Enabling the 3rd Wave of Computing in the Data Center

Megh Computing delivers an efficient, scalable platform for Real Time Analytics using FPGA accelerators for deployment in the public and private cloud.

Let us show you how to catch the 3rd wave.

The Third Wave​

1
CPUs

The first wave started with the roll-out of cloud computing using general purpose CPUs enabled by the rise of hyper-scale cloud service providers.

2
GPUs

The second wave of computing has been driven by GPUs for the computing needs of Deep Learning training in the data center.

3
FPGAs

The third wave is led by FPGAs (Field Programmable Gate Arrays) to meet the growing need for scale out accelerators for real time streaming analytics with Machine Learning/Deep Learning algorithms.

Why FPGA Acceleration

FPGAs provide a reconfigurable sea of hardware gates on which one can:

  • Design a custom hardware accelerator with direct I/O connectivity and low latency
  • Deploy it for a single application to deliver increased performance efficiencies
  • Quickly reconfigure the device as a new accelerator for a different application

Megh Computing is driving the 3rd wave in the Data Center with our FPGA accelerated platform.

Basic FPGA components

Our Solution

Our solution is based on a heterogeneous CPU+FPGA platform for Real Time Stream Processing of Big Data Analytics:

  • Introduces inline processing of various streams including filtering and transformations of data
  • Supports offload processing of ML/DL (Machine Learning / Deep Learning) and other compute intensive functions
  • Abstracts the FPGA by providing Accelerator-as-a-Service via high level APIs
FPGA accelerators coupled with CPUs

Targeted Applications

Retail

  • Operational analytics for better efficiencies to reduce cost
  • Personalizing in-store experience with targeted promotions
  • Customer behavior analytics for higher retention

Finance

  • Low latency processing of market data for faster response by trading platforms
  • Analytics of trading data for fraud detection, compliance and regulatory requirements, risk management and others

Networking

  • Low latency processing of network probe and other signals for telecom service assurance
  • Deep Packet Inspection of network traffic for security operations centers

Key Benefits

Performance Efficiency

Lowers the Total Cost of Operation by more than 2x resulting in significant cost savings for customers.

Time to Value

Supports deployment of new Real Time Analytics use cases with low latency using high volume hardware platform with open source software frameworks and SDK for library development.

Ease of Deployment

Deploy FPGA Accelerator-as-a-Service using Containers or VMs in Public or Private or Edge Cloud.

Request a demo
Find out how to accelerate your Real Time Analytics workloads with Spark Streaming framework and BigDL libraries in the Cloud using FPGA accelerators

Partners

Investors