CAPS develops HMPP™, a directive-based compiler to build parallel GPU accelerated applications, and support for the OpenACC standard has been annouced.

Based on C and FORTRAN directives, HMPP offers a high level abstraction for hybrid programming that fully leverages the computing power of stream processors with a simple programming model.

HMPP compiler integrates powerful data-parallel backends for NVIDIA CUDA and OpenCL that drastically reduce development time. The HMPP runtime ensures application deployment on multi-GPU systems. Software assets are kept independent from both hardware platforms and commercial software. While preserving portability and hardware interoperability, HMPP increases application performance and development productivity.

Key Advantages

Phased Approach
  • Simplified directives programming model, complimentary to OpenMP and MPI
  • Planned support for OpenACC directives standard
  • Enables one code base for multiple processor configurations
  • Developers can use preferred X86 C or FORTRAN compiler
  • Distribute computations between CPU and GPU

Above all CAPS HMPP programming model delivers faster time to results.

Supporting this phased approach, CAPS also provides GPU development consulting services.


CAPS HMPP Workbench is available now.

For more information: