This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: RFC: What inputs to use for sqrt perf testing
- From: "Joseph S. Myers" <joseph at codesourcery dot com>
- To: Siddhesh Poyarekar <siddhesh dot poyarekar at gmail dot com>
- Cc: Carlos O'Donell <carlos at redhat dot com>, Steve Ellcey <sellcey at mips dot com>, GNU C Library <libc-alpha at sourceware dot org>
- Date: Fri, 4 Oct 2013 15:10:32 +0000
- Subject: Re: RFC: What inputs to use for sqrt perf testing
- Authentication-results: sourceware.org; auth=none
- References: <cf183992-8b0e-4439-b651-f3da33cda74d at BAMAIL02 dot ba dot imgtec dot org> <CAAHN_R0wRumvcBkfeCAjP5MTbqOpoqXBPoJMdJY4jCyDaant8g at mail dot gmail dot com> <524E3C70 dot 4070800 at redhat dot com> <CAAHN_R1by6DgiWMqUL1sBzQt5FLRewanfQA0JNg43hT=5EZbJg at mail dot gmail dot com>
On Fri, 4 Oct 2013, Siddhesh Poyarekar wrote:
> > Would it make sense to start off with all the inputs used by
> > libm-test.inc e.g. sqrt_test_data?
>
> Oh yeah, why not. In fact, it won't be a bad idea to do that for all
> functions. That would be a better starting point than using 42.
Test data for libm functions is typically biased to special cases, whereas
benchmarks should be biased to more ordinary inputs and certainly don't
need thorough coverage of many variations on special cases the way the
test data does. (But it's a good idea for any value used as a benchmark
input also to be in libm-test.inc, to verify that the results are correct
for those arguments.)
--
Joseph S. Myers
joseph@codesourcery.com