Massively parallel accelerator processors, primarily graphics processing units (GPUs), have become widely available to end-users. Accelerators offer tremendous compute power at a low cost, and tasks such as media processing, medical imaging and eye-tracking can be accelerated to beat CPU performance by orders of magnitude, both in energy efficiency and execution speed. Despite these advantages, accelerators present a serious challenge for software development. Designing software for the diverse and growing range of platforms on the market is not feasible without better programming languages and tool support.
The aim of CARP is to design techniques and tools for correct and efficient accelerator programming:
- Novel and attractive methods for constructing system-independent accelerator programs.
- Advanced code generation techniques to produce highly optimised system-specific code from system-independent programs.
- Scalable static techniques for analysing accelerator software both qualitatively and quantitatively.
These methods will provide a unified development flow for accelerated software, reducing cost and time-to-market quotas, increasing energy efficiency (and thus battery life in mobile devices) and improving reliability. With respect to key case studies, the CARP technology is anticipated to provide:
- A performance increase of at least 4x when comparing optimised code with non-optimised code, on multiple platforms.
- A reduction of at least 20% in energy consumption.
- Automatic detection of at least 70% of known functional errors.
- A reduction of several orders of magnitude in time taken to design an application to run efficiently across multiple accelerator platforms.
For further details, please see www.carpproject.eu.