Pramod Kumbhar

### Overview of the issue This ticket is to document / investigate the issues to build NEURON on Piz-Daint with GPU support via CoreNEURON. ### Expected result/behavior We should be...

Avoid stdout/stderr clutter from nrnivmodl and nrnivmodl-core

1

## Overview of the feature This is follow-up from the discussion in https://github.com/neuronsimulator/nrn/pull/1661#discussion_r822042348. Currently when we do `nrnivmodl` or `nrnivmodl-core`, we end-up with unnecessary messages that clutter stdout/stderr. For example,...

Support for shared libraries in GPU execution (python launch support)

42

**Description** **Summary** * mod2c now generates code without need of global variables * coreneuron and mechanism library can be built as shared and it enables launching coreneuron on GPU via...

Respect CMAKE_EXE_LINKER_FLAGS/CMAKE_SHARED_LINKER_FLAGS flags set via CLI

2

**Description** In the case of Clang, we were always overriding the above-mentioned flags and hence cmake args were ignored (resulting in link errors) **How to test this?** On BB5 with...

Fixes for building with LLVM / XL OpenMP offload

11

Various changes (including temporary) to make XL OpenMP offload build working * todo: need to rebase this branch on latest hackathon_master * todo: temporary changes to OpenAccHelper.cmake, needs refinement *...

**Describe the issue** If we install OpenMP runtime via `brew` and try to build CoreNEURON with AppleClang then building as well as running tests fail. **To Reproduce** ```bash brew install...

Support for SHARED build with PGI OpenACC build

7

If we build shared library with OpenACC, we are getting: ``` cuda_init_device(threadid=1, device 0) dindex=1, api_context=0x95d090 pgi_uacc_cuda_static hostptr=0x2aaaabedc990-0x2aaaabedc998 size=8 name=_ZN10coreneuron14_slist1_ExpSynE flags=0x100 Failing in Thread:1 call to cuModuleGetGlobal returned error 500:...

Issue with OpenMP enabled python binary wheels

1

**Describe the issue** Like OpenACC/CUDA, ABI compatibility of OpenMP and shipping duplicate OpenMP runtime library is problematic. **To Reproduce** * Build the wheel on manylinux2014_aarch64 * Try to use the...

Improvements for GPU binary wheels

2

This is a placeholder ticket to gather possible improvements for binary wheel: - [ ] As [noted here](https://github.com/BlueBrain/CoreNeuron/pull/634#discussion_r732885338), see if `CMAKE_EXE_LINKER_FLAGS` pollution could be avoided or worth doing. - [...

**Describe the issue** When dynamic MPI support is enabled, we build lincorenrnmpi_.so library. If this library is built with OpenACC flags (e.g. `-acc`) then program crashes at the exit handler:...