CUDA
seamanj
这个作者很懒,什么都没留下…
展开
-
stop auto remove cuda
It depends on how you installed CUDA. If you ran sudo apt-get install , and that package was removed, then CUDA, an automatically installed package, becomes automatically removable. The simple fix is to mark the CUDA packages as manually installed:sudo .转载 2021-10-22 19:02:09 · 161 阅读 · 0 评论 -
matlab中cuda编程中分配grid和block dimension的时候的注意事项
这两天在MATLAB里面用CUDA, 结果老是不对, 找了半天才发现, 原来是分配的问题所以提醒小伙伴们, 分配的时候先看下你的GPU性能>> gpuDeviceans = CUDADevice (具有属性): Name: 'Quadro K2000' Index:原创 2016-11-09 04:54:51 · 2048 阅读 · 0 评论 -
GPU CUDA and MEX Programming
https://uk.mathworks.com/help/distcomp/gpu-cuda-and-mex-programming.htmlmxGPUCopyFromMxArrayCopy mxArray to mxGPUArraymxGPUCopyGPUArrayDuplicate (deep copy) mxGPU转载 2016-11-09 06:28:20 · 1178 阅读 · 0 评论 -
install cuda on ubuntu
Install repository meta-data Note: When using a proxy server with aptitude, ensure thatwget is set up to use the same proxy settings before installing the cuda-repo package. $ sudo dpkg -i cuda-re...原创 2015-11-12 21:52:27 · 510 阅读 · 0 评论 -
How do CUDA blocks/warps/threads map onto CUDA cores?
https://stackoverflow.com/questions/10460742/how-do-cuda-blocks-warps-threads-map-onto-cuda-coreshttp://www.nvidia.com/content/PDF/fermi_white_papers/NVIDIA_Fermi_Compute_Architecture_Whitepaper转载 2017-10-31 19:25:18 · 345 阅读 · 0 评论 -
shared memory global memory constant memory in cuda
http://cuda-programming.blogspot.co.uk/2013/01/shared-memory-and-synchronization-in.htmlhttp://cuda-programming.blogspot.co.uk/2013/01/what-is-constant-memory-in-cuda.html转载 2017-10-31 04:27:17 · 337 阅读 · 0 评论 -
how to compile kinfu_remake with cuda 9.0 opencv2.4.13.4
1. download from the git :https://github.com/Nerei/kinfu_remake.gitupdate on 15, Oct.before compile opencv, please install libgtk2.0-dev and pkg-config first2. As cuda 9.0 splits nppi in...原创 2017-10-24 21:09:41 · 1106 阅读 · 1 评论 -
When to use volatile with shared CUDA Memory
Under what circumstances should you use the volatile keyword with a CUDA kernel's shared memory? I understand that volatile tells the compiler never to cache any values, but my question is about t转载 2017-11-06 05:30:52 · 323 阅读 · 0 评论 -
cuda更新过后, findcuda找不到怎么办?
https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#mandatory-post7.1. Mandatory Actions Some actions must be taken after the installation before the CUDA Toolkit and Driver can b...原创 2018-08-07 17:27:23 · 2097 阅读 · 0 评论 -
scatter and gather in thrust
#include <thrust/scatter.h>#include <thrust/device_vector.h>#include <thrust/execution_policy.h>...// mark even indices with a 1; odd indices with a 0int values[10] = {1, 0, 1, ...原创 2018-10-09 06:53:48 · 949 阅读 · 0 评论 -
CUDA里面GRID, BLOCK 边界检测
dim3 block(BLOCK_X, BLOCK_Y);dim3 grid((roi.width + block.x - 1) / block.x, (roi.height + block.y - 1) / block.y);int y = blockIdx.y * blockDim.y + threadIdx.y;int x = blockIdx.x * blockDim.x + th原创 2016-11-07 21:33:42 · 1469 阅读 · 0 评论 -
mexcuda输入nvcc中的参数
mexcuda -v COMPFLAGS="-arch=sm_30" show_neighbor.cu原创 2016-11-07 17:54:03 · 752 阅读 · 0 评论 -
mexcuda中矩阵数据的传输
数据的传输以0开始,然后以列序传输/* * Example of how to use the mxGPUArray API in a MEX file. This example shows * how to write a MEX function that takes a gpuArray input and returns a * gpuArray output, e.g. B原创 2016-11-07 17:52:49 · 998 阅读 · 0 评论 -
Lesson 1 Hello World
装好CUDA后,我们在cmd里面运行nvcc --version原创 2015-11-05 02:28:17 · 615 阅读 · 0 评论 -
QT+CUDA7.5+UBUNTU14.04
接着前面有篇文章介绍在windows上面对他们进行合成,这篇文章我们介绍下在ubuntu上面对其合成。程序用的是brown大学里面snow-master,该project包括了几个项目,其中有个CUDA_helloworld刚好可以拿来练手CUDA在ubuntu上面的安装我就不多介绍,攻略帖一大堆下面开始介绍下这个项目main.cpp内容如下:#原创 2015-12-03 04:24:19 · 2463 阅读 · 2 评论 -
Lesson2 Square number
//filename: square.cu// By Seamanj 04/11/2015 @NCCA #include __global__void square(float * d_out, float * d_in){ int idx = threadIdx.x; float f = d_in[idx]; d_out[idx] = f * f;}int main(原创 2015-11-05 04:31:47 · 537 阅读 · 0 评论 -
lesson3 some important things in CUDA
40For a 128*128 image, there are different strategies to create specified number of blocks and threads to compute value in each pixel in parallel. For example, we could allocate 128 bloc原创 2016-09-01 21:46:09 · 791 阅读 · 0 评论 -
lesson 4 communication pattern
For the fourth one, we choose to pick Gather rather than D, because this operation is not applied to every element.原创 2016-09-02 22:00:12 · 587 阅读 · 0 评论 -
lesson 6 threads synchronization
原创 2016-09-02 22:43:20 · 314 阅读 · 0 评论 -
lesson 5 memory model
92原创 2016-09-02 22:31:32 · 353 阅读 · 0 评论 -
lesson 7 strategies for efficient CUDA programming
原创 2016-09-03 01:21:59 · 354 阅读 · 0 评论 -
using cuda7.0 in matlab2015b with vs2013 compiler
the tutorial is from the officail website:http://uk.mathworks.com/help/distcomp/run-mex-functions-containing-cuda-code.htmlHowever, there are many problems when I was running command : mexcuda原创 2016-09-08 00:59:26 · 2137 阅读 · 0 评论 -
CUDA + QT Creator + Win7的集成
最近看到brown大学一位同学做的demo简直是牛B,里面居然实现了物体的移动轴,旋转圈等,跟MAYA界面差不多,一直想找一个这样的GUI,找不到,没办法,自己做吧,所以决心学下QT,当然这位同学的程序中用到了CUDA,为了调通他的程序,我又只好硬着头皮去搞下CUDA,花了二天时间,终于把它带的CUDA helloworld程序调通了注意这里QT creator里面的调试器用的VS20原创 2015-11-05 01:13:41 · 7085 阅读 · 5 评论