Instruction compression and encoding for low-power systems

Ismail Kadayif; Mahmut Kandemir

doi:10.1109/ASIC.2002.1158075

Instruction compression and encoding for low-power systems

Ismail Kadayif
, Mahmut Kandemir

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Scopus citations

Abstract

Low-power system design is very important in battery-operated embedded systems. Since instruction memory constitutes a large portion of the system, it is one of the major energy contributors. In this paper, we propose two selective instruction compression methods for reducing instruction memory and instruction bus energy consumption. In these methods, both compressed and uncompressed instructions are stored in the instruction memory in a mixed fashion. The compressed instructions are decompressed on-the-fly by means of an instruction decode table placed between instruction memory and core. Our methods selectively compress instructions in the sense that while some instances of a given instruction are compressed, some other instances of the same instruction are not. Even though both of the proposed methods can reduce both dynamic and leakage energy consumption in the instruction memory, one of them is more oriented towards reducing dynamic energy, whereas the other one mainly targets leakage. To reduce the instruction bus energy consumption further, we also propose a heuristic method for coding compressed instructions to reduce bit switching on the bus.

Original language	English (US)
Title of host publication	Proceedings - 15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002
Editors	John Chickanosky, Ram K. Krishnamurthy, P.R. Mukund
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	301-305
Number of pages	5
ISBN (Electronic)	0780374940
DOIs	https://doi.org/10.1109/ASIC.2002.1158075
State	Published - Jan 1 2002
Event	15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002 - Rochester, United States Duration: Sep 25 2002 → Sep 28 2002

Publication series

Name	Proceedings of the Annual IEEE International ASIC Conference and Exhibit
Volume	2002-January
ISSN (Print)	1063-0988

Other

Other	15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002
Country/Territory	United States
City	Rochester
Period	9/25/02 → 9/28/02

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering

Access to Document

10.1109/ASIC.2002.1158075

Cite this

Kadayif, I., & Kandemir, M. (2002). Instruction compression and encoding for low-power systems. In J. Chickanosky, R. K. Krishnamurthy, & P. R. Mukund (Eds.), Proceedings - 15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002 (pp. 301-305). Article 1158075 (Proceedings of the Annual IEEE International ASIC Conference and Exhibit; Vol. 2002-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASIC.2002.1158075

Kadayif, Ismail ; Kandemir, Mahmut. / Instruction compression and encoding for low-power systems. Proceedings - 15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002. editor / John Chickanosky ; Ram K. Krishnamurthy ; P.R. Mukund. Institute of Electrical and Electronics Engineers Inc., 2002. pp. 301-305 (Proceedings of the Annual IEEE International ASIC Conference and Exhibit).

@inproceedings{1e83b173773243c59d6efcddde0800f3,

title = "Instruction compression and encoding for low-power systems",

abstract = "Low-power system design is very important in battery-operated embedded systems. Since instruction memory constitutes a large portion of the system, it is one of the major energy contributors. In this paper, we propose two selective instruction compression methods for reducing instruction memory and instruction bus energy consumption. In these methods, both compressed and uncompressed instructions are stored in the instruction memory in a mixed fashion. The compressed instructions are decompressed on-the-fly by means of an instruction decode table placed between instruction memory and core. Our methods selectively compress instructions in the sense that while some instances of a given instruction are compressed, some other instances of the same instruction are not. Even though both of the proposed methods can reduce both dynamic and leakage energy consumption in the instruction memory, one of them is more oriented towards reducing dynamic energy, whereas the other one mainly targets leakage. To reduce the instruction bus energy consumption further, we also propose a heuristic method for coding compressed instructions to reduce bit switching on the bus.",

author = "Ismail Kadayif and Mahmut Kandemir",

year = "2002",

month = jan,

day = "1",

doi = "10.1109/ASIC.2002.1158075",

language = "English (US)",

series = "Proceedings of the Annual IEEE International ASIC Conference and Exhibit",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "301--305",

editor = "John Chickanosky and Krishnamurthy, \{Ram K.\} and P.R. Mukund",

booktitle = "Proceedings - 15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002",

address = "United States",

note = "15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002 ; Conference date: 25-09-2002 Through 28-09-2002",

}

Kadayif, I & Kandemir, M 2002, Instruction compression and encoding for low-power systems. in J Chickanosky, RK Krishnamurthy & PR Mukund (eds), Proceedings - 15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002., 1158075, Proceedings of the Annual IEEE International ASIC Conference and Exhibit, vol. 2002-January, Institute of Electrical and Electronics Engineers Inc., pp. 301-305, 15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002, Rochester, United States, 9/25/02. https://doi.org/10.1109/ASIC.2002.1158075

Instruction compression and encoding for low-power systems. / Kadayif, Ismail; Kandemir, Mahmut.
Proceedings - 15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002. ed. / John Chickanosky; Ram K. Krishnamurthy; P.R. Mukund. Institute of Electrical and Electronics Engineers Inc., 2002. p. 301-305 1158075 (Proceedings of the Annual IEEE International ASIC Conference and Exhibit; Vol. 2002-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Instruction compression and encoding for low-power systems

AU - Kadayif, Ismail

AU - Kandemir, Mahmut

PY - 2002/1/1

Y1 - 2002/1/1

N2 - Low-power system design is very important in battery-operated embedded systems. Since instruction memory constitutes a large portion of the system, it is one of the major energy contributors. In this paper, we propose two selective instruction compression methods for reducing instruction memory and instruction bus energy consumption. In these methods, both compressed and uncompressed instructions are stored in the instruction memory in a mixed fashion. The compressed instructions are decompressed on-the-fly by means of an instruction decode table placed between instruction memory and core. Our methods selectively compress instructions in the sense that while some instances of a given instruction are compressed, some other instances of the same instruction are not. Even though both of the proposed methods can reduce both dynamic and leakage energy consumption in the instruction memory, one of them is more oriented towards reducing dynamic energy, whereas the other one mainly targets leakage. To reduce the instruction bus energy consumption further, we also propose a heuristic method for coding compressed instructions to reduce bit switching on the bus.

AB - Low-power system design is very important in battery-operated embedded systems. Since instruction memory constitutes a large portion of the system, it is one of the major energy contributors. In this paper, we propose two selective instruction compression methods for reducing instruction memory and instruction bus energy consumption. In these methods, both compressed and uncompressed instructions are stored in the instruction memory in a mixed fashion. The compressed instructions are decompressed on-the-fly by means of an instruction decode table placed between instruction memory and core. Our methods selectively compress instructions in the sense that while some instances of a given instruction are compressed, some other instances of the same instruction are not. Even though both of the proposed methods can reduce both dynamic and leakage energy consumption in the instruction memory, one of them is more oriented towards reducing dynamic energy, whereas the other one mainly targets leakage. To reduce the instruction bus energy consumption further, we also propose a heuristic method for coding compressed instructions to reduce bit switching on the bus.

UR - https://www.scopus.com/pages/publications/24944432943

UR - https://www.scopus.com/pages/publications/24944432943#tab=citedBy

U2 - 10.1109/ASIC.2002.1158075

DO - 10.1109/ASIC.2002.1158075

M3 - Conference contribution

AN - SCOPUS:24944432943

T3 - Proceedings of the Annual IEEE International ASIC Conference and Exhibit

SP - 301

EP - 305

BT - Proceedings - 15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002

A2 - Chickanosky, John

A2 - Krishnamurthy, Ram K.

A2 - Mukund, P.R.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002

Y2 - 25 September 2002 through 28 September 2002

ER -

Kadayif I, Kandemir M. Instruction compression and encoding for low-power systems. In Chickanosky J, Krishnamurthy RK, Mukund PR, editors, Proceedings - 15th Annual IEEE International ASIC/SOC Conference, ASIC/SOC 2002. Institute of Electrical and Electronics Engineers Inc. 2002. p. 301-305. 1158075. (Proceedings of the Annual IEEE International ASIC Conference and Exhibit). doi: 10.1109/ASIC.2002.1158075

Instruction compression and encoding for low-power systems

Abstract

Publication series

Other

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this