Instruction predecoding
    1.
    发明授权

    公开(公告)号:US10176104B2

    公开(公告)日:2019-01-08

    申请号:US15281226

    申请日:2016-09-30

    Applicant: ARM LIMITED

    Abstract: An apparatus comprises processing circuitry, an instruction cache, decoding circuitry to decode program instructions fetched from the cache to generate macro-operations to be processed by the processing circuitry, and predecoding circuitry to perform a predecoding operation on a block of program instructions fetched from a data store to generate predecode information to be stored to the cache with the block of instructions. In one example the predecoding operation comprises generating information on how many macro-operations are to generated by the decoding circuitry for a group of one or more program instructions. In another example the predecoding operation comprises generating information indicating whether at least one of a given subset of program instructions within the prefetched block is a branch instruction.

    Cache hierarchy management
    3.
    发明授权

    公开(公告)号:US10268581B2

    公开(公告)日:2019-04-23

    申请号:US15479348

    申请日:2017-04-05

    Applicant: ARM Limited

    Abstract: A cache hierarchy and a method of operating the cache hierarchy are disclosed. The cache hierarchy comprises a first cache level comprising an instruction cache, and predecoding circuitry to perform a predecoding operation on instructions having a first encoding format retrieved from memory to generate predecoded instructions having a second encoding format for storage in the instruction cache. The cache hierarchy further comprises a second cache level comprising a cache and the first cache level instruction cache comprises cache control circuitry to control an eviction procedure for the instruction cache in which a predecoded instruction having the second encoding format which is evicted from the instruction cache is stored at the second cache level in the second encoding format. This enables the latency and power cost of the predecoding operation to be avoided when the predecoded instruction is then retrieved from the second cache level for storage in the first level instruction cache again.

Patent Agency Ranking