TY - GEN
T1 - DeepStore
T2 - 52nd Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2019
AU - Mailthody, Vikram Sharma
AU - Qureshi, Zaid
AU - Liang, Weixin
AU - Feng, Ziyan
AU - Gonzalo, Simon Garcia De
AU - Li, Youjie
AU - Franke, Hubertus
AU - Xiong, Jinjun
AU - Huang, Jian
AU - Hwu, Wen Mei
N1 - Funding Information:
We would like to thank the anonymous reviewers and shepherd for their helpful comments and feedback. This work was partially supported by the Applications Driving Architectures (ADA) Research Center and Center for Research on Intelligent Storage and Processing-in-memory (CRISP), JUMP Centers co-sponsored by SRC and DARPA, IBM-ILLINOIS Center for Cognitive Computing Systems Research (C3SR) - a research collaboration as part of the IBM AI Horizon Network, NSF grant CNS-1850317, and NSF grant CCF-1919044.
PY - 2019/10/12
Y1 - 2019/10/12
N2 - Recent advancements in deep learning techniques facilitate intelligentquery support in diverse applications, such as content-based image retrieval and audio texturing. Unlike conventional key-based queries, these intelligent queries lack efficient indexing and require complex compute operations for feature matching. To achieve highperformance intelligent querying against massive datasets, modern computing systems employ GPUs in-conjunction with solid-state drives (SSDs) for fast data access and parallel data processing. However, our characterization with various intelligent-query workloads developed with deep neural networks (DNNs), shows that the storage I/O bandwidth is still the major bottleneck that contributes 56%-90% of the query execution time. To this end, we present DeepStore, an in-storage accelerator architecture for intelligent queries. It consists of (1) energy-efficient in-storage accelerators designed specifically for supporting DNNbased intelligent queries, under the resource constraints in modern SSD controllers; (2) a similarity-based in-storage query cache to exploit the temporal locality of user queries for further performance improvement; and (3) a lightweight in-storage runtime system working as the query engine, which provides a simple software abstraction to support different types of intelligent queries. DeepStore exploits SSD parallelisms with design space exploration for achieving the maximal energy efficiency for in-storage accelerators. We validate DeepStore design with an SSD simulator, and evaluate it with a variety of vision, text, and audio based intelligent queries. Compared with the state-of-the-art GPU+SSD approach, DeepStore improves the query performance by up to 17.7, and energy-efficiency by up to 78.6.
AB - Recent advancements in deep learning techniques facilitate intelligentquery support in diverse applications, such as content-based image retrieval and audio texturing. Unlike conventional key-based queries, these intelligent queries lack efficient indexing and require complex compute operations for feature matching. To achieve highperformance intelligent querying against massive datasets, modern computing systems employ GPUs in-conjunction with solid-state drives (SSDs) for fast data access and parallel data processing. However, our characterization with various intelligent-query workloads developed with deep neural networks (DNNs), shows that the storage I/O bandwidth is still the major bottleneck that contributes 56%-90% of the query execution time. To this end, we present DeepStore, an in-storage accelerator architecture for intelligent queries. It consists of (1) energy-efficient in-storage accelerators designed specifically for supporting DNNbased intelligent queries, under the resource constraints in modern SSD controllers; (2) a similarity-based in-storage query cache to exploit the temporal locality of user queries for further performance improvement; and (3) a lightweight in-storage runtime system working as the query engine, which provides a simple software abstraction to support different types of intelligent queries. DeepStore exploits SSD parallelisms with design space exploration for achieving the maximal energy efficiency for in-storage accelerators. We validate DeepStore design with an SSD simulator, and evaluate it with a variety of vision, text, and audio based intelligent queries. Compared with the state-of-the-art GPU+SSD approach, DeepStore improves the query performance by up to 17.7, and energy-efficiency by up to 78.6.
KW - Hardware accelerators
KW - In-storage computing
KW - Information retrieval
KW - Intelligent query
KW - Solid-state drive
UR - http://www.scopus.com/inward/record.url?scp=85074449092&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85074449092&partnerID=8YFLogxK
U2 - 10.1145/3352460.3358320
DO - 10.1145/3352460.3358320
M3 - Conference contribution
AN - SCOPUS:85074449092
T3 - Proceedings of the Annual International Symposium on Microarchitecture, MICRO
SP - 224
EP - 238
BT - MICRO 2019 - 52nd Annual IEEE/ACM International Symposium on Microarchitecture, Proceedings
PB - IEEE Computer Society
Y2 - 12 October 2019 through 16 October 2019
ER -