| Electronic Components Datasheet Search |
|
SH7616 Datasheet(PDF) 399 Page - Renesas Technology Corp |
|
|
|||||||||||||||||||||||||||||
SH7616 Datasheet(HTML) 399 Page - Renesas Technology Corp |
|
399 / 935 page ![]() Section 8 Cache Rev. 2.00 Mar 09, 2006 page 373 of 906 REJ09B0292-0200 To purge the cache using program logic, the data updates are detected by the program flow and the cache is then purged. For example, if the program inputs data from a disk, whenever reading of a unit (such as a sector) is completed, the buffer address used for reading or the entire cache is purged, thereby maintaining coherency. When data is to be exchanged between two processors, only flags that provide mutual notification of completion of data preparation or completion of a fetch are placed in the cache-through area. The data actually to be transferred is placed in the cache area and the cache is purged before the first data read to maintain the coherency of the data. When semaphores are used as the means of communication, data coherency can be maintained even when the cache is not purged by utilizing the TAS instruction. Direct external access must always be used for a TAS instruction read. When the update unit is small, specific addresses can be purged, so only the relevant addresses are purged. When the update unit is larger, it is faster to purge the entire cache rather than purging all the addresses in order, and then read the data that previously existed in the cache again from external memory. When write-back is used, coherency can be maintained by executing write-backs (flushing) to memory by means of intentional cache miss reads, but since executing flushing incurs an overhead, use of write-through or accessing the cache-through area is recommended in a system in which a number of masters share memory. 8.5.4 Two-Way Cache Mode The 4-kbyte cache can be used as 2-kbyte RAM and 2-kbyte mixed instruction/data cache memory by setting the TW bit in CCR to 1. Ways 2 and 3 become cache, and ways 0 and 1 become RAM. Initialization is performed by writing 1 to the CP bit in CCR, in the same way as with 4 ways. The valid bit, and LRU bits are cleared to 0. When LRU information is initialized to zero, the initial order of use is way 3 → way 2. Thereafter, way 3 or way 2 is selected for replacement in accordance with the LRU information. The conditions for updating the LRU information are the same as for four-way mode, except that the number of ways is two. When designated as 2-kbyte RAM, ways 0 and 1 are accessed by data array access. Figure 8.16 shows the address mapping. |
|
Link URL |
| Does ALLDATASHEET help your business so far? [ DONATE ] |
About Alldatasheet | Advertisement | Contact us | Privacy Policy | Link to Datasheet | Link Exchange | Manufacturer List All Rights Reserved©Alldatasheet.com |
| Russian : Alldatasheetru.com | Korean : Alldatasheet.co.kr | Spanish : Alldatasheet.es | French : Alldatasheet.fr | Italian : Alldatasheetit.com Portuguese : Alldatasheetpt.com | Polish : Alldatasheet.pl | Vietnamese : Alldatasheet.vn Indian : Alldatasheet.in | Mexican : Alldatasheet.com.mx | British : Alldatasheet.co.uk | New Zealand : Alldatasheet.co.nz |
|
Family Site : ic2ic.com |
icmetro.com |