diff options
| author | Cameron Zwarich <zwarich@apple.com> | 2011-04-02 02:40:43 +0000 |
|---|---|---|
| committer | Cameron Zwarich <zwarich@apple.com> | 2011-04-02 02:40:43 +0000 |
| commit | 4071a711126a2a75585a32b96bb5d15ea267a915 (patch) | |
| tree | 1e693a94ba4f9c310640ecc3540de493f3545a59 /test/CodeGen/ARM/fp-arg-shuffle.ll | |
| parent | ed3caf90866e183380a06c0ae49101204a9f3c28 (diff) | |
| download | external_llvm-4071a711126a2a75585a32b96bb5d15ea267a915.zip external_llvm-4071a711126a2a75585a32b96bb5d15ea267a915.tar.gz external_llvm-4071a711126a2a75585a32b96bb5d15ea267a915.tar.bz2 | |
Do some peephole optimizations to remove pointless VMOVs from Neon to integer
registers that arise from argument shuffling with the soft float ABI. These
instructions are particularly slow on Cortex A8. This fixes one half of
<rdar://problem/8674845>.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128759 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/ARM/fp-arg-shuffle.ll')
| -rw-r--r-- | test/CodeGen/ARM/fp-arg-shuffle.ll | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/test/CodeGen/ARM/fp-arg-shuffle.ll b/test/CodeGen/ARM/fp-arg-shuffle.ll new file mode 100644 index 0000000..59303ac --- /dev/null +++ b/test/CodeGen/ARM/fp-arg-shuffle.ll @@ -0,0 +1,11 @@ +; RUN: llc < %s -march=arm -mattr=+neon -float-abi=soft | FileCheck %s + +; CHECK: function1 +; CHECK-NOT: vmov r +define double @function1(double %a, double %b, double %c, double %d, double %e, double %f) nounwind noinline ssp { +entry: + %call = tail call double @function2(double %f, double %e, double %d, double %c, double %b, double %a) nounwind + ret double %call +} + +declare double @function2(double, double, double, double, double, double) |