diff options
| author | Roland Scheidegger <[email protected]> | 2014-09-19 16:56:04 +0200 |
|---|---|---|
| committer | Roland Scheidegger <[email protected]> | 2014-09-19 16:58:28 +0200 |
| commit | f2c39dd0e19e83dac922878b00a4b871c839b609 (patch) | |
| tree | a8c567e7d27718c5bcb4d6e1f0c83874c104b46a /bin/.gitignore | |
| parent | 74d7ff2efda8e33e097ed6e3f9853fc1c8d45618 (diff) | |
util: don't try to emit half-float intrinsics if avx isn't available
These instructions only have vex encodings, thus they can't be used without
avx. (Technically, one can still use avx-128 if avx isn't available because
the environment doesn't store the ymm registers, however I don't think llvm
can.)
Reviewed-by: Jose Fonseca <[email protected]>
Diffstat (limited to 'bin/.gitignore')
0 files changed, 0 insertions, 0 deletions