projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: c3e5d72) | patch
[AArch64] Refactor the NEON scalar floating-point reciprocal step and
authorChad Rosier <mcrosier@codeaurora.org>
Wed, 11 Dec 2013 21:03:43 +0000 (21:03 +0000)
committerChad Rosier <mcrosier@codeaurora.org>
Wed, 11 Dec 2013 21:03:43 +0000 (21:03 +0000)
commit73f468218fc56a0acf9cb9c38eb74b138e955ff5
tree9909a700335d59b93b079dfb6ce0f9de7ae33099tree | snapshot
parentc3e5d72ba83f607d7e1409027f7593c689fc70d0commit | diff
[AArch64] Refactor the NEON scalar floating-point reciprocal step and
floating-point reciprocal square root step LLVM AArch64 intrinsics to
use f32/f64 types, rather than their vector equivalents.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@197067 91177308-0d34-0410-b5e6-96231b3b80d8
include/llvm/IR/IntrinsicsAArch64.td diff | blob | history
lib/Target/AArch64/AArch64InstrNEON.td diff | blob | history
test/CodeGen/AArch64/neon-scalar-recip.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors