Despite advances in the programmable logic capabilities of modern trigger systems, a significant bottleneck remains in the amount of data to be transported from the detector to off-detector logic where trigger decisions are made. We demonstrate that a neural network (NN) autoencoder model can be implemented in a radiation-tolerant application-specific integrated circuit (ASIC) to perform lossy data compression alleviating the data transmission problem while preserving critical information of the detector energy profile. For our application, we consider the high-granularity calorimeter from the Compact Muon Solenoid (CMS) experiment at the CERN Large Hadron Collider. The advantage of the machine learning approach is in the flexibility and configurability of the algorithm. By changing the NN weights, a unique data compression algorithm can be deployed for each sensor in different detector regions and changing detector or collider conditions. To meet area, performance, and power constraints, we perform quantization-aware training to create an optimized NN hardware implementation. The design is achieved through the use of high-level synthesis tools and the hls4ml framework and was processed through synthesis and physical layout flows based on a low-power (LP)-CMOS 65-nm technology node. The flow anticipates 200 Mrad of ionizing radiation to select gates and reports a total area of 3.6 mm 2 and consumes 95 mW of power. The simulated energy consumption per inference is 2.4 nJ. This is the first radiation-tolerant on-detector ASIC implementation of an NN that has been designed for particle physics applications.
29 June 2021 in IEEE Solid-State Circuits Magazine
In the quest to study the fundamental nature of matter and the universe, high-energy physics (HEP) experiments often operate in extreme conditions that lie well outside the standard operating range of integrated circuits (ICs). Two prominent examples of such extreme environments are 1) the irradiation levels experienced at high luminosity colliders and 2) operation at cryogenic temperatures [1]. Cryogenic electronics is a broad term that encompasses circuits operating at temperatures below the standard operating limit (−55 °C in the case of military grade electronics), all of the way down to millikelvin, as in the case of superconducting circuits. Cryogenic circuits have a long history [2] and have found applications in a broad spectrum of applications, such as infrared focal plane arrays, positron emission tomography, and quantum science. While CMOS circuits have been reliably operated at deep-cryogenic temperatures (< 4.2 K), this article focuses on applications down to liquid nitrogen (77 K) and provides an overview of the design considerations, benefits, and unique challenges pertaining to cryogenic CMOS ICs for large HEP experiments.
11 September 2025 in IEEE Transactions on Quantum Engineering
We present an end-to-end workflow for superconducting qubit readout that embeds co-designed Neural Networks (NNs) into the Quantum Instrumentation Control Kit (QICK). Capitalizing on the custom firmware and software of the QICK platform, which is built on Xilinx RFSoC FPGAs, we aim to leverage machine learning (ML) to address critical challenges in qubit readout accuracy and scalability. The workflow utilizes the hls4ml package and employs quantization-aware training to translate ML models into hardware-efficient FPGA implementations via user-friendly Python APIs. We experimentally demonstrate the design, optimization, and integration of an ML algorithm for single transmon qubit readout, achieving 96% single-shot fidelity with a latency of 32.25 ns and less than 16% FPGA look-up table resource utilization. Our results offer the community an accessible workflow to advance ML-driven readout and adaptive control in quantum information processing applications.
The upgrade of the CMS experiment for the high luminosity operation of the LHC comprises the replacement of the current endcap calorimeter by a high granularity sampling calorimeter (HGCAL). The electromagnetic section of the HGCAL is based on silicon sensors interspersed between lead and copper (or copper tungsten) absorbers. The hadronic section uses layers of stainless steel as an absorbing medium and silicon sensors as an active medium in the regions of high radiation exposure, and scintillator tiles directly read out by silicon photomultipliers in the remaining regions. As part of the development of the detector and its readout electronic components, a section of a silicon-based HGCAL prototype detector along with a section of the CALICE AHCAL prototype was exposed to muons, electrons and charged pions in beam test experiments at the H2 beamline at the CERN SPS in October 2018. The AHCAL uses the same technology as foreseen for the HGCAL but with much finer longitudinal segmentation. The performance of the calorimeters in terms of energy response and resolution, longitudinal and transverse shower profiles is studied using negatively charged pions, and is compared to GEANT4 predictions. This is the first report summarizing results of hadronic showers measured by the HGCAL prototype using beam test data.
27 May 2026 in ACM Transactions on Reconfigurable Technology and Systems
We present hls4ml , a free and open source platform that translates machine learning (ML) models from modern deep learning frameworks into high-level synthesis (HLS) code that can be integrated into full designs for field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs). With its flexible and modular design, hls4ml supports a large number of deep learning frameworks and can target HLS compilers from several vendors, including Vitis HLS, Intel oneAPI and Catapult HLS. Together with a wider eco-system for software-hardware co-design, hls4ml has enabled the acceleration of ML inference in a wide range of commercial and scientific applications where low latency, resource usage, and power consumption are critical. In this article, we describe the structure and functionality of the hls4ml platform. The overarching design considerations for the generated HLS code are discussed, together with selected performance results.