[LV] Add tests showing incorrect vector interleaving with early exits.

When interleaving is forced for early-exit loops, we currently create
incorrect code.

Test coverage for scalable vectors is added as AArch64 specific test.

Author: fhahn

llvm/test/Transforms/LoopVectorize/AArch64/single-early-exit-interleave.ll

@@ -0,0 +1,99 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 4
+; RUN: opt -p loop-vectorize -enable-early-exit-vectorization -force-vector-interleave=4 -S %s | FileCheck %s
+
+target triple = "aarch64-unknown-linux-gnu"
+
+declare void @init_mem(ptr, i64);
+
+define i64 @same_exit_block_pre_inc_use1() #0 {
+; CHECK-LABEL: define i64 @same_exit_block_pre_inc_use1(
+; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[P1:%.*]] = alloca [1024 x i8], align 4
+; CHECK-NEXT:    [[P2:%.*]] = alloca [1024 x i8], align 4
+; CHECK-NEXT:    call void @init_mem(ptr [[P1]], i64 1024)
+; CHECK-NEXT:    call void @init_mem(ptr [[P2]], i64 1024)
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 64
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 510, [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 64
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 510, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 510, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 64
+; CHECK-NEXT:    [[INDEX_NEXT:%.*]] = add i64 3, [[N_VEC]]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 3, [[INDEX1]]
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[P1]], i64 [[OFFSET_IDX]]
+; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[TMP7]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 16 x i8>, ptr [[TMP8]], align 1
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[P2]], i64 [[OFFSET_IDX]]
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i8, ptr [[TMP9]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <vscale x 16 x i8>, ptr [[TMP10]], align 1
+; CHECK-NEXT:    [[TMP11:%.*]] = icmp ne <vscale x 16 x i8> [[WIDE_LOAD]], [[WIDE_LOAD2]]
+; CHECK-NEXT:    [[INDEX_NEXT3]] = add nuw i64 [[INDEX1]], [[TMP5]]
+; CHECK-NEXT:    [[TMP12:%.*]] = call i1 @llvm.vector.reduce.or.nxv16i1(<vscale x 16 x i1> [[TMP11]])
+; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT3]], [[N_VEC]]
+; CHECK-NEXT:    [[TMP14:%.*]] = or i1 [[TMP12]], [[TMP13]]
+; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_SPLIT:%.*]], label [[LOOP]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       middle.split:
+; CHECK-NEXT:    br i1 [[TMP12]], label [[VECTOR_EARLY_EXIT:%.*]], label [[LOOP_INC:%.*]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 510, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[LOOP_END:%.*]], label [[SCALAR_PH]]
+; CHECK:       vector.early.exit:
+; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.nxv16i1(<vscale x 16 x i1> [[TMP11]], i1 true)
+; CHECK-NEXT:    [[TMP16:%.*]] = add i64 [[INDEX1]], [[TMP15]]
+; CHECK-NEXT:    [[TMP17:%.*]] = add i64 3, [[TMP16]]
+; CHECK-NEXT:    br label [[LOOP_END]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT]], [[LOOP_INC]] ], [ 3, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[LOOP1:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[INDEX2:%.*]] = phi i64 [ [[INDEX_NEXT1:%.*]], [[LOOP_INC1:%.*]] ], [ [[INDEX]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[P1]], i64 [[INDEX2]]
+; CHECK-NEXT:    [[LD1:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[P2]], i64 [[INDEX2]]
+; CHECK-NEXT:    [[LD2:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT:    [[CMP3:%.*]] = icmp eq i8 [[LD1]], [[LD2]]
+; CHECK-NEXT:    br i1 [[CMP3]], label [[LOOP_INC1]], label [[LOOP_END]]
+; CHECK:       loop.inc:
+; CHECK-NEXT:    [[INDEX_NEXT1]] = add i64 [[INDEX2]], 1
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i64 [[INDEX_NEXT1]], 513
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LOOP1]], label [[LOOP_END]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK:       loop.end:
+; CHECK-NEXT:    [[RETVAL:%.*]] = phi i64 [ [[INDEX2]], [[LOOP1]] ], [ 67, [[LOOP_INC1]] ], [ 67, [[LOOP_INC]] ], [ [[TMP17]], [[VECTOR_EARLY_EXIT]] ]
+; CHECK-NEXT:    ret i64 [[RETVAL]]
+;
+entry:
+  %p1 = alloca [1024 x i8]
+  %p2 = alloca [1024 x i8]
+  call void @init_mem(ptr %p1, i64 1024)
+  call void @init_mem(ptr %p2, i64 1024)
+  br label %loop
+
+loop:
+  %index = phi i64 [ %index.next, %loop.inc ], [ 3, %entry ]
+  %arrayidx = getelementptr inbounds i8, ptr %p1, i64 %index
+  %ld1 = load i8, ptr %arrayidx, align 1
+  %arrayidx1 = getelementptr inbounds i8, ptr %p2, i64 %index
+  %ld2 = load i8, ptr %arrayidx1, align 1
+  %cmp3 = icmp eq i8 %ld1, %ld2
+  br i1 %cmp3, label %loop.inc, label %loop.end
+
+loop.inc:
+  %index.next = add i64 %index, 1
+  %exitcond = icmp ne i64 %index.next, 513
+  br i1 %exitcond, label %loop, label %loop.end
+
+loop.end:
+  %retval = phi i64 [ %index, %loop ], [ 67, %loop.inc ]
+  ret i64 %retval
+}
+
+attributes #0 = { "target-features"="+sve" vscale_range(1,16) }