Processing-in-Memory: Exploring the Design Space

被引：10

作者：

Scrbak, Marko ^{[1
]}

Islam, Mahzabeen ^{[1
]}

Kavi, Krishna M. ^{[1
]}

Ignatowski, Mike ^{[2
]}

Jayasena, Nuwan ^{[2
]}

机构：

[1] Univ N Texas, Denton, TX 76203 USA

[2] AMD Res Adv Micro Devices Inc, Sunnyvale, CA USA

来源：

ARCHITECTURE OF COMPUTING SYSTEMS - ARCS 2015 | 2015年 / 9017卷

关键词：

Processing-in-memory; 3D-DRAM; Big data; MapReduce;

D O I：

10.1007/978-3-319-16086-3_4

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

With the emergence of 3D-DRAM, Processing-in-Memory has once more become of great interest to the research community and industry. In this paper, we present our observations on a subset of the PIM design space. We show how the architectural choices for PIM core frequency and cache sizes will affect the overall power consumption and energy efficiency. Our findings include detailed power consumption modeling for an ARM-like core as a PIM core. We show the maximum number of PIM cores we can place in the logic layer with respect to a power budget. In addition, we explore the optimal design choices for the number of cores as a function of frequency, utilization, and energy efficiency.

引用

页码：43 / 54

页数：12

共 50 条

[31] A survey of spintronic architectures for processing-in-memory and neural networks
Umesh, Sumanth
Mittal, Sparsh
JOURNAL OF SYSTEMS ARCHITECTURE, 2019, 97 (349-372) : 349 - 372
[32] GIM: Versatile GNN Acceleration with Reconfigurable Processing-in-Memory
Nie, Chen
Chen, Guoyang
Zhang, Weifeng
He, Zhezhi
2023 IEEE 41ST INTERNATIONAL CONFERENCE ON COMPUTER DESIGN, ICCD, 2023, : 499 - 506
[33] A Customized Processing-in-Memory Architecture for Biological Sequence Alignment
Akbari, Nasrin
Modarressi, Mehdi
Daneshtalab, Masoud
Loni, Mohammad
2018 IEEE 29TH INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES AND PROCESSORS (ASAP), 2018, : 158 - 165
[34] Massively Parallel Skyline Computation For Processing-In-Memory Architectures
Zois, Vasileios
Gupta, Divya
Tsotras, Vassilis J.
Najjar, Walid A.
Roy, Jean-Francois
27TH INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURES AND COMPILATION TECHNIQUES (PACT 2018), 2018,
[35] Implementation of a Low-Overhead Processing-in-Memory Architecture
Jang, Young-Jong
Kim, Byung-Soo
Kim, Dong-Sun
Hwang, Tae-ho
2016 INTERNATIONAL SOC DESIGN CONFERENCE (ISOCC), 2016, : 185 - 186
[36] Things to Consider to Enable Dynamic Graphs in Processing-in-Memory
Kim, Euna
Kim, Hyesoon
PROCEEDINGS OF THE INTERNATIONAL SYMPOSIUM ON MEMORY SYSTEMS, MEMSYS 2020, 2020, : 297 - 303
[37] Extending the ONNX Runtime Framework for the Processing-in-Memory Execution
Kim, Seok Young
Lee, Jaewook
Kim, Chang Hyun
Lee, Won Jun
Kim, Seon Wook
2022 INTERNATIONAL CONFERENCE ON ELECTRONICS, INFORMATION, AND COMMUNICATION (ICEIC), 2022,
[38] Enabling Relational Database Analytical Processing in Bulk-Bitwise Processing-In-Memory
Perach, Ben
Ronen, Ronny
Kvatinsky, Shahar
2023 IEEE 36TH INTERNATIONAL SYSTEM-ON-CHIP CONFERENCE, SOCC, 2023, : 19 - 24
[39] Optimization of OLAP In-Memory Database Management Systems with Processing-In-Memory Architecture
Hosseinzadeh, Shima
Parvaresh, Amirhossein
Fey, Dietmar
ARCHITECTURE OF COMPUTING SYSTEMS, ARCS 2023, 2023, 13949 : 264 - 278
[40] Plug N? PIM: An integration strategy for Processing-in-Memory accelerators
Santos, Paulo C.
Forlin, Bruno E.
Alves, Marco A. Z.
Carro, Luigi
INTEGRATION-THE VLSI JOURNAL, 2023, 88 : 185 - 195

← 1 2 3 4 5 →