IBM Power Systems built with the POWER8 architecture and processors

被引：0

作者：

20150800545645

机构：

[1] Cahill, J.J.

[2] Nguyen, T.

[3] Vega, M.

[4] Baska, D.

[5] Szerdi, D.

[6] Pross, H.

[7] Arroyo, R.X.

[8] Nguyen, H.

[9] Mueller, M.J.

[10] Henderson, D.J.

[11] Moreira, J.

来源：

| 1600年 / IBM Corporation卷 / 59期

关键词：

Bandwidth;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

This paper describes architectures and significant implementation features of two systems in the IBM POWER8™ processor-based family of servers. Specifically, the scale-out 2-socket rack server and the enterprise scale-up 16-socket rack server are detailed. The description of these systems highlights the increase in memory bandwidth from previous POWER® systems, the enablement of coherent accelerators, the highly-extensible I/O subsystem, and the high-performance directly attached storage subsystem. In addition, reliability, availability, and serviceability features are described. These systems deliver significant increases in core count, memory, and input/output bandwidth over previous POWER systems - with reliability and availability enhancements commensurate with the performance improvements. © 2015 IBM.

引用

共 50 条

[31] Verification of Transactional Memory in POWER8
Adir, Allon
Goodman, Dave
Hershcovich, Daniel
Hershkovitz, Oz
Hickerson, Bryan
Holtz, Karen
Kadry, Wisam
Koyfman, Anatoly
Ludden, John
Meissner, Charles
Nahir, Amir
Pratt, Randall R.
Schiffli, Mike
St Onge, Brett
Thompto, Brian
Tsanko, Elena
Ziv, Avi
2014 51ST ACM/EDAC/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2014,
[32] Evaluating the POWER8 Architecture Through Optimizing Stencil-Based Algorithms
Xu, Jingheng
Fu, Haohuan
Gan, Lin
Song, Yu
Peng, Hongbo
Shi, Wen
Yang, Guangwen
2016 IEEE TRUSTCOM/BIGDATASE/ISPA, 2016, : 1374 - 1381
[33] Debugging post-silicon fails in the IBM POWER8 bring-up lab
Dusanapudi, M.
Fields, S.
Floyd, M. S.
Guthrie, G. L.
Kalla, R.
Kapoor, S.
Leitner, L. S.
Marino, C. F.
McGill, J. J.
Nahir, A.
Reick, K.
Shen, H.
Wright, K. L.
IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 2015, 59 (01)
[34] The Impact of Voltage-Frequency Scaling for the Matrix-Vector Product on the IBM POWER8
Catalan, Sandra
Malossi, A. Cristiano I.
Bekas, Costas
Quintana-Orti, Enrique S.
EURO-PAR 2016: PARALLEL PROCESSING, 2016, 9833 : 103 - 116
[35] Efficient Barrier Implementation on the POWER8 Processor
Sudheer, C. D.
Srinivasan, Ashok
2015 IEEE 22ND INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING (HIPC), 2015, : 165 - 173
[36] POWER8 Design Methodology Innovations for Improving Productivity and Reducing Power
Ziegler, Matthew M.
Puri, Ruchir
Philhower, Bob
Franch, Robert
Luk, Wing
Leenstra, Jens
Verwegen, Peter
Fricke, Niels
Gristede, George
Fluhr, Eric
Zyuban, Victor
2014 IEEE PROCEEDINGS OF THE CUSTOM INTEGRATED CIRCUITS CONFERENCE (CICC), 2014,
[37] Performance Evaluation of Scientific Applications on POWER8
Adinetz, Andrew V.
Baumeister, Paul F.
Boettiger, Hans
Hater, Thorsten
Maurer, Thilo
Pleiter, Dirk
Schenck, Wolfram
Schifano, Sebastiano Fabio
HIGH PERFORMANCE COMPUTING SYSTEMS: PERFORMANCE MODELING, BENCHMARKING, AND SIMULATION, 2015, 8966 : 24 - 45
[38] An Early Performance Study of Large-scale POWER8 SMP Systems
Liu, Xing
Buono, Daniele
Checconi, Fabio
Choi, Jee W.
Que, Xinyu
Petrini, Fabrizio
Gunnels, John A.
Stuechelil, Jeff A.
2016 IEEE 30TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2016), 2016, : 263 - 272
[39] Survey on software tools that implement deep learning algorithms on intel/x86 and IBM/Power8/Power9 platforms
Shaikhislamov D.
Sozykin A.
Voevodin V.
Supercomputing Frontiers and Innovations, 2019, 6 (04) : 57 - 83
[40] Performance Analysis of Spark/GraphX on POWER8 Cluster
Que, Xinyu
Schneidenbach, Lars
Checconi, Fabio
Costa, Carlos H. A.
Buono, Daniele
HIGH PERFORMANCE COMPUTING, ISC HIGH PERFORMANCE 2016 INTERNATIONAL WORKSHOPS, 2016, 9945 : 268 - 285

← 1 2 3 4 5 →