[X86] include cmpccxaddintrin.h from immintrin.h to x86gprintrin.h

[pengfei]

LGTM.

[FreddyYe]

minor fix.

clang/lib/Headers/cmpccxaddintrin.h

 /*===--------------- cmpccxaddintrin.h - CMPCCXADD intrinsics--------------===
  *
  *
  * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
  * See https://llvm.org/LICENSE.txt for license information.
  * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
  *
  *===-----------------------------------------------------------------------===
  */
-#ifndef __IMMINTRIN_H
-#error "Never use <cmpccxaddintrin.h> directly; include <immintrin.h> instead."
-#endif // __IMMINTRIN_H
+#ifndef __X86GPRINTRIN_H
+#error                                                                         \
+    "Never use <cmpccxaddintrin.h> directly; include <x86gprintrin.h> instead."
+#endif // __X86GPRINTRIN_H
 
 #ifndef __CMPCCXADDINTRIN_H
 #define __CMPCCXADDINTRIN_H
 #ifdef __x86_64__
 
 typedef enum {
   _CMPCCX_O,   /* Overflow.  */
   _CMPCCX_NO,  /* No overflow.  */

clang/lib/Headers/immintrin.h

 #include <invpcidintrin.h>
 #endif
 #if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) ||      \
     defined(__AMXFP16__)
 #include <amxfp16intrin.h>
 #endif
 
 #if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) ||      \
-    defined(__CMPCCXADD__)
-#include <cmpccxaddintrin.h>
-#endif
-
-#if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) ||      \
     defined(__KL__) || defined(__WIDEKL__)
 #include <keylockerintrin.h>
 #endif
 
 #if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) ||      \
     defined(__AMXTILE__) || defined(__AMXINT8__) || defined(__AMXBF16__)
 #include <amxintrin.h>
 #endif

clang/lib/Headers/x86gprintrin.h

 #include <prfchiintrin.h>
 #endif
 
 #if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) ||      \
     defined(__RAOINT__)
 #include <raointintrin.h>
 #endif
 
+#if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) ||      \
+    defined(__CMPCCXADD__)
+#include <cmpccxaddintrin.h>
+#endif
+
 #if defined(__i386__)
 #define __SAVE_GPRBX "mov {%%ebx, %%eax |eax, ebx};"
 #define __RESTORE_GPRBX "mov {%%eax, %%ebx |ebx, eax};"
 #define __TMPGPR "eax"
 #else
 // When in 64-bit target, the 32-bit operands generate a 32-bit result,
 // zero-extended to a 64-bit result in the destination general-purpose,
 // It means "mov x %ebx" will clobber the higher 32 bits of rbx, so we