Mimic computing for password recovery

The recovery of encrypted information based on password authentication is an important mechanism to maintain network security. As a result, many password recovery systems have been developed. However, those systems are inefficient and energy intensive because they are primarily optimized for CPUs and GPUs. Inspired by a new computing model, namely, mimic computing - a hardware/software co-designed computing model that can dynamically reconfigure appropriate system structures based on application features - we propose a novel password recovery system. The design of such a system is non-trivial and includes several challenges: (1) how to build high-performance password recovery reconfigurable algorithms; (2) how to partition the hardware and software for password recovery; (3) how to optimize resource utilization and power consumption; and (4) how to improve the scalability. We present our insights, design decisions, and implementation details to address these challenges. Our extensive experiments show that the newly designed password recovery system significantly outperforms traditional CPU-based and GPU-based systems in terms of both efficiency and energy consumption. In particular, our system is 27.81 and 4.23 times faster than CPU-based and GPU-based systems in terms of password cracking, and our system consumes 14.97 and 5.97 times less energy than CPU-based and GPU-based systems.