Özet
In signal processing applications, accuracy of the results can be traded-off for reducing area and power consumption. In this work, finite impulse response filters are designed approximately on FPGA. A frequency response error, which can be adjusted depending on the application, is defined to determine approximation level. Coefficient sensitivity is nuMeriçally analysed for this error. With the result obtained from this analysis, a multiple constant multiplication optimization method is executed, with the aim of reducing transposed filter structure areas. The proposed sensitivity analysis and the modified multiple constant multiplication optimization are used in collaboration, on lowpass and bandpass filter realizations. When filter characteristic error tolerances of 0.01 and 0.001 are introduced, an average area reduction of 534% and 3-28% are obtained, respectively.
Tercüme edilen katkı başlığı | Approximate implementation of FIR filters on FPGA |
---|---|
Orijinal dil | Türkçe |
Ana bilgisayar yayını başlığı | 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 |
Yayınlayan | Institute of Electrical and Electronics Engineers Inc. |
Sayfalar | 1-4 |
Sayfa sayısı | 4 |
ISBN (Elektronik) | 9781538615010 |
DOI'lar | |
Yayın durumu | Yayınlandı - 5 Tem 2018 |
Etkinlik | 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 - Izmir, Turkey Süre: 2 May 2018 → 5 May 2018 |
Yayın serisi
Adı | 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 |
---|
???event.eventtypes.event.conference???
???event.eventtypes.event.conference??? | 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 |
---|---|
Ülke/Bölge | Turkey |
Şehir | Izmir |
Periyot | 2/05/18 → 5/05/18 |
Bibliyografik not
Publisher Copyright:© 2018 IEEE.
Keywords
- Approximate computing
- Digital filters
- FIR
- FPGA