ARM: Improve codegen for vget_low_* and vget_high_ intrinsics.

These intrinsics use the __builtin_shuffle() function to extract the
low and high half, respectively, of a 128-bit NEON vector. Currently,
they're defined to use bitcasts to simplify the emitter, so we get code
like:
uint16x4_t vget_low_u32(uint16x8_t __a) {
  return (uint32x2_t) __builtin_shufflevector((int64x2_t) __a,
                                              (int64x2_t) __a,
                                              0);
}

While this works, it results in those bitcasts going all the way through
to the IR, resulting in code like:
  %1 = bitcast <8 x i16> %in to <2 x i64>
  %2 = shufflevector <2 x i64> %1, <2 x i64> undef, <1 x i32>
  %zeroinitializer
  %3 = bitcast <1 x i64> %2 to <4 x i16>

We can instead easily perform the operation directly on the input vector
like:

uint16x4_t vget_low_u16(uint16x8_t __a) {
  return __builtin_shufflevector(__a, __a, 0, 1, 2, 3);
}

Not only is that much easier to read on its own, it also results in
cleaner IR like:

  %1 = shufflevector <8 x i16> %in, <8 x i16> undef,
                     <4 x i32> <i32 0, i32 1, i32 2, i32 3>

This is both easier to read and easier for the back end to reason
about effectively since the operation is obfuscating the source with
bitcasts.

rdar://13894163

llvm-svn: 181865

1 files changed, 9 insertions, 4 deletions

diff --git a/clang/utils/TableGen/NeonEmitter.cpp b/clang/utils/TableGen/NeonEmitter.cpp
index 34b955e8e9d..05505c99c99 100644
--- a/clang/utils/TableGen/NeonEmitter.cpp
+++ b/clang/utils/TableGen/NeonEmitter.cpp
@@ -1410,12 +1410,17 @@ static std::string GenOpString(OpKind op, const std::string &proto,
     s += ", (int64x1_t)__b, 0, 1);";
     break;
   case OpHi:
-    s += "(" + ts +
-      ")__builtin_shufflevector((int64x2_t)__a, (int64x2_t)__a, 1);";
+    // nElts is for the result vector, so the source is twice that number.
+    s += "__builtin_shufflevector(__a, __a";
+    for (unsigned i = nElts; i < nElts * 2; ++i)
+      s += ", " + utostr(i);
+    s+= ");";
     break;
   case OpLo:
-    s += "(" + ts +
-      ")__builtin_shufflevector((int64x2_t)__a, (int64x2_t)__a, 0);";
+    s += "__builtin_shufflevector(__a, __a";
+    for (unsigned i = 0; i < nElts; ++i)
+      s += ", " + utostr(i);
+    s+= ");";
     break;
   case OpDup:
     s += Duplicate(nElts, typestr, "__a") + ";";