ARM: use natural LLVM IR for vshll instructions

Similarly to the vshrn instructions, these are simple zext/sext + trunc
operations. Using normal LLVM IR should allow for better code, and more sharing
with the AArch64 backend.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@201093 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/ARM/ARMISelLowering.h

@@ -113,9 +113,6 @@ namespace llvm {
       VSHL,         // ...left
       VSHRs,        // ...right (signed)
       VSHRu,        // ...right (unsigned)
-      VSHLLs,       // ...left long (signed)
-      VSHLLu,       // ...left long (unsigned)
-      VSHLLi,       // ...left long (with maximum shift count)
 
       // Vector rounding shift by immediate:
       VRSHRs,       // ...right (signed)