Hi，I have watched the developer tutorial given by @Lunderberg in TVM Conf 21. The great talk helps me obtain the outline of adding a new device.
However, after checking the source code in [CUDA runtime](https://github.com/apache/tvm/tree/main/src/runtime/cuda) , I have following questions about ThreadEntry ([CUDAThreadEntry](https://github.com/apache/tvm/blob/f4af81c5f7bbdf70f7271c5fe54f332857165cab/src/runtime/cuda/cuda_common.h#L55)), which is not included in the tutorial. ``` /*! \brief Thread local workspace */ class CUDAThreadEntry { public: /*! \brief The cuda stream */ cudaStream_t stream{nullptr}; /*! \brief thread local pool*/ WorkspacePool pool; /*! \brief constructor */ CUDAThreadEntry(); // get the threadlocal workspace static CUDAThreadEntry* ThreadLocal(); }; ``` To my understanding, the tvm runtime executes the OPs in a sequential order ([graph_executor.cc](https://github.com/apache/tvm/blob/f4af81c5f7bbdf70f7271c5fe54f332857165cab/src/runtime/graph_executor/graph_executor.cc#L61)); if so, what is the role of the class CUDAThreadEntry ? Besides, when adding a new device, can I ignore this class and do not implement it ? (just as the instructions given in the tutorial) ? Looking forward to help. --- [Visit Topic](https://discuss.tvm.apache.org/t/questions-about-threadentry-in-runtime-module/11746/1) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/824f5d518a7cb964a9f9e56041bab0377b2b85b20723fdd2192849a8ca6e897f).
