High-Performance Storage Patents: Who Leads, Where the Gaps Are 2026
- 79.6% concentration. The top five assignees alone account for 1,807 of the 2,269 records in scope — a field with one dominant filer and a long tail behind it.
- Filing has cooled from its 2022 peak. Filings ran from 100 in 2017 to a peak of 341 in 2022; the last complete comparison, 2021 to 2024, shows a 13% pullback rather than a collapse.
- Almost all activity sits under one IPC class. G06F covers 91.7% of the 2,269 records, with H04L a distant second at 22.0% — most of the technical differentiation happens inside a single classification.
Filing growth compares 2021 (294 records) with 2024 (257) — a three-year span. 2024 is the most recent year we treat as complete: publication lags filing by roughly 18 months, so 2025 onwards are still filling in and any growth rate that ends there would understate the field. Top-5 share is the combined record count of the five largest assignees divided by all 2,269 records in scope (CR5), not by the ranked leaders only.
What this landscape covers
This dataset tracks 2,269 published records matching high-performance storage architectures — parallel file systems, HPC storage, and related cache coherence, memory access, and hardware accelerator claims — filed or published between 2015 and the 2026 cut-off. Coverage spans filing trend, assignee concentration, IPC composition, and receiving office, giving a structural view of where claim density sits and where it does not.
Because publication lags filing by roughly 18 months, the most recent one to two years in any trend understate real filing activity; treat 2024 as the last year that can be read as complete, and the 2025-2026 tail as still filling in.
Let an AI agent run this analysis on your own technology
Pick a task. Every answer cites the patents behind it.
Filing trend and technology composition
Two views of the same 2,269-record corpus: how filing volume has moved year over year, and which IPC subclasses carry the claims.
Filing trend, 2017-2026
Filings rose from 100 in 2017 to a peak of 341 in 2022. The 2021-to-2024 comparison — 294 down to 257 — is a 13% pullback over three years, the most recent span that is not distorted by publication lag. Years after 2024 should be read as undercounted, not as evidence of a further decline.
IPC subclass composition
G06F (electric digital data processing) appears on 91.7% of the 2,269 records, confirming that most claims are framed as digital data processing rather than pure memory or storage hardware. H04L (digital information transmission) reaches 22.0%, and G11C (static and digital memories) only 3.1% — the physical memory layer is comparatively under-claimed relative to the software and system layer above it. Because records can carry several IPC classes, these shares add up to more than 100% of the record total.
Shares are the percentage of the 2,269 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on High-Performance Storage Patent Landscape with Eureka
This page is one run against one query. Ask Eureka your own question about high-performance storage patent landscape and every answer comes back with the patent numbers behind it.
Try EurekaMost-cited records and a representative filing
US20190324857A1 — Adaptive multi-level checkpointing
Filed by Hewlett Packard Enterprise Development LP, this record describes ascertaining a transfer parameter associated with moving checkpoint data from node-local storage to a parallel file system, comparing that parameter against a specified threshold, and deciding whether to transfer the checkpoint data based on the comparison.Published 2019-10-24; representative of the checkpoint-management branch of the corpus rather than the highest-cited record.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US6725392B1 | Controller fault recovery system for a distributed file system | 637 |
| 2 | US6032216A | Parallel file system with method using tokens for locking modes | 482 |
| 3 | US5940838A | Parallel file system and method anticipating cache usage patterns | 438 |
| 4 | US5893086A | Parallel file system and method with extensible hashing | 420 |
| 5 | US20150248366A1 | Method and apparatus for accessing multiple storage devices from multiple hosts without use of remote direct … | 363 |
| 6 | US6023706A | Parallel file system and method for multiple node file access | 335 |
| 7 | US5701516A | High-performance non-volatile RAM protected write cache accelerator system employing DMA and data transferrin… | 310 |
| 8 | US5940841A | Parallel file system with extended file attributes | 308 |
| 9 | US5987477A | Parallel file system and method for parallel write sharing | 297 |
| 10 | US20210117249A1 | Infrastructure processing unit | 222 |
Ranked by citation count within this corpus; older filings accumulate citations simply by being available longer, so treat this as a signal of influence on later filings, not of current commercial weight.
Each row carries its publication number; clicking a row searches Eureka by that number.
Put your own technology through the same analysis
Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →MCP server & REST API
When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →What the numbers mean for a filing decision
Three read-throughs from the concentration, trend and classification data — useful for deciding where a new filing is likely to face dense prior art versus open ground.
One filer sets the terms of this field
With the leader alone holding 1,520 records and the top five combined at 1,807 of 2,269, most of the claim space in high-performance storage is already staked out by a small number of filers. A new entrant is more likely to be designing around an incumbent's claims than filling open ground.
A pullback, not a collapse
Filings peaked at 341 in 2022 and the last complete year-over-year comparison, 2021 to 2024, shows a 13% decline. That is consistent with a maturing filing cohort among the largest assignees rather than a technology losing relevance, especially since 2025-2026 figures are still incomplete due to publication lag.
Claims cluster in digital data processing, not memory hardware
G06F dominates at 91.7% of the 2,269 records, while G11C (static and digital memories) sits at only 3.1% and G11B (magnetic/optical storage) at 0.6%. The imbalance suggests most inventive effort is going into system-level data handling logic, leaving physical memory and storage-media claims comparatively open.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to high-performance storage patent landscape, with the prior art for and against each one.
Who is filing, and where the pace has changed
The ranking covers the 100 companies the data endpoint returns for this search, not an arbitrary top-50 or top-100 cut. Momentum by assignee shows most of the largest historical filers with zero output in the latest year — a sign that recent filing is either shifting to smaller players or, more likely, still working through the publication pipeline.
A single company anchors the field
The leading assignee's 1,520 records exceed the combined total of every other ranked company, positioning it as the reference point for freedom-to-operate checks in this space.
A sharp drop after the leader
Fifth place holds 40 records versus the leader's 1,520 — the gap between first and fifth is far larger than the gap across the rest of the ranked list, which is typical of a field with one dominant incumbent and a competitive second tier.
Even the leader is filing less, on paper
The top-ranked assignee shows 21 records in the latest year, down 85% year over year, while several other historically large filers show zero in the same year. Given the 18-month publication lag, this reads as a pipeline gap rather than a firm signal that filing has stopped.
| Assignee | Recent year | YoY |
|---|---|---|
| Pure Storage, Inc. | 21 | -85% |
| Umbra Technologies Ltd | 0 | -100% |
| International Business Machines Corporation | 0 | — |
| Intel Corp | 0 | — |
| Sun Microsystems, Inc. | 0 | — |
| EMC IP Holding Company LLC | 0 | — |
| OCIENT INC | 0 | — |
| EMC Corporation | 0 | — |
Turning this landscape into a filing or freedom-to-operate decision
The data points to where claims are dense and where they thin out; the next step is testing a specific claim or design against that structure.
Check freedom-to-operate against the leader
With one assignee holding 1,520 of 2,269 records, any new filing in this space should be checked against that portfolio first, not the field average.
Run a freedom-to-operate check in EurekaDraft around the under-claimed branches
G11C and G11B classes carry a small fraction of records relative to G06F, suggesting the memory and storage-media layer has more open claim space than the system-logic layer above it.
Explore white space in EurekaModel the checkpointing branch specifically
US20190324857A1 shows how one incumbent frames checkpoint-transfer logic; understanding its claim boundaries is a fast way to see what a workable design-around looks like.
Analyse this patent family in EurekaCommon questions about high-performance storage patents
One assignee leads clearly, with 1,520 of the 2,269 records in scope, and the top five assignees combined hold 79.6% of all records. That level of concentration means most freedom-to-operate questions in this field come down to checking against a small number of large portfolios rather than a broad competitive set. The ranking used here covers the 100 companies the dataset returns, not an arbitrary top-10 or top-50 cut.
Filing rose from 100 records in 2017 to a peak of 341 in 2022, then eased to 257 by 2024, a 13% decline over that three-year span. That is the last period that can be read reliably, since publication typically lags filing by around 18 months and the 2025-2026 figures are still incomplete. On the evidence available, this looks like a maturing filing cohort rather than a sharp downturn.
The large majority, 91.7% of the 2,269 records, carry a G06F classification for electric digital data processing, with digital information transmission (H04L) present in 22.0% of records. Memory-specific classes such as G11C (static and digital memories, 3.1%) and G11B (magnetic and optical storage, 0.6%) are comparatively small, indicating most claims are framed at the system or software level rather than the physical memory layer. Because a single record can carry multiple IPC codes, these shares add up to more than 100% of the record total and should not be summed.
The classification data points to the physical memory and storage-media layer, where G11C and G11B activity is thin relative to the dominant G06F cluster, and to specific mechanisms like checkpoint-transfer heuristics and accelerator-cluster cache coherence that show up in representative filings but not at high volume across the corpus. These are not guaranteed-open areas, but they carry less claim density than the core system-logic space that the leading assignees have already staked out. A design or claim aimed at one of these branches is less likely to run into the incumbent's core portfolio.
US20190324857A1, filed by Hewlett Packard Enterprise Development LP and published 2019-10-24, describes adaptive multi-level checkpointing: ascertaining a transfer parameter for checkpoint data held in node-local storage, comparing it to a specified threshold, and deciding whether to move that data to a parallel file system based on the comparison. It matters as a representative example of how the checkpoint-management branch of this field is claimed at the system level. Anyone building checkpoint-to-parallel-file-system logic should treat this filing's specific transfer-parameter-and-threshold mechanism as a starting reference point for a design-around.
Research High-Performance Storage Patent Landscape in depth with Eureka
Go past this page: query the whole high-performance storage patent landscape corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company’s registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.