diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -79,14 +79,17 @@
     CacheLineSize = 64;
     break;
   case CortexA35:
-    break;
   case CortexA53:
   case CortexA55:
     PrefFunctionLogAlignment = 4;
+    PrefLoopLogAlignment = 4;
+    MaxBytesForLoopAlignment = 8;
     break;
   case CortexA57:
     MaxInterleaveFactor = 4;
     PrefFunctionLogAlignment = 4;
+    PrefLoopLogAlignment = 4;
+    MaxBytesForLoopAlignment = 8;
     break;
   case CortexA65:
     PrefFunctionLogAlignment = 3;
@@ -94,6 +97,10 @@
   case CortexA72:
   case CortexA73:
   case CortexA75:
+    PrefFunctionLogAlignment = 4;
+    PrefLoopLogAlignment = 4;
+    MaxBytesForLoopAlignment = 8;
+    break;
   case CortexA76:
   case CortexA77:
   case CortexA78:
@@ -102,12 +109,21 @@
   case CortexX1:
   case CortexX1C:
     PrefFunctionLogAlignment = 4;
+    PrefLoopLogAlignment = 5;
+    MaxBytesForLoopAlignment = 16;
     break;
   case CortexA510:
+    PrefFunctionLogAlignment = 4;
+    VScaleForTuning = 1;
+    PrefLoopLogAlignment = 4;
+    MaxBytesForLoopAlignment = 8;
+    break;
   case CortexA710:
   case CortexX2:
     PrefFunctionLogAlignment = 4;
     VScaleForTuning = 1;
+    PrefLoopLogAlignment = 5;
+    MaxBytesForLoopAlignment = 16;
     break;
   case A64FX:
     CacheLineSize = 256;
diff --git a/llvm/test/CodeGen/AArch64/aarch64-p2align-max-bytes-neoverse.ll b/llvm/test/CodeGen/AArch64/aarch64-p2align-max-bytes-neoverse.ll
--- a/llvm/test/CodeGen/AArch64/aarch64-p2align-max-bytes-neoverse.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-p2align-max-bytes-neoverse.ll
@@ -1,12 +1,25 @@
-; RUN: llc -mtriple=aarch64-none-linux-gnu -align-loops=32 < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-DEFAULT
-; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=neoverse-n1 < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-N1
+; RUN: llc -mtriple=aarch64-none-linux-gnu -align-loops=32   < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-DEFAULT
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=neoverse-n1 < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-16
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=neoverse-n2 < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-16
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=neoverse-v1 < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-16
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=cortex-x1   < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-16
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=cortex-x2   < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-16
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=cortex-a35  < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-8
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=cortex-a53  < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-8
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=cortex-a55  < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-8
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=cortex-a57  < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-8
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=cortex-a510 < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-8
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=cortex-a75  < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-8
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=cortex-a710 < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-16
 
 define i32 @a(i32 %x, i32* nocapture readonly %y, i32* nocapture readonly %z) {
 ; CHECK-DEFAULT:    .p2align 5
-; CHECK-N1:         .p2align 5, 0x0, 16
+; CHECK-8:          .p2align 4, 0x0, 8
+; CHECK-16:         .p2align 5, 0x0, 16
 ; CHECK-NEXT:       .LBB0_5: // %vector.body
 ; CHECK-DEFAULT:    .p2align 5
-; CHECK-N1:         .p2align 5, 0x0, 16
+; CHECK-8:          .p2align 4, 0x0, 8
+; CHECK-16:         .p2align 5, 0x0, 16
 ; CHECK-NEXT:       .LBB0_8: // %for.body
 entry:
   %cmp10 = icmp sgt i32 %x, 0
diff --git a/llvm/test/CodeGen/AArch64/merge-store-dependency.ll b/llvm/test/CodeGen/AArch64/merge-store-dependency.ll
--- a/llvm/test/CodeGen/AArch64/merge-store-dependency.ll
+++ b/llvm/test/CodeGen/AArch64/merge-store-dependency.ll
@@ -35,6 +35,7 @@
 ; A53-NEXT:  // %bb.1:
 ; A53-NEXT:    ldr w8, [x19]
 ; A53-NEXT:    ldr w9, [x9]
+; A53-NEXT:    .p2align 4, 0x0, 8
 ; A53-NEXT:  .LBB0_2: // %while.body.i.split.ver.us
 ; A53-NEXT:    // =>This Inner Loop Header: Depth=1
 ; A53-NEXT:    lsl w9, w9, #1
@@ -46,6 +47,7 @@
 ; A53-NEXT:    str x0, [x8, :lo12:gv1]
 ; A53-NEXT:    ldp x30, x19, [sp], #16 // 16-byte Folded Reload
 ; A53-NEXT:    ret
+; A53-NEXT:    .p2align 4, 0x0, 8
 ; A53-NEXT:  .LBB0_4: // %while.body.i.split
 ; A53-NEXT:    // =>This Inner Loop Header: Depth=1
 ; A53-NEXT:    b .LBB0_4
diff --git a/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll b/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll
--- a/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll
+++ b/llvm/test/CodeGen/AArch64/preferred-function-alignment.ll
@@ -1,5 +1,5 @@
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=generic < %s | FileCheck --check-prefixes=ALIGN2,CHECK %s
-; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a35 < %s | FileCheck --check-prefixes=ALIGN2,CHECK %s
+; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a35 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a53 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a55 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
 ; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a57 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s