[GHC] #8256: adding locality levels to prefetch# and friends

[Carter Schonwald]

Hey all,
I'd really love some preliminary feedback on this augmented prefetch patch,
1) so i can have any issues addressed before the merge window closes
2) If the basic patch looks good to folks (subject to some cleanup), I'd
like to also see about adding prefetch support on x86 native backend, and
fallback NOOP on other architectures. (because its something which
shouldn't be llvm only)

thanks!
-Carter


On Tue, Sep 10, 2013 at 1:21 PM, GHC <ghc-devs at haskell.org> wrote:

> #8256: adding locality levels to prefetch# and friends
> -------------------------------------+------------------------------------
>         Reporter:  carter            |            Owner:  carter
>             Type:  task              |           Status:  new
>         Priority:  normal            |        Milestone:  7.8.1
>        Component:  Compiler          |          Version:  7.7
>       Resolution:                    |         Keywords:
> Operating System:  Unknown/Multiple  |     Architecture:  Unknown/Multiple
>  Type of failure:  None/Unknown      |       Difficulty:  Unknown
>        Test Case:                    |       Blocked By:
>         Blocking:                    |  Related Tickets:  #8252 ,#8107
> -------------------------------------+------------------------------------
>
> Comment (by carter):
>
>  one thing i'm worried i'm overlooking, is how do I make sure cmm-lint
>  knows about prefetch op types?
>
>  (or is that a none issue)
>
> --
> Ticket URL: <http://ghc.haskell.org/trac/ghc/ticket/8256#comment:8>
> GHC <http://www.haskell.org/ghc/>
> The Glasgow Haskell Compiler
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.haskell.org/pipermail/ghc-devs/attachments/20130910/80eed73f/attachment.htm>