TESLA

  • What is GPU Computing
  • GPU Applications
  • Servers and Workstations
Developing with GPUs. Getting Started, Open ACC and CUDA on ARM
Divider
Getting Started
OpenACC Directives
CUDA on ARM

Simplest Way to Portable Computing

Ideal for Accelerating Legacy Codes with GPUs

OpenACC directives are the simple and portable way to accelerate your scientific code. With OpenACC, you simply insert compiler hints into your Fortran or C code and the compiler will automatically map compute-intensive portions of your code to the GPU for higher performance.

Now available from industry leaders, Cray, CAPS, and The Portland Group (PGI), OpenACC compilers are:

  • Open: Future-proof your codes with this open standard
  • Simple: Easy, high-level, compiler driven approach to parallel computing
  • Portable: Ideal for accelerating legacy Fortran or C codes

Here's an example of how easy a single directive hint can accelerate the calculation of pi. With GPU directives, you can get started and see results in the same afternoon.

Get the free 30-day trial license of the PGI Accelerator Compiler.

Download

* Registration requires creating an account on the PGI website. After registering, you'll receive an email from PGI with further details.

 
 

"The PGI compiler is now showing us just how powerful it is. On the software we are writing, it's at least 60 times faster on the NVIDIA card. We are very pleased and excited about the future uses. It's like owning a personal supercomputer."
Dr. Kerry Black
University of Melbourne
Learn more...

"I have written micromagnetic codes (written in Fortran 90) to study the properties of two and three dimensional magnetic systems. The directives approach enabled me to port my existing code with ease to perform my computations on the GPU which resulted in a significant speedup (more than 20 times) of the computation."
Professor M. Amin Kayali
University of Houston
Learn more...

Read more success stories...


OpenACC Support PGI Accelerator

Fortran Version
program picalc
      implicit none
      integer, parameter :: n=1000000
      integer :: i
      real(kind=8) :: t, pi
      pi = 0.0
   !$acc parallel loop
      do i=0, n-1
        t = (i+0.5)/n
        pi = pi + 4.0/(1.0 + t*t)
      end do
   !$acc end parallel loop
      print *, 'pi=', pi/n
   end program picalc


DEVELOPER TOOLBOX

Follow these 2 simple steps to help you get started with OpenACC Directives.

    1. Read the short Directives Tips for a Fortran Program or
    Directives for a C Program.
    2. Watch the Introduction video to the PGI Accelerator (11:19)

You'll need an NVIDIA® CUDA-capable GPU and a Fortran or C based application to get started. Don't have a GPU? We recommend an NVIDIA Tesla C2075 GPU.