obtained gcc-4.6.4.tar.bz2 from upstream website;upstream

verified gcc-4.6.4.tar.bz2.sig;
imported gcc-4.6.4 source tree from verified upstream tarball.

downloading a git-generated archive based on the 'upstream' tag
should provide you with a source tree that is binary identical
to the one extracted from the above tarball.

if you have obtained the source via the command 'git clone',
however, do note that line-endings of files in your working
directory might differ from line-endings of the respective
files in the upstream repository.

1 files changed, 46 insertions, 0 deletions

diff --git a/gcc/testsuite/gfortran.dg/vect/fast-math-mgrid-resid.f b/gcc/testsuite/gfortran.dg/vect/fast-math-mgrid-resid.f
new file mode 100644
index 000000000..8f196a69a
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/vect/fast-math-mgrid-resid.f
@@ -0,0 +1,46 @@
+! { dg-do compile { target i?86-*-* x86_64-*-* } }
+! { dg-require-effective-target vect_double }
+! { dg-require-effective-target sse2 }
+! { dg-options "-O3 -ffast-math -msse2 -fpredictive-commoning -ftree-vectorize -fdump-tree-optimized" }
+
+
+******* RESID COMPUTES THE RESIDUAL:  R = V - AU
+*
+*      THIS SIMPLE IMPLEMENTATION COSTS  27A + 4M PER RESULT, WHERE
+*      A AND M DENOTE THE COSTS OF ADDITION (OR SUBTRACTION) AND 
+*      MULTIPLICATION, RESPECTIVELY.  BY USING SEVERAL TWO-DIMENSIONAL 
+*      BUFFERS ONE CAN REDUCE THIS COST TO  13A + 4M IN THE GENERAL 
+*      CASE, OR  10A + 3M WHEN THE COEFFICIENT A(1) IS ZERO.
+*
+      SUBROUTINE RESID(U,V,R,N,A)
+      INTEGER N
+      REAL*8 U(N,N,N),V(N,N,N),R(N,N,N),A(0:3)
+      INTEGER I3, I2, I1
+C
+      DO 600 I3=2,N-1
+      DO 600 I2=2,N-1
+      DO 600 I1=2,N-1
+ 600  R(I1,I2,I3)=V(I1,I2,I3)
+     >      -A(0)*( U(I1,  I2,  I3  ) )
+     >      -A(1)*( U(I1-1,I2,  I3  ) + U(I1+1,I2,  I3  )
+     >                 +  U(I1,  I2-1,I3  ) + U(I1,  I2+1,I3  )
+     >                 +  U(I1,  I2,  I3-1) + U(I1,  I2,  I3+1) )
+     >      -A(2)*( U(I1-1,I2-1,I3  ) + U(I1+1,I2-1,I3  )
+     >                 +  U(I1-1,I2+1,I3  ) + U(I1+1,I2+1,I3  )
+     >                 +  U(I1,  I2-1,I3-1) + U(I1,  I2+1,I3-1)
+     >                 +  U(I1,  I2-1,I3+1) + U(I1,  I2+1,I3+1)
+     >                 +  U(I1-1,I2,  I3-1) + U(I1-1,I2,  I3+1)
+     >                 +  U(I1+1,I2,  I3-1) + U(I1+1,I2,  I3+1) )
+     >      -A(3)*( U(I1-1,I2-1,I3-1) + U(I1+1,I2-1,I3-1)
+     >                 +  U(I1-1,I2+1,I3-1) + U(I1+1,I2+1,I3-1)
+     >                 +  U(I1-1,I2-1,I3+1) + U(I1+1,I2-1,I3+1)
+     >                 +  U(I1-1,I2+1,I3+1) + U(I1+1,I2+1,I3+1) )
+C
+      RETURN
+      END
+! we want to check that predictive commoning did something on the
+! vectorized loop, which means we have to have exactly 13 vector
+! additions.
+! { dg-final { scan-tree-dump-times "vect_var\[^\\n\]*\\+ " 13 "optimized" } }
+! { dg-final { cleanup-tree-dump "vect" } }
+! { dg-final { cleanup-tree-dump "optimized" } }