Pablo Marquez Tello

Hi @ilya-lavrenov Yes, I'll look into the scons files because we have not tested cross-compilation on macos. > The compiler on OSX 11 and higher supports both arm64 and x86_64...

Hi @ilya-lavrenov My understanding is that you have two toolchains on that host: - x86-64 native - arm64 cross-compiler CMake environment won't affect ACL's scons build. You have to manually...

Hi @Afef00 Have you managed to cross-compile ArmNN? Are you looking into doing inference on the Gpu or Cpu? Can you confirm if your board has a CortexA9? https://developer.arm.com/Processors/Cortex-A9 ....

Hi @GW-Renesas Would you please let us know what target arch you are building for? FP16 is enabled when building for armv8.2a. If you build for v8a there is not...

Hi @GW-Renesas I have not managed to reproduce this with a new build from `main`. I built ACL both for v8a and v8.2a and the test passes. Can you please...

Closing this due to inactivity, reopen if you still experience problems.

Hi @matt-gretton-dann This should not be a problem as we guard against 0 in https://github.com/ARM-software/ComputeLibrary/blob/main/src/runtime/CPP/CPPScheduler.cpp#L473 The scheduler won't run the workload when num_threads < 1 ``` 465 void CPPScheduler::run_workloads(std::vector &workloads)...

Hi @snadampal Thanks for raising this. We will discuss the feature request with the team.

Hi @snadampal We discussed this with the team, we are considering exploring sparse tensors support in the context of GenAI but this is not officially in the roadmap for ACL....

Hi @snadampal Apologies if I was not clear. we're exploring ways to accelerate GenAI workloads with ACL. This means that we may consider exploring sparse tensors support in ACL to...