projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 6c6bbfa) | patch
ARM64: fix fmsub patterns which assumed accum operand was first
authorTim Northover <tnorthover@apple.com>
Tue, 8 Apr 2014 12:23:51 +0000 (12:23 +0000)
committerTim Northover <tnorthover@apple.com>
Tue, 8 Apr 2014 12:23:51 +0000 (12:23 +0000)
commit33d07468bc7e915d8248fd80b9485c9a5d38687d
tree08c5d2d9d72cdebc012c195103806ce4a3b5fc78tree | snapshot
parent6c6bbfab1967a9c10b6d2d4c63d4519d3d1a374fcommit | diff
ARM64: fix fmsub patterns which assumed accum operand was first

Confusingly, the NEON fmla instructions put the accumulator first but the
scalar versions put it at the end (like the fma lib function & LLVM's
intrinsic).

This should fix PR19345, assuming there's only one issue.

llvm-svn: 205758
llvm/lib/Target/ARM64/ARM64InstrInfo.td diff | blob | history
llvm/test/CodeGen/ARM64/fmadd.ll diff | blob | history
Domain: System / Toolchain;