Codeplay is at IWOCL 2017 this week, and is pleased to announce support for Ubuntu 16.04 and Eigen with the latest ComputeCpp Community Edition. We will also be letting developers get their hands on this version during a 4 hour tutorial at the conference.
The release of ComputeCpp CE v0.2.0 adds support for the current LTS (long term support) version of Ubuntu, 16.04, and enables developers to use the Eigen library for linear algebra tensor operations whilst taking advantage of the parallel capabilities of heterogeneous OpenCL hardware.
If you haven't already started using ComputeCpp, we have a Getting Started Guide and Integration Guide that will have you set up and using ComputeCpp in no time.
Developers can now use ComputeCpp to build parallel applications using SYCL and standard C++ using Ubuntu 16.04. This also brings support for the latest implementation of ParallelSTL for SYCL for that version of Ubuntu, enabling acceleration of standard C++ algorithms on OpenCL devices.
Eigen is the most popular C++ library for linear algebra and is used in hundreds of applications and frameworks such as Google's machine learning framework TensorFlow, and even mobile applications such as Layar and Artsy. Until now it has only been possible to use the Eigen tensor operations with CPUs or NVidia GPUs, but with support for SYCL added using ComputeCpp it is now possible for developers to target heterogeneous OpenCL devices. We are really excited to offer this new integration to developers, and have a simple guide to getting started with Eigen and SYCL using ComputeCpp.
We also continue to make great progress in our implementation of OpenCL support for TensorFlow (via SYCL). At IWOCL we will be showing some demos of TensorFlow running with ComputeCpp, as well as presenting the details of our implementation at the event on the 18th May.