2results about How to "Solve the complex calculation process" patented technology

The invention belongs to the technical field of ship electronic information system fault propagation analysis, and provides a ship electronic information system fault propagation analysis method based on a public computing environment. Comprising the steps of hardware equipment and software resource identification, function classification and attribute evaluation, hardware resource connection diagram construction, dependency extraction, physical network topology, function logic network construction, association mapping and integration, dependent network construction, node normal threshold setting, failure node determination and load transfer formula setting. And determining a fault propagation mechanism and carrying out k-step iterative propagation. According to the method, the relationship and dependence between each functional module and hardware resources are more intuitive by constructing the system topology model, and an analysis basis is provided for subsequent fault propagation analysis; fault propagation analysis is performed on a physical domain and an information domain, and interaction between the physical domain and the information domain is considered, so that analysis of a fault propagation path is more comprehensive; and the fault propagation calculation process is simplified through a k-step method.

The application discloses a low-bit matrix calculation device with a floating-point scaling factor and a calculation method thereof. The device comprises a scaling factor processing module, an input module, a matrix calculation module, a floating-point accumulation module and an output module. The method first groups and quantizes weight and eigenvalue matrices to obtain quantization values and floating-point scaling factors; then, the scaling factor product is calculated in advance with a single accumulation length as a grouping unit; then, matrix multiplication and accumulation operation is performed, the result is multiplied by the scaling factor product after being converted into an fp16 or bfp16 format, and then accumulated into a final result; and finally, the result is output after being dequantized. The application simplifies the group-wise calculation process, saves hardware resources, guarantees calculation accuracy, meets different scene requirements and improves calculation efficiency by sharing the scaling factor product and using fp16 or bfp16 as an accumulator.