Related papers: A Heterogeneous Chiplet Architecture for Accelerat…

Recently, large-scale transformer-based models have been proven to be effective over various tasks across many domains. Nevertheless, applying them in industrial production requires tedious and heavy works to reduce inference costs. To fill…

As distributed model training scales to span hundreds of thousands of GPUs, scale-out networks face unprecedented performance and efficiency demands. NVIDIA Spectrum-X Ethernet has been designed from the ground up to achieve predictable and…

Large Language Models (LLMs) such as LLaMA and DeepSeek, are built on transformer architectures, which have become a standard model for achieving state-of-the-art performance in natural language processing tasks. Recently, there has been…

The future of artificial intelligence (AI) acceleration demands a paradigm shift beyond the limitations of purely electronic or photonic architectures. Photonic analog computing delivers unmatched speed and parallelism but struggles with…

With the rapid advancement of artificial intelligence technologies such as ChatGPT, AI agents, and video generation, contemporary mobile systems have begun integrating these AI capabilities on local devices to enhance privacy and reduce…

Deployment of modern TinyML tasks on small battery-constrained IoT devices requires high computational energy efficiency. Analog In-Memory Computing (IMC) using non-volatile memory (NVM) promises major efficiency improvements in deep neural…

Fully Homomorphic Encryption (FHE) relies heavily on the Number Theoretic Transform (NTT), making NTT a major performance bottleneck due to its intensive polynomial computations. Hybrid Homomorphic Encryption (HHE), which integrates…

Generative AI, in particular large transformer models, are increasingly driving HPC system design in science and industry. We analyze performance characteristics of such transformer models and discuss their sensitivity to the transformer…

Topology optimization is a computational method used to determine the optimal material distribution within a prescribed design domain, aiming to minimize structural weight while satisfying load and boundary conditions. For critical…

Processing-In-Memory (PIM) architectures offer a promising approach to accelerate Graph Neural Network (GNN) training and inference. However, various PIM devices such as ReRAM, FeFET, PCM, MRAM, and SRAM exist, with each device offering…

Processing-in-Memory (PIM) architectures offer promising solutions for efficiently handling AI applications in energy-constrained edge environments. While traditional PIM designs enhance performance and energy efficiency by reducing data…

Modern AI acceleration faces a fundamental challenge: conventional assumptions about memory requirements, batching effectiveness, and latency-throughput tradeoffs are systemwide generalizations that ignore the heterogeneous computational…

The rapid scaling of large language models (LLMs) has unveiled critical limitations in current hardware architectures, including constraints in memory capacity, computational efficiency, and interconnection bandwidth. DeepSeek-V3, trained…

Heterogeneous hardware like Gaudi processor has been developed to enhance computations, especially matrix operations for Transformer-based large language models (LLMs) for generative AI tasks. However, our analysis indicates that…

One of the challenges for Tiny Machine Learning (tinyML) is keeping up with the evolution of Machine Learning models from Convolutional Neural Networks to Transformers. We address this by leveraging a heterogeneous architectural template…

The deployment of large language models (LLMs) presents significant challenges due to their enormous memory footprints, low arithmetic intensity, and stringent latency requirements, particularly during the autoregressive decoding stage.…

Transformers are central to advances in artificial intelligence (AI), excelling in fields ranging from computer vision to natural language processing. Despite their success, their large parameter count and computational demands challenge…

Fully Homomorphic Encryption (FHE) imposes substantial memory bandwidth demands, presenting significant challenges for efficient hardware acceleration. Near-memory Processing (NMP) has emerged as a promising architectural solution to…

Emerging AI applications such as ChatGPT, graph convolutional networks, and other deep neural networks require massive computational resources for training and inference. Contemporary computing platforms such as CPUs, GPUs, and TPUs are…

Supercomputer architectures are trending toward higher computational throughput due to the inclusion of heterogeneous compute nodes. These multi-GPU nodes increase on-node computational efficiency, while also increasing the amount of data…