re PR tree-optimization/81303 (410.bwaves regression caused by r249919)

2017-12-08  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/81303
	* gfortran.dg/pr81303.f: New testcase.
	* gfortran.dg/vect/pr81303.f: Likewise.

From-SVN: r255499

3 files changed, 100 insertions, 0 deletions

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 258c6d03..3b1a7e2 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2017-12-08  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/81303
+	* gfortran.dg/pr81303.f: New testcase.
+	* gfortran.dg/vect/pr81303.f: Likewise.
+
 2017-12-08  Julia Koval  <julia.koval@intel.com>
 
 	* gcc.target/i386/avx512f-vnni-1.c: Add checks for vdpdwssds.
diff --git a/gcc/testsuite/gfortran.dg/pr81303.f b/gcc/testsuite/gfortran.dg/pr81303.f
new file mode 100644
index 0000000..f83a859
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/pr81303.f
@@ -0,0 +1,44 @@
+! { dg-do compile }
+! { dg-options "-O3 -ffast-math -floop-interchange -fdump-tree-linterchange-details" }
+
+        subroutine mat_times_vec(y,x,a,axp,ayp,azp,axm,aym,azm,
+     $  nb,nx,ny,nz)
+        implicit none
+        integer nb,nx,ny,nz,i,j,k,m,l,kit,im1,ip1,jm1,jp1,km1,kp1
+
+        real*8 y(nb,nx,ny,nz),x(nb,nx,ny,nz)
+
+        real*8 a(nb,nb,nx,ny,nz),
+     1  axp(nb,nb,nx,ny,nz),ayp(nb,nb,nx,ny,nz),azp(nb,nb,nx,ny,nz),
+     2  axm(nb,nb,nx,ny,nz),aym(nb,nb,nx,ny,nz),azm(nb,nb,nx,ny,nz)
+
+
+      do k=1,nz
+         km1=mod(k+nz-2,nz)+1
+         kp1=mod(k,nz)+1
+         do j=1,ny
+            jm1=mod(j+ny-2,ny)+1
+            jp1=mod(j,ny)+1
+            do i=1,nx
+               im1=mod(i+nx-2,nx)+1
+               ip1=mod(i,nx)+1
+               do l=1,nb
+                  y(l,i,j,k)=0.0d0
+                  do m=1,nb
+                     y(l,i,j,k)=y(l,i,j,k)+
+     1               a(l,m,i,j,k)*x(m,i,j,k)+
+     2               axp(l,m,i,j,k)*x(m,ip1,j,k)+
+     3               ayp(l,m,i,j,k)*x(m,i,jp1,k)+
+     4               azp(l,m,i,j,k)*x(m,i,j,kp1)+
+     5               axm(l,m,i,j,k)*x(m,im1,j,k)+
+     6               aym(l,m,i,j,k)*x(m,i,jm1,k)+
+     7               azm(l,m,i,j,k)*x(m,i,j,km1)
+                  enddo
+               enddo
+            enddo
+         enddo
+        enddo          
+        return
+        end
+
+! { dg-final { scan-tree-dump-times "is interchanged" 1 "linterchange" } }
diff --git a/gcc/testsuite/gfortran.dg/vect/pr81303.f b/gcc/testsuite/gfortran.dg/vect/pr81303.f
new file mode 100644
index 0000000..16deb7d
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/vect/pr81303.f
@@ -0,0 +1,50 @@
+! { dg-do compile }
+! { dg-require-effective-target vect_cond_mixed }
+! { dg-require-effective-target vect_double }
+! { dg-additional-options "-O3 -ffast-math -floop-interchange -fdump-tree-linterchange-details" }
+! vect_cond_mixed lies on x86, we cannot do vcond[_eq]v2div2df
+! { dg-additional-options "-msse4.1" { target { x86_64-*-* i?86-*-* } } }
+
+        subroutine mat_times_vec(y,x,a,axp,ayp,azp,axm,aym,azm,
+     $  nb,nx,ny,nz)
+        implicit none
+        integer nb,nx,ny,nz,i,j,k,m,l,kit,im1,ip1,jm1,jp1,km1,kp1
+
+        real*8 y(nb,nx,ny,nz),x(nb,nx,ny,nz)
+
+        real*8 a(nb,nb,nx,ny,nz),
+     1  axp(nb,nb,nx,ny,nz),ayp(nb,nb,nx,ny,nz),azp(nb,nb,nx,ny,nz),
+     2  axm(nb,nb,nx,ny,nz),aym(nb,nb,nx,ny,nz),azm(nb,nb,nx,ny,nz)
+
+
+      do k=1,nz
+         km1=mod(k+nz-2,nz)+1
+         kp1=mod(k,nz)+1
+         do j=1,ny
+            jm1=mod(j+ny-2,ny)+1
+            jp1=mod(j,ny)+1
+            do i=1,nx
+               im1=mod(i+nx-2,nx)+1
+               ip1=mod(i,nx)+1
+               do l=1,nb
+                  y(l,i,j,k)=0.0d0
+                  do m=1,nb
+                     y(l,i,j,k)=y(l,i,j,k)+
+     1               a(l,m,i,j,k)*x(m,i,j,k)+
+     2               axp(l,m,i,j,k)*x(m,ip1,j,k)+
+     3               ayp(l,m,i,j,k)*x(m,i,jp1,k)+
+     4               azp(l,m,i,j,k)*x(m,i,j,kp1)+
+     5               axm(l,m,i,j,k)*x(m,im1,j,k)+
+     6               aym(l,m,i,j,k)*x(m,i,jm1,k)+
+     7               azm(l,m,i,j,k)*x(m,i,j,km1)
+                  enddo
+               enddo
+            enddo
+         enddo
+        enddo          
+        return
+        end
+
+! verify we can vectorize the inner loop after interchange
+! { dg-final { scan-tree-dump-times "is interchanged" 1 "linterchange" } }
+! { dg-final { scan-tree-dump "vectorized 1 loops in function" "vect" } }