RISC-V RVV efficiency for ANN algorithms

• URL: http://arxiv.org/abs/2407.13326v1
• Date: Thu, 18 Jul 2024 09:26:07 GMT
• Title: RISC-V RVV efficiency for ANN algorithms
• Authors: Konstantin Rumyantsev, Pavel Yakovlev, Andrey Gorshkov, Andrey P. Sokolov,
• Abstract summary: This study examines the effectiveness of applying RVV to commonly used ANN algorithms. The algorithms were adapted for RISC-V and optimized using RVV after identifying the primary bottlenecks.
• Score: 0.5892638927736115
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Handling vast amounts of data is crucial in today's world. The growth of high-performance computing has created a need for parallelization, particularly in the area of machine learning algorithms such as ANN (Approximate Nearest Neighbors). To improve the speed of these algorithms, it is important to optimize them for specific processor architectures. RISC-V (Reduced Instruction Set Computer Five) is one of the modern processor architectures, which features a vector instruction set called RVV (RISC-V Vector Extension). In machine learning algorithms, vector extensions are widely utilized to improve the processing of voluminous data. This study examines the effectiveness of applying RVV to commonly used ANN algorithms. The algorithms were adapted for RISC-V and optimized using RVV after identifying the primary bottlenecks. Additionally, we developed a theoretical model of a parameterized vector block and identified the best on average configuration that demonstrates the highest theoretical performance of the studied ANN algorithms when the other CPU parameters are fixed.

Related papers

• Improved vectorization of OpenCV algorithms for RISC-V CPUs [0.0]
  We discuss the possibilities of accelerating computations on available RISC-V processors. It is shown that improved vectorization speeds up computations on existing prototypes of RISC-V devices by tens of percent.
  arXiv  Detail & Related papers  (2023-09-19T12:36:03Z)
• Improved Algorithms for Neural Active Learning [74.89097665112621]
  We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
  arXiv  Detail & Related papers  (2022-10-02T05:03:38Z)
• Towards making the most of NLP-based device mapping optimization for OpenCL kernels [5.6596607119831575]
  We extend the work of Cummins et al., namely Deeptune, that tackles the problem of optimal device selection ( CPU or GPU) for accelerated OpenCL kernels. We propose four different models that provide enhanced contextual information of source codes. Experimental results show that our proposed methodology surpasses that of Cummins et al. work, providing up to 4% improvement in prediction accuracy.
  arXiv  Detail & Related papers  (2022-08-30T10:20:55Z)
• Hyperparameter optimization of data-driven AI models on HPC systems [0.0]
  This work is part of RAISE's work on data-driven use cases which leverages AI- and HPC cross-methods. It is shown that in the case of Machine-Learned Particle reconstruction in High Energy Physics, the ASHA algorithm in combination with Bayesian optimization gives the largest performance increase per compute resources spent out of the investigated algorithms.
  arXiv  Detail & Related papers  (2022-03-02T14:02:59Z)
• AsySQN: Faster Vertical Federated Learning Algorithms with Better Computation Resource Utilization [159.75564904944707]
  We propose an asynchronous quasi-Newton (AsySQN) framework for vertical federated learning (VFL) The proposed algorithms make descent steps scaled by approximate without calculating the inverse Hessian matrix explicitly. We show that the adopted asynchronous computation can make better use of the computation resource.
  arXiv  Detail & Related papers  (2021-09-26T07:56:10Z)
• Benchmarking Processor Performance by Multi-Threaded Machine Learning Algorithms [0.0]
  In this paper, I will make a performance comparison of multi-threaded machine learning clustering algorithms. I will be working on Linear Regression, Random Forest, and K-Nearest Neighbors to determine the performance characteristics of the algorithms.
  arXiv  Detail & Related papers  (2021-09-11T13:26:58Z)
• Provably Faster Algorithms for Bilevel Optimization [54.83583213812667]
  Bilevel optimization has been widely applied in many important machine learning applications. We propose two new algorithms for bilevel optimization. We show that both algorithms achieve the complexity of $mathcalO(epsilon-1.5)$, which outperforms all existing algorithms by the order of magnitude.
  arXiv  Detail & Related papers  (2021-06-08T21:05:30Z)
• Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing [49.73889315176884]
  We present the first provable Least-Squares Value Iteration (LSVI) algorithms that have runtime complexity sublinear in the number of actions. We build the connections between the theory of approximate maximum inner product search and the regret analysis of reinforcement learning.
  arXiv  Detail & Related papers  (2021-05-18T05:23:53Z)
• Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems [59.804810122136345]
  We propose a framework for deep-unfolding, where a general form of iterative algorithm induced deep-unfolding neural network (IAIDNN) is developed. An efficient IAIDNN based on the structure of the classic weighted minimum mean-square error (WMMSE) iterative algorithm is developed. We show that the proposed IAIDNN efficiently achieves the performance of the iterative WMMSE algorithm with reduced computational complexity.
  arXiv  Detail & Related papers  (2020-06-15T02:57:57Z)
• PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives [55.79741270235602]
  We present compiler algorithms to automatically generate high performance implementations of Deep Learning primitives. We develop novel data reuse analysis algorithms using the polyhedral model. We also show that such a hybrid compiler plus a minimal library-use approach results in state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-06-02T06:44:09Z)
• An optimal scheduling architecture for accelerating batch algorithms on Neural Network processor architectures [0.0]
  In neural network topologies, algorithms are running on batches of data tensors. For the algorithms running on batches of data, an optimal batch scheduling architecture is very much needed.
  arXiv  Detail & Related papers  (2020-02-14T17:13:13Z)

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.