The latest update the NVIDIA HPC SDK is now available for download. The NVIDIA HPC SDK is a comprehensive suite of compilers, libraries, and tools enabling HPC developers to program the entire HPC platform from the GPU foundation to the CPU, and through the interconnect. It is the only comprehensive, integrated SDK for programming accelerated computing systems.
The NVIDIA HPC SDK C++ and Fortran compilers are the first and only compilers to support automatic GPU acceleration of standard language constructs including C++17 parallel algorithms and Fortran intrinsics.
New Features in Version 20.11
- Beta support for a subset of an OpenMP target offload on Volta or newer GPUs.
- Fortran DO CONCURRENT construct supports GPU and multi-core acceleration.
- New nvlamath Fortran library GPU accelerates standard BLAS routines.
- Support for CUDA Toolkit 11.1.
- Newest versions of bundled libraries and developer tools.
- RPM packages for the SUSE Linux Enterprise Server.
- C++11 is now the default C++ Standard version.
- New command-line options to improve compatibility with GCC.
See the HPC SDK Release Notes for more information.