[AArch64] Fix the generation of BE Nops

Big endian Nops were being generated as d5 03 20 1f   fnmadd  s21, s30,
s0, s0, getting the bytes of the NOP in the wrong order. This switches
the bytes to not be dependant on the endianness.

Differential Revision: https://reviews.llvm.org/D125980

llvm/lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp

@@ -471,7 +471,7 @@ bool AArch64AsmBackend::writeNopData(raw_ostream &OS, uint64_t Count,
   // We are properly aligned, so write NOPs as requested.
   Count /= 4;
   for (uint64_t i = 0; i != Count; ++i)
-    support::endian::write<uint32_t>(OS, 0xd503201f, Endian);
+    OS.write("\x1f\x20\x03\xd5", 4);
   return true;
 }
 

llvm/test/MC/AArch64/align.s

@@ -0,0 +1,14 @@
+// RUN: llvm-mc -filetype=obj -triple aarch64-none-eabi %s | llvm-objdump -d - | FileCheck %s
+// RUN: llvm-mc -filetype=obj -triple aarch64_be-none-eabi %s | llvm-objdump -d - | FileCheck %s
+
+// CHECK:   0: 00 00 80 d2   mov     x0, #0
+// CHECK:   4: 00 00 80 d2   mov     x0, #0
+// CHECK:   8: 1f 20 03 d5   nop
+// CHECK:   c: 1f 20 03 d5   nop
+// CHECK:  10: 00 00 80 d2   mov     x0, #0
+
+       .text
+       mov x0, #0
+       mov x0, #0
+       .p2align 4
+       mov x0, #0