Posts 21 - 30 of 89

结果:矩阵

Hadamard矩阵

我刚从ICIAM2019 conference在西班牙瓦伦西亚。这是一次巨大的会议 - 4,000多名与会者,数十名奖金和邀请的演讲,数百个平行的迷你典礼。我在由尼克·海姆(Nick Higham)和罗布·科尔斯(Rob Corless)组织的两部分小型葡萄酒中发表了演讲。我概述了演讲的第一部分this blog一个月前。这篇文章概述了第二部分,这是关于Hadamard矩阵的。其中一些取自this blogfive years ago....read more >>

  • send email

Benchmarking a GPU 5

我最近获得了GPU,一个图形处理单元。之所以称为GPU,是因为此类处理器最初是为了加快图形的速度。但是MATLAB使用它来加快计算。让我们看看如何gpuArrayobject benchmarks on my machine. I have been doing computer benchmarks for years. I like to do profiles where I vary the size of a task and see how the amount of memory required affects performance. I always learn something unexpected when I do these profiles. Ben Todoroff is on the MathWorks Parallel Processing team. Last year he contributed#34080,gpubenchto the MATLAB Central File Exchange. He has been able to compare several different GPUs. I am going to consider the performance of only one GPU, but in more detail.重要的提示。This is only about double precision. Single precision is another story.。。。read more >>

Experiments with Variable Format Half Precision

在过去的一个月中,我一直在使用我描述的可变格式16位浮点算术在这篇文章中。It has been frustrating work. I have found that the limited precision and limited range of half precision make it barely usable for the kind of experiments with matrix computation that I like to do. In this post I will describe a few of these experiments....read more >>

MATLAB® History, Modern MATLAB, part 1

The ACM Special Interest Group on Programming Languages, SIGPLAN, expects to hold the fourth in a series of conferences on the History of Programming Languages in 2020, seeHopl-IV。论文的初稿将在2018年8月之前提交。漫长的交付时间使我有机会撰写MATLAB的详细历史。我计划在各节中撰写论文,我将在此博客中发布,因为它们可用。read more >>

Posts 21 - 30 of 89