Related papers: Photonic Fabric Platform for AI Accelerators
Neural networks have demonstrated their outstanding performance in a wide range of tasks. Specifically recurrent architectures based on long-short term memory (LSTM) cells have manifested excellent capability to model time dependencies in…
Neuromorphic photonic computing represents a paradigm shift for next-generation machine intelligence, yet critical gaps persist in emulating the brain's event-driven, asynchronous dynamics,a fundamental barrier to unlocking its full…
When accelerators fail in modern ML datacenters, operators migrate the affected ML training or inference jobs to entirely new racks. This approach, while preserving network performance, is highly inefficient, requiring datacenters to…
The exponential growth of data has driven technology providers to develop new protocols, such as cache coherent interconnects and memory semantic fabrics, to help users and facilities leverage advances in memory technologies to satisfy…
Despite recent advancements in federated learning (FL), the integration of generative models into FL has been limited due to challenges such as high communication costs and unstable training in heterogeneous data environments. To address…
In this paper, we propose a low-power hardware for efficient deployment of binarized neural networks (BNNs) that have been trained for physiological datasets. BNNs constrain weights and feature-map to 1 bit, can pack in as many 1-bit…
Photonic computing shows promise for transformative advancements in machine learning (ML) acceleration, offering ultra-fast speed, massive parallelism, and high energy efficiency. However, current photonic tensor core (PTC) designs based on…
Robotic continuous control tasks impose stringent demands on the energy efficiency and latency of computing architectures due to their high-dimensional state spaces and real-time interaction requirements. Conventional electronic computing…
Silicon photonics has evolved from lab research to commercial products in the past decade as it plays an increasingly crucial role in data communication for next-generation data centers and high performance computing1. Recently,…
In this paper, we propose FusionCIM, an operator-fusion-driven compute-in-memory (CIM) accelerator architecture for efficient and scalable LLM inference, with three key innovations: (1) a hybrid CIM pipeline architecture that maps QKT…
To address the increasing computational demands of artificial intelligence (AI) and big data, compute-in-memory (CIM) integrates memory and processing units into the same physical location, reducing the time and energy overhead of the…
The advancement of artificial intelligence demands flexible multimodal data processing with high throughput and energy efficiency. Photonic integrated circuits (PIC) has demonstrated promising potentials in terms of low latency and low…
Long-context LLM inference is bottlenecked not by compute but by the O(n) memory bandwidth cost of scanning the KV cache at every decode step -- a wall that no amount of arithmetic scaling can break. Recent photonic accelerators have…
FPGA overlays are commonly implemented as coarse-grained reconfigurable architectures with a goal to improve designers' productivity through balancing flexibility and ease of configuration of the underlying fabric. To truly facilitate full…
The proliferation of probabilistic AI has prompted proposals for specialized stochastic computers. Despite promising efficiency gains, these proposals have failed to gain traction because they rely on fundamentally limited modeling…
Foundation models are deep neural networks (such as GPT-5, Gemini~3, and Opus~4) trained on large datasets that can perform diverse downstream tasks -- text and code generation, question answering, summarization, image classification, and…
Computational hardware designed to mimic biological neural networks holds the promise to resolve the drastically growing global energy demand of artificial intelligence. A wide variety of hardware concepts have been proposed, and among…
Processing large-scale graph datasets is computationally intensive and time-consuming. Processor-centric CPU and GPU architectures, commonly used for graph applications, often face bottlenecks caused by extensive data movement between the…
High Performance Computing (HPC) platforms allow scientists to model computationally intensive algorithms. HPC clusters increasingly use General-Purpose Graphics Processing Units (GPGPUs) as accelerators; FPGAs provide an attractive…
Wearable devices are revolutionizing personal technology, but their usability is often hindered by frequent charging due to high power consumption. This paper introduces Distributed Neural Networks (DistNN), a framework that distributes…