相关论文: Optically Connected Memory for Disaggregated Data …
The rapid advancements in machine learning across numerous industries have amplified the demand for extensive matrix-vector multiplication operations, thereby challenging the capacities of traditional von Neumann computing architectures. To…
The development of deep neural networks is witnessing fast growth in network size, which requires novel hardware computing platforms with large bandwidth and low energy consumption. Optical computing has been a potential candidate for…
We propose and model an optical communication scheme for short distance datacom links based on the distribution of information across a wide comb spectrum. This modulation format, orthogonal delay division multiplexing, allows the…
Disaggregated memory is a promising approach that addresses the limitations of traditional memory architectures by enabling memory to be decoupled from compute nodes and shared across a data center. Cloud platforms have deployed such…
Distributed learning is widely used for training large models on large datasets by distributing parts of the model or dataset across multiple devices and aggregating the computed results for subsequent computations or parameter updates.…
Optical computing is considered a promising solution for the growing demand for parallel computing in various cutting-edge fields, requiring high integration and high speed computational capacity. In this paper, we propose a novel optical…
Designing lightweight convolutional neural network (CNN) models is an active research area in edge AI. Compute-in-memory (CIM) provides a new computing paradigm to alleviate time and energy consumption caused by data transfer in von Neumann…
The significant advancements in integrated photonics have enabled high-speed and energy efficient systems for various applications from data communications and high-performance computing, to medical diagnosis, sensing and ranging. However,…
The coherent storage, buffering and retrieval of photons in a quantum memory enables the scalable creation of photonic entangled states via linear optics and repeat-until-success, unlocking applications in quantum communications and…
The disaggregated memory (DM) architecture offers high resource elasticity at the cost of data access performance. While caching frequently accessed data in compute nodes (CNs) reduces access overhead, it requires costly centralized…
Optical neural networks (ONNs) based on programmable photonic integrated circuits (PICs) offer a promising route toward low-latency and energy-efficient deep learning. However, conventional photonic implementations of matrix-vector…
It has become very essential to address the limited spectrum capacity and their efficient utilization to support the increasing number of Internet of Things devices. When it comes to medical infrastructure, it becomes very imperative for…
In neuromorphic photonic systems, device operations are typically governed by analog signals, necessitating digital-to-analog converters (DAC) and analog-to-digital converters (ADC). However, data movement between memory and these…
Despite the promise of alleviating the main memory bottleneck, and the existence of commercial hardware implementations, techniques for Near-Data Processing have seen relatively little real-world deployment. The idea has received renewed…
Modern Hopfield Neural Networks (HNNs), also known as Dense Associative Memories (DAMs), enhance the performance of simple recurrent neural networks by leveraging the nonlinearities in their energy functions. They have broad applications in…
In recent years, the energy consumption of computing systems has increased and a large fraction of this energy is consumed in main memory. Towards this, researchers have proposed use of non-volatile memory, such as phase change memory…
The configurable building blocks of current FPGAs -- Logic blocks (LBs), Digital Signal Processing (DSP) slices, and Block RAMs (BRAMs) -- make them efficient hardware accelerators for the rapid-changing world of Deep Learning (DL).…
The surge in AI usage demands innovative power reduction strategies. Novel Compute-in-Memory (CIM) architectures, leveraging advanced memory technologies, hold the potential for significantly lowering energy consumption by integrating…
In-SRAM computing promises energy efficiency, but circuit nonlinearities and PVT variations pose major challenges in designing robust accelerators. To address this, we introduce OPTIMA, a modeling framework that aids in analyzing bit-line…
High-performance computing systems are moving towards 2.5D and 3D memory hierarchies, based on High Bandwidth Memory (HBM) and Hybrid Memory Cube (HMC) to mitigate the main memory bottlenecks. This trend is also creating new opportunities…