I found out that it might the problem of python thread.Thread instead of TVM.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/multithread-threadpool-performance-degradation-when-running-relay-module-in-multiple-threads/10374/10)
to respond.
You are receiving this because you enabled ma
By "multi-prcocess" I mean run the python script two times simutaniously, while
"multi-thread" is implemented by threading.Thread in python script.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/multithread-threadpool-performance-degradation-when-running-relay-module-in-multiple-thread
Yes, it also has the same problem running on omp as threading backend. We
didn't see much difference between TVM ThreadPool and OMP in such cases.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/multithread-threadpool-performance-degradation-when-running-relay-module-in-multiple-threads
Add an addtional info: in multi-processed run, the performace of module.run()
in each process does not drop.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/multithread-threadpool-performance-degradation-when-running-relay-module-in-multiple-threads/10374/5)
to respond.
You are receiv
Thanks. It doesn't improve. Performace in both single-threaded run and
multi-threaded run drop 10-20%, and CPU utilization drops from nearly 100% to
nearly 50% with TVM_THREAD_POOL_SPIN_COUNT=0, which I think is reasonable.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/multithread-th
* Device: Skylake 8163 with 48 pysical cores
* Env Setting: TVM_BIND_THREADS=0 TVM_NUM_THREADS=4
* Code Snippet:
```
module = graph_executor.GraphModule(lib["default"](ctx))
def thread_run:
for i in range(repeats):
module.run()
threads = []
for i in range(num_threads):
t
