[AArch64] Merge globals when optimising for size

Extern global merging is good for code-size. There's definitely potential for
performance too, but there's one regression in a benchmark that needs
investigating, so that's why we enable it only when we optimise for size for
now.

Patch by Ramakota Reddy and Sjoerd Meijer.

Differential Revision: https://reviews.llvm.org/D61947

llvm-svn: 363130

llvm/lib/Target/AArch64/AArch64TargetMachine.cpp

@@ -462,7 +462,20 @@ bool AArch64PassConfig::addPreISel() {
       EnableGlobalMerge == cl::BOU_TRUE) {
     bool OnlyOptimizeForSize = (TM->getOptLevel() < CodeGenOpt::Aggressive) &&
                                (EnableGlobalMerge == cl::BOU_UNSET);
-    addPass(createGlobalMergePass(TM, 4095, 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();
+
+    // FIXME: extern global merging is only enabled when we optimise for size
+    // because there are some regressions with it also enabled for performance.
+    if (!OnlyOptimizeForSize)
+      MergeExternalByDefault = false;
+
+    addPass(createGlobalMergePass(TM, 4095, OnlyOptimizeForSize,
+                                  MergeExternalByDefault));
   }
 
   return false;

llvm/test/CodeGen/AArch64/global-merge-minsize.ll

@@ -0,0 +1,21 @@
+; RUN: llc %s -o - -verify-machineinstrs | FileCheck %s
+
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64-arm-none-eabi"
+
+@global0 = dso_local local_unnamed_addr global i32 0, align 4
+@global1 = dso_local local_unnamed_addr global i32 0, align 4
+
+define dso_local i32 @func() minsize optsize {
+; CHECK-LABEL: @func
+; CHECK:       adrp x8, .L_MergedGlobals
+; CHECK-NEXT:  add x8, x8, :lo12:.L_MergedGlobals
+; CHECK-NEXT:  ldp w9, w8, [x8]
+; CHECK-NEXT:  add w0, w8, w9
+; CHECK-NEXT:  ret
+entry:
+  %0 = load i32, i32* @global0, align 4
+  %1 = load i32, i32* @global1, align 4
+  %add = add nsw i32 %1, %0
+  ret i32 %add
+}