• Skip to main content
  • Skip to secondary menu
  • Skip to footer

Technologies.org

Technology Trends: Follow the Money

  • Technology Events 2026-2027
  • Sponsored Post
  • Technology Markets
  • About
    • GDPR
  • Contact

Kioxia GP1 Wins FMS Best of Show With 10 Million IOPS, Splitting From SanDisk and SK Hynix on HBF

August 5, 2026 By admin Leave a Comment

Kioxia America announced that its GP Series PCIe NVMe SSD took the Best of Show award in the Specialized Storage category at FMS: the Future of Memory and Storage, running this week in Santa Clara. Trade show awards are not usually worth a paragraph. This one is, because of what else happened at the same event.

One day before the award, SanDisk and SK hynix published the first technical specification for High Bandwidth Flash through the Open Compute Project. Both announcements are attempts to solve the same problem: GPUs have run out of affordable memory capacity, and HBM is not getting cheaper fast enough. The two approaches have almost nothing else in common.

What the GP1 actually is

The GP1 is built on Kioxia’s XL-FLASH generation 2 low-latency flash, with a PCIe 6.0 interface and NVMe 2.2. Kioxia claims up to 10 million random read IOPS at 512-byte access granularity, with read latency under five microseconds, and a stated roadmap toward 100 million IOPS in later generations. Evaluation samples go to selected customers by the end of 2026.

The number that carries the design is not the 10 million. It is the 512 bytes. Ten million reads per second at 512-byte granularity works out to roughly five gigabytes per second of actual data movement, which is a small fraction of what a PCIe 6.0 link can carry. Kioxia has not built a bandwidth product. It has built a product optimized for the rate at which small, scattered reads can be serviced, and then deliberately left most of the link’s throughput unused.

That profile has a history. Intel’s Optane occupied roughly this position in the hierarchy before it was discontinued in 2022, and its disappearance left a hole that storage vendors have been probing at ever since. VAST Data qualified Kioxia’s earlier FL6 drives for metadata work when Optane supply became a risk. The GP1 is the same idea with an order of magnitude more headroom, and on paper it exceeds Optane comfortably on both access rate and latency.

Two different bets on where flash sits

High Bandwidth Flash takes the opposite route. The published specification defines 8-high and 16-high TSV-stacked NAND assemblies reaching 512GB per device, connected over UCIe, with three performance grades spanning roughly 0.4 to 3.0 terabytes per second. The top grade lands in the same range as an HBM4 stack. Google and Tenstorrent joined the consortium during standardization, which tells you the target is accelerator silicon that does not exist yet.

HBF answers a streaming question. If model weights will not fit in HBM, put them in something with comparable bandwidth and eight to sixteen times the capacity, sitting on the package. That is a sequential read problem, and it is why every HBF discussion is framed around inference rather than training. Weights are static during inference. Flash writes are slow and finite, so a tier that is read almost exclusively is the only version of this that works.

The GP1 answers a scatter question. Key-value cache offload, embedding table lookups, vector index traversal, retrieval against a corpus that does not fit anywhere near the accelerator: these are millions of small independent reads, and they are not limited by bandwidth. They are limited by how many separate accesses the storage tier can complete per second and how long each one takes. A drive delivering five gigabytes per second in 512-byte pieces is more useful for that workload than one delivering fifty gigabytes per second in megabyte-sized ones.

Both are called memory extension. They extend memory for different reasons.

Kioxia is hedging across all three tiers

The GP1 was not Kioxia’s only announcement at the show. It is also exhibiting the XL1, a CXL-attached memory expansion module using XL-FLASH, with evaluation samples going to ecosystem partners in August 2026. And Kioxia has its own high-bandwidth flash effort, stacking up to 32 dies with through-silicon vias for connection to the GPU bus, with Nvidia driving the partner discussions.

That is three positions in the memory hierarchy at once: on the accelerator package, on the memory bus via CXL, and at the end of a PCIe link. Kioxia has not committed to a winner, which is a reasonable posture when nobody knows which tier the software will actually target.

There is an oddity in the competitive picture worth noting. Kioxia and SanDisk jointly own the Japanese fabs that produce both companies’ NAND. They are now backing different architectures for the same emerging tier, out of shared wafer capacity, while SanDisk’s partner on the specification is SK hynix.

The part that has to be true

Optane was not killed by physics. It was killed by the fact that almost nobody rewrote their software to use a tier that might not survive the next product cycle, which left volumes too low to justify the manufacturing. Both of this week’s announcements face that problem again. GPU-direct access to flash requires the inference serving stack to be built around it, and HBF requires accelerator vendors to spend package area on it.

SanDisk and SK hynix have moved first on the ecosystem question by publishing an open specification and pulling in a hyperscaler and a chip designer as consortium members. Kioxia’s answer is that its product runs over an interface every server already has, on drives that plug into slots that already exist, with samples this year. Neither of those is a technical argument. They are both arguments about adoption risk, which is the only argument that matters here.

The award is for a sample drive that ships to a handful of customers by December. Watch instead for the first inference framework that treats a PCIe device as an addressable memory tier rather than as storage. That is the announcement that decides whether any of this becomes a product category.

Filed Under: News

Reader Interactions

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Footer

Recent Posts

  • Marvell (MRVL) Turns Celestial AI Into Product, and the $5.5 Billion Earnout Clock Is Now Running
  • Samsung Unveils zHBM and 400-Layer V10 BV-NAND at FMS 2026, and Wafer Bonding Is the Common Thread
  • Kioxia GP1 Wins FMS Best of Show With 10 Million IOPS, Splitting From SanDisk and SK Hynix on HBF
  • The Humanoid Robot Bottleneck Is the Battery: Why Two Kilowatt-Hours Caps the Whole Industry
  • SK hynix HBF Standard Turns NAND Into a Memory Tier, and the Memory Trade Still Has Room to Run
  • The Humanoid Trap: FCC Robot Import Ban Defends the Wrong Form Factor
  • Kioxia Splits Its AI Roadmap Between On-Device Flash and Hyperscale E1.S SSDs
  • Coursera Invests $100 Million in Its Chairman’s New Company: Venture Funding and Acquisitions Roundup
  • Cameras Are Designed for Human Eyes, and AI Vision Pays the Cost
  • Meshy Raised $400 Million at a $1.5 Billion Valuation and Announced It Two Different Ways

Media Partners

  • Market Analysis
  • Cybersecurity Market
  • App Coding
Big Tech Capex Reaches $1.1 Trillion Since 2023, With $745 Billion Planned for 2026
Amphenol’s Record Quarter Shows Where AI Capex Actually Lands
Paper Raises $34 Million and Figma (FIG) Has Already Lost Half Its Value on the Thesis
Google Frozen v2 AI Chip Could Deliver 10x Efficiency Gains Over Current TPUs
The Case for Shorting Budget Airlines as Oil Prices Rise
Morgan Stanley’s $2.3 Billion Capital Markets Haul Signals the AI Boom Is Just Getting Started
Blackstone’s Futronic Deal Bets on Actuators as AI Robotics’ Physical Bottleneck
Zhongji Innolight’s $8 Billion IPO Is a Customer Event for Marvell, Not a Competitive One
Wall Street Splits Between Oversupply Fears and an AI-Proof Supercycle Thesis
The AI Iron Curtain: Xi’s Shanghai Keynote Is the Fulton Speech of the AI Cold War
ISACA Europe Conference 2026: AI Governance and Cyber Resilience in Munich, 7-9 October
Bitdefender Adds EU-Only MDR to Its Sovereign Acceleration Program, Turning Data Sovereignty Into a Product SKU
Lattice Semiconductor Closes $1.65 Billion AMI Acquisition, Merging Server Firmware With Root-of-Trust Silicon
NVD Hits 45,207 Flaws in 2026 as Microsoft Prices AI Vulnerability Discovery at Half the Market
Way Security Raises $20M Seed From Insight Partners and Glilot for AI-Driven Identity Deployment
Jensen Huang Is Right About Open Models and Wrong About Cybersecurity
Glow Emerges From Stealth With $180 Million Series A At $1.2 Billion Valuation
Cisco Releases Antares-350M and Antares-1B Open-Weight AI Models for Vulnerability Detection
OpenAI Models Breached Hugging Face Infrastructure While Cheating on Cybersecurity Benchmark
Empirical Security Raises $25 Million Series A to Expand AI-Driven Threat Prediction
Vibe Coding Works Until You Have to Read the Code
Asynchronous Programming in Python: How the Event Loop, Event Queue, and Thread Pool Fit Together
PixVerse Closes Series C Extension at $439 Million and Pivots From AI Video Into Games
DigitalOcean Launches AI-Native Cloud at Deploy 2026
Verdent Updates AI Platform to Function as a Full Engineering Team for Solo Builders
The Side Project App Is Not Dead. The Side Project App Business Is.
The App Monetization Landscape Has Changed and Most Teams Have Not Caught Up
Building Offline-First Mobile Apps Is Harder Than It Looks and Worth It
State Management in React Native Has Too Many Options and One Right Answer
Mobile Accessibility Is the Case Developers Keep Ignoring

Media Partners

  • Market Research Media
  • Technology Conferences
  • API Coding
Weekly Network Analytics, July 19 to July 25, 2026: Visits Up 14%
Adobe (ADBE) and Figma (FIG) Have Each Lost Roughly Half Their Value to a Competitor Set Worth $34 Million
Getty Images Kills the $3.7 Billion Shutterstock Merger Rather Than Sell the Editorial Business the UK Demanded
Fox’s $22B Roku Deal: 4.6x Sales, Paid in 1.5x Stock
Tuesday Open: AI Earnings Engine Holds the Line as Iran Overhang Fades to Noise
China’s U.S. Treasury Holdings: The Great Repositioning (2021–2025)
Infographic: Why the 2025 CIPA Data Proves the APS-C Renaissance is Real
How WiFi Changed Media
Canva Acquires Simtheory and Ortto to Build End-to-End Work Platform
Netflix Price Hikes, The Economics of Dominance in a Saturated Streaming Market
FMS 2026 in Santa Clara: Kioxia, Samsung, SanDisk and SK Hynix Offer Four Incompatible Fixes for the AI Memory Wall
San Francisco AI Summit 2026: Korea-US AI and Semiconductor Summit, July 24, San Francisco, California
SIGGRAPH 2026 in Los Angeles: NVIDIA’s Physical AI Day, a First Games Summit, and the Bolt Graphics Zeus Bet
Inside AMD Advancing AI 2026: Lisa Su Puts Helios on Stage as OpenAI, Meta, Anthropic and Cerebras Line Up Behind It
Remaining 2026 Tech Conferences: Black Hat, Dreamforce, Web Summit Lisbon and AWS re:Invent
2026 Esri User Conference — July 13–17, San Diego
HubSpot UNBOUND 2026: Analyst Day Set for September 17 in Boston
The Signal for the Event-Tech Sector
The 10 Most Significant Tech Events and Earnings to Watch This Summer
RAISE Summit, July 8-9 2026, Paris
Every Accident in Your API Becomes a Contract
Why Private Domain Data Is the Real Key to AI That Actually Works
Orkes Raises $60M to Bring Production-Grade AI Orchestration to Enterprise Developers
Form.io Launches MCP Server and Agentic Coding Toolset for Governed Enterprise AI Development
Appdome Upgrades MobileBOT Defense With Identity-First Mobile API Protection
Five SDK Generators Compared: Speakeasy, Stainless, Fern, APIMatic, and OpenAPI Generator
API Monetization Models That Work and the Ones That Drive Developers Away
gRPC in Production: What the Documentation Doesn't Tell You
Event-Driven Architecture vs Request-Response: Choosing the Right Communication Pattern
The Business Case for Internal APIs That Most Engineering Leaders Ignore

Copyright © 2026 Technologies.org

Media Partners: Market Analysis · Market Research · Referently · Photography