Steven Li's Zone

Some basic concepts of GPU programming: Here is the overview of a GPU(Fermi Architecture)[1]:It is a 16-way many core (16 SM) GPU. Each way of many core has the architecture like t

This article is illustrated bases on 2.x computation device: Typically speaking, a shared memory has 16KB totally. And it has 32 banks for 2.x computation device. Bank is a unit of parallel read

Let us introduce a new term first[1]. It is the ratio of active warps / maximum number(32) of warps. It depends on three parameters: 1) threads/block (set in >>)2) registers/th

Consideration 1: Branch Divergence Before we talk about this, let us go through what is going on in GPU actually.Here is the abstract model of SM like[1]:Every SM has one con

Global memory coalescing: The storage pattern of global memory in GPU is row first pattern because there is not two dimension array in GPU. Use a matrix as an example[1]: Knowledge of

转载自：http://blog.youkuaiyun.com/jonny_super/article/details/23208227核函数是GPU每个thread上运行的程序。必须通过__gloabl__函数类型限定符定义。形式如下：                __global__ void kernel(param list){  }核函数只能在主机端调用，调用时必须申明执