projects / gcc.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: f6cc254) | patch
[Patch AArch64] Use 128-bit vectors when autovectorizing 16-bit float types
authorJames Greenhalgh <james.greenhalgh@arm.com>
Tue, 14 Feb 2017 14:48:33 +0000 (14:48 +0000)
committerJames Greenhalgh <jgreenhalgh@gcc.gnu.org>
Tue, 14 Feb 2017 14:48:33 +0000 (14:48 +0000)
commitb719f884b44f4b678025606356f25a0da277529d
tree44c3914c58299745b0575286c168d58c9fd95397tree
parentf6cc254a285a61e122ea64316a2726ae7286289dcommit | diff
[Patch AArch64] Use 128-bit vectors when autovectorizing 16-bit float types

gcc/

* config/aarch64/aarch64.c (aarch64_simd_container_mode): Handle
HFmode.

gcc/testsuite/

* gcc.target/aarch64/vect_fp16_1.c: New.

From-SVN: r245429
gcc/ChangeLog diff | blob | history
gcc/config/aarch64/aarch64.c diff | blob | history
gcc/testsuite/ChangeLog diff | blob | history
gcc/testsuite/gcc.target/aarch64/vect_fp16_1.c [new file with mode: 0644] blob