Fundamental energy cost of finite-time parallelizable computing
Konopik, Michael LU ; Korten, Till ; Lutz, Eric and Linke, Heiner LU
(2023)
In Nature Communications
14(1).
- Abstract
The fundamental energy cost of irreversible computing is given by the Landauer bound of kTln 2 /bit, where k is the Boltzmann constant and T is the temperature in Kelvin. However, this limit is only achievable for infinite-time processes. We here determine the fundamental energy cost of finite-time parallelizable computing within the framework of nonequilibrium thermodynamics. We apply these results to quantify the energetic advantage of parallel computing over serial computing. We find that the energy cost per operation of a parallel computer can be kept close to the Landauer limit even for large problem sizes, whereas that of a serial computer fundamentally diverges. We analyze, in particular, the effects of different degrees of... (More)
The fundamental energy cost of irreversible computing is given by the Landauer bound of kTln 2 /bit, where k is the Boltzmann constant and T is the temperature in Kelvin. However, this limit is only achievable for infinite-time processes. We here determine the fundamental energy cost of finite-time parallelizable computing within the framework of nonequilibrium thermodynamics. We apply these results to quantify the energetic advantage of parallel computing over serial computing. We find that the energy cost per operation of a parallel computer can be kept close to the Landauer limit even for large problem sizes, whereas that of a serial computer fundamentally diverges. We analyze, in particular, the effects of different degrees of parallelization and amounts of overhead, as well as the influence of non-ideal electronic hardware. We further discuss their implications in the context of current technology. Our findings provide a physical basis for the design of energy-efficient computers.
(Less)
- author
- Konopik, Michael
LU
; Korten, Till
; Lutz, Eric
and Linke, Heiner
LU
- organization
- publishing date
- 2023-12
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Nature Communications
- volume
- 14
- issue
- 1
- article number
- 447
- publisher
- Nature Publishing Group
- external identifiers
-
- scopus:85146917539
- pmid:36707510
- ISSN
- 2041-1723
- DOI
- 10.1038/s41467-023-36020-2
- language
- English
- LU publication?
- yes
- id
- c47b2db7-fba4-4eec-ab0d-62fa910792d8
- date added to LUP
- 2023-02-09 15:18:52
- date last changed
- 2024-06-11 13:16:14
@article{c47b2db7-fba4-4eec-ab0d-62fa910792d8,
abstract = {{<p>The fundamental energy cost of irreversible computing is given by the Landauer bound of kTln 2 /bit, where k is the Boltzmann constant and T is the temperature in Kelvin. However, this limit is only achievable for infinite-time processes. We here determine the fundamental energy cost of finite-time parallelizable computing within the framework of nonequilibrium thermodynamics. We apply these results to quantify the energetic advantage of parallel computing over serial computing. We find that the energy cost per operation of a parallel computer can be kept close to the Landauer limit even for large problem sizes, whereas that of a serial computer fundamentally diverges. We analyze, in particular, the effects of different degrees of parallelization and amounts of overhead, as well as the influence of non-ideal electronic hardware. We further discuss their implications in the context of current technology. Our findings provide a physical basis for the design of energy-efficient computers.</p>}},
author = {{Konopik, Michael and Korten, Till and Lutz, Eric and Linke, Heiner}},
issn = {{2041-1723}},
language = {{eng}},
number = {{1}},
publisher = {{Nature Publishing Group}},
series = {{Nature Communications}},
title = {{Fundamental energy cost of finite-time parallelizable computing}},
url = {{http://dx.doi.org/10.1038/s41467-023-36020-2}},
doi = {{10.1038/s41467-023-36020-2}},
volume = {{14}},
year = {{2023}},
}