Global merge for global symbols.

This commit is to improve global merge pass and support global symbol merge.
The global symbol merge is not enabled by default. For aarch64, we need some
more back-end fix to make it really benifit ADRP CSE.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210640 91177308-0d34-0410-b5e6-96231b3b80d8

5 files changed, 97 insertions, 65 deletions

diff --git a/test/Transforms/GlobalMerge/AArch64/arm64.ll b/test/Transforms/GlobalMerge/AArch64/arm64.ll
index 4715fd8de2..9174f72574 100644
--- a/test/Transforms/GlobalMerge/AArch64/arm64.ll
+++ b/test/Transforms/GlobalMerge/AArch64/arm64.ll
@@ -1,23 +1,6 @@
-; RUN: llc %s -O0 -o - | FileCheck -check-prefix=NO-MERGE %s
-; RUN: llc %s -O0 -o - -enable-global-merge=false | FileCheck -check-prefix=NO-MERGE %s
-; RUN: llc %s -O0 -o - -enable-global-merge=true | FileCheck -check-prefix=NO-MERGE %s
-; RUN: llc %s -O1 -o - | FileCheck -check-prefix=MERGE %s
-; RUN: llc %s -O1 -o - -enable-global-merge=false | FileCheck -check-prefix=NO-MERGE %s
-; RUN: llc %s -O1 -o - -enable-global-merge=true | FileCheck -check-prefix=MERGE %s
+; RUN: opt %s -mtriple=aarch64-linux-gnuabi -global-merge -S -o - | FileCheck %s
 
-; MERGE-NOT: .zerofill __DATA,__bss,_bar,20,2
-; MERGE-NOT: .zerofill __DATA,__bss,_baz,20,2
-; MERGE-NOT: .zerofill __DATA,__bss,_foo,20,2
-; MERGE: .zerofill __DATA,__bss,__MergedGlobals,60,4
-; MERGE-NOT: .zerofill __DATA,__bss,_bar,20,2
-; MERGE-NOT: .zerofill __DATA,__bss,_baz,20,2
-; MERGE-NOT: .zerofill __DATA,__bss,_foo,20,2
-
-; NO-MERGE-NOT: .zerofill __DATA,__bss,__MergedGlobals,60,4
-; NO-MERGE: .zerofill __DATA,__bss,_bar,20,2
-; NO-MERGE: .zerofill __DATA,__bss,_baz,20,2
-; NO-MERGE: .zerofill __DATA,__bss,_foo,20,2
-; NO-MERGE-NOT: .zerofill __DATA,__bss,__MergedGlobals,60,4
+; CHECK: @_MergedGlobals = internal global { [5 x i32], [5 x i32], [5 x i32] } zeroinitializer
 
 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-n32:64-S128"
 target triple = "arm64-apple-ios7.0.0"
diff --git a/test/Transforms/GlobalMerge/AArch64/global-merge-1.ll b/test/Transforms/GlobalMerge/AArch64/global-merge-1.ll
new file mode 100644
index 0000000000..f8854dd545
--- /dev/null
+++ b/test/Transforms/GlobalMerge/AArch64/global-merge-1.ll
@@ -0,0 +1,22 @@
+; RUN: opt %s -mtriple=aarch64-none-linux-gnu -global-merge -S -o - | FileCheck %s
+; RUN: opt %s -mtriple=aarch64-none-linux-gnu -global-merge -global-merge-on-external -S -o - | FileCheck %s
+
+; RUN: opt %s -mtriple=aarch64-linux-gnuabi -global-merge -S -o - | FileCheck %s
+; RUN: opt %s -mtriple=aarch64-linux-gnuabi -global-merge -global-merge-on-external -S -o - | FileCheck %s
+
+; RUN: opt %s -mtriple=aarch64-apple-ios -global-merge -S -o - | FileCheck %s
+; RUN: opt %s -mtriple=aarch64-apple-ios -global-merge -global-merge-on-external -S -o - | FileCheck %s
+
+@m = internal global i32 0, align 4
+@n = internal global i32 0, align 4
+
+; CHECK: @_MergedGlobals = internal global { i32, i32 } zeroinitializer
+
+define void @f1(i32 %a1, i32 %a2) {
+; CHECK-LABEL: @f1
+; CHECK: getelementptr inbounds ({ i32, i32 }* @_MergedGlobals, i32 0, i32 0)
+; CHECK: getelementptr inbounds ({ i32, i32 }* @_MergedGlobals, i32 0, i32 1)
+  store i32 %a1, i32* @m, align 4
+  store i32 %a2, i32* @n, align 4
+  ret void
+}
diff --git a/test/Transforms/GlobalMerge/AArch64/global-merge-2.ll b/test/Transforms/GlobalMerge/AArch64/global-merge-2.ll
new file mode 100644
index 0000000000..1876483882
--- /dev/null
+++ b/test/Transforms/GlobalMerge/AArch64/global-merge-2.ll
@@ -0,0 +1,30 @@
+; RUN: opt %s -mtriple=aarch64-none-linux-gnu -global-merge -global-merge-on-external -S -o - | FileCheck %s
+; RUN: opt %s -mtriple=aarch64-linux-gnuabi -global-merge -global-merge-on-external -S -o - | FileCheck %s
+; RUN: opt %s -mtriple=aarch64-apple-ios -global-merge -global-merge-on-external -S -o - | FileCheck %s
+
+@x = global i32 0, align 4
+@y = global i32 0, align 4
+@z = global i32 0, align 4
+
+; CHECK: @_MergedGlobals_x = global { i32, i32, i32 } zeroinitializer
+; CHECK: @x = alias getelementptr inbounds ({ i32, i32, i32 }* @_MergedGlobals_x, i32 0, i32 0)
+; CHECK: @y = alias getelementptr inbounds ({ i32, i32, i32 }* @_MergedGlobals_x, i32 0, i32 1)
+; CHECK: @z = alias getelementptr inbounds ({ i32, i32, i32 }* @_MergedGlobals_x, i32 0, i32 2)
+
+define void @f1(i32 %a1, i32 %a2) {
+; CHECK-LABEL: @f1
+; CHECK: getelementptr inbounds ({ i32, i32, i32 }* @_MergedGlobals_x, i32 0, i32 0)
+; CHECK: getelementptr inbounds ({ i32, i32, i32 }* @_MergedGlobals_x, i32 0, i32 1)
+  store i32 %a1, i32* @x, align 4
+  store i32 %a2, i32* @y, align 4
+  ret void
+}
+
+define void @g1(i32 %a1, i32 %a2) {
+; CHECK-LABEL: @g1
+; CHECK: getelementptr inbounds ({ i32, i32, i32 }* @_MergedGlobals_x, i32 0, i32 1)
+; CHECK: getelementptr inbounds ({ i32, i32, i32 }* @_MergedGlobals_x, i32 0, i32 2)
+  store i32 %a1, i32* @y, align 4
+  store i32 %a2, i32* @z, align 4
+  ret void
+}
diff --git a/test/Transforms/GlobalMerge/AArch64/global-merge-3.ll b/test/Transforms/GlobalMerge/AArch64/global-merge-3.ll
new file mode 100644
index 0000000000..811c3eef13
--- /dev/null
+++ b/test/Transforms/GlobalMerge/AArch64/global-merge-3.ll
@@ -0,0 +1,27 @@
+; RUN: opt %s -mtriple=aarch64-none-linux-gnu -global-merge -global-merge-on-external -S -o - | FileCheck %s
+; RUN: opt %s -mtriple=aarch64-linux-gnuabi -global-merge -global-merge-on-external -S -o - | FileCheck %s
+; RUN: opt %s -mtriple=aarch64-apple-ios -global-merge -global-merge-on-external -S -o - | FileCheck %s
+
+@x = global [1000 x i32] zeroinitializer, align 1
+@y = global [1000 x i32] zeroinitializer, align 1
+@z = internal global i32 1, align 4
+
+; CHECK: @_MergedGlobals_x = global { i32, [1000 x i32] } { i32 1, [1000 x i32] zeroinitializer }
+; CHECK: @_MergedGlobals_y = global { [1000 x i32] } zeroinitializer
+
+; CHECK: @x = alias getelementptr inbounds ({ i32, [1000 x i32] }* @_MergedGlobals_x, i32 0, i32 1)
+; CHECK: @y = alias getelementptr inbounds ({ [1000 x i32] }* @_MergedGlobals_y, i32 0, i32 0)
+
+define void @f1(i32 %a1, i32 %a2, i32 %a3) {
+; CHECK-LABEL: @f1
+; CHECK: %x3 = getelementptr inbounds [1000 x i32]* getelementptr inbounds ({ i32, [1000 x i32] }* @_MergedGlobals_x, i32 0, i32 1), i32 0, i64 3
+; CHECK: %y3 = getelementptr inbounds [1000 x i32]* getelementptr inbounds ({ [1000 x i32] }* @_MergedGlobals_y, i32 0, i32 0), i32 0, i64 3
+; CHECK: store i32 %a3, i32* getelementptr inbounds ({ i32, [1000 x i32] }* @_MergedGlobals_x, i32 0, i32 0), align 4
+
+  %x3 = getelementptr inbounds [1000 x i32]* @x, i32 0, i64 3
+  %y3 = getelementptr inbounds [1000 x i32]* @y, i32 0, i64 3
+  store i32 %a1, i32* %x3, align 4
+  store i32 %a2, i32* %y3, align 4
+  store i32 %a3, i32* @z, align 4
+  ret void
+}
diff --git a/test/Transforms/GlobalMerge/ARM/arm.ll b/test/Transforms/GlobalMerge/ARM/arm.ll
index 341597e618..e7553e9183 100644
--- a/test/Transforms/GlobalMerge/ARM/arm.ll
+++ b/test/Transforms/GlobalMerge/ARM/arm.ll
@@ -1,23 +1,4 @@
-; RUN: llc %s -O0 -o - | FileCheck -check-prefix=NO-MERGE %s
-; RUN: llc %s -O0 -o - -enable-global-merge=false | FileCheck -check-prefix=NO-MERGE %s
-; RUN: llc %s -O0 -o - -enable-global-merge=true | FileCheck -check-prefix=NO-MERGE %s
-; RUN: llc %s -O1 -o - | FileCheck -check-prefix=MERGE %s
-; RUN: llc %s -O1 -o - -enable-global-merge=false | FileCheck -check-prefix=NO-MERGE %s
-; RUN: llc %s -O1 -o - -enable-global-merge=true | FileCheck -check-prefix=MERGE %s
-
-; MERGE-NOT: .zerofill __DATA,__bss,_bar,20,2
-; MERGE-NOT: .zerofill __DATA,__bss,_baz,20,2
-; MERGE-NOT: .zerofill __DATA,__bss,_foo,20,2
-; MERGE: .zerofill __DATA,__bss,__MergedGlobals,60,4
-; MERGE-NOT: .zerofill __DATA,__bss,_bar,20,2
-; MERGE-NOT: .zerofill __DATA,__bss,_baz,20,2
-; MERGE-NOT: .zerofill __DATA,__bss,_foo,20,2
-
-; NO-MERGE-NOT: .zerofill __DATA,__bss,__MergedGlobals,60,4
-; NO-MERGE: .zerofill __DATA,__bss,_bar,20,2
-; NO-MERGE: .zerofill __DATA,__bss,_baz,20,2
-; NO-MERGE: .zerofill __DATA,__bss,_foo,20,2
-; NO-MERGE-NOT: .zerofill __DATA,__bss,__MergedGlobals,60,4
+; RUN: opt %s -mtriple=arm-linux-gnuabi -global-merge -S -o - | FileCheck %s
 
 target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
 target triple = "thumbv7-apple-ios3.0.0"
@@ -26,28 +7,30 @@ target triple = "thumbv7-apple-ios3.0.0"
 @baz = internal global [5 x i32] zeroinitializer, align 4
 @foo = internal global [5 x i32] zeroinitializer, align 4
 
+; CHECK: @_MergedGlobals = internal global { [5 x i32], [5 x i32], [5 x i32] } zeroinitializer
+
 ; Function Attrs: nounwind ssp
 define internal void @initialize() #0 {
   %1 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
-  store i32 %1, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 0), align 4, !tbaa !1
+  store i32 %1, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 0), align 4
   %2 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
-  store i32 %2, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 0), align 4, !tbaa !1
+  store i32 %2, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 0), align 4
   %3 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
-  store i32 %3, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 1), align 4, !tbaa !1
+  store i32 %3, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 1), align 4
   %4 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
-  store i32 %4, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 1), align 4, !tbaa !1
+  store i32 %4, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 1), align 4
   %5 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
-  store i32 %5, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 2), align 4, !tbaa !1
+  store i32 %5, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 2), align 4
   %6 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
-  store i32 %6, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 2), align 4, !tbaa !1
+  store i32 %6, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 2), align 4
   %7 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
-  store i32 %7, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 3), align 4, !tbaa !1
+  store i32 %7, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 3), align 4
   %8 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
-  store i32 %8, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 3), align 4, !tbaa !1
+  store i32 %8, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 3), align 4
   %9 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
-  store i32 %9, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 4), align 4, !tbaa !1
+  store i32 %9, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 4), align 4
   %10 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
-  store i32 %10, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 4), align 4, !tbaa !1
+  store i32 %10, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 4), align 4
   ret void
 }
 
@@ -59,10 +42,10 @@ define internal void @calculate() #0 {
   %2 = load <4 x i32>* bitcast ([5 x i32]* @baz to <4 x i32>*), align 4
   %3 = mul <4 x i32> %2, %1
   store <4 x i32> %3, <4 x i32>* bitcast ([5 x i32]* @foo to <4 x i32>*), align 4
-  %4 = load i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 4), align 4, !tbaa !1
-  %5 = load i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 4), align 4, !tbaa !1
+  %4 = load i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 4), align 4
+  %5 = load i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 4), align 4
   %6 = mul nsw i32 %5, %4
-  store i32 %6, i32* getelementptr inbounds ([5 x i32]* @foo, i32 0, i32 4), align 4, !tbaa !1
+  store i32 %6, i32* getelementptr inbounds ([5 x i32]* @foo, i32 0, i32 4), align 4
   ret void
 }
 
@@ -70,16 +53,3 @@ define internal void @calculate() #0 {
 define internal i32* @returnFoo() #2 {
   ret i32* getelementptr inbounds ([5 x i32]* @foo, i32 0, i32 0)
 }
-
-attributes #0 = { nounwind ssp "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" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
-attributes #1 = { "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" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
-attributes #2 = { nounwind readnone ssp "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" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
-attributes #3 = { nounwind }
-
-!llvm.ident = !{!0}
-
-!0 = metadata !{metadata !"LLVM version 3.4 "}
-!1 = metadata !{metadata !2, metadata !2, i64 0}
-!2 = metadata !{metadata !"int", metadata !3, i64 0}
-!3 = metadata !{metadata !"omnipotent char", metadata !4, i64 0}
-!4 = metadata !{metadata !"Simple C/C++ TBAA"}