Re: [Gems-users] simulation of TCC via GEMS

[Jayaram Bobba <bobba@xxxxxxxxxxx>]

Bernard,

GEMS does not simulate TCC. It does contain an 'idealized'
lazy/lazy TM implementation (with infinite store buffers and
zero cycle token arbitration). Please see
http://www.cs.wisc.edu/multifacet/papers/isca07_pathologies.pdf
for more details on the lazy/lazy TM implementation.

For workloads with small transactions that fit in
private caches, I think LL would perform similar to TCC.

Jayaram

ChongBernard wrote:
> Hello,
>
> I was wondering if GEMS could simulate TCC or similar lazy/lazy TM.
>
> My guess is using
>
> simics> ruby0.setparam_str XACT_LAZY_VM "true"
> simics> ruby0.setparam_str XACT_EAGER_CD "false"
>
> would be enough, but I want to make sure just setting those values
> would make
> almost same lazy/lazy TMs like TCC.
>
>
> Thanks,
>
> Bernard
>
> ------------------------------------------------------------------------
> 내 맘대로 바꾸는 배경 화면 색, 더욱 다양해진 홈페이지 슬라이드 쇼 구
> 성! 확 달라진 MSN 홈페이지! <http://www.msn.co.kr>
> ------------------------------------------------------------------------
>
> _______________________________________________
> Gems-users mailing list
> Gems-users@xxxxxxxxxxx
> https://lists.cs.wisc.edu/mailman/listinfo/gems-users
> Use Google to search the GEMS Users mailing list by adding "site:https://lists.cs.wisc.edu/archive/gems-users/"; to your search.
>
>