搜索资源列表
CUDA_BP_neuralnetwork
- 基于nvidia CUDA架构的BP神经网络程序，在G80,G92 GPU上可以完成BP神经网络训练。速度较双核CPU提高十倍
2D CUDA-based bilinear interpolation
- This MEX performs 2d bilinear interpolation using an NVIDIA graphics chipset. To compile and run this software, one needs the NVIDIA CUDA Toolkit (http://www.nvidia.com/object/cuda_get.html) and, of course, an NVIDIA graphics card of reasonably moder
parallel-sorting_GPU
- 基于CUDA的并行排序GPU-BBSort 需要NVIDIA显卡支持-CUDA Parallel Sorting on GPU-BBSort NVIDIA graphics support needed
cuSVMVCcode
- 基于GPU计算的SVM，VC++源码，包括详细文档说明文件。借用了GPU编程的优势，该代码据作者说比常规的libsvm等算法包的训练速度快13-73倍，预测速度快22-172倍。希望对大家有用-cuSVM is a software package for high-speed (Gaussian-kernelized) Support Vector Machine training and prediction that exploits the massively parallel proc
simpleCUFFT
- 基于CUDA的正反FFT实现 需要NVIDIA显卡支持-Based on the positive and negative CUDA FFT implementation needs NVIDIA graphics support
kuaisupaixu_GPU
- 基于CUDA的快速排序算法 需要NVIDIA显卡支持-Fast sorting algorithm based on CUDA NVIDIA graphics support needed
spmv_csr
- 稀疏矩阵的DIA/ELLPACK/COO/CSR/HYB表示形式，以及各表示形式下的稀疏矩阵乘法（稀疏大矩阵*矢量）的CUDA实现。对于矩阵中每一行稀疏元素个数较统一的情况，ELLPACK表示最佳，其次是HYB（ELL+COO）。 CUDA™ 是一种由NVIDIA推出的通用并行计算架构，该架构使GPU能够解决复杂的计算问题。 它包含了CUDA指令集架构（ISA）以及GPU内部的并行计算引擎。 开发人员现在可以使用C语言来为CUDA™ 架构编写程序-Sparse matri
LBM-C-0.1
- LBM-C is a lattice Boltzmann 2D and 3D fluid flow solver implemented using nVidia s CUDA platform. LBM-C is written in CUDA C and is licensed under GPL v2, you are invited to use, alter and improve upon LBM-C at your own discretion.
cuj2k-src-1.1
- A JPEG2000 encoder on CUDA - Converts BMP -> JPEG2000 with your NVIDIA GPU - Commandline tool and CUDA/C++ library - For both lossless and lossy encoding - One of the fastest open-source JPEG2000 encoder: Encodes a 27 megapixel -