Method and system for using dynamic random access memory as cache memory

A method of caching memory in a processor-based system, comprising:

• refreshing each of a plurality of memory blocks of a primary memory one at a time;
• if a first data is directed to be written into a first memory block of the plurality of memory blocks when the first memory block is being refreshed, storing the first data in a second memory;
• and
• after the first memory block has been refreshed, transferring the first data stored in the second memory to the first memory block.

A method of storing data, comprising:

• periodically refreshing at least a portion of a first memory;
• receiving a request to write first data to an address in either the first memory or a second memory;
• if the received request is a request to write the first data to an address in the first memory when at least a portion the first memory is being refreshed, storing the first data in the second memory;
• and
• after at least a portion the first memory has been refreshed, transferring the first data from the second memory to the first memory and storing the first data in the first memory.

A method of storing data in a first memory having a plurality of locations, at least some of which may be inaccessible at times, the method comprising:

• receiving a request to write first data to a first location in the first memory;
• if the request is a request to write the first data to the first location in the first memory that is currently inaccessible, storing the first data in the second memory;
• and
• when the first location in the first memory is no longer inaccessible, transferring the first data from the second memory to the first memory and storing the first data in the first location in the first memory.