Move GlobalMerge from Transform to CodeGen.

This patch is to move GlobalMerge pass from Transform/Scalar                                                           
to CodeGen, because GlobalMerge depends on TargetMachine.
In the mean time, the macro INITIALIZE_TM_PASS is also moved
to CodeGen/Passes.h. With this fix we can avoid making
libScalarOpts depend on libCodeGen.

llvm-svn: 210951

4 files changed, 201 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/AArch64/global-merge-1.ll b/llvm/test/CodeGen/AArch64/global-merge-1.ll
new file mode 100644
index 00000000000..68aba5ebe06
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/global-merge-1.ll
@@ -0,0 +1,26 @@
+; RUN: llc %s -mtriple=aarch64-none-linux-gnu -enable-global-merge -o - | FileCheck %s
+; RUN: llc %s -mtriple=aarch64-none-linux-gnu -enable-global-merge -global-merge-on-external -o - | FileCheck %s
+
+; RUN: llc %s -mtriple=aarch64-linux-gnuabi -enable-global-merge -o - | FileCheck %s
+; RUN: llc %s -mtriple=aarch64-linux-gnuabi -enable-global-merge -global-merge-on-external -o - | FileCheck %s
+
+; RUN: llc %s -mtriple=aarch64-apple-ios -enable-global-merge -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS
+; RUN: llc %s -mtriple=aarch64-apple-ios -enable-global-merge -global-merge-on-external -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS
+
+@m = internal global i32 0, align 4
+@n = internal global i32 0, align 4
+
+define void @f1(i32 %a1, i32 %a2) {
+;CHECK-APPLE-IOS: adrp	x8, __MergedGlobals@PAGE
+;CHECK-APPLE-IOS-NOT: adrp
+;CHECK-APPLE-IOS: add	x8, x8, __MergedGlobals@PAGEOFF
+  store i32 %a1, i32* @m, align 4
+  store i32 %a2, i32* @n, align 4
+  ret void
+}
+
+;CHECK:	.type	_MergedGlobals,@object  // @_MergedGlobals
+;CHECK:	.local	_MergedGlobals
+;CHECK:	.comm	_MergedGlobals,8,8
+
+;CHECK-APPLE-IOS: .zerofill __DATA,__bss,__MergedGlobals,8,3 ; @_MergedGlobals
diff --git a/llvm/test/CodeGen/AArch64/global-merge-2.ll b/llvm/test/CodeGen/AArch64/global-merge-2.ll
new file mode 100644
index 00000000000..a7735667b35
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/global-merge-2.ll
@@ -0,0 +1,51 @@
+; RUN: llc %s -mtriple=aarch64-none-linux-gnu -enable-global-merge -global-merge-on-external -o - | FileCheck %s
+; RUN: llc %s -mtriple=aarch64-linux-gnuabi -enable-global-merge -global-merge-on-external -o - | FileCheck %s
+; RUN: llc %s -mtriple=aarch64-apple-ios -enable-global-merge -global-merge-on-external -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS
+
+@x = global i32 0, align 4
+@y = global i32 0, align 4
+@z = global i32 0, align 4
+
+define void @f1(i32 %a1, i32 %a2) {
+;CHECK-APPLE-IOS-LABEL: _f1:
+;CHECK-APPLE-IOS: adrp	x8, __MergedGlobals_x@PAGE
+;CHECK-APPLE-IOS: add	x8, x8, __MergedGlobals_x@PAGEOFF
+;CHECK-APPLE-IOS-NOT: adrp
+  store i32 %a1, i32* @x, align 4
+  store i32 %a2, i32* @y, align 4
+  ret void
+}
+
+define void @g1(i32 %a1, i32 %a2) {
+;CHECK-APPLE-IOS-LABEL: _g1:
+;CHECK-APPLE-IOS: adrp	x8, __MergedGlobals_x@PAGE
+;CHECK-APPLE-IOS: add	x8, x8, __MergedGlobals_x@PAGEOFF
+;CHECK-APPLE-IOS-NOT: adrp
+  store i32 %a1, i32* @y, align 4
+  store i32 %a2, i32* @z, align 4
+  ret void
+}
+
+;CHECK:	.type	_MergedGlobals_x,@object // @_MergedGlobals_x
+;CHECK:	.globl	_MergedGlobals_x
+;CHECK:	.align	3
+;CHECK: _MergedGlobals_x:
+;CHECK:	.size	_MergedGlobals_x, 12
+
+;CHECK:	.globl	x
+;CHECK: x = _MergedGlobals_x
+;CHECK:	.globl	y
+;CHECK: y = _MergedGlobals_x+4
+;CHECK:	.globl	z
+;CHECK: z = _MergedGlobals_x+8
+
+;CHECK-APPLE-IOS: .globl	__MergedGlobals_x       ; @_MergedGlobals_x
+;CHECK-APPLE-IOS: .zerofill __DATA,__common,__MergedGlobals_x,12,3
+
+;CHECK-APPLE-IOS: .globl	_x
+;CHECK-APPLE-IOS: _x = __MergedGlobals_x
+;CHECK-APPLE-IOS: .globl	_y
+;CHECK-APPLE-IOS: _y = __MergedGlobals_x+4
+;CHECK-APPLE-IOS: .globl	_z
+;CHECK-APPLE-IOS: _z = __MergedGlobals_x+8
+;CHECK-APPLE-IOS: .subsections_via_symbols
diff --git a/llvm/test/CodeGen/AArch64/global-merge-3.ll b/llvm/test/CodeGen/AArch64/global-merge-3.ll
new file mode 100644
index 00000000000..d455d40edcc
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/global-merge-3.ll
@@ -0,0 +1,51 @@
+; RUN: llc %s -mtriple=aarch64-none-linux-gnu -enable-global-merge -global-merge-on-external -o - | FileCheck %s
+; RUN: llc %s -mtriple=aarch64-linux-gnuabi -enable-global-merge -global-merge-on-external -o - | FileCheck %s
+; RUN: llc %s -mtriple=aarch64-apple-ios -enable-global-merge -global-merge-on-external -o - | FileCheck %s --check-prefix=CHECK-APPLE-IOS
+
+@x = global [1000 x i32] zeroinitializer, align 1
+@y = global [1000 x i32] zeroinitializer, align 1
+@z = internal global i32 1, align 4
+
+define void @f1(i32 %a1, i32 %a2, i32 %a3) {
+;CHECK-APPLE-IOS: adrp	x8, __MergedGlobals_x@PAGE
+;CHECK-APPLE-IOS-NOT: adrp
+;CHECK-APPLE-IOS: add	x8, x8, __MergedGlobals_x@PAGEOFF
+;CHECK-APPLE-IOS: adrp	x9, __MergedGlobals_y@PAGE
+;CHECK-APPLE-IOS: add	x9, x9, __MergedGlobals_y@PAGEOFF
+  %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
+}
+
+;CHECK:	.type	_MergedGlobals_x,@object // @_MergedGlobals_x
+;CHECK: .globl	_MergedGlobals_x
+;CHECK: .align	4
+;CHECK: _MergedGlobals_x:
+;CHECK: .size	_MergedGlobals_x, 4004
+
+;CHECK: .type	_MergedGlobals_y,@object // @_MergedGlobals_y
+;CHECK: .globl	_MergedGlobals_y
+;CHECK: _MergedGlobals_y:
+;CHECK: .size	_MergedGlobals_y, 4000
+
+;CHECK-APPLE-IOS: .globl	__MergedGlobals_x       ; @_MergedGlobals_x
+;CHECK-APPLE-IOS: .align	4
+;CHECK-APPLE-IOS:  __MergedGlobals_x:
+;CHECK-APPLE-IOS: .long 1
+;CHECK-APPLE-IOS: .space	4000
+
+;CHECK-APPLE-IOS: .globl	__MergedGlobals_y       ; @_MergedGlobals_y
+;CHECK-APPLE-IOS: .zerofill __DATA,__common,__MergedGlobals_y,4000,4
+
+;CHECK:	.globl	x
+;CHECK: x = _MergedGlobals_x+4
+;CHECK:	.globl	y
+;CHECK: y = _MergedGlobals_y
+
+;CHECK-APPLE-IOS:.globl	_x
+;CHECK-APPLE-IOS: _x = __MergedGlobals_x+4
+;CHECK-APPLE-IOS:.globl	_y
+;CHECK-APPLE-IOS: _y = __MergedGlobals_y
diff --git a/llvm/test/CodeGen/AArch64/global-merge-4.ll b/llvm/test/CodeGen/AArch64/global-merge-4.ll
new file mode 100644
index 00000000000..a525ccd8dee
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/global-merge-4.ll
@@ -0,0 +1,73 @@
+; RUN: llc %s -mtriple=aarch64-linux-gnuabi -enable-global-merge -o - | FileCheck %s
+
+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"
+
+@bar = internal global [5 x i32] zeroinitializer, align 4
+@baz = internal global [5 x i32] zeroinitializer, align 4
+@foo = internal global [5 x i32] zeroinitializer, align 4
+
+; Function Attrs: nounwind ssp
+define internal void @initialize() #0 {
+  %1 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %1, i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 0), align 4
+  %2 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %2, i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 0), align 4
+  %3 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %3, i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 1), align 4
+  %4 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %4, i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 1), align 4
+  %5 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %5, i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 2), align 4
+  %6 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %6, i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 2), align 4
+  %7 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %7, i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 3), align 4
+  %8 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %8, i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 3), align 4
+  %9 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %9, i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 4), align 4
+  %10 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %10, i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 4), align 4
+  ret void
+}
+
+declare i32 @calc(...)
+
+; Function Attrs: nounwind ssp
+define internal void @calculate() #0 {
+  %1 = load i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 0), align 4
+  %2 = load i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 0), align 4
+  %3 = mul nsw i32 %2, %1
+  store i32 %3, i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 0), align 4
+  %4 = load i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 1), align 4
+  %5 = load i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 1), align 4
+  %6 = mul nsw i32 %5, %4
+  store i32 %6, i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 1), align 4
+  %7 = load i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 2), align 4
+  %8 = load i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 2), align 4
+  %9 = mul nsw i32 %8, %7
+  store i32 %9, i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 2), align 4
+  %10 = load i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 3), align 4
+  %11 = load i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 3), align 4
+  %12 = mul nsw i32 %11, %10
+  store i32 %12, i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 3), align 4
+  %13 = load i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 4), align 4
+  %14 = load i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 4), align 4
+  %15 = mul nsw i32 %14, %13
+  store i32 %15, i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 4), align 4
+  ret void
+}
+
+; Function Attrs: nounwind readnone ssp
+define internal i32* @returnFoo() #1 {
+  ret i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 0)
+}
+
+;CHECK:	.type	_MergedGlobals,@object  // @_MergedGlobals
+;CHECK:	.local	_MergedGlobals
+;CHECK:	.comm	_MergedGlobals,60,16
+
+attributes #0 = { nounwind ssp }
+attributes #1 = { nounwind readnone ssp }
+attributes #2 = { nounwind }