Welcome to our Support Center
< All Topics
Print

Installation: Studio application hardware and software requirements

All you need to know about hardware and software sizing for on-premises and cloud deployment.

Machine learning is an intense CPU process and can occupy 100% of the CPU while performing training of algorithms. Therefore, the right hardware configuration is the key and should be aligned with the dataset size to be processed on a single machine as this will affect the duration and length of the algorithm training.

Operating system requirements:
* Windows 8 and 10 are supported, older operating systems are not supported (and may not work).

* Only amd64 (x64) binaries are provided for Windows.* ARM version of Windows is not supported for now.

* Minimum of 16GB memory is required (data sources are fully loaded into memory therefore more memory may be required).
iERP.ai Studio requirements
* Any Intel CPU produced after 2011 with AVX instruction set.
* Any AMD CPU produced after 2011 with AVX instruction set.
iERP.ai Studio requirements (when using GPU – not possible yet)
* NVIDIA® GPU card with CUDA® Compute Capability 3.5 or higher.
* NVIDIA® GPU drivers —CUDA 10.0 requires 410.x or higher.
* CUDA® Toolkit —TensorFlow supports CUDA 10.0 (TensorFlow >= 1.13.0)
* CUPTI ships with the CUDA Toolkit.
* cuDNN SDK (>= 7.4.1)
Other requirements
* Internet access to validate license on weekly basis. iERP Studio can work offline for the period of 7 days but then the license needs to be again validated .
Operating system requirements:

* Minimum OS X version supported is OS X 10.9 or higher. Tested are last 2 major version.
* Only amd64 (x64) binaries are provided for OS X.

* HTTP/HTTPS access to

iERP.ai Studio requirements
* Any Intel CPU produced after 2011 with AVX instruction set
* Any AMD CPU produced after 2011 with AVX instruction set
iERP.ai Studio requirements (when using GPU – not possible yet)
* NVIDIA® GPU card with CUDA® Compute Capability 3.5 or higher.
* NVIDIA® GPU drivers —CUDA 10.0 requires 410.x or higher.
* CUDA® Toolkit —TensorFlow supports CUDA 10.0 (TensorFlow >= 1.13.0)
* CUPTI ships with the CUDA Toolkit.
* cuDNN SDK (>= 7.4.1)
Other requirements
* Internet access to validate license on weekly basis. iERP Studio can work offline for the period of 7 days but then the license needs to be again validated.
Operating system requirements:

* Only amd64 (x64) binaries are provided for Linux.

* Built and tested on the latest Ubuntu LTS.

* Should work on the latest version of Debian, Ubuntu and similar distributions with the correct packages.

* HTTP/HTTPS access to

iERP.ai Studio requirements
* Any Intel CPU produced after 2011 with AVX instruction set
* Any AMD CPU produced after 2011 with AVX instruction set
iERP.ai Studio requirements (when using GPU – not possible yet)
* NVIDIA® GPU card with CUDA® Compute Capability 3.5 or higher.
* NVIDIA® GPU drivers —CUDA 10.0 requires 410.x or higher.
* CUDA® Toolkit —TensorFlow supports CUDA 10.0 (TensorFlow >= 1.13.0)
* CUPTI ships with the CUDA Toolkit.
* cuDNN SDK (>= 7.4.1)
Other requirements
* Internet access to validate license on weekly basis. iERP Studio can work offline for the period of 7 days but then the license needs to be again validated.

Cloud deployment:
* No system requirements for Cloud deployment
* iERP will provide you with a dedicated Windows Virtual Machine (VM) with preinstalled iERP Studio platform.
First steps
  1. Download and run the installer for the selected platform (https://releases.ierp.ai/?list=)
  2. Select machine-wide or single-user installation

  1. Follow the installer steps and continue

Multiusers License activation (Windows Only)
  1. Install the studio for machine-wide or all users
  2. Start the studio

  1. Enter the license key and activation token, and validate license works correctly

 

  1. Share license with all users
    1. Copy this folder (C:\Users\username\AppData\Roaming\ai.ierp.studio\activation) and its contents
    2. Paste into C:\Users\Public\Roaming\ai.ierp.studio\activation if the folder doesn’t exist create it
  2. Restart studio
Offline license install
  1. Retrieve machine fingerprint using the CLI Steps how to get finger print
  2. Send to the iERP team the machine fingerprint. Example:
    Machine fingerprint: 6b0b458b54c2c8647cc21111111111b471fe60b6666669eecd9dbfd93d012768Machine name: Mac 20.3.0Machine platform: darwin
  3. iERP team will send a .json file, copy it to the folder C:\Users\username\AppData\Roaming\ai.ierp.studio\activation
Previous Introduction: iERP.ai Studio application basics
Next Installation: How to install on-premise iERP studio
Table of Contents