AMD today announced the availability of availability of the Mentor Graphics Sourcery lite edition development environment for EPYC and Ryzen CPUs.
The Sourcery CodeBench Lite Edition is a no cost, complete C/C++ and Fortran development environment for scientific and high-performance computing (HPC) applications. Designed for complex multicore heterogeneous architectures, it allows AMD Radeon Instinct™ GPUs to be targeted for execution using the industry-standard OpenMP® and OpenACC Application Programming Interface (API) specifications. This recent release includes a GNU-based C/C++ and Fortran development toolchain for Linux platforms.
“AMD’s innovative hardware technologies combined with Mentor’s leading Sourcery CodeBench Lite environment will help the company’s growing customer base in developing high-performance computing and embedded products,” stated Dr. Randy Allen, director of Advanced Research, Mentor Embedded Platform Solutions. “This integrated solution will allow AMD customers to build, debug and analyze embedded software for multicore, heterogeneous applications with high productivity and optimized performance.”
“Mentor’s Sourcery CodeBench Lite Edition enables developers and domain scientists to create optimized applications targeting AMD CPUs and GPUs,” said Ajit Mathews, corporate vice president of Software Development, Compute and Machine Learning, AMD. “By combining common HPC programming languages with the ability to target execution onto AMD Radeon Instinct™ GPUs using industry-standard specifications, Sourcery CodeBench Lite Edition allows developers to harness the power of AMD CPUs and GPUs for next-generation HPC applications.”
In 2014, AMD and Mentor Graphics (now Mentor, A Siemens Business) established an embedded software ecosystem for developers to offer powerful open source tools for building, debugging, analyzing and optimizing embedded software. With the release of Sourcery CodeBench (AMD GCN) Lite Edition, AMD is expanding its reach into the HPC market with its Radeon Instinct™ line of GPU accelerators.