SendTech Times
Analysis
SUPPLY CHECK:

AMD Drops HBM For LPDDR5X In Versal Memory Package Shift

Newsroom brief

AMD is moving its Versal Premium Gen 2 memory-on-package adaptive SoCs from HBM to LPDDR5X after HBM2e supply limits forced the earlier Versal HBM family toward discontinuation.

Verified against source materialEdited by SendTech Times Chips & Compute DeskSource: ServeTheHome
AMD Drops HBM For LPDDR5X In Versal Memory Package Shift
Image source: ServeTheHome

AMD Shifts Versal Memory Packages From HBM To LPDDR5X

AMD is introducing a Versal Premium Gen 2 Memory on Package lineup that puts LPDDR5X memory on the chip package instead of continuing the HBM path used by earlier programmable-logic products.

ServeTheHome described the AMD devices as adaptive SoCs for FPGA customers that want a more integrated product and faster development than designs using off-package memory.

AMD's programmable-logic group had previously used HBM to give Xilinx and AMD customers more bandwidth inside tightly integrated packages.

The new lineup changes that memory choice rather than only adding another Versal variant.

AMD is making the shift as AI hardware demand has tightened HBM supply for other product lines.

AMD's Instinct accelerators and EPYC CPUs benefited from the AI boom, while the programmable-logic division lost access to the HBM2e supply needed for Versal HBM devices, according to the account.

The product is aimed at a different constraint from AMD's AI accelerator portfolio.

Programmable-logic customers often buy devices for long support windows and embedded designs, so a memory technology that disappears quickly can become a procurement risk even when it offers strong bandwidth.

The LPDDR5X move gives AMD a way to keep an on-package memory option available after older HBM2e supply dried up.

HBM2e Supply Forced A Product-Line Deadline

Xilinx offered Virtex UltraScale+ HBM FPGAs from 2018 with up to 16GB of HBM memory, according to the report.

AMD later sold Versal HBM adaptive SoCs with up to 32GB of HBM2e memory onboard.

Those products targeted customers that needed both integrated memory and higher bandwidth than ordinary DDR memory could reasonably provide.

That long-life product model became harder once HBM supply shifted.

The account says AMD had already announced support for normal UltraScale+ FPGAs until 2045, but on-package memory products also depend on memory suppliers.

SK hynix supplied the first generation of HBM, while Samsung and Micron joined with HBM2, according to the report.

The memory cycle advanced on a shorter timeline than AMD's usual FPGA support horizon.

HBM went through three major specifications in its first nine years, and older HBM types were phased out on shorter cycles than DDR memory as high-performance processors drove demand for newer generations, according to the report.

Customers Still Need Deployment And Availability Detail

The trade article says AMD began discontinuing the Versal HBM family in September 2025 because HBM2e was no longer available at the scale needed for the product.

The new LPDDR5X version arrives on the final day to place orders for Versal HBM chips, making the memory-package switch a supply-chain response rather than a routine portfolio refresh.

The shift also keeps AMD exposed to a narrower proof point.

LPDDR5X can make the package more self-contained for adaptive SoC customers, but it is not the same bandwidth story as HBM.

AMD has to persuade FPGA buyers that integration, availability and product life matter more for this use case than staying with scarce HBM2e.

The public details still leave commercial evidence missing.

The public record still lacks named customers, order volumes, pricing, shipment dates, production-ramp capacity or independent benchmarks for the Versal Premium Gen 2 Memory on Package chips.

Share this article
inXf

Related articles

More
Micron Rally Signals AI Memory Shortage In Data-Centre Buildout
Chips & Semiconductors

Micron Rally Signals AI Memory Shortage In Data-Centre Buildout

Micron's market rally is being driven by AI data-centre memory demand, with TechCrunch citing a $1.27 trillion market cap, a 236% one-month stock gain and supply shortages expected to last into 2027.

Micron And Anthropic Put AI Memory Supply Inside Claude’s Compute Plan
Chips & Semiconductors

Micron And Anthropic Put AI Memory Supply Inside Claude’s Compute Plan

Micron and Anthropic signed a strategic agreement covering AI memory and storage architecture, supply, Claude adoption inside Micron and a Series H investment.

SK Hynix Puts $720B Memory Buildout Behind AI Chip Demand
Chips & Semiconductors

SK Hynix Puts $720B Memory Buildout Behind AI Chip Demand

CNBC reported that SK Hynix is investing $720 billion in South Korean memory factories as AI demand tightens high-bandwidth memory supply and pushes chip buyers toward longer contracts.

SK Hynix Nasdaq Debut Raises $26.5 Billion For AI Memory Capacity
Chips & Semiconductors

SK Hynix Nasdaq Debut Raises $26.5 Billion For AI Memory Capacity

The Associated Press said SK Hynix is raising about $26.5 billion through a Nasdaq listing to fund Korean fabs and packaging capacity, while also flagging a 200% share run and memory-cycle risk.

US Export-Control Shift Opens UAE AI Chip Access, DCD Reports
Chips & Semiconductors

US Export-Control Shift Opens UAE AI Chip Access, DCD Reports

Data Center Dynamics reported that the US government has moved the UAE into a lower-restriction export-control category, giving UAE companies broader access to advanced AI chips from Nvidia and AMD. The account names G42 and hyperscaler data-centre projects, but it does not list chip volumes, approved licences or specific UAE projects.

AMD’s EPYC 9006 Reset Pushes Venice Toward Denser AI Racks
Chips & Semiconductors

AMD’s EPYC 9006 Reset Pushes Venice Toward Denser AI Racks

AMD’s forthcoming EPYC 9006 Venice family adds Zen 6 cores, higher memory bandwidth, PCIe 6, CXL 3.1 and cache-coherent CPU-GPU links for AI-oriented servers.

Maybank Sees AI Demand Driving Singapore Semiconductor Growth
Chips & Semiconductors

Maybank Sees AI Demand Driving Singapore Semiconductor Growth

Maybank Investment Bank said AI-related demand should remain the main growth driver for Singapore semiconductor companies, while warning that large AI infrastructure spending still needs stronger revenue proof.

India AI Compute Buyers Face 36-To-52-Week GPU Lead Times
Chips & Semiconductors

India AI Compute Buyers Face 36-To-52-Week GPU Lead Times

Indian AI infrastructure buyers are still reserving GPU capacity months ahead. NeevCloud cofounder Narendra Sen said next-generation enterprise AI GPU lead times now range between 36 and 52 weeks, while named Indian startups are shifting training and inference around scarce capacity.

Keep Reading

More Stories

Latest
Universal Quantum Raises $100 Million for Trapped-Ion Computing ExpansionChips & SemiconductorsOct 10, 2026Universal Quantum Raises $100 Million for Trapped-Ion Computing ExpansionUniversal Quantum raised more than $100 million in a Series A round to commercialise trapped-ion quantum products and expand in Singapore, the US, Japan and Germany.Neela Raises £2.1M To Pilot Waste-To-SAF BiotechEconomyOct 10, 2026Neela Raises £2.1M To Pilot Waste-To-SAF BiotechCambridge startup Neela Biotech raised £2.1m to move its AI-guided microbial waste-to-SAF process from lab work into pilot trials at an existing biogas plant over the next two years.India and Saudi Arabia Put Port Investment Talks on Strategic Maritime RouteEconomyOct 9, 2026India and Saudi Arabia Put Port Investment Talks on Strategic Maritime RouteIndia and Saudi Arabia discussed possible Saudi participation in Vadhavan and Galathea Bay port projects, linking Gulf trade, container transshipment and maritime capacity building.MIT Expands STEM Workforce Training Through AI And Design ProgramsAIOct 9, 2026MIT Expands STEM Workforce Training Through AI And Design ProgramsMIT for America will scale existing university education programs nationwide, combining calculus support, responsible AI resources and hands-on fabrication to address STEM workforce access gaps.Google Maps Expands Restaurant Search Into Food OrderingCapital & PolicyOct 9, 2026Google Maps Expands Restaurant Search Into Food OrderingGoogle Maps is adding more dining workflow features, with Gemini-powered Ask Maps ordering links through Toast, Square and Uber Eats plus city trend lists and practical restaurant review signals.Lumio Raises $12 Million To Expand Its Consumer-Electronics PortfolioChips & SemiconductorsOct 9, 2026Lumio Raises $12 Million To Expand Its Consumer-Electronics PortfolioLumio raised a $12 million Series A led by Blume Ventures to add products, software, offline retail and support capacity for its smart TV, projector and speaker business.Apple Touchscreen MacBook Report Points To Late-October Hardware SlateChips & SemiconductorsOct 9, 2026Apple Touchscreen MacBook Report Points To Late-October Hardware SlateApple is reportedly preparing a late-October touchscreen MacBook debut alongside an OLED iPad Mini and M6 updates for the entry-level MacBook Pro and iMac.Australia Health Data Modernisation Reaches $32.8 Million on Google CloudCloud & Data CentersOct 9, 2026Australia Health Data Modernisation Reaches $32.8 Million on Google CloudAustralia’s Health department has lifted disclosed spending on a Google Cloud data and analytics modernisation program to $32.8 million across Accenture, NTT, Deloitte and Google contracts.Kioxia LD4 E1.L SSD Targets Dense 1U Hyperscale StorageCloud & Data CentersOct 9, 2026Kioxia LD4 E1.L SSD Targets Dense 1U Hyperscale StorageKioxia’s LD4 Series brings BiCS FLASH generation 8 QLC NAND into the E1.L form factor, starting with 15.36TB and 30.72TB models for read-intensive hyperscale servers while the architecture is validated up to 122.88TB.NeoFleet Raises $4 Million to Expand Taxi-Fleet FinancingReal EstateOct 9, 2026NeoFleet Raises $4 Million to Expand Taxi-Fleet FinancingNeoFleet Capital secured a $4 million pre-seed round to scale a taxi-fleet financing model that combines vehicle credit, telematics, insurance and operating controls across Africa and other emerging markets.Brahma AI Raises US$150 Million Toward Digital-Human LaunchAIOct 8, 2026Brahma AI Raises US$150 Million Toward Digital-Human LaunchBrahma AI raised US$150 million through preferred shares, including US$100 million from Multiples Alternate Asset Management, to expand an enterprise AI content platform and prepare interactive digital humans.OKX Draws Circle and Ripple Backing at $25 Billion ValuationFintech & Digital PaymentsOct 8, 2026OKX Draws Circle and Ripple Backing at $25 Billion ValuationOKX took undisclosed new investment from Circle, Ripple, Standard Chartered’s venture arm and Qube Research as it pushes beyond exchange trading into tokenized shares, stablecoins and consumer finance.