diff --git a/test/Transforms/LoopPredication/invariant_load.ll b/test/Transforms/LoopPredication/invariant_load.ll new file mode 100644 index 00000000000..a49c522c6b4 --- /dev/null +++ b/test/Transforms/LoopPredication/invariant_load.ll @@ -0,0 +1,247 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt -S -basicaa -loop-predication < %s 2>&1 | FileCheck %s +; RUN: opt -S -aa-pipeline=basic-aa -passes='require,require,loop(loop-predication)' < %s 2>&1 | FileCheck %s + +declare void @llvm.experimental.guard(i1, ...) + +@UNKNOWN = external global i1 + +define i32 @neg_length_variant(i32* %array, i32* %length, i32 %n) { +; CHECK-LABEL: @neg_length_variant( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[N:%.*]], 0 +; CHECK-NEXT: br i1 [[TMP5]], label [[EXIT:%.*]], label [[LOOP_PREHEADER:%.*]] +; CHECK: loop.preheader: +; CHECK-NEXT: br label [[LOOP:%.*]] +; CHECK: loop: +; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[LOOP]] ], [ 0, [[LOOP_PREHEADER]] ] +; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[LOOP]] ], [ 0, [[LOOP_PREHEADER]] ] +; CHECK-NEXT: [[UNKNOWN:%.*]] = load volatile i1, i1* @UNKNOWN +; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[UNKNOWN]]) [ "deopt"() ] +; CHECK-NEXT: [[LEN:%.*]] = load i32, i32* [[LENGTH:%.*]], align 4 +; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LEN]] +; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[WITHIN_BOUNDS]], i32 9) [ "deopt"() ] +; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64 +; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]] +; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4 +; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]] +; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1 +; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]] +; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT_LOOPEXIT:%.*]] +; CHECK: exit.loopexit: +; CHECK-NEXT: [[LOOP_ACC_NEXT_LCSSA:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[LOOP]] ] +; CHECK-NEXT: br label [[EXIT]] +; CHECK: exit: +; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[LOOP_ACC_NEXT_LCSSA]], [[EXIT_LOOPEXIT]] ] +; CHECK-NEXT: ret i32 [[RESULT]] +; +entry: + %tmp5 = icmp eq i32 %n, 0 + br i1 %tmp5, label %exit, label %loop.preheader + +loop.preheader: + br label %loop + +loop: + %loop.acc = phi i32 [ %loop.acc.next, %loop ], [ 0, %loop.preheader ] + %i = phi i32 [ %i.next, %loop ], [ 0, %loop.preheader ] + %unknown = load volatile i1, i1* @UNKNOWN + call void (i1, ...) @llvm.experimental.guard(i1 %unknown) [ "deopt"() ] + %len = load i32, i32* %length, align 4 + %within.bounds = icmp ult i32 %i, %len + call void (i1, ...) @llvm.experimental.guard(i1 %within.bounds, i32 9) [ "deopt"() ] + + %i.i64 = zext i32 %i to i64 + %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64 + %array.i = load i32, i32* %array.i.ptr, align 4 + %loop.acc.next = add i32 %loop.acc, %array.i + + %i.next = add nuw i32 %i, 1 + %continue = icmp ult i32 %i.next, %n + br i1 %continue, label %loop, label %exit + +exit: + %result = phi i32 [ 0, %entry ], [ %loop.acc.next, %loop ] + ret i32 %result +} + +define i32 @invariant_load(i32* %array, i32* %length, i32 %n) { +; CHECK-LABEL: @invariant_load( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[N:%.*]], 0 +; CHECK-NEXT: br i1 [[TMP5]], label [[EXIT:%.*]], label [[LOOP_PREHEADER:%.*]] +; CHECK: loop.preheader: +; CHECK-NEXT: br label [[LOOP:%.*]] +; CHECK: loop: +; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[LOOP]] ], [ 0, [[LOOP_PREHEADER]] ] +; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[LOOP]] ], [ 0, [[LOOP_PREHEADER]] ] +; CHECK-NEXT: [[UNKNOWN:%.*]] = load volatile i1, i1* @UNKNOWN +; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[UNKNOWN]]) [ "deopt"() ] +; CHECK-NEXT: [[LEN:%.*]] = load i32, i32* [[LENGTH:%.*]], align 4, !invariant.load !0 +; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LEN]] +; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[WITHIN_BOUNDS]], i32 9) [ "deopt"() ] +; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64 +; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]] +; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4 +; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]] +; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1 +; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]] +; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT_LOOPEXIT:%.*]] +; CHECK: exit.loopexit: +; CHECK-NEXT: [[LOOP_ACC_NEXT_LCSSA:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[LOOP]] ] +; CHECK-NEXT: br label [[EXIT]] +; CHECK: exit: +; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[LOOP_ACC_NEXT_LCSSA]], [[EXIT_LOOPEXIT]] ] +; CHECK-NEXT: ret i32 [[RESULT]] +; +entry: + %tmp5 = icmp eq i32 %n, 0 + br i1 %tmp5, label %exit, label %loop.preheader + +loop.preheader: + br label %loop + +loop: + %loop.acc = phi i32 [ %loop.acc.next, %loop ], [ 0, %loop.preheader ] + %i = phi i32 [ %i.next, %loop ], [ 0, %loop.preheader ] + %unknown = load volatile i1, i1* @UNKNOWN + call void (i1, ...) @llvm.experimental.guard(i1 %unknown) [ "deopt"() ] + %len = load i32, i32* %length, align 4, !invariant.load !{} + %within.bounds = icmp ult i32 %i, %len + call void (i1, ...) @llvm.experimental.guard(i1 %within.bounds, i32 9) [ "deopt"() ] + + %i.i64 = zext i32 %i to i64 + %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64 + %array.i = load i32, i32* %array.i.ptr, align 4 + %loop.acc.next = add i32 %loop.acc, %array.i + + %i.next = add nuw i32 %i, 1 + %continue = icmp ult i32 %i.next, %n + br i1 %continue, label %loop, label %exit + +exit: + %result = phi i32 [ 0, %entry ], [ %loop.acc.next, %loop ] + ret i32 %result +} + +@Length = external constant i32 + +define i32 @constant_memory(i32* %array, i32 %n) { +; CHECK-LABEL: @constant_memory( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[N:%.*]], 0 +; CHECK-NEXT: br i1 [[TMP5]], label [[EXIT:%.*]], label [[LOOP_PREHEADER:%.*]] +; CHECK: loop.preheader: +; CHECK-NEXT: br label [[LOOP:%.*]] +; CHECK: loop: +; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[LOOP]] ], [ 0, [[LOOP_PREHEADER]] ] +; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[LOOP]] ], [ 0, [[LOOP_PREHEADER]] ] +; CHECK-NEXT: [[UNKNOWN:%.*]] = load volatile i1, i1* @UNKNOWN +; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[UNKNOWN]]) [ "deopt"() ] +; CHECK-NEXT: [[LEN:%.*]] = load i32, i32* @Length, align 4 +; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LEN]] +; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[WITHIN_BOUNDS]], i32 9) [ "deopt"() ] +; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64 +; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]] +; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4 +; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]] +; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1 +; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]] +; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT_LOOPEXIT:%.*]] +; CHECK: exit.loopexit: +; CHECK-NEXT: [[LOOP_ACC_NEXT_LCSSA:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[LOOP]] ] +; CHECK-NEXT: br label [[EXIT]] +; CHECK: exit: +; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[LOOP_ACC_NEXT_LCSSA]], [[EXIT_LOOPEXIT]] ] +; CHECK-NEXT: ret i32 [[RESULT]] +; +entry: + %tmp5 = icmp eq i32 %n, 0 + br i1 %tmp5, label %exit, label %loop.preheader + +loop.preheader: + br label %loop + +loop: + %loop.acc = phi i32 [ %loop.acc.next, %loop ], [ 0, %loop.preheader ] + %i = phi i32 [ %i.next, %loop ], [ 0, %loop.preheader ] + %unknown = load volatile i1, i1* @UNKNOWN + call void (i1, ...) @llvm.experimental.guard(i1 %unknown) [ "deopt"() ] + %len = load i32, i32* @Length, align 4 + %within.bounds = icmp ult i32 %i, %len + call void (i1, ...) @llvm.experimental.guard(i1 %within.bounds, i32 9) [ "deopt"() ] + + %i.i64 = zext i32 %i to i64 + %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64 + %array.i = load i32, i32* %array.i.ptr, align 4 + %loop.acc.next = add i32 %loop.acc, %array.i + + %i.next = add nuw i32 %i, 1 + %continue = icmp ult i32 %i.next, %n + br i1 %continue, label %loop, label %exit + +exit: + %result = phi i32 [ 0, %entry ], [ %loop.acc.next, %loop ] + ret i32 %result +} + +define i32 @constant_length(i32* %array, i32 %n) { +; CHECK-LABEL: @constant_length( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[N:%.*]], 0 +; CHECK-NEXT: br i1 [[TMP5]], label [[EXIT:%.*]], label [[LOOP_PREHEADER:%.*]] +; CHECK: loop.preheader: +; CHECK-NEXT: [[TMP0:%.*]] = icmp ule i32 [[N]], 20 +; CHECK-NEXT: [[TMP1:%.*]] = and i1 true, [[TMP0]] +; CHECK-NEXT: br label [[LOOP:%.*]] +; CHECK: loop: +; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[LOOP]] ], [ 0, [[LOOP_PREHEADER]] ] +; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[LOOP]] ], [ 0, [[LOOP_PREHEADER]] ] +; CHECK-NEXT: [[UNKNOWN:%.*]] = load volatile i1, i1* @UNKNOWN +; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[UNKNOWN]]) [ "deopt"() ] +; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], 20 +; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[TMP1]], i32 9) [ "deopt"() ] +; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64 +; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]] +; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4 +; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]] +; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1 +; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]] +; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT_LOOPEXIT:%.*]] +; CHECK: exit.loopexit: +; CHECK-NEXT: [[LOOP_ACC_NEXT_LCSSA:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[LOOP]] ] +; CHECK-NEXT: br label [[EXIT]] +; CHECK: exit: +; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[LOOP_ACC_NEXT_LCSSA]], [[EXIT_LOOPEXIT]] ] +; CHECK-NEXT: ret i32 [[RESULT]] +; +entry: + %tmp5 = icmp eq i32 %n, 0 + br i1 %tmp5, label %exit, label %loop.preheader + +loop.preheader: + br label %loop + +loop: + %loop.acc = phi i32 [ %loop.acc.next, %loop ], [ 0, %loop.preheader ] + %i = phi i32 [ %i.next, %loop ], [ 0, %loop.preheader ] + %unknown = load volatile i1, i1* @UNKNOWN + call void (i1, ...) @llvm.experimental.guard(i1 %unknown) [ "deopt"() ] + %within.bounds = icmp ult i32 %i, 20 + call void (i1, ...) @llvm.experimental.guard(i1 %within.bounds, i32 9) [ "deopt"() ] + + %i.i64 = zext i32 %i to i64 + %array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64 + %array.i = load i32, i32* %array.i.ptr, align 4 + %loop.acc.next = add i32 %loop.acc, %array.i + + %i.next = add nuw i32 %i, 1 + %continue = icmp ult i32 %i.next, %n + br i1 %continue, label %loop, label %exit + +exit: + %result = phi i32 [ 0, %entry ], [ %loop.acc.next, %loop ] + ret i32 %result +} + +