[X86] Fix arithmetic error in extractVector

The computation of the element count for the result VT in extractVector
is incorrect when vector width does not divide VT.getSizeInBits(), which
can occur when the source vector element count is not a power of two,
e.g. extracting a vectorWidth 256b vector from a 384b source.

This rewrites the expression so the division is exact given that
vectorWidth is a multiple of the source element size.

Author: daniel-zabawa

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -4066,6 +4066,10 @@ static SDValue extractSubVector(SDValue Vec, unsigned IdxVal, SelectionDAG &DAG,
                                 const SDLoc &dl, unsigned vectorWidth) {
   EVT VT = Vec.getValueType();
   EVT ElVT = VT.getVectorElementType();
+  unsigned ResultNumElts =
+      (VT.getVectorNumElements() * vectorWidth) / VT.getSizeInBits();
+  EVT ResultVT = EVT::getVectorVT(*DAG.getContext(), ElVT, ResultNumElts);
+
   unsigned Factor = VT.getSizeInBits() / vectorWidth;
   EVT ResultVT = EVT::getVectorVT(*DAG.getContext(), ElVT,
                                   VT.getVectorNumElements() / Factor);