README.md

Environment setup

Add path to libprotobuf.so and libnvdla_compiler.so in LD_LIBRARY_PATH

Compilation Command

Compilation script : miniera-hpvm/src/compile_benchmark.sh

Command:

python3 /home/hsharif3/Gitlab/hpvm_release_nvdla/hpvm/build/tools/hpvm/tools/hpvm-clang/main.py -t nvdla --conf-file data/tuner_confs.txt -DMODEL_PARAMS_DIR=${PATH_TO_MODELPARAMS} -fno-exceptions miniera-hpvm.cpp miniera-hpvm

NOTE: by default hpvm-clang is configured to read calibration inputs from a calib.txt file plaed in the current build directoy (see main.py.in in hpvm-clang). By default, INT8 mode is usedm for testing modify main.py in build directory to use FP16 mode (easily configurable)

Running on EPOCHS chip

The compilation creates an nvdla module named hpvm-mod.nvdla

Connect to EPOCHS chip:

ssh -q -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -p 5506 root@ espgate.cs.columbia.edu

Running on EPOCHS chip:

cd NV_NVDLA/

./nvdla_runtime  --loadable  hpvm-mod.nvdla --image  ${test_image}  --rawdump

Frontend/Source changes required

• Weights must be FP16!

• Weights for FC layers need to be tranposed

• Modify paths to readTrainedWeights to pass constant file path -- use MODEL_PARAMS_STR as part of string