[LLVMdev] BasicAA unable to analyze recursive PHI nodes

[Daniel Berlin]

On Thu, Jun 25, 2015 at 12:52 PM, Tobias Edler von Koch
<tobias at codeaurora.org> wrote:
> Hi Hal, Daniel,
>
> On Mon, 22 Jun 2015 20:45:38 -0500 Hal Finkel <hfinkel at anl.gov> wrote:
>>
>> I agree. In the mean time, let's get this committed turned off by default. Please update your patch so that the new behavior is controlled by some cl::opt that is off by default. This will give us a better way to do more-extensive benchmarking and help isolate the problems.
>>
>
> I've updated the patch and added the flag. Is this OK to go in now?
> http://reviews.llvm.org/D10368
LGTM


>
> We're seeing some small degradations on Hexagon too (and that's in
> simulation, so definitely not noise). At first glance it seems that the
> main difference is that some loops are being replaced by memcpy/memset
> calls (you'd think that's a good thing...), but I'll investigate this
> further.

I'm not shocked, this is basically what happens with any AA changes :)

When I improved GCC's alias analysis by ~30% (in terms of noalias
results returned), it caused about an 5% geomean performance
degradation. :)