Abstract | ||
---|---|---|
ARMv8 based processors are now prevalent in mobile devices while the majority of applications in Google App Store are still ARMv7 code. This causes the desire for supporting backward compatibility. Such circumstances not only complicate the hardware design but also overlook the benefits from running on new ARMv8 processors. This paper presents a software based solution for the backward compatibility via Dynamic Binary Translation (DBT). This DBT framework is able to run ARMv7 executables on pure ARMv8 devices. Moreover, by exploiting ARMv8 SIMD capabilities, the execution achieves an average speedup of 1.49× compared to ARMv7 native run across various benchmarks.
|
Year | Venue | Field |
---|---|---|
2018 | ESWEEK '18: Fourteenth Embedded Systems Week
Turin
Italy
September, 2018 | ARM architecture,App store,Computer science,Parallel computing,SIMD,Binary translation,Software,Backward compatibility,Executable,Speedup |
DocType | ISBN | Citations |
Conference | 978-1-5386-5564-1 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sheng-Yu Fu | 1 | 15 | 5.34 |
Chih-Min Lin | 2 | 0 | 0.34 |
Ding-Yong Hong | 3 | 85 | 9.88 |
Yu-Ping Liu | 4 | 8 | 4.86 |
Jan-Jan Wu | 5 | 550 | 59.21 |
Wei-Chung Hsu | 6 | 719 | 58.87 |