Apparatus and method for filtering unused sub-blocks in cache memories

A memory system, comprising:

• a cache comprising:
• a filtered portion which stores information in blocks;
• and
• an unfiltered portion, which stores information in sub-blocks;
• transfer logic, which evicts blocks from the unfiltered portion in accordance with a policy such that the blocks evicted from the filtered portion have used sub-blocks thereof cached in the unfiltered portion for servicing requests and unused sub-blocks of the blocks are evicted from the filtered portion.

A method for caching information, comprising the steps of:

• dividing a cache into a filtered portion and an unfiltered portion, the filtered portion including block sized components and the unfiltered portion including sub-block sized components;
• evicting a block from the unfiltered portion in accordance with a policy such that blocks evicted from the filtered portion have selected used sub-blocks thereof cached in the unfiltered portion;
• and
• maintaining the selected used sub-blocks in the filtered portion in accordance with the policy.

A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for caching information, the method steps comprising:

• dividing a cache into a filtered portion and an unfiltered portion, the filtered portion including block sized components and the unfiltered portion including sub-block sized components;
• evicting a block from the unfiltered portion in accordance with a policy such that blocks evicted from the filtered portion have selected used sub-blocks thereof cached in the unfiltered portion;
• and
• maintaining the selected used sub-blocks in the filtered portion in accordance with the policy.

A hierarchical cache memory system, comprising:

• a first level cache comprising:
• a filtered portion and an unfiltered portion,
• the filtered portion divided into block sized components and including a usage bit to indicate that selected blocks evicted from the filtered portion have been previously used;
• and
• the unfiltered portion divided into sub-block sized components such that blocks evicted from the filtered portion have selected sub-blocks thereof cached in the unfiltered portion for servicing requests;
• a second level cache comprising a directory for storing a usage pattern based upon usage bits such that if a miss occurs in the level one cache, blocks indicated as used by the usage bits are provided to the level one cache.