Policy for addition and maintenance of compute nodes to the central parallel computer
This document describes the CIS Division policy, formulated according to Technion management guidelines, and the interaction between the general cluster installed at the Technion, that was acquired with the joint funding by the Technion, the Cyber center, the Quantum center and the Energy department, and new nodes, purchased by academic staff members from their research budgets.
Central resources usage
A researcher who joins the cluster by purchasing private compute nodes according to the configurations approved by CIS, will benefit from the following options (some of which are subject to the costs listed below):
- Using the Master Node of the existing cluster
- All central software resources and licensing
- Physical hosting of the aquired nodes at the server farm including:
- Location in the racks
- Dual power supply
- Dedicated air conditioning system
- Central UPS system
- Management services, system administration, installing software and upgrades
- Every research group gets a 500GB storage allocation in the central system 
- Information security services
- Communication services
- Monitoring and control services
Independence of the researcher
1. The calculation tasks marked as belonging to the researcher’s research group will have absolute priority while running on the researcher’s private nodes. The researcher will be given the ability and privilege to set policy priorities between the computational tasks of his research group, subject to the cluster queue management capabilities. Queue management software itself will be selected and installed by the CIS Division.
2. The researcher will be allowed to install dedicated software on the computational nodes he acquired. Each software purchase will be coordinated with the CIS Division prior to making the purchase, to ensure that it is possible and installable.
The principle of cooperation and reciprocity
2. Private nodes which are not utilized will be provided for usage by other users of the cluster.
1. The HPC system is a complex system that is maintained by many factors and requires the purchase of equipment and services.
2. In accordance with the decision of the Steering Committee for ICT on 6/1/2020, purchase and service costs will be covered according to the following policy:
3. At the time of purchase, the researcher will pay 30% of the purchase order value for the hardware, to a dedicated fund managed by the CIS Division to fund maintenance costs, expansion (communications, cabinets, cabling, UPS, electrical work, air conditioning, etc.), hosting, future upgrades, and related expenses except as noted below.
4. The payment is considered to be the participation of the aforementioned researcher for the first 5 years. The Steering Committee will later discuss private server costs beyond the first 5 years.
1. If software is not free and/or not Technion licensed at all, the researcher will bear the costs of purchasing dedicated software for it. Do not install software without proper licensing.
2. All administrative procedures pertaining to the budget billing will be conducted between the CIS Division and the head of the administration of the faculty to which the researcher belongs.
 Beyond the use of local storage in accordance with Section 3 sub-section F under “Central resources usage”, any additional usage of the central storage and backup systems will be charged fees according to the pricelist issued by the CIS Division