3 write miss policy, 4 write-back versus write-through – Intel NETWORK PROCESSOR IXP2800 User Manual
Page 101
Hardware Reference Manual
101
Intel
®
IXP2800 Network Processor
Intel XScale
®
Core
3.6.2.3.3
Write Miss Policy
A write operation that misses the cache, requests a 32-byte cache line from external memory if the
access is cacheable and write allocation is specified in the page; then, the following events occur:
1. The fill buffer is checked to see if an outstanding fill request already exists for that line.
— If so, the current request is placed in the pending buffer and waits until the previously
requested fill completes, after which it writes its data into the recently allocated cache
line.
— If there is no outstanding fill request for that line, the current store request is placed in the
fill buffer and a 32-byte external memory read request is made. If the pending buffer or fill
buffer is full, the Intel XScale
®
core will stall until an entry is available.
2. The 32 bytes of data can be returned back to the Intel XScale
®
core in any word order, i.e, the
eight words in the line can be returned in any order. Note that it does not matter, for
performance reasons, which order the data is returned to the Intel XScale
®
core since the store
operation has to wait until the entire line is written into the cache before it can complete.
3. When the entire 32-byte line has returned from external memory, a line is allocated in the
cache, selected by the round-robin pointer (see
). The line to be written into the
cache may replace a valid line previously allocated in the cache. In this case both dirty bits are
examined and if any are set, the four words associated with a dirty bit that’s asserted will be
written back to external memory as a 4-word burst operation. This write operation will be
placed in the write buffer.
4. The line is written into the cache along with the data associated with the store operation.
If the above condition for requesting a 32-byte cache line is not met, a write miss will cause a write
request to external memory for the exact data size specified by the store operation, assuming the
write request does not coalesce with another write operation in the write buffer.
3.6.2.3.4
Write-Back versus Write-Through
The Intel XScale
®
core supports write-back caching or write-through caching, controlled through
the MMU page attributes. When write-through caching is specified, all store operations are written
to external memory even if the access hits the cache. This feature keeps the external memory
coherent with the cache, i.e., no dirty bits are set for this region of memory in the data/mini-data
cache. This however does not guarantee that the data/mini-data cache is coherent with external
memory, which is dependent on the system level configuration, specifically if the external memory
is shared by another master.
When write-back caching is specified, a store operation that hits the cache will not generate a write
to external memory, thus reducing external memory traffic.