Computational Science and Engineering Malik Ghallab April 2013 - PowerPoint PPT Presentation

LIG, Grenoble Computational Science and Engineering Malik Ghallab April 2013

Centuries of craftsmanship development M. Al Khawarizmi 780 - 850 Tycho Brahe J. Kepler 1546 - 1601 1571 - 1630 S.Hawking E. Hubble 1889 - 1953 2

Centuries of craftsmanship development C. Ptolemy 90 - 168 A. Einstein 1879 - 1955 G. Galileo 1564 - 1642 I. Newton 1642 - 1727 3

Centuries of craftsmanship development Past methods ‣ Data: notebooks, few Kb ‣ Computation: by hand, few flops ‣ Theory: driven by data and computation ‣ Team: 1 bright scientist, few students In Gravitational Physics: - Centuries of small science, small data culture - Few decades of radical change [E. Seidel, NSF] 4

Few decades of radical change Unprecedented growth in ‣ Computation ‣ Data handling ⤴ 10 9 – 10 12 ‣ Communication ‣ Sensing Large Synoptic Survey Telescope: 40 TBytes/night 5

Few decades of radical change Allow science and engineering to address complex challenges ‣ Involving • Numerous coupled phenomena • Widely dissimilar entities and interactions ‣ Requiring very fine views of microscopes and telescopes as well as global integrative views of “ macroscopes ” ‣ Supporting difficult decisions We seek solutions. We don’t seek – dare I say this ? – just scientific papers anymore. [S. Chu, DoE] 6

Outline ✓ Motivations ‣ Ingredients of Computational Science & Engineering 1. Modeling, simulation and computing 2. Instrumentation, sensing and imaging 3. Massive data processing ‣ Impacts of Computational Science & Engineering ‣ Conclusion 7

Ingredients of Computational Science & Engineering New engines of science and technology 1. Computational modeling, simulation and computing 2. Instrumentation, sensing and imaging 3. Massive data processing, mining, analyzing, learning and visualizing Converging conceptual and practical set of tools 8

1. Modeling, Simulation, Computing Methodology ‣ Building computational models of a system or a phenomenon ‣ Analyzing properties of models ‣ Contrasting models to reality: identification, estimation, learning ‣ Designing algorithms and computational schema, parallelization, distribution ‣ Simulation scenarios ‣ Control, optimization What’s new ? 9

1. Modeling, Simulation, Computation What’s new ? Scaling-up : from 10 3 flops to 10 15 flops a) PROJECTED PERFORMANCE DEVELOPMENT 162 1 E flop/s P flop/s 100 P flop/s 17.6 10 P flop/s P flop/s SUM 1 P flop/s N =1 100 T flop/s 76.5 T flop/s 1.17 10 T flop/s T flop/s N =500 1 T flop/s 59.7 G flop/s 100 G flop/s 10 G flop/s 0.4 G flop/s 1 G flop/s 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 [Top 500 Project] 10

1. Modeling, Simulation, Computation What’s new ? Scaling-up : from 10 3 flops to 10 15 flops a) b) Integration of multiple heterogeneous models • Complex problems involve the interaction of several phenomena • Each phenomenon has to be addressed not in isolation but coupled with all relevant interacting effects ➡ Integration of heterogeneous mathematical formalisms : differential, geometric, deterministic, stochastic, combinatorial into algorithms and software components ➡ Composition of elementary components to buildup increasingly more complex and encompassing models 11

Metaphor [D.Sticker, DFKI] 12

Metaphor [D.Sticker, DFKI] 13

Environment modeling [D.Sticker, DFKI] 14

1. Modeling, Simulation, Computation What’s new ? Scaling-up : from 10 3 flops to 10 15 flops a) b) Integration of multiple heterogeneous models c) Universal scope The book of the universe is written in mathematics. [Galileo, Il Saggiatore , 1623] The Galileo vision applied to an exception: only the inanimate world could be written in mathematics. This exception does not hold anymore. But the Galileo model has changed. Nature is written in algorithmic language . [M.Serres, Hominescence , 2001] 15

Outline ✓ Motivations ‣ Ingredients of Computational Science & Engineering 1. Modeling, simulation and computing 2. Instrumentation, sensing and imaging 3. Massive data processing ‣ Impacts of Computational Science & Engineering ‣ Conclusion 16

2. Instrumentation, Sensing, Imaging Methodology ‣ Sense, acquire, measure ground facts and evidence to support science ‣ Over broad spectrum of scales ‣ Over broad spectrum of phenomena and units What’s new ? 17

2. Instrumentation, Sensing, Imaging What’s new ? • Scale-up • Integration • Scope + a) Low-cost massive production b) Signal processing and intelligent sensor fusion techniques c) Distributed, mobile and widely flexible sensors d) Communicating sensors 18

2. Instrumentation, Sensing, Imaging Smart dust [K. Pister, Berkeley] 19

2. Instrumentation, Sensing, Imaging Floating sensor network [A. Bayen, Berkeley] 20

2. Instrumentation, Sensing, Imaging Cell scope [D. Fletcher, Berkeley] 21

Instrumentation, Sensing, Imaging DNA sequencing [NHGRI] 22

Instrumentation, Sensing, Imaging 23

Outline ✓ Motivations ‣ Ingredients of Computational Science & Engineering 1. Modeling, simulation and computing 2. Instrumentation, sensing and imaging 3. Massive data processing ‣ Impacts of Computational Science & Engineering ‣ Conclusion 24

3. Massive Data Processing Methodology ‣ Collect, organize, curate ‣ Compare, associate, cluster into categories ‣ Visualize ‣ Correlate, associate into relations ‣ Interpret, generalize into knowledge What’s new ? 25

3. Massive Data Processing What’s new ? a) Scaling-up : from 10 3 Bytes to 10 18 Bytes [Lesks, Berkeley SIMS, Landauer EMC] 26

3. Massive Data Processing What’s new ? Scaling-up : from 10 3 flops to 10 15 flops a) b) Integration of data • From sensors • From simulations • From broad ranges of phenomena • Over wide space and extended time 27

Ocean Temperature Rise +2.0 �������� 0 –2.0 �� 1910 1930 1950 1970 1990 2010 ���������������� ��������������� ������������� ����������������� ����������������� ����������� +1.0 �� ��������������������� ��������������� ������������� ������������ ���������������� ������������� +0.5 �� ������������ Atlantic 0 ������ –0.5 �� Margin of error Global Below the Waves: Heating [Scientific American, April 2013]

3. Massive Data Processing What’s new ? Scaling-up : from 10 3 flops to 10 15 flops a) b) Integration of data • From sensors • From simulations • From broad ranges of phenomena • Over wide space and extended time • Over masses of “ prosumers” 29

“Prosumers” DARPA Red Balloon Challenge : 40 K$ Find GPS positions of 10 meteorologic balloons deployed randomly over continental US on Dec. 12, 2009, from 10:00 to 16:00 1 st : MIT at 18:52 30

3. Massive Data Processing What’s new ? a) Scaling-up b) Integration c) Automated processing and interpretation capabilities • Automated search, mining • Visualization 31

Data Visualization [LRI-INRIA] 32

3. Massive Data Processing What’s new ? a) Scaling-up b) Integration c) Automated processing and interpretation capabilities • Automated search, mining • Visualization • Machine learning techniques 33

Supervised learning Frêne Arbre de Judée Figuier Chêne Noisetier Cotinus [Pl@ntNet] 34

Action recognition in images Climbing 35

Action recognition in images Reading Cooking [Stanford Images test database] Phoning 36

3. Massive Data Processing What’s new ? a) Scaling-up b) Integration c) Automated processing and interpretation capabilities • Automated search, mining • Machine learning techniques Data ➙ Facts ➙ Knowledge • Semantic association Living organisms function according to protein circuits. Darwin’s theory of evolution suggests that these circuits have evolved through variation guided by natural selection. The question of which circuits can so evolve in realistic population sizes and within realistic numbers of generations has remained essentially unaddressed. [Leslie Valiant] 37

CSE Engines Modeling Instrumentation Simulation Sensing Computing Imaging Knowledge Innovation Massive Data Curating, Structuring Mining, Learning 38

Outline ✓ Motivations ✓ Ingredients 1. Modeling, simulation and computing 2. Instrumentation, sensing and imaging 3. Massive data processing ‣ Impacts • Health and Life sciences • Earth and Environmental sciences • Physics, chemistry, material sciences • Engineering • Humanities and social sciences ‣ Conclusion 39

Health and Life Sciences [CardioSence3D, Inria] 40

Health and Life Sciences Therapy planning anatomy Personalization electro-physiology blood flow Diagnosis perfusion solid mechanics & metabolism Clinical Cardiac data Cardiac modeling applications [CardioSence3D, Inria] 41