Aerodynamics of a hi-performance vehicle: a parallel computing application inside the Hi-ZEV project

Size: px
Start display at page:

Download "Aerodynamics of a hi-performance vehicle: a parallel computing application inside the Hi-ZEV project"

Transcription

1 Workshop HPC enabling of OpenFOAM for CFD applications Aerodynamics of a hi-performance vehicle: a parallel computing application inside the Hi-ZEV project A. De Maio (1), V. Krastev (2), P. Lanucara (3), F. Salvadore (3) (1) Nu.m.i.d.i.a. S. r. l. (2) Dept. of Industrial Engineering, University of Rome Tor Vergata (3) CINECA Roma, Dipartimento SCAI

2 Summary Hi-ZEV project outline Preliminary evaluation of the OpenFOAM code Prototype car simulations: aerodynamic results and scalability/performance tests Conclusions

3 Hi-ZEV: a collaborative industrial research project Granted by the Italian Ministry of Economic Development s program «Industria 2015 Nuove Tecnologie per il Made in Italy» The project aim is the development of an Innovative High Performance Car with Low Environmental Impact based on an Electrical/Hybrid Powertrain The project started on 01/01/2011 and will last until 31/12/2013

4 Hi-ZEV: the partners Technos Reat Fondazione Italiana Nuove Comunicazioni Icomet Microsistemi srl Elettromedia Advanced Devices spa Dyesol Italia srl Leaff Engineering srl ISAM spa Concept Inn srl HPH Consulting

5 Hi-ZEV: the partners Team Leader and Project Coordinator Technos Reat Fondazione Italiana Nuove Comunicazioni Icomet Microsistemi srl Elettromedia Advanced Devices spa Dyesol Italia srl Leaff Engineering srl ISAM spa Concept Inn srl HPH Consulting

6 Hi-ZEV: the partners Team Leader and Project Coordinator Technos Reat Fondazione Italiana Nuove Comunicazioni Icomet Microsistemi srl Elettromedia Advanced Devices spa Dyesol Italia srl Leaff Engineering srl ISAM spa Concept Inn srl HPH Consulting

7 Hi-ZEV: technical Key Points Very light vehicle (low weight/power ratio) High performance Hybrid Powertrain for a wide range torque availability Very advanced chassis and suspensions for an excellent road-holding Accurate Fluid-Dynamic Design

8 Hi-ZEV: technical Key Points Very light vehicle (low weight/power ratio) High performance Hybrid Powertrain for a wide range torque availability Very advanced chassis and suspensions for an excellent road-holding Accurate Fluid-Dynamic Design CFD

9 The role of CFD inside the project In the early, as well as in the more advanced design stages, CFD can be effectively used to optimize: 1. the external aerodynamics of the vehicle; 2. the underhood aerodynamics/thermal management; 3. The HVAC systems. OpenFOAM + HPC CFD The combination of an open source fully parallelized code (OpenFOAM ) with the the HPC infrastructure of CASPUR/CINECA represents an incredibly powerful and efficient answer to these needs. External aerodynamics Underhood HVAC

10 Preliminary simulations on the Matrix cluster Preliminary evaluation of OpenFOAM on the Matrix infrastructure Standard external aerodynamics test case (Ahmed body) 8 cores x node (2 x quad core AMD Opteron 2.1 GHz) 320 nodes with 16 GB RAM each Infiniband DDR connection between nodes 20 Tflops peak perfomance, 177 Mflops/W sustained performance OpenFOAM OpenMPI Scotch for decomposition Steady state solver (simplefoam) on unstructured grids (up to 6*10 6 cells) High-Re RANS turbulence modeling (RNG/realizable k-e + WF) Up to 256 cores (32 nodes) involved

11 Preliminary simulations on the Matrix cluster: computational domain

12 Ahmed body results: wake flow structures, ϕ=25 Symmetry plane 3D (Q- criterion, Q=1 0 4 s - 2 ) (RKE) (RNG)

13 Ahmed body results: wake flow structures, ϕ=25 Symmetry plane 3D (Q- criterion, Q=1 0 4 s - 2 ) (RKE) (RNG)

14 Ahmed body results: wake flow structures, ϕ=25 Symmetry plane 3D (Q- criterion, Q=1 0 4 s - 2 ) (RKE) (RNG)

15 Ahmed body results: wake flow structures, ϕ=35 Symmetry plane 3D (Q- criterion, Q=1 0 4 s - 2 ) (RKE) (RNG)

16 Ahmed body results: wake flow structures, ϕ=35 Symmetry plane 3D (Q- criterion, Q=1 0 4 s - 2 ) (RKE) (RNG)

17 Ahmed body results: velocity profiles in the symmetry plane ϕ=25 ϕ=35

18 Ahmed body results: velocity profiles in the symmetry plane ϕ=25 ϕ=35

19 Ahmed body results: integrated rear pressure drag Overall comparison: Comments: Rear pressure drag coefficients (ϕ =25) Total Difference (%)* Slant Base RKE RNG Lienhart et al Rear pressure drag coefficients (ϕ =35) Total Difference (%)* Slant Base RKE RNG Lienhart et al Results are aligned with previous CFD studies on the 25 /35 configurations The realizable k-ε captures fairly well the relative drag reduction (~ 8%) in the 25 to 35 passage

20 Ahmed body results: some considerations about scalability Case description: Finest grid (~6*10 6 cells) PCG linear solver on pressure equation cores ( nodes) progression Speedup specific efficiency (%) Speedup specific efficiency Nodes increase sse... = speedup relative increase nodes relative increase

21 Ahmed body results: some considerations about scalability Case description: Speedup specific efficiency Finest grid (~6*10 6 cells) PCG linear solver on pressure equation cores ( nodes) progression Almost linear inter-node scaling (at least in the considered interval) Speedup specific efficiency (%) Aaaaaaa Nodes increase

22 Prototype car simulations Aims: 1. Aerodynamic optimization of the Hi-ZEV prototype external design; 2. More systematic scalability tests on the CASPUR/CINECA HPC infrastructures. Two hybrid (prisms+tetras) grids considered: *10 6 cells (symmetric); 2. 15*10 6 cells (complete geometry). Matrix (AMD Opteron) 8 cores x node (2 x quad core AMD Opteron 2.1 GHz) 320 nodes with 16 GB RAM each Infiniband DDR connection between nodes 20 Tflops peak perfomance, 177 Mflops/W sustained performance OpenFOAM Scotch Three architectures selected for the performance tests

23 Prototype car simulations Aims: 1. Aerodynamic optimization of the Hi-ZEV prototype external design; 2. More systematic scalability tests on the CASPUR/CINECA HPC infrastructures. Two hybrid (prisms+tetras) grids considered: *10 6 cells (symmetric); 2. 15*10 6 cells (complete geometry). Jazz (Intel Xeon) 12 cores x node (2 x six-core Intel X GHz ) 16 nodes with 48 GB RAM each Infiniband QDR connection between nodes 14.3Tflops peak perfomance, 785 Mflops/W sustained performance OpenFOAM Scotch Three architectures selected for the performance tests Each node equipped also with 2 nvidia Tesla GPU computing units, not involved in the OpenFOAM simulations

24 Prototype car simulations Aims: 1. Aerodynamic optimization of the Hi-ZEV prototype external design; 2. More systematic scalability tests on the CASPUR/CINECA HPC infrastructures. Two hybrid (prisms+tetras) grids considered: *10 6 cells (symmetric); 2. 15*10 6 cells (complete geometry). Fermi (BG/Q) 16 cores x node (IBM 1.6 GHz) nodes ( cores) with 16 GB RAM each (1 GB x core) Network interface with 11 links ->5D Torus 2 Pflops peak perfomance OpenFOAM Scotch Three architectures selected for the performance tests

25 Prototype car simulations: computational domain half car top outlet moving floor inlet side symmetry plane

26 Prototype car simulations: aerodynamic results (OF vs. Fluent) OpenFOAM settings: Symmetrical prism/tetra grid (exactly the same for both codes) simplefoam pressure-based solver Realizable k-ε for turbulence + standard WF TVD scheme for momentum convection, upwind for k/ε Fluent settings: Symmetrical prism/tetra grid (exactly the same for both codes) pressure-based solver Realizable k-ε for turbulence + nonequilibrium WF Second-order upwind scheme for all convective terms

27 Prototype car simulations: aerodynamic results (OF vs. Fluent) Aerodynamic coefficients OpenFOAM Fluent C d = 0.32, C L = 0.14 C d = 0.31, C L = 0.17

28 Prototype car simulations: aerodynamic results (OF vs. Fluent) Pressure distribution around the car, y=0 (symmetry plane) C p = p p 1 ρ U 2 2 Fluent, 6000 iterations C p p p = 1 ρ U 2 2 OpenFOAM, 4500 iterations

29 Prototype car simulations: aerodynamic results (OF vs. Fluent) Pressure distribution around the car, y= C p = p p 1 ρ U 2 2 Fluent, 6000 iterations C p p p = 1 ρ U 2 2 OpenFOAM, 4500 iterations

30 Prototype car simulations: aerodynamic results (OF vs. Fluent) Pressure distribution around the car, y= C p = p p 1 ρ U 2 2 Fluent, 6000 iterations C p p p = 1 ρ U 2 2 OpenFOAM, 4500 iterations

31 Prototype car simulations: aerodynamic results (OF vs. Fluent) Total pressure distribution around the car, y=0 (symmetry plane) C pt = pt p p p t, Fluent, 6000 iterations C pt = pt p p p t, OpenFOAM, 4500 iterations

32 Prototype car simulations: aerodynamic results (OF vs. Fluent) Total pressure distribution around the car, y= C pt = pt p p p t, Fluent, 6000 iterations C pt = pt p p p t, OpenFOAM, 4500 iterations

33 Prototype car simulations: aerodynamic results (OF vs. Fluent) Total pressure distribution around the car, y= C pt = pt p p p t, Fluent, 6000 iterations C pt = pt p p p t, OpenFOAM, 4500 iterations

34 Prototype car simulations: aerodynamic results (OF vs. Fluent) Total pressure distribution around the car, z=0.11 C pt = pt p p p t, Fluent, 6000 iterations C pt = pt p p p t, OpenFOAM, 4500 iterations

35 Prototype car simulations: inter-node scalability tests (Matrix vs. Jazz) Case description: Speedup, Matrix vs Jazz, PCG Symmetrical grid (~7.5*10 6 cells) 24 PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution Speedup Matrix, PCG Jazz, PCG The computing node is selected as the fundamental unit Number of nodes speedup ( time per step) = 1 ( time per step) node N nodes

36 Prototype car simulations: inter-node scalability tests (Matrix vs. Jazz) Case description: Speedup, Matrix vs Jazz, GAMG Symmetrical grid (~7.5*10 6 cells) 16 PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution Speedup Matrix, GAMG Jazz, GAMG The computing node is selected as the fundamental unit Number of nodes speedup ( time per step) = 1 ( time per step) node N nodes

37 Prototype car simulations: inter-node scalability tests (Matrix vs. Jazz) Case description: Speedup, Matrix, GAMG vs PCG Symmetrical grid (~7.5*10 6 cells) 24 PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution Speedup Matrix, PCG Matrix, GAMG The computing node is selected as the fundamental unit Number of nodes speedup ( time per step) = 1 ( time per step) node N nodes

38 Prototype car simulations: inter-node scalability tests (Matrix vs. Jazz) Case description: Speedup, Jazz, GAMG vs PCG Symmetrical grid (~7.5*10 6 cells) 24 PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution Speedup Jazz, PCG Jazz, GAMG The computing node is selected as the fundamental unit Number of nodes speedup ( time per step) = 1 ( time per step) node N nodes

39 Prototype car simulations: inter-node scalability tests (Matrix vs. Jazz) Case description: Symmetrical grid (~7.5*10 6 cells) PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution The computing node is selected as the fundamental unit Comments: The PCG solver clearly outperforms GAMG when the parallelization starts to become extensive (approximately above 100 processes for the half-car case) Jazz appears to scale better than Matrix, probably because of the more capable infiniband network (QDR vs DDR) and of better cache filling as the single processes become smaller

40 Prototype car simulations: absolute and single-node performances (Matrix vs. Jazz) Case description: Time- per- step, Matrix, GAMG vs PCG Symmetrical grid (~7.5*10 6 cells) 70 Matrix, PCG PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution time (s) Matrix, GAMG Time-per-step evaluated on a percore basis Number of cores

41 Prototype car simulations: absolute and single-node performances (Matrix vs. Jazz) Case description: Time- per- step, Jazz, GAMG vs PCG Symmetrical grid (~7.5*10 6 cells) 30 Jazz, PCG PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution time (s) Jazz, GAMG Time-per-step evaluated on a percore basis Number of cores

42 Prototype car simulations: absolute and single-node performances (Matrix vs. Jazz) Case description: Time- per- step, single- node, Matrix, GAMG vs PCG Symmetrical grid (~7.5*10 6 cells) 300 Matrix, PCG PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution time (s) Matrix, GAMG Time-per-step evaluated on a percore basis Number of cores

43 Prototype car simulations: absolute and single-node performances (Matrix vs. Jazz) Case description: Time- per- step, single- node, Jazz, GAMG vs PCG Symmetrical grid (~7.5*10 6 cells) PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution time (s) Jazz, PCG Jazz, GAMG Time-per-step evaluated on a percore basis Number of cores

44 Prototype car simulations: absolute and single-node performances (Matrix vs. Jazz) Case description: Symmetrical grid (~7.5*10 6 cells) PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution Time-per-step evaluated on a percore basis Comments: Though the very inefficient intranode scaling, the newer Intel arch. is (as expected) much faster than the AMD one If the procs. number is kept in the acceptable scaling range, the GAMG solver is always faster than the PCG one (e. g. 40% faster on 64 Matrix cores)

45 Prototype car simulations: scalability tests (Fermi, symmetrical grid) Case description: Speedup efficiency, 1 6 ppn, PCG vs GAMG Symmetrical grid (~7.5*10 6 cells) PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution Speedup efficiency (%) Fermi, PCG, 16 PPN Fermi, GAMG, 16 PPN 16 and 32 MPI processes per node considered Number of nodes..(%) 100 ( ) node se = time per step ( time per step ) 1 1 N N nodes

46 Prototype car simulations: scalability tests (Fermi, symmetrical grid) Case description: Speedup efficiency, PCG, 16 ppn vs. 32 ppn Symmetrical grid (~7.5*10 6 cells) PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution Speedup efficiency (%) Fermi, PCG, 16 PPN Fermi, PCG, 32 PPN 16 and 32 MPI processes per node considered Number of nodes..(%) 100 ( ) node se = time per step ( time per step ) 1 1 N N nodes

47 Prototype car simulations: scalability tests (Fermi, symmetrical grid) Case description: Speedup efficiency, PCG, 16 ppn vs. 32 ppn Symmetrical grid (~7.5*10 6 cells) PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution Speedup efficiency (%) Fermi, PCG, 16 PPN Fermi, PCG, 32 PPN 16 and 32 MPI processes per node considered Number of nodes What about absolute performance?

48 Prototype car simulations: scalability tests (Fermi, symmetrical grid) Case description: Symmetrical grid (~7.5*10 6 cells) PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution 16 and 32 MPI processes per node considered time (s) Time- per- step, PCG, 16 ppn vs. 32 ppn Fermi, PCG, 16 PPN Fermi, PCG, 32 PPN Number of nodes Apparently usingo more ppn could be beneficial in terms of absolute performance, but actually when the number of nodes reaches a practical value (64) the benefit vanishes, and in addition

49 Prototype car simulations: I/O performance tests (Fermi, symmetrical grid) Case description: Output generation time, PCG, 16 ppn vs. 32 ppn Symmetrical grid (~7.5*10 6 cells) PCG linear solver on pressure Output generation time and initialization time monitored time (s) Fermi, PCG, 16 PPN Fermi, PCG, 32 PPN 16 and 32 MPI processes per node considered Number of nodes

50 Prototype car simulations: I/O performance tests (Fermi, symmetrical grid) Case description: Initialization time, PCG, 16 ppn vs. 32 ppn Symmetrical grid (~7.5*10 6 cells) PCG linear solver on pressure Output generation time and initialization time monitored 16 and 32 MPI processes per node considered time (s) Fermi, PCG, 16 PPN Fermi, PCG, 32 PPN Number of nodes

51 Prototype car simulations: comments about Fermi runs (symmetrical grid) Case description: Symmetrical grid (~7.5*10 6 cells) PCG and GAMG linear solver on pressure equation 50 iterations monitoring, starting from a fairly converged solution 16 and 32 MPI processes per node considered Comments: The case is of course too small to prove Fermi s real potential, but up to the minimum practical node number (64) the SIMPLE iteration scaling is acceptable (PCG) when the I/O capability of the nodes gets actually saturated, a dramatic drop in the I/O efficiency occurs (and things get even worse with 32 ppn)

52 Further simulations on Fermi: doubled grid Case description: Doubled grid (~15*10 6 cells) Time- per- step, PCG, symm. vs. doubled 3 PCG solver on pressure equation 2,5 2 Only 16 ppn considered Comparison made assuming the same mesh-per-node load distribution (i. e. doubling the number of nodes for the bigger grid) time (s) 1,5 1 0, Number of nodes (symm-double) Fermi, PCG, symm Fermi, PCG, double

53 Further simulations on Fermi: doubled grid Case description: O. g. t., PCG, symm. vs. doubled Doubled grid (~15*10 6 cells) 40 PCG solver on pressure equation Only 16 ppn considered Comparison made assuming the same mesh-per-node load distribution (i. e. doubling the number of nodes for the bigger grid) time (s) Number of nodes (symm-double) Fermi, PCG, symm Fermi, PCG, double

54 Further simulations on Fermi: doubled grid Case description: I. t., PCG, symm. vs. doubled Doubled grid (~15*10 6 cells) 600 PCG solver on pressure equation Only 16 ppn considered Comparison made assuming the same mesh-per-node load distribution (i. e. doubling the number of nodes for the bigger grid) time (s) Number of nodes (symm-double) Fermi, PCG, symm Fermi, PCG, double

55 Further simulations on Fermi: doubled grid Case description: Doubled grid (~15*10 6 cells) PCG and GAMG linear solver on pressure equation Only 16 ppn considered Comments: The SIMPLE iteration weak-scaling performance appears fairly good and thus should encourage more tests on bigger cases, but the I/O issues are confirmed Comparison made assuming the same mesh-per-node load distribution (i. e. doubling the number of nodes for the bigger grid)

56 Conclusions (1) Hi-ZEV a is successful example of how industry can take advantage from the combination of parallelized open-source CFD toolkits and highly qualified HPC infrastructures, in a collaborative project framework The OpenFOAM code has been evaluated on conventional AMD and Intel HPC facilities for external aerodynamics applications, showing: Good accuracy compared to well established commercial CFD codes; Interesting parallel performances (still not totally exploited), at least for small/medium size cases (~ 10 7 cells) and depending on the optimal pressure solver choice (PCG scales better, GAMG is faster for smal procs. numbers)

57 Conclusions (2) The OpenFOAM performances have been assessed also on the BG/Q supercomputer Fermi and, in spite of the (relatively) small size of the considered cases, the following remarks can be extracted: The solver iteration scaling performances are promising (with PCG), especially in the perspective of coping with much bigger problems; Though for the considered cases a more conventional architecture (e. g. Intel Xeon) seems to be a better choice, a deeper investigation should be made in order to include also performance vs. energy consumption aspects; Unfortunately, for massively parallel applications (thousands of processes) a dramatic I/O efficiency question rises (further evaluation needed)

58 Aknowledgments A. De Maio (1), V. Krastev (2), P. Lanucara (3), F. Salvadore (3) M. Testa (1) (for providing the half-car grid and Fluent results) (1) Nu.m.i.d.i.a. S. r. l. (2) Dept. of Industrial Engineering, University of Rome Tor Vergata (3) CINECA Roma, Dipartimento SCAI

59 Workshop HPC enabling of OpenFOAM for CFD applications

OpenFOAM on BG/Q porting and performance

OpenFOAM on BG/Q porting and performance OpenFOAM on BG/Q porting and performance Paride Dagna, SCAI Department, CINECA SYSTEM OVERVIEW OpenFOAM : selected application inside of PRACE project Fermi : PRACE Tier- System Model: IBM-BlueGene /Q

More information

Maximize automotive simulation productivity with ANSYS HPC and NVIDIA GPUs

Maximize automotive simulation productivity with ANSYS HPC and NVIDIA GPUs Presented at the 2014 ANSYS Regional Conference- Detroit, June 5, 2014 Maximize automotive simulation productivity with ANSYS HPC and NVIDIA GPUs Bhushan Desam, Ph.D. NVIDIA Corporation 1 NVIDIA Enterprise

More information

Multi-GPU simulations in OpenFOAM with SpeedIT technology.

Multi-GPU simulations in OpenFOAM with SpeedIT technology. Multi-GPU simulations in OpenFOAM with SpeedIT technology. Attempt I: SpeedIT GPU-based library of iterative solvers for Sparse Linear Algebra and CFD. Current version: 2.2. Version 1.0 in 2008. CMRS format

More information

THE INFLUENCE OF MESH CHARACTERISTICS ON OPENFOAM SIMULATIONS OF THE DRIVAER MODEL

THE INFLUENCE OF MESH CHARACTERISTICS ON OPENFOAM SIMULATIONS OF THE DRIVAER MODEL 6 th BETA CAE International Conference THE INFLUENCE OF MESH CHARACTERISTICS ON OPENFOAM SIMULATIONS OF THE DRIVAER MODEL Grigoris Fotiadis *, Vangelis Skaperdas, Aristotelis Iordanidis BETA CAE Systems

More information

Two-Phase flows on massively parallel multi-gpu clusters

Two-Phase flows on massively parallel multi-gpu clusters Two-Phase flows on massively parallel multi-gpu clusters Peter Zaspel Michael Griebel Institute for Numerical Simulation Rheinische Friedrich-Wilhelms-Universität Bonn Workshop Programming of Heterogeneous

More information

Speedup Altair RADIOSS Solvers Using NVIDIA GPU

Speedup Altair RADIOSS Solvers Using NVIDIA GPU Innovation Intelligence Speedup Altair RADIOSS Solvers Using NVIDIA GPU Eric LEQUINIOU, HPC Director Hongwei Zhou, Senior Software Developer May 16, 2012 Innovation Intelligence ALTAIR OVERVIEW Altair

More information

The Cray CX1 puts massive power and flexibility right where you need it in your workgroup

The Cray CX1 puts massive power and flexibility right where you need it in your workgroup The Cray CX1 puts massive power and flexibility right where you need it in your workgroup Up to 96 cores of Intel 5600 compute power 3D visualization Up to 32TB of storage GPU acceleration Small footprint

More information

Application of GPU technology to OpenFOAM simulations

Application of GPU technology to OpenFOAM simulations Application of GPU technology to OpenFOAM simulations Jakub Poła, Andrzej Kosior, Łukasz Miroslaw jakub.pola@vratis.com, www.vratis.com Wroclaw, Poland Agenda Motivation Partial acceleration SpeedIT OpenFOAM

More information

Optimization of parameter settings for GAMG solver in simple solver

Optimization of parameter settings for GAMG solver in simple solver Optimization of parameter settings for GAMG solver in simple solver Masashi Imano (OCAEL Co.Ltd.) Aug. 26th 2012 OpenFOAM Study Meeting for beginner @ Kanto Test cluster condition Hardware: SGI Altix ICE8200

More information

Aerodynamic Study of a Realistic Car W. TOUGERON

Aerodynamic Study of a Realistic Car W. TOUGERON Aerodynamic Study of a Realistic Car W. TOUGERON Tougeron CFD Engineer 2016 Abstract This document presents an aerodynamic CFD study of a realistic car geometry. The aim is to demonstrate the efficiency

More information

HPC and IT Issues Session Agenda. Deployment of Simulation (Trends and Issues Impacting IT) Mapping HPC to Performance (Scaling, Technology Advances)

HPC and IT Issues Session Agenda. Deployment of Simulation (Trends and Issues Impacting IT) Mapping HPC to Performance (Scaling, Technology Advances) HPC and IT Issues Session Agenda Deployment of Simulation (Trends and Issues Impacting IT) Discussion Mapping HPC to Performance (Scaling, Technology Advances) Discussion Optimizing IT for Remote Access

More information

Making Supercomputing More Available and Accessible Windows HPC Server 2008 R2 Beta 2 Microsoft High Performance Computing April, 2010

Making Supercomputing More Available and Accessible Windows HPC Server 2008 R2 Beta 2 Microsoft High Performance Computing April, 2010 Making Supercomputing More Available and Accessible Windows HPC Server 2008 R2 Beta 2 Microsoft High Performance Computing April, 2010 Windows HPC Server 2008 R2 Windows HPC Server 2008 R2 makes supercomputing

More information

ANSYS HPC. Technology Leadership. Barbara Hutchings ANSYS, Inc. September 20, 2011

ANSYS HPC. Technology Leadership. Barbara Hutchings ANSYS, Inc. September 20, 2011 ANSYS HPC Technology Leadership Barbara Hutchings barbara.hutchings@ansys.com 1 ANSYS, Inc. September 20, Why ANSYS Users Need HPC Insight you can t get any other way HPC enables high-fidelity Include

More information

Simulation of Turbulent Flow over the Ahmed Body

Simulation of Turbulent Flow over the Ahmed Body Simulation of Turbulent Flow over the Ahmed Body 58:160 Intermediate Mechanics of Fluids CFD LAB 4 By Timur K. Dogan, Michael Conger, Maysam Mousaviraad, and Fred Stern IIHR-Hydroscience & Engineering

More information

Computer Aided Engineering with Today's Multicore, InfiniBand-Based Clusters ANSYS, Inc. All rights reserved. 1 ANSYS, Inc.

Computer Aided Engineering with Today's Multicore, InfiniBand-Based Clusters ANSYS, Inc. All rights reserved. 1 ANSYS, Inc. Computer Aided Engineering with Today's Multicore, InfiniBand-Based Clusters 2006 ANSYS, Inc. All rights reserved. 1 ANSYS, Inc. Proprietary Our Business Simulation Driven Product Development Deliver superior

More information

ANSYS HPC Technology Leadership

ANSYS HPC Technology Leadership ANSYS HPC Technology Leadership 1 ANSYS, Inc. November 14, Why ANSYS Users Need HPC Insight you can t get any other way It s all about getting better insight into product behavior quicker! HPC enables

More information

Shape optimisation using breakthrough technologies

Shape optimisation using breakthrough technologies Shape optimisation using breakthrough technologies Compiled by Mike Slack Ansys Technical Services 2010 ANSYS, Inc. All rights reserved. 1 ANSYS, Inc. Proprietary Introduction Shape optimisation technologies

More information

THE APPLICATION OF AN ATMOSPHERIC BOUNDARY LAYER TO EVALUATE TRUCK AERODYNAMICS IN CFD

THE APPLICATION OF AN ATMOSPHERIC BOUNDARY LAYER TO EVALUATE TRUCK AERODYNAMICS IN CFD THE APPLICATION OF AN ATMOSPHERIC BOUNDARY LAYER TO EVALUATE TRUCK AERODYNAMICS IN CFD A SOLUTION FOR A REAL-WORLD ENGINEERING PROBLEM Ir. Niek van Dijk DAF Trucks N.V. CONTENTS Scope & Background Theory:

More information

SHAPE pilot Monotricat SRL: Hull resistance simulations for an innovative hull using OpenFOAM

SHAPE pilot Monotricat SRL: Hull resistance simulations for an innovative hull using OpenFOAM Available online at www.prace-ri.eu Partnership for Advanced Computing in Europe SHAPE pilot Monotricat SRL: Hull resistance simulations for an innovative hull using OpenFOAM Lilit Axner a,b, Jing Gong

More information

ANSYS Improvements to Engineering Productivity with HPC and GPU-Accelerated Simulation

ANSYS Improvements to Engineering Productivity with HPC and GPU-Accelerated Simulation ANSYS Improvements to Engineering Productivity with HPC and GPU-Accelerated Simulation Ray Browell nvidia Technology Theater SC12 1 2012 ANSYS, Inc. nvidia Technology Theater SC12 HPC Revolution Recent

More information

University at Buffalo Center for Computational Research

University at Buffalo Center for Computational Research University at Buffalo Center for Computational Research The following is a short and long description of CCR Facilities for use in proposals, reports, and presentations. If desired, a letter of support

More information

Turbostream: A CFD solver for manycore

Turbostream: A CFD solver for manycore Turbostream: A CFD solver for manycore processors Tobias Brandvik Whittle Laboratory University of Cambridge Aim To produce an order of magnitude reduction in the run-time of CFD solvers for the same hardware

More information

Adaptive-Mesh-Refinement Hydrodynamic GPU Computation in Astrophysics

Adaptive-Mesh-Refinement Hydrodynamic GPU Computation in Astrophysics Adaptive-Mesh-Refinement Hydrodynamic GPU Computation in Astrophysics H. Y. Schive ( 薛熙于 ) Graduate Institute of Physics, National Taiwan University Leung Center for Cosmology and Particle Astrophysics

More information

Optimisation Myths and Facts as Seen in Statistical Physics

Optimisation Myths and Facts as Seen in Statistical Physics Optimisation Myths and Facts as Seen in Statistical Physics Massimo Bernaschi Institute for Applied Computing National Research Council & Computer Science Department University La Sapienza Rome - ITALY

More information

OP2 FOR MANY-CORE ARCHITECTURES

OP2 FOR MANY-CORE ARCHITECTURES OP2 FOR MANY-CORE ARCHITECTURES G.R. Mudalige, M.B. Giles, Oxford e-research Centre, University of Oxford gihan.mudalige@oerc.ox.ac.uk 27 th Jan 2012 1 AGENDA OP2 Current Progress Future work for OP2 EPSRC

More information

DrivAer-Aerodynamic Investigations for a New Realistic Generic Car Model using ANSYS CFD

DrivAer-Aerodynamic Investigations for a New Realistic Generic Car Model using ANSYS CFD DrivAer-Aerodynamic Investigations for a New Realistic Generic Car Model using ANSYS CFD Thomas Frank (*), BenediktGerlicher (*), Juan Abanto (**) (*) ANSYS Germany, Otterfing, Germany (**) ANSYS Inc.,

More information

SHAPE Pilot Thesan srl: Design improvement of a rotary turbine supply chamber through CFD analysis. R. Ponzini a, A. Penza a, R. Vadori b, B.

SHAPE Pilot Thesan srl: Design improvement of a rotary turbine supply chamber through CFD analysis. R. Ponzini a, A. Penza a, R. Vadori b, B. Available online at www.prace-ri.eu Partnership for Advanced Computing in Europe SHAPE Pilot Thesan srl: Design improvement of a rotary turbine supply chamber through CFD analysis R. Ponzini a, A. Penza

More information

Porting Scalable Parallel CFD Application HiFUN on NVIDIA GPU

Porting Scalable Parallel CFD Application HiFUN on NVIDIA GPU Porting Scalable Parallel CFD Application NVIDIA D. V., N. Munikrishna, Nikhil Vijay Shende 1 N. Balakrishnan 2 Thejaswi Rao 3 1. S & I Engineering Solutions Pvt. Ltd., Bangalore, India 2. Aerospace Engineering,

More information

Enhancing Analysis-Based Design with Quad-Core Intel Xeon Processor-Based Workstations

Enhancing Analysis-Based Design with Quad-Core Intel Xeon Processor-Based Workstations Performance Brief Quad-Core Workstation Enhancing Analysis-Based Design with Quad-Core Intel Xeon Processor-Based Workstations With eight cores and up to 80 GFLOPS of peak performance at your fingertips,

More information

Why HPC for. ANSYS Mechanical and ANSYS CFD?

Why HPC for. ANSYS Mechanical and ANSYS CFD? Why HPC for ANSYS Mechanical and ANSYS CFD? 1 HPC Defined High Performance Computing (HPC) at ANSYS: An ongoing effort designed to remove computing limitations from engineers who use computer aided engineering

More information

Parallel Performance Studies for a Clustering Algorithm

Parallel Performance Studies for a Clustering Algorithm Parallel Performance Studies for a Clustering Algorithm Robin V. Blasberg and Matthias K. Gobbert Naval Research Laboratory, Washington, D.C. Department of Mathematics and Statistics, University of Maryland,

More information

Introduction to ANSYS CFX

Introduction to ANSYS CFX Workshop 03 Fluid flow around the NACA0012 Airfoil 16.0 Release Introduction to ANSYS CFX 2015 ANSYS, Inc. March 13, 2015 1 Release 16.0 Workshop Description: The flow simulated is an external aerodynamics

More information

Simulation of Flow Development in a Pipe

Simulation of Flow Development in a Pipe Tutorial 4. Simulation of Flow Development in a Pipe Introduction The purpose of this tutorial is to illustrate the setup and solution of a 3D turbulent fluid flow in a pipe. The pipe networks are common

More information

GPU-Acceleration of CAE Simulations. Bhushan Desam NVIDIA Corporation

GPU-Acceleration of CAE Simulations. Bhushan Desam NVIDIA Corporation GPU-Acceleration of CAE Simulations Bhushan Desam NVIDIA Corporation bdesam@nvidia.com 1 AGENDA GPUs in Enterprise Computing Business Challenges in Product Development NVIDIA GPUs for CAE Applications

More information

AERODYNAMIC OPTIMIZATION OF REAR AND FRONT FLAPS ON A CAR

AERODYNAMIC OPTIMIZATION OF REAR AND FRONT FLAPS ON A CAR Student: Giannoni Alberto Professor: Ing. Jan Pralits, Advanced Fluid Dynamics Course Co-Professor: Ing. Matteo Colli AERODYNAMIC OPTIMIZATION OF REAR AND FRONT FLAPS ON A CAR ABSTRACT In this work we

More information

Proceedings of the First International Workshop on Sustainable Ultrascale Computing Systems (NESUS 2014) Porto, Portugal

Proceedings of the First International Workshop on Sustainable Ultrascale Computing Systems (NESUS 2014) Porto, Portugal Proceedings of the First International Workshop on Sustainable Ultrascale Computing Systems (NESUS 2014) Porto, Portugal Jesus Carretero, Javier Garcia Blas Jorge Barbosa, Ricardo Morla (Editors) August

More information

Big Data Analytics Performance for Large Out-Of- Core Matrix Solvers on Advanced Hybrid Architectures

Big Data Analytics Performance for Large Out-Of- Core Matrix Solvers on Advanced Hybrid Architectures Procedia Computer Science Volume 51, 2015, Pages 2774 2778 ICCS 2015 International Conference On Computational Science Big Data Analytics Performance for Large Out-Of- Core Matrix Solvers on Advanced Hybrid

More information

Software and Performance Engineering for numerical codes on GPU clusters

Software and Performance Engineering for numerical codes on GPU clusters Software and Performance Engineering for numerical codes on GPU clusters H. Köstler International Workshop of GPU Solutions to Multiscale Problems in Science and Engineering Harbin, China 28.7.2010 2 3

More information

NUMERICAL 3D TRANSONIC FLOW SIMULATION OVER A WING

NUMERICAL 3D TRANSONIC FLOW SIMULATION OVER A WING Review of the Air Force Academy No.3 (35)/2017 NUMERICAL 3D TRANSONIC FLOW SIMULATION OVER A WING Cvetelina VELKOVA Department of Technical Mechanics, Naval Academy Nikola Vaptsarov,Varna, Bulgaria (cvetelina.velkova1985@gmail.com)

More information

Welcome! Roberto Mucci SuperComputing Applications and Innovation Department

Welcome! Roberto Mucci SuperComputing Applications and Innovation Department Welcome! Roberto Mucci r.mucci@cineca.it SuperComputing Applications and Innovation Department OUTLINE School presentation Introduction to Scientific Visualization Remote visualization @ Cineca ABOUT CINECA

More information

DEPARTMENT OF FLUID DYNAMICS CFD SIMULATION OF FLOW OVER A MOCK URBAN SETTING USING OPENFOAM

DEPARTMENT OF FLUID DYNAMICS CFD SIMULATION OF FLOW OVER A MOCK URBAN SETTING USING OPENFOAM DEPARTMENT OF FLUID DYNAMICS Budapest University of Technology and Economics CFD SIMULATION OF FLOW OVER A MOCK URBAN SETTING USING OPENFOAM Anikó Rákai Gergely Kristóf, Ph. D. 5th OpenFOAM Workshop Gothenburg

More information

OpenFOAM + GPGPU. İbrahim Özküçük

OpenFOAM + GPGPU. İbrahim Özküçük OpenFOAM + GPGPU İbrahim Özküçük Outline GPGPU vs CPU GPGPU plugins for OpenFOAM Overview of Discretization CUDA for FOAM Link (cufflink) Cusp & Thrust Libraries How Cufflink Works Performance data of

More information

Flux Vector Splitting Methods for the Euler Equations on 3D Unstructured Meshes for CPU/GPU Clusters

Flux Vector Splitting Methods for the Euler Equations on 3D Unstructured Meshes for CPU/GPU Clusters Flux Vector Splitting Methods for the Euler Equations on 3D Unstructured Meshes for CPU/GPU Clusters Manfred Liebmann Technische Universität München Chair of Optimal Control Center for Mathematical Sciences,

More information

Large scale Imaging on Current Many- Core Platforms

Large scale Imaging on Current Many- Core Platforms Large scale Imaging on Current Many- Core Platforms SIAM Conf. on Imaging Science 2012 May 20, 2012 Dr. Harald Köstler Chair for System Simulation Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen,

More information

Automatic Hex-Dominant Mesh Generation for CFD Analysis of Formula One Car with cfmeshpro

Automatic Hex-Dominant Mesh Generation for CFD Analysis of Formula One Car with cfmeshpro Automatic Hex-Dominant Mesh Generation for CFD Analysis of Formula One Car with cfmeshpro Alen Cukrov and Franjo Juretić Creative Fields Ltd, X Vrbik 4, 10000 Zagreb, Croatia 1 Introduction This report

More information

Integrating multi-body simulation and CFD: toward complex multidisciplinary design optimisation

Integrating multi-body simulation and CFD: toward complex multidisciplinary design optimisation Integrating multi-body simulation and CFD: toward complex multidisciplinary design optimisation Federico Urban ESTECO Italy Martin Mühlmeier AUDI Germany Stefano Pieri Department of Energetics University

More information

Flux Vector Splitting Methods for the Euler Equations on 3D Unstructured Meshes for CPU/GPU Clusters

Flux Vector Splitting Methods for the Euler Equations on 3D Unstructured Meshes for CPU/GPU Clusters Flux Vector Splitting Methods for the Euler Equations on 3D Unstructured Meshes for CPU/GPU Clusters Manfred Liebmann Technische Universität München Chair of Optimal Control Center for Mathematical Sciences,

More information

HPC-CINECA infrastructure: The New Marconi System. HPC methods for Computational Fluid Dynamics and Astrophysics Giorgio Amati,

HPC-CINECA infrastructure: The New Marconi System. HPC methods for Computational Fluid Dynamics and Astrophysics Giorgio Amati, HPC-CINECA infrastructure: The New Marconi System HPC methods for Computational Fluid Dynamics and Astrophysics Giorgio Amati, g.amati@cineca.it Agenda 1. New Marconi system Roadmap Some performance info

More information

Faster Innovation - Accelerating SIMULIA Abaqus Simulations with NVIDIA GPUs. Baskar Rajagopalan Accelerated Computing, NVIDIA

Faster Innovation - Accelerating SIMULIA Abaqus Simulations with NVIDIA GPUs. Baskar Rajagopalan Accelerated Computing, NVIDIA Faster Innovation - Accelerating SIMULIA Abaqus Simulations with NVIDIA GPUs Baskar Rajagopalan Accelerated Computing, NVIDIA 1 Engineering & IT Challenges/Trends NVIDIA GPU Solutions AGENDA Abaqus GPU

More information

Stan Posey, CAE Industry Development NVIDIA, Santa Clara, CA, USA

Stan Posey, CAE Industry Development NVIDIA, Santa Clara, CA, USA Stan Posey, CAE Industry Development NVIDIA, Santa Clara, CA, USA NVIDIA and HPC Evolution of GPUs Public, based in Santa Clara, CA ~$4B revenue ~5,500 employees Founded in 1999 with primary business in

More information

Verification and Validation of Turbulent Flow around a Clark-Y Airfoil

Verification and Validation of Turbulent Flow around a Clark-Y Airfoil Verification and Validation of Turbulent Flow around a Clark-Y Airfoil 1. Purpose 58:160 Intermediate Mechanics of Fluids CFD LAB 2 By Tao Xing and Fred Stern IIHR-Hydroscience & Engineering The University

More information

Real Application Performance and Beyond

Real Application Performance and Beyond Real Application Performance and Beyond Mellanox Technologies Inc. 2900 Stender Way, Santa Clara, CA 95054 Tel: 408-970-3400 Fax: 408-970-3403 http://www.mellanox.com Scientists, engineers and analysts

More information

MVAPICH2 vs. OpenMPI for a Clustering Algorithm

MVAPICH2 vs. OpenMPI for a Clustering Algorithm MVAPICH2 vs. OpenMPI for a Clustering Algorithm Robin V. Blasberg and Matthias K. Gobbert Naval Research Laboratory, Washington, D.C. Department of Mathematics and Statistics, University of Maryland, Baltimore

More information

Team 194: Aerodynamic Study of Airflow around an Airfoil in the EGI Cloud

Team 194: Aerodynamic Study of Airflow around an Airfoil in the EGI Cloud Team 194: Aerodynamic Study of Airflow around an Airfoil in the EGI Cloud CFD Support s OpenFOAM and UberCloud Containers enable efficient, effective, and easy access and use of MEET THE TEAM End-User/CFD

More information

Adjoint Solver Advances, Tailored to Automotive Applications

Adjoint Solver Advances, Tailored to Automotive Applications Adjoint Solver Advances, Tailored to Automotive Applications Stamatina Petropoulou s.petropoulou@iconcfd.com 1 Contents 1. Icon s Principal Work in FlowHead 2. Demonstration Cases 3. Icon s Further Development

More information

CRAY XK6 REDEFINING SUPERCOMPUTING. - Sanjana Rakhecha - Nishad Nerurkar

CRAY XK6 REDEFINING SUPERCOMPUTING. - Sanjana Rakhecha - Nishad Nerurkar CRAY XK6 REDEFINING SUPERCOMPUTING - Sanjana Rakhecha - Nishad Nerurkar CONTENTS Introduction History Specifications Cray XK6 Architecture Performance Industry acceptance and applications Summary INTRODUCTION

More information

Application of Wray-Agarwal Turbulence Model for Accurate Numerical Simulation of Flow Past a Three-Dimensional Wing-body

Application of Wray-Agarwal Turbulence Model for Accurate Numerical Simulation of Flow Past a Three-Dimensional Wing-body Washington University in St. Louis Washington University Open Scholarship Mechanical Engineering and Materials Science Independent Study Mechanical Engineering & Materials Science 4-28-2016 Application

More information

DNV GL s 16th Technology Week

DNV GL s 16th Technology Week OIL & GAS DNV GL s 16th Technology Week Advanced Simulation for Offshore Application: Application of CFD for Computing VIM of Floating Structures 1 SAFER, SMARTER, GREENER OUTLINE Introduction Elements

More information

Express Introductory Training in ANSYS Fluent Workshop 06 Using Moving Reference Frames and Sliding Meshes

Express Introductory Training in ANSYS Fluent Workshop 06 Using Moving Reference Frames and Sliding Meshes Express Introductory Training in ANSYS Fluent Workshop 06 Using Moving Reference Frames and Sliding Meshes Dimitrios Sofialidis Technical Manager, SimTec Ltd. Mechanical Engineer, PhD PRACE Autumn School

More information

STCE. An (more) effective Discrete Adjoint Model for OpenFOAM

STCE. An (more) effective Discrete Adjoint Model for OpenFOAM An (more) effective Discrete Adjoint Model for OpenFOAM Markus Towara, Uwe Naumann Software and Tools for Computational Engineering Science RWTH Aachen University EuroAD 2013, Oxford, 10. December 2013

More information

Center Extreme Scale CS Research

Center Extreme Scale CS Research Center Extreme Scale CS Research Center for Compressible Multiphase Turbulence University of Florida Sanjay Ranka Herman Lam Outline 10 6 10 7 10 8 10 9 cores Parallelization and UQ of Rocfun and CMT-Nek

More information

Solving Large Complex Problems. Efficient and Smart Solutions for Large Models

Solving Large Complex Problems. Efficient and Smart Solutions for Large Models Solving Large Complex Problems Efficient and Smart Solutions for Large Models 1 ANSYS Structural Mechanics Solutions offers several techniques 2 Current trends in simulation show an increased need for

More information

Introduction to CFX. Workshop 2. Transonic Flow Over a NACA 0012 Airfoil. WS2-1. ANSYS, Inc. Proprietary 2009 ANSYS, Inc. All rights reserved.

Introduction to CFX. Workshop 2. Transonic Flow Over a NACA 0012 Airfoil. WS2-1. ANSYS, Inc. Proprietary 2009 ANSYS, Inc. All rights reserved. Workshop 2 Transonic Flow Over a NACA 0012 Airfoil. Introduction to CFX WS2-1 Goals The purpose of this tutorial is to introduce the user to modelling flow in high speed external aerodynamic applications.

More information

Taming OpenFOAM for Ship Hydrodynamics Applications

Taming OpenFOAM for Ship Hydrodynamics Applications Taming OpenFOAM for Ship Hydrodynamics Applications Sung-Eun Kim, Ph. D. Computational Hydromechanics Division (Code 5700) Naval Surface Warfare Center Carderock Division Background Target Applications

More information

Calculate a solution using the pressure-based coupled solver.

Calculate a solution using the pressure-based coupled solver. Tutorial 19. Modeling Cavitation Introduction This tutorial examines the pressure-driven cavitating flow of water through a sharpedged orifice. This is a typical configuration in fuel injectors, and brings

More information

DES Turbulence Modeling for ICE Flow Simulation in OpenFOAM

DES Turbulence Modeling for ICE Flow Simulation in OpenFOAM 2 nd Two-day Meeting on ICE Simulations Using OpenFOAM DES Turbulence Modeling for ICE Flow Simulation in OpenFOAM V. K. Krastev 1, G. Bella 2 and G. Campitelli 1 University of Tuscia, DEIM School of Engineering

More information

Simulation of Turbulent Flow around an Airfoil

Simulation of Turbulent Flow around an Airfoil 1. Purpose Simulation of Turbulent Flow around an Airfoil ENGR:2510 Mechanics of Fluids and Transfer Processes CFD Lab 2 (ANSYS 17.1; Last Updated: Nov. 7, 2016) By Timur Dogan, Michael Conger, Andrew

More information

Trends in CFD, Engineering Analysis & Computing. ME-561 An Introduction to Computational Fluid Dynamics for Incompressible Flow Mark A.

Trends in CFD, Engineering Analysis & Computing. ME-561 An Introduction to Computational Fluid Dynamics for Incompressible Flow Mark A. Trends in CFD, Engineering Analysis & Computing ME-561 An Introduction to Computational Fluid Dynamics for Incompressible Flow Mark A. Christon Trends in Computer-Aided Engineering Analysis 1965 1975:

More information

Engineers can be significantly more productive when ANSYS Mechanical runs on CPUs with a high core count. Executive Summary

Engineers can be significantly more productive when ANSYS Mechanical runs on CPUs with a high core count. Executive Summary white paper Computer-Aided Engineering ANSYS Mechanical on Intel Xeon Processors Engineer Productivity Boosted by Higher-Core CPUs Engineers can be significantly more productive when ANSYS Mechanical runs

More information

Shape optimization and active flow control for improved aerodynamic properties Siniša Krajnovic

Shape optimization and active flow control for improved aerodynamic properties Siniša Krajnovic Shape optimization and active flow control for improved aerodynamic properties Siniša Krajnovic HPC resources used Computer resources at C3SE at Chalmers in Göteborg Computer cluster: Neolith NSC Linköping

More information

Particleworks: Particle-based CAE Software fully ported to GPU

Particleworks: Particle-based CAE Software fully ported to GPU Particleworks: Particle-based CAE Software fully ported to GPU Introduction PrometechVideo_v3.2.3.wmv 3.5 min. Particleworks Why the particle method? Existing methods FEM, FVM, FLIP, Fluid calculation

More information

Verification of Laminar and Validation of Turbulent Pipe Flows

Verification of Laminar and Validation of Turbulent Pipe Flows 1 Verification of Laminar and Validation of Turbulent Pipe Flows 1. Purpose ME:5160 Intermediate Mechanics of Fluids CFD LAB 1 (ANSYS 18.1; Last Updated: Aug. 1, 2017) By Timur Dogan, Michael Conger, Dong-Hwan

More information

PhD Student. Associate Professor, Co-Director, Center for Computational Earth and Environmental Science. Abdulrahman Manea.

PhD Student. Associate Professor, Co-Director, Center for Computational Earth and Environmental Science. Abdulrahman Manea. Abdulrahman Manea PhD Student Hamdi Tchelepi Associate Professor, Co-Director, Center for Computational Earth and Environmental Science Energy Resources Engineering Department School of Earth Sciences

More information

High Performance Computing

High Performance Computing High Performance Computing ADVANCED SCIENTIFIC COMPUTING Dr. Ing. Morris Riedel Adjunct Associated Professor School of Engineering and Natural Sciences, University of Iceland Research Group Leader, Juelich

More information

PORTABLE AND SCALABLE SOLUTIONS FOR CFD ON MODERN SUPERCOMPUTERS

PORTABLE AND SCALABLE SOLUTIONS FOR CFD ON MODERN SUPERCOMPUTERS PORTABLE AND SCALABLE SOLUTIONS FOR CFD ON MODERN SUPERCOMPUTERS Ricard Borrell Pol Head and Mass Transfer Technological Center cttc.upc.edu Termo Fluids S.L termofluids.co Barcelona Supercomputing Center

More information

S-ducts and Nozzles: STAR-CCM+ at the Propulsion Aerodynamics Workshop. Peter Burns, CD-adapco

S-ducts and Nozzles: STAR-CCM+ at the Propulsion Aerodynamics Workshop. Peter Burns, CD-adapco S-ducts and Nozzles: STAR-CCM+ at the Propulsion Aerodynamics Workshop Peter Burns, CD-adapco Background The Propulsion Aerodynamics Workshop (PAW) has been held twice PAW01: 2012 at the 48 th AIAA JPC

More information

Available online at ScienceDirect. Parallel Computational Fluid Dynamics Conference (ParCFD2013)

Available online at  ScienceDirect. Parallel Computational Fluid Dynamics Conference (ParCFD2013) Available online at www.sciencedirect.com ScienceDirect Procedia Engineering 61 ( 2013 ) 81 86 Parallel Computational Fluid Dynamics Conference (ParCFD2013) An OpenCL-based parallel CFD code for simulations

More information

AcuSolve Performance Benchmark and Profiling. October 2011

AcuSolve Performance Benchmark and Profiling. October 2011 AcuSolve Performance Benchmark and Profiling October 2011 Note The following research was performed under the HPC Advisory Council activities Participating vendors: AMD, Dell, Mellanox, Altair Compute

More information

J. Blair Perot. Ali Khajeh-Saeed. Software Engineer CD-adapco. Mechanical Engineering UMASS, Amherst

J. Blair Perot. Ali Khajeh-Saeed. Software Engineer CD-adapco. Mechanical Engineering UMASS, Amherst Ali Khajeh-Saeed Software Engineer CD-adapco J. Blair Perot Mechanical Engineering UMASS, Amherst Supercomputers Optimization Stream Benchmark Stag++ (3D Incompressible Flow Code) Matrix Multiply Function

More information

3D ADI Method for Fluid Simulation on Multiple GPUs. Nikolai Sakharnykh, NVIDIA Nikolay Markovskiy, NVIDIA

3D ADI Method for Fluid Simulation on Multiple GPUs. Nikolai Sakharnykh, NVIDIA Nikolay Markovskiy, NVIDIA 3D ADI Method for Fluid Simulation on Multiple GPUs Nikolai Sakharnykh, NVIDIA Nikolay Markovskiy, NVIDIA Introduction Fluid simulation using direct numerical methods Gives the most accurate result Requires

More information

Performance Evaluation of a Vector Supercomputer SX-Aurora TSUBASA

Performance Evaluation of a Vector Supercomputer SX-Aurora TSUBASA Performance Evaluation of a Vector Supercomputer SX-Aurora TSUBASA Kazuhiko Komatsu, S. Momose, Y. Isobe, O. Watanabe, A. Musa, M. Yokokawa, T. Aoyama, M. Sato, H. Kobayashi Tohoku University 14 November,

More information

High-Fidelity Simulation of Unsteady Flow Problems using a 3rd Order Hybrid MUSCL/CD scheme. A. West & D. Caraeni

High-Fidelity Simulation of Unsteady Flow Problems using a 3rd Order Hybrid MUSCL/CD scheme. A. West & D. Caraeni High-Fidelity Simulation of Unsteady Flow Problems using a 3rd Order Hybrid MUSCL/CD scheme ECCOMAS, June 6 th -11 th 2016, Crete Island, Greece A. West & D. Caraeni Outline Industrial Motivation Numerical

More information

Verification and Validation of Turbulent Flow around a Clark-Y Airfoil

Verification and Validation of Turbulent Flow around a Clark-Y Airfoil 1 Verification and Validation of Turbulent Flow around a Clark-Y Airfoil 1. Purpose ME:5160 Intermediate Mechanics of Fluids CFD LAB 2 (ANSYS 19.1; Last Updated: Aug. 7, 2018) By Timur Dogan, Michael Conger,

More information

QLogic TrueScale InfiniBand and Teraflop Simulations

QLogic TrueScale InfiniBand and Teraflop Simulations WHITE Paper QLogic TrueScale InfiniBand and Teraflop Simulations For ANSYS Mechanical v12 High Performance Interconnect for ANSYS Computer Aided Engineering Solutions Executive Summary Today s challenging

More information

MAGMA a New Generation of Linear Algebra Libraries for GPU and Multicore Architectures

MAGMA a New Generation of Linear Algebra Libraries for GPU and Multicore Architectures MAGMA a New Generation of Linear Algebra Libraries for GPU and Multicore Architectures Stan Tomov Innovative Computing Laboratory University of Tennessee, Knoxville OLCF Seminar Series, ORNL June 16, 2010

More information

An advanced RBF Morph application: coupled CFD-CSM Aeroelastic Analysis of a Full Aircraft Model and Comparison to Experimental Data

An advanced RBF Morph application: coupled CFD-CSM Aeroelastic Analysis of a Full Aircraft Model and Comparison to Experimental Data An advanced RBF Morph application: coupled CFD-CSM Aeroelastic Analysis of a Full Aircraft Model and Comparison to Experimental Data Dr. Marco Evangelos Biancolini Tor Vergata University, Rome, Italy Dr.

More information

Large-scale Gas Turbine Simulations on GPU clusters

Large-scale Gas Turbine Simulations on GPU clusters Large-scale Gas Turbine Simulations on GPU clusters Tobias Brandvik and Graham Pullan Whittle Laboratory University of Cambridge A large-scale simulation Overview PART I: Turbomachinery PART II: Stencil-based

More information

Scaling to Petaflop. Ola Torudbakken Distinguished Engineer. Sun Microsystems, Inc

Scaling to Petaflop. Ola Torudbakken Distinguished Engineer. Sun Microsystems, Inc Scaling to Petaflop Ola Torudbakken Distinguished Engineer Sun Microsystems, Inc HPC Market growth is strong CAGR increased from 9.2% (2006) to 15.5% (2007) Market in 2007 doubled from 2003 (Source: IDC

More information

HPC Middle East. KFUPM HPC Workshop April Mohamed Mekias HPC Solutions Consultant. Agenda

HPC Middle East. KFUPM HPC Workshop April Mohamed Mekias HPC Solutions Consultant. Agenda KFUPM HPC Workshop April 29-30 2015 Mohamed Mekias HPC Solutions Consultant Agenda 1 Agenda-Day 1 HPC Overview What is a cluster? Shared v.s. Distributed Parallel v.s. Massively Parallel Interconnects

More information

Advances of parallel computing. Kirill Bogachev May 2016

Advances of parallel computing. Kirill Bogachev May 2016 Advances of parallel computing Kirill Bogachev May 2016 Demands in Simulations Field development relies more and more on static and dynamic modeling of the reservoirs that has come a long way from being

More information

Recent Advances in ANSYS Toward RDO Practices Using optislang. Wim Slagter, ANSYS Inc. Herbert Güttler, MicroConsult GmbH

Recent Advances in ANSYS Toward RDO Practices Using optislang. Wim Slagter, ANSYS Inc. Herbert Güttler, MicroConsult GmbH Recent Advances in ANSYS Toward RDO Practices Using optislang Wim Slagter, ANSYS Inc. Herbert Güttler, MicroConsult GmbH 1 Product Development Pressures Source: Engineering Simulation & HPC Usage Survey

More information

Program: Advanced Certificate Program

Program: Advanced Certificate Program Program: Advanced Certificate Program Course: CFD-Vehicle Aerodynamics Directorate of Training and Lifelong Learning #470-P, Peenya Industrial Area, 4th Phase Peenya, Bengaluru 560 058 www.msruas.ac.in

More information

Studies of the ERCOFTAC Centrifugal Pump with OpenFOAM

Studies of the ERCOFTAC Centrifugal Pump with OpenFOAM Title 1/20 Studies of the ERCOFTAC Centrifugal Pump with OpenFOAM Olivier Petit Håkan Nilsson Outline Outline Geometry Boundary conditions Method and cases Comparison of numerical results with the available

More information

Carlo Cavazzoni, HPC department, CINECA

Carlo Cavazzoni, HPC department, CINECA Introduction to Shared memory architectures Carlo Cavazzoni, HPC department, CINECA Modern Parallel Architectures Two basic architectural scheme: Distributed Memory Shared Memory Now most computers have

More information

Performance comparison between a massive SMP machine and clusters

Performance comparison between a massive SMP machine and clusters Performance comparison between a massive SMP machine and clusters Martin Scarcia, Stefano Alberto Russo Sissa/eLab joint Democritos/Sissa Laboratory for e-science Via Beirut 2/4 34151 Trieste, Italy Stefano

More information

Maximizing Memory Performance for ANSYS Simulations

Maximizing Memory Performance for ANSYS Simulations Maximizing Memory Performance for ANSYS Simulations By Alex Pickard, 2018-11-19 Memory or RAM is an important aspect of configuring computers for high performance computing (HPC) simulation work. The performance

More information

Splotch: High Performance Visualization using MPI, OpenMP and CUDA

Splotch: High Performance Visualization using MPI, OpenMP and CUDA Splotch: High Performance Visualization using MPI, OpenMP and CUDA Klaus Dolag (Munich University Observatory) Martin Reinecke (MPA, Garching) Claudio Gheller (CSCS, Switzerland), Marzia Rivi (CINECA,

More information

Study Of Overloading Effects, In A Refrigerated Display Case

Study Of Overloading Effects, In A Refrigerated Display Case Study Of Overloading Effects, In A Refrigerated Display Case Sandeep Palaksha Senior CAE Engineer HUSSMANN Basavanagudi Bangalore 04, India p.sandeep@hussmann.com Narasimhamurthy CAE Engineer HUSSMANN

More information

Research on performance dependence of cluster computing system based on GPU accelerators on architecture and number of cluster nodes

Research on performance dependence of cluster computing system based on GPU accelerators on architecture and number of cluster nodes Research on performance dependence of cluster computing system based on GPU accelerators on architecture and number of cluster nodes D. Akhmedov, S. Yelubayev, T. Bopeyev, F. Abdoldina, D. Muratov, R.

More information

Multi-Level Parallelism for Incompressible Flow Computations on GPU Clusters

Multi-Level Parallelism for Incompressible Flow Computations on GPU Clusters Boise State University ScholarWorks Mechanical and Biomedical Engineering Faculty Publications and Presentations Department of Mechanical and Biomedical Engineering 1-1-2013 Multi-Level Parallelism for

More information