Chip Industry Week In Review


Global spending on 300mm fab equipment is expected to reach a record US$400 billion from 2025 to 2027, according to SEMI. Key drivers are the regionalization of semiconductor fabs and the increasing demand for AI chips in data centers and edge devices, with China, South Korea, and Taiwan leading the way. The Biden-Harris Administration launched the National Semiconductor Technology Center’... » read more

RAG-Enabled AI Stops Hallucinations, Adds Sources


Many EDA companies have taken the first steps to incorporate generative AI into their tools, and in such tightly controlled environments GenAI appears to have great benefits. But its broader adoption has been delayed by its notorious inaccuracy, giving results that are often out of date, untrue, and unsourced. That's starting to change. GenAI is evolving so rapidly that these kinds of proble... » read more

CXL Thriving As Memory Link


CXL is emerging from a jumble of interconnect standards as a predictable way to connect memory to various processing elements, as well as to share memory resources within a data center. Compute Express Link is built on a PCI Express foundation and supported by nearly all the major chip companies. It is used to link CPUs, GPUs, FPGAs, and other purpose-built accelerators using serial communic... » read more

Blog Review: Sept. 11


Cadence's Neha Joshi introduces the IEEE 1801 standard, also known as UPF (Unified Power Format), which offers a uniform framework for defining power domains, power states, and power intent to ensure consistency across diverse tools and phases of the design process. Siemens' John McMillan warns that known good die may not behave the same in 3D-ICs as they do standalone and suggests that mult... » read more

Chip Industry Week In Review


Concerns mount on the use of American-manufactured semiconductors in Russian weapons, with Analog Devices, AMD, Intel and TI set to testify next week before the U.S. Senate Permanent Subcommittee on Investigations. Also, U.S. and other government agencies issued a joint advisory and more details about ongoing Russian military cyberattacks, espionage, and sabotage. The U.S. Commerce Departmen... » read more

New AI Processors Architectures Balance Speed With Efficiency


Leading AI systems designs are migrating away from building the fastest AI processor possible, adopting a more balanced approach that involves highly specialized, heterogeneous compute elements, faster data movement, and significantly lower power. Part of this shift revolves around the adoption of chiplets in 2.5D/3.5D packages, which enable greater customization for different workloads and ... » read more

Chip Industry Technical Paper Roundup: Sept. 3


New technical papers recently added to Semiconductor Engineering’s library: [table id=256 /] More ReadingTechnical Paper Library home » read more

Chip Industry Week in Review


The Biden-Harris Administration announced preliminary terms with HP for $50 million in direct funding under the CHIPs and Science Act to support the expansion and modernization of HP’s existing microfluidics and microelectromechanical systems (“MEMS”) facility in Corvallis, Oregon. CHIPS for America launched the CHIPS Metrology Community, a collaborative initiative designed to advance ... » read more

GPU Microarchitecture Integrating Dedicated Matrix Units At The Cluster Level (UC Berkeley)


A new technical paper titled "Virgo: Cluster-level Matrix Unit Integration in GPUs for Scalability and Energy Efficiency" was published by UC Berkeley. Abstract "Modern GPUs incorporate specialized matrix units such as Tensor Cores to accelerate GEMM operations central to deep learning workloads. However, existing matrix unit designs are tightly coupled to the SIMT core, limiting the size a... » read more

Characterizing Three Supercomputers: Multi-GPU Interconnect Performance


A new technical paper titled "Exploring GPU-to-GPU Communication: Insights into Supercomputer Interconnects" was published by researchers at Sapienza University of Rome, University of Trento, Vrije Universiteit Amsterdam, ETH Zurich, CINECA, University of Antwerp, IBM Research Europe, HPE Cray, and NVIDIA. Abstract "Multi-GPU nodes are increasingly common in the rapidly evolving landscape... » read more

← Older posts Newer posts →