Index: llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll
@@ -0,0 +1,55 @@
+; RUN: opt -loop-vectorize -scalable-vectorization=off -force-vector-width=4 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S < %s 2>&1 | FileCheck %s
+
+; NOTE: These tests aren't really target-specific, but it's convenient to target AArch64
+; so that TTI.isLegalMaskedLoad can return true.
+
+target triple = "aarch64-linux-gnu"
+
+; The original loop had a conditional uniform load. In this case we actually
+; do need to perform conditional loads and so we end up using a gather instead.
+; However, we at least ensure the mask is the overlap of the loop predicate
+; and the original condition.
+define void @cond_uniform_load(i32* nocapture %dst, i32* nocapture readonly %src, i32* nocapture readonly %cond, i64 %n) #0 {
+; CHECK-LABEL: @cond_uniform_load(
+; CHECK:       vector.ph:
+; CHECK:         [[TMP1:%.*]] = insertelement <4 x i32*> poison, i32* %src, i32 0
+; CHECK-NEXT:    [[SRC_SPLAT:%.*]] = shufflevector <4 x i32*> [[TMP1]], <4 x i32*> poison, <4 x i32> zeroinitializer
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[IDX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[IDX_NEXT:%.*]], %vector.body ]
+; CHECK:         [[TMP1:%.*]] = insertelement <4 x i64> poison, i64 [[IDX]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[TMP2]], <i64 0, i64 1, i64 2, i64 3>
+; CHECK:         [[LOOP_PRED:%.*]] = icmp ule <4 x i64> [[INDUCTION]]
+; CHECK:         [[COND_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* {{%.*}}, i32 4, <4 x i1> [[LOOP_PRED]], <4 x i32> poison)
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq <4 x i32> [[COND_LOAD]], zeroinitializer
+; CHECK-NEXT:    [[TMP4:%.*]] = xor <4 x i1> [[TMP3]], <i1 true, i1 true, i1 true, i1 true>
+; CHECK-NEXT:    [[MASK:%.*]] = select <4 x i1> [[LOOP_PRED]], <4 x i1> [[TMP4]], <4 x i1> zeroinitializer
+; CHECK-NEXT:    call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> [[SRC_SPLAT]], i32 4, <4 x i1> [[MASK]], <4 x i32> undef)
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %if.end
+  %index = phi i64 [ %index.next, %if.end ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i32, i32* %cond, i64 %index
+  %0 = load i32, i32* %arrayidx, align 4
+  %tobool.not = icmp eq i32 %0, 0
+  br i1 %tobool.not, label %if.end, label %if.then
+
+if.then:                                          ; preds = %for.body
+  %1 = load i32, i32* %src, align 4
+  br label %if.end
+
+if.end:                                           ; preds = %if.then, %for.body
+  %val.0 = phi i32 [ %1, %if.then ], [ 0, %for.body ]
+  %arrayidx1 = getelementptr inbounds i32, i32* %dst, i64 %index
+  store i32 %val.0, i32* %arrayidx1, align 4
+  %index.next = add nuw i64 %index, 1
+  %exitcond.not = icmp eq i64 %index.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.inc, %entry
+  ret void
+}
+
+
+attributes #0 = { "target-features"="+neon,+sve,+v8.1a" }