Add initial support for nbi put-with-signal

content/shmem_put_signal_nbi.tex

@@ -0,0 +1,81 @@
+\color{Green}
+\apisummary{
+    The nonblocking put-with-signal routines provide a method for copying data
+    from a contiguous local data object to a data object on a specified \ac{PE}
+    and subsequently setting a remote flag to signal completion.
+}
+
+\begin{apidefinition}
+
+\begin{C11synopsis}
+void @\FuncDecl{shmem\_put\_signal\_nbi}@(TYPE *dest, const TYPE *source, size_t nelems, uint64_t *sig_addr, uint64_t signal, int pe);
+void @\FuncDecl{shmem\_put\_signal\_nbi}@(shmem_ctx_t ctx, TYPE *dest, const TYPE *source, size_t nelems, uint64_t *sig_addr, uint64_t signal, int pe);
+\end{C11synopsis}
+where \TYPE{} is one of the standard \ac{RMA} types specified by Table \ref{stdrmatypes}.
+
+\begin{Csynopsis}
+void @\FuncDecl{shmem\_\FuncParam{TYPENAME}\_put\_signal\_nbi}@(TYPE *dest, const TYPE *source, size_t nelems, uint64_t *sig_addr, uint64_t signal, int pe);
+void @\FuncDecl{shmem\_ctx\_\FuncParam{TYPENAME}\_put\_signal\_nbi}@(shmem_ctx_t ctx, TYPE *dest, const TYPE *source, size_t nelems, uint64_t *sig_addr, uint64_t signal, int pe);
+\end{Csynopsis}
+where \TYPE{} is one of the standard \ac{RMA} types and has a corresponding \TYPENAME{} specified by Table \ref{stdrmatypes}.
+
+\begin{CsynopsisCol}
+void @\FuncDecl{shmem\_put\FuncParam{SIZE}\_signal\_nbi}@(void *dest, const void *source, size_t nelems, uint64_t *sig_addr, uint64_t signal, int pe);
+void @\FuncDecl{shmem\_ctx\_put\FuncParam{SIZE}\_signal\_nbi}@(shmem_ctx_t ctx, void *dest, const void *source, size_t nelems, uint64_t *sig_addr, uint64_t signal, int pe);
+\end{CsynopsisCol}
+where \SIZE{} is one of \CONST{8, 16, 32, 64, 128}.
+
+\begin{CsynopsisCol}
+void @\FuncDecl{shmem\_putmem\_signal\_nbi}@(void *dest, const void *source, size_t nelems, uint64_t *sig_addr, uint64_t signal, int pe);
+void @\FuncDecl{shmem\_ctx\_putmem\_signal\_nbi}@(shmem_ctx_t ctx, void *dest, const void *source, size_t nelems, uint64_t *sig_addr, uint64_t signal, int pe);
+\end{CsynopsisCol}
+
+\begin{apiarguments}
+    \apiargument{IN}{ctx}{The context on which to perform the operation.
+      When this argument is not provided, the operation is performed on
+      \CONST{SHMEM\_CTX\_DEFAULT}.}
+    \apiargument{OUT}{dest}{Data object to be updated on the remote \ac{PE}. This
+    data object must be remotely accessible.}
+    \apiargument{IN}{source}{Data object containing the data to be copied.}
+    \apiargument{IN}{nelems}{Number of elements in the \VAR{dest} and \VAR{source}
+    arrays. \VAR{nelems} must be of type \VAR{size\_t} for \Cstd.}
+    \apiargument{OUT}{sig\_addr}{Data object to be updated on the remote
+    \ac{PE} as the signal. This signal data object must be
+    remotely accessible.}
+    \apiargument{IN}{signal}{Unsigned 64-bit value that is assigned to the
+    remote \VAR{sig\_addr} signal data object.}
+    \apiargument{IN}{pe}{\ac{PE} number of the remote \ac{PE}.}
+\end{apiarguments}
+
+\apidescription{
+    The routines return after posting the operation. The operation is considered
+    complete after the subsequent call to \FUNC{shmem\_quiet}. At the completion
+    of \FUNC{shmem\_quiet}, the data has been copied out of the \source{}
+    array on the local \ac{PE} and delivered into the \dest{} array on the
+    destination \ac{PE}. The delivery of \signal{} flag on the remote
+    \ac{PE} indicates the delivery of its corresponding \dest{} data words
+    into the data object on the remote \ac{PE}.
+}
+
+\apireturnvalues{
+    None.
+}
+
+\apinotes{
+    The \VAR{dest} and \VAR{sig\_addr} data objects must both be remotely
+    accessible. The \VAR{sig\_addr} and \VAR{dest} could be of different kinds,
+    for example, one could be a global/static \Cstd variable and the other could
+    be allocated on the symmetric heap.
+
+    The delivery of \signal{} flag on the remote \ac{PE} indicates only the
+    delivery of its corresponding \dest{} data words into the data object on
+    the remote \ac{PE}. Without a memory-ordering operation, there is no implied
+    ordering between the delivery of the signal word of a nonblocking
+    put-with-signal routine and another data transfer. For example, the delivery
+    of the signal word in a sequence consisting of a put routine followed by a
+    nonblocking put-with-signal routine does not imply delivery of the put
+    routine's data.
+}
+
+\end{apidefinition}
+\color{Black}

main_spec.tex

@@ -174,6 +174,9 @@ \subsection{Non-blocking Remote Memory Access Routines}\label{sec:rma_nbi}
 \subsubsection{\textbf{SHMEM\_PUT\_NBI}}\label{subsec:shmem_put_nbi}
 \input{content/shmem_put_nbi.tex}
 
+\subsubsection{\textbf{SHMEM\_PUT\_SIGNAL\_NBI}}\label{subsec:shmem_put_signal_nbi}
+\input{content/shmem_put_signal_nbi.tex}
+
 \subsubsection{\textbf{SHMEM\_GET\_NBI}}\label{subsec:shmem_get_nbi}
 \input{content/shmem_get_nbi.tex}