Charged Particle Beam Drawing Daemon Resource Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional charged particle beam drawing apparatuses face inefficiencies in throughput due to mismatched processing loads, where either underutilization of CPUs occurs when the load is lower than estimated or excessive memory utilization slows processing when the load is higher, leading to suboptimal performance.
Innovation Solution
The apparatus incorporates a daemon system that dynamically manages processing and memory resources by identifying free CPU and memory resources, allowing for the allocation of additional processes when resources are available and refusing new processes when shortages are detected, thereby optimizing resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a predetermined number of CPUs are simultaneously used with a fixed memory utilization rate limit, then system stability is maintained, but throughput cannot be sufficiently increased when actual processing load is smaller than estimated processing load
Solution Approach 1:
The patent implements dynamic resource allocation by allowing the memory utilization rate limit to be changed from a fixed predetermined value to a variable parameter that adapts to actual processing conditions. The system dynamically adjusts the number of simultaneously executable processes based on real-time memory utilization monitoring, enabling throughput optimization without requiring complex manual intervention.
Solution Approach 2:
The patent employs feedback mechanisms where the system continuously monitors memory utilization rates and processing loads, then uses this information to adjust resource allocation decisions. The memory management unit receives feedback about actual processing demands and dynamically modifies the predetermined memory utilization rate limit accordingly, creating a closed-loop control system that optimizes throughput while maintaining stability.
2Reliability
If a predetermined number of CPUs are simultaneously used to maintain memory utilization rate below a limit, then memory stability is ensured, but processing speed decreases when actual processing load is larger than estimated processing load
Solution Approach 1:
The system dynamically adjusts the memory utilization rate limit based on actual processing conditions rather than maintaining a fixed predetermined value. When processing load increases, the system can raise the memory utilization threshold, allowing more memory to be allocated to active processes, thereby maintaining processing speed while still preventing complete system failure.
Solution Approach 2:
The patent changes the parameter of memory utilization rate limit from a static predetermined value to a dynamic parameter that can be adjusted based on processing demands. This parameter change enables the system to adapt to varying workloads, maintaining both reliability and processing speed by optimizing memory allocation in real-time according to actual conditions.
3Productivity
If the memory utilization rate exceeds the limit value, then more processing capacity can be utilized, but processing speed decreases because processes are performed using slower storage devices
Solution Approach 1:
The patent allows memory utilization to partially exceed the traditional limit by implementing a dynamic threshold mechanism. Instead of strictly enforcing a fixed memory utilization rate limit, the system permits controlled excess utilization when beneficial, using the faster memory resources before resorting to slower storage devices, thereby maintaining processing speed while increasing overall processing capacity.
Solution Approach 2:
The system introduces an intermediary memory buffer that acts as a bridge between fast memory and slow storage devices. By dynamically managing this intermediary buffer and allowing its utilization to flexibly exceed traditional limits, the system can maintain high processing speeds by keeping data in fast memory longer, only spilling to slow storage when absolutely necessary.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances throughput by ensuring that CPU and memory resources are utilized efficiently, preventing bottlenecks and maintaining processing speed regardless of varying loads, thus improving overall performance.
Implementation Method 1
patterns corresponding to figures included in a drawing data are drawn in a drawing area of a workpiece by applying a charged particle beam to the workpiece
Data Source
AI summary
In a charged particle beam drawing apparatus, if at least one of calculating portions is free and at least one memory includes a free portion, a report that a next process can be additionally started by using at least one free calculating portion and the free portion of the memory, is transferred from a daemon to a writing control unit, and the next process is additionally started by the daemon on the basis of a start request transferred from the writing control unit to the daemon. If there is a possibility of a shortage of the calculating portions and the memory, and if a start request for starting a next process is transferred from the writing control unit to the daemon, the start request for starting the next process is refused by the daemon.