Portable mapping of data parallel programs to OpenCL for heterogeneous systems

D. Grewe, Zheng Wang, M.F.P. O'Boyle

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

General purpose GPU based systems are highly attractive as they give potentially massive performance at little cost. Realizing such potential is challenging due to the complexity of programming. This paper presents a compiler based approach to automatically generate optimized OpenCL code from data-parallel OpenMP programs for GPUs. Such an approach brings together the benefits of a clear high level-language (OpenMP) and an emerging standard (OpenCL) for heterogeneous multi-cores. A key feature of our scheme is that it leverages existing transformations, especially data transformations, to improve performance on GPU architectures and uses predictive modeling to automatically determine if it is worthwhile running the OpenCL code on the GPU or OpenMP code on the multi-core host. We applied our approach to the entire NAS parallel benchmark suite and evaluated it on two distinct GPU based systems: Core i7/NVIDIA GeForce GTX 580 and Core 17/AMD Radeon 7970. We achieved average (up to) speedups of 4.51× and 4.20× (143× and 67×) respectively over a sequential baseline. This is, on average, a factor 1.63 and 1.56 times faster than a hand-coded, GPU-specific OpenCL implementation developed by independent expert programmers.
Original languageEnglish
Title of host publicationCode Generation and Optimization (CGO), 2013 IEEE/ACM International Symposium on
Number of pages10
Publication statusPublished - 1 Feb 2013

Keywords / Materials (for Non-textual outputs)

  • application program interfaces
  • graphics processing units
  • multiprocessing systems
  • parallel programming
  • program compilers
  • Core i7/AMD Radeon 7970
  • Core i7/NVIDIA GeForce GTX 580
  • NAS parallel benchmark suite
  • OpenCL code
  • OpenMP code
  • compiler
  • data parallel program mapping
  • data transformations
  • data-parallel OpenMP programs
  • general purpose GPU based systems
  • heterogeneous multicores
  • heterogeneous systems
  • high level language
  • predictive modeling
  • Arrays
  • Benchmark testing
  • Feature extraction
  • Graphics processing units
  • Indexes
  • Kernel
  • Predictive models
  • GPU, OpenCL, Machine
  • Learning Mapping


Dive into the research topics of 'Portable mapping of data parallel programs to OpenCL for heterogeneous systems'. Together they form a unique fingerprint.

Cite this