AI Accelerator Spec Maintains Rapid Update Pace
As the AI accelerator “arms race” continues unabated, UALink is likely to continue to get annual updates.
By Gary Hilson, EE Times | May 4, 2026

It makes sense that the standard governing AI accelerators should release an update less than a year after its first iteration.
Ultra Accelerator Link (UALink) 1.0 was released in April 2025, and the UALink consortium just released a major update to the specification that addresses in-network compute, chiplet definition, and manageability. These additions will support the deployment of UALink solutions in multi-workload environments and help improve UALink technology efficiency, performance for AI workloads, and ease of implementation.
In a briefing with EE Times, Kurtis Bowman, UALink consortium board chair, said the evolution of UALink reflects the rapid growth of accelerators in data centers, where memory bandwidth is critical to performance.
To read the full article, click here
Related Semiconductor IP
- UALink PHY + Controller
- Simulation VIP for UALink
- UALink Subsystem
- UALink Controller
- UALink PCS IP Core
Related News
- Synopsys Announces Industry's First Ultra Ethernet and UALink IP Solutions to Connect Massive AI Accelerator Clusters
- Ultra Accelerator Link Consortium (UALink) Welcomes Alibaba, Apple and Synopsys to Board of Directors
- First Benchmarks Revealed for Jalapeño, OpenAI’s Clean-Sheet General Purpose AI Accelerator ASIC
- SEMIFIVE Commences Mass Production of HyperAccel’s LLM AI Inference Accelerator ‘Bertha’ on Samsung 4nm, Spurring Growth Momentum
Latest News
- Sofics Extends Interface Voltage Options in TSMC FinFET and Nanosheet Technologies
- aiMotive and Cadence Demonstrate Layer-by-Layer Workload Placement Across Independent AI Engines
- Alchip collaborates with Synopsys to Address Scale Up and Out Bandwidth Constraints
- M31 and Ambiq Collaborate on TSMC N12e® Foundation IP to Address Demanding SoC Power and Area Targets
- Siemens and TSMC advance AI-powered semiconductor design automation