diff --git a/content/backmatter.tex b/content/backmatter.tex index 2a410eccc..4516bbf22 100644 --- a/content/backmatter.tex +++ b/content/backmatter.tex @@ -522,6 +522,23 @@ \section{Version 1.5} \CONST{SHMEM\_MALLOC\_ATOMICS\_REMOTE} and \CONST{SHMEM\_MALLOC\_SIGNAL\_REMOTE}. \\ See Section \ref{subsec:shmmallochint} and \ref{subsec:library_constants}. % +\item Specified that team-based broadcast operations update the \VAR{dest} object on +all \acp{PE}, including the root \ac{PE}. +\\ See Section \ref{subsec:shmem_broadcast}. +% +\item Deprecated active-set-based collective functions. +\\ See Section \ref{subsec:coll}. +% +\item Added team-based collective functions: \FUNC{shmem\_sync}, + \FUNC{shmem\_broadcast\{mem\}}, \FUNC{shmem\_collect\{mem\}},\\ + \FUNC{shmem\_TYPENAME\_OP\_reduce}, + \FUNC{shmem\_alltoall\{mem\}}, and + \FUNC{shmem\_alltoalls\{mem\}}. + \\ See Sections \ref{subsec:shmem_sync}, + \ref{subsec:shmem_broadcast}, \ref{subsec:shmem_collect}, + \ref{subsec:shmem_reductions}, \ref{subsec:shmem_alltoall}, + and \ref{subsec:shmem_alltoalls}. +% \item Added support for nonblocking \ac{AMO} functions. \\ See Section \ref{sec:amo-nbi}. % diff --git a/content/collective_intro.tex b/content/collective_intro.tex index 21fdd5fad..576fdecc6 100644 --- a/content/collective_intro.tex +++ b/content/collective_intro.tex @@ -108,7 +108,7 @@ \subsubsection*{Active-set-based collectives} \item \FUNC{shmem\_broadcast\{32, 64\}} \item \FUNC{shmem\_collect\{32, 64\}} \item \FUNC{shmem\_fcollect\{32, 64\}} -\item Reduction routines for the following operations: AND, MAX, MIN, SUM, PROD, OR, XOR +\item Reduction routines for the following operations: AND, OR, XOR, MAX, MIN, SUM, PROD \item \FUNC{shmem\_alltoall\{32, 64\}} \item \FUNC{shmem\_alltoalls\{32, 64\}} \end{itemize} @@ -128,7 +128,7 @@ \subsubsection*{Team-implicit collectives} a call to \FUNC{shmem\_ctx\_quiet} on the default context followed by a call to \FUNC{shmem\_team\_sync} on the world team. -\subsubsection*{Error codes returned from collectives} +\subsubsection*{Error codes returned from team-based collectives} Collective operations involving multiple \acp{PE} may return values indicating success while other \acp{PE} are still executing the diff --git a/content/shmem_alltoall.tex b/content/shmem_alltoall.tex index 3d76205dc..c4d74b771 100644 --- a/content/shmem_alltoall.tex +++ b/content/shmem_alltoall.tex @@ -68,7 +68,7 @@ \end{itemize} The data being sent and received are - stored in a contiguous symmetric data object. The total size of each \acp{PE} + stored in a contiguous symmetric data object. The total size of each \ac{PE}'s \VAR{source} object and \VAR{dest} object is \VAR{nelems} times the size of an element times \VAR{N}, where \VAR{N} equals the number of \acp{PE} participating diff --git a/content/shmem_broadcast.tex b/content/shmem_broadcast.tex index 246aabdb3..79603b83b 100644 --- a/content/shmem_broadcast.tex +++ b/content/shmem_broadcast.tex @@ -144,7 +144,7 @@ \apicexample {In the following \Cstd[11] example, the call to \FUNC{shmem\_broadcast} copies \source{} - on \ac{PE} $0$ to \dest{} on \acp{PE} $1\dots npes-1$. + on \ac{PE} $0$ to \dest{} on \acp{PE} $0\dots npes-1$. \CorCpp{} example:} {./example_code/shmem_broadcast_example.c} diff --git a/content/shmem_sync.tex b/content/shmem_sync.tex index eef083ce3..6e41ee825 100644 --- a/content/shmem_sync.tex +++ b/content/shmem_sync.tex @@ -87,7 +87,7 @@ \begin{apiexamples} \apicexample - {The following \FUNC{shmem\_sync\_all} and \FUNC{shmem\_sync} example is + {The following \FUNC{shmem\_sync} example is for \Cstd[11] programs:} {./example_code/shmem_sync_example.c} {} diff --git a/content/shmem_sync_all.tex b/content/shmem_sync_all.tex index 12bad423a..6fc5bbdc0 100644 --- a/content/shmem_sync_all.tex +++ b/content/shmem_sync_all.tex @@ -1,6 +1,7 @@ \apisummary{ Registers the arrival of a \ac{PE} at a synchronization point and suspends - execution until all other \acp{PE} in the world team arrive at a synchronization point. For multithreaded programs, execution is suspended + execution until all other \acp{PE} in the world team arrive at the synchronization point. + For multithreaded programs, execution is suspended as specified by the threading model (Section \ref{subsec:thread_support}). }