Abstract
On the way to Exascale, programmers face the increasing challenge of having to support multiple hardware architectures from the same code base. At the same time, portability of code and performance are increasingly difficult to achieve as hardware architectures are becoming more and more diverse. Today’s heterogeneous systems often include two or more completely distinct and incompatible hardware execution models, such as GPGPU’s, SIMD vector units, and general purpose cores which conventionally have to be programmed using separate tool chains representing non-overlapping programming models. The recent revival of interest in the industry and the wider community for the C++ language has spurred a remarkable amount of standardization proposals and technical specifications in the arena of concurrency and parallelism. This recently includes an increasing amount of discussion around the need for a uniform, higher-level abstraction and programming model for parallelism in the C++ standard targeting heterogeneous and distributed computing. Such an abstraction should perfectly blend with existing, already standardized language and library features, but should also be generic enough to support future hardware developments. In this paper, we present the results from developing such a higher-level programming abstraction for parallelism in C++ which aims at enabling code and performance portability over a wide range of architectures and for various types of parallelism. We present and compare performance data obtained from running the well-known STREAM benchmark ported to our higher level C++ abstraction with the corresponding results from running it natively. We show that our abstractions enable performance at least as good as the comparable base-line benchmarks while providing a uniform programming API on all compared target architectures.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bolt C++ Template Library. http://developer.amd.com/tools-and-sdks/opencl-zone/bolt-c-template-library/
C++ Single-source Heterogeneous Programming for OpenCL. https://www.khronos.org/sycl
HCC: an open source C++ compiler for heterogeneous devices. https://github.com/RadeonOpenCompute/hcc
OpenACC (Directives for Accelerators). http://www.openacc.org/
OpenMP: a proposed Industry standard API for shared memory programming, October 1997. http://www.openmp.org/mp-documents/paper/paper.ps
CUDA (2013). http://www.nvidia.com/object/cuda_home_new.html
N4406: parallel algorithms need executors. Technical report (2015). http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2015/n4406.pdf
Broquedis, F., Clet-Ortega, J., Moreaud, S., Furmento, N., Goglin, B., Mercier, G., Thibault, S., Namyst, R.: hwloc: a generic framework for managing hardware affinities in HPC applications. In: PDP 2010 - The 18th Euromicro International Conference on Parallel, Distributed and Network-Based Computing. IEEE, Pisa, Italy. https://hal.inria.fr/inria-00429889
Deakin, T., McIntosh-Smith, S.: GPU-STREAM: benchmarking the achievable memory bandwidth of graphics processing units. In: IEEE/ACM SuperComputing (2015)
Edwards, H.C., Trott, C.R., Sunderland, D.: Kokkos: enabling manycore performance portability through polymorphic memory access patterns. J. Parallel Distrib. Comput. 74(12), 3202–3216 (2014). Domain-Specific Languages and High-Level Frameworks for High-Performance Computing
Hoberock, J., Bell, N.: Thrust: a parallel template library, vol. 42, p. 43 (2010). http://thrust.googlecode.com
Hornung, R., Keasler, J., et al.: The Raja portability layer: overview andstatus. Lawrence Livermore National Laboratory, Livermore, USA (2014)
Kaiser, H., Adelstein-Lelbach, B., Heller, T., Berg, A., Biddiscombe, J., Bikineev, A., Mercer, G., Schfer, A., Habraken, J., Serio, A., Anderson, M., Stumpf, M., Bourgeois, D., Grubel, P., Brandt, S.R., Copik, M., Amatya, V., Huck, K., Viklund, L., Khatami, Z., Bacharwar, D., Yang, S., Schnetter, E., Bcorde5, Brodowicz, M., Bibek, atrantan, Troska, L., Byerly, Z., Upadhyay, S.: hpx: HPX V0.9.99: a general purpose C++ runtime system for parallel and distributed applications of any scale, July 2016. http://dx.doi.org/10.5281/zenodo.58027
Kaiser, H., Heller, T., Bourgeois, D., Fey, D.: Higher-level parallelization for local and distributed asynchronous task-based programming. In: Proceedings of the First International Workshop on Extreme Scale Programming Models and Middleware, pp. 29–37. ACM (2015)
McCalpin, J.D.: Stream: sustainable memory bandwidth in high performance computers. Technical report, University of Virginia, Charlottesville, Virginia (1991–2007), a continually updated Technical report. http://www.cs.virginia.edu/stream/
McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. IEEE Comput. Soc. Tech. Committee Comput. Archit. (TCCA) Newsl. 59, 19–25 (1995)
The C++ Standards Committee: ISO International Standard ISO/IEC 14882: 2014, Programming Language C++. Technical report, Geneva, Switzerland: International Organization for Standardization (ISO) (2014). http://www.open-std.org/jtc1/sc22/wg21
The C++ Standards Committee: N4578: Working Draft, Technical Specification for C++ Extensions for Parallelism Version 2. Technical report (2016). http://open-std.org/JTC1/SC22/WG21/docs/papers/2016/n4578.pdf
The C++ Standards Committee: N4594: Working Draft, Standard for Programming Language C ++. Technical report (2016). http://open-std.org/JTC1/SC22/WG21/docs/papers/2016/n4594.pdf
Acknowledgement
This work is supported by the NSF awards 1240655 (STAR), 1447831 (PXFS), and 1339782 (STORM), and the DoE award DE-SC0008714 (XPRESS) and by the European Union’s Horizon 2020 research and innovation program under grant agreement No 671603.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Heller, T., Kaiser, H., Diehl, P., Fey, D., Schweitzer, M.A. (2016). Closing the Performance Gap with Modern C++. In: Taufer, M., Mohr, B., Kunkel, J. (eds) High Performance Computing. ISC High Performance 2016. Lecture Notes in Computer Science(), vol 9945. Springer, Cham. https://doi.org/10.1007/978-3-319-46079-6_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-46079-6_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46078-9
Online ISBN: 978-3-319-46079-6
eBook Packages: Computer ScienceComputer Science (R0)