Chip Industry Technical Paper Roundup: May 26


New technical papers recently added to Semiconductor Engineering’s library: Technical Paper Research Organizations SHIP: SRAM-Based Huge Inference Pipelines for Fast LLM Serving 🔗 Nvidia, Groq Not All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning 🔗 USC, University of Wisconsin-Madison Water-based, large-scale transfer of... » read more

Large-scale, SRAM-based LLM Inference Deployment (Groq)


A new technical paper, "SHIP: SRAM-Based Huge Inference Pipelines for Fast LLM Serving," was published by researchers at Nvidia, with work done while at Groq. Abstract "The proliferation of large language models (LLMs) demands inference systems with both low latency and high efficiency at scale. GPU-based serving relies on HBM for model weights and KV caches, creating a memory bandwidth b... » read more

Chip Industry Week In Review


Deals: NVIDIA inked a $20B non-exclusive licensing deal with Groq for its inference technology. The startup's founder, Jonathan Ross, and some other employees will join NVIDIA to assist in scaling and advancing the technology. The non-exclusive licensing deal, versus an outright purchase, is a tool other companies have used to avoid antitrust regulation. Samsung Ventures made a strategic inv... » read more

Chip Industry Week in Review


Retaliations and countermoves leading up to planned trade talks between the U.S. and China led experts to wonder, 'Who's winning?' New activity on this front: China issued questionnaires to some U.S. semiconductor firms as part of an anti-dumping probe, demanding detailed data on sales, profit margins, logistics costs and Chinese customer names for analog chips. The probe appears aimed at ... » read more

Chip Industry Startup Funding: Q3 2025


The third quarter of 2025 was dominated by massive rounds for companies developing AI chips and quantum computers. Over $2.5 billion went to AI, with wafer-scale chip maker Cerebras leading the pack with a $1.1 billion raise. While several edge AI companies received backing, the quarter saw a marked shift towards solutions for the data center as firms seek to reduce the cost and power consumpti... » read more

Chip Industry Week in Review


Amkor, TSMC, and Cadence partnered with Tesoro VC, which will serve as the lead operator of a new Global AI + Semiconductor Startup Hub and a Global Design Center in Phoenix, Arizona, aimed at chip innovation, startup growth, and advanced manufacturing. Nvidia will invest $5 billion in Intel common stock at a purchase price of $23.28 per share and the companies will collaborate on AI infrastru... » read more

Chip Industry Week In Review


GlobalFoundries plans to acquire MIPS, adding RISC-V processor IP and PPA optimization software capabilities to its foundry offerings. MIPS will continue to operate as a standalone business within GF. The deal is expected to close in the second half of 2025. The EU rolled out new general-purpose AI rules this week to limit copyright infringement, protect public safety, and require transparency... » read more

Chip Industry Week In Review


Worldwide silicon wafer shipments declined nearly 2.7% to 12,266 million square inches in 2024, with wafer revenue contracting 6.5% to $11.5 billion, according to the SEMI Silicon Manufacturers Group. CSIS released a new report, “Critical Minerals and the Future of the U.S. Economy,” with detailed analysis and policy recommendations for building a secure mineral supply chain for semicond... » read more

Startup Funding: Q3 2024


Numerous new companies burst on the scene in the third quarter of 2024, including startups with plans for customizable RISC-V-based IP for applications from microcontrollers to data centers, high-speed data center interconnects, compute-in-memory LLM inference chips, and surveillance camera SoCs. Although it did not report funding, AheadComputing also launched last quarter to develop RISC-V cor... » read more

Chip Industry Week In Review


Three Fraunhofer Institutes (IIS/EAS, IZM, and ENAS) launched the Chiplet Center of Excellence, a research initiative to support the commercial introduction of chiplet technology. The center initially will focus on automotive electronics, developing workflows and methods for electronics design, demonstrator construction, and the evaluation of reliability. The UCIe Consortium published the Un... » read more

← Older posts