In-storage Processing of I/O Intensive Applications on Computational Storage Drives

12/23/2021
by   Ali HeydariGorji, et al.
0

Computational storage drives (CSD) are solid-state drives (SSD) empowered by general-purpose processors that can perform in-storage processing. They have the potential to improve both performance and energy significantly for big-data analytics by bringing compute to data, thereby eliminating costly data transfer while offering better privacy. In this work, we introduce Solana, the first-ever high-capacity(12-TB) CSD in E1.S form factor, and present an actual prototype for evaluation. To demonstrate the benefits of in-storage processing on CSD, we deploy several natural language processing (NLP) applications on datacenter-grade storage servers comprised of clusters of the Solana. Experimental results show up to 3.1x speedup in processing while reducing the energy consumption and data transfer by 67 regular enterprise SSDs.

READ FULL TEXT
research
02/17/2020

STANNIS: Low-Power Acceleration of Deep NeuralNetwork Training Using Computational Storage

This paper proposes a framework for distributed, in-storage training of ...
research
02/17/2020

STANNIS: Low-Power Acceleration of Deep Neural Network Training Using Computational Storage

This paper proposes a framework for distributed, in-storage training of ...
research
06/07/2023

An Analytical Model-based Capacity Planning Approach for Building CSD-based Storage Systems

The data movement in large-scale computing facilities (from compute node...
research
02/07/2021

DV-DVFS: Merging Data Variety and DVFS Technique to Manage the Energy Consumption of Big Data Processing

Data variety is one of the most important features of Big Data. Data var...
research
11/20/2021

Freeing Compute Caches from Serialization and Garbage Collection in Managed Big Data Analytics

Managed analytics frameworks (e.g., Spark) cache intermediate results in...
research
11/29/2021

ZCSD: a Computational Storage Device over Zoned Namespaces (ZNS) SSDs

The Big Data trend is putting strain on modern storage systems, which ha...
research
07/16/2020

HyperTune: Dynamic Hyperparameter Tuning For Efficient Distribution of DNN Training Over Heterogeneous Systems

Distributed training is a novel approach to accelerate Deep Neural Netwo...

Please sign up or login with your details

Forgot password? Click here to reset