The BLIS Framework: Experiments in Portability

Abstract

BLIS is a new software framework for instantiating high-performance BLAS-like dense linear algebra libraries. We demonstrate how BLIS acts as a productivity multiplier by using it to implement the level-3 BLAS on a variety of current architectures. The systems for which we demonstrate the framework include state-of-the-art general-purpose, low-power, and many-core architectures. We show, with very little effort, how the BLIS framework yields sequential and parallel implementations that are competitive with the performance of ATLAS, OpenBLAS (an effort to maintain and extend the GotoBLAS), and commercial vendor implementations such as AMD’s ACML, IBM’s ESSL, and Intel’s MKL libraries. Although most of this article focuses on single-core implementation, we also provide compelling results that suggest the framework’s leverage extends to the multithreaded domain.

References

1. Murtaza Ali, Eric Stotzer, Francisco D. Igual, and Robert A. van de Geijn. 2012. Level-3 BLAS on the TI C6678 multi-core DSP. In Proceedings of the 2012 IEEE 24th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD’12). 179--186. DOI:http://dx.doi.org/10.1109/SBAC-PAD.2012.26
2. E. Anderson, Z. Bai, C. Bischof, L. S. Blackford, J. Demmel, Jack J. Dongarra, J. Du Croz, S. Hammarling, A. Greenbaum, A. McKenney, and D. Sorensen. 1999. LAPACK Users’ Guide (3rd ed.). Society for Industrial and Applied Mathematics, Philadelphia, PA.
3. ATLAS. 2013. ATLAS 3.8.4 ARM. Retrieved April 4, 2016, from http://www.vesperix.com/arm/atlas-arm/index.html.
4. Jack J. Dongarra, Jeremy Du Croz, Sven Hammarling, and Iain Duff. 1990. A set of level 3 basic linear algebra subprograms. ACM Transactions on Mathematical Software 16, 1, 1--17.
5. Jack J. Dongarra, Jeremy Du Croz, Sven Hammarling, and Richard J. Hanson. 1988. An extended set of FORTRAN basic linear algebra subprograms. ACM Transactions on Mathematical Software 14, 1, 1--17.
6. Freescale Semiconductor. 1999. AltiVec Technology Programming Interface Manual. Retrieved April 4, 2016, from, http://www.freescale.com/files/32bit/doc/ref_manual/ALTIVECPIM.pdf.
7. Kazushige Goto and Robert van de Geijn. 2008a. Anatomy of high-performance matrix multiplication. ACM Transactions on Mathematical Software 34, 3, 12:1--12:25.
8. Kazushige Goto and Robert van de Geijn. 2008b. High-performance implementation of the level-3 BLAS. ACM Transactions on Mathematical Software 35, 1, 1--14.
9. Michael Gschwind. 2012. Blue Gene/Q: Design for sustained multi-petaflop computing. In Proceedings of the 26th ACM International Conference on Supercomputing (ICS’12). ACM, New York, NY, 245--246. DOI:http://dx.doi.org/10.1145/2304576.2304609
10. John A. Gunnels, Greg M. Henry, and Robert A. van de Geijn. 2001a. A family of high-performance matrix multiplication algorithms. In Computational Science—ICCS 2001. Lecture Notes in Computer Science, Vol. 2073. Springer, 51--60.
11. John A. Gunnels, Robert A. van de Geijn, Daniel S. Katz, and Enrique S. Quintana-Orti. 2001b. Fault-tolerant high-performance matrix multiplication: Theory and practice. In Proceedings of the 2001 International Conference on Dependable Systems and Networks (DSN’01). IEEE, Los Alamitos, CA, 47--56.
12. Alexander Heinecke, Karthikeyan Vaidyanathan, Mikhail Smelyanskiy, Alexander Kobotov, Roman Dubtsov, Greg Henry, Aniruddha G. Shet, George Chrysos, and Pradeep Dubey. 2013. Design and implementation of the Linpack benchmark for single and multi-node systems based on Intel® Xeon Phi™ coprocessor. In Proceedings of the 27th IEEE International Parallel & Distributed Processing Symposium (IPDPS’’13).
13. K. Huang and J. A. Abraham. 1984. Algorithm--based fault tolerance for matrix operations. IEEE Transactions on Computers 33, 6, 518--528.
14. IBM Blue Gene Team. 2013. Design of the IBM Blue Gene/Q compute chip. IBM Journal of Research and Development 57, 1/2, 1:1--1:13. DOI:http://dx.doi.org/10.1147/JRD.2012.2222991
15. Francisco D. Igual, Murtaza Ali, Arnon Friedmann, Eric Stotzer, Timothy Wentz, and Robert A. van de Geijn. 2012. Unleashing the high-performance and low-power of multi-core DSPs for general-purpose HPC. In Proceedings of the International Conference on High Performance Computing, Networking, Storage, and Analysis (SC’12). IEEE, Los Alamitos, CA, 26:1--26:11. http://dl.acm.org/citation.cfm?id=2388996.2389032
16. B. Kågström, P. Ling, and C. Van Loan. 1998. GEMM-based level 3 BLAS: High performance model implementations and performance evaluation benchmark. ACM Transactions on Mathematical Software 24, 3, 268--302.
17. C. L. Lawson, R. J. Hanson, D. R. Kincaid, and F. T. Krogh. 1979. Basic linear algebra subprograms for Fortran usage. ACM Transactions on Mathematical Software 5, 3, 308--323.
18. Loongson Technology. 2009. Loongson 3A Processor Manual. Loongson Technology Corp. Ltd.
19. Tze Meng Low, Francisco D. Igual, Tyler M. Smith, and Enrique S. Quintana-Ortí. 2014. Analytical Modeling Is Enough for High Performance BLIS. Technical Report. Department of Computer Sciences, University of Texas at Austin.
20. OpenBLAS. 2012. OpenBLAS Home Page. Retrieved April 4, 2016, from http://xianyi.github.com/OpenBLAS/.
21. OpenMP Architecture Review Board. 2008. OpenMP Application Program Interface Version 3.0. Retrieved April 4, 2016, from http://www.openmp.org/mp-documents/spec30.pdf.
22. Ardavan Pedram, Andreas Gerstlauer, and Robert A. van de Geijn. 2012a. On the efficiency of register file versus broadcast interconnect for collective communications in data-parallel hardware accelerators. In Proceedings of the 2012 24th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD’12).
23. Ardavan Pedram, Robert A. van de Geijn, and Andreas Gerstlauer. 2012b. Codesign tradeoffs for high-performance, low-power linear algebra architectures. IEEE Transactions on Computers 61, 1724--1736. DOI:http://dx.doi.org/10.1109/TC.2012.132
24. B. Sinharoy, R. Kalla, W. J. Starke, H. Q. Le, R. Cargnoni, J. A. Van Norstrand, B. J. Ronchetti, J. Stuecheli, J. Leenstra, G. L. Guthrie, D. Q. Nguyen, B. Blaner, C. F. Marino, E. Retter, and P. Williams. 2011. IBM POWER7 multicore server processor. IBM Journal of Research and Development 55, 3, 1:1--1:29.
25. Tyler M. Smith, Robert A. van de Geijn, Mikhail Smelyanskiy, Jeff R. Hammond, and Field G. Van Zee. 2014. Anatomy of high-performance many-threaded matrix multiplication. In Proceedings of the 28th IEEE International Parallel & Distributed Processing Symposium (IPDPS’’14).
26. Texas Instruments. 2010. TMS320C66x DSP CPU and Instruction Set Reference Guide. Retrieved April 4, 2016, from http://www.ti.com/lit/ug/sprugh7/sprugh7.pdf.
27. Texas Instruments. 2012. TMS320C6678 Multicore Fixed and Floating-Point Digital Signal Processor. Retrieved April 4, 2016, from http://www.ti.com.cn/cn/lit/ds/symlink/tms320c6678.pdf.
28. Field G. Van Zee. 2012. Libflame : The Complete Reference. www.lulu.com.
29. Field G. Van Zee, Ernie Chan, Robert van de Geijn, Enrique S. Quintana-Ortí, and Gregorio Quintana-Ortí. 2009. The libflame library for dense matrix computations. IEEE Computation in Science & Engineering 11, 6, 56--62.
30. Field G. Van Zee and Robert A. van de Geijn. 2012. BLIS: A Framework for Generating BLAS-Like Libraries. FLAME Working Note #66. Technical Report UTCS TR-12-30. Department of Computer Sciences, University of Texas at Austin.
31. Field G. Van Zee and Robert A. van de Geijn. 2015. BLIS: A framework for rapidly instantiating BLAS functionality. ACM Trans. Math. Software 41, 3, Article No. 14.
32. R. Clint Whaley and Jack J. Dongarra. 1998. Automatically tuned linear algebra software. In Proceedings of the 1998 ACM/IEEE Conference on Supercomputing (SC’98). 1--27.
33. Zhang Xianyi, Wang Qian, and Zhang Yunquan. 2012. Model-driven level 3 BLAS performance optimization on Loongson 3A processor. In Proceedings of the 2012 IEEE 18th International Conference on Parallel and Distributed Systems (ICPADS’12).
34. Kamen Yotov, Xiaoming Li, María Jesús Garzarán, David Padua, Keshav Pingali, and Paul Stodghill. 2005. Is search really necessary to generate high-performance BLAS? Proceedings of the IEEE 93, 2, 358--386.

Index Terms

• Mathematics of computing

  • Mathematical software