This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH] powerpc: strcasestr optimization
- From: Steven Munroe <munroesj at linux dot vnet dot ibm dot com>
- To: Roland McGrath <roland at hack dot frob dot com>
- Cc: OndÅej BÃlka <neleai at seznam dot cz>, Rajalakshmi Srinivasaraghavan <raji at linux dot vnet dot ibm dot com>, GNU C Library <libc-alpha at sourceware dot org>, Steve Munroe <sjmunroe at us dot ibm dot com>
- Date: Tue, 09 Jun 2015 16:26:24 -0500
- Subject: Re: [PATCH] powerpc: strcasestr optimization
- Authentication-results: sourceware.org; auth=none
- References: <55687597 dot 1060101 at linux dot vnet dot ibm dot com> <556C36D8 dot 2070208 at linux dot vnet dot ibm dot com> <20150601122830 dot GA14649 at domone> <1433169407 dot 10235 dot 5 dot camel at sjmunroe-ThinkPad-W500> <20150601162215 dot GA8955 at domone> <1433270823 dot 14958 dot 15 dot camel at sjmunroe-ThinkPad-W500> <20150602210000 dot GB20004 at domone> <1433882432 dot 21101 dot 71 dot camel at sjmunroe-ThinkPad-W500> <20150609210555 dot 3A7CA2C3BDC at topped-with-meat dot com>
- Reply-to: munroesj at linux dot vnet dot ibm dot com
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.
OndÅej BÃlka 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 OndÅej BÃlka believes there is a problem that only he understands
then the onus is on him to provide the appropriate benchmark.