high performance computing on graphics processing units: hgpu.org

Today servers, desktops, mobile devices, and embedded systems contain many processors in addition to the CPU that runs programs. These extra processors are generally called accelerators and could be a GPU, FPGA, Xeon Phi, or other programmable device. There are many types of accelerators available, from many vendors, for many different environments. Khronos developed the OpenCL standard so that an application can offload parallel computation to accelerators in a common way, regardless of their underlying architecture or programming model. OpenCL-enabled software can obtain peak performance by using every OpenCL-enabled parallel processor and accelerator on the system together at the same time.