Information Processing Device with Software-Based Failure Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing failure detection methods for process execution hardware require hardware duplication, limiting the compact configuration of processing elements.
Innovation Solution
An information processing apparatus with a thread scheduler that allocates processes to multiple process execution hardware, incorporating a code reader and allocator to execute diagnostic codes without duplication, allowing failure diagnosis within a mean time to failure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If hardware duplication is used for failure detection, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent uses software copying instead of hardware copying for failure detection. The same diagnostic code is executed on different hardware resources at different timings, creating a virtual duplicate execution environment without physical hardware duplication. This allows reliability improvement through comparative analysis while avoiding the complexity of duplicating hardware structures.
Solution Approach 2:
The patent changes execution parameters (timing and hardware resource assignment) rather than duplicating hardware. By executing the same diagnostic code with different timing parameters and hardware resource assignments, the system achieves failure detection capability without increasing hardware complexity, resolving the contradiction between reliability and device complexity.
2Measurement precision
If hardware duplication is implemented for diagnostic execution, then failure diagnosis accuracy is improved, but manufacturing cost increases
Solution Approach 1:
The patent makes existing hardware resources perform multiple functions: they execute both normal processing tasks and diagnostic code execution. This multi-functionality allows failure diagnosis accuracy to be improved using existing hardware without additional manufacturing costs, as the same hardware serves dual purposes rather than requiring dedicated diagnostic hardware.
Solution Approach 2:
The patent uses software-based code copying and execution instead of physical hardware copying for diagnostics. The diagnostic code is copied and executed on available hardware resources, achieving accurate failure diagnosis without the manufacturing cost of duplicating hardware components.
3Reliability
If dedicated diagnostic hardware is added, then failure detection capability is improved, but loss of time for normal processing increases
Solution Approach 1:
The patent dynamically assigns hardware resources based on operational needs. Hardware resources that are not currently needed for normal processing are dynamically allocated for diagnostic code execution, and then reassigned to normal processing when needed. This dynamic resource management allows failure detection capability to be maintained without permanently reducing normal processing throughput.
Solution Approach 2:
The patent implements periodic diagnostic execution during idle periods or between normal processing tasks. By scheduling diagnostic code execution periodically when hardware resources are available, the system maintains failure detection capability while minimizing impact on normal processing productivity, as diagnostics run during naturally occurring idle windows rather than competing for continuous resources.
Data Source
Figure 1(A)~1(C)
Figure 2
Figure 3
AI summary
An information processing apparatus includes a thread scheduler that allocates a process to multiple process execution hardware that process a program having a graph structure. The information processing apparatus includes: a code reader (141) that reads a diagnostic code stored in advance; and an allocator (142) that causes the multiple process execution hardware to execute the diagnostic code so as to complete diagnosis within a mean time to failure.