Cuda,3d 块中的执行线程顺序 [英] Cuda, executional thread order in a 3d-block
问题描述
作为标题,我想知道正确的执行顺序,以防我们有 3d 块
As title, I would like to know the right execution order in case we have a 3d block
我想记得我已经读过一些关于它的东西,但那是前一段时间,我不记得在哪里,但它是由一个看起来不那么可靠的人来的..
I think to remember that I read already something regarding it, but it was some time ago, I dont remember where but it was coming by someone who didnt look so reliable..
无论如何,我想对此进行一些确认.
Anyway I would like to have some confirmations about it.
是不是如下(分经)?
[0, 0, 0]...[blockDim.x, 0, 0] - [0, 1, 0]...[blockDim.x, 1, 0] - (...) - [0, blockDim.y, 0]...[blockDim.x, blockDim.y, 0] - [0, 0, 1]...[blockDim.x, 0, 1] - (...) - [0, blockDim.y, 1]...[blockDim.x, blockDim.y, 1] - (...) - [blockDim.x, blockDim.y, blockDim.z]
[0, 0, 0]...[blockDim.x, 0, 0] - [0, 1, 0]...[blockDim.x, 1, 0] - (...) - [0, blockDim.y, 0]...[blockDim.x, blockDim.y, 0] - [0, 0, 1]...[blockDim.x, 0, 1] - (...) - [0, blockDim.y, 1]...[blockDim.x, blockDim.y, 1] - (...) - [blockDim.x, blockDim.y, blockDim.z]
推荐答案
是的,这是正确的顺序;线程按照块内的 x 维度首先变化,然后是 y,然后是 z(相当于列优先顺序)进行排序.计算可以表示为
Yes, that is the correct ordering; threads are ordered with the x dimension varying first, then y, then z (equivalent to column-major order) within a block. The calculation can be expressed as
int threadID = threadIdx.x +
blockDim.x * threadIdx.y +
(blockDim.x * blockDim.y) * threadIdx.z;
int warpID = threadID / warpSize;
int laneID = threadID % warpsize;
这里threadID
是block内的线程号,warpID
是block内的warp,laneID
是warp内的线程号.
Here threadID
is the thread number within the block, warpID
is the warp within the block and laneID
is the thread number within the warp.
请注意,线程不一定以与块内此顺序相关的任何可预测顺序执行.执行模型保证同一个warp中的线程被锁步"执行,但是你不能从块内的线程编号推断出更多.
Note that threads are not necessarily executed in any sort of predicable order related to this ordering within a block. The execution model guarantees that threads in the same warp are executed "lock-step", but you can't infer any more than that from the thread numbering within a block.
这篇关于Cuda,3d 块中的执行线程顺序的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!