maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/CodeGen/array-init.c

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

16 lines
785 B
C
Raw Normal View History

Disable -fmerge-all-constants as default. Summary: "-fmerge-all-constants" is a non-conforming optimization and should not be the default. It is also causing miscompiles when building Linux Kernel (https://lkml.org/lkml/2018/3/20/872). Fixes PR18538. Reviewers: rjmccall, rsmith, chandlerc Reviewed By: rsmith, chandlerc Subscribers: srhines, cfe-commits Differential Revision: https://reviews.llvm.org/D45289 llvm-svn: 329300
2018-04-05 23:29:52 +08:00
// RUN: %clang_cc1 %s -O0 -triple x86_64-unknown-linux-gnu -emit-llvm -o - | FileCheck -check-prefix=CHECK-NO-MERGE-CONSTANTS %s
// RUN: %clang_cc1 %s -O0 -triple x86_64-unknown-linux-gnu -fmerge-all-constants -emit-llvm -o - | FileCheck -check-prefix=CHECK-MERGE-CONSTANTS %s
[CodeGen] Use the zero initializer instead of storing an all zero representation. Summary: This change avoids the overhead of storing, and later crawling, an initializer list of all zeros for arrays. When LLVM visits this (llvm/IR/Constants.cpp) ConstantArray::getImpl() it will scan the list looking for an array of all zero. We can avoid the store, and short-cut the scan, by detecting all zeros when clang builds-up the initialization representation. This was brought to my attention when investigating PR36030 Reviewers: majnemer, rjmccall Reviewed By: rjmccall Subscribers: cfe-commits Differential Revision: https://reviews.llvm.org/D42549 llvm-svn: 324776
2018-02-10 06:10:09 +08:00
Disable -fmerge-all-constants as default. Summary: "-fmerge-all-constants" is a non-conforming optimization and should not be the default. It is also causing miscompiles when building Linux Kernel (https://lkml.org/lkml/2018/3/20/872). Fixes PR18538. Reviewers: rjmccall, rsmith, chandlerc Reviewed By: rsmith, chandlerc Subscribers: srhines, cfe-commits Differential Revision: https://reviews.llvm.org/D45289 llvm-svn: 329300
2018-04-05 23:29:52 +08:00
// CHECK-NO-MERGE-CONSTANTS: @{{.*}}.a1 = private unnamed_addr constant [5 x i32] [i32 0, i32 1, i32 2, i32 0, i32 0]
// CHECK-MERGE-CONSTANTS: @{{.*}}.a1 = internal constant [5 x i32] [i32 0, i32 1, i32 2, i32 0, i32 0]
// CHECK-MERGE-CONSTANTS: @{{.*}}.a2 = internal constant [5 x i32] zeroinitializer
// CHECK-MERGE-CONSTANTS: @{{.*}}.a3 = internal constant [5 x i32] zeroinitializer
[CodeGen] Use the zero initializer instead of storing an all zero representation. Summary: This change avoids the overhead of storing, and later crawling, an initializer list of all zeros for arrays. When LLVM visits this (llvm/IR/Constants.cpp) ConstantArray::getImpl() it will scan the list looking for an array of all zero. We can avoid the store, and short-cut the scan, by detecting all zeros when clang builds-up the initialization representation. This was brought to my attention when investigating PR36030 Reviewers: majnemer, rjmccall Reviewed By: rjmccall Subscribers: cfe-commits Differential Revision: https://reviews.llvm.org/D42549 llvm-svn: 324776
2018-02-10 06:10:09 +08:00
void testConstArrayInits(void)
{
const int a1[5] = {0,1,2};
const int a2[5] = {0,0,0};
const int a3[5] = {0};
}