Caching of virtual to physical address translations

A method of storing virtual to physical address translations in a plurality of caches comprising a first cache and a second cache, wherein said first cache can be accessed during an access cycle in response to receipt of a request for an address translation, and said second cache can be accessed during said same access cycle in response to receipt of said request for said address translation from said initiator device the method comprising the steps of:

• receiving a request for a virtual to physical address translation from an initiator device;
• in response to determining that said address translation is not stored in one of said first cache and said second cache:
• retrieving said translation from a lower hierarchical data store and also retrieving a translation for a predicted subsequently required virtual address while accessing said lower hierarchical data store;
• and
• updating said first cache with said retrieved translation and said second cache with said retrieved predicted subsequently required translation in a same access cycle.

A data processing apparatus comprising:

• at least one initiator means for issuing transactions,
• a hierarchical memory system comprising a plurality of caches, a memory, and means for controlling memory access,
• said initiator means being configured to identify storage locations using virtual addresses,
• said hierarchical memory system being configured to store data using physical addresses,
• said means for controlling memory access being configured to control virtual address to physical address translations;
• wherein
• said plurality of caches comprise a first means for caching and a second means for caching;
• said first means for caching configured to store a plurality of address translations of virtual to physical addresses that said initiator means has requested;
• said second means for caching configured to store a plurality of address translations of virtual to physical addresses that it is predicted that said initiator means will subsequently request;
• wherein:
• said first and second caching means are arranged in parallel with each other such that said first caching means can be accessed during an access cycle in response to receipt of a request for an address translation from said initiator means, and said second caching means can be accessed during said same access cycle in response to receipt of said request for said address translation from said initiator means;
• and
• said means for controlling memory access is configured, in response to receipt of said request for said address translation from said initiator means, to look for said translation in said first means for caching and said second means for caching and in response to said requested translation not being present:
• to retrieve said translation from a lower hierarchical data storage means and
• to retrieve a translation for a predicted subsequently required virtual address while accessing said lower hierarchical data storage means and
• to update said first means for caching with said retrieved translation and said second means for caching with said retrieved predicted subsequently required translation at a same time.