[x86] Implement v16i16 support with AVX2 in the new vector shuffle

[oota-llvm.git] / lib / Target / X86 / Utils / X86ShuffleDecode.cpp

diff --git a/lib/Target/X86/Utils/X86ShuffleDecode.cpp b/lib/Target/X86/Utils/X86ShuffleDecode.cpp
index 713e147fbf5ebf7483410455245ea46f9c19e9e4..a3f45233454761f88f6a56a1c914707b551ef87e 100644 (file)
--- a/lib/Target/X86/Utils/X86ShuffleDecode.cpp
+++ b/lib/Target/X86/Utils/X86ShuffleDecode.cpp
@@ -301,11 +301,18 @@ void DecodePSHUFBMask(ArrayRef<uint64_t> RawMask,
   }
 }
 
-void DecodeBLENDMask(MVT VT, unsigned Imm,
-                       SmallVectorImpl<int> &ShuffleMask) {
+void DecodeBLENDMask(MVT VT, unsigned Imm, SmallVectorImpl<int> &ShuffleMask) {
+  int ElementBits = VT.getScalarSizeInBits();
   int NumElements = VT.getVectorNumElements();
-  for (int i = 0; i < NumElements; ++i)
-    ShuffleMask.push_back(((Imm >> i) & 1) ? NumElements + i : i);
+  for (int i = 0; i < NumElements; ++i) {
+    // If there are more than 8 elements in the vector, then any immediate blend
+    // mask applies to each 128-bit lane. There can never be more than
+    // 8 elements in a 128-bit lane with an immediate blend.
+    int Bit = NumElements > 8 ? i % (128 / ElementBits) : i;
+    assert(Bit < 8 &&
+           "Immediate blends only operate over 8 elements at a time!");
+    ShuffleMask.push_back(((Imm >> Bit) & 1) ? NumElements + i : i);
+  }
 }
 
 /// DecodeVPERMMask - this decodes the shuffle masks for VPERMQ/VPERMPD.