The letter

One letter a week, starting soon.

The week's signal, what shipped, what is worth running tonight, and the editor's note. No tracking, no ads, nothing else.

We keep your address, your language and the date you joined, nothing else. Every letter has a one-click unsubscribe link that deletes the record.

SemiEngineering

10 stories

SemiEngineeringSiliconShifting HBM4 Controller Functions Closer To Memory (UC Riverside) Tharunya Yogananda and Wantong Li of the University of California, Riverside published a technical paper titled “Beyond Host-Side Control: HBM Controller Partitioning Across Host and HBM Base Dies.”…

11.13

SemiEngineeringSiliconChip Industry Week In Review Innovations A wave of announcements this week, including several from SEMICON Europa and electronica 2026 in Munich, highlighted advances in semiconductor manufacturing, advanced packaging…

11.13

SemiEngineeringSiliconThe Semiconductor Singularity Semiconductor innovation is entering a new era defined by exponential feedback loops between hardware and software, a transformation Ray Kurzweil characterizes as the “semiconductor singularity.”…

11.12

SemiEngineeringSiliconRethinking Memory For AI Inference Key Takeaways: Moving compute closer to memory can reduce data movement, power consumption, and latency.

11.12

SemiEngineeringSiliconBeyond Bandwidth: AI Inference Is Reshaping The Memory Wall AI infrastructure has spent the past several years in a race for compute. More accelerators, larger heterogeneous clusters, and higher peak performance have enabled increasingly capable models.

11.12

SemiEngineeringSiliconThe Semiconductor Singularity: When AI Starts Accelerating The Silicon That Accelerates AI AI is entering the inner loop of semiconductor engineering by reducing the effort required to develop software, operate software tools and carry out engineering analysis.

11.12

SemiEngineeringSiliconDesigning Edge AI SoCs At Near-Threshold: Why Foundation IP Can Help You Break Down The Power Wall Lowering operating voltage is a key to SoC power optimization. In advanced FinFET processes at ~0.4–0.5V, it can also start to become a design risk.

11.12

SemiEngineeringSiliconIP Integration Challenges Evolve Key Takeaways: Integration challenges go beyond making sure a block is properly connected. Semantic issues cause the most problems, and many are due to incomplete or bad specifications.

11.12

SemiEngineeringSiliconThe Memory Challenge Of Physical AI Most AI hardware conversations start with compute, which is understandable since accelerators are visible, easy to compare, and often tied to headline performance metrics.

11.12

SemiEngineeringSiliconIntroduction To FP8 Formats: Part 1 The industry is moving from high-precision formats (FP32, FP16, BF16) to lower-precision data types for Machine Learning (ML) inference and training.

11.12