The NBody sample by Intel features a load balancing approach to compute an NBody simulation across both the CPU and Intel HD Graphics. This sample illustrates how to maximize the efficiency of the processor by being able to use both the CPU and Intel HD Graphics simultaneously on a platform. The end result is not only being the sum of the performance on both devices, but also largely improving application power performance on platforms such as Ultrabook. Source code is available and is accompanied with graphics visualization of the job distribution between the devices. Get the sample here.
Developed in partnership with AMD, this hands-on four day course will teach you how to write applications in OpenCL that fully leverage the multi-core processing capabilities of the GPU. Taught by Acceleware developers who bring real world experience to the class room, students will benefit from: Hands-on exercises and progressive lectures; Individual laptops with AMD Fusion APU for student use; Small class sizes to maximize learning.
This course will teach you how to develop portable parallel applications. It will expose you to the basis of OpenCL, allowing you to easily write your own hybrid applications. Then it will introduce you to OpenCL device specific optimizations, making you able to fully exploit accelerators and achieve high performance.
The 8th international conference on High-Performance and Embedded Architectures and Compilers gets underway in Berlin Germany from January 21 to 23, 2013. Khronos Benelux Chapter Leader Vincent Hindriksen (Streamcomputing) will be holding an impromptu meet-up as well, in Berlin. If you are interested, please contact Vincent directly through his website.
Portable OpenCL (pocl) is a MIT-licensed open source implementation of the OpenCL standard which can be easily adapted for new targets and devices, both for homogeneous CPU and heterogenous GPUs/accelerators. pocl uses Clang as an OpenCL C frontend and LLVM for the kernel compiler implementation, and as a portability layer. Thus, if your desired target has an LLVM backend, it should be able to get OpenCL support easily by using pocl.
Virtual OpenCL (VCL) is a cluster platform that allows unmodified OpenCL applications to transparently utilize many OpenCL devices in a cluster, as if all the devices are on the local computer. The latest update includes one security fix, bug fixes and the addition of SuperCL special registry, allowing SuperCL programs to read the time in nano-seconds.
JavaCL 1.0.0-RC3 was just released and brings lots of bugfixes, massive performance improvements and preliminary OSGi support. This BSD-licensed library gives Java developer all the power of OpenCL, with just a single cross-platform JAR to put in their classpath (no native libraries headache). The release notes and JavaCL download are available online.