28 September 2010
Tech-X has released version 1.4 of its GPULib library of mathematical functions that facilitate the use of modern GPUs for HPC tasks. New to GPULib v1.4 is support for Cuda streams, enabling concurrent execution of multiple kernels. The product also supports asynchronous data transfer, and leverages new features of IDL v8.0 which enable tighter integration of the two products. The product's Matlab interface has also been updated, and a variety of new algorithms have been included, such as functions for sorting and for producing large histograms. GPULib v1.4 is compatible with Cuda Toolkit 3.1.
GPULib enables users of Matlab and IDL to take advantage of GPUs from within these high-productivity languages. Tech-X offers product training and product usage consulting to help customers leverage the Tech their investment in GPULib as quickly as possible. The company also provides consulting services to help customers accelerate their applications by implementing computational kernels for GPUs.