| Message ID | 20220118173308.1758560-1-skpgkp2@gmail.com |
|---|---|
| State | New |
| Headers | show |
| Series | x86_64: Document libmvec vector functions accuracy [BZ #28766] | expand |
Dear Sunil, > Date: Tue, 18 Jan 2022 09:33:08 -0800 > From: Sunil K Pandey via Libc-alpha <libc-alpha@sourceware.org> > Cc: andrey.kolesov@intel.com, marius.cornea@intel.com > > Document maximum 4 ulps accuracy for x86_64 libmvec functions. > This fixes BZ #28766. > --- > manual/math.texi | 5 +++-- > 1 file changed, 3 insertions(+), 2 deletions(-) > > diff --git a/manual/math.texi b/manual/math.texi > index e00871c303..53b196bb6d 100644 > --- a/manual/math.texi > +++ b/manual/math.texi > @@ -1395,8 +1395,9 @@ The table lists the ULP values for different architectures. Different > architectures have different results since their hardware support for > floating-point operations varies and also the existing hardware support > is different. Only the round-to-nearest rounding mode is covered by > -this table, and vector versions of functions are not covered. > -Functions not listed do not have known errors. > +this table. Functions not listed do not have known errors. Vector > +versions of functions in x86_64 libmvec library have the maximum error > +of 4ulps. > > @page > @c This multitable does not fit on a single page > -- > 2.34.1 looks good to me, with two small editorial changes: Vector versions of functions in *the* x86_64 libmvec library have *a* maximum error of 4 ulps. Thanks! Paul
diff --git a/manual/math.texi b/manual/math.texi index e00871c303..53b196bb6d 100644 --- a/manual/math.texi +++ b/manual/math.texi @@ -1395,8 +1395,9 @@ The table lists the ULP values for different architectures. Different architectures have different results since their hardware support for floating-point operations varies and also the existing hardware support is different. Only the round-to-nearest rounding mode is covered by -this table, and vector versions of functions are not covered. -Functions not listed do not have known errors. +this table. Functions not listed do not have known errors. Vector +versions of functions in x86_64 libmvec library have the maximum error +of 4ulps. @page @c This multitable does not fit on a single page