Reduce data traffic between cache and memory via data access of variable sizes

A method, comprising:

• storing, in a first memory of a computing system, a block of data at a block of contiguous memory addresses in an address space;
• accessing, by a processor of the computing system, data using memory addresses in the address space;
• and
• in response to a request to cache the block of data stored in the first memory,
• communicating a first portion of the block of data from the first memory to a second memory of the computing system according to an item selection vector, wherein the item selection vector has a sequence of bits corresponding to a plurality of contiguous addresses for the block of data, and a count of bits in the item selection vector corresponds to a count of the plurality of contiguous addresses for the block of data;
• and
• caching, in the second memory of the computing system, the first portion of the block of data identified by the item selection vector;
• wherein in response to the request, the communicating of the first portion is performed according to the item selection vector without accessing a second portion of the block of data.

A non-transitory computer storage medium storing instructions which when executed in a computing system, cause the computing system to perform a method, the method comprising:

• storing, in a first memory of the computing system, a block of data at a block of contiguous memory addresses in an address space;
• accessing, by a processor of the computing system, data using memory addresses in the address space;
• and
• in response to a request to cache the block of data stored in the first memory,
• communicating a first portion of the block of data from the first memory to a second memory of the computing system according to an item selection vector without accessing a second portion of the block of data, wherein the item selection vector has a sequence of bits corresponding to a plurality of contiguous addresses for the block of data, and a count of bits in the item selection vector corresponds to a count of the plurality of contiguous addresses for the block of data;
• and
• caching, in the second memory of the computing system, the first portion of the block of data identified by the item selection vector;
• wherein in response to the request, the communicating of the first portion is performed according to the item selection vector without accessing the second portion of the block of data;
• and the second portion is communicated from the first memory to the second memory when an alternative item selection vector is used to cache the block of data.