DFT Parallel Processing Settings for Cost-Aware Node Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods face challenges in determining the optimal number of nodes for parallel processing of density functional theory calculations, leading to increased time, power, and monetary costs, especially when verifying the physical properties of substances.
Innovation Solution
An information processing device that calculates the sum of costs for different candidates of setting values related to the execution environment for parallel processing of density functional theory calculations, determining the optimal setting value based on these costs to minimize resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the number of nodes for parallel processing is increased, then the processing speed of density functional theory calculations is improved, but the time, power, and monetary costs increase
Solution Approach 1:
The patent changes the parameter of node configuration by evaluating multiple candidate settings (different numbers of nodes, processes, and threads) and selecting the optimal configuration that balances processing speed with power consumption and cost, rather than simply increasing nodes to improve speed
Solution Approach 2:
The patent implements a feedback mechanism by calculating the sum of costs for each candidate setting based on model expressions that estimate power consumption and other resources, then using this cost information to determine the optimal setting that minimizes energy loss while maintaining acceptable processing speed
2Speed
If the number of nodes for parallel processing is increased, then the processing speed of density functional theory calculations is improved, but the monetary cost increases
Solution Approach 1:
The patent evaluates multiple parameter configurations for parallel processing (number of nodes, processes per node, threads per process) and selects the optimal set of parameters that achieves sufficient processing speed while minimizing monetary cost, rather than maximally increasing nodes
Solution Approach 2:
The system calculates cost estimates for each candidate configuration using model expressions and feeds this information back to select the setting that provides the best cost-performance ratio, enabling cost-aware optimization of parallel processing
3Productivity
If the optimal setting value is determined through cost calculation, then the resource usage efficiency is improved, but the calculation complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-calculating and storing model expressions that represent the relationship between setting values and costs before actual parallel processing. This allows rapid evaluation of candidate settings without performing complex real-time calculations, thus improving resource efficiency while limiting calculation complexity to the preliminary modeling phase
Data Source
AI summary
A computer-readable recording medium stores therein an information processing program causing a computer to execute a process, the process including: obtaining one or more candidates for a setting value related to an execution environment for parallel processing of a density functional theory calculation for a substance; calculating a sum of costs for each of the obtained one or more candidates, the sum of costs being calculated based on one or more model expressions that, respectively, correspond to one or more calculation processes related to the density functional theory calculation and that, respectively, output an estimated value of a cost incurred when a corresponding one of the one or more calculation processes is performed in response to input of the setting value; and determining the setting value based on the sum calculated for the each of the obtained one or more candidates.