maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/CodeGenCXX/static-initializer-branch-w...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

127 lines
4.5 KiB
C++
Raw Normal View History

Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
// RUN: %clang_cc1 -emit-llvm -std=c++1z %s -o - -triple=x86_64-linux-gnu | FileCheck %s
struct S { S(); ~S(); };
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK-NOT: br
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @global)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
S global;
// CHECK-LABEL: define {{.*}}global_var_init
// FIXME: Do we really need thread-safe initialization here? We don't run
// global ctors on multiple threads. (If we were to do so, we'd need thread-safe
// init for B<int>::member and B<int>::inline_member too.)
// CHECK: load atomic i8, i8* bitcast (i64* @_ZGV13inline_global to i8*) acquire,
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1
// CHECK-NOT: !prof
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @inline_global)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
inline S inline_global;
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK-NOT: br
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @thread_local_global)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
thread_local S thread_local_global;
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK: load i8, i8* bitcast (i64* @_ZGV26thread_local_inline_global to i8*)
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1
// CHECK-NOT: !prof
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @thread_local_inline_global)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
thread_local inline S thread_local_inline_global;
struct A {
static S member;
static thread_local S thread_local_member;
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK: load atomic i8, i8* bitcast (i64* @_ZGVN1A13inline_memberE to i8*) acquire,
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1
// CHECK-NOT: !prof
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @_ZN1A13inline_memberE)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
static inline S inline_member;
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK: load i8, i8* bitcast (i64* @_ZGVN1A26thread_local_inline_memberE to i8*)
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1
// CHECK-NOT: !prof
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @_ZN1A26thread_local_inline_memberE)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
static thread_local inline S thread_local_inline_member;
};
[CodeGenModule] Assume dso_local for -fpic -fno-semantic-interposition Summary: Clang -fpic defaults to -fno-semantic-interposition (GCC -fpic defaults to -fsemantic-interposition). Users need to specify -fsemantic-interposition to get semantic interposition behavior. Semantic interposition is currently a best-effort feature. There may still be some cases where it is not handled well. Reviewers: peter.smith, rnk, serge-sans-paille, sfertile, jfb, jdoerfert Subscribers: dschuff, jyknight, dylanmckay, nemanjai, jvesely, kbarton, fedor.sergeev, asb, rbar, johnrusso, simoncook, sabuasal, niosHD, jrtc27, zzheng, edward-jones, atanasyan, rogfer01, MartinMosbeck, brucehoult, the_o, arphaman, PkmX, jocewei, jsji, Jim, lenary, s.egerton, pzheng, sameer.abuasal, apazos, luismarques, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D73865
2020-02-03 04:23:47 +08:00
// CHECK-LABEL: define dso_local void @_Z1fv()
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
void f() {
// CHECK: load atomic i8, i8* bitcast (i64* @_ZGVZ1fvE12static_local to i8*) acquire,
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1 {{.*}}, !prof ![[WEIGHTS_LOCAL:[0-9]*]]
static S static_local;
// CHECK: load i8, i8* @_ZGVZ1fvE19static_thread_local,
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1 {{.*}}, !prof ![[WEIGHTS_THREAD_LOCAL:[0-9]*]]
static thread_local S static_thread_local;
}
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK-NOT: br
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @_ZN1A6memberE)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
S A::member;
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK-NOT: br
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @_ZN1A19thread_local_memberE)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
thread_local S A::thread_local_member;
template <typename T> struct B {
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK: load i8, i8* bitcast (i64* @_ZGVN1BIiE6memberE to i8*)
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1
// CHECK-NOT: !prof
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @_ZN1BIiE6memberE)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
static S member;
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK: load i8, i8* bitcast (i64* @_ZGVN1BIiE13inline_memberE to i8*)
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1
// CHECK-NOT: !prof
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @_ZN1BIiE13inline_memberE)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
static inline S inline_member;
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK: load i8, i8* bitcast (i64* @_ZGVN1BIiE19thread_local_memberE to i8*)
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1
// CHECK-NOT: !prof
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @_ZN1BIiE19thread_local_memberE)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
static thread_local S thread_local_member;
// CHECK-LABEL: define {{.*}}global_var_init
// CHECK: load i8, i8* bitcast (i64* @_ZGVN1BIiE26thread_local_inline_memberE to i8*)
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1
// CHECK-NOT: !prof
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void @_ZN1SC1Ev({{.*}}* @_ZN1BIiE26thread_local_inline_memberE)
Add branch weights to branches for static initializers. The initializer for a static local variable cannot be hot, because it runs at most once per program. That's not quite the same thing as having a low branch probability, but under the assumption that the function is invoked many times, modeling this as a branch probability seems reasonable. For TLS variables, the situation is less clear, since the initialization side of the branch can run multiple times in a program execution, but we still expect initialization to be rare relative to non-initialization uses. It would seem worthwhile to add a PGO counter along this path to make this estimation more accurate in future. For globals with guarded initialization, we don't yet apply any branch weights. Due to our use of COMDATs, the guard will be reached exactly once per DSO, but we have no idea how many DSOs will define the variable. llvm-svn: 309195
2017-07-27 06:01:09 +08:00
static thread_local inline S thread_local_inline_member;
};
template<typename T> S B<T>::member;
template<typename T> thread_local S B<T>::thread_local_member;
template<typename ...T> void use(T &...);
void use_b() {
use(B<int>::member, B<int>::inline_member, B<int>::thread_local_member,
B<int>::thread_local_inline_member);
}
// CHECK-LABEL: define {{.*}}tls_init()
// CHECK: load i8, i8* @__tls_guard, align 1
// CHECK: icmp eq i8 {{.*}}, 0
// CHECK: br i1 {{.*}}, !prof ![[WEIGHTS_THREAD_LOCAL]]
// CHECK-DAG: ![[WEIGHTS_THREAD_LOCAL]] = !{!"branch_weights", i32 1, i32 1023}
// CHECK-DAG: ![[WEIGHTS_LOCAL]] = !{!"branch_weights", i32 1, i32 1048575}