CUDA Thread Indexing-白红宇

CUDA Thread Indexing

阅读量：5238 次

发布时间：2019-06-14

本文共 2223 字，大约阅读时间需要 7 分钟。

1D grid of 1D blocks__device__ int getGlobalIdx_1D_1D(){return blockIdx.x *blockDim.x + threadIdx.x;}1D grid of 2D blocks__device__ int getGlobalIdx_1D_2D(){return blockIdx.x * blockDim.x * blockDim.y + threadIdx.y * blockDim.x + threadIdx.x;}1D grid of 3D blocks__device__ int getGlobalIdx_1D_3D(){return blockIdx.x * blockDim.x * blockDim.y * blockDim.z + threadIdx.z * blockDim.y * blockDim.x + threadIdx.y * blockDim.x + threadIdx.x;}{return blockIdx.x * blockDim.x * blockDim.y * blockDim.z + threadIdx.z * blockDim.y * blockDim.x + threadIdx.y * blockDim.x + threadIdx.x;}2D grid of 1D blocks __device__ int getGlobalIdx_2D_1D(){int blockId   = blockIdx.y * gridDim.x + blockIdx.x; int threadId = blockId * blockDim.x + threadIdx.x; return threadId;}{int blockId   = blockIdx.y * gridDim.x + blockIdx.x; int threadId = blockId * blockDim.x + threadIdx.x; return threadId;}2D grid of 2D blocks  __device__ int getGlobalIdx_2D_2D(){int blockId = blockIdx.x + blockIdx.y * gridDim.x; int threadId = blockId * (blockDim.x * blockDim.y) + (threadIdx.y * blockDim.x) + threadIdx.x;return threadId;}2D grid of 3D blocks__device__ int getGlobalIdx_2D_3D(){int blockId = blockIdx.x + blockIdx.y * gridDim.x; int threadId = blockId * (blockDim.x * blockDim.y * blockDim.z)  + (threadIdx.z * (blockDim.x * blockDim.y))  + (threadIdx.y * blockDim.x)  + threadIdx.x;return threadId;}3D grid of 1D blocks__device__ int getGlobalIdx_3D_1D(){int blockId = blockIdx.x + blockIdx.y * gridDim.x + gridDim.x * gridDim.y * blockIdx.z; int threadId = blockId * blockDim.x + threadIdx.x;return threadId;}3D grid of 2D blocks__device__ int getGlobalIdx_3D_2D(){int blockId = blockIdx.x         + blockIdx.y * gridDim.x + gridDim.x * gridDim.y * blockIdx.z; int threadId = blockId * (blockDim.x * blockDim.y) + (threadIdx.y * blockDim.x) + threadIdx.x;return threadId;}3D grid of 3D blocks__device__ int getGlobalIdx_3D_3D(){int blockId = blockIdx.x + blockIdx.y * gridDim.x + gridDim.x * gridDim.y * blockIdx.z; int threadId = blockId * (blockDim.x * blockDim.y * blockDim.z) + (threadIdx.z * (blockDim.x * blockDim.y)) + (threadIdx.y * blockDim.x) + threadIdx.x;return threadId;}

转载于:https://www.cnblogs.com/tibetanmastiff/p/4639194.html

你可能感兴趣的文章