diff options
| author | JosJuice <josjuice@gmail.com> | 2021-06-16 18:26:02 +0200 |
|---|---|---|
| committer | JosJuice <josjuice@gmail.com> | 2021-07-11 13:04:02 +0200 |
| commit | 6fe96d12c6a281a93e5bb0c877f26fc0318e3568 (patch) | |
| tree | ff5979c94d6036b9872b5d3eb867cc4d1f43f3f9 /Source/Core/Common/FileUtil.cpp | |
| parent | 88fd9fd577ffc3c1af5a04cdf337ecd2990ccfe2 (diff) | |
Jits: Don't use fast double-to-single when input is double precision
The fast path of using CVTSD2SS/FCVTN rounds the significand if it
can't be exactly represented as a single, whereas the accurate path
instead truncates the significand. So we should only use the fast
path if we know that the lower bits of the significand are not set.
This is not known to affect any games.
Diffstat (limited to 'Source/Core/Common/FileUtil.cpp')
0 files changed, 0 insertions, 0 deletions