Chips and semiconductors: research

394 research items

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

arXiv (research papers) Tanmay Sah SI

A CPU Inside an LLM: Zero-Gradient Compilation of Exact Circuits into Pretrained Weights

Pretrained language models (LMs) remain unreliable on exact multi-digit arithmetic without gradient fine-tuning or external tool interpreters. We introduce closed-form, zero-gradient circuit-grafting primitives that compile deterministic computation directly into pretrained LM weights using zero training examples and zero runtime hooks, while bounding per-layer normalization drift and preserving natural-language (NL) competence. Our construction combines three analytical…

Read at arXiv (research papers)

arXiv (research papers) Víctor Rodrigo González SI

Asuka-FM: A System-Architectural Co-Design Framework for Efficient Text-to-Image Pretraining on Consumer Hardware

Frontier text-to-image (T2I) foundation models predominantly rely on multi-billion parameter Diffusion Transformers (DiTs) pretrained across massive compute clusters, creating an accessibility barrier for academic laboratories. When training DiTs from scratch on single consumer GPUs (e.g., an NVIDIA RTX 4090 with 24\,GB VRAM), practitioners encounter three primary bottlenecks: quadratic attention sequence costs, Just-In-Time (JIT) compilation graph breaks induced by variable…

Read at arXiv (research papers)

arXiv (research papers) Firas Al-Hafez

LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Whole-Body Control

LocoMuJoCo is an open-source benchmark for imitation learning (IL) and reinforcement learning (RL) on whole-body control. The library couples MuJoCo (CPU) with MJX and the MjWarp backend (GPU) under a single API, exposes 9 humanoid, 3 (musculo-)skeletal, and 4 quadruped embodiments, and ships a curated native motion-capture dataset for every humanoid, to which it can also retarget AMASS and LAFAN1. A modular plug-in architecture makes observations, rewards, control modes…

Read at arXiv (research papers)

arXiv (research papers) Robin Geens

Kameleo: In-Situ Activation-Precision Selection for Bit-Serial LLM Accelerators

Weight-only quantization keeps the activations of large language models (LLMs) in a higher-precision format, pushing the on-chip inference cost to the activation arithmetic. Bit-serial, variable-length accelerators offer a promising path to reduce this cost by lowering activation precision while preserving model quality. They process only the mantissa bits that each layer needs. The length has to be chosen per layer and operator, and today it is chosen by offline…

Read at arXiv (research papers)

arXiv (research papers) Luca Colombo

Matching Architecture to Workload: Comparing RISC-V Parallel Accelerators for Energy-Efficient Embedded Computing

Embedded computing demands high performance and energy efficiency across workloads with widely different computational characteristics. Choosing the most suitable execution model therefore requires a quantitative understanding of how each model maps to different workload classes. In this paper, we compare three execution models for energy-efficient embedded computing: scalar multicore, stream ing multicore, and vector processing. We use three open-source RISC-V accelerators…

Read at arXiv (research papers)

arXiv (research papers) Hyunjun Park

CRAFT: Analog Circuit Design by Reasoning LLM Agents from Pre-Computed Lookup Tables

Automated analog circuit sizing methods, from black-box optimizers to recent large language model (LLM) agents, typically search the design space with a SPICE simulator in the loop, whereas an experienced designer works out a design by hand analysis. This paper presents CRAFT, a flow in which an LLM agent designs a given topology by calculation, as a designer does, and without an initial sizing. The agent works only through DeX, a service that uses pre-computed lookup tables…

Read at arXiv (research papers)

arXiv (research papers) Xinzhuang Xiong

Meta-RTL: Evolving Agent Harnesses for RTL Optimization

Large language models enable agents to optimize RTL using EDA feedback, yet their executable search procedures remain largely hand- engineered. We present Meta-RTL, an EDA-grounded framework that evolves RTL optimization harnesses from a minimal loop while keeping the optimization model, EDA flow, and per-design budgets fixed. Compared with Dr. RTL, Meta-RTL* reduces aggregate WNS/TNS violations by 7.8%/11.0% across 20 development designs, with area reductions on 70% of…

Read at arXiv (research papers)

arXiv (research papers) K Chitra

Mitigating Row Buffer Contention Through Multiple Row Buffer (MRB) DRAM

DRAM chips contain multiple banks to handle sev- eral memory requests in parallel. However, requests to different rows of the same bank (e.g., from different cores or workload access patterns) interfere with each other by contending for a single shared row buffer. This introduces row buffer conflicts, which incur performance and energy overheads. In this work, we reduce row buffer conflicts caused by interference by introducing multiple row buffers in each bank. We propose…

Read at arXiv (research papers)

arXiv (research papers) Sikha Pentyala Security

GPU-Accelerated Secure Inference for Drug--Target Interaction Prediction

Deep learning models that predict drug--target interactions (DTI) can speed up drug discovery, but the candidate drugs they score are valuable intellectual property that their owners cannot reveal. Secure multiparty computation (MPC) lets two servers compute a prediction on a secret-shared drug, without either server learning the drug. However, secure inference of deep models is slow. Non-linear operations require communication between the servers, and MPC arithmetic does…

Read at arXiv (research papers)

arXiv (research papers) Jingyi Zhou

GRODE-RTL: Source-Mapped Dependency Views for LLM-Based RTL Repair

Large Language Models show great potential for automated Register-Transfer Level repair, yet they struggle with non-local faults where root causes and failing outputs reside far apart in source code. Treating RTL as a flat token sequence obscures hardware dataflows, whereas exposing complete synthesized graphs overwhelms the model with fine-grained metadata. To resolve this representation dilemma, we propose GRODE-RTL, an anchor-centric representation that extracts the…

Read at arXiv (research papers)

arXiv (research papers) Prabhu Vellaisamy

Splice-Core: Low-Order-Bit-Splicing GEMM for Highly Energy-Efficient AI Inference Accelerators

Splice-Core is a temporal-unary/binary (tub) hybrid general matrix multiplication (GEMM) unit that minimizes low-order accumulation latency, while retaining value-dependent execution for high-order activation bits. We present two novel processing element (PE) variants: (i) Splice-BP utilizing bit planes, and (ii) Splice-LUT, which selects a shared weight multiple in a single cycle. Compared to a binary systolic array, Splice-BP/Splice-LUT achieve 77.4%/76.4% geometric-mean…

Read at arXiv (research papers)

arXiv (research papers) Yuseon Choi

FlashX: Scaling Robotic Experience Reuse for Embodied Agents with CBA-Based NAND Flash

Embodied agents are emerging as a promising paradigm for complex robotic tasks, leveraging Vision-Language-Action (VLA) and World Action Models (WAMs) to generate actions through Diffusion Transformer (DiT)-based iterative denoising. However, existing models often struggle to generalize to out-of-distribution (OOD) environments. We observe that retrieving successful experiences and using them to warm-start denoising enables agents to better adapt to unfamiliar situations…

Read at arXiv (research papers)

arXiv (research papers) Zihao Dan Security

ToolPulse: Side-Channel Eavesdropping on Tool-Using LLM Agents

Large language models (LLMs) are increasingly deployed as agents that translate user requests into sequences of local tool invocations. While prior cache-based side-channel attacks target the locally deployed models, they typically require the adversary to share model-related components or hardware resources with the victim's inference process. These assumptions do not apply to the predominant agentic settings, in which commercial LLMs execute on vendor-controlled…

Read at arXiv (research papers)

arXiv (research papers) Ferran Hermida-Rivera

BOOMerang: Autonomous Translation from RTL to Microarchitectural Simulators and Back

High-level simulators like gem5 are often used to test and demonstrate novel architectural techniques. While these simulators provide high research productivity, they generally lack the means to provide detailed feedback on the realizability of a hardware design. Furthermore, these simulators can frequently fall out-of-sync with the detailed performance characteristics of real hardware designs, which is usually the responsibility of dedicated engineers/teams in industry…

Read at arXiv (research papers)

arXiv (research papers) Siyang Chen SI

SGLayout: Schema-Guided Closed-Loop Refinement for LLM-Driven Parameterized Layout Generation

Large Language Models (LLMs) have shown strong potential in parameterized layout generation via tool-augmented code synthesis. However, LLMs lack spatial awareness, making one-shot generation unreliable. While layout quality can be evaluated with established techniques, a critical gap remains: geometric-domain evaluation outcomes cannot be directly translated into actionable code-level fixes, trapping iterative refinement in blind refactoring. We propose SGLayout, a…

Read at arXiv (research papers)

arXiv (research papers) Faiek Ahsan

Compiling Constraints into Neuromorphic Ising Machines

Most practical combinatorial optimization problems involve constraints, and an Ising machine that flips one spin at a time can respect them only through energy penalties that raise barriers between feasible solutions. Here we show that a higher-order neuromorphic Ising machine can enforce constraints through programmable transitions rather than penalties. In an autoencoder-like architecture, each inner-layer neuron represents a move, a family of multi-spin transitions that…

Read at arXiv (research papers)

arXiv (research papers) Luke Ztz Hu SI

FPGA-GEN: Target-Aware RTL Generation via HLS

Successful C/C++ compilation does not guarantee correct or efficient FPGA hardware after high-level synthesis (HLS). FPGA-GEN is an agentic HLS-C generation workflow that encodes specification, readiness, selection, repair, and admission rules in explicit task contracts and bounded tool-feedback loops for candidate-level decisions. On HLS-Eval, five shared-context outputs per task yield 407/425 (95.8%) public-testbench passes. In a cumulative conversion campaign, FPGA-GEN…

Read at arXiv (research papers)

arXiv (research papers) Jungmin Park Security

From FIPS to FPGA with LLM Agents: Measuring What Tests and Reviews Miss in Post-Quantum Cryptographic Hardware

As LLM agents increasingly generate RTL alongside the tests and reviews that validate it, self-generated evidence is a weak foundation for trustworthy hardware. We present our seven-stage verification-gated workflow, evolved during a post-quantum design port, in which a gate counts only if shown able to fail on negative controls and fault mutants, and reviewer agents audit work before commit. We then audit this evidence with tool-selected netlist mutants, flaw replays, and…

Read at arXiv (research papers)

arXiv (research papers) Minxing Chu

ReLay: Bidirectional Layout-Code Translation and Library Evolution for Reusable and Process-Portable Analog Design

Analog layout generators provide a programmable interface for design reuse and process migration, but their coverage is limited by handcrafted libraries. The designer knowledge embedded in complete layouts remains implicit in their geometry, making it difficult to capture in reusable generator libraries. We present ReLay, a bidirectional layout-code framework that recovers generator programs from existing layouts, enabling cross-PDK portability and parametric resizing of…

Read at arXiv (research papers)

arXiv (research papers) Yi-Chun Liao

RE-CAM: Readout-Enhanced Content-Addressable Memory for Quantitative Similarity Search

Similarity search is essential to many applications but incurs massive data movement when executed on conventional architectures. Content-addressable memory (CAM) is a promising hardware substrate, as it allows similarity search directly in the CAM array, minimizing data movement and offering both low latency and high energy efficiency. However, conventional CAM array readout produces only binary match results, discarding quantitative similarity information that could be…

Read at arXiv (research papers)

arXiv (research papers) Ahmet Efe Security

Verified Netlist-to-RTL Recovery with LLM Agents

Gate-level netlists circulate among IP integrators and foundries and can be extracted from chips. Reverse engineering them into readable register-transfer-level (RTL) code would help an adversary understand and modify a design, but remains difficult because word-level operations are scattered across many gates. Large language models (LLMs) can write and optimize RTL, but often fail to recover it from a whole netlist. We propose LOCA (LOgic Cone Attack), an LLM-based attack…

Read at arXiv (research papers)

arXiv (research papers) Mohamed Bouaziz

Bottom-Up FPGA Reconfigurable Accelerator Overlay Generation

Programmable FPGA overlays run new workloads without re-synthesis, yet they pay twice. An overlay adds a second layer of programmability on top of the FPGA's own overhead. Moreover, overlay generators usually start from a regular template, so they spend logic on switches and links that the workloads never use, and they close timing at low clocks. We present a flow that instead grows an overlay bottom-up from the dataflow graphs of the workloads it must run. The flow clusters…

Read at arXiv (research papers)

arXiv (research papers) Mohamed Bouaziz

Native FPGA Hard-Block Implementation from High-Level Synthesis

High-level synthesis (HLS) maps computations to FPGA hard blocks, yet often leaves their arithmetic modes, internal registers, and cascade links idle and recreates them in the fabric, costing area and timing. We present a C++ template library that reaches native hard-block implementations without modifying the HLS compiler. Templates fix source patterns, and an automatic flow picks scheduling settings and verified RTL patches. On AMD Versal, our matrix multiplication uses…

Read at arXiv (research papers)

arXiv (research papers) Yi-Chun Liao

CAIMS: Scalable Cross-Array In-Memory Search

Search, especially top-k similarity search, plays a vital role in many applications, but its performance can be severely limited by memory access overhead. In-memory search (IMS), an alternative to CPU/GPU-based approaches, exploits massive parallelism within a content-addressable memory (CAM) array to perform search in situ and provides both low latency and high energy efficiency. However, the capacity of a single CAM array is often insufficient for modern workloads…

Read at arXiv (research papers)

arXiv (research papers) Shashwat Jaiswal

TripleKV: Predict, Prefetch, Protect -- KV Cache Management for AI Agents

LLM agents alternate between inference and tool execution, repeatedly reusing their growing context across calls. Under high concurrency, their combined key-value (KV) cache working set can reach hundreds of GiB, far exceeding GPU memory capacity. As idle KV cache blocks are evicted to slower storage tiers, returning agents incur expensive retrievals that stall inference. To address this problem, we present \emph{TripleKV}, a three-tier KV cache management system that hides…

Read at arXiv (research papers)

arXiv (research papers) Jiaru Qian

DVBench: End-to-End Benchmark for Real-World UVM Design Verification Agents

Design verification (DV) remains a major bottleneck in hardware development, with large-scale verification using the Universal Verification Methodology (UVM) being highly labor-intensive. Recent advances in large language models (LLMs) and agentic systems offer new opportunities for DV automation. However, existing benchmarks primarily construct mutually decoupled subtasks, which deviates from the real-world workflow. In this paper, we present DVBench, the first end-to-end…

Read at arXiv (research papers)

arXiv (research papers) Ivan A. Boldin

Dressed-State Quantum Information Processing Using a Multilayer Ion Trap Chip with an Integrated Radio Frequency Resonator

We present the experimental preparation of a radio frequency (RF)-dressed-state qubit, the coherent operation of a single RF-dressed qubit, and the selective readout of RF-dressed hyperfine states of $^{171}$Yb${^+}$ ions trapped using a novel microstructured ion trap chip. We demonstrate the individual addressing of RF-dressed-state qubits in a two-ion Coulomb crystal. To this end, we developed, manufactured, and characterized a trap chip specifcally designed for quantum…

Read at arXiv (research papers)

arXiv (research papers) Hongqin Lyu

MicroAssert: Microarchitecture-Aware Structured Assertion Generation for CPU Verification

Automatic assertion generation reduces manual verification effort, yet existing approaches struggle to capture microarchitectural behaviors and cross-region interactions in CPUs. We present MicroAssert, a microarchitecture-aware framework that identifies functional regions directly from RTL and generates local and composite assertions through structured contracts and deterministic verification primitives. Coverage-guided feedback further improves verification completeness by…

Read at arXiv (research papers)

CEPA (Center for European Policy Analysis) Jack Galloway Geopolitics

New US Chip Controls Squeeze Europe

ASML, Europe’s leading tech company, could face renewed US pressure to cut sales to China.

Read at CEPA (Center for European Policy Analysis)

arXiv (research papers) Yicheng He

Mechanistic Critics for Sample-Efficient NPU Design-Space Exploration

NPU design-space exploration for LLM inference mainly relies on an expensive simulator that often returns only scalar feedback such as latency and power. Such feedback can rank evaluated configurations, but gives little information for deciding why a configuration is slow or which architecture parameter should be changed next. This limitation is especially severe because prefill and decode workloads can be limited by different resources, including compute throughput and HBM…

Read at arXiv (research papers)

Older stories