CAPS has announced that Oak Ridge National Laboratory (ORNL) will use CAPS’ HMPP compiler to leverage the supercomputing power of a graphics processing unit (GPU)-based hybrid cluster.

As a world leader in high-performance computing (HPC), ORNL is preparing the future of nextgeneration petascale computing with machines that will combine general-purpose central processing unit (CPU) cores with hundreds of GPU cores, which can deliver tremendous performance. In this context, ORNL have selected HMPP to enable the programming of high-performing parallel GPU/CPU hybrid applications.

“We are very glad ORNL chose HMPP for the future of their parallel hybrid application development. During the past two years, HMPP has been used by major European HPC leaders and has been able to achieve a level of maturity that makes it a tool of choice.” said Stéphane Bihan, director of CAPS Global Business Development, “Having ORNL select HMPP is a commitment from the industry for a portable, compiler-based solution in manycore computing”.

Based on a set of directives for programming and tuning GPU-accelerated applications, HMPP is a C and Fortran source-to-source compiler that gives developers a high level of abstraction for programming GPUs in scientific applications. HMPP offers developers an incremental way of programming from minimal expertise to advanced and expert. HMPP works with standard compilers and hardware vendor tools to create the application binary.

“We like the way HMPP addresses manycore programming: in addition to GPU programming directives that efficiently define and optimize computations offloaded in GPUs, the tuning directives  give us control over the fine-tuning of the GPU-accelerated kernels,” said Richard Graham, group leader for the Applications Performance Tools group within ORNL’s Computer Science and Mathematics Division. “Also, by letting us use our standard compilers, HMPP really seamlessly integrates in our development environment.”