| commit | 5209a51761f6efe4594a1ef7ffb7dbfbf1af0d1c | |
| author | Erik Lindahl <erik@kth.se> | |
| Mon, 25 Dec 2017 21:34:14 +0000 (25 22:34 +0100) | ||
| committer | Mark Abraham <mark.j.abraham@gmail.com> | |
| Wed, 3 Jan 2018 10:59:42 +0000 (3 11:59 +0100) | ||
| tree | 11a996abd28223badd6ca5348ae9616c2c998e0b | treesnapshot (tar.gz zip) |
| parent | 871f2f46044ef80e64f8cdff17e2dabf3dc1bd34 | commitdiff |
Avoid FTZ triggering simd test failures
For very small arguments on platforms without
FMA support, the Intel compiler's default
usage of flush-to-zero for denormal values can
lead to slight deviations. Since this is a
range we really don't care about, and non-FMA
platforms are anyway a thing of the past, just
avoid testing a very small range around that
threshold for non-FMA SIMD platforms.
Fixes #2335.
Change-Id: I7cfb14284e79534f114891ba4dcd1f1c7223faf3
For very small arguments on platforms without
FMA support, the Intel compiler's default
usage of flush-to-zero for denormal values can
lead to slight deviations. Since this is a
range we really don't care about, and non-FMA
platforms are anyway a thing of the past, just
avoid testing a very small range around that
threshold for non-FMA SIMD platforms.
Fixes #2335.
Change-Id: I7cfb14284e79534f114891ba4dcd1f1c7223faf3
| src/gromacs/simd/tests/simd_math.cpp | diffblobblamehistory |