Data prefetching for graphics data processing

One or more non-transitory computer-readable storage mediums having stored thereon executable computer program instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

• receiving a command to load block instructions in instruction code for a graphics processing unit (GPU) in a computing system;
• commencing execution by the GPU of a current kernel for an application, a driver for the application being aware of a next kernel for the application to follow the current kernel;
• and
• upon commencing execution of the current kernel, issuing a prefetch for an instruction cache utilizing a hardware prefetcher in the computing system, the prefetch being of the next kernel for execution by the GPU, the prefetch for the next kernel being made directly into the instruction cache.

A method comprising:

• receiving a command to load block instructions in instruction code for a graphics processing unit (GPU) in a computing system;
• commencing execution by the GPU of a current kernel for an application, a driver for the application being aware of a next kernel for the application to follow the current kernel;
• and
• upon commencing execution of the current kernel, issuing a prefetch for an instruction cache utilizing a hardware prefetcher in the computing system, the prefetch being of the next kernel for execution by the GPU, the prefetch for the next kernel being made directly into the instruction cache.