Design and Implementation of an FPGA-Based Tiled Matrix Multiplication Accelerator for Transformer Self-Attention on the Xilinx KV260 SoM

• URL: http://arxiv.org/abs/2503.16731v2
• Date: Mon, 24 Mar 2025 02:20:54 GMT
• Title: Design and Implementation of an FPGA-Based Tiled Matrix Multiplication Accelerator for Transformer Self-Attention on the Xilinx KV260 SoM
• Authors: Richie Li, Sicheng Chen,
• Abstract summary: Transformer-based large language models rely heavily on matrix multiplications for attention and feed-forward layers.<n>We introduce a highly optimized tiled matrix multiplication accelerator on a resource-constrained Xilinx KV260 FPGA.<n>Our design exploits persistent on-chip storage, a robust two-level tiling strategy for maximal data reuse, and a systolic-like unrolled compute engine.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based large language models (LLMs) rely heavily on intensive matrix multiplications for attention and feed-forward layers, with the Q, K, and V linear projections in the Multi-Head Self-Attention (MHA) module constituting a decisive performance bottleneck. In this work, we introduce a highly optimized tiled matrix multiplication accelerator on a resource-constrained Xilinx KV260 FPGA that not only addresses this challenge but sets a new standard for efficiency and performance. Our design exploits persistent on-chip storage, a robust two-level tiling strategy for maximal data reuse, and a systolic-like unrolled compute engine that together deliver unparalleled speed and energy efficiency. Integrated with DistilBERT for Q, K, and V projections, our accelerator achieves an unequivocal 7x speedup over ARM CPU implementations (PyTorch) and an extraordinary 200x improvement over naive NumPy, reaching a throughput of up to 3.1~GFLOPs for matrix multiplications on (64,768) x (768,3072) matrices while operating at a conservative 100 MHz. These results decisively demonstrate the transformative potential of FPGA-based acceleration for critical Transformer operations, paving the way for scalable and energy-efficient deep learning inference on edge devices.

Related papers

• BHViT: Binarized Hybrid Vision Transformer [53.38894971164072]
  Model binarization has made significant progress in enabling real-time and energy-efficient computation for convolutional neural networks (CNN) We propose BHViT, a binarization-friendly hybrid ViT architecture and its full binarization model with the guidance of three important observations. Our proposed algorithm achieves SOTA performance among binary ViT methods.
  arXiv  Detail & Related papers  (2025-03-04T08:35:01Z)
• Runtime Tunable Tsetlin Machines for Edge Inference on eFPGAs [0.2294388534633318]
  eFPGAs allow for the design of hardware accelerators of edge Machine Learning (ML) applications at a lower power budget. The limited eFPGA logic and memory significantly constrain compute capabilities and model size. The proposed eFPGA accelerator focuses on minimizing resource usage and allowing flexibility for on-field recalibration over throughput.
  arXiv  Detail & Related papers  (2025-02-10T12:49:22Z)
• A Runtime-Adaptive Transformer Neural Network Accelerator on FPGAs [0.0]
  ADAPTOR is a runtime-adaptive accelerator for dense matrix computations in transformer encoders and decoders on FPGAs. It incorporates efficient matrix tiling to distribute resources across FPGA platforms. It achieves a speedup of 1.7 to 2.25$times$ compared to some state-of-the-art FPGA-based accelerators.
  arXiv  Detail & Related papers  (2024-11-27T08:53:19Z)
• Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation [53.88562288388169]
  A common strategy for. Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks. We propose a novel PEFT approach inspired by Singular Value Decomposition (SVD) for representing the adaptation matrix. SVD decomposes a matrix into the product of a left unitary matrix, a diagonal matrix of scaling values, and a right unitary matrix.
  arXiv  Detail & Related papers  (2024-10-30T12:08:30Z)
• Accelerating Error Correction Code Transformers [56.75773430667148]
  We introduce a novel acceleration method for transformer-based decoders. We achieve a 90% compression ratio and reduce arithmetic operation energy consumption by at least 224 times on modern hardware.
  arXiv  Detail & Related papers  (2024-10-08T11:07:55Z)
• FAMOUS: Flexible Accelerator for the Attention Mechanism of Transformer on UltraScale+ FPGAs [0.0]
  Transformer neural networks (TNNs) are being applied across a widening range of application domains, including natural language processing (NLP), machine translation, and computer vision (CV) This paper proposes textitFAMOUS, a flexible hardware accelerator for dense multi-head attention computation of TNNs on field-programmable gate arrays (FPGAs) It is optimized for high utilization of processing elements and on-chip memories to improve parallelism and reduce latency.
  arXiv  Detail & Related papers  (2024-09-21T05:25:46Z)
• Fast, Scalable, Energy-Efficient Non-element-wise Matrix Multiplication on FPGA [10.630802853096462]
  Modern Neural Network (NN) architectures heavily rely on vast numbers of multiply-accumulate arithmetic operations. This paper proposes a high- throughput, scalable and energy efficient non-element-wise matrix multiplication unit on FPGAs. Using our AMU achieves up to 9x higher throughput and 112x higher energy efficiency over the state-of-the-art solutions for the FPGA-based Quantised Neural Network (QNN) accelerators.
  arXiv  Detail & Related papers  (2024-07-02T15:28:10Z)
• Extreme Compression of Large Language Models via Additive Quantization [59.3122859349777]
  Our algorithm, called AQLM, generalizes the classic Additive Quantization (AQ) approach for information retrieval. We provide fast GPU and CPU implementations of AQLM for token generation, which enable us to match or outperform optimized FP16 implementations for speed.
  arXiv  Detail & Related papers  (2024-01-11T18:54:44Z)
• Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts [60.1586169973792]
  M$3$ViT is the latest multi-task ViT model that introduces mixture-of-experts (MoE) MoE achieves better accuracy and over 80% reduction computation but leaves challenges for efficient deployment on FPGA. Our work, dubbed Edge-MoE, solves the challenges to introduce the first end-to-end FPGA accelerator for multi-task ViT with a collection of architectural innovations.
  arXiv  Detail & Related papers  (2023-05-30T02:24:03Z)
• An Algorithm-Hardware Co-Optimized Framework for Accelerating N:M Sparse Transformers [11.811907838840712]
  We propose an algorithm-hardware co-optimized framework to flexibly and efficiently accelerate Transformers by utilizing general N:M sparsity patterns. We present a flexible and efficient hardware architecture, namely STA, to achieve significant speedup when deploying N:M sparse Transformers. Experimental results show that compared to other methods, N:M sparse Transformers, generated using IDP, achieves an average of 6.7% improvement on accuracy with high training efficiency.
  arXiv  Detail & Related papers  (2022-08-12T04:51:49Z)
• Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization [78.18328503396057]
  Vision transformers (ViTs) are emerging with significantly improved accuracy in computer vision tasks. This work proposes an FPGA-aware automatic ViT acceleration framework based on the proposed mixed-scheme quantization.
  arXiv  Detail & Related papers  (2022-08-10T05:54:46Z)
• VAQF: Fully Automatic Software-hardware Co-design Framework for Low-bit Vision Transformer [121.85581713299918]
  We propose VAQF, a framework that builds inference accelerators on FPGA platforms for quantized Vision Transformers (ViTs) Given the model structure and the desired frame rate, VAQF will automatically output the required quantization precision for activations. This is the first time quantization has been incorporated into ViT acceleration on FPGAs.
  arXiv  Detail & Related papers  (2022-01-17T20:27:52Z)
• Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding [63.539333383965726]
  We propose a novel way to accelerate attention calculation for Transformers with relative positional encoding (RPE) Based upon the observation that relative positional encoding forms a Toeplitz matrix, we mathematically show that kernelized attention with RPE can be calculated efficiently using Fast Fourier Transform (FFT)
  arXiv  Detail & Related papers  (2021-06-23T17:51:26Z)
• Direct Spatial Implementation of Sparse Matrix Multipliers for Reservoir Computing [0.0]
  Reservoir computing systems rely on the recurrent multiplication of a very large, sparse, fixed matrix. We argue that direct implementation of these fixed matrices minimizes the work performed in the computation. We present the structure of our bit-serial matrix multiplier, and evaluate using canonical signed digit representation to further reduce logic utilization.
  arXiv  Detail & Related papers  (2021-01-21T23:16:22Z)
• FTRANS: Energy-Efficient Acceleration of Transformers using FPGA [11.032972017827248]
  We propose an efficient acceleration framework, Ftrans, for transformer-based large scale language representations. Our framework significantly reduces the model size of NLP models by up to 16 times. Our FPGA design achieves 27.07x and 81x improvement in performance and energy efficiency compared to CPU, and up to 8.80x improvement in energy efficiency compared to GPU.
  arXiv  Detail & Related papers  (2020-07-16T18:58:31Z)

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.