From f044d71e331d77a0039cec0a11859b5a3c72bc95 Mon Sep 17 00:00:00 2001
From: Heikki Linnakangas
Date: Wed, 4 Apr 2018 12:22:45 +0300
Subject: Use ARMv8 CRC instructions where available.

ARMv8 introduced special CPU instructions for calculating CRC-32C. Use
them, when available, for speed.

Like with the similar Intel CRC instructions, several factors affect
whether the instructions can be used. The compiler intrinsics for them must
be supported by the compiler, and the instructions must be supported by the
target architecture. If the compilation target architecture does not
support the instructions, but adding "-march=armv8-a+crc" makes them
available, then we compile the code with a runtime check to determine if
the host we're running on supports them or not.

For the runtime check, use glibc getauxval() function. Unfortunately,
that's not very portable, but I couldn't find any more portable way to do
it. If getauxval() is not available, the CRC instructions will still be
used if the target architecture supports them without any additional
compiler flags, but the runtime check will not be available.

Original patch by Yuqi Gu, heavily modified by me. Reviewed by Andres
Freund, Thomas Munro.

Discussion: https://www.postgresql.org/message-id/HE1PR0801MB1323D171938EABC04FFE7FA9E3110%40HE1PR0801MB1323.eurprd08.prod.outlook.com
---
 config/c-compiler.m4 | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

(limited to 'config/c-compiler.m4')

diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index b518851441b..ba5c40db01c 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -667,3 +667,37 @@ if test x"$Ac_cachevar" = x"yes"; then
 fi
 undefine([Ac_cachevar])dnl
 ])# PGAC_SSE42_CRC32_INTRINSICS
+
+
+# PGAC_ARMV8_CRC32C_INTRINSICS
+# -----------------------
+# Check if the compiler supports the CRC32C instructions using the __crc32cb,
+# __crc32ch, __crc32cw, and __crc32cd intrinsic functions. These instructions
+# were first introduced in ARMv8 in the optional CRC Extension, and became
+# mandatory in ARMv8.1.
+#
+# An optional compiler flag can be passed as argument (e.g.
+# -march=armv8-a+crc). If the intrinsics are supported, sets
+# pgac_armv8_crc32c_intrinsics, and CFLAGS_ARMV8_CRC32C.
+AC_DEFUN([PGAC_ARMV8_CRC32C_INTRINSICS],
+[define([Ac_cachevar], [AS_TR_SH([pgac_cv_armv8_crc32c_intrinsics_$1])])dnl
+AC_CACHE_CHECK([for __crc32cb, __crc32ch, __crc32cw, and __crc32cd with CFLAGS=$1], [Ac_cachevar],
+[pgac_save_CFLAGS=$CFLAGS
+CFLAGS="$pgac_save_CFLAGS $1"
+AC_LINK_IFELSE([AC_LANG_PROGRAM([#include <arm_acle.h>],
+  [unsigned int crc = 0;
+   crc = __crc32cb(crc, 0);
+   crc = __crc32ch(crc, 0);
+   crc = __crc32cw(crc, 0);
+   crc = __crc32cd(crc, 0);
+   /* return computed value, to prevent the above being optimized away */
+   return crc == 0;])],
+  [Ac_cachevar=yes],
+  [Ac_cachevar=no])
+CFLAGS="$pgac_save_CFLAGS"])
+if test x"$Ac_cachevar" = x"yes"; then
+  CFLAGS_ARMV8_CRC32C="$1"
+  pgac_armv8_crc32c_intrinsics=yes
+fi
+undefine([Ac_cachevar])dnl
+])# PGAC_ARMV8_CRC32C_INTRINSICS
-- 
cgit v1.2.3