libgomp, docs: Fix misplaced pinned memory description

The NVPTX note about ompx_gnu_pinned_mem_alloc was accidentally placed in
the AMD GCN section.  This patch moves the paragraph to the NVPTX section.

However, the text was not actually wrong in the context of AMD GCN, so I've
adapted the wording, rather than removing it.

libgomp/ChangeLog:

	* libgomp.texi: Separate the ompx_gnu_pinned_mem_alloc notes for
	NVPTX and AMD GCN, and move them to right sections.

diff --git a/libgomp/libgomp.texi b/libgomp/libgomp.texi
index 0e6c20b58291ef979f9ba4ea5a9cfa2d2cd13f58..b047ea172e1be958788de62097798650b0f763c9 100644 (file)
--- a/libgomp/libgomp.texi
+++ b/libgomp/libgomp.texi
@@ -7187,10 +7187,9 @@ The implementation remark:
       pool is exhausted.
 @item Pinned memory allocated using @code{omp_alloc} with the
       @code{ompx_gnu_pinned_mem_alloc} allocator or the @code{pinned} trait is
-      obtained via the CUDA API when an NVPTX device is present.  This provides
-      a performance boost for NVPTX offload code and also allows unlimited use
-      of pinned memory regardless of the OS @code{ulimit}/@code{rlimit}
-      settings.
+      obtained via the CUDA API when an NVPTX device is present (even when
+      the primary device is AMD).  This allows unlimited use of pinned memory
+      regardless of the OS @code{ulimit}/@code{rlimit} settings.
 @item Managed memory allocated on the host with the
       @code{ompx_gnu_managed_mem_alloc} allocator or in the
       @code{ompx_gnu_managed_mem_space} (both GNU extensions) allocate memory
@@ -7387,6 +7386,12 @@ The implementation remark:
       use the fall-back setting. If the default device is configured
       differently when the memory is freed, via @code{omp_free} or
       @code{omp_realloc}, the result may be undefined.
+@item Pinned memory allocated using @code{omp_alloc} with the
+      @code{ompx_gnu_pinned_mem_alloc} allocator or the @code{pinned} trait is
+      obtained via the CUDA API when an NVPTX device is present.  This provides
+      a performance boost for NVPTX offload code and also allows unlimited use
+      of pinned memory regardless of the OS @code{ulimit}/@code{rlimit}
+      settings.
 @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