[PATCH] powerpc: strcasestr optimization

[Steven Munroe]

On Tue, 2015-06-09 at 14:05 -0700, Roland McGrath wrote:
> Our policy is that all such questions should be settled objectively in a
> reproducible manner.  That means a new benchmark should be added that can
> demonstrate the effect of the library change in question, and consensus
> reached on the utility of that particular benchmark (which is always a
> somewhat subjective issue).  Once the benchmark is in, then objective
> reports of benchmark results before and after a change on various hardware
> must be shown to justify the library change.  The onus for making all this
> happen is on the person who wants to change the code from its status quo.
> 

In https://sourceware.org/ml/libc-alpha/2015-06/msg00032.html Raja
provided the results for the existing benchmark. 

So we have meet your and the community requirement.

Ondřej Bílka is asserting that not good enough based based on his
opinion that the algorithm is flawed. But he has not provide a benchmark
that we can use to verify this.

Since we do not understand what the problem is, we can not provide a new
benchmark.

If Ondřej Bílka believes there is a problem that only he understands
then the onus is on him to provide the appropriate benchmark.