Computational storage is a new paradigm in computing where data processing is moved closer to the storage device to enhance performance and reduce data transfer bottlenecks. In this presentation, we showcase how data integrity checks on CSDs with a software toolkit and a dedicated hardware to process the host payload can significantly improve storage performance and reduce data transfer overhead. This is a cross-industry effort that includes the system, the system software, and the CSD representing a complete end-to-end solution. We will compare the performance of the hardware-accelerated solution with traditional host software-based CRC calculations. We will also demonstrate the performance improvement achieved by hardware-accelerated data integrity checks on a CSD, and how this approach lends itself to easy scalability. Attendees will gain insight into how computational storage can be leveraged to reduce data transfer overhead and improve storage performance. This presentation will also highlight the benefits of using a software toolkit that abstracts the underlying hardware and enables easy integration of computational storage into existing storage architectures, and the advantage of adding HW acceleration capabilities at the device level.
Hardware-accelerated Data Integrity Check on a CSD
Tue Sep 19 | 1:00pm
Location:
Salon V
Abstract
Learning Objectives
- How a data integrity check can be executed on a CSD
- End-to-End Computational Storage solution
- How this approach can scale with more CSDs
---
Scott Shadley
Solidigm Technology, SNIA
- Michael MesnierIntel
Related Sessions