GitLab

* Adding System singleton to support multi-node (communication and topology)
* Adding multi-node parsing, rank and device wildcard expansion
* Adding multi-node topology, and various support functions
* Adding multi-node consistency validation of Config and Transfers
* Introducing SINGLE_KERNEL=1 to Makefile to speed up compilation during development
* Updating CHANGELOG.  Overhauling wildcard parsing.  Adding dryrun
* Client refactoring.  Introduction of tabular formatted results and a2a multi-rank preset
* Adding MPI support into CMakeFiles
* Cleaning up multi-node topology using TableHelper
* Reducing compile time by removing some kernel variants
* Updating documentation.  Adding nicrings preset
* Adding NIC_FILTER to allow NIC device filtering via regex
* Updating supported memory types
* Fixing P2P preset, and adding some extra memIndex utility functions

* Adding non-temporal loads and stores via GFX_TEMPORAL
* Adding additional summary details to a2a preset
* Add SHOW_MIN_ONLY for a2asweep preset
* Adding new P CPU memory type which is indexed by closest GPU

Adding NIC execution capabilities, various bug fixes introduced by header-only-library refactor
---------
Co-authored-by: Mustafa Abduljabbar <mustafa.abduljabbar@amd.com>

* Adding source prep kernel (USE_PREP_KERNEL)
* Adding nvcc-only compilation path
* Fix for NVIDIA - set shared mem usage to 0 by default
* Updating default fill pattern for source data
* Restoring missing example.cfg file

* add read the docs configs

* add examples to docs

format example docs

* formatting for configfile format doc page

* generate doxygen docs

* Adding MIMO support, DMA executor, Null memory type

* Updating version to v1.06
* Fixing CPU NUMA allocation
* Fix random sweep repeatability
* Adding unpinned CPU memory as possible memory type
* Adding ability to customize per-transfer byte sizes
* Updating advanced configuration file mode to take in numBytes per Transfer
* Adding logging of sweep tests configuration to lastSweep.cfg
* Add ability to specify #CUs for sweep benchmark