> On Nov. 3, 2015, 10:51 a.m., Andreas Hansson wrote:
> > In my view this patch really needs to be split:
> > 
> > 1. The adding of write masks is an example of functionality that definitely 
> > warrants its own patch, and I would argue the write mask should go into the 
> > packet class.
> > 
> > 2. There are a bunch of changes/flags to the request that seem unrelated to 
> > the atomics and should be split out.
> > 
> > 3. Finally there are the atomic ops.

Sounds reasonable. I will first try address Joel's smaller comments. Then I'll 
split the patch.


- Marc


-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/3185/#review7457
-----------------------------------------------------------


On Nov. 2, 2015, 10:43 p.m., Tony Gutierrez wrote:
> 
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> http://reviews.gem5.org/r/3185/
> -----------------------------------------------------------
> 
> (Updated Nov. 2, 2015, 10:43 p.m.)
> 
> 
> Review request for Default.
> 
> 
> Repository: gem5
> 
> 
> Description
> -------
> 
> Changeset 11191:a831152645c0
> ---------------------------
> mem: support for scoped atomics in GPU ruby protocols
> 
> This patch extends ruby to: (1) do write combining, (2) do GPU-style RMWs at 
> the
> memory controller via functors, (3) support HSA-style scoped memory 
> operations.
> 
> 
> Diffs
> -----
> 
>   src/mem/ruby/common/SConscript 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/ruby/common/WriteMask.hh PRE-CREATION 
>   src/mem/ruby/common/WriteMask.cc PRE-CREATION 
>   src/mem/ruby/slicc_interface/RubyRequest.hh 
> 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/ruby/slicc_interface/RubySlicc_Util.hh 
> 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/ruby/system/RubyPort.cc 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/abstract_mem.cc 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/packet.hh 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/protocol/RubySlicc_Exports.sm 
> 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/base/types.hh 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/ruby/SConscript 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/ruby/common/DataBlock.hh 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/ruby/common/DataBlock.cc 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/protocol/RubySlicc_Types.sm 
> 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/request.hh 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
> 
> Diff: http://reviews.gem5.org/r/3185/diff/
> 
> 
> Testing
> -------
> 
> 
> Thanks,
> 
> Tony Gutierrez
> 
>

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

Reply via email to