From: Prathamesh Kulkarni <prathameshk@nvidia.com>
Date: Tue, 16 Jul 2024 14:13:54 +0000 (+0530)
Subject: Lower zeroing array assignment to memset for allocatable arrays.
X-Git-Tag: basepoints/gcc-16~7487
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=616627245fb06106f7c5bc4a36784acc8ec166f0;p=thirdparty%2Fgcc.git

Lower zeroing array assignment to memset for allocatable arrays.

gcc/fortran/ChangeLog:
	* trans-expr.cc (gfc_trans_zero_assign): Handle allocatable arrays.

gcc/testsuite/ChangeLog:
	* gfortran.dg/array_memset_3.f90: New test.

Signed-off-by: Prathamesh Kulkarni <prathameshk@nvidia.com>
---

diff --git a/gcc/fortran/trans-expr.cc b/gcc/fortran/trans-expr.cc
index 3ff248549c6..fc23fb1a7eb 100644
--- a/gcc/fortran/trans-expr.cc
+++ b/gcc/fortran/trans-expr.cc
@@ -11499,18 +11499,24 @@ gfc_trans_zero_assign (gfc_expr * expr)
   type = TREE_TYPE (dest);
   if (POINTER_TYPE_P (type))
     type = TREE_TYPE (type);
-  if (!GFC_ARRAY_TYPE_P (type))
-    return NULL_TREE;
-
-  /* Determine the length of the array.  */
-  len = GFC_TYPE_ARRAY_SIZE (type);
-  if (!len || TREE_CODE (len) != INTEGER_CST)
+  if (GFC_ARRAY_TYPE_P (type))
+    {
+      /* Determine the length of the array.  */
+      len = GFC_TYPE_ARRAY_SIZE (type);
+      if (!len || TREE_CODE (len) != INTEGER_CST)
+	return NULL_TREE;
+    }
+  else if (GFC_DESCRIPTOR_TYPE_P (type)
+	  && gfc_is_simply_contiguous (expr, false, false))
+    {
+      if (POINTER_TYPE_P (TREE_TYPE (dest)))
+	dest = build_fold_indirect_ref_loc (input_location, dest);
+      len = gfc_conv_descriptor_size (dest, GFC_TYPE_ARRAY_RANK (type));
+      dest = gfc_conv_descriptor_data_get (dest);
+    }
+  else
     return NULL_TREE;
 
-  tmp = TYPE_SIZE_UNIT (gfc_get_element_type (type));
-  len = fold_build2_loc (input_location, MULT_EXPR, gfc_array_index_type, len,
-			 fold_convert (gfc_array_index_type, tmp));
-
   /* If we are zeroing a local array avoid taking its address by emitting
      a = {} instead.  */
   if (!POINTER_TYPE_P (TREE_TYPE (dest)))
@@ -11518,6 +11524,11 @@ gfc_trans_zero_assign (gfc_expr * expr)
 		       dest, build_constructor (TREE_TYPE (dest),
 					      NULL));
 
+  /* Multiply len by element size.  */
+  tmp = TYPE_SIZE_UNIT (gfc_get_element_type (type));
+  len = fold_build2_loc (input_location, MULT_EXPR, gfc_array_index_type,
+			 len, fold_convert (gfc_array_index_type, tmp));
+
   /* Convert arguments to the correct types.  */
   dest = fold_convert (pvoid_type_node, dest);
   len = fold_convert (size_type_node, len);
diff --git a/gcc/testsuite/gfortran.dg/array_memset_3.f90 b/gcc/testsuite/gfortran.dg/array_memset_3.f90
new file mode 100644
index 00000000000..f3945aacbbd
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/array_memset_3.f90
@@ -0,0 +1,52 @@
+! { dg-do compile }
+! { dg-options "-O2 -fdump-tree-original" }
+
+subroutine test1(n)
+  implicit none
+    integer(8) :: n
+    real(4), allocatable :: z(:,:,:)
+
+    allocate(z(n, 100, 200))
+    z = 0
+end subroutine
+
+subroutine test2(n)
+  implicit none
+    integer(8) :: n
+    integer, allocatable :: z(:,:,:)
+
+    allocate(z(n, 100, 200))
+    z = 0
+end subroutine
+
+subroutine test3(n)
+  implicit none
+    integer(8) :: n
+    logical, allocatable :: z(:,:,:)
+
+    allocate(z(n, 100, 200))
+    z = .false. 
+end subroutine
+
+subroutine test4(n, z)
+   implicit none
+   integer :: n
+   real, pointer :: z(:,:,:)     ! need not be contiguous!
+   z = 0
+end subroutine
+
+subroutine test5(n, z)
+   implicit none
+   integer :: n
+   real, contiguous, pointer :: z(:,:,:)
+   z = 0
+end subroutine
+
+subroutine test6 (n, z)
+   implicit none
+   integer :: n
+   real, contiguous, pointer :: z(:,:,:)
+   z(:,::1,:) = 0
+end subroutine
+
+! { dg-final { scan-tree-dump-times "__builtin_memset" 5 "original" } }