Chips and semiconductors: research

Journal articles, academic blogs, think-tank reports and papers in this section, newest first. Back to the news.

arXiv (research papers) Elba Garza

Bit-level Perceptron Prediction for Indirect Branches

Modern software uses indirect branches for various purposes including, but not limited to, virtual method dispatch and implementation of switch statements. Because an indirect branch's target address cannot be determined prior to execution, high-performance processors depend on highly-accurate indirect branch prediction techniques to mitigate control hazards. This paper proposes a new indirect branch prediction scheme that predicts target addresses at the bit level. Using a…

Read at arXiv (research papers)

arXiv (research papers) Guanqi Lyu

AutoC2V: Synthesis-Guided LLM Training for QoR-Optimized C++-to-Verilog Generation

High-level synthesis (HLS) can translate C/C++ kernels into register-transfer level (RTL) designs, yet generating high-quality hardware still relies heavily on manual pragma tuning and repeated synthesis evaluation. We propose AutoC2V, a C++-to-Verilog generation framework driven by real synthesis feedback that enables large language models (LLMs) to directly generate RTL with improved quality of results (QoR) from synthesizable C++ kernels. We construct training data from…

Read at arXiv (research papers)

arXiv (research papers) Wuqian Tang

RTLREX: LLM-Guided Framework for Exact High-Level RTL Recovery

Hardware designs may be available only as gate-level netlists or input-output descriptions when the original register-transfer-level (RTL) design and documentation are not accessible. Low-level representations obscure word-level computation and its finite-width behavior. Recovering high-level RTL from such representations therefore helps engineers understand a circuit's functionality and enables RTL rewriting and resynthesis. A plausible function model is also insufficient…

Read at arXiv (research papers)

arXiv (research papers) Karthikeyan B. Kalyanasundara

PENSA: A Spatial Accelerator for BitNet b1.58 Inference on an HBM-equipped AMD Alveo FPGA

Ternary large language models (tLLMs) replace general multiplication in dominant linear layers with sign-controlled accumulation, shifting hardware bottlenecks toward packed-weight delivery, reduction, and operator occupancy. PENSA is an end-to-end FPGA accelerator for the BitNet b1.58 2B4T model on an AMD Alveo U50. Two row-partitioned ternary matrix engines consume packed TQ1_0 weights from eight independent high-bandwidth memory (HBM) pseudo-channels, each processing…

Read at arXiv (research papers)

arXiv (research papers) Rajat Bhattacharjya

EmbodiedIntentBench: Benchmarking Intent-Driven Runtime Adaptation for Mobile Robotic Missions

Mobile robotic sensing systems must adapt to operator requirements, limited resources, changing connectivity, and observation opportunities shaped by physical motion. Evaluating runtime strategies therefore requires assessing whether their decisions fulfill mission objectives, beyond isolated perception accuracy or execution efficiency. We present EmbodiedIntentBench, a benchmark for intent-driven runtime adaptation in mobile robotic missions. It represents mission intent…

Read at arXiv (research papers)

Journal articles (OpenAlex) Fugeng Wu, Jinbing Zhang, Wentao Shao et al. · Electron

Thermally Conductive and Electrically Insulating Thermal Interface Materials for Advanced Packaging: From Filler and Interface Engineering to Thermal Networks

ABSTRACT Thermal interface materials (TIMs) that combine efficient heat transport with electrical insulation are increasingly important for three‐dimensional integration and high‐power electronic packaging. Existing reviews commonly organize the field by filler type or treat surface modification, filler alignment, and network construction as separate strategies, obscuring their coupling across length scales. Here, we present a hierarchical design framework linking physical…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Manushi Shihara de Silva, Renato J. Cintra, Arjuna Madanayake · Electronics

Agentic Design of Approximate DFT Digital IP Cores on TSMC 28 nm CMOS ASIC Technology with Verification on RF-SoC

Artificial intelligence (AI)-based digital integrated circuit (IC) design is exploding in the chip industry. Agent-based digital logic design is considered the next paradigm in computer architecture at the chip level. In this work, we explore the domain specialization of a Claude-based AI agent on the specific topic of Fast Fourier transform (FFT) algorithms, using butterfly architectures for sparse factorized matrix-vector realization of discrete Fourier transform (DFT)…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Andres Garcia Coleto, Henry Crawford-Eng, Theodore J. Dahl et al. · Nanophotonics

AIM‐Photonics Visible‐to‐Near‐Infrared Silicon‐Nitride‐Based Silicon‐Photonics Platform and Component Library

Silicon-photonics platforms operating at visible and near-infrared wavelengths are essential for a growing range of applications, including biosensing, chemical detection, Raman spectroscopy, quantum, optogenetics, and displays. However, unlike their infrared counterparts, visible-wavelength platforms have lacked comprehensive component libraries with pre-characterized devices, limiting the ability to rapidly design photonic integrated circuits for these applications. In…

Read at Journal articles (OpenAlex)

arXiv (research papers) Prerana Ramkumar

The World Model Planning Accelerator (WMPA): Hardware-Algorithm Co-Design for Embedded AI in Robotics

Embedded AI is moving from perception to prediction. Robots now use world models$\unicode{x2014}$learned simulators that predict the outcome of candidate actions in a compressed latent space before any is executed. Every predicted step must be computed on board within a tight power and thermal budget, yet the energy these steps fundamentally require, and how far real hardware sits from it, have not been characterized. We derive lower bounds on the arithmetic operations and…

Read at arXiv (research papers)

arXiv (research papers) Dayou Du

BitDecoding-FP4: Native FP4 KV Cache Decoding via Algorithm-System Co-Design

The key-value (KV) cache dominates memory capacity and bandwidth in long-context LLM serving. While 4-bit microscaling formats (NVFP4, MXFP4) shrink the cache and run attention on FP4 Tensor Cores, a fundamental gap remains between algorithmic quantization and system-aware acceleration: existing FP4 KV systems use vanilla quantization that causes severe accuracy drops, whereas accuracy-oriented 4-bit algorithms rely on vector codebooks whose lookup overhead degrades decoding…

Read at arXiv (research papers)

arXiv (research papers) Ahmed Zeer

Atik: A Shared-Mesh Transformer Accelerator for RISC-V

Transformer inference repeatedly invokes dense matrix multiplication and attention, including its data-dependent softmax normalization. We present Atik, an open-source RoCC accelerator for RocketChip that executes matrix multiplication and dense attention through one shared fixed-point MAC mesh. Atik accepts and returns BF16 tensors, uses a streaming online-softmax schedule that never materializes the full score matrix, and is invoked through a small descriptor-based ABI. We…

Read at arXiv (research papers)

arXiv (research papers) Adrian Jackson

Memory as a Temporal Resource: Lifetime Contracts for Multi-Retention Systems

Computers move and rewrite data whose useful lifetimes range from inner-loop iterations to years, yet memory systems usually hide retention as a fixed physical property. We argue that required lifetime should become a first-class resource across algorithms, programming systems, controllers, and devices. Building on prior lifetime-aware placement, we propose an event-based validity contract that links application completion events to retention-class selection and renewal of…

Read at arXiv (research papers)

Journal articles (OpenAlex) Gian Francesco Lorusso, Alain Moussa, Sahel Habashieh et al. · Journal of Micro/Nanopatterning Materials and Metrology

High landing energy SEM dimensional metrology for High NA EUVL

BackgroundRecently, High Numerical Aperture Extreme Ultraviolet Lithography (High-NA EUVL) started delivering its first wafers, showing its potential by printing 18 and 16 nm pitch line/space. However, as feature sizes drop below 10 nm, questions are raised on the ability of the current metrology procedures and tools to properly characterize such small targets. In particular, it is critical to assess the impact of limited spatial resolution and identify possible ways…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Li Li, Yuyang Li, Junya Tang et al. · Autonomous Intelligent Systems

Toward autonomous decision support in semiconductor manufacturing: a review of planning, scheduling, dispatching, and execution control

Abstract Semiconductor manufacturing is a high-stakes cyber-physical production domain in which planning targets, scheduling feasibility, dispatching actions, process-control feedback, and human oversight must remain continuously aligned. This paper presents a structured state-of-the-art review of semiconductor smart manufacturing from the perspective of autonomous intelligent systems (AIS). The review does not treat planning, scheduling, dispatching, real-time dispatching…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Kexin Wang, Jianshi Tang, Yibei Zhang et al. · ACS Nano

High-Reliability Ultrascaled IGZO FETs for Multibit 2T0C DRAM toward Monolithic 3D Integration of an AI Accelerator

Abstract The continued scaling of silicon-based dynamic random-access memory (DRAM) slows down due to increased process complexity and reduced storage capacitance. Oxide semiconductors (OS), represented by InGaZnOx (IGZO), offer an attractive alternative owing to their ultralow leakage and low thermal budget, making them promising candidates for next-generation DRAM as well as monolithic three-dimensional (M3D) architectures. However, realizing IGZO devices with…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Sze Pei Lim, Jason Chou, Chun Wei Yang et al. · IMAPSource Proceedings

Novel Interconnect Materials for Advanced Packaging Assembly Processes

As advanced packaging continues to drive towards heterogeneous integration, new materials need to be developed to address the many challenges faced in the assembly process. Development of novel materials for the various assembly processes is crucial to ensuring high yield for the assembly process for reliable SiP applications, and high density, fine pitch interconnects. As ultra-fine pitch flip-chips become prevalent in advanced packaging, with reduced standoff of flip-chips…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Mohsin A. Patel, Raphael Nam, Marisol Valdez et al. · Journal of Micro/Nanopatterning Materials and Metrology

Minimizing line/space pattern defects and roughness of indium nitrate resists through environmental control

The processing environment has a significant effect on the performance of metal oxide resists (MORs). Here, we examine the effects of relative humidity (RH) and atmospheric oxygen on the morphology, chemical composition, and line/space (L/S) patterning results of indium(III) nitrate hydrate (In(NO3)3·xH2O) MORs. Previous work shows that processing In(NO3)3-based resists under ambient conditions at RH≥40% produces localized surface protrusions at the nanoscale, which disrupt…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Poonsub Threepopnatkul, Supanut Phattarateera, Natdanai Sirayanyong et al. · Key engineering materials

Effect of PLA Molecular Weight on Mechanical and Morphological Properties of PVA/PLA Biomaterial Blown Films

This study investigates the influences of polylactic acid (PLA) molecular weight on mechanical behaviors and morphological property of polyvinyl alcohol (PVA)/PLA biomaterial blown films. Three commercial PLAs (L105, L130, and L175) with distinct molecular weights are individually blended with PVA at a fixed ratio of 50 wt%. Glycerol (20 phr) is employed as a plasticizer to enhance film processability. Films are fabricated via twin-screw extrusion followed by film blowing…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Jungrae Park, Joshua Peck, Joshua S. Hooge et al. · IMAPSource Proceedings

Low Thermal Damage Laser Lift-off (LLO) Enabling Multi-Cycle Carrier Wafers Reuse for Advanced Packaging

Fusion and hybrid bonding are becoming critical enablers in advanced packaging for die-to-wafer (D2W), high-bandwidth memory (HBM), and artificial intelligence (AI) applications. Laser lift-off (LLO) employing short-pulsed IR laser beam provides a clean and efficient method to release permanently bonded Si carrier wafers without need of a glue layer or backside grinding processes. LLO enables multiple carrier wafer reuse cycles, offering significant cost reduction and…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Antika Roy, Pratyush Shukla, Junfu Cheng et al. · IMAPSource Proceedings

INSIGHT-X: Multimodal VLM Assistant for Artifact Localization, and Mitigation Guidance in X-ray Inspection

Advanced semiconductor packages rely on X-ray CT and laminography for non-destructive inspection of buried interconnects and internal structures. However, dense metal features and heterogeneous materials often introduce artifacts, including ring artifacts, beam-hardening streaks, geometric distortions, and missing-cone artifacts. These artifacts obscure critical features during inspection, reduce reconstruction fidelity, and complicate defect interpretation, requiring…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Jundi Yuan, Peng Lian, Jinping Chen et al. · Journal of Micro/Nanopatterning Materials and Metrology

Fluorination enhanced lithographic performance of sulfonium-based molecular nonchemically-amplified resist

BackgroundNonchemically amplified resists (n-CARs) have emerged as a promising candidate for the next-generation of resists. Sulfonium-based n-CARs exhibit the capability of forming patterns with high resolution and low LER. However, their practical application is severely hindered by the low sensitivity.AimIt is expected to improve the sensitivity of sulfonium-based n-CARs by enhancing the absorption of extreme ultraviolet (EUV) or electron irradiation, thereby increasing…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Robert L. Bristol · Journal of Micro/Nanopatterning Materials and Metrology

Closing the stochastic resolution gap

BackgroundSince the birth of the integrated circuit, electronics industry growth and innovation have relied on semiconductor manufacturers putting ever smaller features (described by their critical dimensions or CDs) into production. Yet today, stochastics, the randomness inherent to chip making near the atomic scale, is threatening the continued ability to manufacture the smallest possible features in volume production.AimTo understand the impact of stochastics on…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Robert Bishop, Tim Pinkney · IMAPSource Proceedings

Substrate Yield Enhancement Enabled by Advanced Packaging Metrology System

Detecting dimensional errors in substrate fabrication induced by the manufacturing process is a challenge for high-density substrates. Such detection is especially important in advanced substrates that incorporate high-speed impedance-controlled circuits where a small change in linewidth and spacing can impact circuit performance. A 100% metrology inspection system has been developed that can detect these dimensional errors and provide the data needed to correct these…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Kyuhwan Kim, Ju-Young Kim, Song‐Se Yi et al. · Journal of Micro/Nanopatterning Materials and Metrology

Balancing DOF margin and stochastic failure in high-NA EUV process

BackgroundHigh-numerical aperture (NA) extreme ultraviolet (EUV) lithography delivers superior resolution, but it severely restricts the depth of focus (DOF) window. To expand this margin, the detrimental impact of stray photons leaking into unexposed areas must be mitigated. Crucially, we confirmed that increasing the photo contrast to decrease stochastic failure conversely increases sensitivity to this leakage light, thereby degrading the DOF margin.AimWe aim to maximize…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Taehyeok Seo, Jongik Chung, Ilsuk Kang · International Journal of Production Research

Robust process diagnosis using explainable CNNs for highly imbalanced wafer map defect classification in semiconductor manufacturing

Wafer defect pattern classification is essential for yield optimisation in semiconductor manufacturing. However, many existing studies evaluate models under modified class distributions or simplified experimental settings, providing limited evidence of deployment reliability under the severe imbalance observed in production data. This study presents a reproducible CNN-based evaluation framework using all 172,950 labelled samples in the WM-811K dataset, including the dominant…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Mohammad Taghi Mohammadi Anaei, Nicholas May, José Rodrigo Delgadillo Blando et al. · IMAPSource Proceedings

Metrology-Driven Sample Preparation for Advanced Microelectronics Using TESCAN FemtoChisel with Intelligent Multigas Processing, LPL, and AI-Enabled Correlative Workflows

Advanced microelectronics metrology increasingly depends on how the sample is prepared before inspection. In heterogeneous packages, the region of interest may be buried beneath combinations of mold compound, silicon, copper, redistribution layers, dielectrics, underfill, and organic substrate materials. The measurement challenge is therefore not only one of imaging resolution, but also one of physical access: the sample must be opened to the correct level, the exposed…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) 陈小飞, Yiqiao Wang, Yonggui HU et al. · Growth and Change

Path Dependence and Path Breakthrough: Evolutionary Dynamics of Innovation Networks in China's Semiconductor Industry

ABSTRACT This study uses co‐applied patent data from China's semiconductor industry, covering the period from 2001 to 2023, to construct networks of innovation collaboration between cities for each year. It applies social network analysis and a Temporal Exponential Random Graph Model (TERGM) to examine the evolution and formation mechanisms of these networks from the perspective of path dependence and path breakthrough. The results show that the network evolved from a…

Read at Journal articles (OpenAlex)

Older stories