Skip to content

[RUNTIME] Ensure NDArray.CopyTo(Device) always sync #16716

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tqchen merged 1 commit into from
Mar 14, 2024
Merged

[RUNTIME] Ensure NDArray.CopyTo(Device) always sync #16716

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions include/tvm/runtime/device_api.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,6 +147,8 @@ class TVM_DLL DeviceAPI {
* \param from The source array.
* \param to The target array.
* \param stream Optional stream object.
* \note The copy may happen asynchronously if it involves a GPU context.
* Call StreamSync to ensure the copy completes from host's pov.
*/
virtual void CopyDataFromTo(DLTensor* from, DLTensor* to, TVMStreamHandle stream);
/*!
Expand Down
12 changes: 2 additions & 10 deletions include/tvm/runtime/ndarray.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,8 +112,9 @@ class NDArray : public ObjectRef {
* \param dev The target device.
* \param mem_scope The memory scope of the target array.
* \return The array under another device.
* \note The copy always triggers a TVMSynchronize.
*/
inline NDArray CopyTo(const Device& dev, Optional<String> mem_scope = NullOpt) const;
TVM_DLL NDArray CopyTo(const Device& dev, Optional<String> mem_scope = NullOpt) const;
/*!
* \brief Load NDArray from stream
* \param stream The input data stream
Expand Down Expand Up @@ -399,15 +400,6 @@ inline void NDArray::CopyTo(const NDArray& other) const {
CopyFromTo(&(get_mutable()->dl_tensor), &(other.get_mutable()->dl_tensor));
}

inline NDArray NDArray::CopyTo(const Device& dev, Optional<String> mem_scope) const {
ICHECK(data_ != nullptr);
const DLTensor* dptr = operator->();
NDArray ret =
Empty(ShapeTuple(dptr->shape, dptr->shape + dptr->ndim), dptr->dtype, dev, mem_scope);
this->CopyTo(ret);
return ret;
}

inline int NDArray::use_count() const { return data_.use_count(); }

inline const DLTensor* NDArray::operator->() const { return &(get_mutable()->dl_tensor); }
Expand Down
11 changes: 11 additions & 0 deletions src/runtime/ndarray.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -287,6 +287,17 @@ void NDArray::CopyFromBytes(const void* data, size_t nbytes) {
ArrayCopyFromBytes(&get_mutable()->dl_tensor, data, nbytes);
}

NDArray NDArray::CopyTo(const Device& dev, Optional<String> mem_scope) const {
ICHECK(data_ != nullptr);
const DLTensor* dptr = operator->();
NDArray ret =
Empty(ShapeTuple(dptr->shape, dptr->shape + dptr->ndim), dptr->dtype, dev, mem_scope);
this->CopyTo(ret);
Device copy_gpu_dev = dptr->device.device_type != kDLCPU ? dptr->device : dev;
DeviceAPI::Get(copy_gpu_dev)->StreamSync(copy_gpu_dev, nullptr);
return ret;
}

void NDArray::CopyFromTo(const DLTensor* from, DLTensor* to, TVMStreamHandle stream) {
size_t from_size = GetDataSize(*from);
size_t to_size = GetDataSize(*to);
Expand Down