Related Resources

CUDA Indexing

Jan 25, 2017
By Mark Harris
Discuss (0)

Figure 1: The CUDA parallel thread hierarchy. CUDA executes kernels using a grid of blocksof threads. This figure shows the common indexing pattern used in CUDA programs using the CUDA keywords gridDim.x (the number of thread blocks), blockDim.x (the number of threads in each block), blockIdx.x (the index the current block within the grid), and threadIdx.x (the index of the current thread within the block).

Figure 1: The CUDA parallel thread hierarchy. CUDA executes kernels using a grid of blocksof threads. This figure shows the common indexing pattern used in CUDA programs using the CUDA keywords gridDim.x (the number of thread blocks), blockDim.x (the number of threads in each block), blockIdx.x (the index the current block within the grid), and threadIdx.x (the index of the current thread within the block).

Discuss (0)

Tags

About the Authors

About Mark Harris
Mark is an NVIDIA Distinguished Engineer working on RAPIDS. Mark has over twenty years of experience developing software for GPUs, ranging from graphics and games, to physically-based simulation, to parallel algorithms and high-performance computing. While a Ph.D. student at The University of North Carolina he recognized a nascent trend and coined a name for it: GPGPU (General-Purpose computing on Graphics Processing Units).
Follow @harrism on Twitter

Comments

Comments are closed.