SDC vulnerable instruction recognition method based on error propagation analysis
A recognition method and instruction technology, applied in the computer field, can solve problems such as high time and space costs, state explosion, and low accuracy rate, and achieve the effects of avoiding limitations, fewer injection errors, and high accuracy rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0050] by figure 1 The sum program in is taken as an example to illustrate the process of the recognition algorithm. First, find out the key instructions among all instructions. According to the definition of key instructions, node 18 is a key instruction, and other instructions are all non-key instructions. Fault injection is performed on node 18 by modifying one bit of the destination operand, and the result is found to be wrong, and node 18 is added to the vulnerable key instruction set of SDC; the second step is to perform error injection and inference on non-critical instructions. Use the equivalent class injection method to sample the above non-critical instructions, add them to the injection schedule, and modify the destination operand of node 1 from 0 to 1, and the final result changes from 1 to 2, resulting in SDC, and then run inference algorithm. Starting from node 1, sequentially compare the written data of nodes 2-18 with the written data of the same node durin...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 