3D Shared Bus Architecture Using Inductive Coupling Interconnect

Akio Nomura, Yu Fujita, Hiroki Matsutani, Hideharu Amano

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Attention has been focused on 3D chip stacking for reducing the semiconductor area per chip while maintaining the overall performance. By using inductive coupling wireless Thru-Chip Interface (TCI) in chip stack for a 3D multiprocessor, the replacement/addition/removing of chips is made possible using the inductive coupling wireless TCI in the chip stack for a 3D multiprocessor and thus, high flexibility is provided. A bus can be easily formed with the TCI by stacking duplex wired coils in the same place on the stacked chip. However, traditional static time division multiple access (STDMA) cannot make use of the potential bus bandwidth, while dynamic time division multiple access (DTDMA) requires a lot of coils that cannot be efficiently used for the control signals. We propose an asynchronous TDMA bus (A-TDMA bus) that uses the CSMA/CD protocol and a resonant synchronous TDMA bus (RS-TDMA bus) that uses a resonant synchronized clock and a look-ahead technique to improve the use of the bandwidth of a 3D shared bus. The results of a network simulation using the GEM5 simulator showed that the zero-load latency of both proposed methods was reduced by 29% in a four-chip stack and 50% in an eight-chip stack compared to that of STDMA. A full system simulation using GEM5 shows that the execution time of the proposed methods decreased by 6.5% in the four-chip stack and 17% in the eight-chip stack compared with that of STDMA.

Original languageEnglish
Title of host publicationProceedings - IEEE 9th International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages259-266
Number of pages8
ISBN (Print)9781479986699
DOIs
Publication statusPublished - 2015 Nov 11
Event9th IEEE International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015 - Turin, Italy
Duration: 2015 Sep 232015 Sep 25

Other

Other9th IEEE International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015
CountryItaly
CityTurin
Period15/9/2315/9/25

Fingerprint

Time division multiple access
Bandwidth
Carrier sense multiple access
Clocks
Simulators
Semiconductor materials
Network protocols

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Nomura, A., Fujita, Y., Matsutani, H., & Amano, H. (2015). 3D Shared Bus Architecture Using Inductive Coupling Interconnect. In Proceedings - IEEE 9th International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015 (pp. 259-266). [7328213] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MCSoC.2015.27

3D Shared Bus Architecture Using Inductive Coupling Interconnect. / Nomura, Akio; Fujita, Yu; Matsutani, Hiroki; Amano, Hideharu.

Proceedings - IEEE 9th International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 259-266 7328213.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nomura, A, Fujita, Y, Matsutani, H & Amano, H 2015, 3D Shared Bus Architecture Using Inductive Coupling Interconnect. in Proceedings - IEEE 9th International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015., 7328213, Institute of Electrical and Electronics Engineers Inc., pp. 259-266, 9th IEEE International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015, Turin, Italy, 15/9/23. https://doi.org/10.1109/MCSoC.2015.27
Nomura A, Fujita Y, Matsutani H, Amano H. 3D Shared Bus Architecture Using Inductive Coupling Interconnect. In Proceedings - IEEE 9th International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 259-266. 7328213 https://doi.org/10.1109/MCSoC.2015.27
Nomura, Akio ; Fujita, Yu ; Matsutani, Hiroki ; Amano, Hideharu. / 3D Shared Bus Architecture Using Inductive Coupling Interconnect. Proceedings - IEEE 9th International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 259-266
@inproceedings{b476d97452274195920ff8fc68db1a42,
title = "3D Shared Bus Architecture Using Inductive Coupling Interconnect",
abstract = "Attention has been focused on 3D chip stacking for reducing the semiconductor area per chip while maintaining the overall performance. By using inductive coupling wireless Thru-Chip Interface (TCI) in chip stack for a 3D multiprocessor, the replacement/addition/removing of chips is made possible using the inductive coupling wireless TCI in the chip stack for a 3D multiprocessor and thus, high flexibility is provided. A bus can be easily formed with the TCI by stacking duplex wired coils in the same place on the stacked chip. However, traditional static time division multiple access (STDMA) cannot make use of the potential bus bandwidth, while dynamic time division multiple access (DTDMA) requires a lot of coils that cannot be efficiently used for the control signals. We propose an asynchronous TDMA bus (A-TDMA bus) that uses the CSMA/CD protocol and a resonant synchronous TDMA bus (RS-TDMA bus) that uses a resonant synchronized clock and a look-ahead technique to improve the use of the bandwidth of a 3D shared bus. The results of a network simulation using the GEM5 simulator showed that the zero-load latency of both proposed methods was reduced by 29{\%} in a four-chip stack and 50{\%} in an eight-chip stack compared to that of STDMA. A full system simulation using GEM5 shows that the execution time of the proposed methods decreased by 6.5{\%} in the four-chip stack and 17{\%} in the eight-chip stack compared with that of STDMA.",
author = "Akio Nomura and Yu Fujita and Hiroki Matsutani and Hideharu Amano",
year = "2015",
month = "11",
day = "11",
doi = "10.1109/MCSoC.2015.27",
language = "English",
isbn = "9781479986699",
pages = "259--266",
booktitle = "Proceedings - IEEE 9th International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - 3D Shared Bus Architecture Using Inductive Coupling Interconnect

AU - Nomura, Akio

AU - Fujita, Yu

AU - Matsutani, Hiroki

AU - Amano, Hideharu

PY - 2015/11/11

Y1 - 2015/11/11

N2 - Attention has been focused on 3D chip stacking for reducing the semiconductor area per chip while maintaining the overall performance. By using inductive coupling wireless Thru-Chip Interface (TCI) in chip stack for a 3D multiprocessor, the replacement/addition/removing of chips is made possible using the inductive coupling wireless TCI in the chip stack for a 3D multiprocessor and thus, high flexibility is provided. A bus can be easily formed with the TCI by stacking duplex wired coils in the same place on the stacked chip. However, traditional static time division multiple access (STDMA) cannot make use of the potential bus bandwidth, while dynamic time division multiple access (DTDMA) requires a lot of coils that cannot be efficiently used for the control signals. We propose an asynchronous TDMA bus (A-TDMA bus) that uses the CSMA/CD protocol and a resonant synchronous TDMA bus (RS-TDMA bus) that uses a resonant synchronized clock and a look-ahead technique to improve the use of the bandwidth of a 3D shared bus. The results of a network simulation using the GEM5 simulator showed that the zero-load latency of both proposed methods was reduced by 29% in a four-chip stack and 50% in an eight-chip stack compared to that of STDMA. A full system simulation using GEM5 shows that the execution time of the proposed methods decreased by 6.5% in the four-chip stack and 17% in the eight-chip stack compared with that of STDMA.

AB - Attention has been focused on 3D chip stacking for reducing the semiconductor area per chip while maintaining the overall performance. By using inductive coupling wireless Thru-Chip Interface (TCI) in chip stack for a 3D multiprocessor, the replacement/addition/removing of chips is made possible using the inductive coupling wireless TCI in the chip stack for a 3D multiprocessor and thus, high flexibility is provided. A bus can be easily formed with the TCI by stacking duplex wired coils in the same place on the stacked chip. However, traditional static time division multiple access (STDMA) cannot make use of the potential bus bandwidth, while dynamic time division multiple access (DTDMA) requires a lot of coils that cannot be efficiently used for the control signals. We propose an asynchronous TDMA bus (A-TDMA bus) that uses the CSMA/CD protocol and a resonant synchronous TDMA bus (RS-TDMA bus) that uses a resonant synchronized clock and a look-ahead technique to improve the use of the bandwidth of a 3D shared bus. The results of a network simulation using the GEM5 simulator showed that the zero-load latency of both proposed methods was reduced by 29% in a four-chip stack and 50% in an eight-chip stack compared to that of STDMA. A full system simulation using GEM5 shows that the execution time of the proposed methods decreased by 6.5% in the four-chip stack and 17% in the eight-chip stack compared with that of STDMA.

UR - http://www.scopus.com/inward/record.url?scp=84962705260&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962705260&partnerID=8YFLogxK

U2 - 10.1109/MCSoC.2015.27

DO - 10.1109/MCSoC.2015.27

M3 - Conference contribution

AN - SCOPUS:84962705260

SN - 9781479986699

SP - 259

EP - 266

BT - Proceedings - IEEE 9th International Symposium on Embedded Multicore/Manycore SoCs, MCSoC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -