Citation
John Stratton, Sam Stone, Wen-mei Hwu. "MCUDA: An Efficient Implementation of CUDA Kernels on Multi-cores". Technical report, University of Illinois at Urbana-Champaign, IMPACT-08-01, March, 2008.

Abstract
The CUDA programming model, which is based on an extended ANSI C language and a runtime environment, allows the programmer to specify explicitly data parallel computation. NVIDIA developed CUDA to open the architecture of their graphics accelerators to more general applications, but did not provide an efficient mapping to execute the programming model on any other architecture. This document describes Multicore-CUDA (MCUDA), a system that efficiently maps the CUDA programming model to a multicore CPU architecture. The major contribution of this work is the source-to-source translation process that converts CUDA code into standard C that interfaces to a runtime library for parallel execution. We apply the MCUDA framework to some CUDA applications previously shown to have high performance on a GPU, and demonstrate high efficiency executing these applications on a multicore CPU architecture. The thread-level parallelism, data locality and computational regularity of the code as expressed in the CUDA model achieve much of the benefit of hand-tuning an application for the CPU architecture. With the MCUDA framework, it is now possible to write data-parallel code in a single programming model for efficient execution on CPU or GPU architectures.

Electronic downloads

• http://www.crhc.uiuc.edu/IMPACT/ftp/report/impact-08-01-mcuda.ps
• http://www.crhc.uiuc.edu/IMPACT/ftp/report/impact-08-01-mcuda.pdf

Citation formats

• HTML

  John Stratton, Sam Stone, Wen-mei Hwu. <a
  href="http://www.gigascale.org/pubs/1278.html"><i>MCUDA:
  An Efficient Implementation of CUDA Kernels on
  Multi-cores</i></a>, Technical report, 
  University of Illinois at Urbana-Champaign, IMPACT-08-01,
  March, 2008.

• Plain text

  John Stratton, Sam Stone, Wen-mei Hwu. "MCUDA: An Efficient
  Implementation of CUDA Kernels on Multi-cores". Technical
  report,  University of Illinois at Urbana-Champaign,
  IMPACT-08-01, March, 2008.

• BibTeX

  @techreport{StrattonStoneHwu08_MCUDAEfficientImplementationOfCUDAKernelsOnMulticores,
      author = {John Stratton and Sam Stone and Wen-mei Hwu},
      title = {MCUDA: An Efficient Implementation of CUDA Kernels
                on Multi-cores},
      institution = {University of Illinois at Urbana-Champaign},
      number = {IMPACT-08-01},
      month = {March},
      year = {2008},
      abstract = {The CUDA programming model, which is based on an
                extended ANSI C language and a runtime
                environment, allows the programmer to specify
                explicitly data parallel computation. NVIDIA
                developed CUDA to open the architecture of their
                graphics accelerators to more general
                applications, but did not provide an efficient
                mapping to execute the programming model on any
                other architecture. This document describes
                Multicore-CUDA (MCUDA), a system that efficiently
                maps the CUDA programming model to a multicore CPU
                architecture. The major contribution of this work
                is the source-to-source translation process that
                converts CUDA code into standard C that interfaces
                to a runtime library for parallel execution. We
                apply the MCUDA framework to some CUDA
                applications previously shown to have high
                performance on a GPU, and demonstrate high
                efficiency executing these applications on a
                multicore CPU architecture. The thread-level
                parallelism, data locality and computational
                regularity of the code as expressed in the CUDA
                model achieve much of the benefit of hand-tuning
                an application for the CPU architecture. With the
                MCUDA framework, it is now possible to write
                data-parallel code in a single programming model
                for efficient execution on CPU or GPU
                architectures. },
      URL = {http://www.gigascale.org/pubs/1278.html}
  }
  

Posted by John Stratton on 18 Apr 2008..

Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright.