Preliminary Study in Parallel Simulation of Equation-Based System-Level Physical Models

2014 ◽  
Author(s):  
Yan Zhao ◽  
Liping Chen ◽  
Jianwan Ding ◽  
Jianjun Zhao
Keyword(s):  
Parallel Simulation ◽  
Parallel Programs ◽  
Physical Models ◽  
System Level ◽  
Maximum Speed ◽  
Task Graph ◽  
Simulation Code ◽  
Equation Solving ◽  
Speed Up ◽  
Preliminary Study

As the maximum speed for processors seems to have reached its peak, parallelization becomes an important way to speed up the simulation. This paper discusses the problems of parallelizing the task graphs that represent the system-level physical models at the equation level. The methods for estimating the runtimes of the equation solving tasks are presented. There is a focus on an interactive tool which is designed to parallelize the task graph semi-automatically and to generate the parallel simulation code automatically. For further research, this tool can be used to test the automatic parallelizing algorithms. Several example models are parallelized. The parallel programs are generated and experimented. The final results suggest that parallelization at the equation level is effective and better performances are supposed to be found in bigger systems.

scholarly journals PhotoNs-GPU: A GPU accelerated cosmological simulation code

2021 ◽  
Vol 21 (11) ◽  
pp. 281
Author(s):  
Qiao Wang ◽  
Chen Meng
Keyword(s):  
Special Functions ◽  
Fast Multipole Method ◽  
Kernel Functions ◽  
Peak Performance ◽  
Double Precision ◽  
Simulation Code ◽  
Small Noise ◽  
Mixed Precision ◽  
Speed Up ◽  
Different Levels

Abstract We present a GPU-accelerated cosmological simulation code, PhotoNs-GPU, based on an algorithm of Particle Mesh Fast Multipole Method (PM-FMM), and focus on the GPU utilization and optimization. A proper interpolated method for truncated gravity is introduced to speed up the special functions in kernels. We verify the GPU code in mixed precision and different levels of theinterpolated method on GPU. A run with single precision is roughly two times faster than double precision for current practical cosmological simulations. But it could induce an unbiased small noise in power spectrum. Compared with the CPU version of PhotoNs and Gadget-2, the efficiency of the new code is significantly improved. Activated all the optimizations on the memory access, kernel functions and concurrency management, the peak performance of our test runs achieves 48% of the theoretical speed and the average performance approaches to ∼35% on GPU.

scholarly journals Comparison of Serial and Parallel Computation on Predicting Missing Data with EM Algorithm

2021 ◽  
Vol 18 (1) ◽  
pp. 22-30
Author(s):  
Erna Nurmawati ◽  
Robby Hasan Pangaribuan ◽  
Ibnu Santoso
Keyword(s):  
Parallel Computing ◽  
Missing Data ◽  
Data Processing ◽  
Em Algorithm ◽  
Parallel Computation ◽  
Incomplete Data ◽  
Parallel Programs ◽  
Missing Value ◽  
Speed Up ◽  
Compute Time

One way to deal with the presence of missing value or incomplete data is to impute the data using EM Algorithm. The need for large and fast data processing is necessary to implement parallel computing on EM algorithm serial program. In the parallel program architecture of EM Algorithm in this study, the controller is only related to the EM module whereas the EM module itself uses matrix and vector modules intensively. Parallelization is done by using OpenMP in EM modules which results in faster compute time on parallel programs than serial programs. Parallel computing with a thread of 4 (four) increases speed up, reduces compute time, and reduces efficiency when compared to parallel computing by the number of threads 2 (two).

scholarly journals The effect of the north-east ice stream on the Greenland ice sheet in changing climates

2007 ◽  
Vol 1 (1) ◽  
pp. 41-76 ◽  
Author(s):  
R. Greve ◽  
S. Otsu
Keyword(s):  
Large Scale ◽  
Ice Sheet ◽  
Greenland Ice Sheet ◽  
Simulation Code ◽  
North East ◽  
The North ◽  
Ice Stream ◽  
Basal Sliding ◽  
Speed Up ◽  
Fast Flow

Abstract. The north-east Greenland ice stream (NEGIS) was discovered as a large fast-flow feature of the Greenland ice sheet by synthetic aperture radar (SAR) imaginary of the ERS-1 satellite. In this study, the NEGIS is implemented in the dynamic/thermodynamic, large-scale ice-sheet model SICOPOLIS (Simulation Code for POLythermal Ice Sheets). In the first step, we simulate the evolution of the ice sheet on a 10-km grid for the period from 250 ka ago until today, driven by a climatology reconstructed from a combination of present-day observations and GCM results for the past. We assume that the NEGIS area is characterized by enhanced basal sliding compared to the "normal", slowly-flowing areas of the ice sheet, and find that the misfit between simulated and observed ice thicknesses and surface velocities is minimized for a sliding enhancement by the factor three. In the second step, the consequences of the NEGIS, and also of surface-meltwater-induced acceleration of basal sliding, for the possible decay of the Greenland ice sheet in future warming climates are investigated. It is demonstrated that the ice sheet is generally very susceptible to global warming on time-scales of centuries and that surface-meltwater-induced acceleration of basal sliding can speed up the decay significantly, whereas the NEGIS is not likely to dynamically destabilize the ice sheet as a whole.

scholarly journals Timing of Optical Pulses from the Crab Nebula Pulsar

1971 ◽  
Vol 46 ◽  
pp. 119-124
Author(s):  
P. E. Boynton ◽  
E. J. Groth ◽  
R. B. Partridge ◽  
David T. Wilkinson
Keyword(s):  
Neutron Star ◽  
Crab Nebula ◽  
Physical Models ◽  
Quiet Period ◽  
Eccentric Orbit ◽  
Optical Pulses ◽  
Neutron Star Crust ◽  
Alternate Explanation ◽  
Speed Up ◽  
The Crab Nebula

Timing the arrival of optical pulses from NP 0532 is a potentially important tool for studying the physics of this fascinating object. However, there are some difficulties in interpreting the data in terms of physical models. Some progress has been made on understanding the largest effect – the pulsar braking mechanism. The glitch of late September, 1969 can be interpreted as the speed-up, and subsequent relaxation, of the rotation of a neutron star crust. An alternate explanation is that of a planet in an eccentric orbit. Both models fit the rather meager data near the event. A small sinusoidal effect is indicated in a relatively quiet period of the data.

A Study and Development of Primary Circuit Simulation Code for China Experimental Fast Reactor

2013 ◽  
Author(s):  
Jin Wang ◽  
Donghui Zhang ◽  
Wenjun Hu ◽  
Lixia Ren
Keyword(s):  
Fast Reactor ◽  
Nuclear Energy ◽  
Circuit Simulation ◽  
Thermal Power ◽  
Physical Models ◽  
Primary Circuit ◽  
Cooling Channel ◽  
Simulation Code ◽  
Wide Range ◽  
China Experimental Fast Reactor

A fast reactor is one of recommended candidates of Generation IV nuclear energy systems, which would meet wide requirements such as sustainability, safety and economics for nuclear energy development. To be the China’s first fast reactor, China Experimental Fast Reactor (CEFR) typical technical options are following: 65 MW thermal power and 20 MW electric power, three circuits of sodium-sodium-water, integrated pool type structure for the primary circuit. To establish modular simulation system for sodium fast reactor, the code which simulated the thermal-hydraulic behavior of primary circuit was developed. The physical models include reactor core, reactor vessel cooling channel, pumps, protection vessel, intermediate heat exchangers, ionization chamber cooling channel, cold sodium pool, hot sodium pool, inlet plenum, and pipes, etc. The code could compute coolant pressures, flow rates, and temperatures in the primary circuit. This module was designed for analysis of a wide range of transients. Although based on CEFR, it can treat an arbitrary arrangement of components.

Complexity of Task Graph Scheduling with Fixed Communication Capacity

1997 ◽  
Vol 08 (01) ◽  
pp. 43-66 ◽  
Author(s):  
Lucian Finta ◽  
Zhen Liu
Keyword(s):  
Resource Constraints ◽  
Parallel Programs ◽  
Multiprocessor System ◽  
Task Graph ◽  
Multiprocessor Systems ◽  
Scheduling Problem ◽  
Interprocessor Communication ◽  
Communication Capacity ◽  
Data Semantics ◽  
Communication Resource

Consider a scheduling problem of parallel computations in multiprocessor systems. Let a parallel program be modeled by a task graph, where vertices represent tasks and arcs the communications between tasks. An interprocessor communication time incurs when two tasks assigned to two different processors have to communicate. Such a scheduling problem has recently been studied in the literature, mostly for the case where interprocessor communication times are fully determined. In this paper, we consider the scheduling problem with communication resource constraints. More specifically, we consider the case where all interprocessor communications take place on a network of bounded capacity. We consider two variants of the problem: communications with independent-data semantics and common-data semantics. We show that even for very specific subproblems, viz. scheduling of general graphs on two processors and scheduling of binary trees on an infinite number of processors, the minimization of the makespan of parallel programs in such a multiprocessor system is strongly [Formula: see text]-hard. We first establish the results for the case of capacity 1, referred to as the single-bus system. We then extend the results to the more general case of fixed communication capacities. As a consequence, the general scheduling problem of parallel programs with communication resource constraints is strongly [Formula: see text]-hard. These results are to be contrasted with the corresponding scheduling problems without contraint on the communication capacity, where the two-processor case has unknown time complexity and the infinite-processor case is polynomial. Our results are also extended to the case of broadcasting communications, and can be applied to multiprocessor systems with shared memory.

Sign in / Sign up

Export Citation Format

Share Document