[IndVars] Change the order to compute WidenAddRec in widenIVUse.

When both WidenIV::getWideRecurrence and WidenIV::getExtendedOperandRecurrence
return non-null but different WideAddRec, if getWideRecurrence is called
before getExtendedOperandRecurrence, we won't bother to call
getExtendedOperandRecurrence again. But As we know it is possible that after
SCEV folding, we cannot prove the legality using the SCEVAddRecExpr returned
by getWideRecurrence. Meanwhile if getExtendedOperandRecurrence returns non-null
WideAddRec, we know for sure that it is legal to do widening for current instruction.
So it is better to put getExtendedOperandRecurrence before getWideRecurrence, which
will increase the chance of successful widening.

Differential Revision: https://reviews.llvm.org/D26059

llvm-svn: 286987

llvm/lib/Transforms/Scalar/IndVarSimplify.cpp

@@ -1412,9 +1412,9 @@ Instruction *WidenIV::widenIVUse(NarrowIVDefUse DU, SCEVExpander &Rewriter) {
   }
 
   // Does this user itself evaluate to a recurrence after widening?
-  WidenedRecTy WideAddRec = getWideRecurrence(DU);
+  WidenedRecTy WideAddRec = getExtendedOperandRecurrence(DU);
   if (!WideAddRec.first)
-    WideAddRec = getExtendedOperandRecurrence(DU);
+    WideAddRec = getWideRecurrence(DU);
 
   assert((WideAddRec.first == nullptr) == (WideAddRec.second == Unknown));
   if (!WideAddRec.first) {

llvm/test/Transforms/IndVarSimplify/iv-widen-elim-ext.ll

@@ -21,8 +21,11 @@ define void @foo(i32* %A, i32* %B, i32* %C, i32 %N) {
 ; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* %C, i64 [[TMP1]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4
 ; CHECK-NEXT:    [[ADD3:%.*]] = add nsw i32 [[TMP0]], [[TMP2]]
+; CHECK-NEXT:    [[TRUNC0:%.*]] = trunc i64 [[TMP1]] to i32
+; CHECK-NEXT:    [[DIV0:%.*]] = udiv i32 5, [[TRUNC0]]
+; CHECK-NEXT:    [[ADD4:%.*]] = add nsw i32 [[ADD3]], [[DIV0]]
 ; CHECK-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* %A, i64 [[INDVARS_IV]]
-; CHECK-NEXT:    store i32 [[ADD3]], i32* [[ARRAYIDX5]], align 4
+; CHECK-NEXT:    store i32 [[ADD4]], i32* [[ARRAYIDX5]], align 4
 ; CHECK-NEXT:    br label %for.inc
 ; CHECK:       for.inc:
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 1
@@ -51,9 +54,11 @@ for.body:                                         ; preds = %for.body.lr.ph, %fo
   %arrayidx2 = getelementptr inbounds i32, i32* %C, i64 %idxprom1
   %1 = load i32, i32* %arrayidx2, align 4
   %add3 = add nsw i32 %0, %1
+  %div0 = udiv i32 5, %add
+  %add4 = add nsw i32 %add3, %div0
   %idxprom4 = zext i32 %i.02 to i64
   %arrayidx5 = getelementptr inbounds i32, i32* %A, i64 %idxprom4
-  store i32 %add3, i32* %arrayidx5, align 4
+  store i32 %add4, i32* %arrayidx5, align 4
   br label %for.inc
 
 for.inc:                                          ; preds = %for.body

llvm/test/Transforms/IndVarSimplify/iv-widen.ll

@@ -69,3 +69,59 @@ define void @loop_1(i32 %lim) {
 
 declare void @dummy(i32)
 declare void @dummy.i64(i64)
+
+
+define void @loop_2(i32 %size, i32 %nsteps, i32 %hsize, i32* %lined, i8 %tmp1) {
+; CHECK-LABEL: @loop_2(
+entry:
+  %cmp215 = icmp sgt i32 %size, 1
+  %tmp0 = bitcast i32* %lined to i8*
+  br label %for.body
+
+for.body:
+  %j = phi i32 [ 0, %entry ], [ %inc6, %for.inc ]
+  %mul = mul nsw i32 %j, %size
+  %add = add nsw i32 %mul, %hsize
+  br i1 %cmp215, label %for.body2, label %for.inc
+
+; check that the induction variable of the inner loop has been widened after indvars.
+; CHECK:  [[INNERLOOPINV:%[^ ]+]] = add nsw i64
+; CHECK: for.body2:
+; CHECK-NEXT:  %indvars.iv = phi i64 [ 1, %for.body2.preheader ], [ %indvars.iv.next, %for.body2 ]
+; CHECK-NEXT:  [[WIDENED:%[^ ]+]] = add nsw i64 [[INNERLOOPINV]], %indvars.iv
+; CHECK-NEXT:  %add.ptr = getelementptr inbounds i8, i8* %tmp0, i64 [[WIDENED]]
+for.body2:
+  %k = phi i32 [ %inc, %for.body2 ], [ 1, %for.body ]
+  %add4 = add nsw i32 %add, %k
+  %idx.ext = sext i32 %add4 to i64
+  %add.ptr = getelementptr inbounds i8, i8* %tmp0, i64 %idx.ext
+  store i8 %tmp1, i8* %add.ptr, align 1
+  %inc = add nsw i32 %k, 1
+  %cmp2 = icmp slt i32 %inc, %size
+  br i1 %cmp2, label %for.body2, label %for.body3
+
+; check that the induction variable of the inner loop has been widened after indvars.
+; CHECK: for.body3.preheader:
+; CHECK:  [[INNERLOOPINV:%[^ ]+]] = zext i32
+; CHECK: for.body3:
+; CHECK-NEXT:  %indvars.iv2 = phi i64 [ 1, %for.body3.preheader ], [ %indvars.iv.next3, %for.body3 ]
+; CHECK-NEXT:  [[WIDENED:%[^ ]+]] = add nuw nsw i64 [[INNERLOOPINV]], %indvars.iv2
+; CHECK-NEXT:  %add.ptr2 = getelementptr inbounds i8, i8* %tmp0, i64 [[WIDENED]]
+for.body3:
+  %l = phi i32 [ %inc2, %for.body3 ], [ 1, %for.body2 ]
+  %add5 = add nuw i32 %add, %l
+  %idx.ext2 = zext i32 %add5 to i64
+  %add.ptr2 = getelementptr inbounds i8, i8* %tmp0, i64 %idx.ext2
+  store i8 %tmp1, i8* %add.ptr2, align 1
+  %inc2 = add nsw i32 %l, 1
+  %cmp3 = icmp slt i32 %inc2, %size
+  br i1 %cmp3, label %for.body3, label %for.inc
+
+for.inc:
+  %inc6 = add nsw i32 %j, 1
+  %cmp = icmp slt i32 %inc6, %nsteps
+  br i1 %cmp, label %for.body, label %for.end.loopexit
+
+for.end.loopexit:
+  ret void
+}