TY - GEN
T1 - An operand status based instruction steering scheme for clustered architectures
AU - Sato, Yukinori
AU - Suzuki, Ken Ichi
AU - Nakamura, Tadao
PY - 2005
Y1 - 2005
N2 - Clustered architectures which intend to process data within a localized PE are one of the approaches to increase the performance under the difficulties of the wire delay problems. The performance of the clustered architecture depends on the implemented instruction steering scheme. Existing steering schemes insert inter-PE communications to achieve load balance among PEs. These insertions delay the executions of the dependent instructions and lead to the degradation of the performance. In this paper, we propose a novel instruction steering scheme, which gives priority to critical dependencies. The way to find out the critical dependencies is by observing the status of the source operands of an instruction. We evaluate the proposed scheme and compare it with the existing ones. The results show that the proposed scheme outperforms the existing schemes in terms of instruction per clock because of reductions of the critical inter-PE communications with superior load balance among the PEs.
AB - Clustered architectures which intend to process data within a localized PE are one of the approaches to increase the performance under the difficulties of the wire delay problems. The performance of the clustered architecture depends on the implemented instruction steering scheme. Existing steering schemes insert inter-PE communications to achieve load balance among PEs. These insertions delay the executions of the dependent instructions and lead to the degradation of the performance. In this paper, we propose a novel instruction steering scheme, which gives priority to critical dependencies. The way to find out the critical dependencies is by observing the status of the source operands of an instruction. We evaluate the proposed scheme and compare it with the existing ones. The results show that the proposed scheme outperforms the existing schemes in terms of instruction per clock because of reductions of the critical inter-PE communications with superior load balance among the PEs.
KW - Clustered architecture
KW - Data dependence-based design
KW - Instruction steering
KW - Instruction-level parallelism
UR - http://www.scopus.com/inward/record.url?scp=33947144999&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33947144999&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:33947144999
SN - 9781932415544
T3 - Proceedings of the 2005 International Conference on Computer Design, CDES'05
SP - 168
EP - 174
BT - Proceedings of the 2005 International Conference on Computer Design, CDES'05
T2 - 2005 International Conference on Computer Design, CDES'05
Y2 - 27 June 2005 through 30 June 2005
ER -