VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in Transformers

• URL: http://arxiv.org/abs/2504.11227v1
• Date: Tue, 15 Apr 2025 14:28:48 GMT
• Title: VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in Transformers
• Authors: Run Wang, Gamze Islamoglu, Andrea Belano, Viviane Potocnik, Francesco Conti, Angelo Garofalo, Luca Benini,
• Abstract summary: Accelerating Softmax is challenging due to its non-pointwise, non-linear nature, with exponentiation as the most demanding step.<n>We design a custom arithmetic block for Bfloat16 exponentiation leveraging a novel approximation algorithm based on Schraudolph's method.<n>We execute Softmax with 162.7$times$ less latency and 74.3$times$ less energy compared to the baseline cluster.
• Score: 13.984340807378457
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: While Transformers are dominated by Floating-Point (FP) Matrix-Multiplications, their aggressive acceleration through dedicated hardware or many-core programmable systems has shifted the performance bottleneck to non-linear functions like Softmax. Accelerating Softmax is challenging due to its non-pointwise, non-linear nature, with exponentiation as the most demanding step. To address this, we design a custom arithmetic block for Bfloat16 exponentiation leveraging a novel approximation algorithm based on Schraudolph's method, and we integrate it into the Floating-Point Unit (FPU) of the RISC-V cores of a compute cluster, through custom Instruction Set Architecture (ISA) extensions, with a negligible area overhead of 1\%. By optimizing the software kernels to leverage the extension, we execute Softmax with 162.7$\times$ less latency and 74.3$\times$ less energy compared to the baseline cluster, achieving an 8.2$\times$ performance improvement and 4.1$\times$ higher energy efficiency for the FlashAttention-2 kernel in GPT-2 configuration. Moreover, the proposed approach enables a multi-cluster system to efficiently execute end-to-end inference of pre-trained Transformer models, such as GPT-2, GPT-3 and ViT, achieving up to 5.8$\times$ and 3.6$\times$ reduction in latency and energy consumption, respectively, without requiring re-training and with negligible accuracy loss.

Related papers

• Design and Implementation of an FPGA-Based Tiled Matrix Multiplication Accelerator for Transformer Self-Attention on the Xilinx KV260 SoM [0.0]
  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.
  arXiv  Detail & Related papers  (2025-03-20T22:15:42Z)
• AdaSplash: Adaptive Sparse Flash Attention [20.28859850361068]
  We propose AdaSplash, which combines the efficiency of GPU-optimized algorithms with the sparsity benefits of $alpha$-entmax.<n>AdaSplash achieves substantial improvements in runtime and memory efficiency compared to existing $alpha$-entmax implementations.
  arXiv  Detail & Related papers  (2025-02-17T17:56:23Z)
• Progressive Mixed-Precision Decoding for Efficient LLM Inference [49.05448842542558]
  We introduce Progressive Mixed-Precision Decoding (PMPD) to address the memory-boundedness of decoding.<n>PMPD achieves 1.4$-$12.2$times$ speedup in matrix-vector multiplications over fp16 models.<n>Our approach delivers a throughput gain of 3.8$-$8.0$times$ over fp16 models and up to 1.54$times$ over uniform quantization approaches.
  arXiv  Detail & Related papers  (2024-10-17T11:46:33Z)
• PEANO-ViT: Power-Efficient Approximations of Non-Linearities in Vision Transformers [4.523939613157408]
  Vision Transformers (ViTs) are designed for Field-Programmable Gate Arrays (FPGAs) ViTs' non-linear functions pose significant obstacles to efficient hardware implementation due to their complex mathematical operations. PEANO-ViT offers a novel approach to streamlining the implementation of the layer normalization layer.
  arXiv  Detail & Related papers  (2024-06-21T03:54:10Z)
• Inverse-Free Fast Natural Gradient Descent Method for Deep Learning [52.0693420699086]
  We present a fast natural gradient descent (FNGD) method that only requires inversion during the first epoch. FNGD exhibits similarities to the average sum in first-order methods, leading to the computational complexity of FNGD being comparable to that of first-order methods.
  arXiv  Detail & Related papers  (2024-03-06T05:13:28Z)
• HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference [68.59839755875252]
  HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47times$ on a single TPUv5e device.
  arXiv  Detail & Related papers  (2024-02-14T18:04:36Z)
• 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)
• RedMule: A Mixed-Precision Matrix-Matrix Operation Engine for Flexible and Energy-Efficient On-Chip Linear Algebra and TinyML Training Acceleration [15.869673535117032]
  Current training algorithms rely on floating-point matrix operations to meet the precision and dynamic range requirements. RedMulE is a low-power specialized accelerator conceived for multi-precision floating-point General Matrix-Matrix Operations (GEMM-Ops) acceleration. RedMulE achieves up to 58.5 GFLOPS and 117 GFLOPS for FP16 and FP8, respectively, with 99.4% utilization of the array of Computing Elements.
  arXiv  Detail & Related papers  (2023-01-10T11:07:16Z)
• 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)
• EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference [82.1584439276834]
  Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. We present EdgeBERT, an in-depth algorithm- hardware co-design for latency-aware energy optimization for multi-task NLP.
  arXiv  Detail & Related papers  (2020-11-28T19:21:47Z)
• MicroNet: Towards Image Recognition with Extremely Low FLOPs [117.96848315180407]
  MicroNet is an efficient convolutional neural network using extremely low computational cost. A family of MicroNets achieve a significant performance gain over the state-of-the-art in the low FLOP regime. For instance, MicroNet-M1 achieves 61.1% top-1 accuracy on ImageNet classification with 12 MFLOPs, outperforming MobileNetV3 by 11.3%.
  arXiv  Detail & Related papers  (2020-11-24T18:59:39Z)

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.