-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
http://reviews.gem5.org/r/3205/#review7767
-----------------------------------------------------------



src/base/types.hh (line 203)
<http://reviews.gem5.org/r/3205/#comment6720>

    Needs comments



src/mem/abstract_mem.cc (line 343)
<http://reviews.gem5.org/r/3205/#comment6721>

    This does not match what you mention in your comment. I thought this would 
be a special SwapReq (and as such always fit in a cacheline)?



src/mem/protocol/RubySlicc_Exports.sm (line 172)
<http://reviews.gem5.org/r/3205/#comment6728>

    Seems to disagree with the one above



src/mem/request.hh (line 164)
<http://reviews.gem5.org/r/3205/#comment6722>

    How does this interact with SWAP?



src/mem/request.hh (line 353)
<http://reviews.gem5.org/r/3205/#comment6723>

    More elaborate comments please



src/mem/request.hh (line 433)
<http://reviews.gem5.org/r/3205/#comment6724>

    We really need to use delegating constructors for these kinds of things. 
This is just silly :-)



src/mem/request.hh (line 574)
<http://reviews.gem5.org/r/3205/#comment6726>

    const



src/mem/request.hh (line 576)
<http://reviews.gem5.org/r/3205/#comment6725>

    stick to nullptr



src/mem/request.hh (line 580)
<http://reviews.gem5.org/r/3205/#comment6727>

    const


- Andreas Hansson


On Dec. 23, 2015, 6:34 p.m., Tony Gutierrez wrote:
> 
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> http://reviews.gem5.org/r/3205/
> -----------------------------------------------------------
> 
> (Updated Dec. 23, 2015, 6:34 p.m.)
> 
> 
> Review request for Default.
> 
> 
> Repository: gem5
> 
> 
> Description
> -------
> 
> Changeset 11279:ea817032d082
> ---------------------------
> mem: support for gpu-style RMWs in ruby
> 
> This patch adds support for GPU-style read-modify-write (RMW) operations in
> ruby. Such atomic operations are traditionally executed at the memory 
> controller
> (instead of through an L1 cache using cache-line locking).
> 
> Currently, this patch works by propogating operation functors through the 
> memory
> system.
> 
> 
> Diffs
> -----
> 
>   src/mem/request.hh d9a0136ab8cc4b3cf4821d064140b857e60db0dd 
>   src/mem/protocol/RubySlicc_Exports.sm 
> d9a0136ab8cc4b3cf4821d064140b857e60db0dd 
>   src/mem/packet.hh d9a0136ab8cc4b3cf4821d064140b857e60db0dd 
>   src/mem/abstract_mem.cc d9a0136ab8cc4b3cf4821d064140b857e60db0dd 
>   src/base/types.hh d9a0136ab8cc4b3cf4821d064140b857e60db0dd 
> 
> Diff: http://reviews.gem5.org/r/3205/diff/
> 
> 
> Testing
> -------
> 
> 
> Thanks,
> 
> Tony Gutierrez
> 
>

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

Reply via email to