Home
Overview and Installation
Getting started with MemVerge Memory Machine requries that you understand some background information about how persistent memory works. You can then install Memory Machine on a server and begin monitoring memory usage and capturing application snapshots.
Getting Started with Memory Machine
You run Memory Machine on a host equipped with one or more PMEM devices.
Software Recommendations
MemVerge recommends that you conform to software dependencies, such as operating systems and packages, that have been tested with MemVerge products.
Supported Applications

Overview and Installation
Getting started with MemVerge Memory Machine requries that you understand some background information about how persistent memory works. You can then install Memory Machine on a server and begin monitoring memory usage and capturing application snapshots.
- Introduction to MemVerge Memory Machine
  MemVerge Memory Machine (Memory Machine) enables applications to expand from volatile memory (DRAM) into persistent memory (PMEM).
- Getting Started with Memory Machine
  You run Memory Machine on a host equipped with one or more PMEM devices.
  - Hardware Recommendations
  - Network Recommendations
    For optimal performance and consistency throughout the Memory Machine System, MemVerge either requires or recommends specific values for open port numbers, communication protocols, and other network-related configurations.
  - Software Recommendations
    MemVerge recommends that you conform to software dependencies, such as operating systems and packages, that have been tested with MemVerge products.
  - Installing MemVerge Memory Machine
    Install MemVerge Memory Machine (Memory Machine) data service on all hosts requiring memory management.
  - Configuration Files
    MemVerge Memory Machine uses several YAML-formatted configuration files. Two of these, mvmallocd.yml and mvmalloc.yml contain user-configurable parameters.
Using the Memory Machine Dashboard
You can view system resources and performance metrics, and create and restore snapshots in MemVerge Memory Machine using the Memory Machine Dashboard, a web UI application running on one of the installed hosts.
Using the Command Line Interface
You can administer and use MemVerge Memory Machine using the Command Line Interface (CLI) on any installed host.
Working with Applications
MemVerge provides additional instructions for some popular applications supported by Memory Machine, either to assist with complex setup or to support additional functionality.

Supported Applications

A wide variety of applications can be run under Memory Machine's memory mangement.

The following table lists applications that have been tested with Memory Machine.

Software	Description	Links	Supported Functionality
Aerospike 5.2.0.4	NoSQL data platform	https://www.aerospike.com/	Memory management
ExtremeDB 8.2	In-memory database	https://sourceforge.net/software/product/ExtremeDB/	Memory management
Apache Flink 1.10.2	Stream-based distributed processing engine	https://flink.apache.org/	Memory management
TensorFlow 1.15.2, incl. GraphSage	ML library with inductive representation framework	http://snap.stanford.edu/graphsage/, https://www.tensorflow.org/	Memory management
Hazelcast 4.0.3	In-memory data grid	https://hazelcast.org	Memory management, snapshot
kdb+ Release 3.6 2019.08.20	Database	https://kx.com/	Memory management, snapshot
Memcached 1.6.6	Distributed memory caching system	https://aws.amazon.com/memcached/	Memory management, snapshot
Pytorch 1.5.1 BERT	NLP transformer trainer	https://github.com/codertimo/BERT-pytorch	Memory management
Pytorch 1.5.1 OpenNMT	NMT framework	https://github.com/OpenNMT/OpenNMT-py	Memory management
Redis 5.07, 5.08	Key-value database	https://redis.io/	Memory management, snapshot
RocksDB 5.18.3	Key-value database	https://rocksdb.org/	Memory management
Apache Spark 2.4.5	Analytics engine	https://spark.apache.org/	Memory management
Xgboost 1.1.0	Gradient boosting framework	https://github.com/dmlc/xgboost	Memory management, snapshot