Location:
Search - GPU FFT
Search list
Description: UNC GAMMA group发布的这个高性能FFT库可以处理大量1D FFT。实验表明，价值$500的Nvidia 7900 GPU的FFT计算速度是价格$1500-$2000的高端CPU的4倍，事实上，7900 GPU的FFT计算性能可以达到6 GFLOPS。-UNC GAMMA group releases of this high-performance FFT library can handle large FFT 1D. Experiments show that value $ 500 Nvidia 7900 GPU speed FFT calculation is the price $ 1500-$ 20 00 high-end CPU four times, in fact, the FFT 7900 GPU computing performance can be achieved six GFLOPS.
Platform: |
Size: 219613 |
Author: lishi |
Hits:
Description: 选自<gpu gemes 2>,用gpu实现快速傅立叶变换
Platform: |
Size: 14603858 |
Author: 丛日昊 |
Hits:
Description: 基于GPU进行快速科学计算，速度远比CPU快得多。这是在GPU上实现FFT运算的程序代码
Platform: |
Size: 260619 |
Author: 张非 |
Hits:
Description: UNC GAMMA group发布的这个高性能FFT库可以处理大量1D FFT。实验表明，价值$500的Nvidia 7900 GPU的FFT计算速度是价格$1500-$2000的高端CPU的4倍，事实上，7900 GPU的FFT计算性能可以达到6 GFLOPS。-UNC GAMMA group releases of this high-performance FFT library can handle large FFT 1D. Experiments show that value $ 500 Nvidia 7900 GPU speed FFT calculation is the price $ 1500-$ 20 00 high-end CPU four times, in fact, the FFT 7900 GPU computing performance can be achieved six GFLOPS.
Platform: |
Size: 219136 |
Author: lishi |
Hits:
Description: 选自<gpu gemes 2>,用gpu实现快速傅立叶变换-From <gpu gemes 2>, using GPU for fast Fourier transform
Platform: |
Size: 14603264 |
Author: 丛日昊 |
Hits:
Description: 使用GPU的强大并行计算能力来实现稠密矩阵的LU分解计算。-The use of a powerful GPU parallel computing capability to realize dense matrix LU decomposition calculation.
Platform: |
Size: 4578304 |
Author: tiantiancode |
Hits:
Description: 基于GPU进行快速科学计算，速度远比CPU快得多。这是在GPU上实现FFT运算的程序代码-GPU-based fast scientific computing, speed is much faster than the CPU. This is achieved in the GPU computing FFT code
Platform: |
Size: 260096 |
Author: 张非 |
Hits:
Description: GPU实现的MapReduce framework,对于学习并行编程和cuda平台的编程方面有着极好的参考价值，里面附带论文。用户要求有NViDIA显卡，并且安装cuda编程环境。-We design and implement Mars, a MapReduce framework, on graphics
processors (GPUs). MapReduce is a distributed programming
framework originally proposed by Google for the ease of development
of web search applications on a large number of commodity
CPUs. Compared with CPUs, GPUs have an order of magnitude
higher computation power and memory bandwidth, but are harder
to program since their architectures are designed as a special-purpose
co-processor and their programming interfaces are typically for
graphics applications.
Platform: |
Size: 7930880 |
Author: 陈思远 |
Hits:
Description: 在GPU上实现FFT，本科毕设时的资料，用OPENGL实现。-GPU to achieve in the FFT, we completed the set up information at the time, using OPENGL achieve.
Platform: |
Size: 219136 |
Author: 谢坚 |
Hits:
Description: 完成飛行情報區交叉可以高保真的夢想，它的大幅過濾器和線性信號階段。
but current FFT type of FIR crossover on PC loses time information of audio signal.但目前的FFT類型的FIR交叉在PC失去時間信息的音頻信號。 If you use 10ms frame, time information in 10ms are lost.如果您使用10ms幀，在10ms時間信息都將丟失。
Now nVidia CUDA GPU computing power can achieve very fast "Real" FIR conversion, resulting such a sharp filtering like below.現在的nVidia CUDA技術的GPU運算能力可以達到非常快的“真正的”飛行情報區的轉換，從而導致這樣一個尖銳的過濾像如下。 -Complete FIR Crossover can be Audiophile s dream, by it s sharp filter and linear signal phase.
but current FFT type of FIR crossover on PC loses time information of audio signal. If you use 10ms frame, time information in 10ms are lost.
Now nVidia CUDA GPU computing power can achieve very fast "Real" FIR conversion, resulting such a sharp filtering like below.
Platform: |
Size: 1781760 |
Author: bigecho |
Hits:
Description: 在CUDA下的FFT变换程序，可以供爱好GPU编程的参考学习。-It it the FFT transform in CUDA, and very suitable for the programer who is interested in GPU.
Platform: |
Size: 2048 |
Author: IAU |
Hits:
Description: CUFFT GPU的傅立叶变换
GPU的通用计算-CUFFT GPU CUDA
Platform: |
Size: 7168 |
Author: zzs |
Hits:
Description: A very fast FFT for Matlab with GPU
Platform: |
Size: 5120 |
Author: Includer |
Hits:
Description: 应用VC++编写，应用GPU的CUDA扩展平台完成FFT运算-Programming with CUDA FFT program
Platform: |
Size: 1024 |
Author: Louis Fu |
Hits:
Description: 分析了如何創建一個簡單的7x7濾波器的OpenCL是適用於所有的GPU。本案例研究將著眼於提高卷積卷積時的性能與小圖像內核，一般來說，基於 FFT卷積更快的30x30內核及以後 [1]，但實際上它的使用不常見的大窗口大小。
.我們將首先實現卷積圖像，然後使用改進的濾波器性能通過使用__constant OpenCL的內存和緩存圖像信息在__local空間。 -Analysis of how to create a simple 7x7 filter is applied to all OpenCL GPU. This case study will focus on improving the performance of the time convolution convolution kernel with a small image, in general, based on FFT convolution kernel and the subsequent 30x30 faster [1], but in fact it is not common to use a large window size. . We will first implement the convolution image, and then use the filter performance improved through the use of memory and cache __constant OpenCL image information in the __local space.
Platform: |
Size: 1275904 |
Author: yohow |
Hits:
Description: 基于cuda的GPU编程，使用FFT模拟海面，内含cpp文件和cuda文件。-Cuda-based GPU programming, using the FFT simulation of the sea, containing the cpp file and cuda file.
Platform: |
Size: 10240 |
Author: lishuang |
Hits:
Description: 基于在GPU上实现FFT海浪模拟以及大气模拟-On the GPU, the FFT wave simulation as well as atmospheric modeling
Platform: |
Size: 2200576 |
Author: xxx |
Hits:
Description: GPU 实现FFT，包括读取txt文件至内存中实现，实现结果后，将结果以txt文件的格式保存。-After the GPU to realize FFT, including memory read txt file to achieve, achieve results, the results will be saved in txt file format.
Platform: |
Size: 3072 |
Author: 陈大强 |
Hits:
Description: FFT Compution on GPU
Platform: |
Size: 252928 |
Author: mahmoudk
|
Hits: