re PR libfortran/78379 (Processor-specific versions for matmul)

2016-12-03  Thomas Koenig  <tkoenig@gcc.gnu.org>

        PR fortran/78379
        * config/i386/cpuinfo.c:  Move denums for processor vendors,
        processor type, processor subtypes and declaration of
        struct __processor_model into
        * config/i386/cpuinfo.h:  New header file.
        * Makefile.am:  Add dependence of m4/matmul_internal_m4 to
        mamtul files..
        * Makefile.in:  Regenerated.
        * acinclude.m4:  Check for AVX, AVX2 and AVX512F.
        * config.h.in:  Add HAVE_AVX, HAVE_AVX2 and HAVE_AVX512F.
        * configure:  Regenerated.
        * configure.ac:  Use checks for AVX, AVX2 and AVX_512F.
        * m4/matmul_internal.m4:  New file. working part of matmul.m4.
        * m4/matmul.m4:  Implement architecture-specific switching
        for AVX, AVX2 and AVX512F by including matmul_internal.m4
        multiple times.
        * generated/matmul_c10.c: Regenerated.
        * generated/matmul_c16.c: Regenerated.
        * generated/matmul_c4.c: Regenerated.
        * generated/matmul_c8.c: Regenerated.
        * generated/matmul_i1.c: Regenerated.
        * generated/matmul_i16.c: Regenerated.
        * generated/matmul_i2.c: Regenerated.
        * generated/matmul_i4.c: Regenerated.
        * generated/matmul_i8.c: Regenerated.
        * generated/matmul_r10.c: Regenerated.
        * generated/matmul_r16.c: Regenerated.
        * generated/matmul_r4.c: Regenerated.
        * generated/matmul_r8.c: Regenerated.

From-SVN: r243219

libgcc/ChangeLog

+2016-12-03  Thomas Koenig  <tkoenig@gcc.gnu.org>
+
+	PR fortran/78379
+	* config/i386/cpuinfo.c:  Move denums for processor vendors,
+	processor type, processor subtypes and declaration of
+	struct __processor_model into
+	* config/i386/cpuinfo.h:  New header file.
+
 2016-12-02  Andre Vieira  <andre.simoesdiasvieira@arm.com>
 	    Thomas Preud'homme  <thomas.preudhomme@arm.com>
 

libgcc/config/i386/cpuinfo.c

@@ -26,6 +26,7 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 #include "cpuid.h"
 #include "tsystem.h"
 #include "auto-target.h"
+#include "cpuinfo.h"
 
 #ifdef HAVE_INIT_PRIORITY
 #define CONSTRUCTOR_PRIORITY (101)
@@ -36,97 +37,8 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 int __cpu_indicator_init (void)
   __attribute__ ((constructor CONSTRUCTOR_PRIORITY));
 
-/* Processor Vendor and Models. */
 
-enum processor_vendor
-{
-  VENDOR_INTEL = 1,
-  VENDOR_AMD,
-  VENDOR_OTHER,
-  VENDOR_MAX
-};
-
-/* Any new types or subtypes have to be inserted at the end. */
-
-enum processor_types
-{
-  INTEL_BONNELL = 1,
-  INTEL_CORE2,
-  INTEL_COREI7,
-  AMDFAM10H,
-  AMDFAM15H,
-  INTEL_SILVERMONT,
-  INTEL_KNL,
-  AMD_BTVER1,
-  AMD_BTVER2,  
-  AMDFAM17H,
-  CPU_TYPE_MAX
-};
-
-enum processor_subtypes
-{
-  INTEL_COREI7_NEHALEM = 1,
-  INTEL_COREI7_WESTMERE,
-  INTEL_COREI7_SANDYBRIDGE,
-  AMDFAM10H_BARCELONA,
-  AMDFAM10H_SHANGHAI,
-  AMDFAM10H_ISTANBUL,
-  AMDFAM15H_BDVER1,
-  AMDFAM15H_BDVER2,
-  AMDFAM15H_BDVER3,
-  AMDFAM15H_BDVER4,
-  AMDFAM17H_ZNVER1,
-  INTEL_COREI7_IVYBRIDGE,
-  INTEL_COREI7_HASWELL,
-  INTEL_COREI7_BROADWELL,
-  INTEL_COREI7_SKYLAKE,
-  INTEL_COREI7_SKYLAKE_AVX512,
-  CPU_SUBTYPE_MAX
-};
-
-/* ISA Features supported. New features have to be inserted at the end.  */
-
-enum processor_features
-{
-  FEATURE_CMOV = 0,
-  FEATURE_MMX,
-  FEATURE_POPCNT,
-  FEATURE_SSE,
-  FEATURE_SSE2,
-  FEATURE_SSE3,
-  FEATURE_SSSE3,
-  FEATURE_SSE4_1,
-  FEATURE_SSE4_2,
-  FEATURE_AVX,
-  FEATURE_AVX2,
-  FEATURE_SSE4_A,
-  FEATURE_FMA4,
-  FEATURE_XOP,
-  FEATURE_FMA,
-  FEATURE_AVX512F,
-  FEATURE_BMI,
-  FEATURE_BMI2,
-  FEATURE_AES,
-  FEATURE_PCLMUL,
-  FEATURE_AVX512VL,
-  FEATURE_AVX512BW,
-  FEATURE_AVX512DQ,
-  FEATURE_AVX512CD,
-  FEATURE_AVX512ER,
-  FEATURE_AVX512PF,
-  FEATURE_AVX512VBMI,
-  FEATURE_AVX512IFMA,
-  FEATURE_AVX5124VNNIW,
-  FEATURE_AVX5124FMAPS
-};
-
-struct __processor_model
-{
-  unsigned int __cpu_vendor;
-  unsigned int __cpu_type;
-  unsigned int __cpu_subtype;
-  unsigned int __cpu_features[1];
-} __cpu_model = { };
+struct __processor_model __cpu_model = { };
 
 
 /* Get the specific type of AMD CPU.  */

libgcc/config/i386/cpuinfo.h

+/* Get CPU type and Features for x86 processors.
+   Copyright (C) 2012-2016 Free Software Foundation, Inc.
+   Contributed by Sriraman Tallam (tmsriram@google.com)
+
+This file is part of GCC.
+
+GCC is free software; you can redistribute it and/or modify it under
+the terms of the GNU General Public License as published by the Free
+Software Foundation; either version 3, or (at your option) any later
+version.
+
+GCC is distributed in the hope that it will be useful, but WITHOUT ANY
+WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+for more details.
+
+Under Section 7 of GPL version 3, you are granted additional
+permissions described in the GCC Runtime Library Exception, version
+3.1, as published by the Free Software Foundation.
+
+You should have received a copy of the GNU General Public License and
+a copy of the GCC Runtime Library Exception along with this program;
+see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+<http://www.gnu.org/licenses/>.  */
+
+/* Processor Vendor and Models. */
+
+enum processor_vendor
+{
+  VENDOR_INTEL = 1,
+  VENDOR_AMD,
+  VENDOR_OTHER,
+  VENDOR_MAX
+};
+
+/* Any new types or subtypes have to be inserted at the end. */
+
+enum processor_types
+{
+  INTEL_BONNELL = 1,
+  INTEL_CORE2,
+  INTEL_COREI7,
+  AMDFAM10H,
+  AMDFAM15H,
+  INTEL_SILVERMONT,
+  INTEL_KNL,
+  AMD_BTVER1,
+  AMD_BTVER2,  
+  AMDFAM17H,
+  CPU_TYPE_MAX
+};
+
+enum processor_subtypes
+{
+  INTEL_COREI7_NEHALEM = 1,
+  INTEL_COREI7_WESTMERE,
+  INTEL_COREI7_SANDYBRIDGE,
+  AMDFAM10H_BARCELONA,
+  AMDFAM10H_SHANGHAI,
+  AMDFAM10H_ISTANBUL,
+  AMDFAM15H_BDVER1,
+  AMDFAM15H_BDVER2,
+  AMDFAM15H_BDVER3,
+  AMDFAM15H_BDVER4,
+  AMDFAM17H_ZNVER1,
+  INTEL_COREI7_IVYBRIDGE,
+  INTEL_COREI7_HASWELL,
+  INTEL_COREI7_BROADWELL,
+  INTEL_COREI7_SKYLAKE,
+  INTEL_COREI7_SKYLAKE_AVX512,
+  CPU_SUBTYPE_MAX
+};
+
+/* ISA Features supported. New features have to be inserted at the end.  */
+
+enum processor_features
+{
+  FEATURE_CMOV = 0,
+  FEATURE_MMX,
+  FEATURE_POPCNT,
+  FEATURE_SSE,
+  FEATURE_SSE2,
+  FEATURE_SSE3,
+  FEATURE_SSSE3,
+  FEATURE_SSE4_1,
+  FEATURE_SSE4_2,
+  FEATURE_AVX,
+  FEATURE_AVX2,
+  FEATURE_SSE4_A,
+  FEATURE_FMA4,
+  FEATURE_XOP,
+  FEATURE_FMA,
+  FEATURE_AVX512F,
+  FEATURE_BMI,
+  FEATURE_BMI2,
+  FEATURE_AES,
+  FEATURE_PCLMUL,
+  FEATURE_AVX512VL,
+  FEATURE_AVX512BW,
+  FEATURE_AVX512DQ,
+  FEATURE_AVX512CD,
+  FEATURE_AVX512ER,
+  FEATURE_AVX512PF,
+  FEATURE_AVX512VBMI,
+  FEATURE_AVX512IFMA,
+  FEATURE_AVX5124VNNIW,
+  FEATURE_AVX5124FMAPS
+};
+
+extern struct __processor_model
+{
+  unsigned int __cpu_vendor;
+  unsigned int __cpu_type;
+  unsigned int __cpu_subtype;
+  unsigned int __cpu_features[1];
+} __cpu_model;

libgfortran/ChangeLog

+2016-12-03  Thomas Koenig  <tkoenig@gcc.gnu.org>
+
+	PR fortran/78379
+	* Makefile.am:  Add dependence of m4/matmul_internal_m4 to
+	mamtul files..
+	* Makefile.in:  Regenerated.
+	* acinclude.m4:  Check for AVX, AVX2 and AVX512F.
+	* config.h.in:  Add HAVE_AVX, HAVE_AVX2 and HAVE_AVX512F.
+	* configure:  Regenerated.
+	* configure.ac:  Use checks for AVX, AVX2 and AVX_512F.
+	* m4/matmul_internal.m4:  New file. working part of matmul.m4.
+	* m4/matmul.m4:  Implement architecture-specific switching
+	for AVX, AVX2 and AVX512F by including matmul_internal.m4
+	multiple times.
+	* generated/matmul_c10.c: Regenerated.
+        * generated/matmul_c16.c: Regenerated.
+        * generated/matmul_c4.c: Regenerated.
+        * generated/matmul_c8.c: Regenerated.
+        * generated/matmul_i1.c: Regenerated.
+        * generated/matmul_i16.c: Regenerated.
+        * generated/matmul_i2.c: Regenerated.
+        * generated/matmul_i4.c: Regenerated.
+        * generated/matmul_i8.c: Regenerated.
+        * generated/matmul_r10.c: Regenerated.
+        * generated/matmul_r16.c: Regenerated.
+        * generated/matmul_r4.c: Regenerated.
+        * generated/matmul_r8.c: Regenerated.
+
 2016-11-30  Andre Vehreschild  <vehre@gcc.gnu.org>
 
 	* caf/single.c (_gfortran_caf_get_by_ref): Prevent compile time

libgfortran/Makefile.am

@@ -987,7 +987,7 @@ $(i_product_c): m4/product.m4 $(I_M4_DEPS1)
 $(i_sum_c): m4/sum.m4 $(I_M4_DEPS1)
 	$(M4) -Dfile=$@ -I$(srcdir)/m4 sum.m4 > $@
 
-$(i_matmul_c): m4/matmul.m4 $(I_M4_DEPS)
+$(i_matmul_c): m4/matmul.m4 m4/matmul_internal.m4 $(I_M4_DEPS)
 	$(M4) -Dfile=$@ -I$(srcdir)/m4 matmul.m4 > $@
 
 $(i_matmull_c): m4/matmull.m4 $(I_M4_DEPS)

libgfortran/Makefile.in

@@ -6053,7 +6053,7 @@ fpu-target.inc: fpu-target.h $(srcdir)/libgfortran.h
 @MAINTAINER_MODE_TRUE@$(i_sum_c): m4/sum.m4 $(I_M4_DEPS1)
 @MAINTAINER_MODE_TRUE@	$(M4) -Dfile=$@ -I$(srcdir)/m4 sum.m4 > $@
 
-@MAINTAINER_MODE_TRUE@$(i_matmul_c): m4/matmul.m4 $(I_M4_DEPS)
+@MAINTAINER_MODE_TRUE@$(i_matmul_c): m4/matmul.m4 m4/matmul_internal.m4 $(I_M4_DEPS)
 @MAINTAINER_MODE_TRUE@	$(M4) -Dfile=$@ -I$(srcdir)/m4 matmul.m4 > $@
 
 @MAINTAINER_MODE_TRUE@$(i_matmull_c): m4/matmull.m4 $(I_M4_DEPS)

libgfortran/acinclude.m4

@@ -393,3 +393,54 @@ AC_DEFUN([LIBGFOR_CHECK_STRERROR_R], [
 		  [Define if strerror_r takes two arguments and is available in <string.h>.]),)
   CFLAGS="$ac_save_CFLAGS"
 ])
+
+dnl Check for AVX
+
+AC_DEFUN([LIBGFOR_CHECK_AVX], [
+  ac_save_CFLAGS="$CFLAGS"
+  CFLAGS="-O2 -mavx"
+  AC_COMPILE_IFELSE([AC_LANG_PROGRAM([[
+  void _mm256_zeroall (void)
+        {
+           __builtin_ia32_vzeroall ();
+        }]], [[]])],
+	AC_DEFINE(HAVE_AVX, 1,
+	[Define if AVX instructions can be compiled.]),
+	[])
+  CFLAGS="$ac_save_CFLAGS"
+])
+
+dnl Check for AVX2
+
+AC_DEFUN([LIBGFOR_CHECK_AVX2], [
+  ac_save_CFLAGS="$CFLAGS"
+  CFLAGS="-O2 -mavx2"
+  AC_COMPILE_IFELSE([AC_LANG_PROGRAM([[
+  typedef long long __v4di __attribute__ ((__vector_size__ (32)));
+	__v4di
+	mm256_is32_andnotsi256  (__v4di __X, __v4di __Y)
+        {
+	   return __builtin_ia32_andnotsi256 (__X, __Y);
+        }]], [[]])],
+	AC_DEFINE(HAVE_AVX2, 1,
+	[Define if AVX2 instructions can be compiled.]),
+	[])
+  CFLAGS="$ac_save_CFLAGS"
+])
+
+dnl Check for AVX512f
+
+AC_DEFUN([LIBGFOR_CHECK_AVX512F], [
+  ac_save_CFLAGS="$CFLAGS"
+  CFLAGS="-O2 -mavx512f"
+  AC_COMPILE_IFELSE([AC_LANG_PROGRAM([[
+	typedef double __m512d __attribute__ ((__vector_size__ (64)));
+	__m512d _mm512_add (__m512d a)
+	{
+	  return __builtin_ia32_addpd512_mask (a, a, a, 1, 4);
+        }]], [[]])],
+	AC_DEFINE(HAVE_AVX512F, 1,
+	[Define if AVX512f instructions can be compiled.]),
+	[])
+  CFLAGS="$ac_save_CFLAGS"
+])

libgfortran/config.h.in

@@ -78,6 +78,15 @@
 /* Define to 1 if the target supports __attribute__((visibility(...))). */
 #undef HAVE_ATTRIBUTE_VISIBILITY
 
+/* Define if AVX instructions can be compiled. */
+#undef HAVE_AVX
+
+/* Define if AVX2 instructions can be compiled. */
+#undef HAVE_AVX2
+
+/* Define if AVX512f instructions can be compiled. */
+#undef HAVE_AVX512F
+
 /* Define to 1 if you have the `cabs' function. */
 #undef HAVE_CABS
 

libgfortran/configure

@@ -26174,6 +26174,93 @@ $as_echo "#define HAVE_CRLF 1" >>confdefs.h
 
 fi
 
+# Check whether we support AVX extensions
+
+  ac_save_CFLAGS="$CFLAGS"
+  CFLAGS="-O2 -mavx"
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+  void _mm256_zeroall (void)
+        {
+           __builtin_ia32_vzeroall ();
+        }
+int
+main ()
+{
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+
+$as_echo "#define HAVE_AVX 1" >>confdefs.h
+
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+  CFLAGS="$ac_save_CFLAGS"
+
+
+# Check wether we support AVX2 extensions
+
+  ac_save_CFLAGS="$CFLAGS"
+  CFLAGS="-O2 -mavx2"
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+  typedef long long __v4di __attribute__ ((__vector_size__ (32)));
+	__v4di
+	mm256_is32_andnotsi256  (__v4di __X, __v4di __Y)
+        {
+	   return __builtin_ia32_andnotsi256 (__X, __Y);
+        }
+int
+main ()
+{
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+
+$as_echo "#define HAVE_AVX2 1" >>confdefs.h
+
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+  CFLAGS="$ac_save_CFLAGS"
+
+
+# Check wether we support AVX512f extensions
+
+  ac_save_CFLAGS="$CFLAGS"
+  CFLAGS="-O2 -mavx512f"
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+	typedef double __m512d __attribute__ ((__vector_size__ (64)));
+	__m512d _mm512_add (__m512d a)
+	{
+	  return __builtin_ia32_addpd512_mask (a, a, a, 1, 4);
+        }
+int
+main ()
+{
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"; then :
+
+$as_echo "#define HAVE_AVX512F 1" >>confdefs.h
+
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+  CFLAGS="$ac_save_CFLAGS"
+
+
 cat >confcache <<\_ACEOF
 # This file is a shell script that caches the results of configure
 # tests run on this system so they can be shared between configure

libgfortran/configure.ac

@@ -609,6 +609,15 @@ LIBGFOR_CHECK_UNLINK_OPEN_FILE
 # Check whether line terminator is LF or CRLF
 LIBGFOR_CHECK_CRLF
 
+# Check whether we support AVX extensions
+LIBGFOR_CHECK_AVX
+
+# Check wether we support AVX2 extensions
+LIBGFOR_CHECK_AVX2
+
+# Check wether we support AVX512f extensions
+LIBGFOR_CHECK_AVX512F
+
 AC_CACHE_SAVE
 
 if test ${multilib} = yes; then