Broadcom Ships 3.5D Face-to-Face Compute SoC Powering AI Revolution

Rhea-AI Summary

Broadcom (NASDAQ: AVGO) began shipping the industry’s first 2nm custom compute SoC built on its 3.5D XDSiP platform, using Face-to-Face (F2F) integration to enable higher compute density, power efficiency and low latency for AI clusters.

Broadcom said the initial customer is Fujitsu, and that XDSiP-based XPUs for a broader customer base will ship from 2H 2026.

Positive

• Began shipping 2nm custom compute SoC using 3.5D XDSiP for Fujitsu
• 3.5D XDSiP enables independent scaling of compute, memory and network I/O
• Company announced XDSiP-based XPUs shipping from 2H 2026

Negative

• None.

News Market Reaction – AVGO

-3.19%

95 alerts

-3.19% News Effect

-3.4% Trough in 53 min

-$49.82B Valuation Impact

$1.51T Market Cap

0.4x Rel. Volume

On the day this news was published, AVGO declined 3.19%, reflecting a moderate negative market reaction. Argus tracked a trough of -3.4% from its starting point during tracking. Our momentum scanner triggered 95 alerts that day, indicating high trading interest and price volatility. This price movement removed approximately $49.82B from the company's valuation, bringing the market cap to $1.51T at that time.

Data tracked by StockTitan Argus on the day of publication.

Industry’s first 3.5D Face-to-Face (F2F) technology enables large-scale integration of XPUs delivering breakthrough performance, efficiency and scalability for AI clusters

PALO ALTO, Calif., Feb. 26, 2026 (GLOBE NEWSWIRE) -- Broadcom Inc. (NASDAQ: AVGO), a global technology leader that designs, develops and supplies semiconductor and infrastructure software solutions, today announced it has begun shipping the industry’s first 2nm custom compute SoC built on its 3.5D eXtreme Dimension System in Package (XDSiP) platform. A proven modular, multi-dimensional stacked die platform, 3.5D XDSiP combines 2.5D techniques and 3D-IC integration using Face-to-Face (F2F) technology.

3.5D XDSiP is foundational to next-generation XPUs. With 3.5D XDSiP, consumer AI customers can deliver the most advanced XPU with unparalleled signal density, superior power efficiency and low latency to meet the massive computational demands of gigawatt-scale AI clusters. Broadcom’s XDSiP platform allows compute, memory and network I/O to scale independently in a compact form factor, enabling high-efficiency, low-power computing at scale.

“We’re proud to deliver the first 3.5D custom compute SoC for Fujitsu – a testament to the outstanding execution and innovation by the Broadcom team,” said Frank Ostojic, senior vice president and general manager of Broadcom’s ASIC Products Division. “Since introducing our 3.5D XDSiP platform technology in 2024, Broadcom has expanded its 3.5D platform capabilities to support XPUs for our broader customer base that will ship from 2H '26. These developments underscore Broadcom’s unrivaled technology leadership in delivering high-complexity XPUs to enable transformative breakthroughs in AI.”

“The launch of Broadcom’s 3.5D XDSiP technology marks a transformative milestone in advanced semiconductor integration. By combining 2nm process innovation with Face-to-Face 3D integration, it unlocks unprecedented compute density and energy efficiency essential for the next era of AI and HPC,” Naoki Shinjo, SVP, Head of Advanced Technology Development Unit, Fujitsu. “This breakthrough is a key enabler for Fujitsu’s FUJITSU-MONAKA initiative to deliver cutting-edge, high-performance, and low-power processors. We highly value our strategic partnership with Broadcom and believe this technology will help power a more scalable and sustainable AI-driven society.”

For more information on Broadcom’s 3.5D XDSiP, please click here.

About Broadcom
Broadcom Inc. (NASDAQ: AVGO) is a technology leader that designs, develops, and supplies semiconductors and infrastructure software for global organizations’ complex, mission-critical needs. Broadcom combines long-term R&D investment with superb execution to deliver the best technology, at scale. Broadcom is a Delaware corporation headquartered in Palo Alto, CA. For more information, visit www.broadcom.com.

Broadcom, the pulse logo, and Connecting everything are among the trademarks of Broadcom. The term "Broadcom" refers to Broadcom Inc., and/or its subsidiaries. Other trademarks are the property of their respective owners.

Press Contact:
Khanh Lam
Global Communications
press.relations@broadcom.com
Telephone: +1 408 433 8649

FAQ

What did Broadcom (AVGO) announce about its 3.5D XDSiP on Feb 26, 2026?

Broadcom began shipping a 2nm custom compute SoC built on its 3.5D XDSiP platform. According to Broadcom, the shipment is for Fujitsu and uses Face-to-Face integration to boost density, efficiency and latency for AI clusters.

How does Broadcom’s 3.5D XDSiP technology improve AI compute for AVGO investors?

3.5D XDSiP delivers higher signal density, power efficiency and lower latency in compact packages. According to Broadcom, the platform lets compute, memory and network I/O scale independently for gigawatt-scale AI clusters.

Who is the initial customer for Broadcom’s 2nm XDSiP SoC and what does that mean for AVGO?

The initial customer is Fujitsu, per Broadcom. According to Broadcom, this commercial shipment demonstrates customer adoption of the 3.5D XDSiP platform and supports Fujitsu’s FUJITSU-MONAKA initiative for high-performance, low-power processors.

When will Broadcom (AVGO) ship XDSiP-based XPUs to a broader customer base?

Broadcom expects XDSiP-based XPUs to ship from 2H 2026. According to Broadcom, platform capability expansion since 2024 enables broader customer shipments in the second half of 2026.

What technical advantage does Face-to-Face (F2F) integration provide in Broadcom’s announcement?

Face-to-Face (F2F) integration enables closer die-to-die interconnects for greater signal density and efficiency. According to Broadcom, F2F combined with 2nm process yields improved compute density and energy efficiency for AI and HPC workloads.