; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt < %s -loop-predication -S | FileCheck %s ; RUN: opt -S -passes='require<scalar-evolution>,loop-mssa(loop-predication)' -verify-memoryssa < %s 2>&1 | FileCheck %s declare void @prevent_merging() ; Base case - with side effects in loop define i32 @test1(i32* %array, i32 %length, i32 %n, i1 %cond_0) { ; CHECK-LABEL: @test1( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1) ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1 ; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]]) ; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]] ; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]] ; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]] ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP3]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]] ; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; 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: store i32 0, 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:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, %length br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: %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 store i32 0, i32* %array.i.ptr %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 [ %loop.acc.next, %guarded ] ret i32 %result } define i32 @test_non_canonical(i32* %array, i32 %length, i1 %cond_0) { ; CHECK-LABEL: @test_non_canonical( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[LENGTH:%.*]], i32 1) ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1 ; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH]], i32 [[TMP0]]) ; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]] ; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]] ; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]] ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP3]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]] ; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; 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: store i32 0, 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]], [[LENGTH]] ; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, %length br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: %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 store i32 0, i32* %array.i.ptr %loop.acc.next = add i32 %loop.acc, %array.i %i.next = add nuw i32 %i, 1 %continue = icmp ult i32 %i.next, %length br i1 %continue, label %loop, label %exit exit: %result = phi i32 [ %loop.acc.next, %guarded ] ret i32 %result } define i32 @test_two_range_checks(i32* %array, i32 %length.1, i32 %length.2, i32 %n, i1 %cond_0) { ; CHECK-LABEL: @test_two_range_checks( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH_2:%.*]], i32 [[LENGTH_1:%.*]]) ; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1) ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1 ; CHECK-NEXT: [[UMIN1:%.*]] = call i32 @llvm.umin.i32(i32 [[UMIN]], i32 [[TMP0]]) ; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH_1]], [[UMIN1]] ; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]] ; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]] ; CHECK-NEXT: [[TMP4:%.*]] = icmp ugt i32 [[LENGTH_2]], [[UMIN1]] ; CHECK-NEXT: [[TMP5:%.*]] = freeze i1 [[TMP4]] ; CHECK-NEXT: [[TMP6:%.*]] = and i1 [[TMP5]], [[TMP3]] ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP6]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH_1]] ; CHECK-NEXT: br i1 true, label [[GUARDED:%.*]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; CHECK-NEXT: [[WITHIN_BOUNDS2:%.*]] = icmp ult i32 [[I]], [[LENGTH_2]] ; CHECK-NEXT: br i1 true, label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0 ; CHECK: deopt3: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET3]] ; CHECK: guarded2: ; 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: store i32 0, 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:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, %length.1 br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: %within.bounds2 = icmp ult i32 %i, %length.2 br i1 %within.bounds2, label %guarded2, label %deopt3, !prof !0 deopt3: call void @unknown() %deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret3 guarded2: %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 store i32 0, i32* %array.i.ptr %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 [ %loop.acc.next, %guarded2 ] ret i32 %result } @G = external global i32 define i32 @test_unanalyzeable_exit(i32* %array, i32 %length, i32 %n, i1 %cond_0) { ; CHECK-LABEL: @test_unanalyzeable_exit( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[COND_0:%.*]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[VOL:%.*]] = load volatile i32, i32* @G, align 4 ; CHECK-NEXT: [[UNKNOWN:%.*]] = icmp eq i32 [[VOL]], 0 ; CHECK-NEXT: br i1 [[UNKNOWN]], label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0 ; CHECK: deopt3: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET3]] ; CHECK: guarded2: ; 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: store i32 0, 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:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ] call void @unknown() %vol = load volatile i32, i32* @G %unknown = icmp eq i32 %vol, 0 br i1 %unknown, label %guarded2, label %deopt3, !prof !0 deopt3: call void @unknown() %deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret3 guarded2: %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 store i32 0, i32* %array.i.ptr %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 [ %loop.acc.next, %guarded2 ] ret i32 %result } define i32 @test_unanalyzeable_exit2(i32* %array, i32 %length, i32 %n, i1 %cond_0) { ; CHECK-LABEL: @test_unanalyzeable_exit2( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1) ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1 ; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]]) ; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]] ; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]] ; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]] ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP3]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]] ; CHECK-NEXT: br i1 true, label [[GUARDED:%.*]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; CHECK-NEXT: [[VOL:%.*]] = load volatile i32, i32* @G, align 4 ; CHECK-NEXT: [[UNKNOWN:%.*]] = icmp eq i32 [[VOL]], 0 ; CHECK-NEXT: br i1 [[UNKNOWN]], label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0 ; CHECK: deopt3: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET3]] ; CHECK: guarded2: ; 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: store i32 0, 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:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, %length br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: %vol = load volatile i32, i32* @G %unknown = icmp eq i32 %vol, 0 br i1 %unknown, label %guarded2, label %deopt3, !prof !0 deopt3: call void @unknown() %deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret3 guarded2: %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 store i32 0, i32* %array.i.ptr %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 [ %loop.acc.next, %guarded2 ] ret i32 %result } define i32 @test_unanalyzeable_latch(i32* %array, i32 %length, i32 %n, i1 %cond_0) { ; CHECK-LABEL: @test_unanalyzeable_latch( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[COND_0:%.*]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH:%.*]] ; CHECK-NEXT: br i1 [[WITHIN_BOUNDS]], label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; 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: store i32 0, 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: [[VOL:%.*]] = load volatile i32, i32* @G, align 4 ; CHECK-NEXT: [[UNKNOWN:%.*]] = icmp eq i32 [[VOL]], 0 ; CHECK-NEXT: br i1 [[UNKNOWN]], label [[LOOP]], label [[EXIT:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, %length br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: %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 store i32 0, i32* %array.i.ptr %loop.acc.next = add i32 %loop.acc, %array.i %i.next = add nuw i32 %i, 1 %vol = load volatile i32, i32* @G %unknown = icmp eq i32 %vol, 0 br i1 %unknown, label %loop, label %exit exit: %result = phi i32 [ %loop.acc.next, %guarded ] ret i32 %result } define i32 @provably_taken(i32* %array, i1 %cond_0) { ; CHECK-LABEL: @provably_taken( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[TMP0:%.*]] = freeze i1 false ; CHECK-NEXT: [[TMP1:%.*]] = and i1 [[TMP0]], [[COND_0:%.*]] ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP1]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], 198 ; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; 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: store i32 0, 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]], 200 ; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, 198 br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: %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 store i32 0, i32* %array.i.ptr %loop.acc.next = add i32 %loop.acc, %array.i %i.next = add nuw i32 %i, 1 %continue = icmp ult i32 %i.next, 200 br i1 %continue, label %loop, label %exit exit: %result = phi i32 [ %loop.acc.next, %guarded ] ret i32 %result } define i32 @provably_not_taken(i32* %array, i1 %cond_0) { ; CHECK-LABEL: @provably_not_taken( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[TMP0:%.*]] = freeze i1 true ; CHECK-NEXT: [[TMP1:%.*]] = and i1 [[TMP0]], [[COND_0:%.*]] ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP1]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], 205 ; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; 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: store i32 0, 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]], 200 ; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, 205 br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: %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 store i32 0, i32* %array.i.ptr %loop.acc.next = add i32 %loop.acc, %array.i %i.next = add nuw i32 %i, 1 %continue = icmp ult i32 %i.next, 200 br i1 %continue, label %loop, label %exit exit: %result = phi i32 [ %loop.acc.next, %guarded ] ret i32 %result } ;; Unswitch likes to produce some ugly exit blocks without simplifications ;; being applied. Make sure we can handle that form. define i32 @unswitch_exit_form(i32* %array, i32 %length, i32 %n, i1 %cond_0) { ; CHECK-LABEL: @unswitch_exit_form( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1) ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1 ; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]]) ; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]] ; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]] ; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]] ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP3]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt.loopexit: ; CHECK-NEXT: br label [[DEOPT]] ; CHECK: deopt: ; CHECK-NEXT: [[PHI:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ 1, [[DEOPT_LOOPEXIT:%.*]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: br label [[ACTUAL_DEOPT:%.*]] ; CHECK: actual_deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"(i32 [[PHI]]) ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]] ; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT_LOOPEXIT]], !prof !0 ; CHECK: guarded: ; 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: store i32 0, 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:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: ;; This is written to look like an unsimplified loop exit after unswitch ;; (i.e. phis, merge, and branch to actual block) %phi = phi i32 [0, %entry], [1, %loop] call void @unknown() ;; it's okay to skip possible throws br label %actual_deopt actual_deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"(i32 %phi) ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, %length br i1 %within.bounds, label %guarded, label %deopt, !prof !0 guarded: %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 store i32 0, i32* %array.i.ptr %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 [ %loop.acc.next, %guarded ] ret i32 %result } define i32 @swapped_wb(i32* %array, i32 %length, i32 %n, i1 %cond_0) { ; CHECK-LABEL: @swapped_wb( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1) ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1 ; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]]) ; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]] ; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]] ; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]] ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[WIDENABLE_COND]], [[TMP3]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]] ; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; 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: store i32 0, 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:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %widenable_cond, %cond_0 br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, %length br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: %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 store i32 0, i32* %array.i.ptr %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 [ %loop.acc.next, %guarded ] ret i32 %result } define i32 @trivial_wb(i32* %array, i32 %length, i32 %n) { ; CHECK-LABEL: @trivial_wb( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1) ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1 ; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]]) ; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]] ; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]] ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[TMP3]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]] ; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; 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: store i32 0, 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:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() br i1 %widenable_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, %length br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: %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 store i32 0, i32* %array.i.ptr %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 [ %loop.acc.next, %guarded ] ret i32 %result } ; TODO: Non-latch exits can still be predicated ; This is currently prevented by an overly restrictive profitability check. define i32 @todo_unconditional_latch(i32* %array, i32 %length, i1 %cond_0) { ; CHECK-LABEL: @todo_unconditional_latch( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[COND_0:%.*]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH:%.*]] ; CHECK-NEXT: br i1 [[WITHIN_BOUNDS]], label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; 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: store i32 0, 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: br label [[LOOP]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, %length br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: %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 store i32 0, i32* %array.i.ptr %loop.acc.next = add i32 %loop.acc, %array.i %i.next = add nuw i32 %i, 1 br label %loop } ; If we have a stray widenable branch in the loop, we should still be able to ; run. This can happen when unswitching's cost model avoids unswitching some ; branches. define i32 @wb_in_loop(i32* %array, i32 %length, i32 %n, i1 %cond_0) { ; CHECK-LABEL: @wb_in_loop( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[WC2:%.*]] = call i1 @llvm.experimental.widenable.condition() ; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1) ; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1 ; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]]) ; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]] ; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]] ; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]] ; CHECK-NEXT: [[TMP4:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]] ; CHECK-NEXT: [[TMP5:%.*]] = freeze i1 [[TMP4]] ; CHECK-NEXT: [[TMP6:%.*]] = and i1 [[TMP5]], [[TMP3]] ; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP6]], [[WIDENABLE_COND]] ; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0 ; CHECK: deopt: ; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET]] ; CHECK: loop.preheader: ; CHECK-NEXT: br label [[LOOP:%.*]] ; CHECK: loop: ; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ] ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]] ; CHECK-NEXT: br i1 true, label [[GUARDED:%.*]], label [[DEOPT2:%.*]], !prof !0 ; CHECK: deopt2: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET2]] ; CHECK: guarded: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[WITHIN_BOUNDS2:%.*]] = icmp ult i32 [[I]], [[LENGTH]] ; CHECK-NEXT: [[WB_COND:%.*]] = and i1 [[WITHIN_BOUNDS2]], true ; CHECK-NEXT: br i1 true, label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0 ; CHECK: deopt3: ; CHECK-NEXT: call void @unknown() ; CHECK-NEXT: [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ; CHECK-NEXT: ret i32 [[DEOPTRET3]] ; CHECK: guarded2: ; 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: store i32 0, 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:%.*]] ; CHECK: exit: ; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ] ; CHECK-NEXT: ret i32 [[RESULT]] ; entry: %widenable_cond = call i1 @llvm.experimental.widenable.condition() %wc2 = call i1 @llvm.experimental.widenable.condition() %exiplicit_guard_cond = and i1 %cond_0, %widenable_cond br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0 deopt: %deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret loop.preheader: br label %loop loop: %loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ] %i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ] call void @unknown() %within.bounds = icmp ult i32 %i, %length br i1 %within.bounds, label %guarded, label %deopt2, !prof !0 deopt2: call void @unknown() %deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret2 guarded: call void @unknown() %within.bounds2 = icmp ult i32 %i, %length %wb_cond = and i1 %within.bounds2, %wc2 br i1 %wb_cond, label %guarded2, label %deopt3, !prof !0 deopt3: call void @unknown() %deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ] ret i32 %deoptret3 guarded2: %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 store i32 0, i32* %array.i.ptr %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 [ %loop.acc.next, %guarded2 ] ret i32 %result } define void @test_memssa() { bb: %tmp = call i1 @llvm.experimental.widenable.condition() %tmp1 = call i1 @llvm.experimental.widenable.condition() br i1 %tmp, label %bb3, label %bb2 bb2: ; preds = %bb unreachable bb3: ; preds = %bb br label %bb4 bb4: ; preds = %bb6, %bb3 %tmp5 = phi i32 [ %tmp7, %bb6 ], [ 0, %bb3 ] br i1 undef, label %bb10, label %bb6 bb6: ; preds = %bb4 %tmp7 = add nuw nsw i32 %tmp5, 1 %tmp8 = icmp ult i32 %tmp7, undef br i1 %tmp8, label %bb4, label %bb9 bb9: ; preds = %bb6 ret void bb10: ; preds = %bb4 ret void } declare void @unknown() declare i1 @llvm.experimental.widenable.condition() declare i32 @llvm.experimental.deoptimize.i32(...) !0 = !{!"branch_weights", i32 1048576, i32 1} !1 = !{i32 1, i32 -2147483648} !2 = !{i32 0, i32 50}