-
-
Save onionmk2/854c333829f047a5e86cfab5a0ccae3a to your computer and use it in GitHub Desktop.
cuda のid計算がよくわからないので、まとめてみる。
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
//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; | |
} | |
//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; | |
} | |
//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; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
任意1..3の次元数でidを求めるためのすべての関数は、最初のコミット
https://gist.github.com/onionmk2/854c333829f047a5e86cfab5a0ccae3a/7bcd4a696f1f08319ea0564975ed962ce61a484d
に記載がある。