What is OpenACC?

OpenACC is a user-driven directive-based performance-portable parallel programming model designed for scientists and engineers interested in porting their codes to a wide-variety of heterogeneous HPC hardware platforms and architectures with significantly less programming effort than required with a low-level model.

#pragma acc data copy(A) create(Anew)
while ( error > tol  &&  iter  <  iter_max )  {
  error = 0.0;
#pragma acc kernels {
#pragma acc loop independent collapse(2)
  for (  int  j = 1; j < n-1;  j++ )  {
    for (  int  i = 1; i < m-1; i++ )  {
       Anew [j] [i] = 0.25 * ( A [j] [i+1] + A [j] [i-1] +
                                      A [j-1] [i] + A [j+1] [i]);
       error = max ( error, fabs (Anew [j] [i] - A [j] [i]));
      }
    }
  } 
}

Resources Access tutorials, guides, lectures, code samples, hands-on exercises and more. Get the Specs Download the latest OpenACC specification, technical report and work-in-progress proposals. Tools Get OpenACC compilers and tools designed by multiple vendors and academic organizations. Success Stories Learn how OpenACC users accelerated their scientific applications.

Latest News

PGI 18.7 Now Available

Aug. 17, 2018

Porting HPC Codes with Directives and OpenACC

Jul. 19, 2018

OpenACC Helps Scientists Port their code at the Center for Application Readiness (CARR)

Jul. 16, 2018

Using OpenACC to Port Solar Storm Modeling Code to GPUs

Jul. 16, 2018

OpenACC May and June 2018 Highlights

Jun. 18, 2018

Upcoming Events

GPU Hackathon: Brookhaven National Lab
September 17, 2018
Upton, New York, USA
GPU Hackathon: EuroHack18
October 1, 2018
CSCS, Switzerland
GPU Hackathon: ORNL
October 22, 2018
ORNL, Knoxville, TN, USA

Join Us

Tweets by OpenACCorg