zeroshade commented on code in PR #37365:
URL: https://github.com/apache/arrow/pull/37365#discussion_r1309065755
##########
cpp/src/arrow/gpu/cuda_context.h:
##########
@@ -140,6 +142,71 @@ class ARROW_EXPORT CudaDevice : public Device {
/// \param[in] size The buffer size in bytes
Result<std::shared_ptr<CudaHostBuffer>> AllocateHostBuffer(int64_t size);
+ /// \brief EXPERIMENTAL: Wrapper for CUstreams
+ ///
+ /// Does not *own* the CUstream object which must be separately constructed
+ /// and freed using cuStreamCreate and cuStreamDestroy (or equivalent).
+ /// Default construction will use the cuda default stream, and does not allow
+ /// construction from literal 0 or nullptr.
+ class ARROW_EXPORT Stream : public Device::Stream {
+ public:
+ explicit Stream(std::shared_ptr<CudaContext> ctx) noexcept
+ : context_{std::move(ctx)}, stream_{} {}
+
+ ~Stream() = default;
+ explicit Stream(std::shared_ptr<CudaContext> ctx, CUstream stream) noexcept
+ : context_{std::move(ctx)}, stream_{stream} {}
Review Comment:
I tend to agree with both of you and lean towards the synchronicity and
convenience side of things. It's nice having the APIs be similar between the
events and streams and so I lean more towards the ownership of the stream
itself.
That said, I'm not opposed to having it just wrap and not own. What do you
think @bkietz?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
