diff options
| author | Pengxuan Zheng <quic_pzheng@quicinc.com> | 2024-06-07 19:52:00 -0700 |
|---|---|---|
| committer | Pengxuan Zheng <quic_pzheng@quicinc.com> | 2024-06-11 09:58:26 -0700 |
| commit | e7cd8ea1fa3e48404954bb7c06e9bcd603f132dd (patch) | |
| tree | 4a0c6ba98b71a14e79e5663f416958a654ad0bf0 /libcpp | |
| parent | 53ac88cedf9348b0139fa92c3257b877694f6194 (diff) | |
| download | gcc-e7cd8ea1fa3e48404954bb7c06e9bcd603f132dd.zip gcc-e7cd8ea1fa3e48404954bb7c06e9bcd603f132dd.tar.gz gcc-e7cd8ea1fa3e48404954bb7c06e9bcd603f132dd.tar.bz2 | |
aarch64: Add vector floating point trunc pattern
This patch is a follow-up of r15-1079-g230d62a2cdd16c to add vector floating
point trunc pattern for V2DF->V2SF and V4SF->V4HF conversions by renaming the
existing aarch64_float_truncate_lo_<mode><vczle><vczbe> pattern to the standard
optab one, i.e., trunc<Vwide><mode>2<vczle><vczbe>. This allows the vectorizer
to vectorize certain floating point narrowing operations for the aarch64 target.
gcc/ChangeLog:
* config/aarch64/aarch64-builtins.cc (VAR1): Remap float_truncate_lo_
builtin codes to standard optab ones.
* config/aarch64/aarch64-simd.md (aarch64_float_truncate_lo_<mode><vczle><vczbe>):
Rename to...
(trunc<Vwide><mode>2<vczle><vczbe>): ... This.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/trunc-vec.c: New test.
Signed-off-by: Pengxuan Zheng <quic_pzheng@quicinc.com>
Diffstat (limited to 'libcpp')
0 files changed, 0 insertions, 0 deletions