Real World Applications on Massively Parallel Environments

Size: px

Start display at page:

Download "Real World Applications on Massively Parallel Environments"

Erin Tucker
5 years ago
Views:

1 SC12 Nov th, 2012 Real World Applications on Massively Parallel Environments YAMAZAKI, Takashi, Ph.D. Application R&D Division Next Generation Technical Computing Unit Fujitsu Ltd.

2 Contents of Presentation Introduction Industry: Electromagnetic field simulator Environment: Tsunami simulator Healthcare : Heart simulator Conclusion 1

Introduction Aims Effective utilization of

prepare for and protect against disaster

new material - energy saving Health care -

3 Introduction Aims Effective utilization of HPC Broaden the possibilities of HPC Practical applications Environment - prediction and prevention of disaster - prepare for and protect against disaster Application Areas Industry - new product - new material - energy saving Health care - aid diagnosis - personalized therapy - efficient drug trial 2

4 Industry: Electromagnetic field simulator i. Design of Motor ii. Efficiency Improvement of Magnet 3

5 Energy Saving Design of Motor Motors consume almost half of the generated electric power The same tendency is also observed globally IT 5% other 15% heater 10% light 14% motor 56% 570 TWh in Japan (2009, Fuji-Keizai) 1% more efficient 4 Saving One thermal plant

Mx/Ms Coupling of Simulation of Two Scales

design of products realized micro-magnetics

analysis: FEM (deformation & current) 1 0.

6 Mx/Ms Coupling of Simulation of Two Scales Highly precise magnetic field analysis for design of products realized micro-magnetics hysteresis model (material property) EM analysis: FEM (deformation & current) weakly coupling Magnetic Field (A/m) hysteresis loop magnetization FEM analysis result 5

reversal: the phenomenon which direction of magnetization reverses

7 Rare Earth Magnet Analysis Magnetic reversal* process of rare earth magnet analyzed with 3-D micromagnetics simulation *magnetic reversal: the phenomenon which direction of magnetization reverses by direction of an external magnetic field. mesh size < 1nm 8~10 nm 6

8 Environment: Tsunami simulator This whole project is a collaboration with Prof. Imamura of IRIDeS, Tohoku University 7

9 Prevention of Tsunami Disaster Mar., 11th, 2011 M9 earthquake & historic tsunami Over 19,000 victims Target Tsunami-proof design of buildings Escape planning Preliminarily enlightening on the danger City planning Tolerability of evacuation cites or public buildings This movie is for the demonstration of the simulation technique, not for prediction of actual tsunami damage. 8 The Digital terrain data is provided by GEO Technology Laboratory Co., Ltd.

Inundation analysis w/o overdamping Re-examination

10 For Safety Urban Planning 1. Calculation of wave stress Formulation of tsunami-proof intensity standard Tsunami-proof design 2. Inundation analysis w/o overdamping Re-examination of dikes Escape planning Hazard analysis Preliminarily enlightening on the danger Tolerability of evacuation cite or public building 9

Breaking Wave on Surface Surface motion at an

Murakami, Mase (2002) Proc. Coast. Eng., 49, 41.

11 Breaking Wave on Surface Surface motion at an artificial reef casea4 W6 SPH 水槽実験 The time series of wave height matches the experimental data. The source of the experimental data is Oki, Murakami, Mase (2002) Proc. Coast. Eng., 49, 41. wave breaking wave reforming simulation 10 The hydraulic experiment is performed by Prof. Murakami of Univ. of Miyazaki.

Combination of 2-D & 3-D Simulations Seamless 3-D simulation from the epicenter to

Shallow-water model (2-D) for broad area The Digital terrain data is provided by

Imamura of Tohoku Univ. CG made by the collaboration with Bosai Tech Consultants.

12 Combination of 2-D & 3-D Simulations Seamless 3-D simulation from the epicenter to an urban area tsunami simulator SPH method (3-D) for small area combine Shallow-water model (2-D) for broad area The Digital terrain data is provided by GEO Technology Laboratory Co., Ltd. Simulation performed by Porf. Imamura of Tohoku Univ. CG made by the collaboration with Bosai Tech Consultants. calculation of wave tsunami propagation. inundation in urban areas stress to buildings from epicenter 10m 1km 100km 11

13 Healthcare: Heart simulator [UT-Heart] This work is a collaboration with Prof. Hisada and Prof. Sugiura of the University of Tokyo and Fujitsu Limited 12

14 For Personalized Therapy CVD (cardiovascular disease) One of the leading causes of death Computer aided therapy Personalized therapy Efficient drug discovery 13

Multiphysics Multiscale & Multiphysics mechanics Biochemistry Bioelectricity Glucose glycolysis Lactate ATP cross bridge Membrane protein

15 Multiphysics Multiscale & Multiphysics mechanics Biochemistry Bioelectricity Glucose glycolysis Lactate ATP cross bridge Membrane protein sarcomere Na + Ca ++ K + Tension cardiac myocyte Action potential Multiscale P-V loop ECG molecule Cell tissue organ human 10-9 m 10-4 m 10-2 m 10 0 m 14

16 Electrocardiogram (ECG) Comparison of ECG measurement between heart simulator and human heart observed simulated Cardiac Excitation Potential Distribution on torso surface Lead II ECG 15

17 Ventriculoplasty Left Ventricular Pressure [KPa] Virtual surgical treatment Diseased heart Virtual operation Following virtual therapy modest 2 pressure-volume looop : -: -: excision sutura Left Ventricular Volume[cc] Ventricular aneurysm after myocardial infarction radical EF: Ejection Fraction. EF represents the strength of pumping function of heart. Defined as (end-diastolic volume end-systolic volume) / (end-diastolic volume) EF

18 Multiscale Analysis For the personalized therapy in medical domain As a bridge between molecular biology and clinical application multiscale simulation micro molecule cell tissue organ macro EC-coupling metabolism, sarcomere dynamics structural dynamics by FEM contraction force homogenization method FSI by FEM circulation 17

Speed-up ratio Scalability and Performance on "K computer" Succeeded in simulating 1.5 heartbeats lasting about 17 hours and using 602,112 cores.

4 3 2 1 0 close to the ideal slope strong scalability Ideal 49k DOF 0 50000 100000 #Nodes #Nodes 20,736 41,472 82,944 Pflops 0.78 1.49 2.

19 Speed-up ratio Scalability and Performance on "K computer" Succeeded in simulating 1.5 heartbeats lasting about 17 hours and using 602,112 cores. Achieved more than 90% of the ideal scaling and 27.7% of the peak performance using 20,736/41,472/82,944 nodes with 659,456 embedded numerical cells of and 49,248 DOFs close to the ideal slope strong scalability Ideal 49k DOF #Nodes #Nodes 20,736 41,472 82,944 Pflops % of the peak performance % of the ideal scaling Present results were obtained by early access to the "K computer" at RIKEN AICS as a "grand challenge application under the "R&D of Next-Generation Integrated Life-Science Simulation Software" program supported by MEXT. 18

20 Conclusion FUJITSU has been developing the HPC applications for practical use Effective utilization of HPC Broaden the possibilities of HPC Practical applications Some of these were introduced. Tsunami simulator based on article method for disaster prevention From the epicenter to the urban area FEM based Electromagnetic field simulator for industry Coupled with micromagnetics simulator Optimization in macroscopic quantities possible, taking into account of the effect of micro magnetics FEM based human heart simulator (UT-Heart) for personalized medical therapy Multiscale & multiphysics heart simulator Possibilities of use to aid diagnosis not only in surgery but also in a medical domain for personalized medical treatment Achieved more than 90% of the ideal scaling and 27.7% of the peak performance on "K computer" 19

Post K Supercomputer of. FLAGSHIP 2020 Project. FLAGSHIP 2020 Project. Schedule

Post K Supercomputer of. FLAGSHIP 2020 Project. FLAGSHIP 2020 Project. Schedule Post K Supercomputer of FLAGSHIP 2020 Project The post K supercomputer of the FLAGSHIP2020 Project under the Ministry of Education, Culture, Sports, Science, and Technology began in 2014 and RIKEN has