Related papers: A Highly Configurable Hardware/Software Stack for …

Deep Neural Networks (DNNs) continue to grow in complexity with Large Language Models (LLMs) incorporating vast numbers of parameters. Handling these parameters efficiently in traditional accelerators is limited by data-transmission…

Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value…

As DNNs are widely adopted in various application domains while demanding increasingly higher compute and memory requirements, designing efficient and performant NPUs (Neural Processing Units) is becoming more important. However, existing…

This paper proposes a framework for integrating data plane (DP) acceleration within the Network Functions Virtualization (NFV) architecture. Data plane programming (DPP) proves to be beneficial for NFV environments, as it provides full…

With the emergence of wearable devices and other embedded systems, deploying large language models (LLMs) on edge platforms has become an urgent need. However, this is challenging because of their high computational and memory demands.…

We present a compilation flow for the generation of CNN inference accelerators on FPGAs. The flow translates a frozen model into OpenCL kernels with the TVM compiler and uses the Intel OpenCL SDK to compile to an FPGA bitstream. We improve…

Deep learning (DL) models are piquing high interest and scaling at an unprecedented rate. To this end, a handful of tiled accelerators have been proposed to support such large-scale training tasks. However, these accelerators often…

Recurrent neural networks such as Long Short-Term Memories (LSTMs) learn temporal dependencies by keeping an internal state, making them ideal for time-series problems such as speech recognition. However, the output-to-input feedback…

Transformers have revolutionized deep learning and generative modeling, enabling advancements in natural language processing tasks. However, the size of transformer models is increasing continuously, driven by enhanced capabilities across…

The emerging trend of deploying complex algorithms, such as Deep Neural Networks (DNNs), increasingly poses strict memory and energy efficiency requirements on Internet-of-Things (IoT) end-nodes. Mixed-precision quantization has been…

Visual Geometry Transformer (VGGT) is a strong feed-forward model for multiple 3D tasks, but its Alternating-Attention (AA) stack scales quadratically in the total token count, making long clips expensive. Existing token-reduction…

Convolutional Neural Networks (CNNs) have proven to be extremely accurate for image recognition, even outperforming human recognition capability. When deployed on battery-powered mobile devices, efficient computer architectures are required…

Artificial Intelligence (AI) algorithms, such as Deep Neural Networks (DNNs), have become an important tool for a wide range of applications, from computer vision to natural language processing. However, the computational complexity of DNN…

We implemented and optimized matrix multiplications between dense and block-sparse matrices on CUDA. We leveraged TVM, a deep learning compiler, to explore the schedule space of the operation and generate efficient CUDA code. With the…

Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where unseen input patterns received under unpredictable external…

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…

Mobile and embedded platforms are increasingly required to efficiently execute computationally demanding DNNs across heterogeneous processing elements. At runtime, the available hardware resources to DNNs can vary considerably due to other…

Rapid design space exploration in early design stage is critical to algorithm-architecture co-design for accelerators. In this work, a pre-RTL cycle-accurate accelerator simulator based on SystemC transaction-level modeling (TLM),…

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA.…

The next significant step in the evolution and proliferation of artificial intelligence technology will be the integration of neural network (NN) models within embedded and mobile systems. This calls for the design of compact, energy…