paper-with-me

홈 › Papers

Accelerating Barnes-Hut t-SNE Algorithm by Efficient Parallelization on Multi-Core CPUs

2022-12-22 · Narendra Chaudhary, Alexander Pivovar, Pavel Yakovlev, Andrey Gorshkov, Sanchit Misra

t-SNE remains one of the most popular embedding techniques for visualizing high-dimensional data. Most standard packages of t-SNE, such as scikit-learn, use the Barnes-Hut t-SNE (BH t-SNE) algorithm for large datasets. However, existing CPU implementations of this algorithm are inefficient. In this work, we accelerate the BH t-SNE on CPUs via cache optimizations, SIMD, parallelizing sequential steps, and improving parallelization of multithreaded steps. Our implementation (Acc-t-SNE) is up to 261x and 4x faster than scikit-learn and the state-of-the-art BH t-SNE implementation from daal4py, respectively, on a 32-core Intel(R) Icelake cloud instance.

📄 PDF Abstract BibTeX arXiv:2212.11506

Code (0)

등록된 구현이 없습니다.

Tasks

CPU

Similar Papers 제목 키워드 기반

Barnes-Hut-SNE

2013-01-15 · Laurens van der Maaten

The paper presents an O(N log N)-implementation of t-SNE -- an embedding technique that is commonly used for the visualization of high-dimensional data in scatter plots and that normally runs in O(N^2). The new implement…

Accelerating Latency-Critical Applications with AI-Powered Semi-Automatic Fine-Grained Parallelization on SMT Processors

2025-08-31 · Denis Los, Igor Petushkov arxiv

Latency-critical applications tend to show low utilization of functional units due to frequent cache misses and mispredictions during speculative execution in high-performance superscalar processors. However, due to sign…

Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization

2017-08-18 · Viacheslav Khomenko, Oleg Shyshkov, Olga Radyvonenko, Kostiantyn Bokhan

An efficient algorithm for recurrent neural network training is presented. The approach increases the training speed for tasks where a length of the input sequence may vary significantly. The proposed approach is based o…

GPUHandwriting Recognition

Efficient Parallelization of Message Passing Neural Network Potentials for Large-scale Molecular Dynamics

2025-05-10 · Junfan Xia, Bin Jiang

Machine learning potentials have achieved great success in accelerating atomistic simulations. Many of them relying on atom-centered local descriptors are natural for parallelization. More recent message passing neural n…

Barnes-Hut Approximation for Point SetGeodesic Shooting

2019-07-10 · Jiancong Wang, Long Xie, Paul Yushkevich, James Gee

Geodesic shooting has been successfully applied to diffeo-morphic registration of point sets. Exact computation of the geodesicshooting between point sets, however, requiresO(N2) calculations each time step on the number…