gemini-code-assist[bot] commented on code in PR #18581:
URL: https://github.com/apache/tvm/pull/18581#discussion_r2610087138
##########
src/runtime/opencl/opencl_device_api.cc:
##########
@@ -472,7 +472,7 @@ void OpenCLWorkspace::SetNativePtr(const
tvm::runtime::Tensor& narr, void* host_
}
void OpenCLWorkspace::SetPerfHint(Device dev, cl_uint perf_hint) {
-#ifdef CL_CONTEXT_PERF_HINT_QCOM
+#if defined(USER_OPENCL_EXTN_QCOM) && defined(CL_CONTEXT_PERF_HINT_QCOM)
Review Comment:
There appears to be a typo in the preprocessor macro name. The pull request
description and other parts of the codebase (e.g., in `SetNativePtr`, CMake
files, and other headers) consistently use `USE_OPENCL_EXTN_QCOM`. The macro
`USER_OPENCL_EXTN_QCOM` used here is likely incorrect and will prevent this
code path from being compiled as intended. Please correct it to
`USE_OPENCL_EXTN_QCOM` for consistency and to ensure the fix works as expected.
```suggestion
#if defined(USE_OPENCL_EXTN_QCOM) && defined(CL_CONTEXT_PERF_HINT_QCOM)
```
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
