Parallel Processing

<< Click to Display Table of Contents >>

Navigation:  Analysis Setup > Analysis Function >

Parallel Processing

In the modern plastic injection product development, the quality and the time to the market are both the crucial concerns. Due to the geometry and design that are getting more complicated day by day, how to run the simulation more efficiently is the key issue. The three major concerns of industrial CAE users are accuracy, computing speed and user-friendliness. True 3D simulation not only satisfies those concerns, but offers more advantages that conventional 2.5D cannot reach, such as microstructure information, minimized model simplification…etc. However, true 3D simulation inevitably increases computing time and requires more memory. Therefore, the demand for high accuracy and high performance computing can never be underestimated. Obviously, newer and more powerful CPU can improve computing speed. However, the modern CPU won’t increase the clock rate a lot anymore; Instead, the number of cores in the CPU will keep increasing. . Utilization of multi-core CPU is therefore the most effective approach. Furthermore, parallel computing on multi-core PC clusters is an inexpensive alternative to supercomputer for solving large-scale problems of scientific and engineering applications.

 

Remark:

Sometimes, even if the parallel computing environment is functioning normally, the parallel computing may terminate suddenly. This may result from the Anti-Virus software. It is because that running parallel computing may modify files frequently, which may induce Anti-Virus software to do excessive check, and interrupt parallel computing. Currently, NOD 32.2.7 Anti-Virus software is known that it may interrupt parallel computing. Thus, it is recommended that users close Anti-Virus software before running parallel computing.