Block addressing for parallel memory arrays

A method of accessing data from a memory device, the method comprising:

• retrieving first data from a first memory array of the memory device and loading the first data to a first cache register of the memory device;
• receiving at least a block portion of logical addresses originating from a processor, wherein the block portion corresponds to an address range for selecting blocks of memory;
• modifying the received block portion of the logical addresses to generate first modified addresses for the first memory array and second modified addresses for a second memory array for a contiguous logical addresses space;
• pairing blocks of memory from the first memory array and the second memory array for simultaneous access even when the blocks have disparate physical addresses, wherein pairing blocks of the first memory array and the second memory array comprises:
• identifying good blocks and bad blocks of the first memory array and good blocks and bad blocks of the second memory array;
• mapping a good block at a starting physical address of the first memory array with a good block at a starting address of the second memory array;
• and
• consecutively stepping through physical addresses of the first memory array and the second memory array, mapping a next good block of the first memory array with a next good block of the second memory array, skipping only bad blocks of the first memory array and bad blocks of the second memory array, until all good blocks of the first memory array or the second memory array are paired;
• wherein accesses to pages from paired blocks are interleaved;
• and
• providing the first data from the first cache register to a data bus while retrieving second data from the second memory array of the memory device and loading the second data to a second cache register of the memory device.

An apparatus comprising:

• a host processor;
• and
• a memory device comprising:
• a plurality of memory arrays including at least a first memory array and a second memory array;
• an address translator configured to receive at least a block portion of logical addresses originating from a processor, wherein the block portion corresponds to an address range for selecting blocks of memory, wherein the address translator is configured to modify the received block portion of the logical addresses to generate first modified addresses for the first memory array and second modified addresses for the second memory array for a contiguous logical addresses space;
• wherein blocks of memory from the first memory array and the second memory array are paired for simultaneous access even when the blocks have disparate physical addresses, wherein pairing blocks from the first memory array and the second memory array is performed by:
• identifying good blocks and bad blocks of the first memory array and good blocks and bad blocks of the second memory array;
• mapping a good block at a starting physical address of the first memory array with a good block at a starting address of the second memory array;
• and
• consecutively stepping through physical addresses of the first memory array and the second memory array, mapping a next good block of the first memory array with a next good block of the second memory array, skipping only bad blocks of the first memory array and bad blocks of the second memory array, until all good blocks of the first memory array or the second memory array are paired;
• wherein accesses to pages from paired blocks are interleaved;
• and
• a plurality of cache registers including at least a first cache register and a second cache register, wherein the first cache register is disposed in a first signal path between a bus and the first memory array, wherein the second cache register is disposed in a second signal path between the bus and the second memory array, wherein the first cache register is configured to be able to provide first data originally retrieved from the first memory array to a data bus while the second cache register is retrieving second data from the second memory array.