Index: llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
@@ -128,7 +128,7 @@
 static cl::opt<bool>
     EnableGEPOpt("aarch64-enable-gep-opt", cl::Hidden,
                  cl::desc("Enable optimizations on complex GEPs"),
-                 cl::init(false));
+                 cl::init(true));
 
 static cl::opt<bool>
     BranchRelaxation("aarch64-enable-branch-relax", cl::Hidden, cl::init(true),
@@ -563,17 +563,6 @@
       addPass(createFalkorMarkStridedAccessesPass());
   }
 
-  TargetPassConfig::addIRPasses();
-
-  addPass(createAArch64StackTaggingPass(
-      /*IsOptNone=*/TM->getOptLevel() == CodeGenOpt::None));
-
-  // Match interleaved memory accesses to ldN/stN intrinsics.
-  if (TM->getOptLevel() != CodeGenOpt::None) {
-    addPass(createInterleavedLoadCombinePass());
-    addPass(createInterleavedAccessPass());
-  }
-
   if (TM->getOptLevel() == CodeGenOpt::Aggressive && EnableGEPOpt) {
     // Call SeparateConstOffsetFromGEP pass to extract constants within indices
     // and lower a GEP with multiple indices to either arithmetic operations or
@@ -587,6 +576,17 @@
     addPass(createLICMPass());
   }
 
+  TargetPassConfig::addIRPasses();
+
+  addPass(createAArch64StackTaggingPass(
+      /*IsOptNone=*/TM->getOptLevel() == CodeGenOpt::None));
+
+  // Match interleaved memory accesses to ldN/stN intrinsics.
+  if (TM->getOptLevel() != CodeGenOpt::None) {
+    addPass(createInterleavedLoadCombinePass());
+    addPass(createInterleavedAccessPass());
+  }
+
   // Add Control Flow Guard checks.
   if (TM->getTargetTriple().isOSWindows())
     addPass(createCFGuardCheckPass());
Index: llvm/test/CodeGen/AArch64/O3-pipeline.ll
===================================================================
--- llvm/test/CodeGen/AArch64/O3-pipeline.ll
+++ llvm/test/CodeGen/AArch64/O3-pipeline.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc --debugify-and-strip-all-safe=0 -mtriple=arm64-- -O3 -debug-pass=Structure < %s -o /dev/null 2>&1 | \
 ; RUN:     grep -v "Verify generated machine code" | FileCheck %s
 
@@ -33,9 +34,20 @@
 ; CHECK-NEXT:       Scalar Evolution Analysis
 ; CHECK-NEXT:       Loop Data Prefetch
 ; CHECK-NEXT:       Falkor HW Prefetch Fix
-; CHECK-NEXT:       Module Verifier
+; CHECK-NEXT:       Split GEPs to a variadic base and a constant offset for better CSE
+; CHECK-NEXT:       Early CSE
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
+; CHECK-NEXT:       Function Alias Analysis Results
+; CHECK-NEXT:       Memory SSA
 ; CHECK-NEXT:       Canonicalize natural loops
+; CHECK-NEXT:       LCSSA Verifier
+; CHECK-NEXT:       Loop-Closed SSA Form Pass
+; CHECK-NEXT:       Scalar Evolution Analysis
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
+; CHECK-NEXT:       Loop Pass Manager
+; CHECK-NEXT:         Loop Invariant Code Motion
+; CHECK-NEXT:       Module Verifier
 ; CHECK-NEXT:       Loop Pass Manager
 ; CHECK-NEXT:         Canonicalize Freeze Instructions in Loops
 ; CHECK-NEXT:         Induction Variable Users
Index: llvm/test/CodeGen/AArch64/cond-br-tuning.ll
===================================================================
--- llvm/test/CodeGen/AArch64/cond-br-tuning.ll
+++ llvm/test/CodeGen/AArch64/cond-br-tuning.ll
@@ -27,12 +27,13 @@
 define void @test_add_cbz_multiple_use(i32 %a, i32 %b, i32* %ptr) {
 ; CHECK-LABEL: test_add_cbz_multiple_use:
 ; CHECK:       // %bb.0: // %common.ret
-; CHECK-NEXT:    adds w8, w0, w1
+; CHECK-NEXT:    add w8, w0, w1
+; CHECK-NEXT:    cmp w8, #10
 ; CHECK-NEXT:    csel w8, wzr, w8, ne
 ; CHECK-NEXT:    str w8, [x2]
 ; CHECK-NEXT:    ret
   %c = add nsw i32 %a, %b
-  %d = icmp ne i32 %c, 0
+  %d = icmp ne i32 %c, 10
   br i1 %d, label %L1, label %L2
 L1:
   store i32 0, i32* %ptr, align 4