thr3ads.net - llvm dev - [llvm-dev] LLVM v6.0 Internalize and GlobalDCE PASS can not work together? [Oct 2017]

If this information is useful, please help other people find it:
Share via:

Leslie Zhai via llvm-dev

2017-Oct-25 04:22 UTC

[llvm-dev] LLVM v6.0 Internalize and GlobalDCE PASS can not work together?

Hi LLVM developers,

$ cat hello.c
#include <stdio.h>

void foo() {
}

int main(int argc, char *argv[]) {
   for (int i = 0; i < 10; i++) {
     printf("%d\n", i);
   }
   return 0;
}

$ /opt/llvm-svn/bin/clang --version
Fedora clang version 6.0.0 (trunk 316308) (based on LLVM 6.0.0svn)
Target: x86_64-redhat-linux
Thread model: posix
InstalledDir: /opt/llvm-svn/bin

$ /opt/llvm-svn/bin/clang -Xclang -disable-O0-optnone -S -emit-llvm 
hello.c -o hello2.ll

$ cat hello2.ll
; ModuleID = 'hello.c'
source_filename = "hello.c"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1

; Function Attrs: noinline nounwind uwtable
define void @foo() #0 {
entry:
   ret void
}

; Function Attrs: noinline nounwind uwtable
define i32 @main(i32 %argc, i8** %argv) #0 {
entry:
   %retval = alloca i32, align 4
   %argc.addr = alloca i32, align 4
   %argv.addr = alloca i8**, align 8
   %i = alloca i32, align 4
   store i32 0, i32* %retval, align 4
   store i32 %argc, i32* %argc.addr, align 4
   store i8** %argv, i8*** %argv.addr, align 8
   store i32 0, i32* %i, align 4
   br label %for.cond

for.cond:                                         ; preds = %for.inc, %entry
   %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 10
   br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
   %1 = load i32, i32* %i, align 4
   %call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x 
i8], [4 x i8]* @.str, i32 0, i32 0), i32 %1)
   br label %for.inc

for.inc:                                          ; preds = %for.body
   %2 = load i32, i32* %i, align 4
   %inc = add nsw i32 %2, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond

for.end:                                          ; preds = %for.cond
   ret i32 0
}

declare i32 @printf(i8*, ...) #1

attributes #0 = { noinline nounwind uwtable 
"correctly-rounded-divide-sqrt-fp-math"="false" 
"disable-tail-calls"="false"
"less-precise-fpmad"="false"
"no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
"no-infs-fp-math"="false"
"no-jump-tables"="false"
"no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
"stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
"unsafe-fp-math"="false"
"use-soft-float"="false" }
attributes #1 = {
"correctly-rounded-divide-sqrt-fp-math"="false"
"disable-tail-calls"="false"
"less-precise-fpmad"="false"
"no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
"no-infs-fp-math"="false"
"no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
"stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
"unsafe-fp-math"="false"
"use-soft-float"="false" }

!llvm.module.flags = !{!0}
!llvm.ident = !{!1}

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 6.0.0 (git at github.com:llvm-mirror/clang.git 
0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
(git at github.com:llvm-mirror/llvm.git 
d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}

$ /opt/llvm-svn/bin/opt -S -internalize -globaldce hello2.ll -o 
hello2.dce.ll

$ cat hello2.dce.ll
; ModuleID = 'hello2.ll'
source_filename = "hello.c"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

!llvm.module.flags = !{!0}
!llvm.ident = !{!1}

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 6.0.0 (git at github.com:llvm-mirror/clang.git 
0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
(git at github.com:llvm-mirror/llvm.git 
d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}

$ /opt/llvm-svn/bin/lli hello2.dce.ll
'main' function not found in module.


*No* more Alive Functions, so LLVM v6.0 Internalize and GlobalDCE PASS 
failed to MarkLive Function together?


But LLVM 3.1 is able to work together:

$ ./build/Release+Asserts/bin/opt --version
LLVM (http://llvm.org/):
   LLVM version 3.1
   Optimized build with assertions.
   Built Oct 23 2017 (16:22:51).
   Default target: x86_64-unknown-linux-gnu
   Host CPU: corei7-avx

$ ./build/Release+Asserts/bin/clang -S -emit-llvm hello.c -o hello0.ll

$ cat hello0.ll
; ModuleID = 'hello.c'
target datalayout = 
"e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1

define void @foo() nounwind uwtable {
entry:
   ret void
}

define i32 @main(i32 %argc, i8** %argv) nounwind uwtable {
entry:
   %retval = alloca i32, align 4
   %argc.addr = alloca i32, align 4
   %argv.addr = alloca i8**, align 8
   %i = alloca i32, align 4
   store i32 0, i32* %retval
   store i32 %argc, i32* %argc.addr, align 4
   store i8** %argv, i8*** %argv.addr, align 8
   store i32 0, i32* %i, align 4
   br label %for.cond

for.cond:                                         ; preds = %for.inc, %entry
   %0 = load i32* %i, align 4
   %cmp = icmp slt i32 %0, 10
   br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
   %1 = load i32* %i, align 4
   %call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 x 
i8]* @.str, i32 0, i32 0), i32 %1)
   br label %for.inc

for.inc:                                          ; preds = %for.body
   %2 = load i32* %i, align 4
   %inc = add nsw i32 %2, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond

for.end:                                          ; preds = %for.cond
   ret i32 0
}

declare i32 @printf(i8*, ...)

$ ./build/Release+Asserts/bin/opt -S -internalize -globaldce hello0.ll 
-o hello0.dce.ll

$ cat hello0.dce.ll
; ModuleID = 'hello0.ll'
target datalayout = 
"e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1

define i32 @main(i32 %argc, i8** %argv) nounwind uwtable {
entry:
   %retval = alloca i32, align 4
   %argc.addr = alloca i32, align 4
   %argv.addr = alloca i8**, align 8
   %i = alloca i32, align 4
   store i32 0, i32* %retval
   store i32 %argc, i32* %argc.addr, align 4
   store i8** %argv, i8*** %argv.addr, align 8
   store i32 0, i32* %i, align 4
   br label %for.cond

for.cond:                                         ; preds = %for.inc, %entry
   %0 = load i32* %i, align 4
   %cmp = icmp slt i32 %0, 10
   br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
   %1 = load i32* %i, align 4
   %call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 x 
i8]* @.str, i32 0, i32 0), i32 %1)
   br label %for.inc

for.inc:                                          ; preds = %for.body
   %2 = load i32* %i, align 4
   %inc = add nsw i32 %2, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond

for.end:                                          ; preds = %for.cond
   ret i32 0
}

declare i32 @printf(i8*, ...)


Succeeded drop DeadFunction foo.

Maybe I wrongly use the Internalize and GlobalDCE PASS together? please 
give me some hints, thanks a lot!


PS: LLVM 6.0 Internalize PASS is able to work, internal foo:

$ /opt/llvm-svn/bin/opt -S -internalize hello2.ll -o hello2.internal.ll

$ cat hello2.internal.ll
; ModuleID = 'hello2.ll'
source_filename = "hello.c"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1

; Function Attrs: noinline nounwind uwtable
define internal void @foo() #0 {
entry:
   ret void
}

; Function Attrs: noinline nounwind uwtable
define internal i32 @main(i32 %argc, i8** %argv) #0 {
entry:
   %retval = alloca i32, align 4
   %argc.addr = alloca i32, align 4
   %argv.addr = alloca i8**, align 8
   %i = alloca i32, align 4
   store i32 0, i32* %retval, align 4
   store i32 %argc, i32* %argc.addr, align 4
   store i8** %argv, i8*** %argv.addr, align 8
   store i32 0, i32* %i, align 4
   br label %for.cond

for.cond:                                         ; preds = %for.inc, %entry
   %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 10
   br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
   %1 = load i32, i32* %i, align 4
   %call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x 
i8], [4 x i8]* @.str, i32 0, i32 0), i32 %1)
   br label %for.inc

for.inc:                                          ; preds = %for.body
   %2 = load i32, i32* %i, align 4
   %inc = add nsw i32 %2, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond

for.end:                                          ; preds = %for.cond
   ret i32 0
}

declare i32 @printf(i8*, ...) #1

attributes #0 = { noinline nounwind uwtable 
"correctly-rounded-divide-sqrt-fp-math"="false" 
"disable-tail-calls"="false"
"less-precise-fpmad"="false"
"no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
"no-infs-fp-math"="false"
"no-jump-tables"="false"
"no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
"stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
"unsafe-fp-math"="false"
"use-soft-float"="false" }
attributes #1 = {
"correctly-rounded-divide-sqrt-fp-math"="false"
"disable-tail-calls"="false"
"less-precise-fpmad"="false"
"no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
"no-infs-fp-math"="false"
"no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
"stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
"unsafe-fp-math"="false"
"use-soft-float"="false" }

!llvm.module.flags = !{!0}
!llvm.ident = !{!1}

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 6.0.0 (git at github.com:llvm-mirror/clang.git 
0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
(git at github.com:llvm-mirror/llvm.git 
d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}

-- 
Regards,
Leslie Zhai - https://reviews.llvm.org/p/xiangzhai/

Leslie Zhai via llvm-dev

2017-Oct-25 07:42 UTC

head link

[llvm-dev] LLVM v6.0 Internalize and GlobalDCE PASS can not work together?

Workaround patch not the root cause:


diff --git a/lib/Transforms/IPO/Internalize.cpp 
b/lib/Transforms/IPO/Internalize.cpp
index 26db146..a12a8d5 100644
--- a/lib/Transforms/IPO/Internalize.cpp
+++ b/lib/Transforms/IPO/Internalize.cpp
@@ -115,6 +115,9 @@ bool InternalizePass::shouldPreserveGV(const 
GlobalValue &GV) {

  bool InternalizePass::maybeInternalize(
      GlobalValue &GV, const std::set<const Comdat *>
&ExternalComdats) {
+  if (GV.getName() == "main")
+    return false;
+
    if (Comdat *C = GV.getComdat()) {
      if (ExternalComdats.count(C))
        return false;



在 2017年10月25日 12:22, Leslie Zhai 写道:> Hi LLVM developers,
>
> $ cat hello.c
> #include <stdio.h>
>
> void foo() {
> }
>
> int main(int argc, char *argv[]) {
>   for (int i = 0; i < 10; i++) {
>     printf("%d\n", i);
>   }
>   return 0;
> }
>
> $ /opt/llvm-svn/bin/clang --version
> Fedora clang version 6.0.0 (trunk 316308) (based on LLVM 6.0.0svn)
> Target: x86_64-redhat-linux
> Thread model: posix
> InstalledDir: /opt/llvm-svn/bin
>
> $ /opt/llvm-svn/bin/clang -Xclang -disable-O0-optnone -S -emit-llvm 
> hello.c -o hello2.ll
>
> $ cat hello2.ll
> ; ModuleID = 'hello.c'
> source_filename = "hello.c"
> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> target triple = "x86_64-unknown-linux-gnu"
>
> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align
1
>
> ; Function Attrs: noinline nounwind uwtable
> define void @foo() #0 {
> entry:
>   ret void
> }
>
> ; Function Attrs: noinline nounwind uwtable
> define i32 @main(i32 %argc, i8** %argv) #0 {
> entry:
>   %retval = alloca i32, align 4
>   %argc.addr = alloca i32, align 4
>   %argv.addr = alloca i8**, align 8
>   %i = alloca i32, align 4
>   store i32 0, i32* %retval, align 4
>   store i32 %argc, i32* %argc.addr, align 4
>   store i8** %argv, i8*** %argv.addr, align 8
>   store i32 0, i32* %i, align 4
>   br label %for.cond
>
> for.cond:                                         ; preds = %for.inc, 
> %entry
>   %0 = load i32, i32* %i, align 4
>   %cmp = icmp slt i32 %0, 10
>   br i1 %cmp, label %for.body, label %for.end
>
> for.body:                                         ; preds = %for.cond
>   %1 = load i32, i32* %i, align 4
>   %call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x 
> i8], [4 x i8]* @.str, i32 0, i32 0), i32 %1)
>   br label %for.inc
>
> for.inc:                                          ; preds = %for.body
>   %2 = load i32, i32* %i, align 4
>   %inc = add nsw i32 %2, 1
>   store i32 %inc, i32* %i, align 4
>   br label %for.cond
>
> for.end:                                          ; preds = %for.cond
>   ret i32 0
> }
>
> declare i32 @printf(i8*, ...) #1
>
> attributes #0 = { noinline nounwind uwtable 
> "correctly-rounded-divide-sqrt-fp-math"="false" 
> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
> "no-infs-fp-math"="false"
"no-jump-tables"="false"
> "no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
> "no-trapping-math"="false"
"stack-protector-buffer-size"="8"
> "target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
> "unsafe-fp-math"="false"
"use-soft-float"="false" }
> attributes #1 = {
"correctly-rounded-divide-sqrt-fp-math"="false"
> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
> "no-infs-fp-math"="false"
"no-nans-fp-math"="false"
> "no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
> "stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
> "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" 
> "unsafe-fp-math"="false"
"use-soft-float"="false" }
>
> !llvm.module.flags = !{!0}
> !llvm.ident = !{!1}
>
> !0 = !{i32 1, !"wchar_size", i32 4}
> !1 = !{!"clang version 6.0.0 (git at github.com:llvm-mirror/clang.git 
> 0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
> (git at github.com:llvm-mirror/llvm.git 
> d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}
>
> $ /opt/llvm-svn/bin/opt -S -internalize -globaldce hello2.ll -o 
> hello2.dce.ll
>
> $ cat hello2.dce.ll
> ; ModuleID = 'hello2.ll'
> source_filename = "hello.c"
> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> target triple = "x86_64-unknown-linux-gnu"
>
> !llvm.module.flags = !{!0}
> !llvm.ident = !{!1}
>
> !0 = !{i32 1, !"wchar_size", i32 4}
> !1 = !{!"clang version 6.0.0 (git at github.com:llvm-mirror/clang.git 
> 0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
> (git at github.com:llvm-mirror/llvm.git 
> d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}
>
> $ /opt/llvm-svn/bin/lli hello2.dce.ll
> 'main' function not found in module.
>
>
> *No* more Alive Functions, so LLVM v6.0 Internalize and GlobalDCE PASS 
> failed to MarkLive Function together?
>
>
> But LLVM 3.1 is able to work together:
>
> $ ./build/Release+Asserts/bin/opt --version
> LLVM (http://llvm.org/):
>   LLVM version 3.1
>   Optimized build with assertions.
>   Built Oct 23 2017 (16:22:51).
>   Default target: x86_64-unknown-linux-gnu
>   Host CPU: corei7-avx
>
> $ ./build/Release+Asserts/bin/clang -S -emit-llvm hello.c -o hello0.ll
>
> $ cat hello0.ll
> ; ModuleID = 'hello.c'
> target datalayout = 
>
"e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
> target triple = "x86_64-unknown-linux-gnu"
>
> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align
1
>
> define void @foo() nounwind uwtable {
> entry:
>   ret void
> }
>
> define i32 @main(i32 %argc, i8** %argv) nounwind uwtable {
> entry:
>   %retval = alloca i32, align 4
>   %argc.addr = alloca i32, align 4
>   %argv.addr = alloca i8**, align 8
>   %i = alloca i32, align 4
>   store i32 0, i32* %retval
>   store i32 %argc, i32* %argc.addr, align 4
>   store i8** %argv, i8*** %argv.addr, align 8
>   store i32 0, i32* %i, align 4
>   br label %for.cond
>
> for.cond:                                         ; preds = %for.inc, 
> %entry
>   %0 = load i32* %i, align 4
>   %cmp = icmp slt i32 %0, 10
>   br i1 %cmp, label %for.body, label %for.end
>
> for.body:                                         ; preds = %for.cond
>   %1 = load i32* %i, align 4
>   %call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 
> x i8]* @.str, i32 0, i32 0), i32 %1)
>   br label %for.inc
>
> for.inc:                                          ; preds = %for.body
>   %2 = load i32* %i, align 4
>   %inc = add nsw i32 %2, 1
>   store i32 %inc, i32* %i, align 4
>   br label %for.cond
>
> for.end:                                          ; preds = %for.cond
>   ret i32 0
> }
>
> declare i32 @printf(i8*, ...)
>
> $ ./build/Release+Asserts/bin/opt -S -internalize -globaldce hello0.ll 
> -o hello0.dce.ll
>
> $ cat hello0.dce.ll
> ; ModuleID = 'hello0.ll'
> target datalayout = 
>
"e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
> target triple = "x86_64-unknown-linux-gnu"
>
> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align
1
>
> define i32 @main(i32 %argc, i8** %argv) nounwind uwtable {
> entry:
>   %retval = alloca i32, align 4
>   %argc.addr = alloca i32, align 4
>   %argv.addr = alloca i8**, align 8
>   %i = alloca i32, align 4
>   store i32 0, i32* %retval
>   store i32 %argc, i32* %argc.addr, align 4
>   store i8** %argv, i8*** %argv.addr, align 8
>   store i32 0, i32* %i, align 4
>   br label %for.cond
>
> for.cond:                                         ; preds = %for.inc, 
> %entry
>   %0 = load i32* %i, align 4
>   %cmp = icmp slt i32 %0, 10
>   br i1 %cmp, label %for.body, label %for.end
>
> for.body:                                         ; preds = %for.cond
>   %1 = load i32* %i, align 4
>   %call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 
> x i8]* @.str, i32 0, i32 0), i32 %1)
>   br label %for.inc
>
> for.inc:                                          ; preds = %for.body
>   %2 = load i32* %i, align 4
>   %inc = add nsw i32 %2, 1
>   store i32 %inc, i32* %i, align 4
>   br label %for.cond
>
> for.end:                                          ; preds = %for.cond
>   ret i32 0
> }
>
> declare i32 @printf(i8*, ...)
>
>
> Succeeded drop DeadFunction foo.
>
> Maybe I wrongly use the Internalize and GlobalDCE PASS together? 
> please give me some hints, thanks a lot!
>
>
> PS: LLVM 6.0 Internalize PASS is able to work, internal foo:
>
> $ /opt/llvm-svn/bin/opt -S -internalize hello2.ll -o hello2.internal.ll
>
> $ cat hello2.internal.ll
> ; ModuleID = 'hello2.ll'
> source_filename = "hello.c"
> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> target triple = "x86_64-unknown-linux-gnu"
>
> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align
1
>
> ; Function Attrs: noinline nounwind uwtable
> define internal void @foo() #0 {
> entry:
>   ret void
> }
>
> ; Function Attrs: noinline nounwind uwtable
> define internal i32 @main(i32 %argc, i8** %argv) #0 {Let `main` Function *NOT* maybeInternalize, then

$ ./build/bin/opt -S -globaldce hello2.internal.ll -o hello2.dce.ll
$ cat hello2.dce.ll
; ModuleID = 'hello2.ll'
source_filename = "hello.c"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1

; Function Attrs: noinline nounwind uwtable
define i32 @main(i32 %argc, i8** %argv) #0 {
entry:
   %retval = alloca i32, align 4
   %argc.addr = alloca i32, align 4
   %argv.addr = alloca i8**, align 8
   %i = alloca i32, align 4
   store i32 0, i32* %retval, align 4
   store i32 %argc, i32* %argc.addr, align 4
   store i8** %argv, i8*** %argv.addr, align 8
   store i32 0, i32* %i, align 4
   br label %for.cond

for.cond:                                         ; preds = %for.inc, %entry
   %0 = load i32, i32* %i, align 4
   %cmp = icmp slt i32 %0, 10
   br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
   %1 = load i32, i32* %i, align 4
   %call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x 
i8], [4 x i8]* @.str, i32 0, i32 0), i32 %1)
   br label %for.inc

for.inc:                                          ; preds = %for.body
   %2 = load i32, i32* %i, align 4
   %inc = add nsw i32 %2, 1
   store i32 %inc, i32* %i, align 4
   br label %for.cond

for.end:                                          ; preds = %for.cond
   ret i32 0
}

declare i32 @printf(i8*, ...) #1

attributes #0 = { noinline nounwind uwtable 
"correctly-rounded-divide-sqrt-fp-math"="false" 
"disable-tail-calls"="false"
"less-precise-fpmad"="false"
"no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
"no-infs-fp-math"="false"
"no-jump-tables"="false"
"no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
"stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
"unsafe-fp-math"="false"
"use-soft-float"="false" }
attributes #1 = {
"correctly-rounded-divide-sqrt-fp-math"="false"
"disable-tail-calls"="false"
"less-precise-fpmad"="false"
"no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
"no-infs-fp-math"="false"
"no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
"stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
"unsafe-fp-math"="false"
"use-soft-float"="false" }

!llvm.module.flags = !{!0}
!llvm.ident = !{!1}

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 6.0.0 (git at github.com:llvm-mirror/clang.git 
0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
(git at github.com:llvm-mirror/llvm.git 
d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}


$ ./build/bin/lli hello2.dce.ll
0
1
2
3
4
5
6
7
8
9
> entry:
>   %retval = alloca i32, align 4
>   %argc.addr = alloca i32, align 4
>   %argv.addr = alloca i8**, align 8
>   %i = alloca i32, align 4
>   store i32 0, i32* %retval, align 4
>   store i32 %argc, i32* %argc.addr, align 4
>   store i8** %argv, i8*** %argv.addr, align 8
>   store i32 0, i32* %i, align 4
>   br label %for.cond
>
> for.cond:                                         ; preds = %for.inc, 
> %entry
>   %0 = load i32, i32* %i, align 4
>   %cmp = icmp slt i32 %0, 10
>   br i1 %cmp, label %for.body, label %for.end
>
> for.body:                                         ; preds = %for.cond
>   %1 = load i32, i32* %i, align 4
>   %call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x 
> i8], [4 x i8]* @.str, i32 0, i32 0), i32 %1)
>   br label %for.inc
>
> for.inc:                                          ; preds = %for.body
>   %2 = load i32, i32* %i, align 4
>   %inc = add nsw i32 %2, 1
>   store i32 %inc, i32* %i, align 4
>   br label %for.cond
>
> for.end:                                          ; preds = %for.cond
>   ret i32 0
> }
>
> declare i32 @printf(i8*, ...) #1
>
> attributes #0 = { noinline nounwind uwtable 
> "correctly-rounded-divide-sqrt-fp-math"="false" 
> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
> "no-infs-fp-math"="false"
"no-jump-tables"="false"
> "no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
> "no-trapping-math"="false"
"stack-protector-buffer-size"="8"
> "target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
> "unsafe-fp-math"="false"
"use-soft-float"="false" }
> attributes #1 = {
"correctly-rounded-divide-sqrt-fp-math"="false"
> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
> "no-infs-fp-math"="false"
"no-nans-fp-math"="false"
> "no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
> "stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
> "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" 
> "unsafe-fp-math"="false"
"use-soft-float"="false" }
>
> !llvm.module.flags = !{!0}
> !llvm.ident = !{!1}
>
> !0 = !{i32 1, !"wchar_size", i32 4}
> !1 = !{!"clang version 6.0.0 (git at github.com:llvm-mirror/clang.git 
> 0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
> (git at github.com:llvm-mirror/llvm.git 
> d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}
>
-- 
Regards,
Leslie Zhai - https://reviews.llvm.org/p/xiangzhai/

Hal Finkel via llvm-dev

2017-Oct-25 13:20 UTC

head link

[llvm-dev] LLVM v6.0 Internalize and GlobalDCE PASS can not work together?

Hi, Leslie,

When you use internalize, you need to provide it with a list of symbols 
to preserve as external (otherwise everything will be internalized, 
including main, and then DCE will remove everything). You can use 
-internalize-public-api-list=main (a comma-separated list) or 
-internalize-public-api-file=some_file_name where some_file_name has the 
list of symbols. See the comments in lib/Transforms/IPO/Internalize.cpp.

  -Hal

On 10/24/2017 11:22 PM, Leslie Zhai via llvm-dev wrote:> Hi LLVM developers,
>
> $ cat hello.c
> #include <stdio.h>
>
> void foo() {
> }
>
> int main(int argc, char *argv[]) {
>   for (int i = 0; i < 10; i++) {
>     printf("%d\n", i);
>   }
>   return 0;
> }
>
> $ /opt/llvm-svn/bin/clang --version
> Fedora clang version 6.0.0 (trunk 316308) (based on LLVM 6.0.0svn)
> Target: x86_64-redhat-linux
> Thread model: posix
> InstalledDir: /opt/llvm-svn/bin
>
> $ /opt/llvm-svn/bin/clang -Xclang -disable-O0-optnone -S -emit-llvm 
> hello.c -o hello2.ll
>
> $ cat hello2.ll
> ; ModuleID = 'hello.c'
> source_filename = "hello.c"
> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> target triple = "x86_64-unknown-linux-gnu"
>
> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align
1
>
> ; Function Attrs: noinline nounwind uwtable
> define void @foo() #0 {
> entry:
>   ret void
> }
>
> ; Function Attrs: noinline nounwind uwtable
> define i32 @main(i32 %argc, i8** %argv) #0 {
> entry:
>   %retval = alloca i32, align 4
>   %argc.addr = alloca i32, align 4
>   %argv.addr = alloca i8**, align 8
>   %i = alloca i32, align 4
>   store i32 0, i32* %retval, align 4
>   store i32 %argc, i32* %argc.addr, align 4
>   store i8** %argv, i8*** %argv.addr, align 8
>   store i32 0, i32* %i, align 4
>   br label %for.cond
>
> for.cond:                                         ; preds = %for.inc, 
> %entry
>   %0 = load i32, i32* %i, align 4
>   %cmp = icmp slt i32 %0, 10
>   br i1 %cmp, label %for.body, label %for.end
>
> for.body:                                         ; preds = %for.cond
>   %1 = load i32, i32* %i, align 4
>   %call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x 
> i8], [4 x i8]* @.str, i32 0, i32 0), i32 %1)
>   br label %for.inc
>
> for.inc:                                          ; preds = %for.body
>   %2 = load i32, i32* %i, align 4
>   %inc = add nsw i32 %2, 1
>   store i32 %inc, i32* %i, align 4
>   br label %for.cond
>
> for.end:                                          ; preds = %for.cond
>   ret i32 0
> }
>
> declare i32 @printf(i8*, ...) #1
>
> attributes #0 = { noinline nounwind uwtable 
> "correctly-rounded-divide-sqrt-fp-math"="false" 
> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
> "no-infs-fp-math"="false"
"no-jump-tables"="false"
> "no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
> "no-trapping-math"="false"
"stack-protector-buffer-size"="8"
> "target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
> "unsafe-fp-math"="false"
"use-soft-float"="false" }
> attributes #1 = {
"correctly-rounded-divide-sqrt-fp-math"="false"
> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
> "no-infs-fp-math"="false"
"no-nans-fp-math"="false"
> "no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
> "stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
> "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" 
> "unsafe-fp-math"="false"
"use-soft-float"="false" }
>
> !llvm.module.flags = !{!0}
> !llvm.ident = !{!1}
>
> !0 = !{i32 1, !"wchar_size", i32 4}
> !1 = !{!"clang version 6.0.0 (git at github.com:llvm-mirror/clang.git 
> 0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
> (git at github.com:llvm-mirror/llvm.git 
> d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}
>
> $ /opt/llvm-svn/bin/opt -S -internalize -globaldce hello2.ll -o 
> hello2.dce.ll
>
> $ cat hello2.dce.ll
> ; ModuleID = 'hello2.ll'
> source_filename = "hello.c"
> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> target triple = "x86_64-unknown-linux-gnu"
>
> !llvm.module.flags = !{!0}
> !llvm.ident = !{!1}
>
> !0 = !{i32 1, !"wchar_size", i32 4}
> !1 = !{!"clang version 6.0.0 (git at github.com:llvm-mirror/clang.git 
> 0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
> (git at github.com:llvm-mirror/llvm.git 
> d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}
>
> $ /opt/llvm-svn/bin/lli hello2.dce.ll
> 'main' function not found in module.
>
>
> *No* more Alive Functions, so LLVM v6.0 Internalize and GlobalDCE PASS 
> failed to MarkLive Function together?
>
>
> But LLVM 3.1 is able to work together:
>
> $ ./build/Release+Asserts/bin/opt --version
> LLVM (http://llvm.org/):
>   LLVM version 3.1
>   Optimized build with assertions.
>   Built Oct 23 2017 (16:22:51).
>   Default target: x86_64-unknown-linux-gnu
>   Host CPU: corei7-avx
>
> $ ./build/Release+Asserts/bin/clang -S -emit-llvm hello.c -o hello0.ll
>
> $ cat hello0.ll
> ; ModuleID = 'hello.c'
> target datalayout = 
>
"e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
> target triple = "x86_64-unknown-linux-gnu"
>
> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align
1
>
> define void @foo() nounwind uwtable {
> entry:
>   ret void
> }
>
> define i32 @main(i32 %argc, i8** %argv) nounwind uwtable {
> entry:
>   %retval = alloca i32, align 4
>   %argc.addr = alloca i32, align 4
>   %argv.addr = alloca i8**, align 8
>   %i = alloca i32, align 4
>   store i32 0, i32* %retval
>   store i32 %argc, i32* %argc.addr, align 4
>   store i8** %argv, i8*** %argv.addr, align 8
>   store i32 0, i32* %i, align 4
>   br label %for.cond
>
> for.cond:                                         ; preds = %for.inc, 
> %entry
>   %0 = load i32* %i, align 4
>   %cmp = icmp slt i32 %0, 10
>   br i1 %cmp, label %for.body, label %for.end
>
> for.body:                                         ; preds = %for.cond
>   %1 = load i32* %i, align 4
>   %call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 
> x i8]* @.str, i32 0, i32 0), i32 %1)
>   br label %for.inc
>
> for.inc:                                          ; preds = %for.body
>   %2 = load i32* %i, align 4
>   %inc = add nsw i32 %2, 1
>   store i32 %inc, i32* %i, align 4
>   br label %for.cond
>
> for.end:                                          ; preds = %for.cond
>   ret i32 0
> }
>
> declare i32 @printf(i8*, ...)
>
> $ ./build/Release+Asserts/bin/opt -S -internalize -globaldce hello0.ll 
> -o hello0.dce.ll
>
> $ cat hello0.dce.ll
> ; ModuleID = 'hello0.ll'
> target datalayout = 
>
"e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
> target triple = "x86_64-unknown-linux-gnu"
>
> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align
1
>
> define i32 @main(i32 %argc, i8** %argv) nounwind uwtable {
> entry:
>   %retval = alloca i32, align 4
>   %argc.addr = alloca i32, align 4
>   %argv.addr = alloca i8**, align 8
>   %i = alloca i32, align 4
>   store i32 0, i32* %retval
>   store i32 %argc, i32* %argc.addr, align 4
>   store i8** %argv, i8*** %argv.addr, align 8
>   store i32 0, i32* %i, align 4
>   br label %for.cond
>
> for.cond:                                         ; preds = %for.inc, 
> %entry
>   %0 = load i32* %i, align 4
>   %cmp = icmp slt i32 %0, 10
>   br i1 %cmp, label %for.body, label %for.end
>
> for.body:                                         ; preds = %for.cond
>   %1 = load i32* %i, align 4
>   %call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 
> x i8]* @.str, i32 0, i32 0), i32 %1)
>   br label %for.inc
>
> for.inc:                                          ; preds = %for.body
>   %2 = load i32* %i, align 4
>   %inc = add nsw i32 %2, 1
>   store i32 %inc, i32* %i, align 4
>   br label %for.cond
>
> for.end:                                          ; preds = %for.cond
>   ret i32 0
> }
>
> declare i32 @printf(i8*, ...)
>
>
> Succeeded drop DeadFunction foo.
>
> Maybe I wrongly use the Internalize and GlobalDCE PASS together? 
> please give me some hints, thanks a lot!
>
>
> PS: LLVM 6.0 Internalize PASS is able to work, internal foo:
>
> $ /opt/llvm-svn/bin/opt -S -internalize hello2.ll -o hello2.internal.ll
>
> $ cat hello2.internal.ll
> ; ModuleID = 'hello2.ll'
> source_filename = "hello.c"
> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
> target triple = "x86_64-unknown-linux-gnu"
>
> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align
1
>
> ; Function Attrs: noinline nounwind uwtable
> define internal void @foo() #0 {
> entry:
>   ret void
> }
>
> ; Function Attrs: noinline nounwind uwtable
> define internal i32 @main(i32 %argc, i8** %argv) #0 {
> entry:
>   %retval = alloca i32, align 4
>   %argc.addr = alloca i32, align 4
>   %argv.addr = alloca i8**, align 8
>   %i = alloca i32, align 4
>   store i32 0, i32* %retval, align 4
>   store i32 %argc, i32* %argc.addr, align 4
>   store i8** %argv, i8*** %argv.addr, align 8
>   store i32 0, i32* %i, align 4
>   br label %for.cond
>
> for.cond:                                         ; preds = %for.inc, 
> %entry
>   %0 = load i32, i32* %i, align 4
>   %cmp = icmp slt i32 %0, 10
>   br i1 %cmp, label %for.body, label %for.end
>
> for.body:                                         ; preds = %for.cond
>   %1 = load i32, i32* %i, align 4
>   %call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x 
> i8], [4 x i8]* @.str, i32 0, i32 0), i32 %1)
>   br label %for.inc
>
> for.inc:                                          ; preds = %for.body
>   %2 = load i32, i32* %i, align 4
>   %inc = add nsw i32 %2, 1
>   store i32 %inc, i32* %i, align 4
>   br label %for.cond
>
> for.end:                                          ; preds = %for.cond
>   ret i32 0
> }
>
> declare i32 @printf(i8*, ...) #1
>
> attributes #0 = { noinline nounwind uwtable 
> "correctly-rounded-divide-sqrt-fp-math"="false" 
> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
> "no-infs-fp-math"="false"
"no-jump-tables"="false"
> "no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
> "no-trapping-math"="false"
"stack-protector-buffer-size"="8"
> "target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
> "unsafe-fp-math"="false"
"use-soft-float"="false" }
> attributes #1 = {
"correctly-rounded-divide-sqrt-fp-math"="false"
> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
> "no-infs-fp-math"="false"
"no-nans-fp-math"="false"
> "no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
> "stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
> "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" 
> "unsafe-fp-math"="false"
"use-soft-float"="false" }
>
> !llvm.module.flags = !{!0}
> !llvm.ident = !{!1}
>
> !0 = !{i32 1, !"wchar_size", i32 4}
> !1 = !{!"clang version 6.0.0 (git at github.com:llvm-mirror/clang.git 
> 0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
> (git at github.com:llvm-mirror/llvm.git 
> d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}
>
-- 
Hal Finkel
Lead, Compiler Technology and Programming Languages
Leadership Computing Facility
Argonne National Laboratory

Leslie Zhai via llvm-dev

2017-Oct-26 02:07 UTC

head link

[llvm-dev] LLVM v6.0 Internalize and GlobalDCE PASS can not work together?

Hi Hal,

Thanks for your hint!

$ /opt/llvm-svn/bin/opt -S -internalize 
-internalize-public-api-list=main -globaldce hello3.ll -o 
hello3.dce.ll    it works :)

But I argue that `main` Function should be inserted into ExternalNames 
by default:

Index: lib/Transforms/IPO/Internalize.cpp
==================================================================---
lib/Transforms/IPO/Internalize.cpp  (revision 316540)
+++ lib/Transforms/IPO/Internalize.cpp  (working copy)
@@ -61,6 +61,7 @@
      if (!APIFile.empty())
        LoadFile(APIFile);
      ExternalNames.insert(APIList.begin(), APIList.end());
+    ExternalNames.insert("main");
    }

    bool operator()(const GlobalValue &GV) {


在 2017年10月25日 21:20, Hal Finkel 写道:> Hi, Leslie,
>
> When you use internalize, you need to provide it with a list of 
> symbols to preserve as external (otherwise everything will be 
> internalized, including main, and then DCE will remove everything). 
> You can use -internalize-public-api-list=main (a comma-separated list) 
> or -internalize-public-api-file=some_file_name where some_file_name 
> has the list of symbols. See the comments in 
> lib/Transforms/IPO/Internalize.cpp.
>
>  -Hal
>
> On 10/24/2017 11:22 PM, Leslie Zhai via llvm-dev wrote:
>> Hi LLVM developers,
>>
>> $ cat hello.c
>> #include <stdio.h>
>>
>> void foo() {
>> }
>>
>> int main(int argc, char *argv[]) {
>>   for (int i = 0; i < 10; i++) {
>>     printf("%d\n", i);
>>   }
>>   return 0;
>> }
>>
>> $ /opt/llvm-svn/bin/clang --version
>> Fedora clang version 6.0.0 (trunk 316308) (based on LLVM 6.0.0svn)
>> Target: x86_64-redhat-linux
>> Thread model: posix
>> InstalledDir: /opt/llvm-svn/bin
>>
>> $ /opt/llvm-svn/bin/clang -Xclang -disable-O0-optnone -S -emit-llvm 
>> hello.c -o hello2.ll
>>
>> $ cat hello2.ll
>> ; ModuleID = 'hello.c'
>> source_filename = "hello.c"
>> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
>> target triple = "x86_64-unknown-linux-gnu"
>>
>> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00",
align 1
>>
>> ; Function Attrs: noinline nounwind uwtable
>> define void @foo() #0 {
>> entry:
>>   ret void
>> }
>>
>> ; Function Attrs: noinline nounwind uwtable
>> define i32 @main(i32 %argc, i8** %argv) #0 {
>> entry:
>>   %retval = alloca i32, align 4
>>   %argc.addr = alloca i32, align 4
>>   %argv.addr = alloca i8**, align 8
>>   %i = alloca i32, align 4
>>   store i32 0, i32* %retval, align 4
>>   store i32 %argc, i32* %argc.addr, align 4
>>   store i8** %argv, i8*** %argv.addr, align 8
>>   store i32 0, i32* %i, align 4
>>   br label %for.cond
>>
>> for.cond:                                         ; preds = %for.inc, 
>> %entry
>>   %0 = load i32, i32* %i, align 4
>>   %cmp = icmp slt i32 %0, 10
>>   br i1 %cmp, label %for.body, label %for.end
>>
>> for.body:                                         ; preds = %for.cond
>>   %1 = load i32, i32* %i, align 4
>>   %call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 
>> x i8], [4 x i8]* @.str, i32 0, i32 0), i32 %1)
>>   br label %for.inc
>>
>> for.inc:                                          ; preds = %for.body
>>   %2 = load i32, i32* %i, align 4
>>   %inc = add nsw i32 %2, 1
>>   store i32 %inc, i32* %i, align 4
>>   br label %for.cond
>>
>> for.end:                                          ; preds = %for.cond
>>   ret i32 0
>> }
>>
>> declare i32 @printf(i8*, ...) #1
>>
>> attributes #0 = { noinline nounwind uwtable 
>> "correctly-rounded-divide-sqrt-fp-math"="false" 
>> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
>> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
>> "no-infs-fp-math"="false"
"no-jump-tables"="false"
>> "no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
>> "no-trapping-math"="false"
"stack-protector-buffer-size"="8"
>> "target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
>> "unsafe-fp-math"="false"
"use-soft-float"="false" }
>> attributes #1 = {
"correctly-rounded-divide-sqrt-fp-math"="false"
>> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
>> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
>> "no-infs-fp-math"="false"
"no-nans-fp-math"="false"
>> "no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
>> "stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
>> "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" 
>> "unsafe-fp-math"="false"
"use-soft-float"="false" }
>>
>> !llvm.module.flags = !{!0}
>> !llvm.ident = !{!1}
>>
>> !0 = !{i32 1, !"wchar_size", i32 4}
>> !1 = !{!"clang version 6.0.0 (git at
github.com:llvm-mirror/clang.git
>> 0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
>> (git at github.com:llvm-mirror/llvm.git 
>> d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}
>>
>> $ /opt/llvm-svn/bin/opt -S -internalize -globaldce hello2.ll -o 
>> hello2.dce.ll
>>
>> $ cat hello2.dce.ll
>> ; ModuleID = 'hello2.ll'
>> source_filename = "hello.c"
>> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
>> target triple = "x86_64-unknown-linux-gnu"
>>
>> !llvm.module.flags = !{!0}
>> !llvm.ident = !{!1}
>>
>> !0 = !{i32 1, !"wchar_size", i32 4}
>> !1 = !{!"clang version 6.0.0 (git at
github.com:llvm-mirror/clang.git
>> 0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
>> (git at github.com:llvm-mirror/llvm.git 
>> d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}
>>
>> $ /opt/llvm-svn/bin/lli hello2.dce.ll
>> 'main' function not found in module.
>>
>>
>> *No* more Alive Functions, so LLVM v6.0 Internalize and GlobalDCE 
>> PASS failed to MarkLive Function together?
>>
>>
>> But LLVM 3.1 is able to work together:
>>
>> $ ./build/Release+Asserts/bin/opt --version
>> LLVM (http://llvm.org/):
>>   LLVM version 3.1
>>   Optimized build with assertions.
>>   Built Oct 23 2017 (16:22:51).
>>   Default target: x86_64-unknown-linux-gnu
>>   Host CPU: corei7-avx
>>
>> $ ./build/Release+Asserts/bin/clang -S -emit-llvm hello.c -o hello0.ll
>>
>> $ cat hello0.ll
>> ; ModuleID = 'hello.c'
>> target datalayout = 
>>
"e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
>> target triple = "x86_64-unknown-linux-gnu"
>>
>> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00",
align 1
>>
>> define void @foo() nounwind uwtable {
>> entry:
>>   ret void
>> }
>>
>> define i32 @main(i32 %argc, i8** %argv) nounwind uwtable {
>> entry:
>>   %retval = alloca i32, align 4
>>   %argc.addr = alloca i32, align 4
>>   %argv.addr = alloca i8**, align 8
>>   %i = alloca i32, align 4
>>   store i32 0, i32* %retval
>>   store i32 %argc, i32* %argc.addr, align 4
>>   store i8** %argv, i8*** %argv.addr, align 8
>>   store i32 0, i32* %i, align 4
>>   br label %for.cond
>>
>> for.cond:                                         ; preds = %for.inc, 
>> %entry
>>   %0 = load i32* %i, align 4
>>   %cmp = icmp slt i32 %0, 10
>>   br i1 %cmp, label %for.body, label %for.end
>>
>> for.body:                                         ; preds = %for.cond
>>   %1 = load i32* %i, align 4
>>   %call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 
>> x i8]* @.str, i32 0, i32 0), i32 %1)
>>   br label %for.inc
>>
>> for.inc:                                          ; preds = %for.body
>>   %2 = load i32* %i, align 4
>>   %inc = add nsw i32 %2, 1
>>   store i32 %inc, i32* %i, align 4
>>   br label %for.cond
>>
>> for.end:                                          ; preds = %for.cond
>>   ret i32 0
>> }
>>
>> declare i32 @printf(i8*, ...)
>>
>> $ ./build/Release+Asserts/bin/opt -S -internalize -globaldce 
>> hello0.ll -o hello0.dce.ll
>>
>> $ cat hello0.dce.ll
>> ; ModuleID = 'hello0.ll'
>> target datalayout = 
>>
"e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
>> target triple = "x86_64-unknown-linux-gnu"
>>
>> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00",
align 1
>>
>> define i32 @main(i32 %argc, i8** %argv) nounwind uwtable {
>> entry:
>>   %retval = alloca i32, align 4
>>   %argc.addr = alloca i32, align 4
>>   %argv.addr = alloca i8**, align 8
>>   %i = alloca i32, align 4
>>   store i32 0, i32* %retval
>>   store i32 %argc, i32* %argc.addr, align 4
>>   store i8** %argv, i8*** %argv.addr, align 8
>>   store i32 0, i32* %i, align 4
>>   br label %for.cond
>>
>> for.cond:                                         ; preds = %for.inc, 
>> %entry
>>   %0 = load i32* %i, align 4
>>   %cmp = icmp slt i32 %0, 10
>>   br i1 %cmp, label %for.body, label %for.end
>>
>> for.body:                                         ; preds = %for.cond
>>   %1 = load i32* %i, align 4
>>   %call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 
>> x i8]* @.str, i32 0, i32 0), i32 %1)
>>   br label %for.inc
>>
>> for.inc:                                          ; preds = %for.body
>>   %2 = load i32* %i, align 4
>>   %inc = add nsw i32 %2, 1
>>   store i32 %inc, i32* %i, align 4
>>   br label %for.cond
>>
>> for.end:                                          ; preds = %for.cond
>>   ret i32 0
>> }
>>
>> declare i32 @printf(i8*, ...)
>>
>>
>> Succeeded drop DeadFunction foo.
>>
>> Maybe I wrongly use the Internalize and GlobalDCE PASS together? 
>> please give me some hints, thanks a lot!
>>
>>
>> PS: LLVM 6.0 Internalize PASS is able to work, internal foo:
>>
>> $ /opt/llvm-svn/bin/opt -S -internalize hello2.ll -o hello2.internal.ll
>>
>> $ cat hello2.internal.ll
>> ; ModuleID = 'hello2.ll'
>> source_filename = "hello.c"
>> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
>> target triple = "x86_64-unknown-linux-gnu"
>>
>> @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00",
align 1
>>
>> ; Function Attrs: noinline nounwind uwtable
>> define internal void @foo() #0 {
>> entry:
>>   ret void
>> }
>>
>> ; Function Attrs: noinline nounwind uwtable
>> define internal i32 @main(i32 %argc, i8** %argv) #0 {
>> entry:
>>   %retval = alloca i32, align 4
>>   %argc.addr = alloca i32, align 4
>>   %argv.addr = alloca i8**, align 8
>>   %i = alloca i32, align 4
>>   store i32 0, i32* %retval, align 4
>>   store i32 %argc, i32* %argc.addr, align 4
>>   store i8** %argv, i8*** %argv.addr, align 8
>>   store i32 0, i32* %i, align 4
>>   br label %for.cond
>>
>> for.cond:                                         ; preds = %for.inc, 
>> %entry
>>   %0 = load i32, i32* %i, align 4
>>   %cmp = icmp slt i32 %0, 10
>>   br i1 %cmp, label %for.body, label %for.end
>>
>> for.body:                                         ; preds = %for.cond
>>   %1 = load i32, i32* %i, align 4
>>   %call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 
>> x i8], [4 x i8]* @.str, i32 0, i32 0), i32 %1)
>>   br label %for.inc
>>
>> for.inc:                                          ; preds = %for.body
>>   %2 = load i32, i32* %i, align 4
>>   %inc = add nsw i32 %2, 1
>>   store i32 %inc, i32* %i, align 4
>>   br label %for.cond
>>
>> for.end:                                          ; preds = %for.cond
>>   ret i32 0
>> }
>>
>> declare i32 @printf(i8*, ...) #1
>>
>> attributes #0 = { noinline nounwind uwtable 
>> "correctly-rounded-divide-sqrt-fp-math"="false" 
>> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
>> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
>> "no-infs-fp-math"="false"
"no-jump-tables"="false"
>> "no-nans-fp-math"="false"
"no-signed-zeros-fp-math"="false"
>> "no-trapping-math"="false"
"stack-protector-buffer-size"="8"
>> "target-cpu"="x86-64"
"target-features"="+fxsr,+mmx,+sse,+sse2,+x87"
>> "unsafe-fp-math"="false"
"use-soft-float"="false" }
>> attributes #1 = {
"correctly-rounded-divide-sqrt-fp-math"="false"
>> "disable-tail-calls"="false"
"less-precise-fpmad"="false"
>> "no-frame-pointer-elim"="true"
"no-frame-pointer-elim-non-leaf"
>> "no-infs-fp-math"="false"
"no-nans-fp-math"="false"
>> "no-signed-zeros-fp-math"="false"
"no-trapping-math"="false"
>> "stack-protector-buffer-size"="8"
"target-cpu"="x86-64"
>> "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" 
>> "unsafe-fp-math"="false"
"use-soft-float"="false" }
>>
>> !llvm.module.flags = !{!0}
>> !llvm.ident = !{!1}
>>
>> !0 = !{i32 1, !"wchar_size", i32 4}
>> !1 = !{!"clang version 6.0.0 (git at
github.com:llvm-mirror/clang.git
>> 0aed123216ad4a38a9c2b16f1783895fd5cb1a04) 
>> (git at github.com:llvm-mirror/llvm.git 
>> d209b37aec1e392dabbf9b5324ea4a60c36fbc55)"}
>>
>
-- 
Regards,
Leslie Zhai - https://reviews.llvm.org/p/xiangzhai/

Reasonably Related Threads

Search for more maybe matching threads

llvm dev - Oct 2017 - LLVM v6.0 Internalize and GlobalDCE PASS can not work together?

[llvm-dev] LLVM v6.0 Internalize and GlobalDCE PASS can not work together?

[llvm-dev] LLVM v6.0 Internalize and GlobalDCE PASS can not work together?

[llvm-dev] LLVM v6.0 Internalize and GlobalDCE PASS can not work together?

[llvm-dev] LLVM v6.0 Internalize and GlobalDCE PASS can not work together?

Reasonably Related Threads