-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/2471/
-----------------------------------------------------------

Review request for Default.


Repository: gem5


Description
-------

Note: This was orginally posted by Derek Hower as:
http://reviews.m5sim.org/r/1622/

I've updated the patch to work with the tip of the repository and done some 
simple testing on it.

Thanks,
Marc

Changeset 10501:d945f688d61f
---------------------------
x86 isa: This patch attempts an implementation at mwait.

Mwait works as follows:
1. A cpu monitors an address of interest (monitor instruction)
2. A cpu calls mwait - this loads the cache line into that cpu's cache.
3. The cpu goes to sleep.
4. When another processor requests write permission for the line, it is
   evicted from the sleeping cpu's cache. This eviction is forwarded to the
   sleeping cpu, which then wakes up.


Diffs
-----

  configs/ruby/MESI_Two_Level.py 5e0a421e2031 
  configs/ruby/MESI_Three_Level.py 5e0a421e2031 
  configs/ruby/MI_example.py 5e0a421e2031 
  configs/ruby/MOESI_CMP_directory.py 5e0a421e2031 
  configs/ruby/MOESI_CMP_token.py 5e0a421e2031 
  configs/ruby/MOESI_hammer.py 5e0a421e2031 
  configs/ruby/Ruby.py 5e0a421e2031 
  src/arch/x86/isa/decoder/two_byte_opcodes.isa 5e0a421e2031 
  src/arch/x86/isa/formats/formats.isa 5e0a421e2031 
  src/arch/x86/isa/formats/monitor_mwait.isa PRE-CREATION 
  src/cpu/SConscript 5e0a421e2031 
  src/cpu/base.hh 5e0a421e2031 
  src/cpu/base.cc 5e0a421e2031 
  src/cpu/base_dyn_inst.hh 5e0a421e2031 
  src/cpu/checker/cpu.hh 5e0a421e2031 
  src/cpu/exec_context.hh 5e0a421e2031 
  src/cpu/o3/cpu.hh 5e0a421e2031 
  src/cpu/o3/cpu.cc 5e0a421e2031 
  src/cpu/simple/atomic.hh 5e0a421e2031 
  src/cpu/simple/base.hh 5e0a421e2031 
  src/cpu/simple/base.cc 5e0a421e2031 
  src/cpu/simple/timing.hh 5e0a421e2031 
  src/cpu/simple/timing.cc 5e0a421e2031 

Diff: http://reviews.gem5.org/r/2471/diff/


Testing
-------


Thanks,

Marc Orr

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

Reply via email to