搜索资源列表
VectorAdd
- 一个简单的基于CUDA的示例代码，使用SIMD的方法实现向量加法；运行在nVidia的G80系列显卡的GPGPU上；需要nVidia CUDA SDK，169以上版本的驱动。对于学习CUDA很有帮助。
CUDA_NVIDIA
- 3月25-27 NVIDIA 首席科学家DAVID KIRK CUDA技术讲座内容资料
cuda-memcheck-handbook-4.0cn
- CUDA调试工具cuda-gdb，包含一个可以在CUDA中检测和调试内存错误的内存检查特性。该文档描述了这个名为cuda-memcheck的工具与它的功能。 NVIDIA用它强大的cuda-gdb硬件调试器简化了CUDA程序错误的调试。然而，每个程序员总会遇到难以检测到的内存相关错误，并花大量时间去调试。当处理上千条线程时，内存相关的错误的数量会明显增加。cuda-memcheck就是设计用来检测你的CUDA程序中这种内存存取错误的工具。-CUDA debugging tool cud
matrixMul
- Nvidia GPU实现的矩阵相乘的并行算法程序，对学习CUDA技术的初学者有很强的借鉴作用-Nvidia GPU implementation of parallel matrix multiplication algorithm program for beginners to learn CUDA technology, have a strong reference
CUDA
- 学习NVIDIA公司GPU平台CUDA开发环境的好资料，可以大体上了解CUDA的运行环境和编程技巧-NVIDIA' s GPU platform to learn CUDA development environment good information, you can generally understand the CUDA runtime environment and programming skills
asyncAPI
- CUDA开发计算，异步计算接口。可以在主机与现存之间异步执行。来自NVIDIA SDK-CUDA development of computing, asynchronous computing interface. Can be asynchronous between the host and the existing implementation. From the NVIDIA SDK
fft2d_gpu
- using NVIDIA FFT CUDA Library to solve FFT problem
Mars_v2
- 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
NVIDIA_GT200
- 介绍NVIDIA s GT200 GPU的硬件架构，以及CUDA编程模型与GPU硬件实现之间的联系，是理解CUDA运行机理的一篇好文章！-The architeture of NVIDIA s GT200 GPU was Introduced in this paper, And the relationship between CUDA and GPU hardware was indicated. We could get more details of CUDA process in th
CUDA
- 面向大学的课件，介绍NVIDIA公司GPU在CDUA平台下的编程方法，是快速进入研究计算机并行计算的优秀课件，全英文的-For university courseware to introduce NVIDIA' s GPU programming platform in CDUA method is quick access to the best of parallel computing research computer courseware, all in English
An-Introduction-to-GPGPU-Programming
- Nvidia资深工程师编写的CUDA入门书籍，非常简明清晰。是快速掌握CUDA并行计算精髓的小手册！-Nvidia CUDA senior engineers started writing the book, very clear and concise. CUDA parallel computing is to grasp the essence of the booklet!
CUDA_BLASTP-2.0.tar
- CUDA_BLASTP 2.0.tar.gz support Nvidia CUDA need nvidia gpu card
GPU-HMMER-0.92.tar
- GPU-HMMER-0.92.tar.gzsupport Nvidia CUDA need nvidia gpu card
cuda_match
- 使用NVIDIA的CUDA并行架构下的模板匹配，效率比openCV的有很大提升-Template matching using the NVIDIA CUDA parallel architecture, enhance efficiency than openCV
CUDA
- 这是英伟达公司CUDA语言开发包中最重要的几个源文件。其中cufft是快速傅里叶变换的源文件。 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，C语言是应用最广泛的一种高级编程语言。所编写出的程序于是就可以在支持CUDA™ 的处理器上以超高性能运行。 -CUDA™ is a parallel computing platform and programming model invented
cuda
- 文档是从http://cudazone.nvidia.cn/forum/forum.php?mod=viewthread&tid=6266&extra=page=1下载来的，是“yyfn风辰”翻译的文档，原文档是装好cuda sdk后名字为“CUDA_C_Programming_Guide.pdf”的文档-Document is downloaded to from http://cudazone.nvidia.cn/forum/forum.php?mod=viewthread&tid=6266
cudaVectorAdd
- 英伟达公司CUDA架构下图形处理器GPU编程模型，方便CUDA学习者使用-Nvidia CUDA Programming
CudaPad
- CudaPAD is a PTX/SASS viewer for NVIDIA Cuda kernels -CudaPAD is a PTX/SASS viewer for NVIDIA Cuda kernels Introduction CudaPAD is software that aids in the optimizing and understanding of NVidia’s Cuda kernels by displaying an on-the-fly vi
CUDA code
- CUDA(Compute Unified Device Architecture)，是显卡厂商NVIDIA推出的运算平台。 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。(CUDA (Compute Unified Device Architecture), is the graphics platform NVIDIA's computing platform. CUDA is a general purpose parallel computi
4_GPUIntro
- GPU 基本介绍 包括GPU与GPGPU的兴起，GPU加速与高性能计算，Nvidia CUDA简介。(The Basic Introduction of GPU)