Here is a PR doing what you want: https://github.com/apache/tvm/pull/9553
(though it takes an IRModule instead of a PackedFunc).
---
[Visit
Topic](https://discuss.tvm.apache.org/t/papi-counters-with-basic-matmul-relay-function/11263/8)
to respond.
You are receiving this because you enabl
This is exactly what I needed, thanks!
I'm now able to extract the PAPI counters from standalone functions by running
the function exported as an `.so` library in C++, with the above PAPI code!
I'll use this method to get the data I need.
Now, looking forward, I'm thinking how best to expos
You need to manually construct `DeviceWrapper` inside the initializer list.
```
tvm::Map>
metrics({
{tvm::runtime::profiling::DeviceWrapper({kDLCPU, 0}), {"perf::Cycles"}}
});
```
---
[Visit
Topic](https://discuss.tvm.apache.org/t/papi-counters-with-basic-matmul-relay-function/
Many thanks `tkonolige`, I think this is a good excuse for me to learn more
about the internals of the TVM runtime and profiling.
I've started with making a simple C++ deployment of the `matmul_add`, with the
goal of using it to implement Option 1.
I am following the basic structure of `apps/
