NEO Semiconductor, a leading innovator in advanced AI and memory technologies, today announced successful proof-of-concept (POC) results for its 3D X-DRAM technology, marking a major milestone toward next-generation, high-density memory solutions for AI and data-centric systems.

The company also announced a new strategic investment led by Stan Shih, Founder and former Chairman and CEO of Acer, and former Board Director of TSMC for over 20 years. As a globally respected technology pioneer and entrepreneur, Mr. Shih's participation reflects strong confidence in NEO's technology and vision, and will support the company's next phase of development.

SK hynix Inc. (or "the company", www.skhynix.com) announced today that it has recorded 52.5763 trillion won in revenues, 37.6103 trillion won in operating profit (with an operating margin of 72%), and 40.3459 trillion won in net profit (with a net margin of 77%) in the first quarter.

Revenue surpassed 50 trillion won for the first time on a quarterly basis, while operating profit and operating margin reached record highs at 37.6 trillion won and 72%, respectively. Operating profit has nearly doubled compared to the previous quarter, clearly demonstrating an improving profitability.

Zhitai, the consumer-facing brand of YMTC, has launched the TiPlus 9100, its first PCIe 5.0 entry in the TiPlus lineup. The drive is built on YMTC Xtacking 4.0 NAND technology and targets gaming laptops, thin portables, and desktop builds. Currently, Zhitai is offering the TiPlus 9100 NVMe M.2 SSDs with capacities of 1 TB, 2 TB and 4 TB. This isn't YMTC's first PCIe 5.0 client SSD, back in March the company launched the PC550, a four-channel Gen 5 drive built on the same Xtacking 4.0 NAND and rated at up to 10,500 MB/s sequential read. The TiPlus 9100 steps that up considerably with a faster controller, pushing 12,000 MB/s and targeting the higher end of the Gen 5 performance. Despite running without a dedicated DRAM cache, the TiPlus 9100 can reach speeds of up to 12,000 MB/s for sequential reads and 10,700 MB/s for sequential writes, with random performance reaching 1,850K IOPS. The single-sided PCB keeps it compatible with slim systems, and firmware tuning helps manage power draw and thermals under load. Zhitai bundles its own software for health monitoring, performance testing, migration, temperature tracking, and lifespan estimation.

YMTC is in the middle of a significant capacity expansion. Earlier this week we reported that the company plans to add two more fabs on top of one already nearing completion in Wuhan, which would take total monthly wafer output from 200,000 to around 400,000 when all three are fully running. More capacity means more NAND supply, which should support the Zhitai ability to push products like the TiPlus 9100 more aggressively into the market. According to IT Files, pricing for TiPlus 9100 in mainland China is set at 1 TB for 1,459 yuan (around $200), 2 TB for 2,559 yuan, and 4 TB for 4,999 yuan (approximately $690).

During a media tour at Lexar HQ in China, Digital Foundry spoke with Lexar's Europe General Manager, Grace Su, who explained what gamers are buying and where they are willing to compromise. Interestingly, Lexar found that, despite the pricing of DRAM and NAND Flash, users could purchase lower-capacity RAM kits without issues, while SSDs with capacities lower than 512 GB weren't selling well. Although this is not a direct comparison, when building a new PC system, you need both a RAM kit and an SSD. Based on their budget, enthusiasts often have to decide between a larger SSD or a bigger RAM kit. However, Lexar reports that users are so committed to having larger SSD space that they are even willing to revert to HDDs rather than buy an SSD smaller than 512 GB. This is understandable, considering that modern games can take up hundreds of gigabytes of space.

Currently, high RAM prices are driving PC gamers to invest considerably more in their gaming rigs to play smoothly. As 16 GB is somewhat considered the minimum for a Windows 11 system, some games and tasks are so demanding that PC DIY enthusiasts need to invest in 32 GB kits at prices that were unimaginable just a year ago. For example, we reported on the DDR4 spot market pricing, which saw the cost of a single 16 Gb module increase by about 2,200% over the past year, with only a minor 5% correction in March. We can only hope for more corrections soon so that PC gamers can finally see signs of relief, but with AI demand projected to continue rising, that seems far from reality.

YMTC (Yangtze Memory Technologies Corp) is planning to significantly expand its manufacturing capacity, with Reuters reporting the Chinese NAND flash maker intends to build two additional factories on top of one already nearing completion. When all three are running at full capacity, YMTC's total output would more than double from its current 200,000 wafers per month to 400,000 wafers per month (each new plant is designed for 100,000 wafers monthly). The third fab, located in Wuhan alongside the existing two plants, has already been built and is currently being equipped. The fab is expected to start operations later this year and reach 50,000 wafers per month by 2027. Notably, over half of the equipment has been sourced domestically, including tooling for vertical layer stacking, a sign of how much YMTC has leaned into local suppliers since the US added it to the Entity List in December 2022. However, recently, the U.S. Government's Bureau of Industry and Security reportedly removed YMTC from the list of restricted Chinese companies.

The two planned factories don't yet have confirmed locations or target dates, but all three new plants will reportedly allocate some capacity to DRAM production alongside NAND. YMTC has already sent LPDDR samples to clients and expects feedback by year-end, which will shape how aggressively it pursues DRAM going forward. On the NAND side, YMTC already holds 11.8% of the global market, on par with Sandisk and not far behind SK Hynix (16%), Kioxia (15.9%), and Micron (13.3%), while Samsung leads at 30.4%. UBS expects the YMTC shares to pass 14% by early 2027. The company is pushing its Xtacking 4.0 architecture, which is considered competitive with what the industry leaders are shipping.

SK hynix has started shipping its PQC21 cSSD, the first product built on its 321-layer QLC NAND flash technology. The product is available in 1 TB and 2 TB capacities, with Dell as the first customer starting this month. QLC (Quad-Level Cell) stores four bits per cell, which maximizes storage density per unit area but has historically come with a write performance penalty compared to TLC (Triple-Level Cell). SK hynix addresses that with SLC caching, frequently accessed data is written to faster SLC-mode regions first before being transferred to the QLC cells, smoothing out the performance gap for typical workloads.

According to market research from IDC (International Data Corporation), the QLC NAND is expected to go from 22% of the global cSSD market in 2025 to 61% by 2027, so the timing of this launch makes sense. SK hynix says it will expand beyond Dell to other major customers as production scales up.

Valve's next-generation Steam Deck 2 handheld console is reportedly planned for release in 2028, with significant manufacturing changes expected for this sequel to the highly successful handheld gaming device. According to a well-known industry leaker, KeplerL2, posting in the NeoGAF community, Valve is targeting a 2028 refresh for the second-generation Steam Deck. However, the ongoing supply chain shortages of DRAM and NAND Flash could cause disruptions to these plans, potentially leading to delays. Interestingly, this period is when the shortages are expected to start easing, so the Steam Deck 2 could still be released on time, depending on Valve's sourcing capabilities.

One of the most significant procurement shifts for the Steam Deck 2 is Valve's choice of the computing base that will power the handheld. Instead of using a semi-custom AMD APU, Valve is expected to use an off-the-shelf AMD APU that won't require any custom tuning from AMD to meet Valve's needs. This is welcome news, as the latest Steam Machine showed that Valve's reliance on a semi-custom APU solution made the hardware "obsolete" quickly while the rest of the industry advanced. With any semi-custom solution, stockpiling silicon and waiting for DRAM/NAND modules to arrive puts pressure on Valve to ship a product that is significantly underpowered or too expensive. However, with an off-the-shelf solution, Valve could use the best available option at the time of shipping and optimize SteamOS around it.

Solidigm, a pioneer in enterprise data storage, today announced it has exceeded initial investment goals for its Greater Sacramento initiatives, including the company's Rancho Cordova headquarters and surrounding research and development (R&D) campus. Announced in September 2022, Solidigm committed to investing $100 million into regional R&D facilities. Approximately three-and-a-half years into the build out, the company has surpassed this figure and will continue to invest in local talent and technology to help fuel global AI advancements.

In addition to $75 million in local lab investments, Solidigm has introduced close to 100 new NAND tools through the development of more than a $5 million world-class NAND lab and R&D center. "We have the most robust data storage product line for AI data centers," said Greg Matson, SVP, Head of Products and Marketing at Solidigm. "Our industry leading SSDs help our customers achieve the highest levels of efficiency, density, and performance in storage for their AI demands. And all of the innovation for us starts right here in Rancho Cordova."

Worldwide 300 mm fab equipment spending is expected to increase 18% to $133 billion in 2026 and 14% to $151 billion in 2027, SEMI reported today in its latest 300 mm Fab Outlook. This strong growth reflects surging AI chip demand for data centers and edge devices, as well as the growing commitment to semiconductor self-sufficiency across key regions through localized industrial ecosystems and supply chain restructuring. Looking further out, the report projects investment will continue to increase 3% to $155 billion in 2028 and another 11% to $172 billion in 2029, respectively.

"AI is resetting the scale of semiconductor manufacturing investment," said Ajit Manocha, President and CEO of SEMI. "With global 300 mm fab equipment spending projected to exceed $150 billion in 2027 for the first time, the industry is making historic, sustained commitments to the advanced capacity and resilient supply chains needed to power the AI era."

Samsung has developed a new SSD controller based on the open-source RISC-V instruction set, moving away from the Arm ISA in some of its SSD controllers. With the introduction of the BM9K1 PCIe 5.0 QLC NAND SSD, Samsung has officially created a proprietary RISC-V IP that will serve as a foundation for many SSDs the company plans to release. Announced at the China Flash Market Summit 2026, the BM9K1 SSD has been showcased with just one metric: sequential read speed. Achieving a maximum sequential read speed of 11.4 GB/s, Samsung has reached impressive speeds for QLC NAND Flash. While the sequential write speed is unknown, it is expected to be around 10 GB/s, varying slightly depending on Samsung's design. Typically, high-performance SSDs use TLC NAND, as seen in Samsung's own 9100 Pro SSD, which we reviewed. It features 3D TLC V-NAND V8 with 236 layers. While this SSD uses TLC NAND and has a proprietary Samsung Presto 5 nm controller running on Arm-based cores, Samsung might transition a significant portion of its SSD lineup to a RISC-V based design with the BM9K1, offering satisfactory performance with QLC NAND.

Interestingly, Samsung has designed this SSD with considerations for size, power, and AI. For instance, the BM9K1 PCIe 5.0 SSD replaces the previous BM9C1 PCIe 4.0 SSD controller. Although both use QLC NAND, the newer BM9K1 features a new RISC-V controller and a fresh PCIe 5.0 interface, doubling the performance in sequential reads on average. The power efficiency of the new RISC-V design is also improved. Samsung claims a 23% increase in power efficiency, thanks to the flexibility of RISC-V, which allows for greater customization and optimization of the controller firmware to match I/O patterns with the QLC NAND, resulting in nearly a quarter less power consumption. This improvement is expected to have a significant impact on small form factor PCs and client laptops. The main drawback of the design is the use of QLC NAND, but Samsung may introduce TLC NAND SSDs with RISC-V controllers in the future. For now, these remain on the 5 nm Presto Arm-powered controllers.

Team Group Inc., a global leader in memory solutions, today announced the launch of the T-Create Classic H514 M.2 PCIe 5.0 SSD, designed to meet the growing demand for high-performance data storage in the generative AI era. Built on the PCIe Gen 5 x4 interface, the SSD delivers up to 14,200 MB/s read and 13,300 MB/s write. Its ultra-fast data transfer capability significantly enhances the efficiency of accessing large creative assets and supports the performance requirements of video editing, image processing, visual effects, and 3D modeling software. The H514 also enables smooth and stable workflows for local AI model inference and training, empowering professional creative output.

Featuring an advanced 6 nm controller, the T-Create Classic H514 delivers ultra-low read and write latencies of just 0.05 ms and 0.015 ms, respectively. This minimizes data response times and enables seamless coordination with the CPU and GPU, ensuring smooth system performance even when handling complex, high-resolution projects or multi-layered creative tasks. Built with advanced 3D NAND flash, the H514 offers capacities of up to 4 TB, supporting the deployment and storage needs of large AI language models ranging from 7B to 175B parameters. By enabling local data storage, the SSD provides creators with more responsive and stable creative workflows.

If your workstation build has no budget limits, there's now a way to get 16 TB of NVMe PCIe 4.0 SSD storage on a single M.2 2280 SSD. However, this small storage drive will set you back nearly $16,000, with Amazon listing a brand new Exascend PE4 16 TB M.2 SSD at $15,935. What makes this drive so expensive is the fact that you are getting 16 TB of NVMe SSD storage in a super-dense configuration that fits into a single M.2 slot on a motherboard, requiring no additional drives to achieve this capacity. The Exascend PE4 drive uses a PCIe 4.0 interface and can reach sequential read speeds of up to 3,270 MB/s, while write speeds can reach up to 2,980 MB/s, just shy of 3 GB/s. The drive uses TLC 3D NAND Flash storage modules from an unknown manufacturer.

The drive is designed to withstand a TBW of 16,640 TB written to it and about two million hours of MTBF, meaning its usable life is guaranteed to last through any known task, running 24/7 in systems where reliability is the number one factor. Interestingly, Exascend only offers a five-year warranty but claims its hardware will significantly outlast that. Rigorous testing and massive capacity justify the high price point, so some users might find the need for such a drive. Additionally, idle power consumption remains under 1.3 W, while this SSD can reach up to 7.2 W of active power when under full load, meaning that efficiency for such a drive is rather good.

Silicon Motion Technology Corporation, a global leader in designing and marketing NAND flash controllers for solid-state storage devices, today announced that it will showcase a rich portfolio of differentiated enterprise SSD controllers and PCIe NVMe BGA boot SSD at NVIDIA GTC 2026, Booth #3015, purpose-built to meet the evolving requirements of the NVIDIA AI ecosystem. As AI models scale, inference architectures are extending beyond HBM and System DRAM into high-performance NAND storage tiers, as reflected in NVIDIA's ICMS initiative. In this new architecture, NAND-based Storage becomes a performance-critical layer that requires deterministic latency and quality-of-service differentiation.

Silicon Motion delivers a vertically integrated storage solution encompassing advanced SSD controller design, full firmware development, and compact Reference Design Kits (RDKs) aligned with leading enterprise form factors such as E1.S, E1.L, E3.S, E3.L, and U.2 for AI server deployments. The company also provides enterprise PCIe NVMe BGA boot SSD with strong endurance and long-term operational stability, deployed in AI systems.

The widespread adoption of AI inference workloads in 4Q25 significantly raised requirements for data storage systems, according to TrendForce's latest findings on the enterprise SSD market. Meanwhile, enterprises accelerated upgrades to their general-purpose servers, while shortages in HDD supply pushed some demand toward SSD solutions. These factors together drove combined revenue for the world's top five enterprise SSD vendors up 51.7% QoQ to more than US$9.9 billion.

Among leading vendors, Samsung retained its top position, reporting nearly $3.66 billion in revenue in 4Q25, up 49.7% QoQ. The company demonstrated the strength of its vertically integrated business model. As concerns grew over potential DRAM shortages, many customers turned to Samsung because it can rely on its own DRAM and NAND Flash production to ensure stable SSD supply.

Silicon Motion Technology Corporation (NasdaqGS: SIMO), a global leader in designing and marketing NAND flash controllers for solid-state storage devices, today announced the launch of the SM8008, a PCIe Gen 5 x4 NVMe enterprise SSD controller purpose-built for data center boot drives and power-sensitive enterprise storage applications.

As hyperscale and enterprise data centers expand server deployments, boot SSDs have become a critical infrastructure component across every system node. The SM8008 addresses this growing demand with a controller architecture optimized for power efficiency, predictable performance, and enterprise-grade security at scale, while supporting the OCP Hyperscale NVMe Boot SSD Specification to meet production-ready enterprise deployment requirements.

Patriot Memory, a global leader in high-performance memory and storage solutions, is pleased to announce its participation in Embedded World 2026. Under its dedicated industrial and embedded brand, ACPI, Patriot Memory will showcase a comprehensive portfolio of next-generation hardware designed for AIoT, edge computing, and 5G infrastructure. Highlighting the display are the new M2PDR-8LP PCIe Gen 5 x4 SSD, the high-capacity Enterprise NVMe SSD series, and high-speed DDR5 RDIMM modules featuring wide-temperature support.

As industrial applications transition toward data-heavy workloads involving AI training and autonomous systems, the demand for extreme bandwidth and thermal stability has reached a critical point. ACPI's latest offerings are engineered to address these challenges by combining cutting-edge interface standards with industrial-grade reliability.

Applied Materials, Inc. today announced it is working with Micron Technology to develop next-generation DRAM, high-bandwidth memory (HBM) and NAND solutions that increase the energy-efficient performance of AI systems, bringing together advanced R&D capabilities from Applied's EPIC Center in Silicon Valley and Micron's state-of-the-art innovation center in Boise, Idaho to strengthen the semiconductor innovation pipeline in the United States.

"Applied Materials and Micron have a long-standing partnership focused on driving higher performance and more energy-efficient advanced memory chips by pushing the boundaries of materials engineering and manufacturing innovation," said Gary Dickerson, President and CEO of Applied Materials. "We are excited to deepen our collaboration with Micron as a founding partner at the EPIC Center as next-generation memory technologies play an increasingly vital role in the future of AI systems."

The global notebook market is expected to face dual pressures from weak demand and rising component costs in 2026, according to TrendForce's latest research on the notebook industry. In addition to rapidly rising memory prices, CPU pricing has also begun to move higher. TrendForce estimates that to preserve existing margin structures for both notebook brands and distribution channels, the retail price of a mainstream notebook with an original MSRP of US$900 could rise by nearly 40%.

TrendForce notes that since the start of 2026, supply for notebook DRAM and NAND Flash has tightened significantly. Prices have surged, and shortages of certain components have become more pronounced, increasing uncertainty for notebook brands as they plan their procurement strategies.

Chinese NAND Flash maker Yangtze Memory Technologies Corp (YMTC) has introduced its first client M.2 NVMe PCIe 5.0 SSD, named the PC550. As many PC OEMs face challenges in acquiring storage solutions at reasonable prices, YMTC aims to assist with its inaugural PCIe 5.0 NVMe model. The M.2 2242 and 2280 modules feature a PCIe Gen 5 x4 link combined with the NVMe 2.0 protocol and YMTC's X4-9070 3D NAND, built on Xtacking 4.0. YMTC designed the PC550 with a four-channel architecture, which the company claims reduces power consumption and thermal output compared to the more common eight-channel designs. The lineup includes capacities of 512 GB, 1 TB, and 2 TB, with no pricing on the official website. Consumers can contact YMTC, or wait for distribution channels to start offering these SSDs.

YMTC rates the largest variant at up to 10,500 MB/s for sequential reads and up to 10,000 MB/s for sequential writes. These speeds surpass most Gen 4 drives but fall short of some Gen 5 offerings that reach nearly 15,000 MB/s, suggesting a less powerful SSD controller. Random performance scales with capacity. The 512 GB model is listed at up to 880,000 random read IOPS and 1,100,000 random write IOPS, with an endurance rating of 300 TBW. The 1 TB and 2 TB models achieve approximately 1,300,000 random IOPS for both read and write, with endurance ratings of 600 TBW and 1,200 TBW, respectively. Idle power consumption is quoted at under 3 milliwatts, and active consumption is under 6 watts, making these figures suitable for notebook use.

The global NAND Flash industry continued to benefit from AI infrastructure build-outs in 4Q25, according to TrendForce's latest research. All in all, the combined revenue of the top five NAND flash suppliers sharply rose 23.8% QoQ to US$21.17 billion.

The primary growth driver was explosive demand for enterprise SSDs, fueled by large-scale AI server deployments by North American CSPs. Meanwhile, severe HDD shortages and extended lead times accelerated a shift in orders toward NAND solutions, which further tightened supply. The resulting imbalance worsened NAND shortages and pushed prices higher, directly boosting supplier revenues.

Rising memory and storage costs are pricing entry-level PC buyers out of the market, which may disappear entirely. According to the analyst firm Gartner, the sub-$500 PC sector might vanish by 2028. Their analysis indicates that memory, which used to be just a small part of the total bill of materials (BOM) at 16% of the total PC cost in 2025, is expected to rise to nearly a quarter of the PC's cost at 23%, making the entry-level PC segment unsustainable. "This sharp increase removes vendors' ability to absorb costs, making low-margin entry-level laptops nonviable. Ultimately, we expect the sub-$500 entry-level PC segment will disappear by 2028," said Ranjit Atwal, Senior Director Analyst at Gartner. He added, "In addition, rising AI PC prices will delay the projected 50% market penetration of AI PCs until 2028."

We have witnessed multiple price increases across many PC components such as DRAM, NAND Flash, and GPUs. With manufacturers unable to produce PCs at any tangible profit levels in the sub-$500 PC sector, it might entirely disappear from the mainstream PC market. The concept of budget builds might become obsolete, with the majority of PCs ending up in categories above that threshold, near or beyond four figures. Gartner estimates that there will be about a 130% increase in combined DRAM and NAND Flash pricing by the end of this year, increasing PC prices by about 17% compared to 2025 levels. This situation will push consumer and enterprise demand toward premium PCs.

As NAND Flash pricing has skyrocketed, reaching nearly a 500% increase over the past six months, Phison has reportedly started requiring some customers to make prepayments to control the supply. This means that customers who haven't even started a Phison order will need to send funds as a form of credit to purchase a set amount of Phison controllers, SSDs, or any other storage products. According to a notice to its customers, Phison has stated that the rapid increase in NAND Flash demand has driven various parts of the storage supply chain to seek alternative payment methods, with a focus on quicker settlements. This means customers must either accept faster contract settlements or use other forms of payment like prepayment credits.

Phison is a company primarily focused on making SSD controllers, which are manufactured at TSMC, Samsung, or other fabs as logic devices, not NAND Flash. The company's latest E28 controller is produced on TSMC's 6 nm node, a mature class of semiconductor nodes. This suggests that Phison's supply chain is largely intact. However, if Phison is arranging NAND Flash purchases on behalf of customers, that could explain why faster settlements are requested. Specific arrangements likely vary by customer and should be confirmed on a case-by-case basis. There might be situations where Phison provides SSD makers with blueprints for SSDs and handles part of the design and supply chain logistics within the company, making the situation more understandable. In such cases, Phison would need to secure a fast contract settlement to ensure the SSD maker gets the best possible price for the NAND Flash that ultimately pairs with a Phison controller. The full statement follows.

Micron Technology, Inc. celebrated the grand opening of its semiconductor assembly and test facility in Sanand, Gujarat, India. The state-of-the-art facility converts advanced DRAM and NAND wafers from Micron's global manufacturing network into finished memory and storage products. Once fully ramped, the first phase of Micron's Sanand operation will feature more than 500,000 square feet of cleanroom space, making it one of the world's largest single-floor assembly and test cleanrooms. The site serves customers worldwide to meet the growing global demand for memory and storage fueled by AI.

The facility represents a combined investment of approximately $2.75 billion by Micron and its government partners, advancing semiconductor manufacturing capabilities in India. Micron Chairman, President and CEO Sanjay Mehrotra and other executives witnessed the opening ceremony with Prime Minister Narendra Modi, Chief Minister of Gujarat Bhupendra Patel, Union Minister for Railways, Communications, Electronics & IT Ashwini Vaishnaw, U.S. Ambassador to India Sergio Gor and other distinguished government officials and guests.

JEDEC Solid State Technology Association, the global leader in the development of standards for the microelectronics industry, today announced the publication of its highly anticipated JESD220H and JESD223G: Universal Flash Storage 5.0 and UFS Host Controller Interface (UFSHCI) 5.0. Designed for mobile applications, automotive and computing systems that demand high performance with low power consumption, UFS 5.0 will deliver faster data access and improved performance compared to its predecessor while maintaining compatibility with UFS 4.x hardware.

UFS offers high-performance, embedded storage with low power consumption, making it ideal for use in applications where power efficiency is essential. This includes computing and mobile systems like smartphones and wearables, as well as an expanding role in generative AI, automotive applications, edge computing and gaming consoles. Its high-speed serial interface and optimized protocol enable significant throughput for power-efficient system performance.

SK hynix Inc. and Sandisk Corporation held "HBF Spec. Standardization Consortium Kick-Off" event at Sandisk Headquarters in Milpitas, California on the 25th (local time) announcing global standardization strategy of next-generation memory solution HBF (High Bandwidth Flash) aimed at the AI inference era. SK hynix said, "By making HBF an industry standard, together with Sandisk, we will lay the foundation for the entire AI ecosystem to grow together. A dedicated workstream under OCP will be launched with Sandisk to begin standardization work."

Recently, the AI industry is shifting from training which focuses on creating Large Language Models (LLMs) to inference, which accelerates actual AI services to users. Fast and efficient memory is essential as the number of users using AI services increases rapidly. However, the existing memory structure cannot meet the high capacity data processing and power efficiency at the same time in the inference stage and HBF technology is designed to address these limitations. HBF technology is a new memory layer between ultra-fast memory, HBM and high-capacity storage device, SSD. HBF technology can fill the gap between HBM's high performance and SSD's high capacity and ensure both capacity expansion and power efficiency required for AI inferencing. While HBM handles the high level bandwidth, HBF technology serves as a supporting layer in the architecture.