diff options
Diffstat (limited to 'libgomp/libgomp.texi')
| -rw-r--r-- | libgomp/libgomp.texi | 25 |
1 files changed, 15 insertions, 10 deletions
diff --git a/libgomp/libgomp.texi b/libgomp/libgomp.texi index 4217c29..dfd189b 100644 --- a/libgomp/libgomp.texi +++ b/libgomp/libgomp.texi @@ -258,7 +258,7 @@ The OpenMP 4.5 specification is fully supported. device memory mapped by an array section @tab P @tab @item Mapping of Fortran pointer and allocatable variables, including pointer and allocatable components of variables - @tab P @tab Mapping of vars with allocatable components unsupported + @tab Y @tab @item @code{defaultmap} extensions @tab Y @tab @item @code{declare mapper} directive @tab N @tab @item @code{omp_get_supported_active_levels} routine @tab Y @tab @@ -2316,7 +2316,7 @@ the initial device. @end multitable @item @emph{See also}: -@ref{omp_target_memcpy_rect_async}, @ref{omp_target_memcpy} +@ref{omp_target_memcpy_rect_async}, @ref{omp_target_memcpy}, @ref{Offload-Target Specifics} @item @emph{Reference}: @uref{https://www.openmp.org, OpenMP specification v5.1}, Section 3.8.6 @@ -2391,7 +2391,7 @@ the initial device. @end multitable @item @emph{See also}: -@ref{omp_target_memcpy_rect}, @ref{omp_target_memcpy_async} +@ref{omp_target_memcpy_rect}, @ref{omp_target_memcpy_async}, @ref{Offload-Target Specifics} @item @emph{Reference}: @uref{https://www.openmp.org, OpenMP specification v5.1}, Section 3.8.8 @@ -6888,7 +6888,7 @@ The implementation remark: @code{device(ancestor:1)}) are processed serially per @code{target} region such that the next reverse offload region is only executed after the previous one returned. -@item OpenMP code that has a @code{requires} directive with +@item OpenMP code that has a @code{requires} directive with @code{self_maps} or @code{unified_shared_memory} is only supported if all AMD GPUs have the @code{HSA_AMD_SYSTEM_INFO_SVM_ACCESSIBLE_BY_DEFAULT} property; for discrete GPUs, this may require setting the @code{HSA_XNACK} environment @@ -6911,6 +6911,11 @@ The implementation remark: @code{omp_thread_mem_alloc}, all use low-latency memory as first preference, and fall back to main graphics memory when the low-latency pool is exhausted. +@item The OpenMP routines @code{omp_target_memcpy_rect} and + @code{omp_target_memcpy_rect_async} and the @code{target update} + directive for non-contiguous list items use the 3D memory-copy function + of the HSA library. Higher dimensions call this functions in a loop and + are therefore supported. @item The unique identifier (UID), used with OpenMP's API UID routines, is the value returned by the HSA runtime library for @code{HSA_AMD_AGENT_INFO_UUID}. For GPUs, it is currently @samp{GPU-} followed by 16 lower-case hex digits, @@ -7040,7 +7045,7 @@ The implementation remark: Per device, reverse offload regions are processed serially such that the next reverse offload region is only executed after the previous one returned. -@item OpenMP code that has a @code{requires} directive with +@item OpenMP code that has a @code{requires} directive with @code{self_maps} or @code{unified_shared_memory} runs on nvptx devices if and only if all of those support the @code{pageableMemoryAccess} property;@footnote{ @uref{https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#um-requirements}} @@ -7048,11 +7053,6 @@ The implementation remark: devices (``host fallback''). @item The default per-warp stack size is 128 kiB; see also @code{-msoft-stack} in the GCC manual. -@item The OpenMP routines @code{omp_target_memcpy_rect} and - @code{omp_target_memcpy_rect_async} and the @code{target update} - directive for non-contiguous list items will use the 2D and 3D - memory-copy functions of the CUDA library. Higher dimensions will - call those functions in a loop and are therefore supported. @item Low-latency memory (@code{omp_low_lat_mem_space}) is supported when the the @code{access} trait is set to @code{cgroup}, and libgomp has been built for PTX ISA version 4.1 or higher (such as in GCC's @@ -7070,6 +7070,11 @@ The implementation remark: @code{omp_thread_mem_alloc}, all use low-latency memory as first preference, and fall back to main graphics memory when the low-latency pool is exhausted. +@item The OpenMP routines @code{omp_target_memcpy_rect} and + @code{omp_target_memcpy_rect_async} and the @code{target update} + directive for non-contiguous list items use the 2D and 3D memory-copy + functions of the CUDA library. Higher dimensions call those functions + in a loop and are therefore supported. @item The unique identifier (UID), used with OpenMP's API UID routines, consists of the @samp{GPU-} prefix followed by the 16-bytes UUID as returned by the CUDA runtime library. This UUID is output in grouped lower-case |