Real-time object detection in software with custom vector instructions and algorithm changes

Edwards, Joseph R.; Lemieux, Guy

doi:10.1109/asap.2017.7995262

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al utilized the custom instruction approach to protect cryptographic software implementations against Side Channel Attack (SCA) by emulating the behavior of the secure hardware circuits [5]. Similarly, custom instruction approach has also been used to efficiently implement the face detection algorithm [8] and S8 AES algorithm [1]. Viterbi algorithm has also been implemented in Xtensa [26] and in DLX [2] processors using custom instruction approach.…”

Section: Related Workmentioning

confidence: 99%

Accelerating Viterbi Algorithm using Custom Instruction Approach

Ahmad

Abbassi

Sanwal

et al. 2018

2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)

View full text Add to dashboard Cite

In recent years, the decoding algorithms in communication networks are becoming increasingly complex aiming to achieve high reliability in correctly decoding received messages. These decoding algorithms involve computationally complex operations requiring high performance computing hardware, which are generally expensive. A cost-effective solution is to enhance the Instruction Set Architecture (ISA) of the processors by creating new custom instructions for the computational parts of the decoding algorithms. In this paper, we propose to utilize the custom instruction approach to efficiently implement the widely used Viterbi decoding algorithm by adding the assembly language instructions to the ISA of DLX, PicoJava II and NIOS II processors, which represent RISC, stack and FPGA-based softcore processor architectures, respectively. By using the custom instruction approach, the execution time of the Viterbi algorithm is significantly improved by approximately 3 times for DLX and PicoJava II, and by 2 times for NIOS II.

show abstract

Section: Related Workmentioning

confidence: 99%