Performance Engineering for Linear Solvers. Half-day tutorial at SC24, Atlanta, GA, November 18, 2024 (with Christie L. Alappat and Hartwig Anzt [TU München]).
Core-Level Performance Engineering. Half-day tutorial at SC24, Atlanta, GA, November 18, 2024 (with Jan Laukemann).
Analytic Performance Modeling for HPC Workloads. Invited talk at the Sino-German Workshop on Multiphysics Device
Simulation and Hardware-Aware Computing, Xi’An, China, October 10-16, 2024.
Core-Level Performance Engineering. Full-day on-site tutorial at PPAM 2024, the 15th International Conference on Parallel Parallel Processing and Applied Mathematics, Ostrava, Czech Republic, September 8-11, 2024.
Hardware Evolution from an HPC Point of View. Invited talk at 20 ans du Groupe Calcul, Paris, France, June 3, 2024.
Hybrid Programming in HPC – MPI+X. Three-day online tutorial at High Performance Computing Center Stuttgart (HLRS), Stuttgart, Germany, January 23-25, 2024 (Georg Hager, with Rolf Rabenseifner [HLRS] and Claudia Blaas-Schenner [TU Wien]).
A. Afzal (G. Hager): Physical Oscillator Model for Supercomputing. Short paper presentation at PMBS23, the 14th Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems, Denver, CO, November 13, 2023. Slides
A. Afzal (G. Hager): SPEChpc 2021 Benchmarks on Ice Lake and Sapphire Rapids Infiniband Clusters: A Performance and Energy Case Study. Paper presentation at PMBS23, the 14th Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems, Denver, CO, November 13, 2023. Slides
Core-Level Performance Engineering. Full-day on-site tutorial at PACT 2023, the 32nd International Conference on Parallel Architectures and Compilation Techniques, Vienna, Austria, October 21-25, 2023.
Parallelization and Efficient Programming on High Performance Computers. Five-day block course at the University of Greifswald Computing Center, Greifswald, Germany, September 21-27, 2023.
Resources for High Performance Computing at FAU. Talk at the FAU Graduate Centre, September 14, 2023 (with Jan Eitzinger).
Core-Level Performance Engineering. Full-day tutorial at ICPE 2023, the 14th ACM/SPEC International Conference on Performance Engineering, Coimbra, Portugal, April 15-19, 2023 (with Jan Laukemann).
Application Knowledge Required: Performance Modeling for Fun and Profit. Keynote at ICPE 2023, the 14th ACM/SPEC International Conference on Performance Engineering, Coimbra, Portugal, April 15-19, 2023
Annual course Parallel Programming of High-Performance Systems (PPHPS23). Three-day online course, March 7-9, 2023 (with Markus Wittmann, Ayesha Afzal, and LRZ staff).
Performance Engineering in CSE: A Bird’s-Eye View. Talk at the SIAM CSE23 Minisymposium “Performance Engineering and Applications” (MS167), Amsterdam, The Netherlands, March 1, 2023. Slides
Resources for High Performance Computing at FAU. Talk at the FAU Graduate Centre, February 16, 2023 (with Jan Eitzinger).
News from NHR@FAU – Fritz, Alex and Woody. ECAP Seminar, FAU Erlangen-Nürnberg, January 19, 2023 (with Johannes Veh).
The National High-Performance Computing Alliance and NHR@FAU: New Structures and Opportunities. Physikalisches Kolloquium, Universität Regensburg, December 19, 2022 (with Gerhard Wellein).
Hybrid Programming in HPC-MPI+X. Three-day online PRACE tutorial at Vienna Scientific Cluster (VSC), TU Wien, Austria, December 12-14, 2022 (with Rolf Rabenseifner [HLRS] and Claudia Blaas-Schenner [TU Wien]).
Resources for High Performance Computing at FAU. Talk at the FAU Graduate Centre, September 22, 2022 (with Jan Eitzinger).
Spontaneous asynchronicity: parallel programs out of lockstep. Invited talk at PPAM 2022, the 14th International Conference on Parallel Processing and Applied Mathematics, Gdansk, Poland, September 11-14, 2022. Slides
Hybrid Programming in HPC – MPI+X. Three-day online PRACE tutorial at Leibniz Supercomputing Centre (LRZ), Garching, Germany, June 22-24, 2022 (with Rolf Rabenseifner [HLRS] and Claudia Blaas-Schenner [TU Wien]).
NHR Graduate School Course Week 2022. Five-day training event for NHR Graduate School students at the Zuse-Institute Berlin (ZIB), June 13-17, 2022 (with Markus Wittmann and ZIB/TU Darmstadt staff).
Hybrid Programming in HPC-MPI+X. Three-day online PRACE tutorial at Vienna Scientific Cluster (VSC), TU Wien, Austria, April 5-7, 2022 (with Rolf Rabenseifner [HLRS] and Claudia Blaas-Schenner [TU Wien]).
Annual course Parallel Programming of High-Performance Systems (PPHPS22). Three-day online course, March 8-10, 2022 (with Markus Wittmann, Ayesha Afzal, and LRZ staff).
Modeling and tuning of SpMV and a lattice QCD kernel on the A64FX. Invited online talk at the online A64FX Symposium, Stony Brook University, Stony Brook, NY, August 12, 2021. Slides
Introduction to Hybrid Programming in HPC. Three-day online tutorial at Vienna Scientific Cluster (VSC), TU Wien, Austria, June 15-17, 2021 (with Rolf Rabenseifner [HLRS] and Claudia Blaas-Schenner [TU Wien]).
Annual course Parallel Programming of High-Performance Systems (PPHPS21). Three-day online course, April 13-15, 2021 (together with LRZ staff).
Introduction to Hybrid Programming in HPC. Two-day PRACE tutorial at High Performance Computing Center Stuttgart (HLRS), Stuttgart, Germany, January 27-28, 2020 (with Rolf Rabenseifner [HLRS], Irene Reichl, and Claudia Blaas-Schenner [TU Wien]).
Some observations on NEC Aurora Tsubasa 10B – stencils and spMVM. Talk at the NEC Aurora community meeting, ISC 2019, June 16, 2019, Frankfurt, Germany. 2019-06-16_GHa_spMVM_Stencil_Tsubasa.pdf
Von der Wettervorhersage zur Kernwaffe: Supercomputer – was sie sind und was sie können. Night of Science, Universität Frankfurt, 14. Juni 2019.
Introduction to Hybrid Programming in HPC. Two-day tutorial at Vienna Scientific Cluster (VSC), TU Wien, Austria, June 12-13, 2019 (with Rolf Rabenseifner [HLRS], Irene Reichl, and Claudia Blaas-Schenner [TU Wien]).
Introduction to Hybrid Programming in HPC. Two-day PRACE tutorial at Leibniz Supercomputing Centre (LRZ), Garching, January 28-29, 2019 (with Rolf Rabenseifner [HLRS], Irene Reichl, and Claudia Blaas-Schenner [TU Wien]).
The Execution-Cache-Memory (ECM) Performance Model. Intel Platform Performance Brown Bag Talk, October 25, 2018. Hager_BrownBag_2018.pdf
Making sense of performance numbers. Invited talk at OpenMPCon 2018, Barcelona, Spain, September 24-26, 2018. Hager_OMPCon_2018.pdf
Thirteen modern ways to fool the masses with performance results on parallel computers. GridKa School 2018, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany, August 29, 2018. FTM-GridKa18-c.pdf
Performance Engineering – Why and How?PASC MS05, Basel, Switzerland, July 2-4, 2018. PASC18_MS05_Hager.pdf
Introduction to Hybrid Programming in HPC. One-day PTC short course at HLRS Stuttgart, June 19, 2018 (with Rolf Rabenseifner, HLRS). Details and registration: https://www.hlrs.de/training/2018-06-19-hy-s/
Von der Wettervorhersage zur Kernwaffe: Supercomputer – was sie sind und was sie können. Night of Science, Universität Frankfurt, 8. Juni 2018.
Annual course on “Parallel Programming of High Performance Systems“, RRZE, March 12-16, 2018 (together with LRZ staff).
“If it doesn’t work, we learn something.” Instructive case studies from performance engineering. Minisymposium MS29 at SIAM PP18, the 2018 Conference on Parallel Processing, March 8, 2018, Tokyo, Japan. PP18MS29_Hager.pdf
Parallelization and Efficient Programming of High Performance Computers. Five-day block course at the Institute of Physics, University of Greifswald, September 25-29, 2017.
The curses and blessings of analytic performance modeling. Invited talk at PPAM‘2017, the 12th International Conference on Parallel Processing and Applied Mathematics, Lublin, Poland, September 10-13, 2017. PPAM17_Hager.pdf
MPI+X – Hybrid Programming on Modern Compute Clusters with Multicore Processors and Accelerators. One-day PATC short course at HLRS Stuttgart, June 12, 2017 (with Rolf Rabenseifner).
Supercomputer: Mächtiges Werkzeug und Forschungsobjekt. Night of Science, Universität Frankfurt, 9. Juni 2017. 2017-06-09_NoS.pdf (in German). Video recording
Thirteen modern ways to fool the masses with performance results on parallel computers. Evening talk at the Course on “Parallel Programming of High Performance Systems 2017”, LRZ Garching, March 6-10, 2017.
Annual course on “Parallel Programming of High Performance Systems“, LRZ Garching, March 6-10, 2017 (together with Markus Wittmann, Volker Weinberg, and others).
Making sense of temporally blocked stencil performance via analytic modeling. Invited talk at the 7th AICS International Symposium, Integrated Research Center of Kobe University, Kobe, Japan, February 23-24, 2017. AICS17_Hager.pdf
Annual course on “Parallel Programming of High Performance Systems“, RRZE, March 7-11, 2016 (together with Markus Wittmann, Volker Weinberg, and others).
Efficient multicore programming. Lecture series together with G. Wellein at the Ohm University of Applied Sciences, Nuremberg, February 29-March 3, 2016.
What role does software play in energy efficiency? Panel kick-off talk at the workshop on Energy-Efficient Supercomputing (E2SC 2015) at SC15, Austin, TX, November 15, 2015. E2SC15_Panel_Hager.pdf
Holistic node-level performance engineering for maximum resource efficiency on modern multi-core CPUs. Talk at ParisTech TELECOM, Paris, France, September 7, 2015. Hager_ParisTech.pdf
Model-guided performance engineering of numerical kernels. Invited talk at the meeting of the SFB Transregio 55 “Hadron Physics from Lattice QCD,” University of Wuppertal, Germany, July 10, 2015. Hager_Analytic_PM_BUW_15.pdf
White-box modeling for performance and energy: Useful patterns for resource optimization. Invited lecture at PACO 2015, the Workshop on Power-Aware Computing, Max Planck Institute for Dynamics of Complex Technical Systems, Magdeburg, Germany, July 6-7, 2015. PACO-PE.pdf
Quantifying performance bottlenecks of stencil computations using the Execution-Cache-Memory model. Talk at ICS’15, the 29th ACM International Conference on Supercomputing, June 8-11, 2015, Newport Beach, CA. ICS15_Hager.pdf
Annual course on “Parallel Programming of High Performance Systems“, LRZ Garching, March 9-13, 2015 (together with Markus Wittmann, Volker Weinberg, and Carla Guillen Carias).
Node-Level Performance Engineering. Two-day tutorial at the second “SPPEXA Doctoral Retreat”, Sarntal, South Tyrol, September 22-26, 2014 (together with Gerhard Wellein).
Node-Level Performance Engineering. Two-day short course at the Summer School for Modern Computational Science (MCS 2014), University of Oldenburg, September 4-5, 2014.
Node-Level Performance Engineering. Full-day tutorial at the International Supercomputing Conference (ISC14), Leipzig, Germany, June 22-26, 2014 (with Jan Treibig and Gerhard Wellein).
Basic performance modeling for numerical applications: Roofline and beyond. Lecture at the SPPEXA PhD seminar, University of Erlangen-Nuremberg, April 30, 2014. Roofline_ECM_SPPEXA_PhD_2014.pdf
Performance-oriented programming on multicore-based systems, with a focus on the Cray XE6 and XC30. One-day PATC tutorial at the Cray XE6/XC30 optimization workshop, HLRS Stuttgart, March 20, 2014 (together with Jan Treibig). Cray_MC_SS_2014.pdf
Annual course on “Parallel Programming of High Performance Systems“, RRZE, March 10-14, 2014 (together with Markus Wittmann, Jan Treibig, Volker Weinberg, and Carla Guillen Carias).
Sparse Matrix-Vector Multiplication with Wide SIMD Units: Performance Models and a Unified Storage Format. Invited talk at Minisymposium MS53 on “Sparse Computations on Accelerators” at the SIAM Conference on Parallel Processing for Scientific Computing 2014 (PP14), Portland, OR, Feb 18-21, 2014. SELL-C-sigma.pdf
Efficient multicore programming. Lecture series together with G. Wellein at the Ohm University of Applied Sciences, Nuremberg, Feb 25-28, 2014.
Node-Level Performance Engineering. Full-day tutorial at the first “SPPEXA Doctoral Retreat”, TU Darmstadt, September 16-20, 2013 (together with Gerhard Wellein).
More Science per Joule: Bottleneck Computing. Invited talk at the 10th International Conference on Parallel Processing and Applied Mathematics (PPAM 2013), Warsaw, Poland, September 8-11, 2013. PPAM13_Hager_Invited.pdf
Node-Level Performance Engineering. Half-day tutorial at the 10th International Conference on Parallel Processing and Applied Mathematics (PPAM 2013), Warsaw, Poland, September 8-11, 2013.
Node-Level Performance Engineering. Full-day tutorial at the International Supercomputing Conference (ISC13), Leipzig, Germany, June 16-20, 2013 (with Jan Treibig and Gerhard Wellein).
Performance-oriented programming on multicore-based systems, with a focus on the Cray XE6. One-day PATC tutorial at the Cray XE6 optimization workshop, HLRS Stuttgart (together with Jan Treibig)
News about LIKWID. Talk at ZKI AK Supercomputing, University of Paderborn, Parallel Computing Center, March 15, 2013, Paderborn, Germany. Hager_ZKI_Maerz13_LIKWID.pdf
Node-level performance engineering. Two-day short course (together with Gerhard Wellein and Moritz Kreutzer) at DLR Köln, March 13-14, 2013, Cologne, Germany.
Performance engineering on multi-and manycores. Half-day tutorial at the 3rd Saudi-Arabian HPC Users Conference (SAHPC 2012) at King Abdullah University of Science and Technology (KAUST), December 1-3, 2012, Thuwal, Saudi-Arabia.
Performance patterns and hardware metrics on modern multicore processors: Best practices for performance engineering. Talk at PROPER 2012, the 5th Workshop on Productivity and Performance, at Euro-Par 2012, Rhodes Island, Greece, August 28, 2012. Hager-PROPER12-paper.pdf
Performance Engineering: From Numbers to Insight. Invited talk at PROPER 2012, the 5th Workshop on Productivity and Performance, at Euro-Par 2012, Rhodes Island, Greece, August 28, 2012. Hager-PROPER12-invited.pdf
Performance Engineering for Multi- and Manycores: Unveiling the Mysteries of Application Performance. Invited session “Application Performance: Lessons Learned From Petascale Computing” at ISC12, Hamburg, Germany, June 18, 2012. Hager-ISC12.pdf
Performance-oriented programming on multicore-based systems. Tutorial at the NUG 2012 Meeting, Potsdam, Germany, June 12, 2012 (together with R. Fischer). RRZE-Multicore.pdf
Teaching High Performance Computing to Scientists and Engineers: A Model-Based Approach. Award talk at the 7th European Computer Science Summit, Politecnico di Milano, Milan, Italy, November 7-9, 2011. IEAward.pdf
Final report on KONWIHR project HQS@HPC-II. KONWIHR Results and Review Workshop, LRZ Garching, October 12, 2011.
Parallel Programming of Multi- and Manycore Systems. Block lecture together with G. Wellein at the Ohm University of Applied Sciences, Nuremberg, September 26-30, 2011.
Monitoring, Accounting und Nutzerverwaltung auf den HPC-Systemen des RRZE. Talk at the ZIH Kolloquium, TU Dresden, August 25, 2011. ZIH_110825.pdf
Prospects for Truly Asynchronous Communication with Pure MPI and Hybrid MPI/OpenMP on Current Supercomputing Platforms. Talk at the Cray User Group Conference 2011, May 23-26, 2011, Fairbanks, AK. Hager-Slides-CUG11.pdf
Parallel sparse matrix-vector multiplication as a test case for hybrid MPI+OpenMP programming. Talk at the 2011 Workshop on Large-Scale Parallel Processing (LSPP 2011), May 20, 2011, Anchorage, AK. Hager-Slides-LSPP11.pdf
Thirteen modern ways to fool the masses with performance results on parallel computers. Evening talk at the Course on “Parallel Programming of High Performance Systems 2011”, LRZ Garching, March 7-11, 2011.
Annual course on “Parallel Programming of High Performance Systems“, RRZE, March 2010 (together with Jan Treibig, Markus Müller, and Reinhold Bader).
Hybrid applications on modern architectures: Things to consider. Invited talk at the SIAM Conference on Parallel Processing for Scientific Computing (PP10), February 24-26, 2010, Seattle, WA. hager-pp10.pdf
Lecture series “Efficient multi-core programming“ together with G. Wellein at the Ohm University of Applied Sciences, Nuremberg, Feb 8-10, 2010.
Wavefront Parallel Temporal Blocking on Multi-Core Processors with Shared Caches. Los Alamos National Laboratory, Performance Architecture Lab (PAL), August 26th, 2009. lanl-pal-2009-08-26.pdf
C++ for C and Fortran programmers. Four-day tutorial at CD-Adapco, Nuremberg, March 16-19, 2009.
Annual course on “Parallel Programming of High Performance Systems“, LRZ Garching, February 2009 (together with Reinhold Bader).
Hybrid MPI/OpenMP Parallel Programming on Clusters of Multi-Core SMP Nodes. Talk at the 17th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP 2009), February 18-20, 2009. mpi_openmp_pdp09.pdf
Annual course on “Parallel Programming of High Performance Systems“, RRZE, March 2008 (together with Reinhold Bader).
Effiziente Nutzung von Hochleistungsrechnern in der numerischen Strömungsmechanik.NUMET-Kurzlehrgang, 10.-13.03.2008, LSTM, Universität Erlangen numet_hager_08.pdf
Windows Compute Cluster Server 2003 Evaluation. ZKI AK Supercomputing, Oct 25th, 2007, GWDG Göttingen zki_winccs_07.pdf
Sun UltraSPARC T2 – First Tests. SunDay at RRZE, Nov 6th, 2007. rrze-n2-ea.pdf
Performance Evaluation of Current HPC Architectures Using Low-Level and Application Benchmarks. HLRB2/KONWIHR Result and Review Workshop, Dec 3rd, 2007, LRZ. hzsw-hlrb07.pdf
2006
Why is performance productivity poor on modern architectures? Talk with Jan Treibig at the Dagstuhl Seminar on Petacomputing, Feb 13-17, 2006, Dagstuhl performance_productivity.pdf
Effiziente Nutzung von Hochleistungsrechnern in der numerischen Strömungsmechanik.NUMET-Kurzlehrgang, 13.-16.03.2006, LSTM, Universität Erlangen numet06_hager.pdf
Erfahrungen und Benchmarks mit Dual-Core Prozessoren. ZKI AK Supercomputing, Karlsruhe, 22.09.2005 zki2_05_dualcore.pdf
Betrieb eines heterogenen Clusters. ZKI AK Supercomputing, Karlsruhe, 23.09.2005 zki2_05_cluster.pdf
Benchmarks on Current Dual Core CPUs (and some comments on OpenMP, C++, Tools etc.). Video conference with ZIH Dresden, Oct 10, 2005 vk_201005.pdf
2004
Investigation of Stripe Formation in Hubbard Ladders using Parallel DMRG. KONWIHR result and review workshop, March 2-3, 2004, TU Munich hqshpc_04.pdf
Application Performance: Altix vs. the Rest. SGI User Group Conference, May 24-27, 2004, Orlando, Florida hager_sgi04.pdf
Intel VTune für Linux. Videokonferenz mit HLRS, 14.07.2004, RRZE vtune2_04.pdf
2003
Parallelization Strategies for Density Matrix Renormalization Group Algorithms on Shared-Memory Systems. Informal DMRG workshop, May 7-9 2003, RRZE dmrg03.pdf
Writing Efficient Programs in Fortran, C and C++: Selected Case Studies. Workshop on efficient HPC programming, July 21st 2003, LRZ cases_03.pdf
Introduction to IA32 and IA64: Architectures, Tools and Libraries. Workshop on Parallel Programming for High Performance Computers, Oct 13-17 2003, RRZE intel_architectures_03.pdf
2002
Paralleles Rechnen in der Physik. Kolloquium zur Physik-Didaktik, Universität Erlangen, 07.05.2002 phydid-070502.pdf