Related papers: A Low-Dissipation and Scalable GEMM Accelerator wi…
Purpose: To systematically investigate the influence of various data consistency layers, (semi-)supervised learning and ensembling strategies, defined in a $\Sigma$-net, for accelerated parallel MR image reconstruction using deep learning.…
Integrated photonics based on silicon photonics platform is driving several application domains, from enabling ultra-fast chip-scale communication in high-performance computing systems to energy-efficient optical computation in artificial…
Analog in-memory computing (AIMC) cores offers significant performance and energy benefits for neural network inference with respect to digital logic (e.g., CPUs). AIMCs accelerate matrix-vector multiplications, which dominate these…
Applications such as augmented and virtual reality (AR/VR), optical atomic clocks, and quantum computing require photonic integration of (near-)visible laser sources to enable commercialization at scale. The heterogeneous integration of…
Silicon Photomultipliers (SiPMs) are photon-counting detectors with great potential to improve the sensitivity of optical receivers. Recent studies of SiPMs in communication focus on the speed rather than the power consumption of the…
Human beings construct perception of space by integrating sparse observations into massively interconnected synapses and neurons, offering a superior parallelism and efficiency. Replicating this capability in AI finds wide applications in…
CMOS-compatible short- and mid-wave infrared emitters are highly coveted for the monolithic integration of silicon-based photonic and electronic integrated circuits to serve a myriad of applications in sensing and communications. In this…
High-performance programmable silicon photonic circuits are considered to be a critical part of next generation architectures for optical processing, photonic quantum circuits and neural networks. Low-loss optical phase change materials…
Photonic systems for high-performance information processing have attracted renewed interest. Neuromorphic silicon photonics has the potential to integrate processing functions that vastly exceed the capabilities of electronics. We report…
Metallic nanoparticle-on-a-mirror (NPoM) cavities enable extreme field confinement in sub-nm gaps, leading to unrivaled performance for nonlinear processes such as surface-enhanced Raman scattering (SERS). So far, prevailing experimental…
Developing kernels for Processing-In-Memory (PIM) platforms poses unique challenges in data management and parallel programming on limited processing units. Although software development kits (SDKs) for PIM, such as the UPMEM SDK, provide…
This publication focuses on the study of silicon photomultipliers (SiPMs) in view of a reconstruction of the incident photon flux in the regime of highly non-linear response. SiPMs are semiconductor based light detectors compiled of…
Various processing-in-memory (PIM) accelerators based on various devices, micro-architectures, and interfaces have been proposed to accelerate deep neural networks (DNNs). How to deploy DNNs onto PIM-based accelerators is the key to explore…
In-memory database query processing frequently involves substantial data transfers between the CPU and memory, leading to inefficiencies due to Von Neumann bottleneck. Processing-in-Memory (PIM) architectures offer a viable solution to…
Hashing retrieval is a pivotal technology for large-scale similarity search, widely applied in retrieval-augmented generation (RAG) for large language models (LLMs), massive image repositories, and bioinformatics sequence matching. However,…
Ternary Deep Neural Networks (DNN) have shown a large potential for highly energy-constrained systems by virtue of their low power operation (due to ultra-low precision) with only a mild degradation in accuracy. To enable an…
We present a novel approach for accelerating convolutions during inference for CPU-based architectures. The most common method of computation involves packing the image into the columns of a matrix (im2col) and performing general matrix…
Several manufacturers have already started to commercialize near-bank Processing-In-Memory (PIM) architectures. Near-bank PIM architectures place simple cores close to DRAM banks and can yield significant performance and energy improvements…
Structured illumination microscopy (SIM) enables live cell, super-resolution imaging at high speeds. SIM uses sophisticated optical systems to generate pre-determined excitation light patterns, and reconstruction algorithms to enhance the…
The need to efficiently execute different Deep Neural Networks (DNNs) on the same computing platform, coupled with the requirement for easy scalability, makes Multi-Chip Module (MCM)-based accelerators a preferred design choice. Such an…