Research in the field of evolvable hardware can be split into the two related areas of evolutionary hardware design and adaptive hardware. While evolutionary hardware design is the use of evolutionary algorithms for creating innovative (and sometimes patentable) physical designs, the goal of adaptive hardware is to endow physical systems with some adaptive characteristics in order to allow them to operate successfully in a changing environment or under presence of faults. The EHW@FIT group does research in both areas. We also pioneered a design method in which an evolutionary algorithm is used to approximate digital circuits to obtain a good trade-off between the quality output and power consumption. Recently, we have been working on hardware accelerators of approximate neural networks.
Pinned Loading
Repositories
Showing 10 of 15 repositories
- timeloop-with-quantization Public Forked from NVlabs/timeloop
Timeloop performs modeling, mapping and code-generation for Tensor Algebra workloads running on Explicitly-Decoupled Data Orchestration (EDDO) architectures.
ehw-fit/timeloop-with-quantization’s past year of commit activity