bibtype |
C -
Conference Paper (international conference)
|
ARLID |
0075993 |
utime |
20240111140645.8 |
mtime |
20070206235959.9 |
title
(primary) (eng) |
Efficient FPGA Implementation of Equalizer for Finite Interval Constant Modulus Algorithm |
specification |
page_count |
10 s. |
media_type |
CD-ROM |
|
serial |
ARLID |
cav_un_epca*0078249 |
ISBN |
1-4244-0777-X |
title
|
IEEE Symposium on Industrial Embedded Systems - IES 2006, Proceedings of |
page_num |
1-10 |
publisher |
place |
Lyon |
name |
CNRS-ENS |
year |
2006 |
|
|
title
(cze) |
Efektivní FPGA implementace FI-CMA ekvalizéru |
keyword |
high-level synthesis |
keyword |
cyclic scheduling |
keyword |
iterative algorithms |
keyword |
imperfectly nested loops |
keyword |
integer linear programming |
keyword |
FPGA |
keyword |
control |
author
(primary) |
ARLID |
cav_un_auth*0202761 |
name1 |
Šůcha |
name2 |
P. |
country |
CZ |
|
author
|
ARLID |
cav_un_auth*0202762 |
name1 |
Hanzálek |
name2 |
Z. |
country |
CZ |
|
author
|
ARLID |
cav_un_auth*0101105 |
name1 |
Heřmánek |
name2 |
Antonín |
institution |
UTIA-B |
fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
author
|
ARLID |
cav_un_auth*0101190 |
name1 |
Schier |
name2 |
Jan |
institution |
UTIA-B |
full_dept |
Department of Image Processing |
fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
source |
source_type |
textový dokument |
|
COSATI |
09 |
COSATI |
09J |
cas_special |
project |
project_id |
1ET300750402 |
agency |
GA AV ČR |
country |
CZ |
ARLID |
cav_un_auth*0001795 |
|
project |
project_id |
1ET400750406 |
agency |
GA AV ČR |
country |
CZ |
ARLID |
cav_un_auth*0001796 |
|
project |
project_id |
1M0567 |
agency |
GA MŠk |
country |
CZ |
ARLID |
cav_un_auth*0202350 |
|
research |
CEZ:AV0Z10750506 |
abstract
(eng) |
This paper deals with the optimization of iterative algorithms with matrix operations or nested loops for hardware implementation in FPGA, using Integer Linear Programming (ILP). The method is demonstrated on an implementation of the FI-CMA. We used two pipelined arithmetic libraries based on the logarithmic number system or the IEEE floating-point number system. Traditional approaches to the scheduling of nested loops lead to a relatively large code, which is unsuitable for FPGA implementation. This paper presents a new high-level synthesis methodology, which models both, iterative loops and imperfectly nested loops, by means of the system of linear inequalities. Moreover, memory access is considered as an additional resource constraint. Since the solutions of ILP formulated problems are known to be computationally intensive, important part of the article is devoted to the reduction of the problem size. |
abstract
(cze) |
Příspěvek presentuje metodu optimalizace iterativních algoritmů s maticovými operacemi nebo s vnořenými smyčkami a její použití pro implementaci těchto algoritmů na FPGA. Metoda je demonstrována na implementaci FI-CMA ekvalizéru. V práci byli použity dvě pipelinované aritmetické knihovny pro práci s necelými čísli: logaritmická aritmetika a standardní IEEE floating pointová aritmetika. Tradiční metody optimalizace vnořených smyček vedou ke kódu, který není vhodný pro implementaci na FPGA. Tento příspěvek presentuje novou metodologii syntézy vyšší úrovně, která je schopna modelovat obecné vnořené smyčky pomocí systému nerovností. Navíc, počet přístupů do paměti je uvažována jako přádavné omezující kritérium. Článek se také zabývá snížením výpočetní náročnosti ILP problému. |
action |
ARLID |
cav_un_auth*0225280 |
name |
IEEE Symposium on Industrial Embedded Systems - IES 2006 |
place |
Antibes Juan-Les-Pins |
dates |
18.10.2006-20.10.2006 |
country |
FR |
|
reportyear |
2007 |
RIV |
JA |
permalink |
http://hdl.handle.net/11104/0143207 |
arlyear |
2006 |
mrcbU56 |
textový dokument |
mrcbU63 |
cav_un_epca*0078249 IEEE Symposium on Industrial Embedded Systems - IES 2006, Proceedings of 1-4244-0777-X 1 10 Lyon CNRS-ENS 2006 |
|