[LoopVectorize] LLVM fails to vectorise loops with multi-bool varables (#89226)

This change allows to consider compare instructions in the loop with
multiple use inside the loop and outside.

This change allows to vectorise this loop:
int foo(float* a, int n) {
  _Bool any = 0;
  _Bool all = 1;
  for (int i = 0; i < n; i++) {
    if (a[i] < 0.0f) {
      any = 1;
    } else {
      all = 0;
    }
  }
  return all ? 1 : any ? 2 : 3;
}

Author: Dinar Temirbulatov

llvm/lib/Analysis/IVDescriptors.cpp

@@ -635,9 +635,8 @@ RecurrenceDescriptor::isAnyOfPattern(Loop *Loop, PHINode *OrigPhi,
       return InstDesc(Select, Prev.getRecKind());
   }
 
-  // Only match select with single use cmp condition.
-  if (!match(I, m_Select(m_OneUse(m_Cmp(Pred, m_Value(), m_Value())), m_Value(),
-                         m_Value())))
+  if (!match(I,
+             m_Select(m_Cmp(Pred, m_Value(), m_Value()), m_Value(), m_Value())))
     return InstDesc(false, I);
 
   SelectInst *SI = cast<SelectInst>(I);

llvm/test/Transforms/LoopVectorize/AArch64/select-costs.ll

@@ -1,28 +1,26 @@
 ; REQUIRES: asserts
-; RUN: opt < %s -passes=loop-vectorize -debug-only=loop-vectorize -S 2>&1 | FileCheck %s
+; RUN: opt < %s -passes=loop-vectorize -debug-only=loop-vectorize -disable-output -S 2>&1 | FileCheck %s
 
 target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
 target triple = "arm64-apple-ios5.0.0"
 
 define void @selects_1(ptr nocapture %dst, i32 %A, i32 %B, i32 %C, i32 %N) {
+; CHECK: LV: Checking a loop in 'selects_1'
 ; CHECK: LV: Found an estimated cost of 1 for VF 2 For instruction:   %cond = select i1 %cmp1, i32 10, i32 %and
 ; CHECK: LV: Found an estimated cost of 1 for VF 2 For instruction:   %cond6 = select i1 %cmp2, i32 30, i32 %and
 ; CHECK: LV: Found an estimated cost of 1 for VF 2 For instruction:   %cond11 = select i1 %cmp7, i32 %cond, i32 %cond6
 
 ; CHECK: LV: Found an estimated cost of 1 for VF 4 For instruction:   %cond = select i1 %cmp1, i32 10, i32 %and
 ; CHECK: LV: Found an estimated cost of 1 for VF 4 For instruction:   %cond6 = select i1 %cmp2, i32 30, i32 %and
 ; CHECK: LV: Found an estimated cost of 1 for VF 4 For instruction:   %cond11 = select i1 %cmp7, i32 %cond, i32 %cond6
-
-; CHECK-LABEL: define void @selects_1(
-; CHECK:       vector.body:
-; CHECK:         select <4 x i1>
+; CHECK: LV: Selecting VF: 4
 
 entry:
   %cmp26 = icmp sgt i32 %N, 0
   br i1 %cmp26, label %for.body.preheader, label %for.cond.cleanup
 
 for.body.preheader:                               ; preds = %entry
-  %wide.trip.count = zext i32 %N to i64
+  %n = zext i32 %N to i64
   br label %for.body
 
 for.body:                                         ; preds = %for.body.preheader, %for.body
@@ -38,7 +36,7 @@ for.body:                                         ; preds = %for.body.preheader,
   %cond11 = select i1 %cmp7, i32 %cond, i32 %cond6
   store i32 %cond11, ptr %arrayidx, align 4
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
+  %exitcond.not = icmp eq i64 %indvars.iv.next, %n
   br i1 %exitcond.not, label %for.cond.cleanup.loopexit, label %for.body
 
 for.cond.cleanup.loopexit:                        ; preds = %for.body
@@ -47,3 +45,31 @@ for.cond.cleanup.loopexit:                        ; preds = %for.body
 for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
   ret void
 }
+
+define i32 @multi_user_cmp(ptr readonly %a, i64 noundef %n) {
+; CHECK: LV: Checking a loop in 'multi_user_cmp'
+; CHECK: LV: Found an estimated cost of 4 for VF 16 For instruction:   %cmp1 = fcmp olt float %load1, 0.000000e+00
+; CHECK: LV: Found an estimated cost of 1 for VF 16 For instruction:   %.any.0.off0 = select i1 %cmp1, i1 true, i1 %any.0.off09
+; CHECK: LV: Found an estimated cost of 1 for VF 16 For instruction:   %all.off = select i1 %cmp1, i1 %all.off.next, i1 false
+; CHECK: LV: Selecting VF: 16.
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %all.off.next = phi i1 [ true, %entry ], [ %all.off, %for.body ]
+  %any.0.off09 = phi i1 [ false, %entry ], [ %.any.0.off0, %for.body ]
+  %arrayidx = getelementptr inbounds float, ptr %a, i64 %indvars.iv
+  %load1 = load float, ptr %arrayidx, align 4
+  %cmp1 = fcmp olt float %load1, 0.000000e+00
+  %.any.0.off0 = select i1 %cmp1, i1 true, i1 %any.0.off09
+  %all.off = select i1 %cmp1, i1 %all.off.next, i1 false
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond.not = icmp eq i64 %indvars.iv.next, %n
+  br i1 %exitcond.not, label %exit, label %for.body
+
+exit:
+  %0 = select i1 %.any.0.off0, i32 2, i32 3
+  %1 = select i1 %all.off, i32 1, i32 %0
+  ret i32 %1
+}