NVMe powers SSDs in the enterprise
Kam Eshghi, Integrated Device Technology
EETimes (11/27/2012 11:00 AM EST)
PCI express (PCIe) solid state drives (SSDs) offer significant performance benefits in enterprise applications versus traditional hard disk drives (HDDs), as well as SSDs with a legacy storage interface. By realizing the full performance potential of flash memory, PCIe SSDs accelerate I/O-intensive enterprise applications, such as data mining, online transaction processing (OLTP), and financial transaction processing. The strong need for high-performance PCIe SSDs is underlined by the growing performance gap between processors and storage subsystems. Until recently, however, the lack of a host control interface standard has inhibited the widespread adoption of PCIe SSDs. Existing solutions have required proprietary software drivers that complicate OEM qualification, inhibiting broad adoption of PCIe SSDs.
With the emergence of non-volatile memory express (NVMe), a scalable host controller interface specifically developed for PCIe SSDs, and a supporting ecosystem plus dedicated devices such as NVMe programmable flash controller chips, the potential of PCIe SSDs for enterprise computing applications can be fully realized. Device programmability will allow SSD suppliers to lead an industry transition to NVMe PCIe SSDs while still being able to differentiate products through their own firmware. Server and storage OEMs meanwhile, will benefit through dramatically improved performance and greatly simplified and expedited qualification processes.
To read the full article, click here
Related Semiconductor IP
- NVMe IP core -- Directly connect PCIe SSD without external memory
- NVMe Verification IP
- NVMe Host Controller
- NVMe 2.3 Verification IP
- Verification IP for NVMe
Related Articles
- Conquering the challenges of PCIe with NVMe in order to deliver highly competitive Enterprise PCIe SSD
- NVMe IP for Enterprise SSD
- Sharing NVMe SSDs for heterogeneous architectures
- MIPI in next generation of AI IoT devices at the edge
Latest Articles
- Low-Energy Reduced RISC-V Instruction Subset Processor for Tsetlin Machine Inference at the Edge
- Si-GT: Fast Interconnect Signal Integrity Analysis For Integrated Circuit Design Via Graph Transformers
- Hardware Mechanisms to Dynamically Throttle AI Performance
- SEAM-V: A Hybrid-Decoupled RISC-V Vector Processor with Backend-Visible EP Context for Sustained Vector Throughput
- New Number Formats for FFT IP Cores in Optical OFDM Transceivers