Abstract: A processing apparatus is described. The apparatus includes a central processing unit (CPU), a graphics processing unit (GPU) and data sharing logic to perform static physical data sharing between the CPU and the GPU by changing code written for the GPU to operate with CPU variables.

Abstract: Execution of a first kernel may be offloaded from a central processing unit to a graphics processing unit using a ring task buffer with a fixed number of task slots incurring full overhead of runtime driver interaction. Execution of a second kernel is offloaded using said ring task buffer, so at least two kernels may be offloaded from a central processing unit to a graphics processing unit via said ring task buffer, while incurring about the same offloading overhead as would be incurred from offloading a single kernel, in some embodiments. Multiple kernels are automatically grouped together by a compiler and linker.

Abstract: A processing apparatus is described. The apparatus includes a central processing unit (CPU), a graphics processing unit (GPU) and data sharing logic to perform static physical data sharing between the CPU and the GPU by changing code written for the GPU to operate with CPU variables.

Abstract: A method of performing transactions in a code management software system. The method includes starting a transaction, determining existence of a state table for a workspace, creating the state table for the workspace if the state table does not exist, updating the state table for the workspace, and comparing a state table of a first workspace with a state table of a second workspace. A list of names of different files is created from the comparison of the state table of the first workspace and the state table of the second workspace. The list of names of different files is accessed during a match files phase. The state table is updated if the workspace is modified prior to an end of the transaction. The code management system is accessed using a graphical user interface.