@@ -725,7 +725,7 @@ LIBOMPTARGET_DEBUG
725
725
""""""""""""""""""
726
726
727
727
``LIBOMPTARGET_DEBUG `` controls whether or not debugging information will be
728
- displayed. This feature is only availible if ``libomptarget `` was built with
728
+ displayed. This feature is only available if ``libomptarget `` was built with
729
729
``-DOMPTARGET_DEBUG ``. The debugging output provided is intended for use by
730
730
``libomptarget `` developers. More user-friendly output is presented when using
731
731
``LIBOMPTARGET_INFO ``.
@@ -975,7 +975,7 @@ going wrong.
975
975
Libomptarget error: Consult https://openmp.llvm.org/design/Runtimes.html for debugging options.
976
976
sum.cpp:5:1: Libomptarget error 1: failure of target construct while offloading is mandatory
977
977
978
- This shows that there is an illegal memory access occuring inside the OpenMP
978
+ This shows that there is an illegal memory access occurring inside the OpenMP
979
979
target region once execution has moved to the CUDA device, suggesting a
980
980
segmentation fault. This then causes a chain reaction of failures in
981
981
``libomptarget ``. Another message suggests using the ``LIBOMPTARGET_INFO ``
@@ -1061,7 +1061,7 @@ of LLVM did not.
1061
1061
LIBOMPTARGET_JIT_OPT_LEVEL
1062
1062
""""""""""""""""""""""""""
1063
1063
1064
- This environment variable can be used to change the optimization pipeleine used
1064
+ This environment variable can be used to change the optimization pipeline used
1065
1065
to optimize the embedded device code as part of the device JIT. The value is
1066
1066
corresponds to the ``-O{0,1,2,3} `` command line argument passed to ``clang ``.
1067
1067
@@ -1225,9 +1225,9 @@ LIBOMPTARGET_AMDGPU_MAX_ASYNC_COPY_BYTES
1225
1225
1226
1226
This environment variable specifies the maximum size in bytes where the memory
1227
1227
copies are asynchronous operations in the AMDGPU plugin. Up to this transfer
1228
- size, the memory copies are asychronous operations pushed to the corresponding
1228
+ size, the memory copies are asynchronous operations pushed to the corresponding
1229
1229
stream. For larger transfers, they are synchronous transfers. Memory copies
1230
- involving already locked/pinned host buffers are always asychronous . The default
1230
+ involving already locked/pinned host buffers are always asynchronous . The default
1231
1231
value is ``1*1024*1024 `` bytes (1 MB).
1232
1232
1233
1233
LIBOMPTARGET_AMDGPU_NUM_INITIAL_HSA_SIGNALS
@@ -1288,7 +1288,7 @@ LIBOMPTARGET_RPC_ADDRESS
1288
1288
The address and port at which the server is running. This needs to be set for
1289
1289
the server and the application, the default is ``0.0.0.0:50051 ``. A single
1290
1290
OpenMP executable can offload onto multiple remote hosts by setting this to
1291
- comma-seperated values of the addresses.
1291
+ comma-separated values of the addresses.
1292
1292
1293
1293
LIBOMPTARGET_RPC_ALLOCATOR_MAX
1294
1294
""""""""""""""""""""""""""""""
0 commit comments