Index: doc/bibliography/pl.bib
===================================================================
--- doc/bibliography/pl.bib	(revision c884f2d126e0594e6d9223e0afc85a588178f92f)
+++ doc/bibliography/pl.bib	(revision 972540e714dedc02bc563d19e713b0a42b7e3abd)
@@ -1141,4 +1141,17 @@
 }
 
+@inproceedings{Tarditi18,
+    keywords	= {Checked C},
+    contributer	= {a3moss@uwaterloo.ca},
+    author	= {Tarditi, David and Elliott, Archibald Samuel and Ruef, Andrew and Hicks, Michael},
+    title	= {Checked C: Making C Safe by Extension},
+    booktitle	= {2018 IEEE Cybersecurity Development (SecDev)}, 
+    publisher	= {IEEE},
+    year	= {2018},
+    month	= seep,
+    pages	= {53-60},
+    url		= {https://www.microsoft.com/en-us/research/publication/checkedc-making-c-safe-by-extension/},
+}
+
 @book{Yourdon79,
     keywords	= {software engineering},
@@ -1301,5 +1314,8 @@
     journal	= sigplan,
     year	= 1986,
-    month	= oct, volume = 21, number = 10, pages = {19-28},
+    month	= oct,
+    volume	= 21,
+    number	= 10,
+    pages	= {19-28},
     note	= {Object Oriented Programming Workshop}
 }
@@ -7791,4 +7807,19 @@
 % Y
 
+@article{Boehm12,
+    keywords	= {memory model, race condition},
+    contributer	= {pabuhr@plg},
+    author	= {Boehm, Hans-J. and Adve, Sarita V.},
+    title	= {You Don'T Know Jack About Shared Variables or Memory Models},
+    journal	= cacm,
+    volume	= 55,
+    number	= 2,
+    month	= feb,
+    year	= 2012,
+    pages	= {48--54},
+    publisher	= {ACM},
+    address	= {New York, NY, USA},
+}
+
 % Z
 
Index: doc/papers/concurrency/Paper.tex
===================================================================
--- doc/papers/concurrency/Paper.tex	(revision c884f2d126e0594e6d9223e0afc85a588178f92f)
+++ doc/papers/concurrency/Paper.tex	(revision 972540e714dedc02bc563d19e713b0a42b7e3abd)
@@ -228,5 +228,5 @@
 }
 
-\title{\texorpdfstring{Concurrency in \protect\CFA}{Concurrency in Cforall}}
+\title{\texorpdfstring{Advanced Control-flow in \protect\CFA}{Advanced Control-flow in Cforall}}
 
 \author[1]{Thierry Delisle}
@@ -241,14 +241,14 @@
 
 \abstract[Summary]{
-\CFA is a modern, polymorphic, \emph{non-object-oriented}, backwards-compatible extension of the C programming language.
-This paper discusses the concurrency and parallelism features in \CFA, and its runtime system.
+\CFA is a modern, polymorphic, non-object-oriented, backwards-compatible extension of the C programming language.
+This paper discusses the advanced control-flow features in \CFA, which include concurrency and parallelism, and its supporting runtime system.
 These features are created from scratch as ISO C's concurrency is low-level and unimplemented, so C programmers continue to rely on the C pthreads library.
-\CFA provides high-level control-flow mechanisms, like coroutines and lightweight (user) threads, and monitors for mutual exclusion and synchronization.
-A unique contribution of this work is allowing multiple monitors to be safely acquired \emph{simultaneously}.
+\CFA provides high-level control-flow mechanisms, like coroutines and user-level threads, and monitors for mutual exclusion and synchronization.
+A unique contribution of this work is allowing multiple monitors to be safely acquired \emph{simultaneously} (deadlock free), while integrating this capability with all monitor synchronization mechanisms.
 All features respect the expectations of C programmers, while being fully integrate with the \CFA polymorphic type-system and other language features.
 Experimental results show comparable performance of the new features with similar mechanisms in other concurrent programming-languages.
 }%
 
-\keywords{concurrency, parallelism, coroutines, threads, monitors, runtime, C, \CFA (Cforall)}
+\keywords{coroutines, concurrency, parallelism, threads, monitors, runtime, C, \CFA (Cforall)}
 
 
@@ -261,34 +261,62 @@
 \section{Introduction}
 
-This paper discusses the design of the high-level concurrency and parallelism features in \CFA, and its runtime.
-\CFA is a modern, polymorphic, \emph{non-object-oriented}, backwards-compatible extension of the C programming language~\cite{Moss18}.
-Within the \CFA framework, new concurrency features were created from scratch.
-While ISO \Celeven defines concurrency~\cite[\S~7.26]{C11}, it is largely wrappers for a subset of the pthreads library~\cite{Butenhof97,Pthreads}.
-Furthermore, \Celeven and pthreads concurrency is simple: create/join threads in a function and a few locks, which is low-level and error prone;
+This paper discusses the design of advanced, high-level control-flow extensions (especially concurrency and parallelism) in \CFA and its runtime.
+\CFA is a modern, polymorphic, non-object-oriented\footnote{
+\CFA has features often associated with object-oriented programming languages, such as constructors, destructors, virtuals and simple inheritance.
+However, functions \emph{cannot} be nested in structures, so there is no lexical binding between a structure and set of functions (member/method) implemented by an implicit \lstinline@this@ (receiver) parameter.},
+backwards-compatible extension of the C programming language~\cite{Moss18}.
+Within the \CFA framework, new control-flow features were created from scratch.
+ISO \Celeven defines only a subset of the \CFA extensions, and with respect to concurrency~\cite[\S~7.26]{C11}, the features are largely wrappers for a subset of the pthreads library~\cite{Butenhof97,Pthreads}.
+Furthermore, \Celeven and pthreads concurrency is basic, based on thread fork/join in a function and a few locks, which is low-level and error prone;
 no high-level language concurrency features exist.
-Interestingly, 8 years since publication of the \Celeven standard, neither gcc-8 nor clang-8 (most recent versions) support \Celeven @threads.h@, indicating little interest in the C concurrency approach.
-Finally, while the \Celeven standard does not state a concurrent threading-model, the strong association with pthreads suggests the threading model is kernel-level threading (1:1)~\cite{ThreadModel}.
-
-There has been a re-interest during the past decade in user-level (M:N, green) threading in new and old programming languages, and providing high-level constructs like coroutines, monitors, tasks, and actors for presenting advanced control-flow.
+Interestingly, almost a decade after publication of the \Celeven standard, neither gcc-8, clang-8 nor msvc-19 (most recent versions) support the \Celeven include @threads.h@, indicating little interest in the C concurrency approach.
+Finally, while the \Celeven standard does not state a concurrent threading-model, the historical association with pthreads suggests the threading model is kernel-level threading (1:1)~\cite{ThreadModel}.
+
+In contrast, there has been a renewed interest during the past decade in user-level (M:N, green) threading in old and new programming languages.
 As multi-core hardware became available in the 1980/90s, both user and kernel threading were examined.
 Kernel threading was chosen, largely because of its simplicity and fit with the simpler operating systems and hardware architectures at the time, which gave it a performance advantage~\cite{Drepper03}.
-Libraries like pthreads were developed for C and the Solaris operating-system switched from user (JDK 1.1~\cite{JDK1.1}) to kernel threads.
+Libraries like pthreads were developed for C, and the Solaris operating-system switched from user (JDK 1.1~\cite{JDK1.1}) to kernel threads.
 As a result, languages like Java, Scala~\cite{Scala}, Objective-C~\cite{obj-c-book}, \CCeleven~\cite{C11}, and C\#~\cite{Csharp} adopted the 1:1 kernel-threading model, with a variety of presentation mechanisms.
 From 2000 onwards, languages like Go~\cite{Go}, Erlang~\cite{Erlang}, Haskell~\cite{Haskell}, D~\cite{D}, and \uC~\cite{uC++,uC++book} have championed the M:N user-threading model, and many user-threading libraries have appeared~\cite{Qthreads,MPC,BoostThreads}, including putting green threads back into Java~\cite{Quasar}.
-Because advanced control-flow (including exception handling) is pervasive in a programming language and its runtime, these features must be understood by the language (i.e., not added via a library) to prevent invalidation by sequential optimizations~\cite{Buhr95a,Boehm05}.
-
-The main argument for user-level threading is matching the concurrency model with the programming-language style, versus adapting language concurrency to one general approach.
-For example, it is possible to provide coroutines, monitors, and tasks as specialized types in an object-oriented language, integrating these constructs to allow leveraging the type-system (static type-checking) and all other object-oriented capabilities~\cite{uC++}.
-The user-threading approach facilitates a simpler concurrency construction using thread objects and leveraging sequential patterns versus call-backs and events~\cite{vonBehren03}.
-As well, user-level threads are lighter weight than kernel threads, so there is less restriction on programming styles that encourage large numbers of threads performing smaller work-units to facilitate load balancing by the runtime~\cite{Verch12}.
-User threading is also able to layer multiple concurrency models into a single language (locks, monitors, tasks, actors, futures), so programmers can chose the model that best fits an application.
-Finally, it is possible to discretely fold locking and non-blocking I/O multiplexing into the language's I/O libraries, so threading implicitly dovetails with the I/O subsystem.
-Performant user-threading implementations (both time and space) are appearing that are competitive with direct kernel-threading implementations, while achieving the programming advantages of high concurrency levels and safety.
-
-Adding advanced control-flow to \CFA is similar to current and future extensions in \CCeleven through to \CCtwenty.
-However, we contend the \CFA extensions are demonstrably better than those proposed for \CC.
-For example, a unique contribution of this work is allowing multiple monitors to be safely acquired \emph{simultaneously} (deadlock free), while integrating this capability with all monitor synchronization mechanisms.
-As well, all control-flow features respect the expectations of C programmers, with statically type-safe interfaces that integrate with the \CFA polymorphic type-system and other language features.
-Experimental results show comparable performance of the new features with similar mechanisms in other concurrent programming-languages.
+The main argument for user-level threading is that they are lighter weight than kernel threads (locking and context switching do not cross the kernel boundary), so there is less restriction on programming styles that encourage large numbers of threads performing smaller work-units to facilitate load balancing by the runtime~\cite{Verch12}.
+As well, user-threading facilitates a simpler concurrency approach using thread objects that leverage sequential patterns versus events with call-backs~\cite{vonBehren03}.
+Finally, performant user-threading implementations (both time and space) are largely competitive with direct kernel-threading implementations, while achieving the programming advantages of high concurrency levels and safety.
+
+A further effort over the past decade is the development of language memory-models to deal with the conflict between certain language features and compiler/hardware optimizations.
+This issue can be rephrased as some features are pervasive (language and runtime) and cannot be safely added via a library to prevent invalidation by sequential optimizations~\cite{Buhr95a,Boehm05}.
+The consequence is that a language must be cognizant of these features and provide sufficient tools to program around any safety issues.
+For example, C created the @volatile@ qualifier to provide correct execution for @setjmp@/@logjmp@ (concurrency came later).
+The simplest solution is to provide a handful of complex qualifiers and functions (e.g., @volatile@ and atomics) allowing programmers to write consistent/race-free programs, often in the sequentially-consistent memory-model~\cite{Boehm12}.
+
+While having a sufficient memory-model allows sound libraries to be constructed, writing these libraries can quickly become awkward and error prone, and using these low-level libraries has the same issues.
+Essentially, using low-level explicit locks is the concurrent equivalent of assembler programming.
+Just as most assembler programming is replaced with programming in a high-level language, explicit locks can be replaced with high-level concurrency constructs in a programming language.
+The goal is to get the compiler to check for correct usage and follow any complex coding conventions implicitly.
+The drawback is that language constructs may preclude certain specialized techniques, therefore introducing inefficiency or inhibiting concurrency.
+For most concurrent programs, these drawbacks are insignificant in comparison to the speed of composition, and subsequent reliability and maintainability of the high-level concurrent program.
+(The same is true for high-level programming versus assembler programming.)
+Only very rarely should it be necessary to drop down to races and/or explicit locks to apply a specialized technique to achieve maximum speed or concurrency.
+As stated, this observation applies to non-concurrent forms of complex control-flow, like exception handling and coroutines.
+
+Adapting the programming language allows matching the control-flow model with the programming-language style, versus adapting to one general (sound) library/paradigm.
+For example, it is possible to provide exceptions, coroutines, monitors, and tasks as specialized types in an object-oriented language, integrating these constructs to allow leveraging the type-system (static type-checking) and all other object-oriented capabilities~\cite{uC++}.
+It is also possible to leverage call/return for blocking communication via new control structures, versus switching to alternative communication paradigms, like channels or message passing.
+As well, user threading is often a complementary feature, allowing light-weight threading to match with low-cost objects, while hiding the application/kernel boundary.
+User threading also allows layering of implicit concurrency models (no explicit thread creation), such executors, data-flow, actors, into a single language, so programmers can chose the model that best fits an algorithm.\footnote{
+All implicit concurrency models have explicit threading in their implementation, and hence, can be build from explicit threading;
+however, the reverse is seldom true, i.e., given implicit concurrency, e.g., actors, it is virtually impossible to create explicit concurrency, e.g., blocking thread objects.}
+Finally, with extended language features and user-level threading it is possible to discretely fold locking and non-blocking I/O multiplexing into the language's I/O libraries, so threading implicitly dovetails with the I/O subsystem.
+
+\CFA embraces language extensions and user-level threading to provide advanced control-flow and concurrency.
+We attempt to show the \CFA extensions and runtime are demonstrably better than those proposed for \CC and other concurrent, imperative programming languages.
+The contributions of this work are:
+\begin{itemize}
+\item
+allowing multiple monitors to be safely acquired \emph{simultaneously} (deadlock free), while seamlessly integrating this capability with all monitor synchronization mechanisms.
+\item
+all control-flow features respect the expectations of C programmers, with statically type-safe interfaces that integrate with the \CFA polymorphic type-system and other language features.
+\item
+experimental results show comparable performance of the new features with similar mechanisms in other concurrent programming-languages.
+\end{itemize}
 
 \begin{comment}
@@ -587,44 +615,7 @@
 
 
-\section{Concurrency}
-\label{s:Concurrency}
-
-At its core, concurrency is based on multiple call-stacks and scheduling threads executing on these stacks.
-Multiple call stacks (or contexts) and a single thread of execution, called \newterm{coroutining}~\cite{Conway63,Marlin80}, does \emph{not} imply concurrency~\cite[\S~2]{Buhr05a}.
-In coroutining, the single thread is self-scheduling across the stacks, so execution is deterministic, \ie the execution path from input to output is fixed and predictable.
-A \newterm{stackless} coroutine executes on the caller's stack~\cite{Python} but this approach is restrictive, \eg preventing modularization and supporting only iterator/generator-style programming;
-a \newterm{stackful} coroutine executes on its own stack, allowing full generality.
-Only stackful coroutines are a stepping stone to concurrency.
-
-The transition to concurrency, even for execution with a single thread and multiple stacks, occurs when coroutines also context switch to a \newterm{scheduling oracle}, introducing non-determinism from the coroutine perspective~\cite[\S~3]{Buhr05a}.
-Therefore, a minimal concurrency system is possible using coroutines (see Section \ref{coroutine}) in conjunction with a scheduler to decide where to context switch next.
-The resulting execution system now follows a cooperative threading-model, called \newterm{non-preemptive scheduling}.
-
-Because the scheduler is special, it can either be a stackless or stackful coroutine.
-For stackless, the scheduler performs scheduling on the stack of the current coroutine and switches directly to the next coroutine, so there is one context switch.
-For stackful, the current coroutine switches to the scheduler, which performs scheduling, and it then switches to the next coroutine, so there are two context switches.
-A stackful scheduler is often used for simplicity and security.
-
-Regardless of the approach used, a subset of concurrency related challenges start to appear.
-For the complete set of concurrency challenges to occur, the missing feature is \newterm{preemption}, where context switching occurs randomly between any two instructions, often based on a timer interrupt, called \newterm{preemptive scheduling}.
-While a scheduler introduces uncertainty in the order of execution, preemption introduces uncertainty about where context switches occur.
-Interestingly, uncertainty is necessary for the runtime (operating) system to give the illusion of parallelism on a single processor and increase performance on multiple processors.
-The reason is that only the runtime has complete knowledge about resources and how to best utilized them.
-However, the introduction of unrestricted non-determinism results in the need for \newterm{mutual exclusion} and \newterm{synchronization} to restrict non-determinism for correctness;
-otherwise, it is impossible to write meaningful programs.
-Optimal performance in concurrent applications is often obtained by having as much non-determinism as correctness allows.
-
-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 \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.
-Hence, concurrent programs should be written using high-level mechanisms, and only step down to lower-level mechanisms when performance bottlenecks are encountered.
-
-
-\subsection{Coroutines: A Stepping Stone}\label{coroutine}
-
-While the focus of this discussion is concurrency and parallelism, it is important to address coroutines, which are a significant building block of a concurrency system (but not concurrent among themselves).
+\section{Coroutines: A Stepping Stone}\label{coroutine}
+
+Advanced controlWhile the focus of this discussion is concurrency and parallelism, it is important to address coroutines, which are a significant building block of a concurrency system (but not concurrent among themselves).
 Coroutines are generalized routines allowing execution to be temporarily suspended and later resumed.
 Hence, unlike a normal routine, a coroutine may not terminate when it returns to its caller, allowing it to be restarted with the values and execution location present at the point of suspension.
@@ -1094,4 +1085,41 @@
 \end{cquote}
 The combination of these two approaches allows an easy and concise specification to coroutining (and concurrency) for normal users, while more advanced users have tighter control on memory layout and initialization.
+
+
+\section{Concurrency}
+\label{s:Concurrency}
+
+At its core, concurrency is based on multiple call-stacks and scheduling threads executing on these stacks.
+Multiple call stacks (or contexts) and a single thread of execution, called \newterm{coroutining}~\cite{Conway63,Marlin80}, does \emph{not} imply concurrency~\cite[\S~2]{Buhr05a}.
+In coroutining, the single thread is self-scheduling across the stacks, so execution is deterministic, \ie the execution path from input to output is fixed and predictable.
+A \newterm{stackless} coroutine executes on the caller's stack~\cite{Python} but this approach is restrictive, \eg preventing modularization and supporting only iterator/generator-style programming;
+a \newterm{stackful} coroutine executes on its own stack, allowing full generality.
+Only stackful coroutines are a stepping stone to concurrency.
+
+The transition to concurrency, even for execution with a single thread and multiple stacks, occurs when coroutines also context switch to a \newterm{scheduling oracle}, introducing non-determinism from the coroutine perspective~\cite[\S~3]{Buhr05a}.
+Therefore, a minimal concurrency system is possible using coroutines (see Section \ref{coroutine}) in conjunction with a scheduler to decide where to context switch next.
+The resulting execution system now follows a cooperative threading-model, called \newterm{non-preemptive scheduling}.
+
+Because the scheduler is special, it can either be a stackless or stackful coroutine.
+For stackless, the scheduler performs scheduling on the stack of the current coroutine and switches directly to the next coroutine, so there is one context switch.
+For stackful, the current coroutine switches to the scheduler, which performs scheduling, and it then switches to the next coroutine, so there are two context switches.
+A stackful scheduler is often used for simplicity and security.
+
+Regardless of the approach used, a subset of concurrency related challenges start to appear.
+For the complete set of concurrency challenges to occur, the missing feature is \newterm{preemption}, where context switching occurs randomly between any two instructions, often based on a timer interrupt, called \newterm{preemptive scheduling}.
+While a scheduler introduces uncertainty in the order of execution, preemption introduces uncertainty about where context switches occur.
+Interestingly, uncertainty is necessary for the runtime (operating) system to give the illusion of parallelism on a single processor and increase performance on multiple processors.
+The reason is that only the runtime has complete knowledge about resources and how to best utilized them.
+However, the introduction of unrestricted non-determinism results in the need for \newterm{mutual exclusion} and \newterm{synchronization} to restrict non-determinism for correctness;
+otherwise, it is impossible to write meaningful programs.
+Optimal performance in concurrent applications is often obtained by having as much non-determinism as correctness allows.
+
+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 \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.
+Hence, concurrent programs should be written using high-level mechanisms, and only step down to lower-level mechanisms when performance bottlenecks are encountered.
 
 
Index: doc/papers/concurrency/mail
===================================================================
--- doc/papers/concurrency/mail	(revision c884f2d126e0594e6d9223e0afc85a588178f92f)
+++ doc/papers/concurrency/mail	(revision 972540e714dedc02bc563d19e713b0a42b7e3abd)
@@ -27,2 +27,415 @@
 
 Software: Practice and Experience Editorial Office
+
+
+
+Date: Wed, 3 Oct 2018 21:25:28 +0000
+From: Richard Jones <onbehalfof@manuscriptcentral.com>
+Reply-To: R.E.Jones@kent.ac.uk
+To: tdelisle@uwaterloo.ca, pabuhr@uwaterloo.ca
+Subject: Software: Practice and Experience - Decision on Manuscript ID
+ SPE-18-0205
+
+03-Oct-2018
+
+Dear Dr Buhr,
+
+Many thanks for submitting SPE-18-0205 entitled "Concurrency in C∀" to Software: Practice and Experience.
+
+In view of the comments of the referees found at the bottom of this letter, I cannot accept your paper for publication in Software: Practice and Experience. I hope that you find the referees' very detailed comments helpful.
+
+Thank you for considering Software: Practice and Experience for the publication of your research.  I hope the outcome of this specific submission will not discourage you from submitting future manuscripts.
+
+Yours sincerely,
+
+
+Prof. Richard Jones
+Editor, Software: Practice and Experience
+R.E.Jones@kent.ac.uk
+
+Referee(s)' Comments to Author:
+
+Reviewing: 1
+
+Comments to the Author
+"Concurrency in Cforall" presents a design and implementation of a set of standard concurrency features, including coroutines, user-space and kernel-space threads, mutexes, monitors, and a scheduler, for a polymorphic derivation of C called Cforall.
+
+Section 2 is an overview of sequential Cforall that does not materially contribute to the paper. A brief syntax explanation where necessary in examples would be plenty.
+
+Section 3 begins with with an extensive discussion of concurrency that also does not materially contribute to the paper. A brief mention of whether a particular approach implements cooperative or preemptive scheduling would be sufficient. Section 3 also makes some unfortunate claims, such as C not having threads -- C does in fact define threads, and this is noted as being true in a footnote, immediately after claiming that it does not. The question remains why the C11 parallelism design is insufficient and in what way this paper proposes to augment it. While I am personally a proponent of parallel programming languages, backing the assertion that all modern languages must have threading with citations from 2005 ignores the massive popularity of modern non-parallel languages (Javascript, node.js, Typescript, Python, Ruby, etc.) and parallel languages that are not thread based, although the authors are clearly aware of such approaches.
+
+Sections 3.1 and 3.2 dicusses assymetric and symmetric coroutines. This also does not seem to materially contribute to a paper that is ostensibly about concurrency in a modern systems programming language. The area of coroutines, continuations, and generators is already well explored in the context of systems languages, including compilation techniques for these constructs that are more advanced than the stack instantiation model discussed in the paper.
+
+Section 3.3 describes threads in Cforall, briefly touching on user-space vs. kernel-space thread implementations without detailing the extensive practical differences. It is unclear how the described interface differes from C++11 threads, as the description seems to center on an RAII style approach to joining in the destructor.
+
+Section 4 briefly touches on a collection of well known synchronisation primitives. Again, this discussion does not materially contribute to the paper.
+
+Section 5 describes monitors, which are a well known and well researched technique. The Cforall implementation is unsurprising. The "multi-acquire semantics" described are not a contribution of this paper, as establishing a stable order for lock acquisition is a well known technique, one example of which is the C++ std::scoped_lock.
+
+Section 6 is a discussion of scheduling that does not appear to be informed by the literature. There is no discussion of work-stealing vs. work-scheduling, static vs. dynamic priorities, priority inversion, or fairness. There is a claim in secion 6.1 for a novel technique, partial signalling, that appears to be a form of dynamic priority, but no comparison is made. In section 6.6, a very brief mention of other synchronisation techniques is made, without reference to current techniques such as array-based locks, CLH or MCS queue locks, RCU and other epoch-based mechanisms, etc. Perhaps these are considered out of scope.
+
+Section 7 discusses parallelism, but does not materially contribute to the paper. It is claimed that preemption is necessary to implement spinning, which is not correct, since two cores can implement a spinning based approach without preemption. It is claimed that with thread pools "concurrency errors return", but no approach to removing concurrency errors with either preemptive or cooperatively scheduled user threads has been proposed in the paper that would not also apply to thread pools.
+
+Section 8 is intended to describe the Cforall runtime structure, but does so in a way that uses terminology in an unfamiliar way. The word cluster is more usually used in distributed systems, but here refers to a process. The term virtual processor is more usually used in hardware virtualisation, but here refers to a kernel thread. The term debug kernel is more usually used in operating systems to refer to kernels that have both debug info and a method for using a debugger in kernel space, but here refers to a debug build of a user-space process. This section does not materially contribute to the paper.
+
+Section 9 is intended to describe the Cforall runtime implementation. It makes some unusual claims, such as C libraries migrating to stack chaining (stack chaining was an experimental GCC feature that has been abandoned, much as it has been abandoned in both Go and Rust).
+
+The performance measurements in section 10 are difficult to evaluate. While I appreciate that comparable concurrency benchmarks are very difficult to write, and the corpus of existing benchmarks primarily boils down to the parallel programs in the Computer Language Benchmark Game, the lack of detail as to what is being measured in these benchmarks (particularly when implemented in other languages) is unfortunate. For example, in table 3, the benchmark appears to measure uncontended lock access, which is not a useful micro-benchmark.
+
+It is not clear what the contributions of this paper are intended to be. A concise listing of the intended contributions would be helpful. Currently, it appears that the paper makes neither PL contributions in terms of novel features in Cforall, nor does it make systems contributions in terms of novel features in the runtime.
+
+
+Reviewing: 2
+
+Comments to the Author
+This article presents the design and rationale behind the concurrency
+features of C-forall, a new low-level programming language.  After an
+introduction that defines a selection of standard terminology, section
+2 gives crucial background on the design of the C-forall language.
+Section 3 then starts the core of the article, discussing the
+language's support for "concurrency" which in this case means
+coroutines and threads; a very brief Section 4 builds on section 3
+with a discussion of lower level synchronizations.  Section 5 the
+presents the main features of concurrency control in C-forall:
+monitors and mutexes. Section 6 then extends monitors with condition
+variables to to support scheduling, and a very brief section 7
+discusses preemption and pooling. Section 8 discusses the runtime
+conceptual model, section 9 gives implementation detail, and section
+10 briefly evaluates C-forall's performance via five concurrent
+micro benchmarks. Finally section 11 concludes the article, and then
+section 12 presents some future work.  
+
+
+At the start of section 7, article lays out its rationale: that while
+"historically, computer performance was about processor speeds" but
+"Now, high-performance applications must care about parallelism,
+which requires concurrency". The doomsayers trumpeting the death of
+Moore's law have been proved correct at last, with CPUs sequential
+performance increasing much more slowly than the number of cores
+within each die. This means programmers --- especially low-level,
+systems programmers --- must somehow manage the essential complexity
+of writing concurrent programs to run in parallel in multiple threads
+across multiple cores. Unfortunately, the most venerable widely used
+systems programming language, C, supports parallelism only via an
+e.g. the threads library.  This article aims to integrate concurrent
+programming mechanisms more closely into a novel low-level C-based
+programming language, C-forall. The article gives an outline of much of
+C-forall, presents a series of concurrency mechanisms, and finally
+some microbenchmark results.  The article is detailed, comprehensive,
+and generally well written in understandable English.
+
+My main concern about the article are indicated by the fact that the
+best summary of the problem the design of concurrent C-forall sets
+out to solve is buried more than halfway through the article in section
+7, as above, and then the best overview of the proposed solution is
+given in the 2nd, 4th and 5th sentence of the conclusion:
+
+   "The approach provides concurrency based on a preemptive M:N
+    user-level threading-system, executing in clusters, which
+    encapsulate scheduling of work on multiple kernel threads
+    providing parallelism... High-level objects (monitor/task) are the
+    core mechanism for mutual exclusion and synchronization. A novel
+    aspect is allowing multiple mutex-objects to be accessed
+    simultaneously reducing the potential for deadlock for this
+    complex scenario."
+
+That is, in my reading of the article, it proceeds bottom up rather
+than top down, and so my main recommendation is to essentially reverse
+the order of the article, proceeding from the problem to be solved,
+the high level architecture of the proposed solutions, and then going
+down to the low-level mechanisms.  My biggest problem reading the
+article was for explanations of why a particular decision was taken,
+or why a particular mechanism may be used --- often this description
+is actually later in the article, but at that point it's too late for
+the reader.  I have tried to point out most of these places in the
+detailed comments below.
+
+My second concern is that the article makes several claims that are
+not really justified by the design or implementation in the article.
+These include claims that this approach meets the expectations of C
+programmers, is minimal, is implemented in itself, etc.  The article
+doesn't generally offer evidence to support these assertions (for many
+of them, that would require empirical studies of programmers, or at
+least corpus studies). The solution here is to talk about motivations
+for the design choices "we made these decisions hoping that C
+programmers would be comfortable" rather than claims of fact "C
+programmers are comfortable".  Again I attempt to point these out below.
+
+* abstract: needs to characterize the work top down, and not make
+  claims "features respect the expectations of C programmers" that
+  are not supported empirically.
+
+* p1 line 14 "integrated"
+
+* introduction needs to introduce the big ideas and scope of the
+  article, not define terms.  Some of the terms / distinctions are
+  non-standard (e.g. the distinction between "concurrency" and
+  "parallelism") and can be avoided by using more specific terms
+  (mutual exclusion, synchronization, parallel execution. etc).
+
+* to me this article introduces novel language features, not just an
+  API.  Similarly, it doesn't talk about any additions "to the
+  language translator" - i.e compiler changes! - rather about language
+  features.
+
+
+* section 2 lines 6-9 why buy this fight against object-orientation?
+  this article doesn't need to make this argument, but needs to do a
+  better job of it if it does (see other comments below)
+
+* sec 2.1 - are these the same as C++. IF so, say so, if not, say why
+  not.
+
+* 2.2 calling it a "with statement" was confusing, given that a with
+  clause can appear in a routine declaration with a shorthand syntax.
+
+* 2.3 again compare with C++ and Java (as well as Ada)
+
+* line 9 "as we will see in section 3"
+
+* 2.4 I really quite like this syntax for operators, destructors not
+  so much.
+
+* 2.5 and many places elsewhere. Always first describe the semantics
+  of your language constructs, then describe their properties, then
+  compare with e.g. related languages (mostly C++ & Java?).  E.g in
+  this case, something like:
+
+  "C-forall includes constructors, which are called to initialize
+  newly allocated objects, and constructors, which are called when
+  objects are deallocated. Constructors and destructors are written as
+  functions returning void, under the special names "?{}" for
+  constructors and "^{}" for destructors: constructors may be
+  overridden, but destructors may not be.  The semantics of C-forall's
+  constructors and destructors are essentially those of C++."
+
+  this problem repeats many times throughout the article and should be
+  fixed everywhere.
+
+
+* 2.6 again, first describe then properties then comparison.
+   in this case, compare e.g. with C++ templates, Java/Ada generics
+   etc.
+
+* why special case forward declarations? It's not 1970 any more.
+
+* what are traits?  structural interfaces (like Go interfaces) or
+  nominal bindings?
+
+* section 3 - lines 2-30, also making very specific global definitions
+  as in the introduction. The article does not need to take on this
+  fight either, rather make clear that this is the conceptual model in
+  C-forall. (If the article starts at the top and works down, that may
+  well follow anyway).
+
+* "in modern programming languages... unacceptable"; "in a
+  system-level language.. concurrent programs should be written with
+  high-level features" - again, no need to take on these fights.
+
+* 3.1 onwards; I found all this "building" up hard to follow.
+  also it's not clear a "minimal" API must separately support
+  coroutines, threads, fibres, etc
+
+* FIG 2B - where's the output?
+  syntax "sout | next(f1) | next(f2) | endl" nowhere explained
+    why not use C++s' << and >>
+
+* FIG 3 be clearer, earlier about the coroutine" constructor syntax
+
+** ensure all figures are placed *after* their first mention in the
+   text. consider interleaving smaller snippets of text rather than
+   just referring to large figures
+
+* sec 3.1 p7 etc,. need more context / comparison e.g. Python
+  generators etc.
+
+* FIGURE 4 is this right?  should there a constructor for Cons taking
+  a Prod?
+
+
+* sec 3.2 order of constructors depends on the language.  more
+  generally, if the article is going to make arguments against OO
+  (e.g. section 2) then the article needs to explain, in detail, why
+  e.g. coroutine, thread, etc *cannot* be classes / objects.
+
+* "type coroutine_t must be an abstract handle.. descriptor and is
+  stack are non-copyable" - too many assumptions in here (and other
+  similar passages) that are not really spelled out in detail.
+
+* p10 line 4 introduces "coroutine" keyword. needs to give its
+  semantics. also needs to introduce and define properties and compare
+  before all the examples using coroutines.
+
+* p10 again, trait semantics need to be better defined 
+
+* 3.3 should be an introduction to this section. Note that section
+  titles are not part of the text of the article.
+
+* what's the difference between "coroutines" and "user threads" (and
+  "fibres?")
+
+* what's a "task type" or an "interface routine"  or "underlying
+  thread"
+
+* section 4 - "... meaningless". nope some semantics are possible
+  e.g. if there's a memory model.
+
+* whatare "call/return based languages"
+
+* p12 - what if a programmer wants to join e.g. "1st of N" or "1st 3 of N"
+  threads rather than all threads in order
+
+* 4.1 p12 13-25, again it's not clear where this is going.  presenting the model
+  top down may hopefully resolve this
+
+* section 4 should be merged e.g. into sec 3 (or 5)
+
+
+
+* section 5 p13 what's "routine" scope. "call/return paradigm"
+
+* thread/ coroutine declarations, traits etc, all look pretty close to
+  inheritance. why wouldn't inheritance work?
+
+* open/closed locks = free/acquired free locks?
+
+* testability?
+
+* p14 lines 14-20 I had trouble following this.  e.g/. what's the
+  difference between "a type that is a monitor" and "a type that looks
+  like a monitor"?  why?
+
+* line 39 - what's an "object-oriented monitor"?    Java?
+    there is no one OO model of such things.
+
+* line 47 significant asset - how do you know?
+
+* how could this e.g. build a reader/writer lock
+
+* *p15 what's the "bank account transfer problem"
+
+*p16 lines6-10  why? explain?
+
+*p17 semantics of arrays of conditions is unclear
+     given e.g. previous comments about arrays of mutexes.
+
+*p18 define "spurious wakeup"
+
+*p18 line 44 - "a number of approaches were examined"?  which
+ approaches? examined by whom?  if this is a novel contribution, needs
+ rather more there, and more comparison with related work 
+
+* FIG 8 consider e.g. sequence diagrams rather than code to show these
+  cases
+
+* 6.2 p19 line 5 "similarly, monitor routines can be added at any
+  time" really?  I thought C-forall was compiled? there's a big
+  difference between "static" and "dynamic" inheritance. which is this
+  closer to?
+
+* line 25 "FIgure 9 (B) shows the monitor implementation"
+   I didn't understand this, especially not as an implementation.
+
+* section 6.6 - if the article is to make claims about completeness,
+  about supporting low and high level operations, then this must be
+  expanded to give enough detail to support that argument
+
+* "truest realization" huh?
+
+* section 7 should be merged into 6 or 8.
+  it's not clear if this is exploring rejected alternatives,
+  out outlining different features offered by C-forall, or what.
+
+
+* sec 7.2 how do the other threads in sections 5 & 6 relate to the
+  user threads, fibres, etc here;
+
+* sec 8.1 I found these sections hard to follow. how is a cluster a
+  "collection of threads and virtual processors... like a virtual
+  machine"? Where do the thread pools from 7.3 fit in?
+
+*  sec 8.3 is out of place, probably unneeded in the paper
+
+* section 9 dives straight into details with no overview.  Section 9
+  seems very detailed, and depends on assumptions or details that are
+  not in the article.
+
+* section 10 covers only microbenchmarks. are there any moderate sized
+  macrobenchmarks that can compare across the different systems?
+  (e.g the Erlang Ring?)
+
+* sec 11 claims that "the entire C-forall runtime system are written
+  in C-forall". The article doesn't
+
+
+* future work should precede conclusion, not follow it
+
+* the article should have a related work section (2-3 pages) comparing
+  the design overall with various competing designs (C++, Java, go,
+  Rust,...)
+
+To encourage accountability, I'm signing my reviews in 2018. For the record, I am James Noble, kjx@ecs.vuw.ac.nz. 
+
+Reviewing: 3
+
+Comments to the Author
+This paper describes the design and implementation of coroutine- and thread-based concurrency in the C-for-all (I will write "C\/") system, a considerably extended form of the C language with many concurrency features.
+
+It first provides an overview of the non-concurrency-related aspects of the host language (references, operator overloading, generics, etc.), then addresses several technical issues around concurrency, including the multi-monitor design, bulk acquiring of locks (including deadlock-avoiding management of acquisition order), solutions to difficult scheduling problems around these, and implementation of monitors in the presence of separate compilation. It also presents empirical data showing the execution times of several microbenchmarks in comparison with other threaded concurrency systems, in support of the claim that the implementation is competitive with them.
+
+Overall the impression I gained is that this is a substantial system into which have gone much thought and effort.
+
+However, the present paper is not written so as to communicate sufficiently clearly the novel practices or experiences that emerged from that effort. This manifests itself in several ways.
+
+The system is described in general, rather than with a focus on novel insights or experiences. It was not until page 18 that I found a statement that hinted at a possible core contribution: "Supporting barging prevention as well as extending internal scheduling to multiple monitors is the main source of complexity in design and implementation of C\/ concurrency." Even then, it is unclear whether such challenges have already been surmounted in prior systems, or what other challenges the paper may also be covering. The most complete list of claims appears to be in the Conclusion (section 11; oddly not the last section), although not everything listed is a novel feature of the work (e.g. N:M threading models are an old idea). This presentation needs to be completely inverted, to focus from the outset on the claimed novel/noteworthy experiences that the work embodies.
+
+The text describing the system's motivation is unconvincing on one point: the claim that library support for threading in C is "far from widespread" (p5, footnote A). The pthreads library API is standardised, albeit not in the C language specification but rather in POSIX -- a widespread standard indeed. (With systems languages, even if the language does not define a feature, it of course does not follow that that feature is not available -- since such languages permit extension of their own runtime and/or toolchain.) Of course, the combination of C and pthreads does not provide close to the full complement of C\/-supported features, so it is easy to make a case for C\/'s targeted "gap in the market". But again, a presentation focused on novel aspects would bring this out and enable the reader to learn from the authors' efforts much more readily.
+
+Certain sections of the text read like a tutorial on concurrency... which is potentially valuable, but does not seem to belong here. For example, much effort is spent introducing the notions of "synchronization" and "mutual exclusion", including the whole of Section 4.2. Presently it is unclear how this content supports the findings/experiences that the paper is detailing.
+
+Similarly, section 8 reads mostly as a basic introduction to user versus kernel threading implementations (including hybrid models such as N:M scheduling), and appears superfluous to this paper. Mixed into this are details of C\/'s specific approach. These could instead be stated directly, with references to handle the unlikely case where the reader is unfamiliar.
+
+I also found the definitions of certain terms through the paper a bit non-standard, for unclear reasons. For example, why "condition lock" rather than the standard "condition variable" (if indeed that is what is intended)? To say that "synchronisation" is about "timing" strikes me as potentially confusing, since in truth synchronisation concerns only relative timing, i.e. ordering. (Even ordering is something of a derived concept -- since of course, most commonly, control over ordering is built atop synchronisation primitives, rather than being provided directly by them.)
+
+The empirical data presented is a reasonable start at characterising the implementation's performance. However, it currently suffers certain flaws.
+
+Firstly, it is not clear what is being claimed. The data cannot really be said to "verify the implementation" (section 10). Presumably the claim is that the system is competitive with other systems offering reasonably high-level concurrency constructs (Java monitors, Go channels, etc.) and/or on low-level facilities (mutexes, coroutines). A claim of this form, emphasising the latter, does eventually appear in the Conclusion, but it needs to be made explicitly during the presentation of the experiments. Shifting the focus towards higher-level features may be a better target, since this appears to be C\/'s main advance over pthreads and similar libraries.
+
+It appears some additional or alternative competitor systems might be a better match. For example, many green-thread or N:M libraries for C exist (libdill/libmill, Marcel, even GNU Pth). It would be instructive to compare with these.
+
+It would help greatly if the "functionally identical" benchmark code that was run on the competing systems were made available somewhere. Omitting it from the main text of the paper is understandable, since it would take too much space, but its details may still have a critical bearing on the results.
+
+In some cases it simply wasn't clear what is being compared. In Table 3, what are "FetchAdd + FetchSub"? I'm guessing this is some open-coded mutex using C++ atomics, but (unless I'm missing something) I cannot see an explanation in the text.
+
+The reports of variance (or, rather, standard deviation) are not always plausible. Is there really no observable variation in three of Table 3's cases? At the least, I would appreciate more detail on the measures taken to reduce run-time variance (e.g. disabling CPU throttling perhaps?).
+
+The text habitually asserts the benefits of C\/'s design without convincing argument. For example, in 2.1, do C\/'s references really reduce "syntactic noise"? I am sympathetic to the problem here, because many design trade-offs simply cannot be evaluated without very large-scale or long-term studies. However, the authors could easily refrain from extrapolating to a grand claim that cannot be substantiated. For example, instead of saying C\/ is "expressive" or "flexible" or "natural", or (say) that fork/join concurrency is "awkward and unnecessary" (p11), it would be preferable simply to give examples of the cases are captured well in the C\/ design (ideally together with any less favourable examples that illustrate the design trade-off in question) and let them speak for themselves.
+
+One thing I found confusing in the presentation of coroutines is that it elides the distinction between "coroutines" (i.e. their definitions) and activations thereof. It would be helpful to make this clearer, since at present this makes some claims/statements hard to understand. For example, much of 3.2 talks about "adding fields", which implies that a coroutine's activation state exists as fields in a structured object -- as, indeed, it does in C\/. This is non-obvious because in a more classical presentation of coroutines, their state would live not in "fields" but in local variables. Similarly, the text also talks about composition of "coroutines" as fields within other "coroutines", and so on, whereas if I understand correctly, these are also activations. (By later on in the text, the "C\/ style" of such constructs is clear, but not at first.)
+
+I was expecting a reference to Adya et al's 2002 Usenix ATC paper, on the topic of "fibers" and cooperative threading generally but also for its illustrative examples of stack ripping (maybe around "linearized code is the bane of device drivers", p7, which seems to be making a similar observation).
+
+Minor comments:
+
+The writing is rather patchy. It has many typos, and also some cases of "not meaning what is said", unclear allusions, etc.. The following is a non-exhaustive list.
+
+- p2 line 7: "C has a notion of objects" -- true, but this is not intended as "object" in anything like the same sense as "object-oriented", so raising it here is somewhere between confusing and meaningless.
+
+- lots of extraneous hyphenation e.g "inheritance-relationships", "critical-section", "mutual-exclusion", "shared-state" (as a general rule, only hyphenate noun phrases when making an adjective out of them)
+
+- p4 "impossible in most type systems" -- this is not a property of the "type system" as usually understood, merely the wider language design
+
+- p17: "release all acquired mutex types in the parameter list" should just say "release all acquired mutexes that are designated in the parameter list" (it is not "types" that are being released or acquired);
+
+- p19: "a class includes an exhaustive list of operations" -- except it is definitively *not* exhaustive, for the reasons given immediately afterwards. I do see the problem here, about separate compilation meaning that the space of functions using a particular type is not bounded at compile time, but that needs to be identified clearly as the problem. (Incidentally, one idea is that perhaps this mapping onto a dense space could be solved at link- or load-time, in preference to run-time indirection.)
+
+- p22: in 6.5, the significance of this design decision ("threads... are monitors") was still not clear to me.
+
+- p22: [user threads are] "the truest realization of concurrency" sounds like unnecessary editorializing (many systems can exist that can also encode all others, without necessarily giving one supremacy... e.g. actors can be used to encode shared-state concurrency).
+
+- p24: on line 19, the necessary feature is not "garbage collection" but precise pointer identification (which is distinct; not all GCs have it, and it has other applications besides GC)
+
+- p24: lines 32-39 are very dense and of unclear significance; an example, including code, would be much clearer.
+
+- p25: "current UNIX systems" seems to mean "Linux", so please say that or give the behaviour or some other modern Unix (I believe Solaris is somewhat different, and possibly the BSDs too). Also, in the explanation of signal dynamics, it would be useful to adopt the quotation's own terminology of "process-directed" signals. Presumably the "internal" thread-directed signals were generated using tgkill()? And presumably the timer expiry signal is left unblocked only on the thread (virtual processor) running the "simulation"? (Calling it a "simulation" is a bit odd, although I realise it is borrowing the concept of a discrete event queue.)
+
Index: libcfa/src/iostream.cfa
===================================================================
--- libcfa/src/iostream.cfa	(revision c884f2d126e0594e6d9223e0afc85a588178f92f)
+++ libcfa/src/iostream.cfa	(revision 972540e714dedc02bc563d19e713b0a42b7e3abd)
@@ -10,6 +10,6 @@
 // Created On       : Wed May 27 17:56:53 2015
 // Last Modified By : Peter A. Buhr
-// Last Modified On : Mon Dec 24 18:33:40 2018
-// Update Count     : 589
+// Last Modified On : Mon Mar  4 20:57:24 2019
+// Update Count     : 593
 //
 
@@ -27,4 +27,22 @@
 
 forall( dtype ostype | ostream( ostype ) ) {
+	ostype & ?|?( ostype & os, zero_t ) {
+		if ( sepPrt( os ) ) fmt( os, "%s", sepGetCur( os ) );
+		fmt( os, "%d", 0n );
+		return os;
+	} // ?|?
+	void ?|?( ostype & os, zero_t z ) {
+		(ostype &)(os | z); nl( os );
+	} // ?|?
+
+	ostype & ?|?( ostype & os, one_t ) {
+		if ( sepPrt( os ) ) fmt( os, "%s", sepGetCur( os ) );
+		fmt( os, "%d", 1n );
+		return os;
+	} // ?|?
+	void ?|?( ostype & os, one_t o ) {
+		(ostype &)(os | o); nl( os );
+	} // ?|?
+
 	ostype & ?|?( ostype & os, bool b ) {
 		if ( sepPrt( os ) ) fmt( os, "%s", sepGetCur( os ) );
Index: libcfa/src/iostream.hfa
===================================================================
--- libcfa/src/iostream.hfa	(revision c884f2d126e0594e6d9223e0afc85a588178f92f)
+++ libcfa/src/iostream.hfa	(revision 972540e714dedc02bc563d19e713b0a42b7e3abd)
@@ -10,6 +10,6 @@
 // Created On       : Wed May 27 17:56:53 2015
 // Last Modified By : Peter A. Buhr
-// Last Modified On : Mon Dec 24 18:33:40 2018
-// Update Count     : 220
+// Last Modified On : Tue Feb 26 16:57:22 2019
+// Update Count     : 221
 //
 
@@ -62,4 +62,9 @@
 
 forall( dtype ostype | ostream( ostype ) ) {
+	ostype & ?|?( ostype &, zero_t );
+	void ?|?( ostype &, zero_t );
+	ostype & ?|?( ostype &, one_t );
+	void ?|?( ostype &, one_t );
+
 	ostype & ?|?( ostype &, bool );
 	void ?|?( ostype &, bool );
Index: tests/.expect/io1.txt
===================================================================
--- tests/.expect/io1.txt	(revision c884f2d126e0594e6d9223e0afc85a588178f92f)
+++ tests/.expect/io1.txt	(revision 972540e714dedc02bc563d19e713b0a42b7e3abd)
@@ -1,6 +1,6 @@
 9 6 28 0 7 1 2
-1 2 3
-123
-123
+0 1 2 3
+0123
+0123
 
 opening delimiters
Index: tests/io1.cfa
===================================================================
--- tests/io1.cfa	(revision c884f2d126e0594e6d9223e0afc85a588178f92f)
+++ tests/io1.cfa	(revision 972540e714dedc02bc563d19e713b0a42b7e3abd)
@@ -10,6 +10,6 @@
 // Created On       : Wed Mar  2 16:56:02 2016
 // Last Modified By : Peter A. Buhr
-// Last Modified On : Fri Dec 21 16:02:55 2018
-// Update Count     : 114
+// Last Modified On : Mon Mar  4 21:42:47 2019
+// Update Count     : 115
 //
 
@@ -19,7 +19,7 @@
 	int x = 3, y = 5, z = 7;
 	sout | x * 3 | y + 1 | z << 2 | x == y | (x | y) | (x || y) | (x > z ? 1 : 2);
-	sout | 1 | 2 | 3;
-	sout | '1' | '2' | '3';
-	sout | 1 | "" | 2 | "" | 3;
+	sout | 0 | 1 | 2 | 3;
+	sout | '0' | '1' | '2' | '3';
+	sout | 0 | "" | 1 | "" | 2 | "" | 3;
 	sout | nl;