fling logo of Supernova - Accelerating Machine Learning Inference

Supernova - Accelerating Machine Learning Inference

version 1.2 — December 17, 2020

Contributors 6

View All

Summary

With machine learning is widely used in enterprises, big data are trained on the edge, inference services go to production either in the cloud or on the edge.

On the edge

  • Edge devices have limited resources, space and power supply
  • Edge servers cost much higher than devices
  • Hardware accelerators are heterogeneous in architecture and various on interfaces and performance on the edge

In the cloud

  • Accelerator market is dominated by Nvidia GPU
  • Other options come as AMD GPU, Intel Habana Goya/Altera FPGA, AWS Inferentia, Xilinx FPGA etc
  • Common inference interfaces from cloud to edge doesn’t appear generally
  • Limitation on specific hardware accelerators or cloud leads to new vendor lock-in

Project Supernova is to build a common machine learning inference service framework by enabling machine learning inference accelerators across edge endpoint devices, edge systems and cloud, with or without hardware accelerators.

  • Micro-service based architecture with Restful API
  • Support heterogenous system architectures from leading vendors
  • Support accelerator compilers to native code
  • Neutral to ML training framework file formats
  • Work on both edge devices and clouds
  • Support Xilinx Cloud FPGA
  • Hardware CPU support:
    • x86-64, ARM64
  • Hardware accelerator support:
    • Intel VPU, Google Edge TPU, Nvidia GPU, AMD GPU
  • Software
    • Inference toolkit support: OpenVINO, TensorRT & Tenserflow Lite
    • Training framework data format: Tensorflow, Caffe, ONNX, MxNet

Requirements

The common computing platforms including most resource-constrained edge system, PC, server, etc, where can deploy Linux/Docker.

Instructions

Instructions are included in the download directory as "Supernova Quickstart Guide.docx"

Changelog

Version 1.2 Update 

  • Support Xilinx Cloud FPGA

Version 1.1 Update

  • Support Bitfusion
  • K8S and docker-compose deployment

Version 1.0 Update 

Compared 0.0.1, this release supports:

  1. New HW accelerators - AMD GPU + Xilinx FPGA
  2. CPU Accelerations with OpenVINO
  3. Basic K8S deployment
  4. Versatile APIs
  5. vSphere Bitfusion support
  6. More use cases like facial mask
 
It's version 2 compared to Fling version 1, https://flings.vmware.com/supernova-accelerating-machine-learning-inference,
  1. New HW accelerators - AMD GPU + Xilinx FPGA
  2. CPU Accelerations with OpenVINO ased on AVX/SSE
  3. Basic K8S deployment
  4. Versatile API set
  5. More use cases like facial mask
  6. vSphere Bitfusion support

Please add the following two lines for our release:

Similar Flings

No similar flings found. Check these out instead...
Jun 11, 2020
fling logo of True SSO Configuration Utility

True SSO Configuration Utility

version 1.0

This project is intended for the VMware Horizon customers in order to use True SSO Configuration Utility to help you configuring TrueSSO using View Connection Server, Enrollment Server and your Certificate Authoriry / Active Directory.

Dec 07, 2018
fling logo of PowerCLI Extensions

PowerCLI Extensions

version 3.0.0.11173018

With the many existing cmdlets designed for the system administrator or vSphere Admin, PowerCLI is the easiest and most powerful tool for managing your environment.

Dec 11, 2013
fling logo of Real-Time Audio-Video Test Application

Real-Time Audio-Video Test Application

version 1.0

This application verifies the correct installation and operation of the View Horizon Real-Time Audio-Video functionality.

Apr 15, 2019
fling logo of Identity Manager Migration/Backup Tool

Identity Manager Migration/Backup Tool

version 1.6

Identity Manager Migration/Backup Tool automates the process of exporting or importing applications and entitlements from one Identity Manager instance to another.

Jan 22, 2020
fling logo of Cross vCenter Workload Migration Utility

Cross vCenter Workload Migration Utility

version 3.1

This Fling allows users to easily migrate virtual machines in bulk from a graphical user interface between vCenter Servers (same & different SSO Domains supported) using the Cross-vCenter vMotion feature.

Oct 17, 2011
fling logo of CIM Plugin

CIM Plugin

version 1.0.0

The plugin is general enough to support other CIM compliant services and is not limited only to ESX. However the primary goal for developing the plugin was to expose ESX CIMOM in the vCenter Orchestrator. This affected the API design.

View More