Abstract: Examples described herein generally relate to indicating resource utilization by a graphics processing unit (GPU). Data indicating a hierarchy of architectural units for executing processing threads on a GPU can be obtained. An indication of a slot assigned to a collection of threads for executing on the GPU can be received, where the slot is associated with a single instruction multiple data (SIMD) module capable of concurrently executing multiple collections of threads. An architectural unit to which the slot is assigned can be determined based on the data indicating the hierarchy of architectural units. An indication of the architectural unit as executing the collection of threads can be outputted.

Abstract: Examples described herein generally relate to indicating resource utilization by a graphics processing unit (GPU). Data indicating a hierarchy of architectural units for executing processing threads on a GPU can be obtained. An indication of a slot assigned to a collection of threads for executing on the GPU can be received, where the slot is associated with a single instruction multiple data (SIMD) module capable of concurrently executing multiple collections of threads. An architectural unit to which the slot is assigned can be determined based on the data indicating the hierarchy of architectural units. An indication of the architectural unit as executing the collection of threads can be outputted.