On 2018/12/7 04:57 AM, Thomas Schwinge wrote>> ---
a/libgomp/plugin/plugin-nvptx.c
+++ b/libgomp/plugin/plugin-nvptx.c
+struct goacc_asyncqueue *
+GOMP_OFFLOAD_openacc_async_construct (void)
+{
+ struct goacc_asyncqueue *aq
+ = GOMP_PLUGIN_malloc (sizeof (struct goacc_asyncqueue));
+ aq->cuda_stream = NULL;
+ CUDA_CALL_ASSERT (cuStreamCreate, &aq->cuda_stream, CU_STREAM_DEFAULT);
Curiously (this was the same in the code before): does this have to be
"CU_STREAM_DEFAULT" instead of "CU_STREAM_NON_BLOCKING", because we want
to block anything from running in parallel with "acc_async_sync" GPU
kernels, that use the "NULL" stream? (Not asking you to change this now,
but I wonder if this is overly strict?)
IIUC, this non-blocking only pertains to the "Legacy Default Stream" in
CUDA, which we're pretty much ignoring; we should be using the newer
per-thread default stream model. We could review this issue later.
+ if (aq->cuda_stream == NULL)
+ GOMP_PLUGIN_fatal ("CUDA stream create NULL\n");
Can this actually happen, given the "CUDA_CALL_ASSERT" usage above?
Hmm, yeah I think this is superfluous too...
+ CUDA_CALL_ASSERT (cuStreamSynchronize, aq->cuda_stream);
Why is the synchronization needed here?
I don't remember, could likely be something added during debug.
I'll remove this and test if things are okay.
Thanks,
Chung-Lin
