Archived

This repository has been archived on 2023-11-05. You can view files and clone it, but cannot push or open issues or pull requests.

History

Wenyong Huang a3074df21b Import SIMD feature and add some workload samples (#438 )		2020-11-05 18:15:15 +08:00
..
build.sh	Import SIMD feature and add some workload samples (#438 )	2020-11-05 18:15:15 +08:00
README.md	Update build script to enable running tensorflow workload in linux-sgx (#435 )	2020-10-29 03:33:49 +00:00
tf_lite.patch	Import SIMD feature and add some workload samples (#438 )	2020-11-05 18:15:15 +08:00

"tensorflow" sample introduction

This sample demonstrates how to build tensorflow into WebAssembly with emcc toolchain and run it with iwasm. Please first install emsdk:

git clone https://github.com/emscripten-core/emsdk.git
cd emsdk
./emsdk install latest
./emsdk activate latest

And set up ensdk environment:

source emsdk_env.sh

Then run

./build.sh
# for linux platform, or
./build.sh --sgx
# for linux-sgx platform

to build tensorflow and run it with iwasm, which basically contains the following steps:

hack emcc to delete some objects in libc.a
build tf-lite with emcc compiler
build iwasm with pthread enable and include libiary under libc-emcc
run benchmark model with iwasm: --max-secs 300: means the max training time cost is 5 minutes, you can adjust by yourself