[SLP] Improve horizontal vectorization for non-power-of-2 number of

instructions.

If number of instructions in horizontal reduction list is not power of 2
then only PowerOf2Floor(NumberOfInstructions) last elements are actually
vectorized, other instructions remain scalar. Patch tries to vectorize
the remaining elements either.

Differential Revision: https://reviews.llvm.org/D28959

llvm-svn: 293042

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -4262,15 +4262,15 @@ class HorizontalReduction {
     Builder.setFastMathFlags(Unsafe);
     unsigned i = 0;
 
-    for (; i < NumReducedVals - ReduxWidth + 1; i += ReduxWidth) {
+    while (i < NumReducedVals - ReduxWidth + 1 && ReduxWidth > 2) {
       auto VL = makeArrayRef(&ReducedVals[i], ReduxWidth);
       V.buildTree(VL, ReductionOps);
       if (V.shouldReorder()) {
         SmallVector<Value *, 8> Reversed(VL.rbegin(), VL.rend());
         V.buildTree(Reversed, ReductionOps);
       }
       if (V.isTreeTinyAndNotFullyVectorizable())
-        continue;
+        break;
 
       V.computeMinimumValueSizes();
 
@@ -4296,6 +4296,8 @@ class HorizontalReduction {
                                              ReducedSubTree, "bin.rdx");
       } else
         VectorizedTree = ReducedSubTree;
+      i += ReduxWidth;
+      ReduxWidth = PowerOf2Floor(NumReducedVals - i);
     }
 
     if (VectorizedTree) {