vladl-innopeaktech

Results 11 comments of vladl-innopeaktech

I believe I've run into this as well, using the resize example and Adams2019 autoscheduler. Unhandled exception: Error: Can only unroll for loops over a constant extent. Loop over kernel_y.s0.k...

@aankit-ca I've added comments to the code, is this what you had in mind?

@alexreinking @aankit-ca Updated according to requests

That sounds good. The flag would need to be applied at the build configuration level, right? Where could I look for an example of this runtime module design?

@alexreinking I have put the build behind a feature flag (I think) and am building the DSP library based on whether or not the Hexagon SDK environment is present. I...

@alexreinking I've made an attempt at enabling the instrumentation without the user having to include. I wound up moving the header into `src` as I needed visibility there, although if...

@alexreinking It's definitely not ready to merge yet, I just need a few pointers on how to proceed. Once I've got everything in place and then test it, we could...

Just FYI, I am getting multiple build failures from the latest commit, using the commands: $ cmake -G Ninja -DCMAKE_BUILD_TYPE=Release -S . -B build -DTARGET_WEBASSEMBLY=OFF $ cmake --build build -j17...

Using this patch https://gist.github.com/vladl-innopeaktech/37e5fc044479ca7186911dc140d71479 I am able to whittle down the errors to just some linker failure here: ``` [1/23] Linking CXX executable src/autoschedulers/anderson2021/anderson2021-test_apps_autoscheduler FAILED: src/autoschedulers/anderson2021/anderson2021-test_apps_autoscheduler : && /usr/bin/c++ -O3...

@aekul It looks like the autotuning script and the `retrain_cost_model` binary are out-of-sync. I've tried to bridge the gap with the arguments but it looks like `retrain_cost_model` just gets stuck...