Related papers: A Low-Dissipation and Scalable GEMM Accelerator wi…
Silicon nitride (SiN) photonics platform has attributes of ultra-low linear and nonlinear propagation losses and CMOS-compatible fabrication process, promising large-scale multifunctional photonic circuits. However, the centrosymmetric…
The use of the Silicon-on-Insulator (SOI) platform has been prominent for realizing CMOS-compatible, high-performance photonic integrated circuits (PICs). But in recent years, the silicon-nitride-on-silicon-dioxide (SiN-on-SiO$_2$) platform…
Silicon nitride (SiN) has emerged as a promising platform for integrated nonlinear photonics because of its low propagation loss, wide transparency window, and CMOS compatibility. Nonlinear processes arising from photon-electron…
The use of the Silicon-on-Insulator (SOI) platform has been prominent for realizing CMOS-compatible, high-performance photonic integrated circuits (PICs). But in recent years, the silicon-nitride-on-silicon-dioxide (SiN-on-SiO$_2$) platform…
Several microring resonator (MRR) based analog photonic architectures have been proposed to accelerate general matrix-matrix multiplications (GEMMs) in deep neural networks with exceptional throughput and energy efficiency. To implement…
Photonic integrated circuits are emerging as a promising platform for accelerating matrix multiplications in deep learning, leveraging the inherent parallel nature of light. Although various schemes have been proposed and demonstrated to…
Deep Neural Networks (DNNs) predominantly rely on General Matrix Multiply (GEMM) kernels, which are often accelerated using specialized hardware architectures. Recently, analog photonic GEMM accelerators have emerged as a promising…
A system-on-chip (SoC) photonic-electronic linear-algebra accelerator with the features of wavelength-division-multiplexing (WDM) based broadband photodetections and high-dimensional matrix-inversion operations fabricated in advanced…
Sparse neural networks can greatly facilitate the deployment of neural networks on resource-constrained platforms as they offer compact model sizes while retaining inference accuracy. Because of the sparsity in parameter matrices, sparse…
In-memory computing (IMC) on a monolithic chip for deep learning faces dramatic challenges on area, yield, and on-chip interconnection cost due to the ever-increasing model sizes. 2.5D integration or chiplet-based architectures interconnect…
The number of parameters in deep neural networks (DNNs) is scaling at about 5$\times$ the rate of Moore's Law. To sustain this growth, photonic computing is a promising avenue, as it enables higher throughput in dominant general…
The computing wall and data movement challenges of deep neural networks (DNNs) have exposed the limitations of conventional CMOS-based DNN accelerators. Furthermore, the deep structure and large model size will make DNNs prohibitive to…
Sparse Ternary General Matrix-Matrix Multiplication (GEMM) remains under-optimized in existing libraries for Apple Silicon CPUs. We present a Sparse Ternary GEMM kernel optimized specifically for Apple's M-series processors. We propose a…
Current Artificial Intelligence (AI) computation systems face challenges, primarily from the memory-wall issue, limiting overall system-level performance, especially for Edge devices with constrained battery budgets, such as smartphones,…
General matrix multiplication (GeMM) is a core operation in virtually all AI applications. Systolic array (SA) based architectures have shown great promise as GeMM hardware accelerators thanks to their speed and energy efficiency.…
There is a growing interest in custom spatial accelerators for machine learning applications. These accelerators employ a spatial array of processing elements (PEs) interacting via custom buffer hierarchies and networks-on-chip. The…
Silicon nitride (SiN) waveguides with ultra-low optical loss enable integrated photonic applications including low noise, narrow linewidth lasers, chip-scale nonlinear photonics, and microwave photonics. Lasers are key components to SiN…
Broadband active materials are pivotal for advancing emerging technologies spanning on-chip optical interconnects, artificial intelligence, quantum systems and precision metrology. Current semiconductor gain media face bandwidth…
The currently dominant AI/ML workloads, such as Large Language Models (LLMs), rely on the efficient execution of General Matrix-Matrix Multiplication (GEMM) operations. Thus, most systems are equipped with dedicated matrix hardware…
Monolithic integration of solid-state color centers with photonic elements of the same material is a promising approach to overcome the constraints of fabrication complexity and coupling losses in traditional hybrid integration approaches.…