maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/CodeGenObjCXX/arc.mm

337 lines
12 KiB
Plaintext
Raw Normal View History

Make -fobjc-nonfragile-abi the -cc1 default, since it's the increasingly prevailing case to the point that new features like ARC don't even support the fragile ABI anymore. This required a little bit of reshuffling with exceptions because a check was assuming that ObjCNonFragileABI was only being set in ObjC mode, and that's actually a bit obnoxious to do. Most, though, it involved a perl script to translate a ton of test cases. Mostly no functionality change for driver users, although there are corner cases with disabling language-specific exceptions that we should handle more correctly now. llvm-svn: 140957
2011-10-02 09:16:38 +08:00
// RUN: %clang_cc1 -triple x86_64-apple-darwin10 -emit-llvm -fobjc-runtime-has-weak -fblocks -fobjc-arc -O2 -disable-llvm-optzns -o - %s | FileCheck %s
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
Clean up the analysis of the collection operand to ObjC for-in statements; specifically, make sure to close over any temporaries or cleanups it might require. In ARC, this has implications for the lifetime of the collection, so emit it with a retain and release it upon exit from the loop. rdar://problem/9817306 llvm-svn: 136204
2011-07-27 09:07:15 +08:00
struct NSFastEnumerationState;
@interface NSArray
- (unsigned long) countByEnumeratingWithState: (struct NSFastEnumerationState*) state
objects: (id*) buffer
count: (unsigned long) bufferSize;
@end;
NSArray *nsarray() { return 0; }
// CHECK: define [[NSARRAY:%.*]]* @_Z7nsarrayv()
void use(id);
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// rdar://problem/9315552
// The analogous ObjC testcase test46 in arr.m.
void test0(__weak id *wp, __weak volatile id *wvp) {
extern id test0_helper(void);
// TODO: this is sub-optimal, we should retain at the actual call site.
// TODO: in the non-volatile case, we do not need to be reloading.
// CHECK: [[T0:%.*]] = call i8* @_Z12test0_helperv()
In ARC, reclaim all return values of retainable type, not just those where we have an immediate need of a retained value. As an exception, don't do this when the call is made as the immediate operand of a __bridge retain. This is more in the way of a workaround than an actual guarantee, so it's acceptable to be brittle here. rdar://problem/9504800 llvm-svn: 134605
2011-07-07 14:58:02 +08:00
// CHECK-NEXT: [[T1:%.*]] = call i8* @objc_retainAutoreleasedReturnValue(i8* [[T0]])
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK-NEXT: [[T2:%.*]] = load i8**, i8*** {{%.*}}, align 8
In ARC, reclaim all return values of retainable type, not just those where we have an immediate need of a retained value. As an exception, don't do this when the call is made as the immediate operand of a __bridge retain. This is more in the way of a workaround than an actual guarantee, so it's acceptable to be brittle here. rdar://problem/9504800 llvm-svn: 134605
2011-07-07 14:58:02 +08:00
// CHECK-NEXT: [[T3:%.*]] = call i8* @objc_storeWeak(i8** [[T2]], i8* [[T1]])
// CHECK-NEXT: [[T4:%.*]] = call i8* @objc_retain(i8* [[T3]])
// CHECK-NEXT: store i8* [[T4]], i8**
// CHECK-NEXT: call void @objc_release(i8* [[T1]])
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
id x = *wp = test0_helper();
// CHECK: [[T0:%.*]] = call i8* @_Z12test0_helperv()
In ARC, reclaim all return values of retainable type, not just those where we have an immediate need of a retained value. As an exception, don't do this when the call is made as the immediate operand of a __bridge retain. This is more in the way of a workaround than an actual guarantee, so it's acceptable to be brittle here. rdar://problem/9504800 llvm-svn: 134605
2011-07-07 14:58:02 +08:00
// CHECK-NEXT: [[T1:%.*]] = call i8* @objc_retainAutoreleasedReturnValue(i8* [[T0]])
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK-NEXT: [[T2:%.*]] = load i8**, i8*** {{%.*}}, align 8
In ARC, reclaim all return values of retainable type, not just those where we have an immediate need of a retained value. As an exception, don't do this when the call is made as the immediate operand of a __bridge retain. This is more in the way of a workaround than an actual guarantee, so it's acceptable to be brittle here. rdar://problem/9504800 llvm-svn: 134605
2011-07-07 14:58:02 +08:00
// CHECK-NEXT: [[T3:%.*]] = call i8* @objc_storeWeak(i8** [[T2]], i8* [[T1]])
// CHECK-NEXT: [[T4:%.*]] = call i8* @objc_loadWeakRetained(i8** [[T2]])
// CHECK-NEXT: store i8* [[T4]], i8**
// CHECK-NEXT: call void @objc_release(i8* [[T1]])
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
id y = *wvp = test0_helper();
}
// rdar://problem/9320648
struct Test1_helper { Test1_helper(); };
@interface Test1 @end
@implementation Test1 { Test1_helper x; } @end
// CHECK: define internal i8* @"\01-[Test1 .cxx_construct]"(
// CHECK: call void @_ZN12Test1_helperC1Ev(
// CHECK-NEXT: load
// CHECK-NEXT: bitcast
// CHECK-NEXT: ret i8*
void test34(int cond) {
__strong id strong;
__weak id weak;
extern void test34_sink(id *);
test34_sink(cond ? &strong : 0);
test34_sink(cond ? &weak : 0);
CHECK-LABEL-ify some code gen tests to improve diagnostic experience when tests fail. llvm-svn: 188447
2013-08-15 14:47:53 +08:00
// CHECK-LABEL: define void @_Z6test34i(
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: [[COND:%.*]] = alloca i32
// CHECK-NEXT: [[STRONG:%.*]] = alloca i8*
// CHECK-NEXT: [[WEAK:%.*]] = alloca i8*
// CHECK-NEXT: [[TEMP1:%.*]] = alloca i8*
// CHECK-NEXT: [[TEMP2:%.*]] = alloca i8*
objective-C arc: load of a __weak object happens via call to objc_loadWeak. This retains and autorelease the weakly-refereced object. This hidden autorelease sometimes makes __weak variable alive even after the weak reference is erased, because the object is still referenced by an autorelease pool. This patch overcomes this behavior by loading a weak object via call to objc_loadWeakRetained(), followng it by objc_release at appropriate place, thereby removing the hidden autorelease. // rdar://10849570 llvm-svn: 168740
2012-11-28 07:02:53 +08:00
// CHECK-NEXT: [[CONDCLEANUPSAVE:%.*]] = alloca i8*
// CHECK-NEXT: [[CONDCLEANUP:%.*]] = alloca i1
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: store i32
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK-NEXT: [[STRONGP:%.*]] = bitcast i8** [[STRONG]] to i8*
// CHECK-NEXT: call void @llvm.lifetime.start(i64 8, i8* [[STRONGP]])
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: store i8* null, i8** [[STRONG]]
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK-NEXT: [[WEAKP:%.*]] = bitcast i8** [[WEAK]] to i8*
// CHECK-NEXT: call void @llvm.lifetime.start(i64 8, i8* [[WEAKP]])
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: call i8* @objc_initWeak(i8** [[WEAK]], i8* null)
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK-NEXT: [[T0:%.*]] = load i32, i32* [[COND]]
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: [[T1:%.*]] = icmp ne i32 [[T0]], 0
// CHECK: [[ARG:%.*]] = phi i8**
// CHECK-NEXT: [[T0:%.*]] = icmp eq i8** [[ARG]], null
// CHECK-NEXT: [[T1:%.*]] = select i1 [[T0]], i8** null, i8** [[TEMP1]]
// CHECK-NEXT: br i1 [[T0]],
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK: [[T0:%.*]] = load i8*, i8** [[ARG]]
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: store i8* [[T0]], i8** [[TEMP1]]
// CHECK-NEXT: br label
Under ARC, when we're passing the address of a strong variable to an out-parameter using the indirect-writeback conversion, and we copied the current value of the variable to the temporary, make sure that we register an intrinsic use of that value with the optimizer so that the value won't get released until we have a chance to retain it. rdar://13195034 llvm-svn: 177813
2013-03-23 10:35:54 +08:00
// CHECK: [[W0:%.*]] = phi i8* [ [[T0]], {{%.*}} ], [ undef, {{%.*}} ]
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call void @_Z11test34_sinkPU15__autoreleasingP11objc_object(i8** [[T1]])
// CHECK-NEXT: [[T0:%.*]] = icmp eq i8** [[ARG]], null
// CHECK-NEXT: br i1 [[T0]],
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK: [[T0:%.*]] = load i8*, i8** [[TEMP1]]
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: [[T1:%.*]] = call i8* @objc_retain(i8* [[T0]])
[opaque pointer types] Explicit non-pointer type for call expressions (migration for recent LLVM change to textual IR for calls) llvm-svn: 235147
2015-04-17 07:25:00 +08:00
// CHECK-NEXT: call void (...) @clang.arc.use(i8* [[W0]])
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK-NEXT: [[T2:%.*]] = load i8*, i8** [[ARG]]
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: store i8* [[T1]], i8** [[ARG]]
// CHECK-NEXT: call void @objc_release(i8* [[T2]])
// CHECK-NEXT: br label
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK: [[T0:%.*]] = load i32, i32* [[COND]]
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: [[T1:%.*]] = icmp ne i32 [[T0]], 0
// CHECK: [[ARG:%.*]] = phi i8**
// CHECK-NEXT: [[T0:%.*]] = icmp eq i8** [[ARG]], null
// CHECK-NEXT: [[T1:%.*]] = select i1 [[T0]], i8** null, i8** [[TEMP2]]
objective-C arc: load of a __weak object happens via call to objc_loadWeak. This retains and autorelease the weakly-refereced object. This hidden autorelease sometimes makes __weak variable alive even after the weak reference is erased, because the object is still referenced by an autorelease pool. This patch overcomes this behavior by loading a weak object via call to objc_loadWeakRetained(), followng it by objc_release at appropriate place, thereby removing the hidden autorelease. // rdar://10849570 llvm-svn: 168740
2012-11-28 07:02:53 +08:00
// CHECK-NEXT: store i1 false, i1* [[CONDCLEANUP]]
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: br i1 [[T0]],
objective-C arc: load of a __weak object happens via call to objc_loadWeak. This retains and autorelease the weakly-refereced object. This hidden autorelease sometimes makes __weak variable alive even after the weak reference is erased, because the object is still referenced by an autorelease pool. This patch overcomes this behavior by loading a weak object via call to objc_loadWeakRetained(), followng it by objc_release at appropriate place, thereby removing the hidden autorelease. // rdar://10849570 llvm-svn: 168740
2012-11-28 07:02:53 +08:00
// CHECK: [[T0:%.*]] = call i8* @objc_loadWeakRetained(i8** [[ARG]])
// CHECK-NEXT: store i8* [[T0]], i8** [[CONDCLEANUPSAVE]]
// CHECK-NEXT: store i1 true, i1* [[CONDCLEANUP]]
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: store i8* [[T0]], i8** [[TEMP2]]
// CHECK-NEXT: br label
// CHECK: call void @_Z11test34_sinkPU15__autoreleasingP11objc_object(i8** [[T1]])
// CHECK-NEXT: [[T0:%.*]] = icmp eq i8** [[ARG]], null
// CHECK-NEXT: br i1 [[T0]],
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK: [[T0:%.*]] = load i8*, i8** [[TEMP2]]
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: call i8* @objc_storeWeak(i8** [[ARG]], i8* [[T0]])
// CHECK-NEXT: br label
// CHECK: call void @objc_destroyWeak(i8** [[WEAK]])
// CHECK: ret void
}
struct Test35_Helper {
static id makeObject1() __attribute__((ns_returns_retained));
id makeObject2() __attribute__((ns_returns_retained));
static id makeObject3();
id makeObject4();
};
CHECK-LABEL-ify some code gen tests to improve diagnostic experience when tests fail. llvm-svn: 188447
2013-08-15 14:47:53 +08:00
// CHECK-LABEL: define void @_Z6test3513Test35_HelperPS_
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
void test35(Test35_Helper x0, Test35_Helper *x0p) {
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.start
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call i8* @_ZN13Test35_Helper11makeObject1Ev
// CHECK-NOT: call i8* @objc_retain
id obj1 = Test35_Helper::makeObject1();
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.start
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call i8* @_ZN13Test35_Helper11makeObject2Ev
// CHECK-NOT: call i8* @objc_retain
id obj2 = x0.makeObject2();
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.start
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call i8* @_ZN13Test35_Helper11makeObject2Ev
// CHECK-NOT: call i8* @objc_retain
id obj3 = x0p->makeObject2();
id (Test35_Helper::*pmf)() __attribute__((ns_returns_retained))
= &Test35_Helper::makeObject2;
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.start
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call i8* %
// CHECK-NOT: call i8* @objc_retain
id obj4 = (x0.*pmf)();
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.start
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call i8* %
// CHECK-NOT: call i8* @objc_retain
id obj5 = (x0p->*pmf)();
// CHECK: call void @objc_release
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.end
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call void @objc_release
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.end
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call void @objc_release
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.end
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call void @objc_release
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.end
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call void @objc_release
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.end
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: ret void
}
CHECK-LABEL-ify some code gen tests to improve diagnostic experience when tests fail. llvm-svn: 188447
2013-08-15 14:47:53 +08:00
// CHECK-LABEL: define void @_Z7test35b13Test35_HelperPS_
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
void test35b(Test35_Helper x0, Test35_Helper *x0p) {
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.start
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call i8* @_ZN13Test35_Helper11makeObject3Ev
// CHECK: call i8* @objc_retain
id obj1 = Test35_Helper::makeObject3();
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.start
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call i8* @_ZN13Test35_Helper11makeObject4Ev
// CHECK: call i8* @objc_retain
id obj2 = x0.makeObject4();
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.start
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call i8* @_ZN13Test35_Helper11makeObject4Ev
// CHECK: call i8* @objc_retain
id obj3 = x0p->makeObject4();
id (Test35_Helper::*pmf)() = &Test35_Helper::makeObject4;
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.start
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call i8* %
// CHECK: call i8* @objc_retain
id obj4 = (x0.*pmf)();
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.start
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call i8* %
// CHECK: call i8* @objc_retain
id obj5 = (x0p->*pmf)();
// CHECK: call void @objc_release
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.end
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call void @objc_release
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.end
// CHECK: call void @llvm.lifetime.end
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call void @objc_release
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.end
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call void @objc_release
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.end
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK: call void @objc_release
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK: call void @llvm.lifetime.end
Automatic Reference Counting. Language-design credit goes to a lot of people, but I particularly want to single out Blaine Garst and Patrick Beard for their contributions. Compiler implementation credit goes to Argyrios, Doug, Fariborz, and myself, in no particular order. llvm-svn: 133103
2011-06-16 07:02:42 +08:00
// CHECK-NEXT: ret void
}
Be sure to try a final ARC-production even in Objective-C++. llvm-svn: 133215
2011-06-17 07:24:51 +08:00
// rdar://problem/9603128
CHECK-LABEL-ify some code gen tests to improve diagnostic experience when tests fail. llvm-svn: 188447
2013-08-15 14:47:53 +08:00
// CHECK-LABEL: define i8* @_Z6test36P11objc_object(
Be sure to try a final ARC-production even in Objective-C++. llvm-svn: 133215
2011-06-17 07:24:51 +08:00
id test36(id z) {
// CHECK: objc_retain
// CHECK: objc_retain
// CHECK: objc_release
// CHECK: objc_autoreleaseReturnValue
return z;
}
Clean up the analysis of the collection operand to ObjC for-in statements; specifically, make sure to close over any temporaries or cleanups it might require. In ARC, this has implications for the lifetime of the collection, so emit it with a retain and release it upon exit from the loop. rdar://problem/9817306 llvm-svn: 136204
2011-07-27 09:07:15 +08:00
// Template instantiation side of rdar://problem/9817306
@interface Test37
Make sure that we infer __strong, etc. when we instantiate variables under ARC. Fixes <rdar://problem/10530209>. llvm-svn: 146307
2011-12-10 09:22:52 +08:00
+ alloc;
- init;
Clean up the analysis of the collection operand to ObjC for-in statements; specifically, make sure to close over any temporaries or cleanups it might require. In ARC, this has implications for the lifetime of the collection, so emit it with a retain and release it upon exit from the loop. rdar://problem/9817306 llvm-svn: 136204
2011-07-27 09:07:15 +08:00
- (NSArray *) array;
@end
template <class T> void test37(T *a) {
for (id x in a.array) {
use(x);
}
}
extern template void test37<Test37>(Test37 *a);
template void test37<Test37>(Test37 *a);
CHECK-LABEL-ify some code gen tests to improve diagnostic experience when tests fail. llvm-svn: 188447
2013-08-15 14:47:53 +08:00
// CHECK-LABEL: define weak_odr void @_Z6test37I6Test37EvPT_(
Use the right CHECK prefix so that we actually do this checking. Miraculously, this hasn't broken llvm-svn: 146303
2011-12-10 08:28:18 +08:00
// CHECK: [[T0:%.*]] = call [[NSARRAY]]* bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to [[NSARRAY]]* (i8*, i8*)*)(
// CHECK-NEXT: [[T1:%.*]] = bitcast [[NSARRAY]]* [[T0]] to i8*
// CHECK-NEXT: [[T2:%.*]] = call i8* @objc_retainAutoreleasedReturnValue(i8* [[T1]])
// CHECK-NEXT: [[COLL:%.*]] = bitcast i8* [[T2]] to [[NSARRAY]]*
Clean up the analysis of the collection operand to ObjC for-in statements; specifically, make sure to close over any temporaries or cleanups it might require. In ARC, this has implications for the lifetime of the collection, so emit it with a retain and release it upon exit from the loop. rdar://problem/9817306 llvm-svn: 136204
2011-07-27 09:07:15 +08:00
// Make sure it's not immediately released before starting the iteration.
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK-NEXT: load i8*, i8** @OBJC_SELECTOR_REFERENCES_
Use the right CHECK prefix so that we actually do this checking. Miraculously, this hasn't broken llvm-svn: 146303
2011-12-10 08:28:18 +08:00
// CHECK-NEXT: [[T0:%.*]] = bitcast [[NSARRAY]]* [[COLL]] to i8*
// CHECK-NEXT: @objc_msgSend
Clean up the analysis of the collection operand to ObjC for-in statements; specifically, make sure to close over any temporaries or cleanups it might require. In ARC, this has implications for the lifetime of the collection, so emit it with a retain and release it upon exit from the loop. rdar://problem/9817306 llvm-svn: 136204
2011-07-27 09:07:15 +08:00
// This bitcast is for the mutation check.
Use the right CHECK prefix so that we actually do this checking. Miraculously, this hasn't broken llvm-svn: 146303
2011-12-10 08:28:18 +08:00
// CHECK: [[T0:%.*]] = bitcast [[NSARRAY]]* [[COLL]] to i8*
// CHECK-NEXT: @objc_enumerationMutation
Clean up the analysis of the collection operand to ObjC for-in statements; specifically, make sure to close over any temporaries or cleanups it might require. In ARC, this has implications for the lifetime of the collection, so emit it with a retain and release it upon exit from the loop. rdar://problem/9817306 llvm-svn: 136204
2011-07-27 09:07:15 +08:00
// This bitcast is for the 'next' message send.
Use the right CHECK prefix so that we actually do this checking. Miraculously, this hasn't broken llvm-svn: 146303
2011-12-10 08:28:18 +08:00
// CHECK: [[T0:%.*]] = bitcast [[NSARRAY]]* [[COLL]] to i8*
// CHECK-NEXT: @objc_msgSend
Clean up the analysis of the collection operand to ObjC for-in statements; specifically, make sure to close over any temporaries or cleanups it might require. In ARC, this has implications for the lifetime of the collection, so emit it with a retain and release it upon exit from the loop. rdar://problem/9817306 llvm-svn: 136204
2011-07-27 09:07:15 +08:00
// This bitcast is for the final release.
Use the right CHECK prefix so that we actually do this checking. Miraculously, this hasn't broken llvm-svn: 146303
2011-12-10 08:28:18 +08:00
// CHECK: [[T0:%.*]] = bitcast [[NSARRAY]]* [[COLL]] to i8*
// CHECK-NEXT: call void @objc_release(i8* [[T0]])
When we manage to re-use an expression during tree transformation (= template instantiation), and that expression might produce a temporary, invoke MaybeBindToTemporary. Otherwise, we forget to destroy objects, release objects, etc. Fixes <rdar://problem/10531073>. llvm-svn: 146301
2011-12-10 08:23:21 +08:00
template<typename T>
void send_release() {
[Test37 array];
}
CHECK-LABEL-ify some code gen tests to improve diagnostic experience when tests fail. llvm-svn: 188447
2013-08-15 14:47:53 +08:00
// CHECK-LABEL: define weak_odr void @_Z12send_releaseIiEvv(
When we manage to re-use an expression during tree transformation (= template instantiation), and that expression might produce a temporary, invoke MaybeBindToTemporary. Otherwise, we forget to destroy objects, release objects, etc. Fixes <rdar://problem/10531073>. llvm-svn: 146301
2011-12-10 08:23:21 +08:00
// CHECK: call %0* bitcast (i8* (i8*, i8*, ...)* @objc_msgSend
// CHECK-NEXT: bitcast
// CHECK-NEXT: call i8* @objc_retainAutoreleasedReturnValue
// CHECK-NEXT: bitcast
// CHECK-NEXT: bitcast
// CHECK-NEXT: call void @objc_release
// CHECK-NEXT: ret void
template void send_release<int>();
Make sure that we infer __strong, etc. when we instantiate variables under ARC. Fixes <rdar://problem/10530209>. llvm-svn: 146307
2011-12-10 09:22:52 +08:00
template<typename T>
Test37 *instantiate_init() {
Test37 *result = [[Test37 alloc] init];
return result;
}
CHECK-LABEL-ify some code gen tests to improve diagnostic experience when tests fail. llvm-svn: 188447
2013-08-15 14:47:53 +08:00
// CHECK-LABEL: define weak_odr %2* @_Z16instantiate_initIiEP6Test37v
Make sure that we infer __strong, etc. when we instantiate variables under ARC. Fixes <rdar://problem/10530209>. llvm-svn: 146307
2011-12-10 09:22:52 +08:00
// CHECK: call i8* bitcast (i8* (i8*, i8*, ...)* @objc_msgSend
// CHECK: call i8* bitcast (i8* (i8*, i8*, ...)* @objc_msgSend
// CHECK: call i8* @objc_retain
// CHECK: call void @objc_release
// CHECK: call i8* @objc_autoreleaseReturnValue
template Test37* instantiate_init<int>();
Fix a Sema invariant bug that I recently introduced involving the template instantiation of statement-expressions. I think it was jyasskin who had a crashing testcase in this area; hopefully this fixes it and he can find his testcase and check it in. llvm-svn: 154189
2012-04-07 02:20:53 +08:00
// Just make sure that the AST invariants hold properly here,
// i.e. that we don't crash.
// The block should get bound in the full-expression outside
// the statement-expression.
template <class T> class Test38 {
void test(T x) {
^{ (void) x; }, ({ x; });
}
};
CHECK-LABEL-ify some code gen tests to improve diagnostic experience when tests fail. llvm-svn: 188447
2013-08-15 14:47:53 +08:00
// CHECK-LABEL: define weak_odr void @_ZN6Test38IiE4testEi(
Fix a Sema invariant bug that I recently introduced involving the template instantiation of statement-expressions. I think it was jyasskin who had a crashing testcase in this area; hopefully this fixes it and he can find his testcase and check it in. llvm-svn: 154189
2012-04-07 02:20:53 +08:00
template class Test38<int>;
Don't crash *or* insert a bogus autorelease when emitting a this-adjustment thunk in ARC++. llvm-svn: 161014
2012-07-31 08:33:55 +08:00
// rdar://problem/11964832
class Test39_base1 {
virtual void foo();
};
class Test39_base2 {
virtual id bar();
};
class Test39 : Test39_base1, Test39_base2 { // base2 is at non-zero offset
virtual id bar();
};
id Test39::bar() { return 0; }
// Note lack of autorelease.
CHECK-LABEL-ify some code gen tests to improve diagnostic experience when tests fail. llvm-svn: 188447
2013-08-15 14:47:53 +08:00
// CHECK-LABEL: define i8* @_ZThn8_N6Test393barEv(
Don't crash *or* insert a bogus autorelease when emitting a this-adjustment thunk in ARC++. llvm-svn: 161014
2012-07-31 08:33:55 +08:00
// CHECK: call i8* @_ZN6Test393barEv(
// CHECK-NEXT: ret i8*
Drop ObjCIndirectCopyRestoreExprs during template instantiation. It's a kind of implicit conversion, which we generally drop, but more importantly it's got very specific placement requirements. rdar://13617051 llvm-svn: 179254
2013-04-11 10:14:26 +08:00
// rdar://13617051
// Just a basic sanity-check that IR-gen still works after instantiating
// a non-dependent message send that requires writeback.
@interface Test40
+ (void) foo:(id *)errorPtr;
@end
template <class T> void test40_helper() {
id x;
[Test40 foo: &x];
};
template void test40_helper<int>();
CHECK-LABEL-ify some code gen tests to improve diagnostic experience when tests fail. llvm-svn: 188447
2013-08-15 14:47:53 +08:00
// CHECK-LABEL: define weak_odr void @_Z13test40_helperIiEvv()
Drop ObjCIndirectCopyRestoreExprs during template instantiation. It's a kind of implicit conversion, which we generally drop, but more importantly it's got very specific placement requirements. rdar://13617051 llvm-svn: 179254
2013-04-11 10:14:26 +08:00
// CHECK: [[X:%.*]] = alloca i8*
// CHECK-NEXT: [[TEMP:%.*]] = alloca i8*
Revert "Revert r234581, it might have caused a few miscompiles in Chromium." This reverts commit r234700. It turns out that the lifetime markers were not the cause of Chromium failing but a bug which was uncovered by optimizations exposed by the markers. llvm-svn: 235553
2015-04-23 05:38:15 +08:00
// CHECK-NEXT: [[XP:%.*]] = bitcast i8** [[X]] to i8*
// CHECK-NEXT: call void @llvm.lifetime.start(i64 8, i8* [[XP]])
Drop ObjCIndirectCopyRestoreExprs during template instantiation. It's a kind of implicit conversion, which we generally drop, but more importantly it's got very specific placement requirements. rdar://13617051 llvm-svn: 179254
2013-04-11 10:14:26 +08:00
// CHECK-NEXT: store i8* null, i8** [[X]]
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK: [[T0:%.*]] = load i8*, i8** [[X]]
Drop ObjCIndirectCopyRestoreExprs during template instantiation. It's a kind of implicit conversion, which we generally drop, but more importantly it's got very specific placement requirements. rdar://13617051 llvm-svn: 179254
2013-04-11 10:14:26 +08:00
// CHECK-NEXT: store i8* [[T0]], i8** [[TEMP]]
// CHECK: @objc_msgSend
Update Clang tests to handle explicitly typed load changes in LLVM. llvm-svn: 230795
2015-02-28 05:19:58 +08:00
// CHECK-NEXT: [[T0:%.*]] = load i8*, i8** [[TEMP]]
Drop ObjCIndirectCopyRestoreExprs during template instantiation. It's a kind of implicit conversion, which we generally drop, but more importantly it's got very specific placement requirements. rdar://13617051 llvm-svn: 179254
2013-04-11 10:14:26 +08:00
// CHECK-NEXT: call i8* @objc_retain(i8* [[T0]])
In ARC, peephole the initialization of a __weak variable with a value loaded from a __weak variable into a call to objc_copyWeak or objc_moveWeak. llvm-svn: 250916
2015-10-22 02:06:31 +08:00
// Check that moves out of __weak variables are compiled to use objc_moveWeak.
void test41(__weak id &&x) {
__weak id y = static_cast<__weak id &&>(x);
}
// CHECK-LABEL: define void @_Z6test41OU6__weakP11objc_object
// CHECK: [[X:%.*]] = alloca i8**
// CHECK: [[Y:%.*]] = alloca i8*
// CHECK: [[T0:%.*]] = load i8**, i8*** [[X]]
// CHECK-NEXT: call void @objc_moveWeak(i8** [[Y]], i8** [[T0]])
// CHECK-NEXT: call void @objc_destroyWeak(i8** [[Y]])