Find file History
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

TVM in Intel SGX Example

This application demonstrates the use of a simple TVM model in the Intel SGX trusted computing environment.


  1. The TVM premade Docker image


  1. A GNU/Linux environment
  2. TVM compiled with LLVM and SGX; and the tvm Python module
  3. The Linux SGX SDK link to pre-built libraries
  4. Rust
  5. The rust-sgx-sdk
  6. xargo

Check out the /tvm/install/ for the commands to get these dependencies.

Running the example

If using Docker, start by running

git clone --recursive
docker run --rm -it -v $(pwd)/tvm:/mnt tvmai/ci-cpu /bin/bash

then, in the container

cd /mnt
mkdir build && cd build
cmake .. -DUSE_LLVM=ON -DUSE_SGX=/opt/sgxsdk -DRUST_SGX_SDK=/opt/rust-sgx-sdk
make -j4
cd ..
pip install -e python -e topi/python -e nnvm/python
cd apps/sgx

Once TVM is build and installed, just


If everything goes well, you should see a lot of build messages and below them the text It works!.

High-level overview

First of all, it helps to think of an SGX enclave as a library that can be called to perform trusted computation. In this library, one can use other libraries like TVM.

Building this example performs the following steps:

  1. Creates a simple TVM module that computes x + 1 and save it as a system library.
  2. Builds a TVM runtime that links the module and allows running it using the TVM Python runtime.
  3. Packages the bundle into an SGX enclave
  4. Runs the enclave using the usual TVM Python module API

For more information on building, please refer to the Makefile.
For more information on the TVM module, please refer to ../howto_deploy.
For more in formation on SGX enclaves, please refer to the SGX Enclave Demo