Article

OpenCL 2.0 中的 GPU-Quicksort: 嵌套并行性和工作组扫描函数

简介
Автор: Robert I. (Intel) Последнее обновление: 31.05.2019 - 14:20
Article

Caffe* Training on Multi-node Distributed-memory Systems Based on Intel® Xeon® Processor E5 Family

Caffe is a deep learning framework developed by the Berkeley Vision and Learning Center (BVLC) and one of the most popular community frameworks for image recognition. Caffe is often used as a benchmark together with AlexNet*, a neural network topology for image recognition, and ImageNet*, a database of labeled images.
Автор: Gennady F. (Blackbelt) Последнее обновление: 05.07.2019 - 14:54
Article

Caffe* Scoring Optimization for Intel® Xeon® Processor E5 Series

    In continued efforts to optimize Deep Learning workloads on Intel® architecture, our engineers explore various paths leading to the maximum performance.

Автор: Gennady F. (Blackbelt) Последнее обновление: 21.03.2019 - 12:28
Article

针对英特尔® 至强™ 处理器 E5 系列的 Caffe* 评分优化

为了不断优化英特尔® 架构的深度学习工作负载,我们的工程师探索不同的路径,以达到最高性能。

Автор: Gennady F. (Blackbelt) Последнее обновление: 21.03.2019 - 12:28
Article

Code Sample: Optimizing Binarized Neural Networks on Intel® Xeon® Scalable Processors

In the previous article, we discussed the performance and accuracy of Binarized Neural Networks (BNN). We also introduced a BNN coded from scratch in the Wolfram Language. The key component of this neural network is Matrix Multiplication.
Автор: Yash Akhauri Последнее обновление: 21.03.2019 - 12:40