Chip Industry Technical Paper Roundup: August 5


New technical papers recently added to Semiconductor Engineering’s library: [table id=460 /] Find more semiconductor research papers here. » read more

LLM Inference: Core Bottlenecks Imposed By Memory, Compute Capacity, Synchronization Overheads (NVIDIA)


A new technical paper titled "Efficient LLM Inference: Bandwidth, Compute, Synchronization, and Capacity are all you need" was published by NVIDIA. Abstract "This paper presents a limit study of transformer-based large language model (LLM) inference, focusing on the fundamental performance bottlenecks imposed by memory bandwidth, memory capacity, and synchronization overhead in distributed ... » read more

Chip Industry Week in Review


The U.S. government announced new import tariff actions and deals this week, including: The EU: 15% tariff on most goods including semiconductors. According to the EU's president, the action excludes semiconductor equipment. Copper: 50% tariff on all imports of semi-finished copper products and intensive copper derivative products, effective Aug. 1, but raw input material is excluded. ... » read more

Chip Industry Week in Review


Intel reported flat year-over year revenue for Q2, exceeding Wall Street's pessimistic expectations. In a message to employees, CEO Lip-Bu Tan said the company will: Cut about 15% of its staff, ending the year with about 75,000 employees, down from a high of nearly 132,000 in 2022; Scrap projects in Poland and Germany, consolidate other sites in central America and Southeast Asia, and s... » read more

CMOS 2.0: Layered Logic For The Post-Nanosheet Era


The semiconductor industry has relied on a simple equation for more than five decades — shrink the transistor, pack more onto every wafer, and watch performance soar as costs plummet. While each new node delivered predictable gains in speed, power efficiency, and density, that formula is rapidly running out of steam. As transistors approach single-digit nanometer processes, manufacturing c... » read more

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

← Older posts Newer posts →