diff options
author | Thomas Schwinge <thomas@codesourcery.com> | 2023-03-24 15:14:57 +0100 |
---|---|---|
committer | Thomas Schwinge <thomas@codesourcery.com> | 2023-04-03 16:30:26 +0200 |
commit | 165b44cd22232ba7fc16dfd457322f6c95499d01 (patch) | |
tree | 75a19151d6676f6a89d4736b27d3eab659338bc7 | |
parent | 472783f3137475b82baadac31cca31021b69aba9 (diff) | |
download | gcc-165b44cd22232ba7fc16dfd457322f6c95499d01.zip gcc-165b44cd22232ba7fc16dfd457322f6c95499d01.tar.gz gcc-165b44cd22232ba7fc16dfd457322f6c95499d01.tar.bz2 |
libgomp: Document OpenMP 'pinned' memory
libgomp/
* libgomp.texi (AMD Radeon, nvptx): Document OpenMP 'pinned'
memory.
-rw-r--r-- | libgomp/ChangeLog.omp | 5 | ||||
-rw-r--r-- | libgomp/libgomp.texi | 8 |
2 files changed, 13 insertions, 0 deletions
diff --git a/libgomp/ChangeLog.omp b/libgomp/ChangeLog.omp index 22beccc..d8a7e47 100644 --- a/libgomp/ChangeLog.omp +++ b/libgomp/ChangeLog.omp @@ -1,3 +1,8 @@ +2023-04-03 Thomas Schwinge <thomas@codesourcery.com> + + * libgomp.texi (AMD Radeon, nvptx): Document OpenMP 'pinned' + memory. + 2023-03-27 Julian Brown <julian@codesourcery.com> * testsuite/libgomp.c++/static-aggr-constructor-destructor-1.C: New diff --git a/libgomp/libgomp.texi b/libgomp/libgomp.texi index 288e0b3..6355ce2 100644 --- a/libgomp/libgomp.texi +++ b/libgomp/libgomp.texi @@ -4456,6 +4456,9 @@ The implementation remark: @item OpenMP code that has a requires directive with @code{unified_address} or @code{unified_shared_memory} will remove any GCN device from the list of available devices (``host fallback''). +@item OpenMP @emph{pinned} memory (@code{omp_atk_pinned}, + @code{ompx_pinned_mem_alloc}, for example) + is allocated via @code{mmap}, @code{mlock}. @end itemize @@ -4518,6 +4521,11 @@ The implementation remark: @item OpenMP code that has a requires directive with @code{unified_address} or @code{unified_shared_memory} will remove any nvptx device from the list of available devices (``host fallback''). +@item OpenMP @emph{pinned} memory (@code{omp_atk_pinned}, + @code{ompx_pinned_mem_alloc}, for example) + is allocated via @code{cuMemHostAlloc} (CUDA Driver API). + This potentially helps optimization of host <-> device data + transfers. @end itemize |