Method and apparatus for using compression to improve performance of low voltage caches

A cache device, comprising:

• an input configured to receive a memory access request;
• replacement logic circuitry coupled with the input and a data array of the cache, wherein the replacement logic circuitry is configured to:
• in response to receiving the memory access request at the input, determine compressibility of data specified by the request,
• select in the data array a destination portion for storing the data based on the compressibility of the data and a persistent fault history of the destination portion, and
• store a compressed copy of the data in a non-faulted subportion of the destination portion, wherein the persistent fault history indicates that the non-faulted subportion excludes any persistent faults;
• a compression engine circuit coupled with the replacement logic circuitry and configured to generate the compressed copy of the data;
• and
• control logic circuitry configured to:
• prior to the receiving of the memory access request, allocate error protection data for protecting prior data stored in the destination portion, and
• in response to storing the compressed copy of the data in the non-faulted subportion of the destination portion, reallocating the error protection data for protecting other data in a different portion of the cache having one or more persistent faults.

A computing device, comprising:

• one or more processing cores;
• and
• a set of one or more cache devices, wherein each cache device in the set of one or more cache devices is coupled with a processing core of the one or more processing cores and is configured to:
• in response to receiving a memory access request from the processing core, determine compressibility of data specified by the request;
• select in the cache device a destination portion for storing the data based on the compressibility of the data and a persistent fault history of the destination portion;
• store a compressed copy of the data in a non-faulted subportion of the destination portion, wherein the persistent fault history indicates that the non-faulted subportion excludes any persistent faults;
• prior to the receiving of the memory access request, allocate error protection data for protecting prior data stored in the destination portion;
• and
• in response to storing the compressed copy of the data in the non-faulted subportion of the destination portion, reallocating the error protection data for protecting other data in a different portion of the cache having one or more persistent faults.