[ARM] Make GlobalMerge merge extern globals by default

Enabling merging of extern globals appears to be generally either beneficial or
harmless. On some benchmarks suites (on Cortex-M4F, Cortex-A9, and Cortex-A57)
it gives improvements in the 1-5% range, but in the rest the overall effect is
zero.

Differential Revision: http://reviews.llvm.org/D10966


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243874 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/ARM/ARMTargetMachine.cpp

@@ -348,7 +348,13 @@ bool ARMPassConfig::addPreISel() {
     // tricky when doing code gen per function.
     bool OnlyOptimizeForSize = (TM->getOptLevel() < CodeGenOpt::Aggressive) &&
                                (EnableGlobalMerge == cl::BOU_UNSET);
-    addPass(createGlobalMergePass(TM, 127, OnlyOptimizeForSize));
+    // Merging of extern globals is enabled by default on non-Mach-O as we
+    // expect it to be generally either beneficial or harmless. On Mach-O it
+    // is disabled as we emit the .subsections_via_symbols directive which
+    // means that merging extern globals is not safe.
+    bool MergeExternalByDefault = !TM->getTargetTriple().isOSBinFormatMachO();
+    addPass(createGlobalMergePass(TM, 127, OnlyOptimizeForSize,
+                                  MergeExternalByDefault));
   }
 
   return false;

test/CodeGen/ARM/global-merge-external.ll

@@ -0,0 +1,48 @@
+; RUN: llc < %s -mtriple=arm-eabi  -arm-global-merge                                 | FileCheck %s --check-prefix=CHECK-MERGE
+; RUN: llc < %s -mtriple=arm-eabi  -arm-global-merge -global-merge-on-external=true  | FileCheck %s --check-prefix=CHECK-MERGE
+; RUN: llc < %s -mtriple=arm-eabi  -arm-global-merge -global-merge-on-external=false | FileCheck %s --check-prefix=CHECK-NO-MERGE
+; RUN: llc < %s -mtriple=arm-macho -arm-global-merge                                 | FileCheck %s --check-prefix=CHECK-NO-MERGE
+
+@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:          f1:
+;CHECK:          ldr {{r[0-9]+}}, [[LABEL1:\.LCPI[0-9]+_[0-9]]]
+;CHECK:          [[LABEL1]]:
+;CHECK-MERGE:    .long _MergedGlobals_x
+;CHECK-NO-MERGE: .long {{_?x}}
+  store i32 %a1, i32* @x, align 4
+  store i32 %a2, i32* @y, align 4
+  ret void
+}
+
+define void @g1(i32 %a1, i32 %a2) {
+;CHECK:          g1:
+;CHECK:          ldr {{r[0-9]+}}, [[LABEL2:\.LCPI[0-9]+_[0-9]]]
+;CHECK:          [[LABEL2]]:
+;CHECK-MERGE:    .long _MergedGlobals_x
+;CHECK-NO-MERGE: .long {{_?y}}
+  store i32 %a1, i32* @y, align 4
+  store i32 %a2, i32* @z, align 4
+  ret void
+}
+
+;CHECK-NO-MERGE-NOT: .globl _MergedGlobals_x
+
+;CHECK-MERGE:	.type	_MergedGlobals_x,%object
+;CHECK-MERGE:	.globl	_MergedGlobals_x
+;CHECK-MERGE:	.align	2
+;CHECK-MERGE: _MergedGlobals_x:
+;CHECK-MERGE:	.size	_MergedGlobals_x, 12
+
+;CHECK-MERGE:	.globl	x
+;CHECK-MERGE: x = _MergedGlobals_x
+;CHECK-MERGE: .size x, 4
+;CHECK-MERGE:	.globl	y
+;CHECK-MERGE: y = _MergedGlobals_x+4
+;CHECK-MERGE: .size y, 4
+;CHECK-MERGE:	.globl	z
+;CHECK-MERGE: z = _MergedGlobals_x+8
+;CHECK-MERGE: .size z, 4