PR libfortran/97063 - Wrong result for vector (step size is negative) * matrix

The MATMUL intrinsic provided a wrong result for rank-1 times rank-2 array
when a negative stride was used for addressing the elements of the rank-1
array, because a check on strides was erroneously placed before the check
on the rank.  Interchange order of checks.

libgfortran/ChangeLog:

	* m4/matmul_internal.m4: Move check for rank-1 times rank-2 before
	checks on strides for rank-2 times rank-2.
	* generated/matmul_c10.c: Regenerated.
	* generated/matmul_c16.c: Likewise.
	* generated/matmul_c4.c: Likewise.
	* generated/matmul_c8.c: Likewise.
	* generated/matmul_i1.c: Likewise.
	* generated/matmul_i16.c: Likewise.
	* generated/matmul_i2.c: Likewise.
	* generated/matmul_i4.c: Likewise.
	* generated/matmul_i8.c: Likewise.
	* generated/matmul_r10.c: Likewise.
	* generated/matmul_r16.c: Likewise.
	* generated/matmul_r4.c: Likewise.
	* generated/matmul_r8.c: Likewise.
	* generated/matmulavx128_c10.c: Likewise.
	* generated/matmulavx128_c16.c: Likewise.
	* generated/matmulavx128_c4.c: Likewise.
	* generated/matmulavx128_c8.c: Likewise.
	* generated/matmulavx128_i1.c: Likewise.
	* generated/matmulavx128_i16.c: Likewise.
	* generated/matmulavx128_i2.c: Likewise.
	* generated/matmulavx128_i4.c: Likewise.
	* generated/matmulavx128_i8.c: Likewise.
	* generated/matmulavx128_r10.c: Likewise.
	* generated/matmulavx128_r16.c: Likewise.
	* generated/matmulavx128_r4.c: Likewise.
	* generated/matmulavx128_r8.c: Likewise.

gcc/testsuite/ChangeLog:

	* gfortran.dg/matmul_20.f90: New test.

1 files changed, 28 insertions, 28 deletions

diff --git a/libgfortran/generated/matmulavx128_c4.c b/libgfortran/generated/matmulavx128_c4.c
index 97b53d3..850bd2b 100644
--- a/libgfortran/generated/matmulavx128_c4.c
+++ b/libgfortran/generated/matmulavx128_c4.c
@@ -555,20 +555,6 @@ matmul_c4_avx128_fma3 (gfc_array_c4 * const restrict retarray,
 	    }
 	}
     }
-  else if (axstride < aystride)
-    {
-      for (y = 0; y < ycount; y++)
-	for (x = 0; x < xcount; x++)
-	  dest[x*rxstride + y*rystride] = (GFC_COMPLEX_4)0;
-
-      for (y = 0; y < ycount; y++)
-	for (n = 0; n < count; n++)
-	  for (x = 0; x < xcount; x++)
-	    /* dest[x,y] += a[x,n] * b[n,y] */
-	    dest[x*rxstride + y*rystride] +=
-					abase[x*axstride + n*aystride] *
-					bbase[n*bxstride + y*bystride];
-    }
   else if (GFC_DESCRIPTOR_RANK (a) == 1)
     {
       const GFC_COMPLEX_4 *restrict bbase_y;
@@ -583,6 +569,20 @@ matmul_c4_avx128_fma3 (gfc_array_c4 * const restrict retarray,
 	  dest[y*rxstride] = s;
 	}
     }
+  else if (axstride < aystride)
+    {
+      for (y = 0; y < ycount; y++)
+	for (x = 0; x < xcount; x++)
+	  dest[x*rxstride + y*rystride] = (GFC_COMPLEX_4)0;
+
+      for (y = 0; y < ycount; y++)
+	for (n = 0; n < count; n++)
+	  for (x = 0; x < xcount; x++)
+	    /* dest[x,y] += a[x,n] * b[n,y] */
+	    dest[x*rxstride + y*rystride] +=
+					abase[x*axstride + n*aystride] *
+					bbase[n*bxstride + y*bystride];
+    }
   else
     {
       const GFC_COMPLEX_4 *restrict abase_x;
@@ -1124,20 +1124,6 @@ matmul_c4_avx128_fma4 (gfc_array_c4 * const restrict retarray,
 	    }
 	}
     }
-  else if (axstride < aystride)
-    {
-      for (y = 0; y < ycount; y++)
-	for (x = 0; x < xcount; x++)
-	  dest[x*rxstride + y*rystride] = (GFC_COMPLEX_4)0;
-
-      for (y = 0; y < ycount; y++)
-	for (n = 0; n < count; n++)
-	  for (x = 0; x < xcount; x++)
-	    /* dest[x,y] += a[x,n] * b[n,y] */
-	    dest[x*rxstride + y*rystride] +=
-					abase[x*axstride + n*aystride] *
-					bbase[n*bxstride + y*bystride];
-    }
   else if (GFC_DESCRIPTOR_RANK (a) == 1)
     {
       const GFC_COMPLEX_4 *restrict bbase_y;
@@ -1152,6 +1138,20 @@ matmul_c4_avx128_fma4 (gfc_array_c4 * const restrict retarray,
 	  dest[y*rxstride] = s;
 	}
     }
+  else if (axstride < aystride)
+    {
+      for (y = 0; y < ycount; y++)
+	for (x = 0; x < xcount; x++)
+	  dest[x*rxstride + y*rystride] = (GFC_COMPLEX_4)0;
+
+      for (y = 0; y < ycount; y++)
+	for (n = 0; n < count; n++)
+	  for (x = 0; x < xcount; x++)
+	    /* dest[x,y] += a[x,n] * b[n,y] */
+	    dest[x*rxstride + y*rystride] +=
+					abase[x*axstride + n*aystride] *
+					bbase[n*bxstride + y*bystride];
+    }
   else
     {
       const GFC_COMPLEX_4 *restrict abase_x;