Simon McIntosh-Smith's publications

Selected papers, publications and invited talks

• Invited conference talk: "The continuing renaissance in parallel programming languages", Multicore Challenge 2014 workshop, Bristol, September 23rd 2014 (local pdf)
• Seminar: "Developing performance portable many-core codes", Stanford University, October 2nd 2014 (local pdf)
• Invited conference talk: "Fault Tolerance Techniques for Sparse Matrix Methods", SIAM Workshop on Exascale Applied Mathematics Challenges and Opportunities (EX14), Chicago, July 6th 2014 (local pdf)
• Conference paper: "On the Performance Portability of Structured Grid Codes on Many-Core Computer Architectures", S.N. McIntosh-Smith, M. Boulton, D. Curran and J.R. Price, International Supercomputing Conference, Leipzig, June 22-26th 2014. DOI: 10.1007/978-3-319-07518-1_4 (full paper, conference slides)
• Conference paper: "Evaluation of a performance portable lattice Boltzmann code using OpenCL", Simon McIntosh-Smith and Dan Curran, International Workshop on OpenCL (IWOCL), Bristol, May 12-13 2014.
• Conference talk: "The Intel Parallel Computing Center at the University of Bristol", 11th Intel HPC roundtable, Downing College, Cambridge, April 9th 2014 (local pdf)
• Invited conference talk: "Performance Portability for Embedded GPUs", LPGPU Workshop on Power-Efficient GPU and Many-core Computing (PEGPUM 2014), HiPEAC 2014 (local pdf)
• Journal paper: "High performance in silico virtual drug screening on many-core processors", Simon McIntosh-Smith, James Price, Richard B Sessions and Amaurys A Ibarra, International Journal of High Performance Computing Applications (IJHPCA), published online 9 April 2014. DOI: 10.1177/1094342014528252.
• Journal paper: "Analysis and assay of oseltamivir-resistant mutants of influenza neuraminidase via direct observation of drug unbinding and rebinding in simulation", Christopher J. Woods, Maturos Malaisree, Benjamin Long, Simon McIntosh-Smith and Adrian J. Mulholland, Biochemistry, October 15th 2013. DOI: 10.1021/bi400754t
• Invited talk: "Building HPC Systems from Mobile Processors: The Mont Blanc Project", Multicore Challenge 2013 workshop, Bristol, UK. (local pdf, video on YouTube)
• Conference paper: "Porting a commercial application to OpenCL: a case study", Simon Krige, Mark Mackey, Simon McIntosh-Smith and Richard Sessions. The 1st International Workshop on OpenCL (IWOCL), Georgia Tech, Atlanta, Georgia, May 2013.
• Conference paper: "How GPUs can find your next hit: Accelerating virtual screening with OpenCL", Simon Krige, Mark Mackey, Simon McIntosh-Smith and Richard Sessions. Advances in Virtual High-Throughput Screening, 245th American Chemical Society (ACS) Meeting, April 7-11, 2013, New Orleans, Louisiana. (local pdf)
• Invited keynote: "Trends in heterogeneous systems architectures", LPGPU Workshop on Power-Efficient GPU and Many-core Computing (PEGPUM 2013), HiPEAC 2013. (local pdf)
• Conference paper: "Accelerating Hydrocodes with OpenACC, OpenCL and CUDA", A.J. Herdman, W.P. Gaudin, S. McIntosh-Smith, M. Boulton, D.A. Beckingsale, A.C. Mallinson, and S.A. Jarvis. In High Performance Computing, Networking, Storage and Analysis (SCC), 2012 SC Companion:, pp. 465-471. IEEE, 2012. (local pdf)
• Micro group talk: "Trends in Heterogeneous Systems Architectures", University of Bristol Microelectronics Research Group seminar series, Bristol, UK, July 31st 2012. (local pdf)
• Invited talk: "Trends in Heterogeneous Systems Architectures (and how they'll affect parallel programming models)", The Oxford e-Research Centre Many-Core Seminar Series Trinity 2012, Oxford, UK, June 13th 2012. (local pdf)
• Conference paper: "Adaptive Heterogeneous Computing with OpenCL: Harnessing hundreds of GPUs and CPUs", Los Alamos National Laboratory Accelerated High Performance Computing Symposium (AHPCS), NVIDIA GPU Technology Conference, San Jose, USA, May 16th 2012. (local pdf)
• Invited talk: "Power: the new metric", Los Alamos National Laboratory Accelerated High Performance Computing Symposium (AHPCS), NVIDIA GPU Technology Conference, San Jose, USA, May 17th 2012. (local pdf)
• Invited talk: "Adaptive Heterogeneous Computing with OpenCL: Harnessing hundreds of GPUs and CPUs (extended talk)", Los Alamos National Laboratory, New Mexico, USA, May 8th 2012. (local pdf)
• Invited talk: "The resurgence of parallel programming languages", British Computer Society evening talks, S. McIntosh-Smith and J. Hanlon, London, Apr 12th 2012. (local pdf)
• Invited talk: "Major hardware trends affecting Exascale developments and their potential impact on software", PRACE- 1IP Work Package 9 Future Technologies Workshop, Daresbury, UK, Apr 11th 2012. (local pdf)
• Conference paper: "Energy Efficient HPC Software: Learning from Embedded Systems Development", K. Eder, S. Kerrison and S. McIntosh-Smith, SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP12), Savanah, Georgia, February 2012. (local pdf)
• Invited keynote: "Mechanisms for exploiting heterogeneous computing: Harnessing hundreds of GPUs and CPUs", MULTIPROG workshop, HiPEAC 2012, Paris, Jan 23-25 2012. (local pdf)
• Conference tutorial: "Heterogeneous Computing", in collaboration with Benedict Gaster and Lee Howes of AMD, HiPEAC 2012, Paris, Jan 23-25 2012. (local pdf)
• Invited talk: "The impact of many-core computer architectures on numerical libraries: past, present and future", Advances in High Performance Scientific Computing (AHPSC), 16th January 2012, School of Mathematics, The University of Manchester. (local pdf)
• Conference paper: "Exploiting OpenCL for heterogeneous computing: a case study", The Third UK GPU Developer Conference (UKGPU11), Imperial College, London, 14th December 2011. (local pdf)
• Conference paper: "A method for automatically generating analogue benchmarksuites using low-level hardware metrics", ACM SIGMETRICS 2nd International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems (PMBS 11), ACM / IEEE Supercomputing 2011 (SC11), Seattle, November 12-18, 2011. (local pdf)
• Invited talk: "Speeding up molecular docking simulations using graphics processors", Cresset User Group Meeting, Downing Hall, Cambridge University, 22nd September, 2011. (local pdf)
• Invited paper: "The GPU Computing Revolution: From Multi-Core CPUs to Many-Core Graphics Processors", Simon McIntosh-Smith, A Knowledge Transfer Report from the London Mathematical Society and Knowledge Transfer Network for Industrial Mathematics, September 2011. (pdf)
• Journal paper: "Benchmarking energy efficiency, power costs and carbon emissions on heterogeneous systems", Simon McIntosh-Smith, Terry Wilson, Amaurys Avila Ibarra, Jon Crisp and Richard B.Sessions, The Computer Journal, September 12th 2011. DOI: 10.1093/comjnl/bxr091
• Journal paper: "Energy-aware metrics for benchmarking heterogeneous systems", Simon McIntosh-Smith, Terry Wilson, Jon Crisp, Amaurys Avila Ibarra and Richard B.Sessions, ACM SIGMETRICS Perform. Eval. Rev., 38(4):88--94, March 2011. DOI: 10.1145/1964218.1964233
• Invited talk: "Accelerating molecular docking on multi- and many-core computer architectures", The Molecular Graphics Modelling Society's workshop on Exploiting New Computer Architectures in Molecular Dynamics Simulations, School of Oriental and African Studies, London, 23 March, 2011. (local pdf)
• Conference paper: "Energy-aware metrics for benchmarking heterogeneous systems", ACM SIGMETRICS 1st International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems (PMBS 10), ACM / IEEE Supercomputing 2010 (SC10), New Orleans, November 13-19, 2010. (local pdf | slides from talk)
• Invited seminar: "How energy efficiency is driving the future of computing", Oxford e-Research Centre, Oxford University, 26th October 2010 (local pdf)
• Invited talk: "HPC Hardware and trends from a designer's perspective", AWE Exascale Computing workshop, Aldermaston, 13th October 2010
• Invited conference keynote: "An analysis of the impact of Heterogeneous Many-core Computing", The 26th UK Performance Evaluation Workshop (UKPEW), Warwick, UK, July 2010 (local pdf) (conference pdf)
• Conference paper: "Heterogeneous Many-core Computing Trends: Past, Present and Future", SIAM Conference on Parallel Processing for Scientific Computing (PP10), Seattle, February 2010 (pdf)
• Mini symposium chair: "Trends and Experiences in Heterogeneous Many-core Computing" MS36 mini symposium at SIAM's PP10, Seattle, February 2010
• Journal paper: "A massively multicore parallelization of the Kohn-Sham energy gradients", Philip Brown, Frederick R. Manby, Simon McIntosh-Smith and Christopher J. Woods, Journal of Computational Chemistry, February 1st 2010. DOI: 10.1002/jcc.21485
• Panel session: "Teach Parallel", SuperComputing 2009 (SC09), with Bill Daly (Nvidia/Stanford), John Gustafson (Intel), Bob Chesebrough (Intel), Charlie Peck (Earlham College), Tom Murphy (Contra Costa)
• Invited talk: "Developments in High Performance Computing", University of Bristol HPC symposium, Bristol, 21st October 2009 (pdf)
• Invited talk: "The latest trends in High Performance Computing", NAG Ltd Colloquium, Oxford, 25th September 2009
• Invited talk: "High Performance Computing", AWE collaboration meeting, Warwick University, 24th September 2009
• Invited talk: "The latest trends in High Performance Computing", Simon McIntosh-Smith, UK HPC-SIG, Oxford University, 16th July 2009 (pdf)
• Interview: "Are we virtually there yet?" by Maggie Philbin, The Times virtualisation supplement, April 29th 2009
• Journal paper: "Massively Multicore Parallelization of Kohn-Sham Theory", Philip Brown, Frederick R. Manby, Simon McIntosh-Smith and Christopher J. Woods, Journal of Chemical Theory and Computation (JCTC), 4 (10), 1620-1626, 2008. DOI 10.1021/ct800261j
• Conference paper: "A next-generation many-core processor with reliability, fault tolerance and adaptive power management features optimized for embedded and high performance computing applications", Simon McIntosh-Smith, High Performance Embedded Computing, MIT Lincoln Laboratories, September 2008 (pdf)
• Conference paper: "An Accelerated, Computer Assisted Molecular Modeling Method for Drug Design", Dr Richard Sessions, Simon McIntosh-Smith, International SuperComputing '08, Dresden, June 2008 (pdf)
• Journal paper: "Accelerating drug development", Next Generation Pharmaceutical 12, March 2008
• Conference paper: "The best of both worlds: Delivering aggregated performance for high-performance math libraries in accelerated systems", Simon McIntosh-Smith, Dr James Irwin, International SuperComputing '07, Dresden, June 2007 (pdf)
• Conference paper: "Accelerating Intel Math Kernel Library (MKL) with ClearSpeed Advance boards on multi-core systems", Simon McIntosh-Smith, Intel Developer Forum, San Francisco, September 2006
• Journal paper: "Optimizing the discovery engine", Next Generation Pharmaceutical 6, August 2006
• Journal paper: "A Desktop Supercomputer", IEEE Spectrum, January 2006
• Conference paper: "Turbo-charged applications on ClearSpeed's streaming processors", American Chemical Society national meeting, Philadelphia, August 2004
• Conference paper: "A 50-GFLOPS Processor for Scientific Computing and DSP", Microprocessor Forum, San Jose, October 2004
• Conference paper: "MTAP Technology for High-Performance Computing", Scientific American's BioSilicon 2003, Stanford University, October 2003

---

• Back to Simon's home page