe )` (`Safe` == `To`),
+allowing this same code to be used for the single-step conversion as well.
+This proposal does come at the cost of an extra copy initialization of the
+target value, though.
+Contrariwise, if a monomorphic conversion from `From` to `Safe` is written,
+e.g:
+        void ?{safe}( Safe& this, From that ) {
+                this{ /* some parameters involving that */ };
+        }
+Then the code for a transitive conversion from `From` to any `To` type
+convertable from `Safe` is written:
+        forall(otype To | { void ?{safe}( To&, Safe ) })
+        void ?{safe}( To& this, From that ) {
+                Safe tmp = that;  // uses monomorphic conversion
+                this{ tmp };      // initialize from assertion parameter
+        }
+Given the entirely-boilerplate nature of this code, but negative performance
+implications of the unmodified constructor idiom, it might be fruitful to have
+transitive and single step conversion operators, and let CFA build the
+transitive conversions; some possible names:
+        void ?{safe}  (To&, From);    void ?{final safe} (To&, From);  // single-step
+        void ?{safe*} (To&, From);    void ?{safe}       (To&, From);  // transitive
 What selective non-use of the constructor idiom gives us is the ability to
 define a conversion that may only be the *last* conversion in a chain of such.
+Constructing a conversion graph able to unambiguously represent the full
+hierarchy of implicit conversions in C is provably impossible using only
+single-step conversions with no additional information (see Appendix A), but
+this mechanism is sufficiently powerful (see [1], though the design there has
+some minor bugs; the general idea is to use the constructor idiom to define
+two chains of conversions, one among the signed integral types, another among
+the unsigned, and to use monomorphic conversions to allow conversions between
+signed and unsigned integer types).
+One use for this is to solve the problem that `explicit` conversions were
+added to C++ for, that of conversions to `bool` chaining to become conversions
+to any arithmetic type.
+Another use is to unambiguously represent the full hierarchy of implicit
+conversions in C by making sign conversions non-transitive, allowing the
+compiler to resolve e.g. `int -> unsigned long` as
+`int -> long -> unsigned long` over `int -> unsigned int -> unsigned long`.
+See [2] for more details.
+[2] ../working/glen_conversions/index.html#usual
 ### Appendix A: Partial and Total Orders ###
 …
 convert from `int` to `unsigned long`, so we just put in a direct conversion
 and make the compiler smart enough to figure out the costs" - this is the
 approach taken by the existing compipler, but given that in a user-defined
+approach taken by the existing compiler, but given that in a user-defined
 conversion proposal the users can build an arbitrary graph of conversions,
 this case still needs to be handled.
 …
 exists a chain of conversions from `a` to `b` (see Appendix A for description
 of preorders and related constructs).
 This preorder corresponds roughly to a more usual type-theoretic concept of
+This preorder roughly corresponds to a more usual type-theoretic concept of
 subtyping ("if I can convert `a` to `b`, `a` is a more specific type than
 `b`"); however, since this graph is arbitrary, it may contain cycles, so if
 …
 and so is considered to be the nearer type.
 By transitivity, then, the conversion from `X` to `Y2` should be cheaper than
 the conversion from `X` to `W`, but in this case the `X` and `W` are
+the conversion from `X` to `W`, but in this case the `Y2` and `W` are
 incomparable by the conversion preorder, so the tie is broken by the shorter
 path from `X` to `W` in favour of `W`, contradicting the transitivity property

doc/refrat/Makefile

-                      r97397a26
+                      rb21c77a
         dvips ${Build}/$< -o $@
 ${BASE}.dvi : Makefile ${Build} ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
                 ${Macros}/common.tex ${Macros}/lstlang.sty ${Macros}/indexstyle ../bibliography/pl.bib
+${BASE}.dvi : Makefile ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
+                ${Macros}/common.tex ${Macros}/lstlang.sty ${Macros}/indexstyle ../bibliography/pl.bib | ${Build}
         # Conditionally create an empty *.ind (index) file for inclusion until makeindex is run.
         if [ ! -r ${basename $@}.ind ] ; then touch ${Build}/${basename $@}.ind ; fi
 …
         mkdir -p ${Build}
 %.tex : %.fig ${Build}
+%.tex : %.fig | ${Build}
         fig2dev -L eepic $< > ${Build}/$@
 %.ps : %.fig ${Build}
+%.ps : %.fig | ${Build}
         fig2dev -L ps $< > ${Build}/$@
 %.pstex : %.fig ${Build}
+%.pstex : %.fig | ${Build}
         fig2dev -L pstex $< > ${Build}/$@
         fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t

doc/theses/aaron_moss/comp_II/Makefile

-                      r97397a26
+                      rb21c77a
 DOCUMENT = comp_II.pdf
+BASE = ${basename ${DOCUMENT}}
 # Directives #
 …
 clean :
         @rm -frv ${DOCUMENT} ${basename ${DOCUMENT}}.ps ${Build}
+        @rm -frv ${DOCUMENT} ${BASE}.ps ${Build}
 # File Dependencies #
 ${DOCUMENT} : ${basename ${DOCUMENT}}.ps
+${DOCUMENT} : ${BASE}.ps
         ps2pdf $<
 ${basename ${DOCUMENT}}.ps : ${basename ${DOCUMENT}}.dvi
+${BASE}.ps : ${BASE}.dvi
         dvips ${Build}/$< -o $@
 ${basename ${DOCUMENT}}.dvi : Makefile ${Build} ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
                 ${Macros}/common.tex ${Macros}/indexstyle ../../../bibliography/pl.bib
+${BASE}.dvi : Makefile ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
+                ${Macros}/common.tex ${Macros}/indexstyle ../../../bibliography/pl.bib | ${Build}
         # Must have *.aux file containing citations for bibtex
         if [ ! -r ${basename $@}.aux ] ; then ${LaTeX} ${basename $@}.tex ; fi
 …
         mkdir -p ${Build}
 %.tex : %.fig
+%.tex : %.fig ${Build}
         fig2dev -L eepic $< > ${Build}/$@
 %.ps : %.fig
+%.ps : %.fig | ${Build}
         fig2dev -L ps $< > ${Build}/$@
 %.pstex : %.fig
+%.pstex : %.fig | ${Build}
         fig2dev -L pstex $< > ${Build}/$@
         fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t

doc/theses/thierry_delisle/.gitignore

r97397a26	rb21c77a
25	25	*.pdf
26	26	*.png
	27	*.ps
27	28	figures/*.tex
28	29

doc/theses/thierry_delisle/Makefile

-                      r97397a26
+                      rb21c77a
 DOCUMENT = thesis.pdf
+BASE = ${basename ${DOCUMENT}}
 # Directives #
 …
 clean :
         @rm -frv ${DOCUMENT} ${basename ${DOCUMENT}}.ps ${Build}
+        @rm -frv ${DOCUMENT} ${BASE}.ps ${Build}
 # File Dependencies #
 ${DOCUMENT} : ${basename ${DOCUMENT}}.ps
+${DOCUMENT} : ${BASE}.ps
         ps2pdf $<
 ${basename ${DOCUMENT}}.ps : ${basename ${DOCUMENT}}.dvi
+${BASE}.ps : ${BASE}.dvi
         dvips ${Build}/$< -o $@
 ${basename ${DOCUMENT}}.dvi : Makefile ${Build} ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
                 ${Macros}/common.tex ${Macros}/indexstyle annex/local.bib ../../bibliography/pl.bib
+${BASE}.dvi : Makefile ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
+                ${Macros}/common.tex ${Macros}/indexstyle annex/local.bib ../../bibliography/pl.bib | ${Build}
         # Must have *.aux file containing citations for bibtex
         if [ ! -r ${basename $@}.aux ] ; then ${LaTeX} ${basename $@}.tex ; fi
 …
         mkdir -p ${Build}
 %.tex : %.fig
+%.tex : %.fig ${Build}
         fig2dev -L eepic $< > ${Build}/$@
 %.ps : %.fig
+%.ps : %.fig | ${Build}
         fig2dev -L ps $< > ${Build}/$@
 %.pstex : %.fig
+%.pstex : %.fig | ${Build}
         fig2dev -L pstex $< > ${Build}/$@
         fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t
 …
 # Tools to generate png files
 # to create a png we create a pdf and convert it to png
 %.png : build/%.pstex figures/%.tex
+%.png : build/%.pstex figures/%.tex ${Build}
         echo ${basename $@}
         ${LaTeX} figures/${basename $@}.tex
 …
 # creating a pdf of a figure requires generating some latex that just includes the figure
 figures/%.tex: build/%.pstex
+figures/%.tex: build/%.pstex ${Build}
         echo -n         "\documentclass[preview]{standalone}\n"         \
                         "\usepackage[T1]{fontenc}\n"                    \

doc/user/Makefile

-                      r97397a26
+                      rb21c77a
         dvips ${Build}/$< -o $@
 ${BASE}.dvi : Makefile ${Build} ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
                 ${Macros}/common.tex ${Macros}/lstlang.sty ${Macros}/indexstyle ../bibliography/pl.bib
+${BASE}.dvi : Makefile ${GRAPHS} ${PROGRAMS} ${PICTURES} ${FIGURES} ${SOURCES} \
+                ${Macros}/common.tex ${Macros}/lstlang.sty ${Macros}/indexstyle ../bibliography/pl.bib | ${Build}
         # Conditionally create an empty *.ind (index) file for inclusion until makeindex is run.
         if [ ! -r ${basename $@}.ind ] ; then touch ${Build}/${basename $@}.ind ; fi
 …
         mkdir -p ${Build}
 %.tex : %.fig ${Build}
+%.tex : %.fig | ${Build}
         fig2dev -L eepic $< > ${Build}/$@
 %.ps : %.fig ${Build}
+%.ps : %.fig | ${Build}
         fig2dev -L ps $< > ${Build}/$@
 %.pstex : %.fig ${Build}
+%.pstex : %.fig | ${Build}
         fig2dev -L pstex $< > ${Build}/$@
         fig2dev -L pstex_t -p ${Build}/$@ $< > ${Build}/$@_t

src/CodeGen/CodeGenerator.cc

-                      r97397a26
+                      rb21c77a
                 output << "__attribute__ ((";
                 for ( list< Attribute * >::iterator attr( attributes.begin() );; ) {
                         output << (*attr)->get_name();
                         if ( ! (*attr)->get_parameters().empty() ) {
+                        output << (*attr)->name;
+                        if ( ! (*attr)->parameters.empty() ) {
                                 output << "(";
                                 genCommaList( (*attr)->get_parameters().begin(), (*attr)->get_parameters().end() );
+                                genCommaList( (*attr)->parameters.begin(), (*attr)->parameters.end() );
                                 output << ")";
                         } // if
 …
         // *** Declarations
         void CodeGenerator::postvisit( FunctionDecl * functionDecl ) {
+                // deleted decls should never be used, so don't print them
+                if ( functionDecl->isDeleted && genC ) return;
                 extension( functionDecl );
                 genAttributes( functionDecl->get_attributes() );
 …
                         functionDecl->get_statements()->accept( *visitor );
                 } // if
+                if ( functionDecl->isDeleted ) {
+                        output << " = void";
+                }
+        }
         void CodeGenerator::postvisit( ObjectDecl * objectDecl ) {
+                // deleted decls should never be used, so don't print them
+                if ( objectDecl->isDeleted && genC ) return;
                 if (objectDecl->get_name().empty() && genC ) {
                         // only generate an anonymous name when generating C code, otherwise it clutters the output too much
 …
                         objectDecl->get_init()->accept( *visitor );
                 } // if
+                if ( objectDecl->isDeleted ) {
+                        output << " = void";
+                }
                 if ( objectDecl->get_bitfieldWidth() ) {
 …
                 expr->expr->accept( *visitor );
+        }
+        void CodeGenerator::postvisit( DefaultArgExpr * arg ) {
+                assertf( ! genC, "Default argument expressions should not reach code generation." );
+                arg->expr->accept( *visitor );
+        }
+        void CodeGenerator::postvisit( GenericExpr * expr ) {
+                assertf( ! genC, "C11 _Generic expressions should not reach code generation." );
+                output << "_Generic(";
+                expr->control->accept( *visitor );
+                output << ", ";
+                unsigned int numAssocs = expr->associations.size();
+                unsigned int i = 0;
+                for ( GenericExpr::Association & assoc : expr->associations ) {
+                        if (assoc.isDefault) {
+                                output << "default: ";
+                        } else {
+                                output << genType( assoc.type, "", pretty, genC ) << ": ";
+                        }
+                        assoc.expr->accept( *visitor );
+                        if ( i+1 != numAssocs ) {
+                                output << ", ";
+                        }
+                        i++;
+                }
+                output << ")";
+        }
         // *** Statements

src/CodeGen/CodeGenerator.h

r97397a26	rb21c77a
94	94	void postvisit( ConstructorExpr * );
95	95	void postvisit( DeletedExpr * );
	96	void postvisit( DefaultArgExpr * );
	97	void postvisit( GenericExpr * );
96	98
97	99	//*** Statements

src/Common/Debug.h

r97397a26	rb21c77a
28	28	namespace Debug {
29	29	/// debug codegen a translation unit
30		static inline void codeGen( __attribute__((unused)) const std::list< Declaration * > & translationUnit, __attribute__((unused)) const std::string & label, __attribute__((unused)) LinkageSpec::Spec linkageFilter = LinkageSpec::~~Compiler~~ ) {
	30	static inline void codeGen( __attribute__((unused)) const std::list< Declaration * > & translationUnit, __attribute__((unused)) const std::string & label, __attribute__((unused)) LinkageSpec::Spec linkageFilter = LinkageSpec::Builtin ) {
31	31	#ifdef DEBUG
32	32	std::list< Declaration * > decls;

src/Common/PassVisitor.h

-                      r97397a26
+                      rb21c77a
         virtual void visit( InitExpr *  initExpr ) override final;
         virtual void visit( DeletedExpr *  delExpr ) override final;
+        virtual void visit( DefaultArgExpr * argExpr ) override final;
+        virtual void visit( GenericExpr * genExpr ) override final;
         virtual void visit( VoidType * basicType ) override final;
 …
         virtual Expression * mutate( InitExpr *  initExpr ) override final;
         virtual Expression * mutate( DeletedExpr *  delExpr ) override final;
+        virtual Expression * mutate( DefaultArgExpr * argExpr ) override final;
+        virtual Expression * mutate( GenericExpr * genExpr ) override final;
         virtual Type * mutate( VoidType * basicType ) override final;
 …
 private:
+        bool inFunction = false;
         template<typename pass_t> friend void acceptAll( std::list< Declaration* > &decls, PassVisitor< pass_t >& visitor );
         template<typename pass_t> friend void mutateAll( std::list< Declaration* > &decls, PassVisitor< pass_t >& visitor );
 …
         void indexerAddUnionFwd ( UnionDecl                 * node  ) { indexer_impl_addUnionFwd ( pass, 0, node ); }
         void indexerAddTrait    ( TraitDecl                 * node  ) { indexer_impl_addTrait    ( pass, 0, node ); }
         void indexerAddWith     ( std::list< Expression * > & exprs, BaseSyntaxNode * withStmt ) { indexer_impl_addWith     ( pass, 0, exprs, withStmt ); }
+        void indexerAddWith     ( std::list< Expression * > & exprs, BaseSyntaxNode * withStmt ) { indexer_impl_addWith( pass, 0, exprs, withStmt ); }

src/Common/PassVisitor.impl.h

-                      r97397a26
+                      rb21c77a
                         indexerAddId( func );
                         maybeAccept_impl( node->type, *this );
+                        // function body needs to have the same scope as parameters - CompoundStmt will not enter
+                        // a new scope if inFunction is true
+                        ValueGuard< bool > oldInFunction( inFunction );
+                        inFunction = true;
                         maybeAccept_impl( node->statements, *this );
                         maybeAccept_impl( node->attributes, *this );
 …
                         indexerAddId( func );
                         maybeMutate_impl( node->type, *this );
+                        // function body needs to have the same scope as parameters - CompoundStmt will not enter
+                        // a new scope if inFunction is true
+                        ValueGuard< bool > oldInFunction( inFunction );
+                        inFunction = true;
                         maybeMutate_impl( node->statements, *this );
                         maybeMutate_impl( node->attributes, *this );
 …
         VISIT_START( node );
+        {
+                auto guard1 = makeFuncGuard( [this]() { indexerScopeEnter(); }, [this]() { indexerScopeLeave(); } );
+                // do not enter a new scope if inFunction is true - needs to check old state before the assignment
+                ValueGuard< bool > oldInFunction( inFunction );
+                auto guard1 = makeFuncGuard( [this, &oldInFunction]() { if ( ! oldInFunction.old ) indexerScopeEnter(); }, [this, &oldInFunction]() { if ( ! oldInFunction.old ) indexerScopeLeave(); } );
                 auto guard2 = makeFuncGuard( [this]() { call_beginScope();   }, [this]() { call_endScope();     } );
+                inFunction = false;
                 visitStatementList( node->kids );
+        }
 …
         MUTATE_START( node );
+        {
+                auto guard1 = makeFuncGuard( [this]() { indexerScopeEnter(); }, [this]() { indexerScopeLeave(); } );
+                // do not enter a new scope if inFunction is true - needs to check old state before the assignment
+                ValueGuard< bool > oldInFunction( inFunction );
+                auto guard1 = makeFuncGuard( [this, &oldInFunction]() { if ( ! oldInFunction.old ) indexerScopeEnter(); }, [this, &oldInFunction]() { if ( ! oldInFunction.old ) indexerScopeLeave(); } );
                 auto guard2 = makeFuncGuard( [this]() { call_beginScope();   }, [this]() { call_endScope();     } );
+                inFunction = false;
                 mutateStatementList( node->kids );
+        }
 …
         VISIT_START( node );
+        visitExpression( node->condition );
+        node->body = visitStatement( node->body );
+        {
+                // while statements introduce a level of scope (for the initialization)
+                auto guard = makeFuncGuard( [this]() { indexerScopeEnter(); }, [this]() { indexerScopeLeave(); } );
+                maybeAccept_impl( node->initialization, *this );
+                visitExpression ( node->condition );
+                node->body = visitStatement( node->body );
+        }
         VISIT_END( node );
 …
         MUTATE_START( node );
+        node->condition = mutateExpression( node->condition );
+        node->body      = mutateStatement ( node->body      );
+        {
+                // while statements introduce a level of scope (for the initialization)
+                auto guard = makeFuncGuard( [this]() { indexerScopeEnter(); }, [this]() { indexerScopeLeave(); } );
+                maybeMutate_impl( node->initialization, *this );
+                node->condition = mutateExpression( node->condition );
+                node->body      = mutateStatement ( node->body      );
+        }
         MUTATE_END( Statement, node );
 …
 //--------------------------------------------------------------------------
+// DefaultArgExpr
+template< typename pass_type >
+void PassVisitor< pass_type >::visit( DefaultArgExpr * node ) {
+        VISIT_START( node );
+        indexerScopedAccept( node->result, *this );
+        maybeAccept_impl( node->expr, *this );
+        VISIT_END( node );
+}
+template< typename pass_type >
+Expression * PassVisitor< pass_type >::mutate( DefaultArgExpr * node ) {
+        MUTATE_START( node );
+        indexerScopedMutate( node->env, *this );
+        indexerScopedMutate( node->result, *this );
+        maybeMutate_impl( node->expr, *this );
+        MUTATE_END( Expression, node );
+}
+//--------------------------------------------------------------------------
+// GenericExpr
+template< typename pass_type >
+void PassVisitor< pass_type >::visit( GenericExpr * node ) {
+        VISIT_START( node );
+        indexerScopedAccept( node->result, *this );
+        maybeAccept_impl( node->control, *this );
+        for ( GenericExpr::Association & assoc : node->associations ) {
+                indexerScopedAccept( assoc.type, *this );
+                maybeAccept_impl( assoc.expr, *this );
+        }
+        VISIT_END( node );
+}
+template< typename pass_type >
+Expression * PassVisitor< pass_type >::mutate( GenericExpr * node ) {
+        MUTATE_START( node );
+        indexerScopedMutate( node->env, *this );
+        indexerScopedMutate( node->result, *this );
+        maybeMutate_impl( node->control, *this );
+        for ( GenericExpr::Association & assoc : node->associations ) {
+                indexerScopedMutate( assoc.type, *this );
+                maybeMutate_impl( assoc.expr, *this );
+        }
+        MUTATE_END( Expression, node );
+}
+//--------------------------------------------------------------------------
 // VoidType
 template< typename pass_type >

src/Common/SemanticError.cc

-                      r97397a26
+                      rb21c77a
 // Created On       : Mon May 18 07:44:20 2015
 // Last Modified By : Peter A. Buhr
 // Last Modified On : Wed May 16 15:01:20 2018
 // Update Count     : 9
+// Last Modified On : Thu Jun  7 08:05:26 2018
+// Update Count     : 10
 //
 …
 void SemanticError( CodeLocation location, std::string error ) {
         SemanticErrorThrow = true;
         throw SemanticErrorException(location, error);
+        throw SemanticErrorException( location, error );
+}

src/Concurrency/Keywords.cc

-                      r97397a26
+                      rb21c77a
                 void postvisit(   StructDecl * decl );
                 std::list<DeclarationWithType*> findMutexArgs( FunctionDecl* );
+                std::list<DeclarationWithType*> findMutexArgs( FunctionDecl*, bool & first );
                 void validate( DeclarationWithType * );
                 void addDtorStatments( FunctionDecl* func, CompoundStmt *, const std::list<DeclarationWithType * > &);
 …
         void MutexKeyword::postvisit(FunctionDecl* decl) {
+                std::list<DeclarationWithType*> mutexArgs = findMutexArgs( decl );
+                if( mutexArgs.empty() ) return;
+                if( CodeGen::isConstructor(decl->name) ) SemanticError( decl, "constructors cannot have mutex parameters" );
+                bool first = false;
+                std::list<DeclarationWithType*> mutexArgs = findMutexArgs( decl, first );
                 bool isDtor = CodeGen::isDestructor( decl->name );
+                // Is this function relevant to monitors
+                if( mutexArgs.empty() ) {
+                        // If this is the destructor for a monitor it must be mutex
+                        if(isDtor) {
+                                Type* ty = decl->get_functionType()->get_parameters().front()->get_type();
+                                // If it's a copy, it's not a mutex
+                                ReferenceType* rty = dynamic_cast< ReferenceType * >( ty );
+                                if( ! rty ) return;
+                                // If we are not pointing directly to a type, it's not a mutex
+                                Type* base = rty->get_base();
+                                if( dynamic_cast< ReferenceType * >( base ) ) return;
+                                if( dynamic_cast< PointerType * >( base ) ) return;
+                                // Check if its a struct
+                                StructInstType * baseStruct = dynamic_cast< StructInstType * >( base );
+                                if( !baseStruct ) return;
+                                // Check if its a monitor
+                                if(baseStruct->baseStruct->is_monitor() || baseStruct->baseStruct->is_thread())
+                                        SemanticError( decl, "destructors for structures declared as \"monitor\" must use mutex parameters\n" );
+                        }
+                        return;
+                }
+                // Monitors can't be constructed with mutual exclusion
+                if( CodeGen::isConstructor(decl->name) && !first ) SemanticError( decl, "constructors cannot have mutex parameters" );
+                // It makes no sense to have multiple mutex parameters for the destructor
                 if( isDtor && mutexArgs.size() != 1 ) SemanticError( decl, "destructors can only have 1 mutex argument" );
+                // Make sure all the mutex arguments are monitors
                 for(auto arg : mutexArgs) {
                         validate( arg );
+                }
+                // Check if we need to instrument the body
                 CompoundStmt* body = decl->get_statements();
                 if( ! body ) return;
+                // Do we have the required headers
                 if( !monitor_decl || !guard_decl || !dtor_guard_decl )
+                        SemanticError( decl, "mutex keyword requires monitors to be in scope, add #include <monitor>" );
+                        SemanticError( decl, "mutex keyword requires monitors to be in scope, add #include <monitor>\n" );
+                // Instrument the body
                 if( isDtor ) {
                         addDtorStatments( decl, body, mutexArgs );
 …
+        }
         std::list<DeclarationWithType*> MutexKeyword::findMutexArgs( FunctionDecl* decl ) {
+        std::list<DeclarationWithType*> MutexKeyword::findMutexArgs( FunctionDecl* decl, bool & first ) {
                 std::list<DeclarationWithType*> mutexArgs;
+                bool once = true;
                 for( auto arg : decl->get_functionType()->get_parameters()) {
                         //Find mutex arguments
                         Type* ty = arg->get_type();
                         if( ! ty->get_mutex() ) continue;
+                        if(once) {first = true;}
+                        once = false;
                         //Append it to the list

src/ControlStruct/ForExprMutator.cc

-                      r97397a26
+                      rb21c77a
                 return hoist( forStmt, forStmt->initialization );
+        }
+        Statement *ForExprMutator::postmutate( WhileStmt *whileStmt ) {
+                return hoist( whileStmt, whileStmt->initialization );
+        }
 } // namespace ControlStruct

src/ControlStruct/ForExprMutator.h

-                      r97397a26
+                      rb21c77a
 class IfStmt;
 class ForStmt;
+class WhileStmt;
 class Statement;
 …
                 Statement *postmutate( IfStmt * );
                 Statement *postmutate( ForStmt * );
+                Statement *postmutate( WhileStmt * );
         };
 } // namespace ControlStruct

src/ControlStruct/Mutate.cc

-                      r97397a26
+                      rb21c77a
 #include "SynTree/Visitor.h"       // for acceptAll
+using namespace std;
+namespace ControlStruct {
+        void fixLabels( std::list< Declaration * > & translationUnit ) {
+                PassVisitor<LabelFixer> lfix;
+                acceptAll( translationUnit, lfix );
+        }
+namespace ControlStruct {
+        void mutate( std::list< Declaration * > translationUnit ) {
+                // hoist initialization out of for statements
+        void hoistControlDecls( std::list< Declaration * > & translationUnit ) {
                 PassVisitor<ForExprMutator> formut;
-                // normalizes label definitions and generates multi-level exit labels
-                PassVisitor<LabelFixer> lfix;
                 mutateAll( translationUnit, formut );
-                acceptAll( translationUnit, lfix );
+        }
 } // namespace CodeGen

src/ControlStruct/Mutate.h

-                      r97397a26
+                      rb21c77a
 // file "LICENCE" distributed with Cforall.
 //
 // Mutate.h --
+// Mutate.h --
 //
 // Author           : Rodolfo G. Esteves
 …
 class Declaration;
+/// Desugars Cforall control structures
 namespace ControlStruct {
+        /// Desugars Cforall control structures
+        void mutate( std::list< Declaration* > translationUnit );
+        /// normalizes label definitions and generates multi-level exit labels
+        void fixLabels( std::list< Declaration * > & translationUnit );
+        /// hoist initialization out of for statements
+        void hoistControlDecls( std::list< Declaration * > & translationUnit );
 } // namespace ControlStruct

src/GenPoly/Lvalue.cc

-                      r97397a26
+                      rb21c77a
         namespace {
                 // true for intrinsic function calls that return a reference
+                // true for intrinsic function calls that return an lvalue in C
                 bool isIntrinsicReference( Expression * expr ) {
+                        // known intrinsic-reference prelude functions
+                        static std::set<std::string> lvalueFunctions = { "*?", "?[?]" };
                         if ( UntypedExpr * untyped = dynamic_cast< UntypedExpr * >( expr ) ) {
                                 std::string fname = InitTweak::getFunctionName( untyped );
+                                // known intrinsic-reference prelude functions
+                                return fname == "*?" || fname == "?[?]";
+                                return lvalueFunctions.count(fname);
                         } else if ( ApplicationExpr * appExpr = dynamic_cast< ApplicationExpr * > ( expr ) ) {
                                 if ( DeclarationWithType * func = InitTweak::getFunction( appExpr ) ) {
+                                        // use type of return variable rather than expr result type, since it may have been changed to a pointer type
+                                        FunctionType * ftype = GenPoly::getFunctionType( func->get_type() );
+                                        Type * ret = ftype->returnVals.empty() ? nullptr : ftype->returnVals.front()->get_type();
+                                        return func->linkage == LinkageSpec::Intrinsic && dynamic_cast<ReferenceType *>( ret );
+                                        return func->linkage == LinkageSpec::Intrinsic && lvalueFunctions.count(func->name);
+                                }
+                        }
 …
                                                 // TODO: it's likely that the second condition should be ... && ! isIntrinsicReference( arg ), but this requires investigation.
                                                 if ( function->get_linkage() != LinkageSpec::Intrinsic && isIntrinsicReference( arg ) ) {
+                                                if ( function->linkage != LinkageSpec::Intrinsic && isIntrinsicReference( arg ) ) {
                                                         // needed for definition of prelude functions, etc.
                                                         // if argument is dereference or array subscript, the result isn't REALLY a reference, but non-intrinsic functions expect a reference: take address
 …
                                                         arg = new AddressExpr( arg );
                                                 // } else if ( function->get_linkage() == LinkageSpec::Intrinsic && InitTweak::getPointerBase( arg->result ) ) {
                                                 } else if ( function->get_linkage() == LinkageSpec::Intrinsic && arg->result->referenceDepth() != 0 ) {
+                                                } else if ( function->linkage == LinkageSpec::Intrinsic && arg->result->referenceDepth() != 0 ) {
                                                         // argument is a 'real' reference, but function expects a C lvalue: add a dereference to the reference-typed argument
                                                         PRINT(

src/Parser/DeclarationNode.cc

-                      r97397a26
+                      rb21c77a
 // Created On       : Sat May 16 12:34:05 2015
 // Last Modified By : Peter A. Buhr
 // Last Modified On : Tue May 22 08:39:29 2018
 // Update Count     : 1074
+// Last Modified On : Thu Jun  7 12:08:55 2018
+// Update Count     : 1079
 //
 …
+}
 DeclarationNode * DeclarationNode::newFunction( string * name, DeclarationNode * ret, DeclarationNode * param, StatementNode * body ) {
+DeclarationNode * DeclarationNode::newFunction( const string * name, DeclarationNode * ret, DeclarationNode * param, StatementNode * body ) {
         DeclarationNode * newnode = new DeclarationNode;
         newnode->name = name;
 …
 } // DeclarationNode::newForall
 DeclarationNode * DeclarationNode::newFromTypedef( string * name ) {
+DeclarationNode * DeclarationNode::newFromTypedef( const string * name ) {
         DeclarationNode * newnode = new DeclarationNode;
         newnode->type = new TypeData( TypeData::SymbolicInst );
 …
 } // DeclarationNode::newAggregate
 DeclarationNode * DeclarationNode::newEnum( string * name, DeclarationNode * constants, bool body ) {
+DeclarationNode * DeclarationNode::newEnum( const string * name, DeclarationNode * constants, bool body ) {
         assert( name );
         DeclarationNode * newnode = new DeclarationNode;
 …
 } // DeclarationNode::newEnum
 DeclarationNode * DeclarationNode::newEnumConstant( string * name, ExpressionNode * constant ) {
+DeclarationNode * DeclarationNode::newEnumConstant( const string * name, ExpressionNode * constant ) {
         DeclarationNode * newnode = new DeclarationNode;
         newnode->name = name;
 …
 } // DeclarationNode::newEnumConstant
 DeclarationNode * DeclarationNode::newName( string * name ) {
+DeclarationNode * DeclarationNode::newName( const string * name ) {
         DeclarationNode * newnode = new DeclarationNode;
         newnode->name = name;
 …
 } // DeclarationNode::newName
 DeclarationNode * DeclarationNode::newFromTypeGen( string * name, ExpressionNode * params ) {
+DeclarationNode * DeclarationNode::newFromTypeGen( const string * name, ExpressionNode * params ) {
         DeclarationNode * newnode = new DeclarationNode;
         newnode->type = new TypeData( TypeData::SymbolicInst );
 …
 } // DeclarationNode::newFromTypeGen
 DeclarationNode * DeclarationNode::newTypeParam( TypeClass tc, string * name ) {
+DeclarationNode * DeclarationNode::newTypeParam( TypeClass tc, const string * name ) {
         DeclarationNode * newnode = new DeclarationNode;
         newnode->type = nullptr;
 …
 } // DeclarationNode::newTraitUse
 DeclarationNode * DeclarationNode::newTypeDecl( string * name, DeclarationNode * typeParams ) {
+DeclarationNode * DeclarationNode::newTypeDecl( const string * name, DeclarationNode * typeParams ) {
         DeclarationNode * newnode = new DeclarationNode;
         newnode->name = name;
 …
 } // DeclarationNode::newBuiltinType
 DeclarationNode * DeclarationNode::newAttr( string * name, ExpressionNode * expr ) {
+DeclarationNode * DeclarationNode::newAttr( const string * name, ExpressionNode * expr ) {
         DeclarationNode * newnode = new DeclarationNode;
         newnode->type = nullptr;
 …
+}
 DeclarationNode * DeclarationNode::newAttr( string * name, DeclarationNode * type ) {
+DeclarationNode * DeclarationNode::newAttr( const string * name, DeclarationNode * type ) {
         DeclarationNode * newnode = new DeclarationNode;
         newnode->type = nullptr;
 …
+}
 DeclarationNode * DeclarationNode::newAttribute( string * name, ExpressionNode * expr ) {
+DeclarationNode * DeclarationNode::newAttribute( const string * name, ExpressionNode * expr ) {
         DeclarationNode * newnode = new DeclarationNode;
         newnode->type = nullptr;
 …
                                         type->aggregate.params->appendList( q->type->forall ); // augment forall qualifier
                                 } else {                                                                // not polymorphic
+                                        type->aggregate.params = q->type->forall; // make polymorphic type
+                                        // change implicit typedef from TYPEDEFname to TYPEGENname
+                                        typedefTable.changeKind( *type->aggregate.name, TYPEGENname );
+                                        type->aggregate.params = q->type->forall; // set forall qualifier
                                 } // if
                         } else {                                                                        // not polymorphic
 …
                         SemanticError( this, "invalid function specifier for " );
                 } // if
+                return buildDecl( type, name ? *name : string( "" ), storageClasses, maybeBuild< Expression >( bitfieldWidth ), funcSpecs, linkage, asmName, maybeBuild< Initializer >(initializer), attributes )->set_extension( extension );
+                bool isDelete = initializer && initializer->get_isDelete();
+                Declaration * decl = buildDecl( type, name ? *name : string( "" ), storageClasses, maybeBuild< Expression >( bitfieldWidth ), funcSpecs, linkage, asmName, isDelete ? nullptr : maybeBuild< Initializer >(initializer), attributes )->set_extension( extension );
+                if ( isDelete ) {
+                        DeclarationWithType * dwt = strict_dynamic_cast<DeclarationWithType *>( decl );
+                        dwt->isDeleted = true;
+                }
+                return decl;
         } // if

src/Parser/ExpressionNode.cc

-                      r97397a26
+                      rb21c77a
 // Created On       : Sat May 16 13:17:07 2015
 // Last Modified By : Peter A. Buhr
 // Last Modified On : Thu Mar 22 11:57:39 2018
 // Update Count     : 801
+// Last Modified On : Mon Jun  4 21:24:45 2018
+// Update Count     : 802
 //
 …
 Expression * build_constantStr( string & str ) {
+        assert( str.length() > 0 );
         string units;                                                                           // units
         sepString( str, units, '"' );                                           // separate constant from units

src/Parser/InitializerNode.cc

-                      r97397a26
+                      rb21c77a
 InitializerNode::InitializerNode( ExpressionNode * _expr, bool aggrp, ExpressionNode * des )
                 : expr( _expr ), aggregate( aggrp ), designator( des ), kids( nullptr ), maybeConstructed( true ) {
+                : expr( _expr ), aggregate( aggrp ), designator( des ), kids( nullptr ), maybeConstructed( true ), isDelete( false ) {
         if ( aggrp )
                 kids = dynamic_cast< InitializerNode * >( get_next() );
 …
 InitializerNode::InitializerNode( InitializerNode * init, bool aggrp, ExpressionNode * des )
                 : expr( nullptr ), aggregate( aggrp ), designator( des ), kids( nullptr ), maybeConstructed( true ) {
+                : expr( nullptr ), aggregate( aggrp ), designator( des ), kids( nullptr ), maybeConstructed( true ), isDelete( false ) {
         if ( init )
                 set_last( init );
 …
                 set_next( nullptr );
 } // InitializerNode::InitializerNode
+InitializerNode::InitializerNode( bool isDelete ) : expr( nullptr ), aggregate( false ), designator( nullptr ), kids( nullptr ), maybeConstructed( false ), isDelete( isDelete ) {}
 InitializerNode::~InitializerNode() {
 …
 Initializer * InitializerNode::build() const {
+        assertf( ! isDelete, "Should not build delete stmt InitializerNode" );
         if ( aggregate ) {
                 // steal designators from children

src/Parser/ParseNode.h

-                      r97397a26
+                      rb21c77a
 // Created On       : Sat May 16 13:28:16 2015
 // Last Modified By : Peter A. Buhr
 // Last Modified On : Mon Apr 30 09:19:17 2018
 // Update Count     : 831
+// Last Modified On : Wed Jun  6 16:17:18 2018
+// Update Count     : 843
 //
 …
         ParseNode * next = nullptr;
         std::string * name = nullptr;
+        const std::string * name = nullptr;
         CodeLocation location = yylloc;
 }; // ParseNode
 …
         InitializerNode( ExpressionNode *, bool aggrp = false,  ExpressionNode * des = nullptr );
         InitializerNode( InitializerNode *, bool aggrp = false, ExpressionNode * des = nullptr );
+        InitializerNode( bool isDelete );
         ~InitializerNode();
         virtual InitializerNode * clone() const { assert( false ); return nullptr; }
 …
         InitializerNode * set_maybeConstructed( bool value ) { maybeConstructed = value; return this; }
         bool get_maybeConstructed() const { return maybeConstructed; }
+        bool get_isDelete() const { return isDelete; }
         InitializerNode * next_init() const { return kids; }
 …
         InitializerNode * kids;
         bool maybeConstructed;
+        bool isDelete;
 }; // InitializerNode
 …
 };
 Expression * build_constantInteger( std::string &str );
 Expression * build_constantFloat( std::string &str );
 Expression * build_constantChar( std::string &str );
 Expression * build_constantStr( std::string &str );
+Expression * build_constantInteger( std::string & str ); // these 4 routines modify the string
+Expression * build_constantFloat( std::string & str );
+Expression * build_constantChar( std::string & str );
+Expression * build_constantStr( std::string & str );
 Expression * build_field_name_FLOATING_FRACTIONconstant( const std::string & str );
 Expression * build_field_name_FLOATING_DECIMALconstant( const std::string & str );
 …
         static DeclarationNode * newBuiltinType( BuiltinType );
         static DeclarationNode * newForall( DeclarationNode * );
         static DeclarationNode * newFromTypedef( std::string * );
         static DeclarationNode * newFunction( std::string * name, DeclarationNode * ret, DeclarationNode * param, StatementNode * body );
+        static DeclarationNode * newFromTypedef( const std::string * );
+        static DeclarationNode * newFunction( const std::string * name, DeclarationNode * ret, DeclarationNode * param, StatementNode * body );
         static DeclarationNode * newAggregate( Aggregate kind, const std::string * name, ExpressionNode * actuals, DeclarationNode * fields, bool body );
         static DeclarationNode * newEnum( std::string * name, DeclarationNode * constants, bool body );
         static DeclarationNode * newEnumConstant( std::string * name, ExpressionNode * constant );
         static DeclarationNode * newName( std::string * );
         static DeclarationNode * newFromTypeGen( std::string *, ExpressionNode * params );
         static DeclarationNode * newTypeParam( TypeClass, std::string * );
+        static DeclarationNode * newEnum( const std::string * name, DeclarationNode * constants, bool body );
+        static DeclarationNode * newEnumConstant( const std::string * name, ExpressionNode * constant );
+        static DeclarationNode * newName( const std::string * );
+        static DeclarationNode * newFromTypeGen( const std::string *, ExpressionNode * params );
+        static DeclarationNode * newTypeParam( TypeClass, const std::string * );
         static DeclarationNode * newTrait( const std::string * name, DeclarationNode * params, DeclarationNode * asserts );
         static DeclarationNode * newTraitUse( const std::string * name, ExpressionNode * params );
         static DeclarationNode * newTypeDecl( std::string * name, DeclarationNode * typeParams );
+        static DeclarationNode * newTypeDecl( const std::string * name, DeclarationNode * typeParams );
         static DeclarationNode * newPointer( DeclarationNode * qualifiers, OperKinds kind );
         static DeclarationNode * newArray( ExpressionNode * size, DeclarationNode * qualifiers, bool isStatic );
 …
         static DeclarationNode * newTuple( DeclarationNode * members );
         static DeclarationNode * newTypeof( ExpressionNode * expr );
         static DeclarationNode * newAttr( std::string *, ExpressionNode * expr ); // @ attributes
         static DeclarationNode * newAttr( std::string *, DeclarationNode * type ); // @ attributes
         static DeclarationNode * newAttribute( std::string *, ExpressionNode * expr = nullptr ); // gcc attributes
+        static DeclarationNode * newAttr( const std::string *, ExpressionNode * expr ); // @ attributes
+        static DeclarationNode * newAttr( const std::string *, DeclarationNode * type ); // @ attributes
+        static DeclarationNode * newAttribute( const std::string *, ExpressionNode * expr = nullptr ); // gcc attributes
         static DeclarationNode * newAsmStmt( StatementNode * stmt ); // gcc external asm statement
         static DeclarationNode * newStaticAssert( ExpressionNode * condition, Expression * message );
 …
 };
+Expression * build_if_control( IfCtl * ctl, std::list< Statement * > & init );
 Statement * build_if( IfCtl * ctl, StatementNode * then_stmt, StatementNode * else_stmt );
 Statement * build_switch( bool isSwitch, ExpressionNode * ctl, StatementNode * stmt );
 Statement * build_case( ExpressionNode * ctl );
 Statement * build_default();
+Statement * build_while( ExpressionNode * ctl, StatementNode * stmt, bool kind = false );
+Statement * build_while( IfCtl * ctl, StatementNode * stmt );
+Statement * build_do_while( ExpressionNode * ctl, StatementNode * stmt );
 Statement * build_for( ForCtl * forctl, StatementNode * stmt );
 Statement * build_branch( BranchStmt::Type kind );

src/Parser/StatementNode.cc

-                      r97397a26
+                      rb21c77a
 // Created On       : Sat May 16 14:59:41 2015
 // Last Modified By : Peter A. Buhr
 // Last Modified On : Mon Apr 30 09:21:16 2018
 // Update Count     : 354
+// Last Modified On : Tue Jun  5 08:58:34 2018
+// Update Count     : 362
 //
 …
         caseStmt->get_statements().splice( caseStmt->get_statements().end(), stmts );
         return this;
+}
+} // StatementNode::append_last_case
 Statement * build_expr( ExpressionNode * ctl ) {
         Expression * e = maybeMoveBuild< Expression >( ctl );
+        if ( e )
+                return new ExprStmt( e );
+        else
+                return new NullStmt();
+}
+Statement * build_if( IfCtl * ctl, StatementNode * then_stmt, StatementNode * else_stmt ) {
+        Statement * thenb, * elseb = 0;
+        std::list< Statement * > branches;
+        buildMoveList< Statement, StatementNode >( then_stmt, branches );
+        assert( branches.size() == 1 );
+        thenb = branches.front();
+        if ( else_stmt ) {
+                std::list< Statement * > branches;
+                buildMoveList< Statement, StatementNode >( else_stmt, branches );
+                assert( branches.size() == 1 );
+                elseb = branches.front();
+        } // if
+        std::list< Statement * > init;
+        if ( e ) return new ExprStmt( e );
+        else return new NullStmt();
+} // build_expr
+Expression * build_if_control( IfCtl * ctl, std::list< Statement * > & init ) {
         if ( ctl->init != 0 ) {
                 buildMoveList( ctl->init, init );
 …
         if ( ctl->condition ) {
                 // compare the provided condition against 0
                 cond =  notZeroExpr( maybeMoveBuild< Expression >(ctl->condition) );
+                cond = notZeroExpr( maybeMoveBuild< Expression >(ctl->condition) );
         } else {
                 for ( Statement * stmt : init ) {
 …
+        }
         delete ctl;
+        return cond;
+} // build_if_control
+Statement * build_if( IfCtl * ctl, StatementNode * then_stmt, StatementNode * else_stmt ) {
+        Statement * thenb, * elseb = nullptr;
+        std::list< Statement * > branches;
+        buildMoveList< Statement, StatementNode >( then_stmt, branches );
+        assert( branches.size() == 1 );
+        thenb = branches.front();
+        if ( else_stmt ) {
+                std::list< Statement * > branches;
+                buildMoveList< Statement, StatementNode >( else_stmt, branches );
+                assert( branches.size() == 1 );
+                elseb = branches.front();
+        } // if
+        std::list< Statement * > init;
+        Expression * cond = build_if_control( ctl, init );
         return new IfStmt( cond, thenb, elseb, init );
+}
+} // build_if
 Statement * build_switch( bool isSwitch, ExpressionNode * ctl, StatementNode * stmt ) {
 …
         // branches.size() == 0 for switch (...) {}, i.e., no declaration or statements
         return new SwitchStmt( maybeMoveBuild< Expression >(ctl), branches );
+}
+} // build_switch
 Statement * build_case( ExpressionNode * ctl ) {
         std::list< Statement * > branches;
         return new CaseStmt( maybeMoveBuild< Expression >(ctl), branches );
+}
+} // build_case
 Statement * build_default() {
         std::list< Statement * > branches;
         return new CaseStmt( nullptr, branches, true );
+}
+Statement * build_while( ExpressionNode * ctl, StatementNode * stmt, bool kind ) {
+        std::list< Statement * > branches;
+        buildMoveList< Statement, StatementNode >( stmt, branches );
+        assert( branches.size() == 1 );
+        return new WhileStmt( notZeroExpr( maybeMoveBuild< Expression >(ctl) ), branches.front(), kind );
+}
+} // build_default
+Statement * build_while( IfCtl * ctl, StatementNode * stmt ) {
+        std::list< Statement * > branches;
+        buildMoveList< Statement, StatementNode >( stmt, branches );
+        assert( branches.size() == 1 );
+        std::list< Statement * > init;
+        Expression * cond = build_if_control( ctl, init );
+        return new WhileStmt( cond, branches.front(), init, false );
+} // build_while
+Statement * build_do_while( ExpressionNode * ctl, StatementNode * stmt ) {
+        std::list< Statement * > branches;
+        buildMoveList< Statement, StatementNode >( stmt, branches );
+        assert( branches.size() == 1 );
+        std::list< Statement * > init;
+        return new WhileStmt( notZeroExpr( maybeMoveBuild< Expression >(ctl) ), branches.front(), init, true );
+} // build_do_while
 Statement * build_for( ForCtl * forctl, StatementNode * stmt ) {
 …
         delete forctl;
         return new ForStmt( init, cond, incr, branches.front() );
+}
+} // build_for
 Statement * build_branch( BranchStmt::Type kind ) {
         Statement * ret = new BranchStmt( "", kind );
         return ret;
+}
+} // build_branch
 Statement * build_branch( std::string * identifier, BranchStmt::Type kind ) {
         Statement * ret = new BranchStmt( * identifier, kind );
         delete identifier;                                                                      // allocated by lexer
         return ret;
+}
+} // build_branch
 Statement * build_computedgoto( ExpressionNode * ctl ) {
         return new BranchStmt( maybeMoveBuild< Expression >(ctl), BranchStmt::Goto );
+}
+} // build_computedgoto
 Statement * build_return( ExpressionNode * ctl ) {
 …
         buildMoveList( ctl, exps );
         return new ReturnStmt( exps.size() > 0 ? exps.back() : nullptr );
+}
+} // build_return
 Statement * build_throw( ExpressionNode * ctl ) {
 …
         assertf( exps.size() < 2, "This means we are leaking memory");
         return new ThrowStmt( ThrowStmt::Terminate, !exps.empty() ? exps.back() : nullptr );
+}
+} // build_throw
 Statement * build_resume( ExpressionNode * ctl ) {
 …
         assertf( exps.size() < 2, "This means we are leaking memory");
         return new ThrowStmt( ThrowStmt::Resume, !exps.empty() ? exps.back() : nullptr );
+}
+} // build_resume
 Statement * build_resume_at( ExpressionNode * ctl, ExpressionNode * target ) {
 …
         (void)target;
         assertf( false, "resume at (non-local throw) is not yet supported," );
+}
+} // build_resume_at
 Statement * build_try( StatementNode * try_stmt, StatementNode * catch_stmt, StatementNode * finally_stmt ) {
 …
         FinallyStmt * finallyBlock = dynamic_cast< FinallyStmt * >(maybeMoveBuild< Statement >(finally_stmt) );
         return new TryStmt( tryBlock, branches, finallyBlock );
+}
+} // build_try
 Statement * build_catch( CatchStmt::Kind kind, DeclarationNode * decl, ExpressionNode * cond, StatementNode * body ) {
         std::list< Statement * > branches;
 …
         assert( branches.size() == 1 );
         return new CatchStmt( kind, maybeMoveBuild< Declaration >(decl), maybeMoveBuild< Expression >(cond), branches.front() );
+}
+} // build_catch
 Statement * build_finally( StatementNode * stmt ) {
         std::list< Statement * > branches;
 …
         assert( branches.size() == 1 );
         return new FinallyStmt( dynamic_cast< CompoundStmt * >( branches.front() ) );
+}
+} // build_finally
 WaitForStmt * build_waitfor( ExpressionNode * targetExpr, StatementNode * stmt, ExpressionNode * when ) {
 …
         return node;
+}
+} // build_waitfor
 WaitForStmt * build_waitfor( ExpressionNode * targetExpr, StatementNode * stmt, ExpressionNode * when, WaitForStmt * node ) {
 …
         return node;
+}
+} // build_waitfor
 WaitForStmt * build_waitfor_timeout( ExpressionNode * timeout, StatementNode * stmt, ExpressionNode * when ) {
 …
                 node->timeout.statement = maybeMoveBuild<Statement >( stmt    );
                 node->timeout.condition = notZeroExpr( maybeMoveBuild<Expression>( when ) );
+        }
+        else {
+        } else {
                 node->orelse.statement  = maybeMoveBuild<Statement >( stmt );
                 node->orelse.condition  = notZeroExpr( maybeMoveBuild<Expression>( when ) );
+        }
+        } // if
         return node;
+}
+} // build_waitfor_timeout
 WaitForStmt * build_waitfor_timeout( ExpressionNode * timeout, StatementNode * stmt, ExpressionNode * when,  StatementNode * else_stmt, ExpressionNode * else_when ) {
 …
         return node;
+}
+} // build_waitfor_timeout
 WithStmt * build_with( ExpressionNode * exprs, StatementNode * stmt ) {
 …
         Statement * s = maybeMoveBuild<Statement>( stmt );
         return new WithStmt( e, s );
+}
+} // build_with
 Statement * build_compound( StatementNode * first ) {
 …
         buildMoveList( first, cs->get_kids() );
         return cs;
+}
+} // build_compound
 Statement * build_asm( bool voltile, Expression * instruction, ExpressionNode * output, ExpressionNode * input, ExpressionNode * clobber, LabelNode * gotolabels ) {
 …
         buildMoveList( clobber, clob );
         return new AsmStmt( voltile, instruction, out, in, clob, gotolabels ? gotolabels->labels : noLabels );
+}
+} // build_asm
 Statement * build_directive( string * directive ) {
         return new DirectiveStmt( *directive );
+}
+} // build_directive
 // Local Variables: //

src/Parser/TypeData.cc

-                      r97397a26
+                      rb21c77a
 // Created On       : Sat May 16 15:12:51 2015
 // Last Modified By : Peter A. Buhr
 // Last Modified On : Thu Apr 26 13:46:07 2018
 // Update Count     : 603
+// Last Modified On : Wed Jun  6 17:40:33 2018
+// Update Count     : 604
 //
 …
           case Aggregate:
                 // aggregate = new Aggregate_t;
+                aggregate.kind = DeclarationNode::NoAggregate;
                 aggregate.name = nullptr;
                 aggregate.params = nullptr;
 …
                 aggregate.fields = nullptr;
                 aggregate.body = false;
+                aggregate.tagged = false;
+                aggregate.parent = nullptr;
                 break;
           case AggregateInst:
 …
                 break;
           case Aggregate:
+                newtype->aggregate.kind = aggregate.kind;
                 newtype->aggregate.name = aggregate.name ? new string( *aggregate.name ) : nullptr;
                 newtype->aggregate.params = maybeClone( aggregate.params );
                 newtype->aggregate.actuals = maybeClone( aggregate.actuals );
                 newtype->aggregate.fields = maybeClone( aggregate.fields );
-                newtype->aggregate.kind = aggregate.kind;
                 newtype->aggregate.body = aggregate.body;
                 newtype->aggregate.tagged = aggregate.tagged;
 …
           case DeclarationNode::Int128:
                 ret = td->signedness == 1 ? BasicType::UnsignedInt128 : BasicType::SignedInt128;
+                ret = td->signedness == DeclarationNode::Unsigned ? BasicType::UnsignedInt128 : BasicType::SignedInt128;
                 if ( td->length != DeclarationNode::NoLength ) {
                         genTSError( DeclarationNode::lengthNames[ td->length ], td->basictype );
 …
                         genTSError( DeclarationNode::lengthNames[ td->length ], td->basictype );
                 } // if
                 if ( td->basictype == DeclarationNode::Float && td->length == DeclarationNode::Long ) {
+                if ( td->basictype != DeclarationNode::Double && td->length == DeclarationNode::Long ) {
                         genTSError( DeclarationNode::lengthNames[ td->length ], td->basictype );
                 } // if
 …
                         const_cast<TypeData *>(td)->basictype = DeclarationNode::LongDouble;
                 } // if
+                if ( td->basictype == DeclarationNode::Float80 || td->basictype == DeclarationNode::Float128 ) {
+                        // if ( td->complextype != DeclarationNode::NoComplexType ) {
+                        //      genTSError( DeclarationNode::complexTypeNames[ td->complextype ], td->basictype );
+                        // }
+                        if ( td->basictype == DeclarationNode::Float80 ) ret = BasicType::Float80;
+                        else ret = BasicType::Float128;
+                        break;
+                }
                 ret = floattype[ td->complextype ][ td->basictype - DeclarationNode::Float ];

src/Parser/TypedefTable.cc

-                      r97397a26
+                      rb21c77a
 // Created On       : Sat May 16 15:20:13 2015
 // Last Modified By : Peter A. Buhr
 // Last Modified On : Tue May 22 08:40:01 2018
 // Update Count     : 121
+// Last Modified On : Fri Jun 22 06:14:39 2018
+// Update Count     : 206
 //
 …
 #include "TypedefTable.h"
 #include <cassert>                                                                              // for assert
+#include <iostream>
 #if 0
+#include <iostream>
+#define debugPrint( x ) cerr << x
+#define debugPrint( code ) code
 #else
 #define debugPrint( x )
+#define debugPrint( code )
 #endif
 using namespace std;                                                                    // string, iostream
+debugPrint(
+static const char *kindName( int kind ) {
+        switch ( kind ) {
+          case IDENTIFIER: return "identifier";
+          case TYPEDEFname: return "typedef";
+          case TYPEGENname: return "typegen";
+          default:
+                cerr << "Error: cfa-cpp internal error, invalid kind of identifier" << endl;
+                abort();
+        } // switch
+} // kindName
+)
 TypedefTable::~TypedefTable() {
         if ( ! SemanticErrorThrow && kindTable.currentScope() != 0 ) {
+                // std::cerr << "scope failure " << kindTable.currentScope() << endl;
+                cerr << "Error: cfa-cpp internal error, scope failure " << kindTable.currentScope() << endl;
+                abort();
         } // if
 } // TypedefTable::~TypedefTable
 …
 } // TypedefTable::isKind
-void TypedefTable::changeKind( const string & identifier, int kind ) {
-        KindTable::iterator posn = kindTable.find( identifier );
-        if ( posn != kindTable.end() ) posn->second = kind;     // exists => update
-} // TypedefTable::changeKind
 // SKULLDUGGERY: Generate a typedef for the aggregate name so the aggregate does not have to be qualified by
 // "struct". Only generate the typedef, if the name is not in use. The typedef is implicitly (silently) removed if the
 // name is explicitly used.
+void TypedefTable::makeTypedef( const string & name ) {
+void TypedefTable::makeTypedef( const string & name, int kind ) {
+//    Check for existence is necessary to handle:
+//        struct Fred {};
+//        void Fred();
+//        void fred() {
+//           struct Fred act; // do not add as type in this scope
+//           Fred();
+//        }
         if ( ! typedefTable.exists( name ) ) {
                 typedefTable.addToEnclosingScope( name, TYPEDEFname );
+                typedefTable.addToEnclosingScope( name, kind, "MTD" );
         } // if
 } // TypedefTable::makeTypedef
+void TypedefTable::addToEnclosingScope( const std::string & identifier, int kind ) {
+        assert( kindTable.currentScope() >= 1 );
+        auto scope = kindTable.currentScope() - 1;
+        debugPrint( "Adding " << identifier << " as kind " << kind << " scope " << scope << endl );
+void TypedefTable::addToScope( const string & identifier, int kind, const char * locn __attribute__((unused)) ) {
+        auto scope = kindTable.currentScope();
+        debugPrint( cerr << "Adding current at " << locn << " " << identifier << " as " << kindName( kind ) << " scope " << scope << endl );
+        auto ret = kindTable.insertAt( scope, identifier, kind );
+        //if ( ! ret.second ) ret.first->second = kind;         // exists => update
+        assert( ret.first->second == kind );                            // exists
+} // TypedefTable::addToScope
+void TypedefTable::addToEnclosingScope( const string & identifier, int kind, const char * locn __attribute__((unused)) ) {
+        assert( kindTable.currentScope() >= 1 + level );
+        auto scope = kindTable.currentScope() - 1 - level;
+        debugPrint( cerr << "Adding enclosing at " << locn << " " << identifier << " as " << kindName( kind ) << " scope " << scope << " level " << level << endl );
         auto ret = kindTable.insertAt( scope, identifier, kind );
         if ( ! ret.second ) ret.first->second = kind;           // exists => update
 …
 void TypedefTable::enterScope() {
         kindTable.beginScope();
         debugPrint( "Entering scope " << kindTable.currentScope() << endl );
+        debugPrint( cerr << "Entering scope " << kindTable.currentScope() << endl; print() );
 } // TypedefTable::enterScope
 void TypedefTable::leaveScope() {
         debugPrint( "Leaving scope " << kindTable.currentScope() << endl );
+        debugPrint( cerr << "Leaving scope " << kindTable.currentScope() << endl; print() );
         kindTable.endScope();
 } // TypedefTable::leaveScope
+// void TypedefTable::print( void ) const {
+//      for ( KindTable::const_iterator i = table.begin(); i != table.end(); i++) {
+//              debugPrint( (*i ).first << ": " );
+//              list< Entry > declList = (*i).second;
+//              for ( list< Entry >::const_iterator j = declList.begin(); j != declList.end(); j++ ) {
+//                      debugPrint( "(" << (*j).scope << " " << (*j).kind << ") " );
+//              }
+//              debugPrint( endl );
+//      } // for
+// }
+void TypedefTable::print( void ) const {
+        KindTable::size_type scope = kindTable.currentScope();
+        debugPrint( cerr << "[" << scope << "]" );
+        for ( KindTable::const_iterator i = kindTable.begin(); i != kindTable.end(); i++ ) {
+                while ( i.get_level() != scope ) {
+                        --scope;
+                        debugPrint( cerr << endl << "[" << scope << "]" );
+                } // while
+                debugPrint( cerr << " " << (*i).first << ":" << kindName( (*i).second ) );
+        } // for
+        while ( scope > 0 ) {
+                --scope;
+                debugPrint( cerr << endl << "[" << scope << "]" );
+        } // while
+        debugPrint( cerr << endl );
+} // TypedefTable::print
 // Local Variables: //

src/Parser/TypedefTable.h

-                      r97397a26
+                      rb21c77a
 // Created On       : Sat May 16 15:24:36 2015
 // Last Modified By : Peter A. Buhr
 // Last Modified On : Tue May 22 08:39:29 2018
 // Update Count     : 77
+// Last Modified On : Fri Jun 22 05:29:58 2018
+// Update Count     : 86
 //
 …
         typedef ScopedMap< std::string, int > KindTable;
         KindTable kindTable;
+        unsigned int level = 0;
   public:
         ~TypedefTable();
 …
         bool exists( const std::string & identifier );
         int isKind( const std::string & identifier ) const;
         void changeKind( const std::string & identifier, int kind );
         void makeTypedef( const std::string & name );
         void addToEnclosingScope( const std::string & identifier, int kind );
+        void makeTypedef( const std::string & name, int kind = TYPEDEFname );
+        void addToScope( const std::string & identifier, int kind, const char * );
+        void addToEnclosingScope( const std::string & identifier, int kind, const char * );
         void enterScope();
         void leaveScope();
+        void up() { level += 1; }
+        void down() { level -= 1; }
+        void print( void ) const;
 }; // TypedefTable

src/Parser/lex.ll

-                      r97397a26
+                      rb21c77a
  * Created On       : Sat Sep 22 08:58:10 2001
  * Last Modified By : Peter A. Buhr
  * Last Modified On : Thu May  3 13:42:40 2018
  * Update Count     : 676
+ * Last Modified On : Wed Jun 20 09:08:28 2018
+ * Update Count     : 682
  */
 …
 //**************************** Includes and Defines ****************************
+// trigger before each matching rule's action
+#define YY_USER_ACTION \
+        yylloc.first_line = yylineno; \
+        yylloc.first_column = column; \
+        column += yyleng; \
+        yylloc.last_column = column; \
+        yylloc.last_line = yylineno; \
+        yylloc.filename = yyfilename ? yyfilename : "";
 unsigned int column = 0;                                                                // position of the end of the last token parsed
-#define YY_USER_ACTION yylloc.first_line = yylineno; yylloc.first_column = column; column += yyleng; yylloc.last_column = column; yylloc.last_line = yylineno; yylloc.filename = yyfilename ? yyfilename : "";                          // trigger before each matching rule's action
 #include <string>
 …
 #define NUMERIC_RETURN(x)       rm_underscore(); RETURN_VAL( x ) // numeric constant
 #define KEYWORD_RETURN(x)       RETURN_CHAR( x )                        // keyword
 #define QKEYWORD_RETURN(x)      typedefTable.isKind( yytext ); RETURN_VAL(x); // quasi-keyword
+#define QKEYWORD_RETURN(x)      RETURN_VAL(x);                          // quasi-keyword
 #define IDENTIFIER_RETURN()     RETURN_VAL( typedefTable.isKind( yytext ) )
 #define ATTRIBUTE_RETURN()      RETURN_VAL( ATTR_IDENTIFIER )
 …
 finally                 { KEYWORD_RETURN(FINALLY); }                    // CFA
 float                   { KEYWORD_RETURN(FLOAT); }
+_Float32                { KEYWORD_RETURN(FLOAT); }                              // GCC
+_Float32x               { KEYWORD_RETURN(FLOAT); }                              // GCC
+_Float64                { KEYWORD_RETURN(DOUBLE); }                             // GCC
+_Float64x               { KEYWORD_RETURN(DOUBLE); }                             // GCC
 __float80               { KEYWORD_RETURN(FLOAT80); }                    // GCC
 float80                 { KEYWORD_RETURN(FLOAT80); }                    // GCC
+_Float128               { KEYWORD_RETURN(FLOAT128); }                   // GCC
+_Float128x              { KEYWORD_RETURN(FLOAT128); }                   // GCC
 __float128              { KEYWORD_RETURN(FLOAT128); }                   // GCC
 float128                { KEYWORD_RETURN(FLOAT128); }                   // GCC
 …
 %%
 // ----end of lexer----
 void yyerror( const char * errmsg ) {
+        SemanticErrorThrow = true;
         cout << (yyfilename ? yyfilename : "*unknown file*") << ':' << yylineno << ':' << column - yyleng + 1
                  << ": " << ErrorHelpers::error_str() << errmsg << " at token \"" << (yytext[0] == '\0' ? "EOF" : yytext) << '"' << endl;

src/Parser/parser.yy

-                      r97397a26
+                      rb21c77a
 // Created On       : Sat Sep  1 20:22:55 2001
 // Last Modified By : Peter A. Buhr
 // Last Modified On : Thu May 24 18:11:59 2018
 // Update Count     : 3369
+// Last Modified On : Fri Jun 22 13:59:11 2018
+// Update Count     : 3586
 //
 …
 } // build_postfix_name

Context Navigation

Legend: