Crisis Ahead: Power Consumption In AI Data Centers


AI data centers are consuming energy at roughly four times the rate that more electricity is being added to grids, setting the stage for fundamental shifts in where power is generated, where AI data centers are built, and much more efficient system, chip, and software architectures. The numbers are particularly striking for the United States and China, which are in a race to ramp up AI data ... » read more

Chip Industry Week in Review


The U.S. government will grant licenses to NVIDIA and AMD to again sell some AI chips — NVIDIA's H20 GPU and AMD's MI308 — to Chinese companies. TrendForce projects that the availability of NVIDIA chips, in particular, will create a surge in demand from Chinese AI firms and cloud service providers, and boost high-bandwidth memory (HBM) consumption. The move could raise China’s share of... » read more

Rowhammer Attack On NVIDIA GPUs With GDDR6 DRAM (University of Toronto)


A new technical paper titled "GPUHammer: Rowhammer Attacks on GPU Memories are Practical" was published by researchers at University of Toronto. Abstract: "Rowhammer is a read disturbance vulnerability in modern DRAM that causes bit-flips, compromising security and reliability. While extensively studied on Intel and AMD CPUs with DDR and LPDDR memories, its impact on GPUs using GDDR memorie... » read more

Chip Industry Technical Paper Roundup: July 15


New technical papers recently added to Semiconductor Engineering’s library: [table id=446 /] Find more semiconductor research papers here. » read more

Startup Funding: Q2 2025


Investors were drawn to a wide range of innovative approaches in Q2 2025, backing startups developing superconducting logic, chips for an emerging number format, big data processors, and novel power semi architectures. At the same time, photonics continues to draw investment dollars due to its ability to move data faster and with less energy at both the chip-to-chip and data center levels. T... » read more

NVIDIA GPU Confidential Computing: Threat Model And Security Insights (IBM Research, Ohio State)


A new technical paper titled "NVIDIA GPU Confidential Computing Demystified" was published by IBM Research and Ohio State University. Abstract "GPU Confidential Computing (GPU-CC) was introduced as part of the NVIDIA Hopper Architecture, extending the trust boundary beyond traditional CPU-based confidential computing. This innovation enables GPUs to securely process AI workloads, providing ... » read more

Chip Industry Week in Review


[Editor's Note: Early edition due to the U.S. July 4th holiday.] The U.S. government lifted export restrictions that barred Synopsys, Siemens EDA, and Cadence from selling EDA tools to China. In a statement, Synopsys said it received a letter from the U.S. Commerce Department immediately rescinding those restrictions. Siemens issued a similar statement. Which tools or hardware accelerated t... » read more

Review Paper: Wafer-Scale Accelerators Versus GPUs (UC Riverside)


A new technical paper titled "Performance, efficiency, and cost analysis of wafer-scale AI accelerators vs. single-chip GPUs" was published by researchers at UC Riverside. "This review compares wafer-scale AI accelerators and single-chip GPUs, examining performance, energy efficiency, and cost in high-performance AI applications. It highlights enabling technologies like TSMC’s chip-on-wafe... » read more

TSMC: King Of Data Center AI


Large language models (LLMs like ChatGPT) are driving the rapid expansion of data center AI capacity and performance. More capable LLM models drive demand and need more compute. AI data centers require GPUs/AI Accelerators, switches, CPUs, storage and DRAM. About half of semiconductors are consumed by AI data centers now. This percentage will be much higher by 2030. TSMC has essentially 1... » read more

Chip Industry Week in Review


The Chinese Academy of Sciences unveiled a fully automated processor chip design system, claiming the potential to accelerate semiconductor development and replace human programmers. Micron Technology plans to expand its U.S. investments to approximately $150 billion in domestic memory manufacturing and $50 billion in R&D, which is $30 billion higher than previously reported. AMD laun... » read more

← Older posts Newer posts →