We use cookies to understand how you use our site and to improve your experience.
This includes personalizing content and advertising.
By pressing "Accept All" or closing out of this banner, you consent to the use of all cookies and similar technologies and the sharing of information they collect with third parties.
You can reject marketing cookies by pressing "Deny Optional," but we still use essential, performance, and functional cookies.
In addition, whether you "Accept All," Deny Optional," click the X or otherwise continue to use the site, you accept our Privacy Policy and Terms of Service, revised from time to time.
You are being directed to ZacksTrade, a division of LBMZ Securities and licensed broker-dealer. ZacksTrade and Zacks.com are separate companies. The web link between the two companies is not a solicitation or offer to invest in a particular security or type of security. ZacksTrade does not endorse or adopt any particular investment strategy, any analyst opinion/rating/report or any approach to evaluating individual securities.
If you wish to go to ZacksTrade, click OK. If you do not, click Cancel.
MRVL's Modular Packaging Tech: Can it Transform AI Accelerators?
Read MoreHide Full Article
Key Takeaways
MRVL is deploying modular RDL interposer tech to build larger, high-efficiency AI accelerator solutions.
The design supports HBM3/3E integration, enables die replacement, and enhances power and latency performance.
MRVL sees a $94B data center chip market by 2028, with custom compute offerings witnessing a 53% CAGR.
Marvell Technology (MRVL - Free Report) uses advanced CMOS technologies at 5nm and 3nm nodes and is now shifting toward 2nm and below, which include innovations like gate-all-around transistors and backside power delivery.
For advanced packaging solutions, Marvell Technology has been leveraging Chip-on-Wafer-on-Substrate and Integrated Fan-Out methods, which enabled it to develop complex 2.5D, 3D, and 3.5D designs for high-performance compute Application Specific Integrated Circuit.
Marvell Technology is now enhancing its capabilities with modular redistribution layer (RDL) interposer technology as an alternative to traditional silicon interposers. This 2.5D packaging technology can be used to develop multi-die AI accelerator solutions that are 2.8 times larger compared to existing single monolithic dies and integrate four HBM3/3E stacks across six RDL layers.
The RDL interposer technology also offers shorter die-to-die connections to reduce latency and improve power efficiency. As the RDL solution is modular in nature, it allows seamless replacement of defective dies, which finally reduces costs and increases yields. The technology is compatible with HBM3/3E, XPU-type chips, and is expected to be qualified for the upcoming HBM-4.
These factors have made it attractive for hyperscalers to use it readily. As data center infrastructure investments grow at a rapid pace, Marvell Technology is expected to capitalize on it. MRVL anticipates that its total addressable market for data center semiconductors will rise to $94 billion by 2028. It expects its accelerated custom compute offerings to reach $55.4 billion with a CAGR of 53% from 2023 to 2028.
How Competitors Fare Against Marvell Technology
Broadcom’s (AVGO - Free Report) advanced 3.5D XDSiP packaging platform is specifically designed to enhance the performance and efficiency of custom AI XPUs for AI accelerators. Broadcom’s Semiconductor segment, which accounts for its custom silicon solutions, grew 11% year over year in the first quarter of fiscal 2025.
Advanced Micro Devices (AMD - Free Report) is another player in the custom silicon solutions and AI accelerator space with its semi-custom SoC offerings and Instinct Accelerators that power numerous data centers. Advanced Micro Devices’ reconfigurable Alveo Adaptable Accelerator Cards are used to speed up compute-intensive applications in data centers.
While Broadcom and Advanced Micro Devices are formidable players in the custom silicon space for AI accelerators, Marvell Technology’s move toward the 2.5D packaging platform and leveraging of modular RDL interposer technology is likely to push it much ahead of other players in this space.
The Zacks Consensus Estimate for Marvell’s fiscal 2026 and 2027 earnings implies year-over-year growth of 77.7% and 27.73%, respectively. The estimates for fiscal 2026 and 2027 have been revised upward in the past seven days.
Image: Bigstock
MRVL's Modular Packaging Tech: Can it Transform AI Accelerators?
Key Takeaways
Marvell Technology (MRVL - Free Report) uses advanced CMOS technologies at 5nm and 3nm nodes and is now shifting toward 2nm and below, which include innovations like gate-all-around transistors and backside power delivery.
For advanced packaging solutions, Marvell Technology has been leveraging Chip-on-Wafer-on-Substrate and Integrated Fan-Out methods, which enabled it to develop complex 2.5D, 3D, and 3.5D designs for high-performance compute Application Specific Integrated Circuit.
Marvell Technology is now enhancing its capabilities with modular redistribution layer (RDL) interposer technology as an alternative to traditional silicon interposers. This 2.5D packaging technology can be used to develop multi-die AI accelerator solutions that are 2.8 times larger compared to existing single monolithic dies and integrate four HBM3/3E stacks across six RDL layers.
The RDL interposer technology also offers shorter die-to-die connections to reduce latency and improve power efficiency. As the RDL solution is modular in nature, it allows seamless replacement of defective dies, which finally reduces costs and increases yields. The technology is compatible with HBM3/3E, XPU-type chips, and is expected to be qualified for the upcoming HBM-4.
These factors have made it attractive for hyperscalers to use it readily. As data center infrastructure investments grow at a rapid pace, Marvell Technology is expected to capitalize on it. MRVL anticipates that its total addressable market for data center semiconductors will rise to $94 billion by 2028. It expects its accelerated custom compute offerings to reach $55.4 billion with a CAGR of 53% from 2023 to 2028.
How Competitors Fare Against Marvell Technology
Broadcom’s (AVGO - Free Report) advanced 3.5D XDSiP packaging platform is specifically designed to enhance the performance and efficiency of custom AI XPUs for AI accelerators. Broadcom’s Semiconductor segment, which accounts for its custom silicon solutions, grew 11% year over year in the first quarter of fiscal 2025.
Advanced Micro Devices (AMD - Free Report) is another player in the custom silicon solutions and AI accelerator space with its semi-custom SoC offerings and Instinct Accelerators that power numerous data centers. Advanced Micro Devices’ reconfigurable Alveo Adaptable Accelerator Cards are used to speed up compute-intensive applications in data centers.
While Broadcom and Advanced Micro Devices are formidable players in the custom silicon space for AI accelerators, Marvell Technology’s move toward the 2.5D packaging platform and leveraging of modular RDL interposer technology is likely to push it much ahead of other players in this space.
MRVL's Price Performance, Valuation and Estimates
Shares of MRVL have lost 34.5% year to date against the Electronics - Semiconductors industry’s growth of 15%.
Marvell Technology YTD Performance Chart
Image Source: Zacks Investment Research
From a valuation standpoint, Marvell Technology trades at a forward price-to-sales ratio of 7.02X, lower than the industry’s average of 8.72X.
Marvell Technology Forward Twelve Months (P/S) Valuation Chart
Image Source: Zacks Investment Research
The Zacks Consensus Estimate for Marvell’s fiscal 2026 and 2027 earnings implies year-over-year growth of 77.7% and 27.73%, respectively. The estimates for fiscal 2026 and 2027 have been revised upward in the past seven days.
Image Source: Zacks Investment Research
Marvell Technology currently carries a Zacks Rank #3 (Hold). You can see the complete list of today’s Zacks #1 Rank (Strong Buy) stocks here.