TY - GEN
T1 - A floorplan-driven high-level synthesis algorithm with operation chainings using chaining enumeration
AU - Teradat, Kotaro
AU - Yanagisawa, Masao
AU - Togawa, Nozomu
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2015/2/5
Y1 - 2015/2/5
N2 - In deep-submicron era, interconnection delays are not negligible even in high-level synthesis and RDR (Regular-Distributed-Register) architecture has been proposed to cope with this problem. In this paper, we propose a high-level synthesis algorithm using operation chainings which reduces the overall latency targeting RDR architectures. Our algorithm consists of three steps: The first step enumerates candidates for chaining. The second step introduces maximal chaining distance (MCD), which gives the maximum allowable distance on RDR architecture between chaining candidate operations. The last step performs list-scheduling and binding simultaneously using the results of two preceding steps. Our algorithm enumerates feasible chaining candidates and selects the best ones for RDR architecture. Experimental results show that our algorithm reduces the latency by up to 28.6%, the number of registers by up to 37.5%, the number of multiplexers by up to 25.0%, compared to the conventional approaches.
AB - In deep-submicron era, interconnection delays are not negligible even in high-level synthesis and RDR (Regular-Distributed-Register) architecture has been proposed to cope with this problem. In this paper, we propose a high-level synthesis algorithm using operation chainings which reduces the overall latency targeting RDR architectures. Our algorithm consists of three steps: The first step enumerates candidates for chaining. The second step introduces maximal chaining distance (MCD), which gives the maximum allowable distance on RDR architecture between chaining candidate operations. The last step performs list-scheduling and binding simultaneously using the results of two preceding steps. Our algorithm enumerates feasible chaining candidates and selects the best ones for RDR architecture. Experimental results show that our algorithm reduces the latency by up to 28.6%, the number of registers by up to 37.5%, the number of multiplexers by up to 25.0%, compared to the conventional approaches.
UR - http://www.scopus.com/inward/record.url?scp=84937826465&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84937826465&partnerID=8YFLogxK
U2 - 10.1109/APCCAS.2014.7032766
DO - 10.1109/APCCAS.2014.7032766
M3 - Conference contribution
AN - SCOPUS:84937826465
T3 - IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS
SP - 248
EP - 251
BT - 2014 IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2014
Y2 - 17 November 2014 through 20 November 2014
ER -