maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/ConstantMerge/merge-both.ll

40 lines
1.4 KiB
LLVM
Raw Normal View History

Don't merge two constants if we care about the address of both. This fixes the original testcase in PR8927. It also causes a clang binary built with a patched clang to increase in size by 0.21%. We can probably get some of the size back by writing a pass that detects that a global never has its pointer compared and adds unnamed_addr to it (maybe extend global opt). It is also possible that there are some other cases clang could add unnamed_addr to. I will investigate extending globalopt next. llvm-svn: 123584
2011-01-17 01:05:09 +08:00
; RUN: opt -constmerge %s -S -o - | FileCheck %s
; Test that in one run var3 is merged into var2 and var1 into var4.
Teach the ConstantMerge pass about alignment. Fixes PR10514! llvm-svn: 136250
2011-07-28 03:47:34 +08:00
; Test that we merge @var5 and @var6 into one with the higher alignment, and
; don't merge var7/var8 into var5/var6.
Don't merge two constants if we care about the address of both. This fixes the original testcase in PR8927. It also causes a clang binary built with a patched clang to increase in size by 0.21%. We can probably get some of the size back by writing a pass that detects that a global never has its pointer compared and adds unnamed_addr to it (maybe extend global opt). It is also possible that there are some other cases clang could add unnamed_addr to. I will investigate extending globalopt next. llvm-svn: 123584
2011-01-17 01:05:09 +08:00
declare void @zed(%struct.foobar*, %struct.foobar*)
%struct.foobar = type { i32 }
@var1 = internal constant %struct.foobar { i32 2 }
@var2 = unnamed_addr constant %struct.foobar { i32 2 }
@var3 = internal constant %struct.foobar { i32 2 }
@var4 = unnamed_addr constant %struct.foobar { i32 2 }
; CHECK: %struct.foobar = type { i32 }
; CHECK-NOT: @
; CHECK: @var2 = constant %struct.foobar { i32 2 }
; CHECK-NEXT: @var4 = constant %struct.foobar { i32 2 }
Teach the ConstantMerge pass about alignment. Fixes PR10514! llvm-svn: 136250
2011-07-28 03:47:34 +08:00
declare void @helper([16 x i8]*)
@var5 = internal constant [16 x i8] c"foo1bar2foo3bar\00", align 16
@var6 = private unnamed_addr constant [16 x i8] c"foo1bar2foo3bar\00", align 1
@var7 = internal constant [16 x i8] c"foo1bar2foo3bar\00"
@var8 = private unnamed_addr constant [16 x i8] c"foo1bar2foo3bar\00"
; CHECK-NEXT: @var6 = private constant [16 x i8] c"foo1bar2foo3bar\00", align 16
; CHECK-NEXT: @var8 = private constant [16 x i8] c"foo1bar2foo3bar\00"
Don't merge two constants if we care about the address of both. This fixes the original testcase in PR8927. It also causes a clang binary built with a patched clang to increase in size by 0.21%. We can probably get some of the size back by writing a pass that detects that a global never has its pointer compared and adds unnamed_addr to it (maybe extend global opt). It is also possible that there are some other cases clang could add unnamed_addr to. I will investigate extending globalopt next. llvm-svn: 123584
2011-01-17 01:05:09 +08:00
define i32 @main() {
entry:
call void @zed(%struct.foobar* @var1, %struct.foobar* @var2)
call void @zed(%struct.foobar* @var3, %struct.foobar* @var4)
Teach the ConstantMerge pass about alignment. Fixes PR10514! llvm-svn: 136250
2011-07-28 03:47:34 +08:00
call void @helper([16 x i8]* @var5)
call void @helper([16 x i8]* @var6)
call void @helper([16 x i8]* @var7)
call void @helper([16 x i8]* @var8)
Don't merge two constants if we care about the address of both. This fixes the original testcase in PR8927. It also causes a clang binary built with a patched clang to increase in size by 0.21%. We can probably get some of the size back by writing a pass that detects that a global never has its pointer compared and adds unnamed_addr to it (maybe extend global opt). It is also possible that there are some other cases clang could add unnamed_addr to. I will investigate extending globalopt next. llvm-svn: 123584
2011-01-17 01:05:09 +08:00
ret i32 0
}