here is a guide for you to run the current version of vta(i’ve successed the GEMM test and rpc test this way on pynq)
- do a brand new recursive git clone of tvm on board
- for pynq follow https://tvm.apache.org/docs/vta/install.html to the cmake … step
- perform a full build of tvm by typing make -j2 instead of make runtime vta -j2 because ir.RegisterOpLowerIntrinsic seems not built for runtime.this step takes roughly about 4 hrs
- copy the lib*.so(3 lib files) in /build to your host computer because we need these file after
- go back to the /build on pynq and delete the lib*.so
- make runtime vta -j2 on pynq
- paste the libtvm.so you’ve just backed up back to the /build on pynq.this lib should be enough, but check for the file size. you can back up these library files to prevent building all of these again
- edit the vta/python/vta/exec.py and python/tvm/rpc/init.py on pynq Test_benchmark_topi_conv2d.py failure caused by AttributeError: Module has no function ‘tvm.contrib.vta.init’
- start the server and perform the test on host PC if you have the cloudpickle issue see Problem - RPC server on ZCU104