Related papers: VCSEL-based CPO for Scale-Up in A.I. Datacenter. S…
TCP/IP network stack is irreplaceable for Web services in datacenter front-end servers, and the demand for which is growing rapidly for emerging high concurrency network service applications (including Internet, Internet of Things, mobile…
Inspired by the renaissance of optical computing recently, this poster presents a disruptive outlook on the possibility of seamless integration between optical communications and optical computing infrastructures, paving the way for…
We have designed three ASICs for possible applications in the optical links of a new layer of pixel detector in the ATLAS experiment for the first phase of the LHC luminosity upgrade. The ASICs include a high-speed driver for the VCSEL, a…
In our exploration of Composable Memory systems utilizing CXL, we focus on overcoming adoption barriers at Hyperscale, underscored by economic models demonstrating Total Cost of Ownership (TCO). While CXL addresses the pressing memory…
Extreme edge-AI systems, such as those in readout ASICs for radiation detection, must operate under stringent hardware constraints such as micron-level dimensions, sub-milliwatt power, and nanosecond-scale speed while providing clear…
Transformers have revolutionized AI in natural language processing and computer vision, but their large computation and memory demands pose major challenges for hardware acceleration. In practice, end-to-end throughput is often limited by…
Recent years have witnessed a remarkable development in communication and computing systems, mainly driven by the increasing demands of data and processing intensive applications such as virtual reality, M2M, connected vehicles, IoT…
The insatiable appetite of Artificial Intelligence (AI) workloads for computing power is pushing the industry to develop faster and more efficient accelerators. The rigidity of custom hardware, however, conflicts with the need for scalable…
In large-scale distributed LLM training, communication between devices becomes the key performance bottleneck. Chiplet technology can integrate multiple dies into a package to scale-up node performance with higher bandwidth. Meanwhile,…
The rise of power-efficient embedded computers based on highly-parallel accelerators opens a number of opportunities and challenges for researchers and engineers, and paved the way to the era of edge computing. At the same time, advances in…
All-optical image processing offers a high-speed, energy-efficient alternative to conventional electronic systems by leveraging the wave nature of light for parallel computation. However, traditional optical processors rely on bulky…
The torrential influx of floating-point data from domains like IoT and HPC necessitates high-performance lossless compression to mitigate storage costs while preserving absolute data fidelity. Leveraging GPU parallelism for this task…
Transfer learning has become an essential tool in modern computer vision, allowing practitioners to leverage backbones, pretrained on large datasets, to train successful models from limited annotated data. Choosing the right backbone is…
Photonic computing promises ultrafast and energy-efficient artificial intelligence. However, existing photonic neural networks (PNNs) remain functionally shallow and difficult to scale. Here we establish a theory-guided framework showing…
In this paper, we propose an energy efficient passive optical network (PON) architecture for backhaul connectivity in indoor visible light communication (VLC) systems. The proposed network is used to support a fog computing architecture…
Retrieving data from large-scale source code archives is vital for AI training, neural-based software analysis, and information retrieval, to cite a few. This paper studies and experiments with the design of a compressed key-value store for…
Composable data centers (DCs) have been proposed to enable greater efficiencies as the uptake of on-demand computing services grows. In this article we give an overview of composable DCs by discussing their enabling technologies, benefits,…
Computation intensive kernels, such as convolutions, matrix multiplication and Fourier transform, are fundamental to edge-computing AI, signal processing and cryptographic applications. Interleaved-Multi-Threading (IMT) processor cores are…
This paper proposes a cloud architecture for the correlation of wide bandwidth VLBI data. Cloud correlation facilitates processing of entire experiments in parallel using flexibly allocated and practically unlimited compute resources. This…
Powerline communication (PLC) provides inexpensive, secure and high speed network connectivity, by leveraging the existing power distribution networks inside the buildings. While PLC technology has the potential to improve connectivity and…