> On Nov. 2, 2015, 3:56 p.m., Joel Hestness wrote:
> > This is pretty cool. Looking forward to when gem5-gpu can shift over to use 
> > this!
> > 
> > A couple big questions, but mostly minor comments below.
> 
> Marc Orr wrote:
>     Hey Joel,
>     
>     First off, thanks for your review. FYI, please keep in mind that the 
> original authors of this patch, who were an intern and a post-doc, are no 
> longer at AMD. I've been assigned to this patch, and will do my best to 
> address the feedback, but it will take some effort, since I didn't write the 
> code...
>     
>     I've responded to comments below. I'm still trying to decide how to 
> handle the feedback. I'm thinking to:
>     (1) Take care of the style issues and minor feedback you pointed out.
>     (2) Split up the patch as Andreas requested. We will need to copy the 
> unaddressed comments over...
>     (3) Tackle the larger pieces of feedback, after the patches are split up.
>     
>     Thanks,
>     Marc

We split this patch up into 3 (see 3205 and 3206), and I think I moved over all 
of your unaddressed comments to their relevant patches.


- Tony


-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/3185/#review7448
-----------------------------------------------------------


On Nov. 12, 2015, 1:59 p.m., Tony Gutierrez wrote:
> 
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> http://reviews.gem5.org/r/3185/
> -----------------------------------------------------------
> 
> (Updated Nov. 12, 2015, 1:59 p.m.)
> 
> 
> Review request for Default.
> 
> 
> Repository: gem5
> 
> 
> Description
> -------
> 
> Changeset 11191:017c08d70a70
> ---------------------------
> mem: misc flags for AMD gpu model
> 
> This patch add support to mark memory requests/packets with attributes defined
> in HSA, such as memory order and scope.
> 
> 
> Diffs
> -----
> 
>   src/mem/protocol/RubySlicc_Exports.sm 
> 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/protocol/RubySlicc_Types.sm 
> 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/request.hh 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/ruby/common/DataBlock.hh 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/ruby/slicc_interface/RubyRequest.hh 
> 4daf60db14d794e2344a6c86a93bdd8273bc5bb6 
>   src/mem/ruby/system/RubyPort.cc 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