diff options
| author | Xi Ruoyao <xry111@xry111.site> | 2023-11-14 00:17:19 +0800 |
|---|---|---|
| committer | Xi Ruoyao <xry111@xry111.site> | 2023-11-17 19:21:11 +0800 |
| commit | bdf20fdfc342746d1e1785f5aaa36e33897b1574 (patch) | |
| tree | bd147f723562223035e0ce07617b4e248b54450b /gcc/tree-vect-loop.cc | |
| parent | 10615c8a10d6b61e813254924d76be728dbd4688 (diff) | |
| download | gcc-bdf20fdfc342746d1e1785f5aaa36e33897b1574.zip gcc-bdf20fdfc342746d1e1785f5aaa36e33897b1574.tar.gz gcc-bdf20fdfc342746d1e1785f5aaa36e33897b1574.tar.bz2 | |
LoongArch: Handle vectorized copysign (x, -1) expansion efficiently
With LSX or LASX, copysign (x[i], -1) (or any negative constant) can be
vectorized using [x]vbitseti.{w/d} instructions to directly set the
signbits.
Inspired by Tamar Christina's "AArch64: Handle copysign (x, -1) expansion
efficiently" (r14-5289).
gcc/ChangeLog:
* config/loongarch/lsx.md (copysign<mode>3): Allow operand[2] to
be an reg_or_vector_same_val_operand. If it's a const vector
with same negative elements, expand the copysign with a bitset
instruction. Otherwise, force it into an register.
* config/loongarch/lasx.md (copysign<mode>3): Likewise.
gcc/testsuite/ChangeLog:
* g++.target/loongarch/vect-copysign-negconst.C: New test.
* g++.target/loongarch/vect-copysign-negconst-run.C: New test.
Diffstat (limited to 'gcc/tree-vect-loop.cc')
0 files changed, 0 insertions, 0 deletions