You can not select more than 25 topics
Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
Varec-CC
Deep Learning Accelerator Stack
Introduction
- varecc/ includes varec compiler, runtime driver source files.
- examples/ includes some end-to-end examples
- models/ includes pre-built YOLO models
- hardware/ includes pre-built hardware bitstreams
- patch/ includes some patches of tvm.
Installation
- Check TVM for dependencies.
- Run make to clone tvm and build.
- Set environment variables in setup.sh and run source setup.sh.
Examples
Simulation
- Set “TARGET” to “sim” in “varecc/config/varec_config.json”
- Remake libvarec.so by “cd tvm/build && make varec”
- In examples directory, run “python3 yolo.py”
On-board (Pynq images)
- Copy varecc/ and tvm/(without build/) to Pynq (/home/xilinx/)
- (On Pynq)Set “TARGET” to “pynq” in “varecc/config/varec_config.json”
- Add varecc/VAREC.cmake into tvm/CMakeLists.txt
- In tvm directory, “mkdir build && cp cmake/config.cmake build/ && cd build && make runtime varec”
- Change to varecc directory, run “sudo ./scripts/start_rpc.sh” to start RPC
- (On the host)Set “TARGET” to “pynq” in “varecc/config/varec_config.json”
- In examples directory, run “python3 yolo.py”
Python
C++
C
CMake
INI
other