Frequently Asked Questions
Q1. Is Python3.6 a strict requirement for installation?
Yes, our HPVM python packages require python version = 3.6. If you don't have a Python3.6 on your system, we encourage using the provided env.yaml conda environment.
Q2. What to do when running into out of memory errors?
Users can configure the batch size through Keras/PyTorch frontends. Users are encouraged to reduce batch size when encountering out of memory errors.
Q3. Should I expect speedups with approximations on my hardware system?
The approximation implementations in HPVM are currently optimized for the Nvidia Tegra Tx2 edge device. The routines are not expected to provide speedups across other hardware devices - though systems with similar hardware specifications may exhibit similar performance. We are working on providing speedups across a wider range of devices.
Q4. How many autotuning iterations should I use with `predtuner` package in HPVM?
The number of tuning iterations required to achieve good results varies across benchmarks. Users must tune this on a per-benchmark basis. For the included 10 CNNs, we recommmend using atleast 10K iterations.
Q5. How can I extend HPVM to include new custom approximations?
Users can update the hpvm-tensor-rt in HPVM to include new custom approximations that are targeted by the compiler.
Alternatively developers can update the HPVM backends to compile to external libraries with support for custom approximations. The HPVM backends are documented in detail in [TODO : Add link to Backends Doc]
The predtuner in HPVM is flexible to include more approximation knobs. [TODO: Yifan should add more details on how to add more knobs]
Q6. Does this release support combining HPVM tensor and non-tensor operations in a single program?
Currently we do not support tensor and non-tensor code in the same application. We will support this feature in the next release.
Q7. Does this release support object detection models?
Currrently, HPVM doesn't support object detection models. Support will be added in future releases.