Multi-port shared cache apparatus

A method of controlling a cache memory accessible by a plurality of processes, comprising:

• accessing at least one line configuration identifying for each process of the plurality of processes a maximum number of cache lines that are able to be utilized by the each process;
• detecting a memory request from a process of the plurality of processes;
• determining, in response to detecting the memory request, that all cache lines of the plurality of cache lines have been utilized;
• determining, in response to all cache lines of the plurality of cache lines having been utilized, that the process has utilized its maximum allocation of cache lines;
• and
• in response to determining that all cache lines of the plurality of cache lines have been utilized and that the process has utilized its maximum allocation of cache lines:
• determining that a plurality of cache line replacement policies is available;
• identifying a cache line replacement policy from the plurality of cache line replacement policies configured for the process, wherein different cache line replacement policies are concurrently applied to different processes of the plurality of processes;
• and
• allocating, in accordance with the identified cache line replacement policy, a replacement cache line to the process only from a cache line currently allocated to and already used by the process, whereby allocating the replacement cache line to the process prevents the process from exceeding its maximum allocation of cache lines.

A non-transitory computer readable medium having computer executable instructions stored thereon which, when executed, perform a method of:

• accessing at least one line configuration identifying for each process of the plurality of processes a maximum number of cache lines that are able to be utilized by the each process;
• detecting a memory request from a process of the plurality of processes;
• determining, in response to detecting the memory request, that all cache lines of the plurality of cache lines have been utilized;
• determining, in response to all cache lines of the plurality of cache lines having been utilized, that the process has utilized its maximum allocation of cache lines;
• and
• in response to determining that all cache lines of the plurality of cache lines have been utilized and that the process has utilized its maximum allocation of cache lines:
• determining that a plurality of cache line replacement policies is available;
• identifying a cache line replacement policy from the plurality of cache line replacement policies configured for the process, wherein different cache line replacement policies are concurrently applied to different processes of the plurality of processes;
• and
• allocating, in accordance with the identified cache line replacement policy, a replacement cache line to the process only from a cache line currently allocated to and already used by the process, whereby allocating the replacement cache line to the process prevents the process from exceeding its maximum allocation of cache lines.