Index: doc/papers/general/Paper.tex =================================================================== --- doc/papers/general/Paper.tex (revision 82c367d755e131d264edfb331d24d316b2e338bd) +++ doc/papers/general/Paper.tex (revision ea46db7297c45707f04194d6fafa0612eaa4f569) @@ -990,5 +990,158 @@ \section{Control Structures} -\CFA identifies missing and problematic control structures in C, and extends and modifies these control structures to increase functionality and safety. +\CFA identifies inconsistent, problematic, and missing control structures in C, and extends, modifies, and adds to control structures to increase functionality and safety. + + +\subsection{\texorpdfstring{\LstKeywordStyle{if} Statement}{if Statement}} + +The @if@ expression allows declarations, similar to @for@ declaration expression: +\begin{cfa} +if ( int x = f() ) ... $\C{// x != 0}$ +if ( int x = f(), y = g() ) ... $\C{// x != 0 \&\& y != 0}$ +if ( int x = f(), y = g(); `x < y` ) ... $\C{// relational expression}$ +\end{cfa} +Unless a relational expression is specified, each variable is compared not equal to 0, which is the standard semantics for the @if@ expression, and the results are combined using the logical @&&@ operator.\footnote{\CC only provides a single declaration always compared not equal to 0.} +The scope of the declaration(s) is local to the @if@ statement but exist within both the ``then'' and ``else'' clauses. + + +\subsection{\texorpdfstring{\LstKeywordStyle{switch} Statement}{switch Statement}} + +There are a number of deficiencies with the C @switch@ statements: enumerating @case@ lists, placement of @case@ clauses, scope of the switch body, and fall through between case clauses. + +C has no shorthand for specifying a list of case values, whether the list is non-contiguous or contiguous\footnote{C provides this mechanism via fall through.}. +\CFA provides a shorthand for a non-contiguous list: +\begin{cquote} +\lstDeleteShortInline@% +\begin{tabular}{@{}l@{\hspace{\parindentlnth}}l@{}} +\multicolumn{1}{c@{\hspace{\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ +\begin{cfa} +case 2, 10, 34, 42: +\end{cfa} +& +\begin{cfa} +case 2: case 10: case 34: case 42: +\end{cfa} +\end{tabular} +\lstMakeShortInline@% +\end{cquote} +for a contiguous list:\footnote{gcc provides the same mechanism with awkward syntax, \lstinline@2 ... 42@, where spaces are required around the ellipse.} +\begin{cquote} +\lstDeleteShortInline@% +\begin{tabular}{@{}l@{\hspace{\parindentlnth}}l@{}} +\multicolumn{1}{c@{\hspace{\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ +\begin{cfa} +case 2~42: +\end{cfa} +& +\begin{cfa} +case 2: case 3: ... case 41: case 42: +\end{cfa} +\end{tabular} +\lstMakeShortInline@% +\end{cquote} +and a combination: +\begin{cfa} +case -12~-4, -1~5, 14~21, 34~42: +\end{cfa} + +C allows placement of @case@ clauses \emph{within} statements nested in the @switch@ body (see Duff's device~\cite{Duff83}); +\begin{cfa} +switch ( i ) { + case 0: + for ( int i = 0; i < 10; i += 1 ) { + ... + `case 1:` // no initialization of loop index + ... + } +} +\end{cfa} +\CFA precludes this form of transfer into a control structure because it causes undefined behaviour, especially with respect to missed initialization, and provides very limited functionality. + +C allows placement of declaration within the @switch@ body and unreachable code at the start, resulting in undefined behaviour: +\begin{cfa} +switch ( x ) { + `int y = 1;` $\C{// unreachable initialization}$ + `x = 7;` $\C{// unreachable code without label/branch}$ + case 0: + ... + `int z = 0;` $\C{// unreachable initialization, cannot appear after case}$ + z = 2; + case 1: + `x = z;` $\C{// without fall through, z is undefined}$ +} +\end{cfa} +\CFA allows the declaration of local variables, \eg @y@, at the start of the @switch@ with scope across the entire @switch@ body, \ie all @case@ clauses. +\CFA disallows the declaration of local variable, \eg @z@, directly within the @switch@ body, because a declaration cannot occur immediately after a @case@ since a label can only be attached to a statement, and the use of @z@ is undefined in @case 1@ as neither storage allocation nor initialization may have occurred. + +C @switch@ provides multiple entry points into the statement body, but once an entry point is selected, control continues across \emph{all} @case@ clauses until the end of the @switch@ body, called \newterm{fall through}; +@case@ clauses are made disjoint by the @break@ statement. +While the ability to fall through \emph{is} a useful form of control flow, it does not match well with programmer intuition, resulting in many errors from missing @break@ statements. +For backwards compatibility, \CFA provides a \emph{new} control structure, @choose@, which mimics @switch@, but reverses the meaning of fall through (see Figure~\ref{f:ChooseSwitchStatements}). +Collectively, these enhancements reduce programmer burden and increase readability and safety. + +\begin{figure} +\centering +\lstDeleteShortInline@% +\begin{tabular}{@{}l@{\hspace{2\parindentlnth}}l@{}} +\multicolumn{1}{c@{\hspace{2\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ +\begin{cfa} +`choose` ( day ) { + case Mon~Thu: // program + + case Fri: // program + wallet += pay; + `fallthrough;` + case Sat: // party + wallet -= party; + + case Sun: // rest + + default: // error +} +\end{cfa} +& +\begin{cfa} +switch ( day ) { + case Mon: case Tue: case Wed: case Thu: // program + `break;` + case Fri: // program + wallet += pay; + + case Sat: // party + wallet -= party; + `break;` + case Sun: // rest + `break;` + default: // error +} +\end{cfa} +\end{tabular} +\lstMakeShortInline@% +\caption{\lstinline|choose| versus \lstinline|switch| Statements} +\label{f:ChooseSwitchStatements} +\end{figure} + +\begin{comment} +Forgotten @break@ statements at the end of @switch@ cases are a persistent sort of programmer error in C, and the @break@ statements themselves introduce visual clutter and an un-C-like keyword-based block delimiter. +\CFA addresses this error by introducing a @choose@ statement, which works identically to a @switch@ except that its default end-of-case behaviour is to break rather than to fall through for all non-empty cases. +Since empty cases like @case 7:@ in @case 7: case 11:@ still have fall-through semantics and explicit @break@ is still allowed at the end of a @choose@ case, many idiomatic uses of @switch@ in standard C can be converted to @choose@ statements by simply changing the keyword. +Where fall-through is desired for a non-empty case, it can be specified with the new @fallthrough@ statement, making @choose@ equivalently powerful to @switch@, but more concise in the common case where most non-empty cases end with a @break@ statement, as in the example below: + +\begin{cfa} +choose( i ) { + case 2: + printf("even "); + fallthrough; + case 3: case 5: case 7: + printf("small prime\n"); + case 4,6,8,9: + printf("small composite\n"); + case 13~19: + printf("teen\n"); + default: + printf("something else\n"); +} +\end{cfa} +\end{comment} @@ -1050,5 +1203,5 @@ } else { ... goto `LIF`; ... - } `L3:` ; + } `LIF:` ; } `LS:` ; } `LC:` ; @@ -1100,143 +1253,123 @@ -\subsection{\texorpdfstring{Enhanced \LstKeywordStyle{switch} Statement}{Enhanced switch Statement}} - -There are a number of deficiencies with the C @switch@ statements: enumerating @case@ lists, placement of @case@ clauses, scope of the switch body, and fall through between case clauses. - -C has no shorthand for specifying a list of case values, whether the list is non-contiguous or contiguous\footnote{C provides this mechanism via fall through.}. -\CFA provides a shorthand for a non-contiguous list: +\subsection{Exception Handling} + +The following framework for \CFA exception handling is in place, excluding a run-time type information and dynamic casts. +\CFA provides two forms of exception handling: \newterm{fix-up} and \newterm{recovery} (see Figure~\ref{f:CFAExceptionHandling}). +Both mechanisms provide dynamic call to a handler using dynamic name-lookup, where fix-up has dynamic return and recovery has static return from the handler. +\CFA restricts exception types to those defined by aggregate type @exception@. +The form of the raise dictates the set of handlers examined during propagation: \newterm{resumption propagation} (@resume@) only examines resumption handlers (@catchResume@); \newterm{terminating propagation} (@throw@) only examines termination handlers (@catch@). +If @resume@ or @throw@ have no exception type, it is a reresume/rethrow, meaning the currently exception continues propagation. +If there is no current exception, the reresume/rethrow results in a runtime error. + +\begin{figure} \begin{cquote} \lstDeleteShortInline@% -\begin{tabular}{@{}l@{\hspace{\parindentlnth}}l@{}} -\multicolumn{1}{c@{\hspace{\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ -\begin{cfa} -case 2, 10, 34, 42: -\end{cfa} -& -\begin{cfa} -case 2: case 10: case 34: case 42: +\begin{tabular}{@{}l@{\hspace{2\parindentlnth}}l@{}} +\multicolumn{1}{c@{\hspace{2\parindentlnth}}}{\textbf{Resumption}} & \multicolumn{1}{c}{\textbf{Termination}} \\ +\begin{cfa} +`exception R { int fix; };` +void f() { + R r; + ... `resume( r );` ... + ... r.fix // control does return here after handler +} +`try` { + ... f(); ... +} `catchResume( R r )` { + ... r.fix = ...; // return correction to raise +} // dynamic return to _Resume +\end{cfa} +& +\begin{cfa} +`exception T {};` +void f() { + + ... `throw( T{} );` ... + // control does NOT return here after handler +} +`try` { + ... f(); ... +} `catch( T t )` { + ... // recover and continue +} // static return to next statement \end{cfa} \end{tabular} \lstMakeShortInline@% \end{cquote} -for a contiguous list:\footnote{gcc provides the same mechanism with awkward syntax, \lstinline@2 ... 42@, where spaces are required around the ellipse.} +\caption{\CFA Exception Handling} +\label{f:CFAExceptionHandling} +\end{figure} + +The set of exception types in a list of catch clause may include both a resumption and termination handler: +\begin{cfa} +try { + ... resume( `R{}` ); ... +} catchResume( `R` r ) { ... throw( R{} ); ... } $\C{\color{red}// H1}$ + catch( `R` r ) { ... } $\C{\color{red}// H2}$ + +\end{cfa} +The resumption propagation raises @R@ and the stack is not unwound; +the exception is caught by the @catchResume@ clause and handler H1 is invoked. +The termination propagation in handler H1 raises @R@ and the stack is unwound; +the exception is caught by the @catch@ clause and handler H2 is invoked. +The termination handler is available because the resumption propagation did not unwind the stack. + +An additional feature is conditional matching in a catch clause: +\begin{cfa} +try { + ... write( `datafile`, ... ); ... $\C{// may throw IOError}$ + ... write( `logfile`, ... ); ... +} catch ( IOError err; `err.file == datafile` ) { ... } $\C{// handle datafile error}$ + catch ( IOError err; `err.file == logfile` ) { ... } $\C{// handle logfile error}$ + catch ( IOError err ) { ... } $\C{// handler error from other files}$ +\end{cfa} +where the throw inserts the failing file-handle in the I/O exception. +Conditional catch cannot be trivially mimicked by other mechanisms because once an exception is caught, handler clauses in that @try@ statement are no longer eligible.. + +The resumption raise can specify an alternate stack on which to raise an exception, called a \newterm{nonlocal raise}: +\begin{cfa} +resume( $\emph{exception-type}$, $\emph{alternate-stack}$ ) +resume( $\emph{alternate-stack}$ ) +\end{cfa} +These overloads of @resume@ raise the specified exception or the currently propagating exception (reresume) at another coroutine or task~\cite{Delisle18}. +Nonlocal raise is restricted to resumption to provide the exception handler the greatest flexibility because processing the exception does not unwind its stack, allowing it to continue after the handle returns. + +To facilitate nonlocal exception, \CFA provides dynamic enabling and disabling of nonlocal exception-propagation. +The constructs for controlling propagation of nonlocal exceptions are the @enable@ and the @disable@ blocks: \begin{cquote} \lstDeleteShortInline@% -\begin{tabular}{@{}l@{\hspace{\parindentlnth}}l@{}} -\multicolumn{1}{c@{\hspace{\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ -\begin{cfa} -case 2~42: -\end{cfa} -& -\begin{cfa} -case 2: case 3: ... case 41: case 42: +\begin{tabular}{@{}l@{\hspace{2\parindentlnth}}l@{}} +\begin{cfa} +enable $\emph{exception-type-list}$ { + // allow non-local resumption +} +\end{cfa} +& +\begin{cfa} +disable $\emph{exception-type-list}$ { + // disallow non-local resumption +} \end{cfa} \end{tabular} \lstMakeShortInline@% \end{cquote} -and a combination: -\begin{cfa} -case -12~-4, -1~5, 14~21, 34~42: -\end{cfa} - -C allows placement of @case@ clauses \emph{within} statements nested in the @switch@ body (see Duff's device~\cite{Duff83}); -\begin{cfa} -switch ( i ) { - case 0: - for ( int i = 0; i < 10; i += 1 ) { - ... - `case 1:` // no initialization of loop index - ... - } -} -\end{cfa} -\CFA precludes this form of transfer into a control structure because it causes undefined behaviour, especially with respect to missed initialization, and provides very limited functionality. - -C allows placement of declaration within the @switch@ body and unreachable code at the start, resulting in undefined behaviour: -\begin{cfa} -switch ( x ) { - `int y = 1;` $\C{// unreachable initialization}$ - `x = 7;` $\C{// unreachable code without label/branch}$ - case 0: - ... - `int z = 0;` $\C{// unreachable initialization, cannot appear after case}$ - z = 2; - case 1: - `x = z;` $\C{// without fall through, z is undefined}$ -} -\end{cfa} -\CFA allows the declaration of local variables, \eg @y@, at the start of the @switch@ with scope across the entire @switch@ body, \ie all @case@ clauses. -\CFA disallows the declaration of local variable, \eg @z@, directly within the @switch@ body, because a declaration cannot occur immediately after a @case@ since a label can only be attached to a statement, and the use of @z@ is undefined in @case 1@ as neither storage allocation nor initialization may have occurred. - -C @switch@ provides multiple entry points into the statement body, but once an entry point is selected, control continues across \emph{all} @case@ clauses until the end of the @switch@ body, called \newterm{fall through}; -@case@ clauses are made disjoint by the @break@ statement. -While the ability to fall through \emph{is} a useful form of control flow, it does not match well with programmer intuition, resulting in many errors from missing @break@ statements. -For backwards compatibility, \CFA provides a \emph{new} control structure, @choose@, which mimics @switch@, but reverses the meaning of fall through (see Figure~\ref{f:ChooseSwitchStatements}). -Collectively, these enhancements reduce programmer burden and increase readability and safety. - -\begin{figure} -\centering -\lstDeleteShortInline@% -\begin{tabular}{@{}l@{\hspace{2\parindentlnth}}l@{}} -\multicolumn{1}{c@{\hspace{2\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ -\begin{cfa} -`choose` ( day ) { - case Mon~Thu: // program - - case Fri: // program - wallet += pay; - `fallthrough;` - case Sat: // party - wallet -= party; - - case Sun: // rest - - default: // error -} -\end{cfa} -& -\begin{cfa} -switch ( day ) { - case Mon: case Tue: case Wed: case Thu: // program - `break;` - case Fri: // program - wallet += pay; - - case Sat: // party - wallet -= party; - `break;` - case Sun: // rest - `break;` - default: // error -} -\end{cfa} -\end{tabular} -\lstMakeShortInline@% -\caption{\lstinline|choose| versus \lstinline|switch| Statements} -\label{f:ChooseSwitchStatements} -\end{figure} - -\begin{comment} -Forgotten @break@ statements at the end of @switch@ cases are a persistent sort of programmer error in C, and the @break@ statements themselves introduce visual clutter and an un-C-like keyword-based block delimiter. -\CFA addresses this error by introducing a @choose@ statement, which works identically to a @switch@ except that its default end-of-case behaviour is to break rather than to fall through for all non-empty cases. -Since empty cases like @case 7:@ in @case 7: case 11:@ still have fall-through semantics and explicit @break@ is still allowed at the end of a @choose@ case, many idiomatic uses of @switch@ in standard C can be converted to @choose@ statements by simply changing the keyword. -Where fall-through is desired for a non-empty case, it can be specified with the new @fallthrough@ statement, making @choose@ equivalently powerful to @switch@, but more concise in the common case where most non-empty cases end with a @break@ statement, as in the example below: - -\begin{cfa} -choose( i ) { - case 2: - printf("even "); - fallthrough; - case 3: case 5: case 7: - printf("small prime\n"); - case 4,6,8,9: - printf("small composite\n"); - case 13~19: - printf("teen\n"); - default: - printf("something else\n"); -} -\end{cfa} -\end{comment} +The arguments for @enable@/@disable@ specify the exception types allowed to be propagated or postponed, respectively. +Specifying no exception type is shorthand for specifying all exception types. +Both @enable@ and @disable@ blocks can be nested, turning propagation on/off on entry, and on exit, the specified exception types are restored to their prior state. + +Finally, \CFA provides a Java like @finally@ clause after the catch clauses: +\begin{cfa} +try { + ... f(); ... +// catchResume or catch clauses +} `finally` { + // house keeping +} +\end{cfa} +The finally clause is always executed, i.e., if the try block ends normally or if an exception is raised. +If an exception is raised and caught, the handler is run before the finally clause. +Like a destructor (see Section~\ref{s:ConstructorsDestructors}), a finally clause can raise an exception but not if there is an exception being propagated. +Mimicking the @finally@ clause with mechanisms like RAII is non-trivially when there are multiple types and local accesses. @@ -1253,5 +1386,5 @@ S s, as[10]; \end{cfa} -However, routines manipulating aggregates must repeat the aggregate name to access its containing fields: +However, functions manipulating aggregates must repeat the aggregate name to access its containing fields: \begin{cfa} void f( S s ) { @@ -1271,5 +1404,5 @@ } \end{C++} -Object-oriented nesting of member routines in a \lstinline[language=C++]@class@ allows eliding \lstinline[language=C++]@this->@ because of lexical scoping. +Object-oriented nesting of member functions in a \lstinline[language=C++]@class@ allows eliding \lstinline[language=C++]@this->@ because of lexical scoping. However, for other aggregate parameters, qualification is necessary: \begin{cfa} @@ -1301,5 +1434,5 @@ 'with' '(' $\emph{expression-list}$ ')' $\emph{compound-statement}$ \end{cfa} -and may appear as the body of a routine or nested within a routine body. +and may appear as the body of a function or nested within a function body. Each expression in the expression-list provides a type and object. The type must be an aggregate type. @@ -1328,5 +1461,5 @@ Qualification or a cast is used to disambiguate. -There is an interesting problem between parameters and the routine @with@, \eg: +There is an interesting problem between parameters and the function @with@, \eg: \begin{cfa} void ?{}( S & s, int i ) with ( s ) { $\C{// constructor}$ @@ -1334,5 +1467,5 @@ } \end{cfa} -Here, the assignment @s.i = i@ means @s.i = s.i@, which is meaningless, and there is no mechanism to qualify the parameter @i@, making the assignment impossible using the routine @with@. +Here, the assignment @s.i = i@ means @s.i = s.i@, which is meaningless, and there is no mechanism to qualify the parameter @i@, making the assignment impossible using the function @with@. To solve this problem, parameters are treated like an initialized aggregate: \begin{cfa} @@ -1342,5 +1475,5 @@ } params; \end{cfa} -and implicitly opened \emph{after} a routine open, to give them higher priority: +and implicitly opened \emph{after} a function open, to give them higher priority: \begin{cfa} void ?{}( S & s, int i ) with ( s ) `with( $\emph{\color{red}params}$ )` { @@ -1370,125 +1503,4 @@ -\subsection{Exception Handling} - -The following framework for \CFA exception handling is in place, excluding a run-time type information and dynamic casts. -\CFA provides two forms of exception handling: \newterm{fix-up} and \newterm{recovery} (see Figure~\ref{f:CFAExceptionHandling}). -Both mechanisms provide dynamic call to a handler using dynamic name-lookup, where fix-up has dynamic return and recovery has static return from the handler. -\CFA restricts exception types to those defined by aggregate type @exception@. -The form of the raise dictates the set of handlers examined during propagation: \newterm{resumption propagation} (@resume@) only examines resumption handlers (@catchResume@); \newterm{terminating propagation} (@throw@) only examines termination handlers (@catch@). -If @resume@ or @throw@ have no exception type, it is a reresume/rethrow, meaning the currently exception continues propagation. -If there is no current exception, the reresume/rethrow results in a runtime error. - -\begin{figure} -\begin{cquote} -\lstDeleteShortInline@% -\begin{tabular}{@{}l@{\hspace{2\parindentlnth}}l@{}} -\multicolumn{1}{c@{\hspace{2\parindentlnth}}}{\textbf{Resumption}} & \multicolumn{1}{c}{\textbf{Termination}} \\ -\begin{cfa} -`exception R { int fix; };` -void f() { - R r; - ... `resume( r );` ... - ... r.fix // control does return here after handler -} -`try` { - ... f(); ... -} `catchResume( R r )` { - ... r.fix = ...; // return correction to raise -} // dynamic return to _Resume -\end{cfa} -& -\begin{cfa} -`exception T {};` -void f() { - - ... `throw( T{} );` ... - // control does NOT return here after handler -} -`try` { - ... f(); ... -} `catch( T t )` { - ... // recover and continue -} // static return to next statement -\end{cfa} -\end{tabular} -\lstMakeShortInline@% -\end{cquote} -\caption{\CFA Exception Handling} -\label{f:CFAExceptionHandling} -\end{figure} - -The set of exception types in a list of catch clause may include both a resumption and termination handler: -\begin{cfa} -try { - ... resume( `R{}` ); ... -} catchResume( `R` r ) { ... throw( R{} ); ... } $\C{\color{red}// H1}$ - catch( `R` r ) { ... } $\C{\color{red}// H2}$ - -\end{cfa} -The resumption propagation raises @R@ and the stack is not unwound; -the exception is caught by the @catchResume@ clause and handler H1 is invoked. -The termination propagation in handler H1 raises @R@ and the stack is unwound; -the exception is caught by the @catch@ clause and handler H2 is invoked. -The termination handler is available because the resumption propagation did not unwind the stack. - -An additional feature is conditional matching in a catch clause: -\begin{cfa} -try { - ... write( `datafile`, ... ); ... $\C{// may throw IOError}$ - ... write( `logfile`, ... ); ... -} catch ( IOError err; `err.file == datafile` ) { ... } $\C{// handle datafile error}$ - catch ( IOError err; `err.file == logfile` ) { ... } $\C{// handle logfile error}$ - catch ( IOError err ) { ... } $\C{// handler error from other files}$ -\end{cfa} -where the throw inserts the failing file-handle in the I/O exception. -Conditional catch cannot be trivially mimicked by other mechanisms because once an exception is caught, handler clauses in that @try@ statement are no longer eligible.. - -The resumption raise can specify an alternate stack on which to raise an exception, called a \newterm{nonlocal raise}: -\begin{cfa} -resume( $\emph{exception-type}$, $\emph{alternate-stack}$ ) -resume( $\emph{alternate-stack}$ ) -\end{cfa} -These overloads of @resume@ raise the specified exception or the currently propagating exception (reresume) at another coroutine or task~\cite{Delisle18}. -Nonlocal raise is restricted to resumption to provide the exception handler the greatest flexibility because processing the exception does not unwind its stack, allowing it to continue after the handle returns. - -To facilitate nonlocal exception, \CFA provides dynamic enabling and disabling of nonlocal exception-propagation. -The constructs for controlling propagation of nonlocal exceptions are the @enable@ and the @disable@ blocks: -\begin{cquote} -\lstDeleteShortInline@% -\begin{tabular}{@{}l@{\hspace{2\parindentlnth}}l@{}} -\begin{cfa} -enable $\emph{exception-type-list}$ { - // allow non-local resumption -} -\end{cfa} -& -\begin{cfa} -disable $\emph{exception-type-list}$ { - // disallow non-local resumption -} -\end{cfa} -\end{tabular} -\lstMakeShortInline@% -\end{cquote} -The arguments for @enable@/@disable@ specify the exception types allowed to be propagated or postponed, respectively. -Specifying no exception type is shorthand for specifying all exception types. -Both @enable@ and @disable@ blocks can be nested, turning propagation on/off on entry, and on exit, the specified exception types are restored to their prior state. - -Finally, \CFA provides a Java like @finally@ clause after the catch clauses: -\begin{cfa} -try { - ... f(); ... -// catchResume or catch clauses -} `finally` { - // house keeping -} -\end{cfa} -The finally clause is always executed, i.e., if the try block ends normally or if an exception is raised. -If an exception is raised and caught, the handler is run before the finally clause. -Like a destructor (see Section~\ref{s:ConstructorsDestructors}), a finally clause can raise an exception but not if there is an exception being propagated. -Mimicking the @finally@ clause with mechanisms like RAII is non-trivially when there are multiple types and local accesses. - - \section{Declarations} @@ -1518,14 +1530,14 @@ Is this an array of 5 pointers to integers or a pointer to an array of 5 integers? If there is any doubt, it implies productivity and safety issues even for basic programs. -Another example of confusion results from the fact that a routine name and its parameters are embedded within the return type, mimicking the way the return value is used at the routine's call site. -For example, a routine returning a pointer to an array of integers is defined and used in the following way: +Another example of confusion results from the fact that a function name and its parameters are embedded within the return type, mimicking the way the return value is used at the function's call site. +For example, a function returning a pointer to an array of integers is defined and used in the following way: \begin{cfa} int `(*`f`())[`5`]` {...}; $\C{// definition}$ ... `(*`f`())[`3`]` += 1; $\C{// usage}$ \end{cfa} -Essentially, the return type is wrapped around the routine name in successive layers (like an onion). +Essentially, the return type is wrapped around the function name in successive layers (like an onion). While attempting to make the two contexts consistent is a laudable goal, it has not worked out in practice. -\CFA provides its own type, variable and routine declarations, using a different syntax. +\CFA provides its own type, variable and function declarations, using a different syntax. The new declarations place qualifiers to the left of the base type, while C declarations place qualifiers to the right. The qualifiers have the same meaning but are ordered left to right to specify a variable's type. @@ -1555,5 +1567,5 @@ \end{cquote} The only exception is bit field specification, which always appear to the right of the base type. -% Specifically, the character @*@ is used to indicate a pointer, square brackets @[@\,@]@ are used to represent an array or function return value, and parentheses @()@ are used to indicate a routine parameter. +% Specifically, the character @*@ is used to indicate a pointer, square brackets @[@\,@]@ are used to represent an array or function return value, and parentheses @()@ are used to indicate a function parameter. However, unlike C, \CFA type declaration tokens are distributed across all variables in the declaration list. For instance, variables @x@ and @y@ of type pointer to integer are defined in \CFA as follows: @@ -1641,8 +1653,8 @@ \lstMakeShortInline@% \end{cquote} -Specifiers must appear at the start of a \CFA routine declaration\footnote{\label{StorageClassSpecifier} +Specifiers must appear at the start of a \CFA function declaration\footnote{\label{StorageClassSpecifier} The placement of a storage-class specifier other than at the beginning of the declaration specifiers in a declaration is an obsolescent feature.~\cite[\S~6.11.5(1)]{C11}}. -The new declaration syntax can be used in other contexts where types are required, \eg casts and the pseudo-routine @sizeof@: +The new declaration syntax can be used in other contexts where types are required, \eg casts and the pseudo-function @sizeof@: \begin{cquote} \lstDeleteShortInline@% @@ -1662,5 +1674,5 @@ \end{cquote} -The syntax of the new routine prototype declaration follows directly from the new routine definition syntax; +The syntax of the new function-prototype declaration follows directly from the new function-definition syntax; as well, parameter names are optional, \eg: \begin{cfa} @@ -1671,6 +1683,6 @@ [ * int, int ] j ( int ); $\C{// returning pointer to int and int, with int parameter}$ \end{cfa} -This syntax allows a prototype declaration to be created by cutting and pasting source text from the routine definition header (or vice versa). -Like C, it is possible to declare multiple routine-prototypes in a single declaration, where the return type is distributed across \emph{all} routine names in the declaration list, \eg: +This syntax allows a prototype declaration to be created by cutting and pasting source text from the function-definition header (or vice versa). +Like C, it is possible to declare multiple function-prototypes in a single declaration, where the return type is distributed across \emph{all} function names in the declaration list, \eg: \begin{cquote} \lstDeleteShortInline@% @@ -1687,16 +1699,16 @@ \lstMakeShortInline@% \end{cquote} -where \CFA allows the last routine in the list to define its body. - -The syntax for pointers to \CFA routines specifies the pointer name on the right, \eg: -\begin{cfa} -* [ int x ] () fp; $\C{// pointer to routine returning int with no parameters}$ -* [ * int ] ( int y ) gp; $\C{// pointer to routine returning pointer to int with int parameter}$ -* [ ] ( int, char ) hp; $\C{// pointer to routine returning no result with int and char parameters}$ -* [ * int, int ] ( int ) jp; $\C{// pointer to routine returning pointer to int and int, with int parameter}$ -\end{cfa} -Note, a routine name cannot be specified: -\begin{cfa} -* [ int x ] f () fp; $\C{// routine name "f" is disallowed}$ +where \CFA allows the last function in the list to define its body. + +The syntax for pointers to \CFA functions specifies the pointer name on the right, \eg: +\begin{cfa} +* [ int x ] () fp; $\C{// pointer to function returning int with no parameters}$ +* [ * int ] ( int y ) gp; $\C{// pointer to function returning pointer to int with int parameter}$ +* [ ] ( int, char ) hp; $\C{// pointer to function returning no result with int and char parameters}$ +* [ * int, int ] ( int ) jp; $\C{// pointer to function returning pointer to int and int, with int parameter}$ +\end{cfa} +Note, a function name cannot be specified: +\begin{cfa} +* [ int x ] f () fp; $\C{// function name "f" is disallowed}$ \end{cfa} @@ -1918,18 +1930,11 @@ Destruction parameters are useful for specifying storage-management actions, such as de-initialize but not deallocate.}. \begin{cfa} -struct VLA { - int len, * data; -}; -void ?{}( VLA & vla ) with ( vla ) { $\C{// default constructor}$ - len = 10; data = alloc( len ); $\C{// shallow copy}$ -} -void ^?{}( VLA & vla ) with ( vla ) { $\C{// destructor}$ - free( data ); -} +struct VLA { int len, * data; }; +void ?{}( VLA & vla ) with ( vla ) { len = 10; data = alloc( len ); } $\C{// default constructor}$ +void ^?{}( VLA & vla ) with ( vla ) { free( data ); } $\C{// destructor}$ { VLA x; $\C{// implicit: ?\{\}( x );}$ } $\C{// implicit: ?\^{}\{\}( x );}$ \end{cfa} -(Note, the example is purposely kept simple by using shallow-copy semantics.) @VLA@ is a \newterm{managed type}\footnote{ A managed type affects the runtime environment versus a self-contained type.}: a type requiring a non-trivial constructor or destructor, or with a field of a managed type. @@ -1939,11 +1944,12 @@ \CFA also provides syntax for \newterm{initialization} and \newterm{copy}: \begin{cfa} -void ?{}( VLA & vla, int size, char fill ) with ( vla ) { $\C{// initialization}$ +void ?{}( VLA & vla, int size, char fill ) with ( vla ) { $\C{// initialization}$ len = size; data = alloc( len, fill ); } -void ?{}( VLA & vla, VLA other ) { $\C{// copy}$ +void ?{}( VLA & vla, VLA other ) { $\C{// copy, shallow}$ vla.len = other.len; vla.data = other.data; } \end{cfa} +(Note, the example is purposely kept simple by using shallow-copy semantics.) An initialization constructor-call has the same syntax as a C initializer, except the initialization values are passed as arguments to a matching constructor (number and type of paremeters). \begin{cfa} @@ -1959,6 +1965,6 @@ \begin{cfa} { - VLA x, y = { 20, 0x01 }, z = y; - // implicit: ?{}( x ); ?{}( y, 20, 0x01 ); ?{}( z, y ); z points to y + VLA x, y = { 20, 0x01 }, z = y; $\C{// z points to y}$ + // ?{}( x ); ?{}( y, 20, 0x01 ); ?{}( z, y ); ^x{}; $\C{// deallocate x}$ x{}; $\C{// reallocate x}$ @@ -1967,5 +1973,5 @@ y{ x }; $\C{// reallocate y, points to x}$ x{}; $\C{// reallocate x, not pointing to y}$ - // implicit: ^?{}(z); ^?{}(y); ^?{}(x); + // ^?{}(z); ^?{}(y); ^?{}(x); } \end{cfa} @@ -1998,5 +2004,39 @@ C already includes limited polymorphism for literals -- @0@ can be either an integer or a pointer literal, depending on context, while the syntactic forms of literals of the various integer and float types are very similar, differing from each other only in suffix. In keeping with the general \CFA approach of adding features while respecting the ``C-style'' of doing things, C's polymorphic constants and typed literal syntax are extended to interoperate with user-defined types, while maintaining a backwards-compatible semantics. -A trivial example is allowing the underscore to separate prefixes, digits, and suffixes in all \CFA constants, as in Ada, \eg @0x`_`1.ffff`_`ffff`_`p`_`128`_`l@. +A trivial example is allowing the underscore, as in Ada, to separate prefixes, digits, and suffixes in all \CFA constants, \eg @0x`_`1.ffff`_`ffff`_`p`_`128`_`l@. + + +\subsection{Integral Suffixes} + +Additional integral suffixes are added to cover all the integral types and lengths. +\begin{cquote} +\lstDeleteShortInline@% +\begin{tabular}{@{}l@{\hspace{\parindentlnth}}l@{\hspace{\parindentlnth}}l@{}} +\begin{cfa} +20`_hh` // signed char +21`_hhu` // unsigned char +22`_h` // signed short int +23`_uh` // unsigned short int +24`z` // size_t +\end{cfa} +& +\begin{cfa} +20`_L8` // int8_t +21`_ul8` // uint8_t +22`_l16` // int16_t +23`_ul16` // uint16_t +24`_l32` // int32_t +\end{cfa} +& +\begin{cfa} +25`_ul32` // uint32_t +26`_l64` // int64_t +27`_l64u` // uint64_t +26`_L128` // int128 +27`_L128u` // unsigned int128 +\end{cfa} +\end{tabular} +\lstMakeShortInline@% +\end{cquote} @@ -2015,62 +2055,84 @@ -\subsection{Integral Suffixes} - -Additional integral suffixes are added to cover all the integral types and lengths. -\begin{cquote} +\subsection{User Literals} + +For readability, it is useful to associate units to scale literals, \eg weight (stone, pound, kilogram) or time (seconds, minutes, hours). +The left of Figure~\ref{f:UserLiteral} shows the \CFA alternative call-syntax (literal argument before function name), using the backquote, to convert basic literals into user literals. +The backquote is a small character, making the unit (function name) predominate. +For examples, the multi-precision integers in Section~\ref{s:MultiPrecisionIntegers} make use of user literals: +{\lstset{language=CFA,moredelim=**[is][\color{red}]{|}{|},deletedelim=**[is][]{`}{`}} +\begin{cfa} +y = 9223372036854775807L|`mp| * 18446744073709551615UL|`mp|; +y = "12345678901234567890123456789"|`mp| + "12345678901234567890123456789"|`mp|; +\end{cfa} +Because \CFA uses a standard function, all types and literals are applicable, as well as overloading and conversions. +}% + +The right of Figure~\ref{f:UserLiteral} shows the equivalent \CC version using the underscore for the call-syntax. +However, \CC restricts the types, \eg @unsigned long long int@ and @long double@ to represent integral and floating literals. +After which, user literals must match (no conversions); +hence, it is necessary to overload the unit with all appropriate types. +Finally, the use of the single quote as a separator is restricted to digits, precluding its use in the literal prefix or suffix, and causes problems with most IDEs, which must be extended to deal with this alternate use of the single quote. + +\begin{figure} +\centering +\lstset{language=CFA,moredelim=**[is][\color{red}]{|}{|},deletedelim=**[is][]{`}{`}} \lstDeleteShortInline@% -\begin{tabular}{@{}l@{\hspace{\parindentlnth}}l@{\hspace{\parindentlnth}}l@{}} -\begin{cfa} -20`_hh` // signed char -21`_hhu` // unsigned char -22`_h` // signed short int -23`_uh` // unsigned short int -24`z` // size_t -\end{cfa} -& -\begin{cfa} -20`_L8` // int8_t -21`_ul8` // uint8_t -22`_l16` // int16_t -23`_ul16` // uint16_t -24`_l32` // int32_t -\end{cfa} -& -\begin{cfa} -25`_ul32` // uint32_t -26`_l64` // int64_t -27`_l64u` // uint64_t -26`_L128` // int128 -27`_L128u` // unsigned int128 +\begin{tabular}{@{}l@{\hspace{\parindentlnth}}l@{}} +\multicolumn{1}{c@{\hspace{\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{\CC}} \\ +\begin{cfa} +struct W { + double stones; +}; +void ?{}( W & w ) { w.stones = 0; } +void ?{}( W & w, double w ) { w.stones = w; } +W ?+?( W l, W r ) { + return (W){ l.stones + r.stones }; +} +W |?`st|( double w ) { return (W){ w }; } +W |?`lb|( double w ) { return (W){ w / 14.0 }; } +W |?`kg|( double w ) { return (W) { w * 0.16 }; } + + + +int main() { + W w, heavy = { 20 }; + w = 155|`lb|; + w = 0b_1111|`st|; + w = 0_233|`lb|; + w = 0x_9b_u|`kg|; + w = 5.5|`st| + 8|`kg| + 25.01|`lb| + heavy; +} +\end{cfa} +& +\begin{cfa} +struct W { + double stones; + W() { stones = 0.0; } + W( double w ) { stones = w; } +}; +W operator+( W l, W r ) { + return W( l.stones + r.stones ); +} +W |operator"" _st|( unsigned long long int w ) { return W( w ); } +W |operator"" _lb|( unsigned long long int w ) { return W( w / 14.0 ); } +W |operator"" _kg|( unsigned long long int w ) { return W( w * 0.16 ); } +W |operator"" _st|( long double w ) { return W( w ); } +W |operator"" _lb|( long double w ) { return W( w / 14.0 ); } +W |operator"" _kg|( long double w ) { return W( w * 0.16 ); } +int main() { + W w, heavy = { 20 }; + w = 155|_lb|; + w = 0b1111|_lb|; // error, binary unsupported + w = 0${\color{red}'}$233|_lb|; // quote separator + w = 0x9b|_kg|; + w = 5.5d|_st| + 8|_kg| + 25.01|_lb| + heavy; +} \end{cfa} \end{tabular} \lstMakeShortInline@% -\end{cquote} - - -\subsection{Units} - -Alternative call syntax (literal argument before routine name) to convert basic literals into user literals. - -{\lstset{language=CFA,moredelim=**[is][\color{red}]{|}{|},deletedelim=**[is][]{`}{`}} -\begin{cfa} -struct Weight { double stones; }; -void ?{}( Weight & w ) { w.stones = 0; } $\C{// operations}$ -void ?{}( Weight & w, double w ) { w.stones = w; } -Weight ?+?( Weight l, Weight r ) { return (Weight){ l.stones + r.stones }; } - -Weight |?`st|( double w ) { return (Weight){ w }; } $\C{// backquote for units}$ -Weight |?`lb|( double w ) { return (Weight){ w / 14.0 }; } -Weight |?`kg|( double w ) { return (Weight) { w * 0.1575}; } - -int main() { - Weight w, heavy = { 20 }; $\C{// 20 stone}$ - w = 155|`lb|; - w = 0x_9b_u|`lb|; $\C{// hexadecimal unsigned weight (155)}$ - w = 0_233|`lb|; $\C{// octal weight (155)}$ - w = 5|`st| + 8|`kg| + 25|`lb| + heavy; -} -\end{cfa} -}% +\caption{User Literal} +\label{f:UserLiteral} +\end{figure} @@ -2082,5 +2144,5 @@ In many cases, the interface is an inline wrapper providing overloading during compilation but zero cost at runtime. The following sections give a glimpse of the interface reduction to many C libraries. -In many cases, @signed@/@unsigned@ @char@, @short@, and @_Complex@ routines are available (but not shown) to ensure expression computations remain in a single type, as conversions can distort results. +In many cases, @signed@/@unsigned@ @char@, @short@, and @_Complex@ functions are available (but not shown) to ensure expression computations remain in a single type, as conversions can distort results. @@ -2110,11 +2172,10 @@ \begin{cquote} \lstDeleteShortInline@% -\begin{tabular}{@{}l@{\hspace{\parindentlnth}}l@{}} -\multicolumn{1}{c@{\hspace{\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ +\lstset{basicstyle=\linespread{0.9}\sf\small} +\begin{tabular}{@{}l@{\hspace{0.5\parindentlnth}}l@{}} +\multicolumn{1}{c@{\hspace{0.5\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ \begin{cfa} MIN - MAX - PI E @@ -2122,8 +2183,6 @@ & \begin{cfa} -SCHAR_MIN, CHAR_MIN, SHRT_MIN, INT_MIN, LONG_MIN, LLONG_MIN, - FLT_MIN, DBL_MIN, LDBL_MIN -SCHAR_MAX, UCHAR_MAX, SHRT_MAX, INT_MAX, LONG_MAX, LLONG_MAX, - FLT_MAX, DBL_MAX, LDBL_MAX +SCHAR_MIN, CHAR_MIN, SHRT_MIN, INT_MIN, LONG_MIN, LLONG_MIN, FLT_MIN, DBL_MIN, LDBL_MIN +SCHAR_MAX, UCHAR_MAX, SHRT_MAX, INT_MAX, LONG_MAX, LLONG_MAX, FLT_MAX, DBL_MAX, LDBL_MAX M_PI, M_PIl M_E, M_El @@ -2136,6 +2195,6 @@ \subsection{Math} -C library @math.h@ provides many mathematical routines. -\CFA routine overloading is used to condense these mathematical routines, \eg: +C library @math.h@ provides many mathematical functions. +\CFA function overloading is used to condense these mathematical functions, \eg: \begin{cquote} \lstDeleteShortInline@% @@ -2156,5 +2215,5 @@ \lstMakeShortInline@% \end{cquote} -The result is a significant reduction in names to access math routines, \eg: +The result is a significant reduction in names to access math functions, \eg: \begin{cquote} \lstDeleteShortInline@% @@ -2175,14 +2234,14 @@ \lstMakeShortInline@% \end{cquote} -While \Celeven has type-generic math~\cite[\S~7.25]{C11} in @tgmath.h@ to provide a similar mechanism, these macros are limited, matching a routine name with a single set of floating type(s). +While \Celeven has type-generic math~\cite[\S~7.25]{C11} in @tgmath.h@ to provide a similar mechanism, these macros are limited, matching a function name with a single set of floating type(s). For example, it is impossible to overload @atan@ for both one and two arguments; instead the names @atan@ and @atan2@ are required (see Section~\ref{s:NameOverloading}). -The key observation is that only a restricted set of type-generic macros are provided for a limited set of routine names, which do not generalize across the type system, as in \CFA. +The key observation is that only a restricted set of type-generic macros are provided for a limited set of function names, which do not generalize across the type system, as in \CFA. \subsection{Standard} -C library @stdlib.h@ provides many general routines. -\CFA routine overloading is used to condense these utility routines, \eg: +C library @stdlib.h@ provides many general functions. +\CFA function overloading is used to condense these utility functions, \eg: \begin{cquote} \lstDeleteShortInline@% @@ -2203,5 +2262,5 @@ \lstMakeShortInline@% \end{cquote} -The result is a significant reduction in names to access utility routines, \eg: +The result is a significant reduction in names to access utility functions, \eg: \begin{cquote} \lstDeleteShortInline@% @@ -2222,5 +2281,5 @@ \lstMakeShortInline@% \end{cquote} -In additon, there are polymorphic routines, like @min@ and @max@, which work on any type with operators @??@. +In additon, there are polymorphic functions, like @min@ and @max@, which work on any type with operators @??@. The following shows one example where \CFA \emph{extends} an existing standard C interface to reduce complexity and provide safety. @@ -2239,59 +2298,7 @@ An array may be filled, resized, or aligned. \end{description} -Table~\ref{t:StorageManagementOperations} shows the capabilities provided by C/\Celeven allocation-routines and how all the capabilities can be combined into two \CFA routines. - -\CFA storage-management routines extend the C equivalents by overloading, providing shallow type-safety, and removing the need to specify the base allocation-size. -The following example contrasts \CFA and C storage-allocation operation performing the same operations with the same type safety: -\begin{cquote} -\begin{cfa}[aboveskip=0pt] -size_t dim = 10; $\C{// array dimension}$ -char fill = '\xff'; $\C{// initialization fill value}$ -int * ip; -\end{cfa} -\lstDeleteShortInline@% -\begin{tabular}{@{}l@{\hspace{\parindentlnth}}l@{}} -\multicolumn{1}{c@{\hspace{\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ -\begin{cfa} -ip = alloc(); -ip = alloc( fill ); -ip = alloc( dim ); -ip = alloc( dim, fill ); -ip = alloc( ip, 2 * dim ); -ip = alloc( ip, 4 * dim, fill ); - -ip = align_alloc( 16 ); -ip = align_alloc( 16, fill ); -ip = align_alloc( 16, dim ); -ip = align_alloc( 16, dim, fill ); -\end{cfa} -& -\begin{cfa} -ip = (int *)malloc( sizeof( int ) ); -ip = (int *)malloc( sizeof( int ) ); memset( ip, fill, sizeof( int ) ); -ip = (int *)malloc( dim * sizeof( int ) ); -ip = (int *)malloc( sizeof( int ) ); memset( ip, fill, dim * sizeof( int ) ); -ip = (int *)realloc( ip, 2 * dim * sizeof( int ) ); -ip = (int *)realloc( ip, 4 * dim * sizeof( int ) ); memset( ip, fill, 4 * dim * sizeof( int ) ); - -ip = memalign( 16, sizeof( int ) ); -ip = memalign( 16, sizeof( int ) ); memset( ip, fill, sizeof( int ) ); -ip = memalign( 16, dim * sizeof( int ) ); -ip = memalign( 16, dim * sizeof( int ) ); memset( ip, fill, dim * sizeof( int ) ); -\end{cfa} -\end{tabular} -\lstMakeShortInline@% -\end{cquote} -Variadic @new@ (see Section~\ref{sec:variadic-tuples}) cannot support the same overloading because extra parameters are for initialization. -Hence, there are @new@ and @anew@ routines for single and array variables, and the fill value is the arguments to the constructor, \eg: -\begin{cfa} -struct S { int i, j; }; -void ?{}( S & s, int i, int j ) { s.i = i; s.j = j; } -S * s = new( 2, 3 ); $\C{// allocate storage and run constructor}$ -S * as = anew( dim, 2, 3 ); $\C{// each array element initialized to 2, 3}$ -\end{cfa} -Note, \CC can only initialization array elements via the default constructor. - -Finally, the \CFA memory-allocator has \newterm{sticky properties} for dynamic storage: fill and alignment are remembered with an object's storage in the heap. -When a @realloc@ is performed, the sticky properties are respected, so that new storage is correctly aligned and initialized with the fill character. +Table~\ref{t:StorageManagementOperations} shows the capabilities provided by C/\Celeven allocation-functions and how all the capabilities can be combined into two \CFA functions. +\CFA storage-management functions extend the C equivalents by overloading, providing shallow type-safety, and removing the need to specify the base allocation-size. +Figure~\ref{f:StorageAllocation} contrasts \CFA and C storage-allocation operation performing the same operations with the same type safety. \begin{table} @@ -2319,4 +2326,62 @@ \end{table} +\begin{figure} +\centering +\begin{cquote} +\begin{cfa}[aboveskip=0pt] +size_t dim = 10; $\C{// array dimension}$ +char fill = '\xff'; $\C{// initialization fill value}$ +int * ip; +\end{cfa} +\lstDeleteShortInline@% +\begin{tabular}{@{}l@{\hspace{\parindentlnth}}l@{}} +\multicolumn{1}{c@{\hspace{\parindentlnth}}}{\textbf{\CFA}} & \multicolumn{1}{c}{\textbf{C}} \\ +\begin{cfa} +ip = alloc(); +ip = alloc( fill ); +ip = alloc( dim ); +ip = alloc( dim, fill ); +ip = alloc( ip, 2 * dim ); +ip = alloc( ip, 4 * dim, fill ); + +ip = align_alloc( 16 ); +ip = align_alloc( 16, fill ); +ip = align_alloc( 16, dim ); +ip = align_alloc( 16, dim, fill ); +\end{cfa} +& +\begin{cfa} +ip = (int *)malloc( sizeof( int ) ); +ip = (int *)malloc( sizeof( int ) ); memset( ip, fill, sizeof( int ) ); +ip = (int *)malloc( dim * sizeof( int ) ); +ip = (int *)malloc( sizeof( int ) ); memset( ip, fill, dim * sizeof( int ) ); +ip = (int *)realloc( ip, 2 * dim * sizeof( int ) ); +ip = (int *)realloc( ip, 4 * dim * sizeof( int ) ); memset( ip, fill, 4 * dim * sizeof( int ) ); + +ip = memalign( 16, sizeof( int ) ); +ip = memalign( 16, sizeof( int ) ); memset( ip, fill, sizeof( int ) ); +ip = memalign( 16, dim * sizeof( int ) ); +ip = memalign( 16, dim * sizeof( int ) ); memset( ip, fill, dim * sizeof( int ) ); +\end{cfa} +\end{tabular} +\lstMakeShortInline@% +\end{cquote} +\caption{\CFA versus C Storage-Allocation} +\label{f:StorageAllocation} +\end{figure} + +Variadic @new@ (see Section~\ref{sec:variadic-tuples}) cannot support the same overloading because extra parameters are for initialization. +Hence, there are @new@ and @anew@ functions for single and array variables, and the fill value is the arguments to the constructor, \eg: +\begin{cfa} +struct S { int i, j; }; +void ?{}( S & s, int i, int j ) { s.i = i; s.j = j; } +S * s = new( 2, 3 ); $\C{// allocate storage and run constructor}$ +S * as = anew( dim, 2, 3 ); $\C{// each array element initialized to 2, 3}$ +\end{cfa} +Note, \CC can only initialization array elements via the default constructor. + +Finally, the \CFA memory-allocator has \newterm{sticky properties} for dynamic storage: fill and alignment are remembered with an object's storage in the heap. +When a @realloc@ is performed, the sticky properties are respected, so that new storage is correctly aligned and initialized with the fill character. + \subsection{I/O} @@ -2406,5 +2471,5 @@ }% \end{itemize} -There are routines to set and get the separator string, and manipulators to toggle separation on and off in the middle of output. +There are functions to set and get the separator string, and manipulators to toggle separation on and off in the middle of output. @@ -2413,5 +2478,5 @@ \CFA has an interface to the GMP multi-precision signed-integers~\cite{GMP}, similar to the \CC interface provided by GMP. -The \CFA interface wraps GMP routines into operator routines to make programming with multi-precision integers identical to using fixed-sized integers. +The \CFA interface wraps GMP functions into operator functions to make programming with multi-precision integers identical to using fixed-sized integers. The \CFA type name for multi-precision signed-integers is @Int@ and the header file is @gmp@. The following multi-precision factorial programs contrast using GMP with the \CFA and C interfaces. @@ -2458,5 +2523,5 @@ Since all these languages share a subset essentially comprising standard C, maximal-performance benchmarks would show little runtime variance, other than in length and clarity of source code. A more illustrative benchmark measures the costs of idiomatic usage of each language's features. -Figure~\ref{fig:BenchmarkTest} shows the \CFA benchmark tests for a generic stack based on a singly linked-list, a generic pair-data-structure, and a variadic @print@ routine similar to that in Section~\ref{sec:variadic-tuples}. +Figure~\ref{fig:BenchmarkTest} shows the \CFA benchmark tests for a generic stack based on a singly linked-list, a generic pair-data-structure, and a variadic @print@ function similar to that in Section~\ref{sec:variadic-tuples}. The benchmark test is similar for C and \CC. The experiment uses element types @int@ and @pair(_Bool, char)@, and pushes $N=40M$ elements on a generic stack, copies the stack, clears one of the stacks, finds the maximum value in the other stack, and prints $N/2$ (to reduce graph height) constants. @@ -2472,5 +2537,5 @@ TIMED( "copy_int", t = s; ) TIMED( "clear_int", clear( s ); ) - REPEAT_TIMED( "pop_int", N, int x = pop( t ); max = max( x, max ); ) + REPEAT_TIMED( "pop_int", N, int v = pop( t ); max = max( v, max ); ) REPEAT_TIMED( "print_int", N/2, out | val | ':' | val | endl; ) @@ -2481,5 +2546,5 @@ TIMED( "copy_pair", t = s; ) TIMED( "clear_pair", clear( s ); ) - REPEAT_TIMED( "pop_pair", N, pair(_Bool, char) x = pop( t ); max = max( x, max ); ) + REPEAT_TIMED( "pop_pair", N, pair(_Bool, char) v = pop( t ); max = max( v, max ); ) REPEAT_TIMED( "print_pair", N/2, out | val | ':' | val | endl; ) } @@ -2553,11 +2618,11 @@ \CC is the most similar language to \CFA; both are extensions to C with source and runtime backwards compatibility. -The fundamental difference is in their engineering approach to C compatibility and programmer expectation. -While \CC provides good backwards compatibility with C, it has a steep learning curve for many of its extensions. +The fundamental difference is the engineering approach to maintain C compatibility and programmer expectation. +While \CC provides good compatibility with C, it has a steep learning curve for many of its extensions. For example, polymorphism is provided via three disjoint mechanisms: overloading, inheritance, and templates. The overloading is restricted because resolution does not use the return type, inheritance requires learning object-oriented programming and coping with a restricted nominal-inheritance hierarchy, templates cannot be separately compiled resulting in compilation/code bloat and poor error messages, and determining how these mechanisms interact and which to use is confusing. In contrast, \CFA has a single facility for polymorphic code supporting type-safe separate-compilation of polymorphic functions and generic (opaque) types, which uniformly leverage the C procedural paradigm. -The key mechanism to support separate compilation is \CFA's \emph{explicit} use of assumed properties for a type. -Until \CC concepts~\cite{C++Concepts} are standardized (anticipated for \CCtwenty), \CC provides no way to specify the requirements of a generic function in code beyond compilation errors during template expansion; +The key mechanism to support separate compilation is \CFA's \emph{explicit} use of assumed type properties. +Until \CC concepts~\cite{C++Concepts} are standardized (anticipated for \CCtwenty), \CC provides no way to specify the requirements of a generic function beyond compilation errors during template expansion; furthermore, \CC concepts are restricted to template polymorphism. @@ -2610,4 +2675,7 @@ +\subsection{Control Structures / Declarations / Literals} + + \section{Conclusion and Future Work} @@ -2669,5 +2737,7 @@ stack_node(T) ** crnt = &s.head; for ( stack_node(T) * next = t.head; next; next = next->next ) { - *crnt = malloc(){ next->value }; + stack_node(T) * new_node = ((stack_node(T)*)malloc()); + (*new_node){ next->value }; /***/ + *crnt = new_node; stack_node(T) * acrnt = *crnt; crnt = &acrnt->next; @@ -2684,13 +2754,14 @@ forall(otype T) _Bool empty( const stack(T) & s ) { return s.head == 0; } forall(otype T) void push( stack(T) & s, T value ) { - s.head = malloc(){ value, s.head }; + stack_node(T) * new_node = ((stack_node(T)*)malloc()); + (*new_node){ value, s.head }; /***/ + s.head = new_node; } forall(otype T) T pop( stack(T) & s ) { stack_node(T) * n = s.head; s.head = n->next; - T x = n->value; - ^n{}; - free( n ); - return x; + T v = n->value; + delete( n ); + return v; } forall(otype T) void clear( stack(T) & s ) { @@ -2848,99 +2919,4 @@ -\begin{comment} -\subsubsection{bench.h} -(\texttt{bench.hpp} is similar.) - -\lstinputlisting{evaluation/bench.h} - -\subsection{C} - -\subsubsection{c-stack.h} ~ - -\lstinputlisting{evaluation/c-stack.h} - -\subsubsection{c-stack.c} ~ - -\lstinputlisting{evaluation/c-stack.c} - -\subsubsection{c-pair.h} ~ - -\lstinputlisting{evaluation/c-pair.h} - -\subsubsection{c-pair.c} ~ - -\lstinputlisting{evaluation/c-pair.c} - -\subsubsection{c-print.h} ~ - -\lstinputlisting{evaluation/c-print.h} - -\subsubsection{c-print.c} ~ - -\lstinputlisting{evaluation/c-print.c} - -\subsubsection{c-bench.c} ~ - -\lstinputlisting{evaluation/c-bench.c} - -\subsection{\CFA} - -\subsubsection{cfa-stack.h} ~ - -\lstinputlisting{evaluation/cfa-stack.h} - -\subsubsection{cfa-stack.c} ~ - -\lstinputlisting{evaluation/cfa-stack.c} - -\subsubsection{cfa-print.h} ~ - -\lstinputlisting{evaluation/cfa-print.h} - -\subsubsection{cfa-print.c} ~ - -\lstinputlisting{evaluation/cfa-print.c} - -\subsubsection{cfa-bench.c} ~ - -\lstinputlisting{evaluation/cfa-bench.c} - -\subsection{\CC} - -\subsubsection{cpp-stack.hpp} ~ - -\lstinputlisting[language=c++]{evaluation/cpp-stack.hpp} - -\subsubsection{cpp-print.hpp} ~ - -\lstinputlisting[language=c++]{evaluation/cpp-print.hpp} - -\subsubsection{cpp-bench.cpp} ~ - -\lstinputlisting[language=c++]{evaluation/cpp-bench.cpp} - -\subsection{\CCV} - -\subsubsection{object.hpp} ~ - -\lstinputlisting[language=c++]{evaluation/object.hpp} - -\subsubsection{cpp-vstack.hpp} ~ - -\lstinputlisting[language=c++]{evaluation/cpp-vstack.hpp} - -\subsubsection{cpp-vstack.cpp} ~ - -\lstinputlisting[language=c++]{evaluation/cpp-vstack.cpp} - -\subsubsection{cpp-vprint.hpp} ~ - -\lstinputlisting[language=c++]{evaluation/cpp-vprint.hpp} - -\subsubsection{cpp-vbench.cpp} ~ - -\lstinputlisting[language=c++]{evaluation/cpp-vbench.cpp} -\end{comment} - \end{document}