TriGen: NPU Architecture for End-to-End Acceleration of Large Language Models based on SW-HW Co-Design

• URL: http://arxiv.org/abs/2602.12962v1
• Date: Fri, 13 Feb 2026 14:28:31 GMT
• Title: TriGen: NPU Architecture for End-to-End Acceleration of Large Language Models based on SW-HW Co-Design
• Authors: Jonghun Lee, Junghoon Lee, Hyeonjin Kim, Seoho Jeon, Jisup Yoon, Hyunbin Park, Meejeong Park, Heonjae Ha,
• Abstract summary: TriGen is a novel NPU architecture tailored for resource-constrained environments through software-hardware co-design.<n>We show that TriGen achieves an average 2.73x performance speedup and 52% less memory transfer over the baseline NPU design with negligible accuracy loss.
• Score: 4.251127523213289
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent studies have extensively explored NPU architectures for accelerating AI inference in on-device environments, which are inherently resource-constrained. Meanwhile, transformer-based large language models (LLMs) have become dominant, with rapidly increasing model sizes but low degree of parameter reuse compared to conventional CNNs, making end-to-end execution on resource-limited devices extremely challenging. To address these challenges, we propose TriGen, a novel NPU architecture tailored for resource-constrained environments through software-hardware co-design. Firstly, TriGen adopts low-precision computation using microscaling (MX) to enable additional optimization opportunities while preserving accuracy, and resolves the issues that arise by employing such precision. Secondly, to jointly optimize both nonlinear and linear operations, TriGen eliminates the need for specialized hardware for essential nonlinear operations by using fast and accurate LUT, thereby maximizing performance gains and reducing hardware-cost in on-device environments, and finally, by taking practical hardware constraints into account, further employs scheduling techniques to maximize computational utilization even under limited on-chip memory capacity. We evaluate the performance of TriGen on various LLMs and show that TriGen achieves an average 2.73x performance speedup and 52% less memory transfer over the baseline NPU design with negligible accuracy loss.

Related papers

• Accelerating 3D Gaussian Splatting with Neural Sorting and Axis-Oriented Rasterization [14.87046071090259]
  3D Gaussian Splatting (3DGS) has recently gained significant attention for high-quality and efficient view synthesis.<n>Despite its impressive algorithmic performance, real-time rendering on resource-constrained devices remains a major challenge due to tight power and area budgets.
  arXiv  Detail & Related papers  (2025-06-08T10:14:54Z)
• XAMBA: Enabling Efficient State Space Models on Resource-Constrained Neural Processing Units [0.6063137165121326]
  State-Space Models (SSMs) have emerged as efficient alternatives to transformers for sequential data tasks.<n>XAMBA is the first framework to enable and optimize SSMs on commercial off-the-shelf (COTS) state-of-the-art (SOTA) NPUs.<n>XAMBA mitigates key bottlenecks using CumBA and ReduBA, replacing sequential CumSum and ReduceSum operations with matrix-based computations.
  arXiv  Detail & Related papers  (2025-02-10T17:33:30Z)
• Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity [39.483346492111515]
  Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference.<n>Unstructured sparsity offers a compelling solution, enabling substantial reductions in compute and memory requirements when accelerated by compatible hardware platforms.<n>We find that highly sparse linear RNNs consistently achieve better efficiency-performance trade-offs than dense baselines.
  arXiv  Detail & Related papers  (2025-02-03T13:09:21Z)
• Dynamic Range Reduction via Branch-and-Bound [1.0141085397402314]
  Key strategy to enhance hardware accelerators is the reduction of precision in arithmetic operations.<n>This paper introduces a fully principled Branch-and-Bound algorithm for reducing precision needs in QUBO problems.<n> Experiments validate our algorithm's effectiveness on an actual quantum annealer.
  arXiv  Detail & Related papers  (2024-09-17T03:07:56Z)
• Taming 3DGS: High-Quality Radiance Fields with Limited Resources [50.92437599516609]
  3D Gaussian Splatting (3DGS) has transformed novel-view synthesis with its fast, interpretable, and high-fidelity rendering. We tackle the challenges of training and rendering 3DGS models on a budget. We derive faster, numerically equivalent solutions for gradient computation and attribute updates.
  arXiv  Detail & Related papers  (2024-06-21T20:44:23Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• FPGA-optimized Hardware acceleration for Spiking Neural Networks [69.49429223251178]
  This work presents the development of a hardware accelerator for an SNN, with off-line training, applied to an image recognition task. The design targets a Xilinx Artix-7 FPGA, using in total around the 40% of the available hardware resources. It reduces the classification time by three orders of magnitude, with a small 4.5% impact on the accuracy, if compared to its software, full precision counterpart.
  arXiv  Detail & Related papers  (2022-01-18T13:59:22Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Reconfigurable co-processor architecture with limited numerical precision to accelerate deep convolutional neural networks [0.38848561367220275]
  Convolutional Neural Networks (CNNs) are widely used in deep learning applications, e.g. visual systems, robotics etc. Here, we present a model-independent reconfigurable co-processing architecture to accelerate CNNs. In contrast to existing solutions, we introduce limited precision 32 bit Q-format fixed point quantization for arithmetic representations and operations.
  arXiv  Detail & Related papers  (2021-08-21T09:50:54Z)
• Multi-Exit Semantic Segmentation Networks [78.44441236864057]
  We propose a framework for converting state-of-the-art segmentation models to MESS networks. specially trained CNNs that employ parametrised early exits along their depth to save during inference on easier samples. We co-optimise the number, placement and architecture of the attached segmentation heads, along with the exit policy, to adapt to the device capabilities and application-specific requirements.
  arXiv  Detail & Related papers  (2021-06-07T11:37:03Z)
• A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework [56.57225686288006]
  Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices. Previous pruning methods mainly focus on reducing the model size and/or improving performance without considering the privacy of user data. We propose a privacy-preserving-oriented pruning and mobile acceleration framework that does not require the private training dataset.
  arXiv  Detail & Related papers  (2020-03-13T23:52:03Z)
• PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning [57.20262984116752]
  We introduce a new dimension, fine-grained pruning patterns inside the coarse-grained structures, revealing a previously unknown point in design space. With the higher accuracy enabled by fine-grained pruning patterns, the unique insight is to use the compiler to re-gain and guarantee high hardware efficiency.
  arXiv  Detail & Related papers  (2020-01-01T04:52:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.