High Performance Computing in CST STUDIO SUITE Felix Wolfheimer
GPU Computing Performance Speedup 18 16 14 12 10 8 6 4 2 0 Promo offer for EUC participants: 25% discount for K40 cards Speedup of Solver Loop CST STUDIO SUITE 2013 CST STUDIO SUITE 2014 0 1 2 3 4 Number of GPUs (Tesla K40) GPU computing performance has been improved for CST STUDIO SUITE 2014 as CPU and GPU resources are used in parallel. GPU CPU Benchmark performed on system equipped with dual Xeon E5-2630 v2 (Ivy Bridge EP) processors, and four Tesla K40 cards. Model has 80 million mesh cells.
Typical GPU System Configurations Entry level Professional level Enterprise level Workstation with 1 GPU card Available "off the shelf Good acceleration for smaller models Limited model size (depends on available GPU memory and features used) Workstation/server with multiple internal or external GPU cards CST engineers are available to discuss with you which configuration makes sense for your applications and usage scenario. Many configurations available Good acceleration for medium size and large models Limited model size (depends on available GPU memory and features used) Cluster system with highspeed interconnect. High flexibility: Can handle extremely large models using MPI Computing and also a lot of parallel simulation tasks using Distributed Computing (DC) Administrative overhead Higher price
MPI Computing Area of Application MPI Computing is a way to handle very large models efficiently Some application examples for MPI Computing: Electrically very large structures (e.g. RCS calculation, lightning strike) Extremely complex structures (e.g.si simulation for a full package)
MPI Computing Working Principle Subdomain boundary CST STUDIO SUITE Frontend connects to MPI Client Nodes Domain decomposition is shown in mesh view. High speed/low latency interconnection network (optional) Based on a domain decomposition of the simulation domain. Each cluster computer works on its part of the domain. Automatic load balancing ensures an equal distribution of the workload. It works cross-platform on Windows and Linux systems.
MPI Matrix Computation The performance of the matrix computation step has been improved significantly for the new version of CST STUDIO SUITE. Performance Results (for two cluster nodes):* Model Matrix Comp. Time/s (2013) Matrix Comp. Time/s (2014) Speedup (Matrix Comp.)** Speedup (Total Sim.)** 10,301 1,217 8.46 2.63 340M cells 12,921 4,018 3.22 1.85 CPU Core CPU Core Matrix computation is single-threaded in case of MPI up to version 2013. 47M cells CPU Core CPU Core Version 2014 uses all available cores on all cluster nodes. * =System configuration: Compute nodes are equipped with dual eight core Xeon E5-2650 processors, 4xK20 GPUs, and Infiniband FDR interconnect. **=Speedup between version 2013 and 2014 of CST STUDIO SUITE.
MPI Calculation Example 2 GHz blade antenna positioned on aircraft 2 GHz 17.4 x 4.5 x 16.2 m 116 x 30 x 108 λ 375,840 λ 3 660 million cells 4 node MPI cluster 4 Tesla K20 GPU on each node Total of 16 GPUs with 6GB RAM at 60% Memory Total memory: < 100 GB
MPI Calculation Example 2 GHz blade antenna positioned on aircraft 2 GHz 17.4 x 4.5 x 16.2 m 116 x 30 x 108 λ 375,840 λ 3 660 million cells 4 node MPI cluster 4 Tesla K20 GPU on each node Total of 16 GPUs with 6GB RAM at 60% Memory Total memory: < 100 GB Broadband calculation time ~ 4h
Sub-Volume Monitors Sub-volume monitors allow to record field data only in a region of interest allowing for a reduction of data. This is especially important for large models which have hundreds of millions mesh cells. Field data is only stored in the sub-volume defined by the box
Distributed Computing CST STUDIO SUITE Frontend Jobs could be: port excitations* frequency points* parameter variations optimization iterations *2 in parallel included with standard license connects to DC Main Controller DC Solver Servers
Model has 16 ports Only 8 ports need to be computed if defining symmetry conditions Distribute the 8 simulation runs to different solver servers with GPU acceleration
DC Simulation Time Improvement 30 Speedup (total time) Speedup 25 20 15 10 CPU 1 GPU (Tesla 20) 5 0 1 2 4 8 Number of DC Solver Servers Dual Intel Xeon X5675 CPUs (3.06 GHz), fastest memory configuration, 1 Tesla 20 GPU per node, 1 Gb Ethernet interconnect, 40 million mesh cells
DC Main Controller The DC Main Controller gives you a complete overview about what is happening on your cluster. Job Status Machine Status Essential resources (RAM usage and disk space) are monitored as well in the 2014 version.
GPU Assignment Users who have smaller jobs can start multiple solver servers and assign each GPU to a separate server. This allows for a more efficient use of multi- GPU hardware
Supported Acceleration Methods Acceleration methods supported by the solvers of CST STUDIO SUITE. Solver Multithreading GPU Computing Distributed Computing MPI Computing on one GPU card Most other solvers support Multithreading and Distributed Computing for parameter sweeps and optimization.
Choose the Right Acceleration Method Solver Model Size Number of Simulations Acceleration Technique Transient below memory limit of GPU hardware low GPU Computing Transient below memory limit of GPU hardware medium/high GPU Computing on a DC Cluster (Distributed Excitations) Transient above memory limit of GPU hardware - MPI or combined MPI+GPU Computing Frequency Domain can be handled by a single machine medium/high Distributed Computing (Distributed Frequency Points) Integral Equation can't be handled by a single machine - MPI Computing Integral Equation can be handled by a single machine medium/high Distributed Computing (Distributed Frequency Points) Parameter Sweep/Optimization n/a medium/high Distributed Computing
HPC in the Cloud CST is working together with HPC hardware and service providers to enable easy access to large computing power for challenging simulations which can't be run on in-house hardware. Users rent a CST license for the resources they need and pay the HPC provider for the required hardware. + HPC system provider Currently supported providers hosting CST STUDIO SUITE: More information can be found in the HPC section of our website: https://www.cst.com/products/hpc/cloud-computing
HPC Hardware Design Process A general hardware recommendation is available on our website which helps you to configure standard systems (e.g. workstations) for CST STUDIO SUITE. For HPC systems (multi-gpu systems, clusters) our hardware experts are available to guide you through the whole process of system design and benchmarking to ensure that your new system is compatible with CST STUDIO SUITE and delivers the expected performance. HPC System Design Process Personal contact with CST engineers to design solution. Benchmarking of designed computing solution in the hardware test center of the preferred vendor. Buy the machine if it fulfills your expectations.