Nvidia has released a new version of its CUDA parallel computing platform with a targeted focus on researchers and engineers for building advanced simulations and GPU-intensive computational work. Singling out computational biologists, chemists, physicists, and geophysicists as key users, the Nvidia CUDA parallel computing platform has a redesigned visual profiler, a new compiler, and new imaging and signal-processing functions.

Nvidia says that it is supplying "hundreds" of new imaging and signal-processing functions, effectively doubling the size of its Performance Primitives library. This enables developers using image or signal-processing algorithms to gain the benefit of GPU acceleration, with the addition of library calls into their application. The updated NPP library can be used for a wide variety of image and signal-processing algorithms, ranging from basic filtering to advanced workflows.

"The new Visual Profiler makes it easy for developers at all experience levels to optimize their code for maximum performance. Featuring automated performance analysis and an expert guidance system that delivers step-by-step optimization suggestions, the Visual Profiler identifies application performance bottlenecks and recommends actions, with links to the optimization guides. Using the new Visual Profiler, performance bottlenecks are easily identified and actionable,” said the company.

The LLVM open-source compiler infrastructure features a modular design to add support for new programming languages and processor architectures. Using the new LLVM- based CUDA compiler, the company claims that developers can achieve up to 10 percent additional performance gains on existing GPU-accelerated applications with a recompile. In addition, LLVM's modular design should allow third-party software tool developers to provide a custom LLVM solution for non-Nvidia processor architectures, enabling CUDA applications to run across Nvidia GPUs, as well as those from other vendors.