blocks|key|667468|text|我不知道这个算法，但是如果你发现你对设备的想法足够快，那你为什么不把实现从使用纹理内存更改为一个简单的数组，也许你可以使用共享内存来做更多的加速呢？|type|ordered-list-item|depth|inlineStyleRanges|entityRanges|data|667469|我找到了一些用matlab和fortran+77编写的：
http://www.cims.nyu.edu/cmcl/nufft/nufft.html
http://www.mathworks.com/matlabcentral/fileexchange/25135-nufft-nufft-usffft|offset|length|667470|unstyled|entityMap|0|LINK|mutability|MUTABLE|url|http://www.cims.nyu.edu/cmcl/nufft/nufft.html|1|http://www.mathworks.com/matlabcentral/fileexchange/25135-nufft-nufft-usffft^0|0|T|19|0|23|24|1|0^^$0|@$1|2|3|4|5|6|7|Q|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|R|8|@]|9|@$D|S|E|T|1|U]|$D|V|E|W|1|X]]|A|$]]|$1|F|3|-4|5|G|7|Y|8|@]|9|@]|A|$]]]|H|$I|$5|J|K|L|A|$M|N]]|O|$5|J|K|L|A|$M|P]]]]

<ol>
<li>I don't know about that algorithm, but if what you've found you think fast enough for your equipment, then why dont you change the implementation from using texture memory to just a simple array, and maybe you can do more speedup using shared memory?</li>
<li>I've found some written in matlab and fortran 77:

<a href="http://www.cims.nyu.edu/cmcl/nufft/nufft.html" rel="nofollow">http://www.cims.nyu.edu/cmcl/nufft/nufft.html</a>

<a href="http://www.mathworks.com/matlabcentral/fileexchange/25135-nufft-nufft-usffft" rel="nofollow">http://www.mathworks.com/matlabcentral/fileexchange/25135-nufft-nufft-usffft</a></li>
</ol>

blocks|key|870653|text|关于#1|type|unstyled|depth|inlineStyleRanges|entityRanges|data|870654|Ruijters的bi/tricubic样条插值，我想你指的是http://dannyruijters.nl/cubicinterpolation，(编辑！)现在使用一维数据，谢谢！在这一页上见Danny+Ruijters的回答。|offset|length|870655|关于#2|870656|下面是我所知道的几个NUFFT实现，并简要介绍它们。|870657|@adiyu07，Greengard等人提到的第一个库是Fortran，它是快速高斯网格的实现，我不知道，所以我没有花很长时间看这个库(虽然这确实提供了类型III的非均匀到非均匀的转换)。|ordered-list-item|870658|第二个是费拉拉在Matlab/MEX中实现Greengard的算法，我无法得到它给出正确的解决方案(请参阅我刚才在Mathworks+FileExchange上的评论)。|870659|http://www-user.tu-chemnitz.de/~potts/nfft/我无法在Windows上编译它，所以我放弃了它。它也有第三类NUFFT。|870660|http://web.eecs.umich.edu/~fessler/code/是用Matlab/MEX编写的，至少为Linux和Windows提供了预编译的二进制文件。当然是由非专业程序员编写的，但这是我得到的4个中唯一一个正确工作的。我甚至让它在got中工作，因为Octave可以使用预编好的MEX二进制文件，所以我在少数地方修改了他们的Matlab源代码(基本上是通过查看产生八度错误的地方)。这也使用了与Greengard或Potts不同的算法，基于minimize准则(它的解决方案保证最大DFT错误最小化)，但缺少类型-III+NUFFT(只有类型-I和II:其中一个域必须是统一的)。|870661|我相信第五个NUFFT/“网格”实现是由Hargreaves等人：http://www-mrsrl.stanford.edu/~brian/gridding/+(论文at+http://dx.doi.org/10.1109/TMI.2005.848376)完成的。它是在Matlab/MEX中实现的。事实上，它并不像清单上的前四种那样通用，因为它很大程度上嵌入了核磁共振成像的背景中。|870662|这里还有第六个实现，使用Cython+(快速Python)，具有type-III非统一到非一致转换和其他一些很好的特性，唉，在GPL：https://github.com/mrbell/gfft下面。|870663|我正在缓慢地将Fessler的算法移植到Python/Cython，也可能是CUDA+(“可能”，因为标准(CU)FFT和线性插值似乎足够有效)。祝你好运。|870664|entityMap|0|LINK|mutability|MUTABLE|url|http://dannyruijters.nl/cubicinterpolation|1|http://www-user.tu-chemnitz.de/~potts/nfft/|2|http://web.eecs.umich.edu/~fessler/code/|3|http://www-mrsrl.stanford.edu/~brian/gridding/|4|http://dx.doi.org/10.1109/TMI.2005.848376|5|https://github.com/mrbell/gfft^0|0|V|16|0|0|0|0|0|0|0|17|1|0|0|14|2|0|X|1A|3|2E|15|4|0|1V|U|5|0|0^^$0|@$1|2|3|4|5|6|7|1G|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|1H|8|@]|9|@$D|1I|E|1J|1|1K]]|A|$]]|$1|F|3|G|5|6|7|1L|8|@]|9|@]|A|$]]|$1|H|3|I|5|6|7|1M|8|@]|9|@]|A|$]]|$1|J|3|K|5|L|7|1N|8|@]|9|@]|A|$]]|$1|M|3|N|5|L|7|1O|8|@]|9|@]|A|$]]|$1|O|3|P|5|L|7|1P|8|@]|9|@$D|1Q|E|1R|1|1S]]|A|$]]|$1|Q|3|R|5|L|7|1T|8|@]|9|@$D|1U|E|1V|1|1W]]|A|$]]|$1|S|3|T|5|L|7|1X|8|@]|9|@$D|1Y|E|1Z|1|20]|$D|21|E|22|1|23]]|A|$]]|$1|U|3|V|5|L|7|24|8|@]|9|@$D|25|E|26|1|27]]|A|$]]|$1|W|3|X|5|6|7|28|8|@]|9|@]|A|$]]|$1|Y|3|-4|5|6|7|29|8|@]|9|@]|A|$]]]|Z|$10|$5|11|12|13|A|$14|15]]|16|$5|11|12|13|A|$14|17]]|18|$5|11|12|13|A|$14|19]]|1A|$5|11|12|13|A|$14|1B]]|1C|$5|11|12|13|A|$14|1D]]|1E|$5|11|12|13|A|$14|1F]]]]

<h2>Regarding #1</h2>

Ruijters' bi/tricubic spline interpolation, which is I think what you refer to <a href="http://dannyruijters.nl/cubicinterpolation" rel="nofollow">http://dannyruijters.nl/cubicinterpolation</a>, (edited!) now works with 1D data, thank you! See Danny Ruijters' answer on this page.

<h2>Regarding #2</h2>

Here're a few NUFFT implementations that I'm aware of, and brief thoughts on them.

<ol>
<li>The first library mentioned by @ardiyu07, Greengard, et alia's implementation of fast Gaussian gridding, is in Fortran, which I don't know and so I didn't look at this for long (though this does offer type-III nonuniform-to-nonuniform transforms). </li>
<li>The second one is Ferrara's implementation of Greengard's algorithm in Matlab/MEX, and I couldn't get it to give me the correct solution (see my comment to that effect on Mathworks FileExchange, which I just posted).</li>
<li>Potts, et al., <a href="http://www-user.tu-chemnitz.de/~potts/nfft/" rel="nofollow">http://www-user.tu-chemnitz.de/~potts/nfft/</a> I couldn't get this to compile in Windows so I gave up on it. It also has type-III NUFFTs.</li>
<li>Fessler, et al., <a href="http://web.eecs.umich.edu/~fessler/code/" rel="nofollow">http://web.eecs.umich.edu/~fessler/code/</a> written in Matlab/MEX and pre-compiled binaries provided for Linux and Windows at least. Definitely written by non-professional programmers, but it's the only one of the 4 that I've gotten to work correctly. I even got it to work in GNU Octave after changing their Matlab source code in a handful of places (basically by seeing where Octave errors were raised), since Octave can use pre-compiled MEX binaries. This also uses a different algorithm than Greengard's or Potts', based on min-max criteria (its solutions are guaranteed to minimize the maximum DFT error), but lacks type-III NUFFTs (only types-I and II: one of the domains has to be uniform).</li>
<li>I believe a fifth NUFFT/"gridding" implementation is by Hargreaves, et al.: <a href="http://www-mrsrl.stanford.edu/~brian/gridding/" rel="nofollow">http://www-mrsrl.stanford.edu/~brian/gridding/</a> (paper at <a href="http://dx.doi.org/10.1109/TMI.2005.848376" rel="nofollow">http://dx.doi.org/10.1109/TMI.2005.848376</a>). It is in Matlab/MEX. As is, it is not as general-purpose as the previous four on this list, as it's very much embedded in its MRI context.</li>
<li>And here' a sixth implementation, in Cython (fast Python), with type-III nonuniform-to-nonuniform transforms and some other nice features, alas under GPL: <a href="https://github.com/mrbell/gfft" rel="nofollow">https://github.com/mrbell/gfft</a></li>
</ol>

I'm working, at a glacial pace, on porting Fessler's algorithm to Python/Cython, and maybe CUDA ("maybe" because just zero-padding the standard (CU)FFT and linear interpolation seems to work well enough). Best of luck.

blocks|key|1350127|text|老实说，对于GPU来说，您的并行性似乎有点低。在这里，具有SSE优化的6核可能优于GPU。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1350128|entityMap^0|0^^$0|@$1|2|3|4|5|6|7|D|8|@]|9|@]|A|$]]|$1|B|3|-4|5|6|7|E|8|@]|9|@]|A|$]]]|C|$]]

To be honest, your parallelism seems to be a bit low for the GPU. A 6core with SSE optimizations might outperform a GPU here.

blocks|key|1350319|text|自从更多的人问这个问题以来，我把我的CUDA三次插值代码也扩展到了一维三次插值。您可以在这里找到更新的代码：http://www.dannyruijters.nl/cubicinterpolation/|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|1350320|一个工作的CUDA示例，也包含一维三次插值，可以在cudaAccuracyTest示例中的CI.zip子目录中找到。|1350321|对于那些对SSE方法更感兴趣的人，我在示例子目录中的referenceCubicTexture3D示例中有一些优化的多线程三次插值代码(尽管是3D的，而不是1D的)。|1350322|编辑:三次插值代码现在可以在github上使用。一维三次插值程序为这里。|1350323|entityMap|0|LINK|mutability|MUTABLE|url|http://www.dannyruijters.nl/cubicinterpolation/|1|http://www.dannyruijters.nl/cubicinterpolation/CI.zip|2|https://github.com/DannyRuijters/CubicInterpolationCUDA|3|https://github.com/DannyRuijters/CubicInterpolationCUDA/blob/master/code/internal/cubicTex1D_kernel.cu^0|1I|1B|0|0|19|6|1|0|0|E|6|2|X|2|3|0^^$0|@$1|2|3|4|5|6|7|X|8|@]|9|@$A|Y|B|Z|1|10]]|C|$]]|$1|D|3|E|5|6|7|11|8|@]|9|@$A|12|B|13|1|14]]|C|$]]|$1|F|3|G|5|6|7|15|8|@]|9|@]|C|$]]|$1|H|3|I|5|6|7|16|8|@]|9|@$A|17|B|18|1|19]|$A|1A|B|1B|1|1C]]|C|$]]|$1|J|3|-4|5|6|7|1D|8|@]|9|@]|C|$]]]|K|$L|$5|M|N|O|C|$P|Q]]|R|$5|M|N|O|C|$P|S]]|T|$5|M|N|O|C|$P|U]]|V|$5|M|N|O|C|$P|W]]]]

Since more people have asked this, I have extended my CUDA cubic interpolation code with 1D cubic interpolation as well. You can find the updated code here: <a href="http://www.dannyruijters.nl/cubicinterpolation/" rel="nofollow">http://www.dannyruijters.nl/cubicinterpolation/</a>

A working CUDA example that also contains 1D cubic interpolation can be found in the cudaAccuracyTest sample in the examples subdirectory in <a href="http://www.dannyruijters.nl/cubicinterpolation/CI.zip" rel="nofollow">CI.zip</a>.

For those of you who are more interested in a SSE approach, I have some working SSE optimized multi-threaded cubic interpolation code (albeit in 3D, not 1D) in the referenceCubicTexture3D sample in the examples subdirectory.

edit: The cubic interpolation code is now available on <a href="https://github.com/DannyRuijters/CubicInterpolationCUDA" rel="nofollow">github</a>. The 1D cubic interpolation code is <a href="https://github.com/DannyRuijters/CubicInterpolationCUDA/blob/master/code/internal/cubicTex1D_kernel.cu" rel="nofollow">here</a>.

I'm making a medical imaging equipment. I want to use CUDA for making faster equipment

I receive 1024 size 1d data from CCD 512 times.
before I perform IFFT 
I have to apply high performance interpolation algorithm (like cubic spline interpolation)
to the 1024 size data each (then 1d interpolation 512 times).

<ol>
<li>Is there any CUDA library to perform cubic spline interpolation?
(I found that there is one library, but it is for 2 or 3 dimensional image.
Since I need to perform other complicated filtering functions, I need the data on the global memory, not on the texture memory.)</li>
<li>Is there any NUFFT (non uniform fast Fourier transform) library (doesn't need to be written for CUDA)? 
I'm thinking that if I have NUFFT function, I don't have to do interpolation and IFFT separately which is possible for making even faster equipment.</li>
</ol>

CUDA: 1-dimensional cubic spline interpolation in CUDA

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

教程

学习中心

腾讯云实验室

直播

竞赛

腾讯云代码分析专区

腾讯iOA零信任安全管理系统专区

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云智能顾问专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯轻量云游戏服专区

EdgeOne AI 安全实战专区

腾讯云最具价值专家

腾讯云架构师技术同盟

腾讯云创作之星

腾讯云开发者先锋

腾讯云代码助手

云原生构建

TAPD 敏捷项目管理

Cloud Studio

SDK中心

API中心

命令行工具

涵盖代码开发、场景应用、自动测试全流程，助你从零构建专属AI助手

一站式MCP教程库，解锁AI应用新玩法

聚焦“写作效率、视觉美观与运行性能”三方面进行全面升级，为您提供更高效、稳定的创作环境

社区富文本&Markdown编辑器全新改版上线，欢迎大家体验!

诚挚邀请您参与本次调研，分享您的真实使用感受与建议。您的反馈至关重要，感谢您的支持与参与！

社区新版编辑器体验调研

我在做医学成像设备。我想用CUDA制造更快的设备我收到1024大小的一维数据从CCD 512次。在执行IFFT之前，我必须将高性能的插值算法(如三次样条插值)应用于每个1024个大小的数据(然后是1d插值512次)。是否有任何CUDA库执行三次样条插值？(我发现有一个库，但它是用于二维或三维图像的。因为我需要执行其他复...

问CUDA中的一维三次样条插值
EN

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问CUDA中的一维三次样条插值EN