diff options
author | Antonio Sanchez <cantonios@google.com> | 2020-11-23 14:13:59 -0800 |
---|---|---|
committer | Antonio Sanchez <cantonios@google.com> | 2020-11-23 14:13:59 -0800 |
commit | 38abf2be4289a8da5db2d5b1db759f26800ae1d3 (patch) | |
tree | d12493bc35c41785aceef33fa7374ff3a386d662 /unsupported | |
parent | 4cf01d2cf5e10c38fdec01acd335b11b924de399 (diff) |
Fix Half NaN definition and test.
The `half_float` test was failing with `-mcpu=cortex-a55` (native `__fp16`) due
to a bad NaN bit-pattern comparison (in the case of casting a float to `__fp16`,
the signaling `NaN` is quieted). There was also an inconsistency between
`numeric_limits<half>::quiet_NaN()` and `NumTraits::quiet_NaN()`. Here we
correct the inconsistency and compare NaNs according to the IEEE 754
definition.
Also modified the `bfloat16_float` test to match.
Tested with `cortex-a53` and `cortex-a55`.
Diffstat (limited to 'unsupported')
0 files changed, 0 insertions, 0 deletions