-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/2001/
-----------------------------------------------------------

Review request for Default.


Repository: gem5


Description
-------

Allow forcing tagged prefetches for IFETCH requests given to stride prefetchers.

For systems with a tightly coupled L2, a stride-based prefetcher may observe 
access requests from both instruction and data L1 caches.  However, the PC 
address of an instruction miss gives no relevant training information to the 
stride based prefetcher(there is no stride to train).  In theses cases, its 
better if the L2 stride prefetcher simply reverted back to a simple N-block 
ahead prefetcher.  This patch enables this option.

Note: This patch relies upon the earlier patch submitted in review request 
#2000.

Negligibly improves performance on SPEC, but SPEC isn't an instruction 
footprint heavy suite.


Diffs
-----

  src/mem/cache/prefetch/Prefetcher.py a317086a3e19 
  src/mem/cache/prefetch/stride.hh a317086a3e19037a2b0c8332b7cb8c411aab390d 
  src/mem/cache/prefetch/stride.cc a317086a3e19 

Diff: http://reviews.gem5.org/r/2001/diff/


Testing
-------


Thanks,

Mitch Hayenga

_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev

Reply via email to