[multiple changes]

2016-11-15  Jerry DeLisle  <jvdelisle@gcc.gnu.org>
	    Thomas Koenig  <tkoenig@gcc.gnu.org>

	PR libgfortran/51119
	* Makefile.am: Add new optimization flags matmul.
	* Makefile.in: Regenerate.
	* m4/matmul.m4: For the case of all strides = 1, implement a
	fast blocked matrix multiply. Fix some whitespace.
	* generated/matmul_c10.c: Regenerate.
	* generated/matmul_c16.c: Regenerate.
	* generated/matmul_c4.c: Regenerate.
	* generated/matmul_c8.c: Regenerate.
	* generated/matmul_i1.c: Regenerate.
	* generated/matmul_i16.c: Regenerate.
	* generated/matmul_i2.c: Regenerate.
	* generated/matmul_i4.c: Regenerate.
	* generated/matmul_i8.c: Regenerate.
	* generated/matmul_r10.c: Regenerate.
	* generated/matmul_r16.c: Regenerate.
	* generated/matmul_r4.c: Regenerate.
	* generated/matmul_r8.c: Regenerate.

2016-11-15  Thomas Koenig  <tkoenig@gcc.gnu.org>

	PR libgfortran/51119
	* gfortran.dg/matmul_12.f90: New test case.

From-SVN: r242462

gcc/testsuite/ChangeLog

+2016-11-15  Thomas Koenig  <tkoenig@gcc.gnu.org>
+
+	PR libgfortran/51119
+	* gfortran.dg/matmul_12.f90: New test case.
+
 2016-11-15  Uros Bizjak  <ubizjak@gmail.com>
 
 	* gcc.target/i386/funcspec-56.inc: New file.

gcc/testsuite/gfortran.dg/matmul_12.f90

+! { dg-do run }
+program main
+  integer, parameter :: sz=5, su=3
+  integer, parameter :: l=2
+  integer, parameter :: u=l-1+su
+  integer(kind=4), dimension(sz,sz) :: r,a,b
+  integer :: i,j
+  do i=1,4
+     do j=1,4
+        a(i,j) = i*10+j
+        b(i,j) = 100+i*10+j
+     end do
+  end do
+  r = -1
+  b(l:u,l:u) = reshape([(i,i=1,su*su)],[su,su]);
+  a(l:u,l:u) = reshape([(i,i=1,su*su)],[su,su]);
+
+  r(1:su,1:su) = matmul(a(l:u,l:u),b(l:u,l:u))
+  if (any(reshape(r,[sz*sz]) /= [30, 36, 42, -1, -1, 66, 81, 96, -1, -1,&
+       & 102, 126, 150, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1])) &
+       call abort
+end program main

libgfortran/ChangeLog

+2016-11-15  Jerry DeLisle  <jvdelisle@gcc.gnu.org>
+	    Thomas Koenig  <tkoenig@gcc.gnu.org>
+
+	PR libgfortran/51119
+	* Makefile.am: Add new optimization flags matmul.
+	* Makefile.in: Regenerate.
+	* m4/matmul.m4: For the case of all strides = 1, implement a
+	fast blocked matrix multiply. Fix some whitespace.
+	* generated/matmul_c10.c: Regenerate.
+	* generated/matmul_c16.c: Regenerate.
+	* generated/matmul_c4.c: Regenerate.
+	* generated/matmul_c8.c: Regenerate.
+	* generated/matmul_i1.c: Regenerate.
+	* generated/matmul_i16.c: Regenerate.
+	* generated/matmul_i2.c: Regenerate.
+	* generated/matmul_i4.c: Regenerate.
+	* generated/matmul_i8.c: Regenerate.
+	* generated/matmul_r10.c: Regenerate.
+	* generated/matmul_r16.c: Regenerate.
+	* generated/matmul_r4.c: Regenerate.
+	* generated/matmul_r8.c: Regenerate.
+
 2016-11-15  Matthias Klose  <doko@ubuntu.com>
 
 	* configure: Regenerate.

libgfortran/Makefile.am

@@ -850,7 +850,7 @@ intrinsics/dprod_r8.f90 \
 intrinsics/f2c_specifics.F90
 
 # Turn on vectorization and loop unrolling for matmul.
-$(patsubst %.c,%.lo,$(notdir $(i_matmul_c))): AM_CFLAGS += -ftree-vectorize -funroll-loops
+$(patsubst %.c,%.lo,$(notdir $(i_matmul_c))): AM_CFLAGS += -ffast-math -fno-protect-parens -fstack-arrays -ftree-vectorize -funroll-loops --param max-unroll-times=4 
 # Logical matmul doesn't vectorize.
 $(patsubst %.c,%.lo,$(notdir $(i_matmull_c))): AM_CFLAGS += -funroll-loops
 

libgfortran/Makefile.in

@@ -5956,7 +5956,7 @@ uninstall-am: uninstall-cafexeclibLTLIBRARIES \
 @LIBGFOR_USE_SYMVER_SUN_TRUE@@LIBGFOR_USE_SYMVER_TRUE@	 > $@ || (rm -f $@ ; exit 1)
 
 # Turn on vectorization and loop unrolling for matmul.
-$(patsubst %.c,%.lo,$(notdir $(i_matmul_c))): AM_CFLAGS += -ftree-vectorize -funroll-loops
+$(patsubst %.c,%.lo,$(notdir $(i_matmul_c))): AM_CFLAGS += -ffast-math -fno-protect-parens -fstack-arrays -ftree-vectorize -funroll-loops --param max-unroll-times=4 
 # Logical matmul doesn't vectorize.
 $(patsubst %.c,%.lo,$(notdir $(i_matmull_c))): AM_CFLAGS += -funroll-loops