[llvm] r285106 - [AArch64] Adjust the cost model for Exynos M1.

[Evandro Menezes via llvm-commits]

Agreed.

-- 
Evandro Menezes

On 10/25/16 16:21, Renato Golin wrote:
> On 25 October 2016 at 22:03, Evandro Menezes <e.menezes at samsung.com> wrote:
>> Short of going into the details of the indirect branch predictor in M1, the
>> change that improved the heuristics creating jump tables
>> (https://reviews.llvm.org/D25212) results in a tad more conditional
>> branches, which tend to perform better than indirect branches on most
>> processors.  This heuristic change called for a revision of the limit of the
>> size of jump tables for M1, based on a suite of benchmarks, such as SPEC
>> CPU2000 and CPU2006.
> That would have been a much better commit message. :)
>
> Maybe just adding something like "SPEC2k +x% SPEC2k6 +y%" would have
> been nice, too.
>
> cheers,
> --renato
>
>
>