echuraev commented on code in PR #12711:
URL: https://github.com/apache/tvm/pull/12711#discussion_r963695735
##########
src/runtime/contrib/clml/clml_runtime.cc:
##########
@@ -146,22 +169,7 @@ class CLMLRuntime : public JSONRuntimeBase {
LOG(WARNING) << "CLML Runtime Init: Qualcomm extn not present.\n";
return;
}
-
- // Reuse the OpenCl work space from TVM Device API.
- auto func = tvm::runtime::Registry::Get("device_api.opencl");
- ICHECK(func != nullptr) << "Cannot find OpenCL device_api in registry";
- auto device_api = static_cast<cl::OpenCLWorkspace*>(((*func)()).operator
void*());
- this->context = device_api->context;
- bool queue_found = false;
- for (size_t i = 0; i < device_api->devices.size(); ++i) {
- if (device_api->devices[i] == device_id) {
- this->queue = device_api->queues[i];
- this->evts = &(device_api->events[i]);
- queue_found = true;
- }
- }
- ICHECK(queue_found != false) << "Device queue not found in OpenCL
Workspace";
-
+ this->queue = GetCommadQueue();
Review Comment:
Sorry, probably I missed something. I have never looked at OpenCLML part of
TVM before. Could you please explain why you didn't reuse code from OpenCL
runtime?
Won't this pseudocode work in the same way?
```suggestion
void InitCLML() {
// Setup CLML Context
cl_int result = 0;
// Initialize Context and Command Queue
OpenCLWorkspace* workspace = OpenCLWorkspace::Global();
workspace->Init();
OpenCLThreadEntry* t = workspace->GetThreadEntry();
cl_device_id did = workspace->devices[t->device.device_id];
if (!ExtensionStringPresent(did)) {
LOG(WARNING) << "CLML Runtime Init: Qualcomm extn not present.\n";
return;
}
this->queue = workspace->GetQueue(t->device);
```
If it works, it won't be necessary to implement function `GetCommadQueue`.
--
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]
