Executing generated LLVM code without TVM runtime

srp1970 · October 29, 2018, 10:45am

Hello
I am new to TVM usage. I am trying to generate the LLVM code from TVM and wanted to understand who we can compile LLVM to executable and run it without TVM runtime. But, first step is to able to compile and run the generated LLVM code. Can someone give me steps on how we could do this?

I was able to generate the LLVM code but unable to compile that to an executable.

Thanks for any help.

regards
Prakash

grwlf · October 29, 2018, 1:02pm

Hi. Consider visiting

tvm0.cpp defines a program which output LLVM assembly to its stdout. See build.sh for details.

srkreddy1238 · October 30, 2018, 11:33am

Could refer to

github.com

dmlc/tvm/blob/master/docs/deploy/nnvm.md#deploy-as-system-module

# Deploy NNVM Modules
NNVM compiled modules are fully embedded in TVM runtime as long as ```GRAPH_RUNTIME``` option
is enabled in tvm runtime.


In a nutshell, we will need three items to deploy a compiled module.
Checkout our tutorials on getting started with NNVM compiler for more details.

- The graph json data which contains the execution graph.
- The tvm module library of compiled functions.
- The parameter blobs for stored parameters.

We can then use TVM's runtime API to deploy the compiled module.
Here is an example in python.

```python
import tvm

# tvm module for compiled functions.
loaded_lib = tvm.module.load("deploy.so")

This file has been truncated. show original

to deploy as system module.