RAPID - Heterogeneous Secure Multi-level Remote Acceleration Service for Low-Power Integrated Systems and Devices





What user need or pain point is your project addressing?

RAPID targets a novel heterogeneous CPU-GPU multi-level cloud acceleration focusing on applications running on embedded systems found on low-power devices such as smartphones, notebooks, tablets, wearable devices (smart watches, glasses), robots, cars, etc. Many such low-power devices can't always cope with the increased demand for processing power, memory and storage required by several applications in entertainment, vision, security, robotics, and aerospace such as gaming, antivirus, augmented reality, face and speech recognition, movement detection, biometrics, and CCTV. These applications require tremendous performance and cannot run on most existing battery operated devices. As a result, most such applications are only executed on high-end servers.


Project's major results: 
RAPID targets a novel heterogeneous CPU-GPU multi-level Cloud acceleration focusing on applications running on embedded systems of low-power devices. The project takes advantage of abundant mobile computation power and ubiquitous high-speed networks to provide a distributed heterogeneous acceleration infrastructure that can change the future of mobile applications. RAPID developments can be summarized as follows:
- A secure unified model where almost any device or infrastructure can operate as an accelerated entity and/or as an accelerator.
- A registration mechanism which permits the accelerated entity to automatically find and connect the nearby accelerators.

Target stakeholders: 

Small & medium enterprises, Open Source developers, Large companies, Technology providers, Research institutions.



Project Start: 
01/01/2015
Project End: 
31/12/2017


How will your solution/service benefit the end-user?

RAPID will allow the end-user to run applications that require tremendous processing power, memory and storage on low-power devices. Wearable devices and smartphones will benefit from RAPID by being able to execute more efficiently several applications such as speech recognition, augmented reality, navigation, video editing, as well as gaming. Moreover, power-operated robotic devices can use RAPID to run applications in a wide variety of fields such as medicine and surgery, personal assistance, security, warehouse and distribution applications, aerospace, defence, and ocean and space exploration.

Finally laptops, notebooks and desktops can also take advantage of cloud resources through RAPID by running even more demanding applications such as 3D video and image processing, advanced design, simulation and analysis tools used by engineers, and High Performance Computing.


Potential exploitation strategy: 
RAPID will create new innovation opportunities to service providers by introducing the concept of Acceleration as a Service. RAPID opens the door of GPU- based computation in the Cloud. Within the RAPID project, the first Public Acceleration Cloud service will become available and commercially exploitable. Through the implementation of three use cases (hand tracking, bio surveillance and antivirus), RAPID will demonstrate its effectiveness in different sectors aiming to cover a wide range of potential stakeholders that can benefit from project results. RAPID platform will be offered as a service on a pay-per-use basis or under a subscription fee, depending on the user profile (accelerator or accelerated entity).

Vertical Market: 

Smart cities, Media, Other.