[llvm-bugs] [Bug 26450] ARM code runs 2x slower compared to gcc

[via llvm-bugs]

https://llvm.org/bugs/show_bug.cgi?id=26450

Renato Golin <renato.golin at linaro.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|REOPENED                    |RESOLVED
         Resolution|---                         |FIXED

--- Comment #15 from Renato Golin <renato.golin at linaro.org> ---
Fixed on r259657.

It turns out it wasn't a regression, but a long term FIXME. I remember this
decision was taken because isTargetEABI didn't cover GNU and we didn't have
isTargetGNUEABI at the time, so I assumed the worse, given the problems we had
with __aeabi_mem*.

Not only we have a check for gnueabi now, but it's also always safe (and many
times profitable) to call __aeabi_divmod*, which doesn't have the same problem
as the memory builtins.

I'm not sure we'll get it into 3.8.0, but I'm marking it for 3.8.1 for sure,
which will come in the next few months.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20160203/4d81142e/attachment.html>