CUDA Thread Indexing
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 | 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; } |
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】凌霞软件回馈社区,博客园 & 1Panel & Halo 联合会员上线
【推荐】抖音旗下AI助手豆包,你的智能百科全书,全免费不限次数
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步