[AAarch64] Optimize CSINC-branch sequence
authorGerolf Hoflehner <ghoflehner@apple.com>
Tue, 14 Oct 2014 23:07:53 +0000 (23:07 +0000)
committerGerolf Hoflehner <ghoflehner@apple.com>
Tue, 14 Oct 2014 23:07:53 +0000 (23:07 +0000)
commita4c96d02a2068a5889b282730e6afa8e1418d1ad
treeec7418e16cb8f0d939f187c1b681f25f2737a0bd
parent1a600faba0329f5cde0aab1ce7bbff2f09252eff
[AAarch64] Optimize CSINC-branch sequence

Peephole optimization that generates a single conditional branch
for csinc-branch sequences like in the examples below. This is
possible when the csinc sets or clears a register based on a condition
code and the branch checks that register. Also the condition
code may not be modified between the csinc and the original branch.

Examples:

1. Convert csinc w9, wzr, wzr, <CC>;tbnz w9, #0, 0x44
   to b.<invCC>

2. Convert csinc w9, wzr, wzr, <CC>; tbz w9, #0, 0x44
   to b.<CC>

rdar://problem/18506500

llvm-svn: 219742
llvm/include/llvm/Target/TargetInstrInfo.h
llvm/lib/CodeGen/PeepholeOptimizer.cpp
llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
llvm/lib/Target/AArch64/AArch64InstrInfo.h
llvm/test/CodeGen/AArch64/arm64-bcc.ll [new file with mode: 0644]