ACADEMIA

CAPS entreprise has announced that its HMPP directive-based compiler has added support for AMD’s GPU technology. Based on OpenACC and OpenHMPP directive-based programming model, HMPP compiler fully integrates data-parallel backend for OpenCL and will leverage the computing power of AMD GPU and APU devices. Addressing this new target in OpenACC demonstrates CAPS commitment to provide portable solutions for its customers. The initial GPUs supported in this release are AMD FireProW9000, FirePro S8000 and FirePro W8000 series.

“Supporting an industry standard such as OpenCL in our products is critical to reach larger developer community that is using GPU compute” said Eric Courtois, director of software development at CAPS. “When designing our products, we focus on key tools used by programmers with various levels of expertise from beginners to advanced users. With this release, we are enabling our customers to transition their applications to the latest generation of AMD hardware to fully leverage the underlying computing power of the platform.”

The initial performance results are extremely promising and illustrate how the compiler directives can be used to leverage AMD FirePro capabilities while preserving C or FORTRAN codes. With a few directives, the performance of image-processing routines like Sobel Filter was increased by more than an order of magnitude (x40). Furthermore, CAPS technology helps users take advantage of AMD Accelerated Parallel Processing Math Libraries (APPML), the software libraries containing FFT and BLAS functions designed to run on AMD GPUs.