Value Iteration on Multicore Processors

被引：0

作者：

Jain, Anuj ^{[1
]}

Sahni, Sartaj ^{[2
]}

机构：

[1] Adobe Syst Inc, Lehi, UT 84043 USA

[2] Univ Florida, CISE Dept, Gainesville, FL USA

来源：

2020 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY (ISSPIT 2020) | 2020年

基金：

美国国家科学基金会;

关键词：

Reinforcement Learning; Markov Decision Process; Value Iteration; Multicore; Parallelization;

D O I：

10.1109/ISSPIT51521.2020.9408773

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Value Iteration (VI) is a powerful, though time consuming, approach to solve reinforcement learning problems modeled as Markov Decision Processes (MDPs). In this paper, we explore strategies to run the sate-of-the-art cache efficient algorithm for VI developed by us [1], [2] on a multicore processor. We demonstrate a speedup of up to 2.59 on a 10-core multiprocessor using 20 threads on popular benchmark data. The speedup for the parallelized portion of the computation is up to 5.89.

引用

页数：7

共 50 条

[41] On Efficient Posting List Intersection with Multicore Processors
Tatikonda, Shirish
Junqueira, Flavio
Barla Cambazoglu, B.
Plachouras, Vassilis
PROCEEDINGS 32ND ANNUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2009, : 738 - 739
[42] Benefits from isolation in commodity multicore processors
Aggarwal, Nidhi
Ranganathan, Parthasarathy
Jouppi, Norman P.
Smith, James E.
COMPUTER, 2007, 40 (06) : 49 - +
[43] Configuration Technique for Adaptability of Multicore Processors on FPGA
Miyauchi, Tetsuo
Tanaka, Kiyofumi
2016 IEEE 27TH INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES AND PROCESSORS (ASAP), 2016, : 219 - 220
[44] Performance implications of cache affinity on multicore processors
Kazempour, Vahid
Fedorova, Alexandra
Alagheband, Pollya
EURO-PAR 2008 PARALLEL PROCESSING, PROCEEDINGS, 2008, 5168 : 151 - 161
[45] Optimizing Graph Algorithms in Asymmetric Multicore Processors
Krishna, Jyothi V. S.
Nasre, Rupesh
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2018, 37 (11) : 2673 - 2684
[46] High accuracy and interval arithmetic on multicore processors
Carlos A. Hölbig
Andriele Do Carmo
Luis P. Arendt
Computational and Applied Mathematics, 2013, 32 : 425 - 434
[47] Throughput Regulation in Shared Memory Multicore Processors
Chen, X.
Xiao, H.
Wardi, Y.
Yalamanchili, S.
2015 IEEE 22ND INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING (HIPC), 2015, : 12 - 20
[48] Throughput Regulation in Multicore Processors via IPA
Almoosa, N.
Song, W.
Yalamanchili, S.
Wardi, Y.
2012 IEEE 51ST ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2012, : 7267 - 7272
[49] DOMAIN PARTITIONING TECHNOLOGY FOR EMBEDDED MULTICORE PROCESSORS
Nojiri, Tohru
Kondo, Yuki
Irie, Naohiko
Ito, Masayuki
Sasaki, Hajime
Maejima, Hideo
IEEE MICRO, 2009, 29 (06) : 7 - 17
[50] Multicore Processors: Status Quo and Future Directions
Zahran, Mohamed
2014 10TH INTERNATIONAL COMPUTER ENGINEERING CONFERENCE (ICENCO), 2014, : 1 - 4

← 1 2 3 4 5 →