Simulation / Modeling / Design

New PGI Release Supports V100 Tensor Cores, Full C++ 17 Language, OpenACC printf()

Feb 21, 2019
By Nefi Alarcon
Discuss (0)

AI-Generated Summary
  • PGI Compilers & Tools 19.1 introduces CUDA Fortran support for Tensor Cores on Tesla V100 GPUs.
  • The release adds full C++17 language feature support for developers.
  • OpenACC debugging improves with the ability to insert printf() statements directly in code.
  • Expanded PGI Compiler Assisted Software Testing directives enhance comparative debugging capabilities.
  • An upgrade to LLVM 7.0 delivers improved performance on x86 and OpenPOWER CPUs.

Next Step

Powered by NVIDIA Nemotron. AI-generated content may summarize information incompletely. Verify important information. Learn more

PGI Compilers & Tools are used by scientists and engineers developing applications for high-performance computing (HPC). PGI products deliver world-class multicore CPU performance, an easy on-ramp to GPU computing with OpenACC directives, and performance portability across all major HPC platforms. New version 19.1 is available now for users with current PGI Professional support. The latest free PGI Community Edition is version 18.10.

New Features in PGI 19.1

  • V100 Tensor Core Support – CUDA Fortran now supports using Tensor Cores on Tesla V100 GPUs
  • C++17 – Full support for C++17 language features
  • OpenACC printf() – Insert printf() statements to analyze and debug your OpenACC code
  • PCAST – Expanded PGI Compiler Assisted Software Testing directives for comparative debugging
  • LLVM 7.0 – Improved performance on x86 and OpenPOWER CPUs

Link to full description of features

Discuss (0)

Tags

Simulation / Modeling / Design | HPC / Scientific Computing | General | General Interest | News | Accelerated Computing Libraries

About the Authors

Nefi Alarcon
About Nefi Alarcon
Nefi Alarcon is a senior executive communications manager on NVIDIA's leadership team. He has years of media relations and communication experience, and has previously worked at Google, Mozilla, and CNN. He received his bachelor's degree in Journalism from George Washington University.

Comments