Heterogeneous Voltage Frequency Scaling of Data-Parallel Applications for Energy Saving on Homogeneous Multicore Platforms

被引：4

作者：

Bratek, Pawel ^{[1
]}

Szustak, Lukasz ^{[1
]}

Wyrzykowski, Roman ^{[1
]}

Olas, Tomasz ^{[1
]}

Chmiel, Tomasz ^{[1
]}

机构：

[1] Czestochowa Tech Univ, Dept Comp Sci, Dabrowskiego 69, PL-42201 Czestochowa, Poland

来源：

EURO-PAR 2021: PARALLEL PROCESSING WORKSHOPS | 2022年 / 13098卷

关键词：

Data-parallel applications; Energy saving; Heterogeneous voltage frequency scaling; Multicore; ccNUMA; PERFORMANCE;

D O I：

10.1007/978-3-031-06156-1_12

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this paper, for the first time, we explore and establish the combined benefits of heterogeneous DVFS (dynamic voltage frequency scaling) control in improving the energy-performance behavior of data-parallel applications on shared-memory multicore systems. We propose to customize the clock frequency individually for the appropriately selected groups of cores corresponding to the diversified time of actual computation. In consequence, the advantage of up to 20% points over the homogeneous frequency scaling is achieved on the ccNUMA server with two 18-core Intel Xeon Gold 6240 containing 72 logical cores in total. The cost and efficiency of the proposed pruning algorithm for selecting heterogeneous DVFS configurations against the brute-force search are verified and compared experimentally.

引用

页码：141 / 153

页数：13

共 50 条

[21] Analytical Communication Performance Models as a metric in the partitioning of data-parallel kernels on heterogeneous platforms
Juan A. Rico-Gallego
Juan C. Díaz-Martín
Carmen Calvo-Jurado
Sergio Moreno-Álvarez
Juan L. García-Zapata
The Journal of Supercomputing, 2019, 75 : 1654 - 1669
[22] Scaling Data-Intensive Applications on Heterogeneous Platforms with Accelerators
Balevic, Ana
Kienhuis, Bart
2012 IEEE 26TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS & PHD FORUM (IPDPSW), 2012, : 1866 - 1873
[23] Energy Efficient Mapping of Mixed Criticality Applications on Unrelated Heterogeneous Multicore Platforms
Awan, Muhammad Ali
Masson, Damien
Tovar, Eduardo
2016 11TH IEEE INTERNATIONAL SYMPOSIUM ON INDUSTRIAL EMBEDDED SYSTEMS (SIES), 2016,
[24] Parallel Dynamic Voltage and Frequency Scaling for Stream Decoding using a Multicore Embedded System
Lai, Ying-Xun
Huang, Yueh-Min
Lai, Chin-Feng
Trajkovic, Ljiljana
2011 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2011, : 1956 - 1959
[25] Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms
Rico-Gallego, Juan A.
Diaz-Martin, Juan C.
Moreno-Alvarez, Sergio
Calvo-Jurado, Carmen
Garcia-Zapata, Juan L.
COMPUTATIONAL AND MATHEMATICAL METHODS, 2020, 2 (01)
[26] Resource-Aware Device Allocation of Data-Parallel Applications on Heterogeneous Systems
Kim, Donghyeon
Kang, Seokwon
Lim, Junsu
Jung, Sunwook
Kim, Woosung
Park, Yongjun
ELECTRONICS, 2020, 9 (11) : 1 - 18
[27] Energy-Optimal Dynamic Voltage Scaling in Multicore Platforms with Reconfigurable Power Distribution Network
Kim, Juyeon
Kim, Taewhan
2018 19TH INTERNATIONAL SYMPOSIUM ON QUALITY ELECTRONIC DESIGN (ISQED), 2018, : 31 - 36
[28] Dynamic Voltage and Frequency Scaling based Parallel Scheduling Scheme for Video Recognition on Multicore Systems
Chen, Yen-Lin
Chang, Ming-Feng
Liang, Wen-Yew
2016 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS-TAIWAN (ICCE-TW), 2016, : 357 - 358
[29] Performance and Energy Efficient Dynamic Voltage and Frequency Scaling Scheme for Multicore Embedded System
Chen, Yen-Lin
Chang, Ming-Feng
Liang, Wen-Yew
Lee, Chao-Hsien
2016 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE), 2016,
[30] Adaptive Voltage/Frequency Scaling and Core Allocation for Balanced Energy and Performance on Multicore CPUs
Papadimitriou, George
Chatzidimitriou, Athanasios
Gizopoulos, Dimitris
2019 25TH IEEE INTERNATIONAL SYMPOSIUM ON HIGH PERFORMANCE COMPUTER ARCHITECTURE (HPCA), 2019, : 133 - 146

← 1 2 3 4 5 →