|Home > Execution stages of an OpenCL application > Executing the kernel > Determining the optimal global work size|
The global work size is the total number of work-items required for all dimensions combined.
You can change the global work size by processing multiple data items in a single work-item. The new global work size is then the original global work size divided by the number of data items processed by each work-item.
The global work size must be large if you want to ensure high performance. Typically, the number is several thousand, but the ideal number depends on the number of shader cores in your device.