MPI4Spark Changelog
----------------------
This file briefly describes the changes to the MPI4Spark software package. 
The logs are arranged in the "most recent first" order.

MPI4Spark v0.3 - (08/28/2024)

* New Features & Enhancements
      - Enhanced MPI Dynamic Process Management (DPM) logic for 
        launching executor processes for the standalone 
        cluster manager
      - Relies on the Multiple-Program-Multiple-Data (MPMD) launcher 
        mode for both YARN and the Standalone cluster managers
      - Supports MVAPICH versions 2.3.7 and 4.0
      - Tested with
        * OSU HiBD-Benchmarks, GroupBy and SortBy
        * Intel HiBench Suite, Micro Benchmarks, Machine Learning and
          Graph Workloads

MPI4Spark v0.2 - (08/25/2023)

* New Features & Enhancements
      - Support for the YARN Cluster Manager
      - Executor processes are launched using the Multiple-Program-
        Multiple-Data (MPMD) MPI launcher mode
      - Tested with
        * OSU HiBD-Benchmarks, GroupBy and SortBy
        * Intel HiBench Suite, Micro Benchmarks, Machine Learning and
          Graph Workloads

MPI4Spark v0.1 (11/11/2022)

* New Features & Enhancements
      - Based on Apache Spark 3.3.0
      - Compliant with user-level Apach Spark APIs and packages
      - High performance design that utilizes MPI-based communication
        * Utilizes MPI point-to-point operations
        * Relies on MPI Dynamic Process Management (DPM) features for
          launching executor processes
      - Built on top of the MVAPICH2-J Java bindings for MVAPICH2 family
        of MPI libraries
      - Tested with
        * OSU HiBD-Benchmarks, GroupBy and SortBy
        * Intel HiBench Suite, Micro Benchmarks, Machine Learning and
          Graph Workloads
        * Mellanox InfiniBand adapters (EDR and HDR 100G and 200G)
        * HPC systems with Omni-Path interconnects
        * Various multi-core platforms