Pregled bibliografske jedinice broj: 1059558
An Area Efficient and Reusable HEVC 1D-DCT Hardware Accelerator
An Area Efficient and Reusable HEVC 1D-DCT Hardware Accelerator // Parallel Processing and Applied Mathematics / Wyrzykowski, Roman ; Deelman, Ewa ; Dongarra, Jack ; Karczewski, Konrad (ur.).
Białystok, Poljska: Springer, 2020. str. 199-208 doi:10.1007/978-3-030-43229-4_18 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1059558 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
An Area Efficient and Reusable HEVC 1D-DCT Hardware Accelerator
Autori
Cobrnic, Mate ; Duspara, Alen ; Dragic, Leon ; Piljic, Igor ; Mlinaric, Hrvoje ; Kovac, Mario
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Parallel Processing and Applied Mathematics
/ Wyrzykowski, Roman ; Deelman, Ewa ; Dongarra, Jack ; Karczewski, Konrad - : Springer, 2020, 199-208
ISBN
978-3-030-43228-7
Skup
13th International Conference on Parallel Processing and Applied Mathematics
Mjesto i datum
Białystok, Poljska, 08.09.2019. - 11.09.2019
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Integer Discrete Cosine Transform (DCT) ; High Efficiency Video Coding (HEVC) ; Field-Programmable Gate Array (FPGA) ; Pipelined architecture
Sažetak
In this paper is presented an area efficient reusable architecture for integer one dimensional Discrete Cosine Transform (1D DCT) with adjustable transform sizes in High Efficiency Video Coding (HEVC). Optimization is based on exploiting of symmetry and subset properties of the transform matrix. The proposed multiply-accumulate architecture is fully pipelined and applicable for all transform sizes. It provides the interface over which the processing system can control the datapath of the transform process and the synchronization channel that enables the system to receive the feedback information about utilization from the device. An intuitive line approach for calculating transform coefficients for all transform sizes was used instead of the commonly applied recursive decomposition approach. This approach simplifies disabling of lines that are not employed for a particular transform size. The proposed architecture is implemented on the FPGA platform, can operate at 407, 5 MHz, achieves throughput of 815 Msps and can support encoding of a 4K UHD@30 fps video sequence in real time.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
EK-H2020-826647 - Inicijativa za Europski procesor (EPI SGA1) (Kovač, Mario, EK ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
Citiraj ovu publikaciju:
Časopis indeksira:
- Scopus