https://gcc.gnu.org/g:98586c2f620d2b6789257c29b4bc77567b1152c6
commit 98586c2f620d2b6789257c29b4bc77567b1152c6
Author: Thomas Schwinge <tho...@codesourcery.com>
Date: Sat Apr 19 20:57:56 2025 +0000
libgomp: Document OpenMP 'pinned' memory
libgomp/
* libgomp.texi (AMD Radeon, nvptx): Document OpenMP 'pinned'
memory.
Diff:
---
libgomp/libgomp.texi | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/libgomp/libgomp.texi b/libgomp/libgomp.texi
index 57460c4a631b..2dc2ef7976a0 100644
--- a/libgomp/libgomp.texi
+++ b/libgomp/libgomp.texi
@@ -6889,6 +6889,9 @@ The implementation remark:
does not support XNACK, consider using @code{ROCR_VISIBLE_DEVICES} to
enable only the APU. If not supported, all AMD GPU devices are removed
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}.
@item The available stack size can be changed using the @code{GCN_STACK_SIZE}
environment variable; the default is 32 kiB per thread.
@item Low-latency memory (@code{omp_low_lat_mem_space}) is supported when the
@@ -7053,6 +7056,11 @@ The implementation remark:
@uref{https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#um-requirements}}
otherwise, all nvptx device are removed 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.
@item The default per-warp stack size is 128 kiB; see also @code{-msoft-stack}
in the GCC manual.
@item Low-latency memory (@code{omp_low_lat_mem_space}) is supported when the
