Originator + supplier
Organization index / public roles
Industry and ecosystem map
The ecosystem is still compact. This map distinguishes specification owners and participants from vendors pursuing technically adjacent fast-flash products.
Supplier + co-standardizer
SK hynix
Positions HBF as AIN-B in its AI-NAND strategy and co-authors the standards work.Standards venue
Open Compute Project
Hosts the HBF workstream, currently listed in its semi-private workstream directory.Workstream participants
Google + Tenstorrent
Named in the August 2026 announcement as participants in the initial technical specification work.Adjacent flash path
Kioxia
Develops high-bandwidth PCIe flash modules and GPU-direct SSD products, not announced OCP HBF devices.Interface ecosystem
UCIe Consortium
Maintains the chiplet interconnect named as HBF's host-facing link.Core HBF activity / 01
Core HBF records
SK hynix describes an HBF base-die architecture
SK hynix discussed AIN-B, a vertically stacked NAND architecture with a logic base die and high-bandwidth interface for AI workloads.
SK hynix places HBF inside its AI-NAND portfolio
SK hynix described HBF as the bandwidth-oriented branch of its AI-NAND strategy and discussed vertically stacked NAND for AI systems.
The first compact public HBF architecture brief
A two-page overview of the HBF concept, its proposed system role, projected stack organization, and comparison with conventional high-bandwidth memory.
High Bandwidth Flash enters the public roadmap
Sandisk's investor presentation introduced HBF as a vertically integrated, capacity-oriented memory tier for AI inference and set out the earliest public product roadmap located by this project.
Adjacent paths / 02
Adjacent technology records
These sources illuminate alternative interfaces, packages, and software data paths. The catalog intentionally does not rename them HBF.
ONFI 6.0 defines the underlying NAND interface layer
The public ONFI 6.0 specification defines NAND device interfaces and operating modes, including high-speed signaling used below system-level memory products.
GPUDirect Storage provides the adjacent software data path
NVIDIA's documentation explains direct data movement between storage and GPU memory with reduced CPU bounce buffering.
Kioxia targets GPU-direct flash through Storage-Next
Kioxia announced an SSD family designed for NVIDIA's Storage-Next architecture and high-IOPS, direct data paths into accelerated systems.
A technical explainer connects UCIe chiplets and HBF
An engineering overview of using UCIe to connect logic-base-die memory stacks, including HBF-like flash configurations, to AI and HPC systems.
A 5 TB, 64 GB/s flash prototype explores another path
Kioxia and partners reported a PCIe 6.0-connected flash module prototype delivering 5 TB capacity and 64 GB/s aggregate bandwidth at under 40 W.
UCIe 3.0 doubles die-to-die data rates
UCIe 3.0 adds 48 and 64 GT/s operation plus manageability and system-in-package improvements for interoperable chiplets.