Documentation Update for NCCL

Makefile

@@ -2,7 +2,7 @@ PIP := $(shell command -v pip3 2> /dev/null || command which pip 2> /dev/null)
 PYTHON := $(shell command -v python3 2> /dev/null || command which python 2> /dev/null)
 NUM_PROCESSES = 3
 
-.PHONY: install dev-install install_conda dev-install_conda tests doc docupdate run_examples run_tutorials
+.PHONY: install dev-install install_conda dev-install_conda tests tests_nccl doc docupdate run_examples run_tutorials
 
 pipcheck:
 ifndef PIP
@@ -30,12 +30,19 @@ install_conda:
 dev-install_conda:
 	conda env create -f environment-dev.yml && conda activate pylops_mpi && pip install -e .
 
+dev-install_conda_nccl:
+	conda env create -f environment-dev.yml && conda activate pylops_mpi && conda install -c conda-forge cupy cudnn cutensor nccl && pip install -e .
+
 lint:
 	flake8 pylops_mpi/ tests/ examples/ tutorials/
 
 tests:
 	mpiexec -n $(NUM_PROCESSES) pytest tests/ --with-mpi
 
+# assuming NUM_PROCESSES <= number of gpus available
+tests_nccl:	
+	mpiexec -n $(NUM_PROCESSES) pytest tests_nccl/ --with-mpi
+
 doc:
 	cd docs  && rm -rf source/api/generated && rm -rf source/gallery &&\
 	rm -rf source/tutorials && rm -rf build &&\

docs/source/installation.rst

@@ -100,6 +100,16 @@ If you prefer a ``pip`` installation, we provide the following command
 Note that, differently from the  ``conda`` command, the above **will not** create a virtual environment.
 Make sure you create and activate your environment previously.
 
+Enable Nvidia Collective Communication Library (NCCL)
+=======================================================
+To obtain highly-optimized performance on GPU clusters, PyLops-MPI also supports the Nvidia's collective communication calls (NCCL).
+`NCCL <https://developer.nvidia.com/nccl>
+
+.. code-block:: bash
+
+   >> make dev-install_conda_nc
+
+
 Run tests
 =========
 To ensure that everything has been setup correctly, run tests:
@@ -110,6 +120,12 @@ To ensure that everything has been setup correctly, run tests:
 
 Make sure no tests fail, this guarantees that the installation has been successful.
 
+If PyLops-MPI is installed with NCCL, also run tests:
+
+.. code-block:: bash
+
+   >> make tests_nccl
+
 Run examples and tutorials
 ==========================
 Since the sphinx-gallery creates examples/tutorials using only a single process, it is highly recommended to test the

setup.cfg

@@ -1,9 +1,9 @@
 [tool:pytest]
 addopts = --verbose
-python_files = tests/*.py
+python_files = tests/*.py tests_nccl/*.py
 
 [flake8]
 ignore = E203, E501, W503, E402
 per-file-ignores =
-    __init__.py: F401, F403, F405
-max-line-length = 88
+__init__.py: F401, F403, F405
+max-line-length = 88