Cross-layer caching firmware for key-value storage devices
This technology creates a smarter way for computers and storage devices to share and coordinate their memory caches when handling key-value databases — the kind used by cloud services, apps, and enterprise software. Normally, the software running on a server and the storage hardware manage their own caches independently, which leads to redundant work and wasted memory. This system mirrors the cache between the host computer and the storage device, keeping them in perfect sync so data lookups are faster and resources are used more efficiently. The storage device itself participates in the computation, rather than passively receiving read/write commands, which is the emerging 'computational storage' paradigm.
What you could build
A firmware or driver stack for NVMe computational storage devices that enables synchronized, cross-layer caching for key-value workloads; target buyers are enterprise storage OEMs (think Samsung, Western Digital, Micron) and hyperscale cloud infrastructure teams building custom storage hardware.
Who in Virginia should care
Northern Virginia data center operators, cloud infrastructure teams at AWS/Microsoft Azure Virginia regions, and DoD IT infrastructure contractors would have direct interest in storage performance optimization.
Readiness: Prototype likely
Concept — described but not yet demonstrated. Lab validated — supported by experimental results in the patent. Prototype likely — the text describes a built, working embodiment.
Readiness is inferred from the patent text, not from a lab visit.
The record
- Inventors
- Naga Sanjana Bikonda, Wookhee Kim, Madhava Krishnan Ramanathan, Changwoo Min, Vishwanath Maram
- Granted
- June 25, 2024
- Status
- Granted patent
- Patent number
- 12019548
Ready to talk?
Virginia Tech Intellectual Properties handles licensing for this technology.
Prosim summaries are generated from public patent text and are not legal advice.