1 / 7

Intro to cache memory

Intro to cache memory. Kosarev Nikolay MIPT Nov, 200 9. Agenda. Cache Placement of cache block Searching of data in the cache Replacement policies Write policies. Cache. Cache is a buffer for storing of data copies for rapid access

jorn
Télécharger la présentation

Intro to cache memory

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Intro to cache memory Kosarev Nikolay MIPT Nov, 2009

  2. Agenda • Cache • Placement of cache block • Searching of data in the cache • Replacement policies • Write policies

  3. Cache Cache is a buffer for storing of data copies for rapid access • Takes advantage of the principle of locality (temporal, spatial) • Consists of blocks / lines (portions of data retrieved from the main memory) • Each block has an address tag (address of the block in the main memory) • Hit (Miss) – data was found (wasn’t found) in the cache

  4. Placement of cache block 3 types of cache • Direct mapped: (block address) mod (blocks in cache) • Set associative: (block address) mod (sets in cache) • Fully associative 2-way set associative cache

  5. Searching of data Processor address is analyzed • Index field selects the set • Tag is compared against all blocks in set for a hit • Offset field selects data from the block • Note: all address tags are searched in parallel • Cache HIT access time is critical

  6. Replacement policies 3 frequently used algorithms • Random • Simple to implement • Least recently used (LRU) • Block unused for the longest time is replaced • Complicated to calculate -> approximated • First in first out (FIFO) • The oldest block is replaced

More Related