Try to fix the CRC-32C autoconf magic for icc compiler.

On gcc and clang, the _mm_crc32_u8 and _mm_crc32_u64 intrinsics are not
defined at all, when not building with -msse4.2. But on icc, they are.
So we cannot assume that if those intrinsics are defined, we can always use
them safely, we might still need the runtime check.

To fix, check if the __SSE_4_2__ preprocessor symbol is defined. That's
supposed to be defined only when the compiler is targeting a processor that
has SSE 4.2 support.

Per buildfarm members fulmar and okapi.

diff --git a/configure b/configure
index 145056a55d164c58add5a7368df8f7cbd26acc5e..640314116371c00593cb5932aa1e62a42cf5b3e7 100755 (executable)
--- a/configure
+++ b/configure
@@ -14169,7 +14169,7 @@ fi
 
 # Check for Intel SSE 4.2 intrinsics to do CRC calculations.
 #
-# First check if the _mm_crc32_u8 and _mmcrc32_u64 intrinsics can be used
+# First check if the _mm_crc32_u8 and _mm_crc32_u64 intrinsics can be used
 # with the default compiler flags. If not, check if adding the -msse4.2
 # flag helps. CFLAGS_SSE42 is set to -msse4.2 if that's required.
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking for _mm_crc32_u8 and _mm_crc32_u64 with CFLAGS=" >&5
@@ -14254,23 +14254,49 @@ fi
 fi
 
 
+# Are we targeting a processor that supports SSE 4.2? gcc, clang and icc all
+# define __SSE4_2__ in that case.
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+int
+main ()
+{
+
+#ifndef __SSE4_2__
+#error __SSE4_2__ not defined
+#endif
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+  SSE4_2_TARGETED=1
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+
 # Select CRC-32C implementation.
 #
-# If the SSE 4.2 intrinsics are available without extra CFLAGS, then use them
-# always. If they require extra CFLAGS, compile both implementations and
-# select which one to use at runtime, depending on whether SSE 4.2 is
-# supported by the processor we're running on.
+# If we are targeting a processor that has SSE 4.2 instructions, we can use the
+# special CRC instructions for calculating CRC-32C. If we're not targeting such
+# a processor, but we can nevertheless produce code that uses the SSE
+# intrinsics, perhaps with some extra CFLAGS, compile both implementations and
+# select which one to use at runtime, depending on whether SSE 4.2 is supported
+# by the processor we're running on.
 #
 # You can override this logic by setting the appropriate USE_*_CRC32 flag to 1
 # in the template or configure command line.
 if test x"$USE_SSE42_CRC32C" = x"" && test x"$USE_SSE42_CRC32C_WITH_RUNTIME_CHECK" = x"" && test x"$USE_SLICING_BY_8_CRC32C" = x""; then
-  if test x"$pgac_sse42_crc32_intrinsics" = x"yes" && test x"$CFLAGS_SSE42" = x"" ; then
+  if test x"$pgac_sse42_crc32_intrinsics" = x"yes" && test x"$SSE4_2_TARGETED" = x"1" ; then
     USE_SSE42_CRC32C=1
   else
     # the CPUID instruction is needed for the runtime check.
     if test x"$pgac_sse42_crc32_intrinsics" = x"yes" && (test x"$pgac_cv__get_cpuid" = x"yes" || test x"$pgac_cv__cpuid" = x"yes"); then
       USE_SSE42_CRC32C_WITH_RUNTIME_CHECK=1
     else
+      # fall back to slicing-by-8 algorithm which doesn't require any special
+      # CPU support.
       USE_SLICING_BY_8_CRC32C=1
     fi
   fi

diff --git a/configure.in b/configure.in
index 96efdafcbb32c8e238ed22e3454a9410bbb31106..1cd9e1eb46fea48a091bda9e50f50b7d47e5a094 100644 (file)
--- a/configure.in
+++ b/configure.in
@@ -1816,7 +1816,7 @@ fi
 
 # Check for Intel SSE 4.2 intrinsics to do CRC calculations.
 #
-# First check if the _mm_crc32_u8 and _mmcrc32_u64 intrinsics can be used
+# First check if the _mm_crc32_u8 and _mm_crc32_u64 intrinsics can be used
 # with the default compiler flags. If not, check if adding the -msse4.2
 # flag helps. CFLAGS_SSE42 is set to -msse4.2 if that's required.
 PGAC_SSE42_CRC32_INTRINSICS([])
@@ -1825,23 +1825,35 @@ if test x"$pgac_sse42_crc32_intrinsics" != x"yes"; then
 fi
 AC_SUBST(CFLAGS_SSE42)
 
+# Are we targeting a processor that supports SSE 4.2? gcc, clang and icc all
+# define __SSE4_2__ in that case.
+AC_TRY_COMPILE([], [
+#ifndef __SSE4_2__
+#error __SSE4_2__ not defined
+#endif
+], [SSE4_2_TARGETED=1])
+
 # Select CRC-32C implementation.
 #
-# If the SSE 4.2 intrinsics are available without extra CFLAGS, then use them
-# always. If they require extra CFLAGS, compile both implementations and
-# select which one to use at runtime, depending on whether SSE 4.2 is
-# supported by the processor we're running on.
+# If we are targeting a processor that has SSE 4.2 instructions, we can use the
+# special CRC instructions for calculating CRC-32C. If we're not targeting such
+# a processor, but we can nevertheless produce code that uses the SSE
+# intrinsics, perhaps with some extra CFLAGS, compile both implementations and
+# select which one to use at runtime, depending on whether SSE 4.2 is supported
+# by the processor we're running on.
 #
 # You can override this logic by setting the appropriate USE_*_CRC32 flag to 1
 # in the template or configure command line.
 if test x"$USE_SSE42_CRC32C" = x"" && test x"$USE_SSE42_CRC32C_WITH_RUNTIME_CHECK" = x"" && test x"$USE_SLICING_BY_8_CRC32C" = x""; then
-  if test x"$pgac_sse42_crc32_intrinsics" = x"yes" && test x"$CFLAGS_SSE42" = x"" ; then
+  if test x"$pgac_sse42_crc32_intrinsics" = x"yes" && test x"$SSE4_2_TARGETED" = x"1" ; then
     USE_SSE42_CRC32C=1
   else
     # the CPUID instruction is needed for the runtime check.
     if test x"$pgac_sse42_crc32_intrinsics" = x"yes" && (test x"$pgac_cv__get_cpuid" = x"yes" || test x"$pgac_cv__cpuid" = x"yes"); then
       USE_SSE42_CRC32C_WITH_RUNTIME_CHECK=1
     else
+      # fall back to slicing-by-8 algorithm which doesn't require any special
+      # CPU support.
       USE_SLICING_BY_8_CRC32C=1
     fi
   fi