DirectNVM: Hardware-accelerated NVMe SSDs for High-performance Embedded Computing
Abstract
With data-intensive artificial intelligence (AI) and machine learning (ML) applications rapidly surging, modern high-performance embedded systems, with heterogeneous computing resources, critically demand low-latency and high-bandwidth data communication. As such, the newly emerging NVMe (Non-Volatile Memory Express) protocol, with parallel queuing, access prioritization, and optimized I/O arbitration, starts to be widely adopted as a de facto fast I/O communication interface. However, effectively leveraging the potential of modern NVMe storage proves to be nontrivial and demands fine-grained control, high processing concurrency, and application-specific optimization. Fortunately, modern FPGA devices, capable of efficient parallel processing and application-specific programmability, readily meet the underlying physical layer requirements of the NVMe protocol, therefore providing unprecedented opportunities to implementing a rich-featured NVMe middleware to benefit modern high-performance embedded computing.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jan 31, 2022
- Source ID
- 10.1145/3463911
Entities
People
- Amro Awad
- Mingjie Lin
- Yu Zou
Organizations
- Defense Advanced Research Projects Agency
- North Carolina State University
- University of Central Florida