aarch64: Relax aarch64_<sur>q<r>shr<u>n2_n<mode> RTL pattern
authorJonathan Wright <jonathan.wright@arm.com>
Thu, 4 Mar 2021 12:36:09 +0000 (12:36 +0000)
committerJonathan Wright <jonathan.wright@arm.com>
Wed, 19 May 2021 13:44:10 +0000 (14:44 +0100)
commit4e26303e0b90038473e3d7490dc0369a74866b1b
treee478d5f9b8d2f3e54b637500bb381e3d96b459a1
parent3eddaad02dcce21fb67c42cc6e1e8f951a630ac1
aarch64: Relax aarch64_<sur>q<r>shr<u>n2_n<mode> RTL pattern

Implement saturating right-shift and narrow high Neon intrinsic RTL
patterns using a vec_concat of a register_operand and a VQSHRN_N
unspec - instead of just a VQSHRN_N unspec. This more relaxed pattern
allows for more aggressive combinations and ultimately better code
generation.

gcc/ChangeLog:

2021-03-04  Jonathan Wright  <jonathan.wright@arm.com>

* config/aarch64/aarch64-simd.md (aarch64_<sur>q<r>shr<u>n2_n<mode>):
Implement as an expand emitting a big/little endian
instruction pattern.
(aarch64_<sur>q<r>shr<u>n2_n<mode>_insn_le): Define.
(aarch64_<sur>q<r>shr<u>n2_n<mode>_insn_be): Define.
gcc/config/aarch64/aarch64-simd.md