Leveraging SPDK Acceleration Framework for Optimal IPU Storage Workflows

Mon Sep 16 | 1:30pm
Location:
Winchester
Abstract

Infrastructure Processing Units (IPUs) is revolutionizing the networked storage paradigm for cloud service providers (CSPs). The type of device enhances system architecture by exposing NVMe PCI devices to the host and offloading network storage tasks onto the IPU. The Storage Performance Development Kit (SPDK) Acceleration Framework is perfectly suited to operate on these devices, capitalizing on their hardware offloading capabilities for efficient data movement and transformation. This means executing DMA operations between the host/IPU, while simultaneously encrypting/decrypting the data as well as calculating NVMe/TCP data digest, all in one go.

In this talk, we will explore how Intel's IPU hardware integrates with the SPDK Acceleration Framework to optimize storage workflows. We will present examples demonstrating this integration and discuss the substantial benefits of this approach. Attendees will learn why the SPDK Acceleration Framework, when paired with IPU technology, is a powerful solution for enhancing CSP storage performance and efficiency.

Learning Objectives

Upon completion, participant will be able to understand where SPDK acceleration framework shall be used     
Upon completion, participant will be able to understand how the HW capabilities IPU like devices can be integrated to SPDK acceleration framework     
Upon completion, participant will be able to learn how it has been done for Intel IPU and what are benefits of usage the framework and IPU HW capabilities together


---

Deb Chatterjee
Intel Corporation
Related Sessions