[LoopVectorize][NFC] Regenerate some early exit test CHECK lines (#124900)

Author: david-arm

llvm/test/Transforms/LoopVectorize/AArch64/simple_early_exit.ll

@@ -15,20 +15,20 @@ define i64 @same_exit_block_pre_inc_use1() #1 {
 ; CHECK-NEXT:    call void @init_mem(ptr [[P2]], i64 1024)
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
-; CHECK-NEXT:    [[INDEX2:%.*]] = phi i64 [ [[INDEX_NEXT1:%.*]], [[LOOP_INC:%.*]] ], [ 3, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[P1]], i64 [[INDEX2]]
-; CHECK-NEXT:    [[TMP38:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
-; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[P2]], i64 [[INDEX2]]
-; CHECK-NEXT:    [[TMP39:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
-; CHECK-NEXT:    [[CMP3:%.*]] = icmp eq i8 [[TMP38]], [[TMP39]]
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[LOOP_INC:%.*]] ], [ 3, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[P1]], i64 [[INDEX]]
+; CHECK-NEXT:    [[LD1:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[P2]], i64 [[INDEX]]
+; CHECK-NEXT:    [[LD2:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT:    [[CMP3:%.*]] = icmp eq i8 [[LD1]], [[LD2]]
 ; CHECK-NEXT:    br i1 [[CMP3]], label [[LOOP_INC]], label [[LOOP_END:%.*]]
 ; CHECK:       loop.inc:
-; CHECK-NEXT:    [[INDEX_NEXT1]] = add i64 [[INDEX2]], 1
-; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i64 [[INDEX_NEXT1]], 67
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 1
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i64 [[INDEX_NEXT]], 67
 ; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LOOP]], label [[LOOP_END]]
 ; CHECK:       loop.end:
-; CHECK-NEXT:    [[START_0_LCSSA:%.*]] = phi i64 [ [[INDEX2]], [[LOOP]] ], [ 67, [[LOOP_INC]] ]
-; CHECK-NEXT:    ret i64 [[START_0_LCSSA]]
+; CHECK-NEXT:    [[RETVAL:%.*]] = phi i64 [ [[INDEX]], [[LOOP]] ], [ 67, [[LOOP_INC]] ]
+; CHECK-NEXT:    ret i64 [[RETVAL]]
 ;
 entry:
   %p1 = alloca [1024 x i8]
@@ -66,7 +66,7 @@ define i64 @same_exit_block_pre_inc_use4() {
 ; CHECK-NEXT:    [[P2:%.*]] = alloca [1024 x i64], align 8
 ; CHECK-NEXT:    call void @init_mem(ptr [[P1]], i64 1024)
 ; CHECK-NEXT:    call void @init_mem(ptr [[P2]], i64 1024)
-; CHECK-NEXT:    br label [[LOOP1:%.*]]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[LOOP_INC:%.*]] ], [ 3, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[P1]], i64 [[INDEX]]
@@ -76,9 +76,9 @@ define i64 @same_exit_block_pre_inc_use4() {
 ; CHECK:       loop.inc:
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i64 [[INDEX_NEXT]], 67
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LOOP1]], label [[LOOP_END]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LOOP]], label [[LOOP_END]]
 ; CHECK:       loop.end:
-; CHECK-NEXT:    [[RETVAL:%.*]] = phi i64 [ [[INDEX]], [[LOOP1]] ], [ 67, [[LOOP_INC]] ]
+; CHECK-NEXT:    [[RETVAL:%.*]] = phi i64 [ [[INDEX]], [[LOOP]] ], [ 67, [[LOOP_INC]] ]
 ; CHECK-NEXT:    ret i64 [[RETVAL]]
 ;
 entry:
@@ -114,20 +114,20 @@ define i64 @loop_contains_safe_call() #1 {
 ; 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:    br label [[LOOP1:%.*]]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
-; CHECK-NEXT:    [[INDEX2:%.*]] = phi i64 [ [[INDEX_NEXT1:%.*]], [[LOOP_INC1:%.*]] ], [ 3, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[P1]], i64 [[INDEX2]]
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[LOOP_INC:%.*]] ], [ 3, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[P1]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[LD1:%.*]] = load float, ptr [[ARRAYIDX]], align 1
 ; CHECK-NEXT:    [[SQRT:%.*]] = tail call fast float @llvm.sqrt.f32(float [[LD1]])
 ; CHECK-NEXT:    [[CMP:%.*]] = fcmp fast ult float [[SQRT]], 3.000000e+00
-; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP_INC1]], label [[LOOP_END:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP_INC]], label [[LOOP_END:%.*]]
 ; CHECK:       loop.inc:
-; CHECK-NEXT:    [[INDEX_NEXT1]] = add i64 [[INDEX2]], 1
-; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i64 [[INDEX_NEXT1]], 67
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LOOP1]], label [[LOOP_END]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 1
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i64 [[INDEX_NEXT]], 67
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LOOP]], label [[LOOP_END]]
 ; CHECK:       loop.end:
-; CHECK-NEXT:    [[RETVAL:%.*]] = phi i64 [ [[INDEX2]], [[LOOP1]] ], [ 67, [[LOOP_INC1]] ]
+; CHECK-NEXT:    [[RETVAL:%.*]] = phi i64 [ [[INDEX]], [[LOOP]] ], [ 67, [[LOOP_INC]] ]
 ; CHECK-NEXT:    ret i64 [[RETVAL]]
 ;
 entry:
@@ -216,7 +216,7 @@ define i64 @loop_contains_load_after_early_exit(ptr dereferenceable(1024) align(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[P1:%.*]] = alloca [1024 x i8], align 4
 ; CHECK-NEXT:    call void @init_mem(ptr [[P1]], i64 1024)
-; CHECK-NEXT:    br label [[LOOP1:%.*]]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[LOOP_INC:%.*]] ], [ 3, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[P1]], i64 [[INDEX]]
@@ -228,9 +228,9 @@ define i64 @loop_contains_load_after_early_exit(ptr dereferenceable(1024) align(
 ; CHECK-NEXT:    [[LD2:%.*]] = load i64, ptr [[ARRAYIDX2]], align 8
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 1
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i64 [[INDEX_NEXT]], 67
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LOOP1]], label [[LOOP_END]]
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LOOP]], label [[LOOP_END]]
 ; CHECK:       loop.end:
-; CHECK-NEXT:    [[RETVAL:%.*]] = phi i64 [ [[INDEX]], [[LOOP1]] ], [ [[LD2]], [[LOOP_INC]] ]
+; CHECK-NEXT:    [[RETVAL:%.*]] = phi i64 [ [[INDEX]], [[LOOP]] ], [ [[LD2]], [[LOOP_INC]] ]
 ; CHECK-NEXT:    ret i64 [[RETVAL]]
 ;
 entry:
@@ -272,9 +272,9 @@ define i32 @diff_exit_block_needs_scev_check(i32 %end) {
 ; CHECK-NEXT:    call void @init_mem(ptr [[P1]], i64 1024)
 ; CHECK-NEXT:    call void @init_mem(ptr [[P2]], i64 1024)
 ; CHECK-NEXT:    [[END_CLAMPED:%.*]] = and i32 [[END]], 1023
-; CHECK-NEXT:    [[TMP19:%.*]] = trunc i32 [[END]] to i10
-; CHECK-NEXT:    [[TMP20:%.*]] = zext i10 [[TMP19]] to i64
-; CHECK-NEXT:    [[UMAX1:%.*]] = call i64 @llvm.umax.i64(i64 [[TMP20]], i64 1)
+; CHECK-NEXT:    [[TMP0:%.*]] = trunc i32 [[END]] to i10
+; CHECK-NEXT:    [[TMP1:%.*]] = zext i10 [[TMP0]] to i64
+; CHECK-NEXT:    [[UMAX1:%.*]] = call i64 @llvm.umax.i64(i64 [[TMP1]], i64 1)
 ; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[UMAX1]], 12
 ; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
 ; CHECK:       vector.scevcheck:
@@ -289,40 +289,40 @@ define i32 @diff_exit_block_needs_scev_check(i32 %end) {
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[UMAX1]], 4
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[UMAX1]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[IND_END:%.*]] = trunc i64 [[N_VEC]] to i8
-; CHECK-NEXT:    br label [[FOR_BODY1:%.*]]
+; CHECK-NEXT:    [[TMP8:%.*]] = trunc i64 [[N_VEC]] to i8
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[FOR_BODY1]] ]
-; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, ptr [[P1]], i64 [[TMP8]]
-; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, ptr [[TMP9]], i32 0
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP10]], align 4
-; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, ptr [[P2]], i64 [[TMP8]]
-; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[TMP11]], i32 0
-; CHECK-NEXT:    [[WIDE_LOAD3:%.*]] = load <4 x i32>, ptr [[TMP12]], align 4
-; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq <4 x i32> [[WIDE_LOAD]], [[WIDE_LOAD3]]
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, ptr [[P1]], i64 [[TMP9]]
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, ptr [[TMP10]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP11]], align 4
+; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[P2]], i64 [[TMP9]]
+; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[TMP12]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <4 x i32>, ptr [[TMP13]], align 4
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq <4 x i32> [[WIDE_LOAD]], [[WIDE_LOAD2]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; CHECK-NEXT:    [[TMP16:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[TMP13]])
-; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    [[TMP18:%.*]] = or i1 [[TMP16]], [[TMP17]]
-; CHECK-NEXT:    br i1 [[TMP18]], label [[MIDDLE_SPLIT:%.*]], label [[FOR_BODY1]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT:    [[TMP15:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[TMP14]])
+; CHECK-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    [[TMP17:%.*]] = or i1 [[TMP15]], [[TMP16]]
+; CHECK-NEXT:    br i1 [[TMP17]], label [[MIDDLE_SPLIT:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.split:
-; CHECK-NEXT:    br i1 [[TMP16]], label [[FOUND:%.*]], label [[MIDDLE_BLOCK:%.*]]
+; CHECK-NEXT:    br i1 [[TMP15]], label [[FOUND:%.*]], label [[MIDDLE_BLOCK:%.*]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[UMAX1]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i8 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[BC_RESUME_VAL2:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[ENTRY]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP8]], [[MIDDLE_BLOCK]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL3:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[ENTRY]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[IND:%.*]] = phi i8 [ [[IND_NEXT:%.*]], [[FOR_INC:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
-; CHECK-NEXT:    [[GEP_IND:%.*]] = phi i64 [ [[GEP_IND_NEXT:%.*]], [[FOR_INC]] ], [ [[BC_RESUME_VAL2]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[GEP_IND:%.*]] = phi i64 [ [[GEP_IND_NEXT:%.*]], [[FOR_INC]] ], [ [[BC_RESUME_VAL3]], [[SCALAR_PH]] ]
 ; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[P1]], i64 [[GEP_IND]]
-; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX1]], align 4
+; CHECK-NEXT:    [[TMP18:%.*]] = load i32, ptr [[ARRAYIDX1]], align 4
 ; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[P2]], i64 [[GEP_IND]]
-; CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
-; CHECK-NEXT:    [[CMP_EARLY:%.*]] = icmp eq i32 [[TMP0]], [[TMP1]]
+; CHECK-NEXT:    [[TMP19:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
+; CHECK-NEXT:    [[CMP_EARLY:%.*]] = icmp eq i32 [[TMP18]], [[TMP19]]
 ; CHECK-NEXT:    br i1 [[CMP_EARLY]], label [[FOUND]], label [[FOR_INC]]
 ; CHECK:       for.inc:
 ; CHECK-NEXT:    [[IND_NEXT]] = add i8 [[IND]], 1