Key insights
- Marvell Technology Inc. has launched two new connectivity products, the Alaska E 3.2T retimer and the second-generation Alaska A 1.6T AEC DSP, designed for AI infrastructure. These chips support 224G signaling, offering higher bandwidth, longer reach, and improved power efficiency crucial for AI scale-up networks. The products are currently sampling to customers, with the AI networking market projected to exceed $50 billion by 2030.
SANTA CLARA, Calif. - Marvell Technology Inc. (NASDAQ:MRVL) announced Tuesday two connectivity products designed for AI infrastructure: the Alaska E 3.2T protocol-aware retimer and second-generation Alaska A 1.6T AEC DSP.
The Alaska E 3.2T retimer provides 3.2 terabits per second aggregate bandwidth through 16 lanes of 224G PAM4 connectivity. The device supports Ethernet, UALink and ESUN protocols and offers insertion loss compensation exceeding 45 decibels for on-board and backplane applications.
The second-generation Alaska A 1.6T AEC DSP, built on 3-nanometer technology, delivers eight lanes of 224G PAM4 connectivity for active electrical cables. The chip consumes 12.8 watts and supports copper reaches exceeding six meters, double the reach of the first-generation product. The device offers eight watts in power savings compared to 5-nanometer designs, according to the company’s press release statement.
Both products support data rates ranging from 50 gigabits to 1.6 terabits per second and are compatible with Ethernet, UALink and ESUN protocols. The devices are integrated into Marvell’s RELIANT interconnect telemetry platform.
"AI scale-up networks are moving rapidly to 224G signaling, making signal integrity, low latency and power efficiency critical to connecting increasingly dense infrastructure," said Xi Wang, senior vice president and general manager of Marvell’s Connectivity Business Group.
The products are currently sampling to customers. Marvell is showcasing the Alaska portfolio at OCP Global Summit 2026.
Vladimir Kozlov, founder and CEO of LightCounting, stated the AI scale-up networking market will exceed $50 billion by 2030, driven by the transition to rack-scale architectures and the move to 224G signaling.
This article was generated with the support of AI and reviewed by an editor. For more information see our T&C.
ProPicks AI re-scores MRVL every month against thousands of alternatives on 100+ financial metrics, then builds the strategies that came out ahead.Energy Elite is beating its benchmark by 37% year to date. Mid Cap Movers by 21%. Tech Titans, our flagship, has beaten the S&P 500 by 112% since launch three years ago.See whether MRVL made the cut — and which stocks did.