Add handling of MULT_EXPR/PLUS_EXPR for wrapping overflow in affine combination(PR83403)

Use determine_value_range to get value range info for fold convert expressions
with internal operation PLUS_EXPR/MINUS_EXPR/MULT_EXPR when not overflow on
wrapping overflow inner type.  i.e.:

(long unsigned int)((unsigned int)n * 10 + 1)
=>
(long unsigned int)n * (long unsigned int)10 + (long unsigned int)1

With this patch for affine combination, load/store motion could detect
more address refs independency and promote some memory expressions to
registers within loop.

PS: Replace the previous "(T1)(X + CST) as (T1)X - (T1)(-CST))"
to "(T1)(X + CST) as (T1)X + (T1)(CST))" for wrapping overflow.

Bootstrap and regression tested pass on Power8-LE.

gcc/ChangeLog

	2020-05-11  Xiong Hu Luo  <luoxhu@linux.ibm.com>

	PR tree-optimization/83403
	* tree-affine.c (expr_to_aff_combination): Replace SSA_NAME with
	determine_value_range, Add fold conversion of MULT_EXPR, fix the
	previous PLUS_EXPR.

gcc/testsuite/ChangeLog

	2020-05-11  Xiong Hu Luo  <luoxhu@linux.ibm.com>

	PR tree-optimization/83403
	* gcc.dg/tree-ssa/pr83403-1.c: New test.
	* gcc.dg/tree-ssa/pr83403-2.c: New test.
	* gcc.dg/tree-ssa/pr83403.h: New header.

4 files changed, 53 insertions, 0 deletions

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 791c62aeab8..aa11ca3fd99 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,10 @@
+2020-05-11  Xiong Hu Luo  <luoxhu@linux.ibm.com>
+
+	PR tree-optimization/83403
+	* gcc.dg/tree-ssa/pr83403-1.c: New test.
+	* gcc.dg/tree-ssa/pr83403-2.c: New test.
+	* gcc.dg/tree-ssa/pr83403.h: New header.
+
 2020-05-10  Harald Anlauf  <anlauf@gmx.de>
 
 	PR fortran/93499
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr83403-1.c b/gcc/testsuite/gcc.dg/tree-ssa/pr83403-1.c
new file mode 100644
index 00000000000..748375b03af
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr83403-1.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -funroll-loops -fdump-tree-lim2-details" } */
+
+#define TYPE unsigned int
+
+#include "pr83403.h"
+
+/* { dg-final { scan-tree-dump-times "Executing store motion of" 10 "lim2" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr83403-2.c b/gcc/testsuite/gcc.dg/tree-ssa/pr83403-2.c
new file mode 100644
index 00000000000..ca2e6bbd61c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr83403-2.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -funroll-loops -fdump-tree-lim2-details" } */
+
+#define TYPE int
+
+#include "pr83403.h"
+
+/* { dg-final { scan-tree-dump-times "Executing store motion of" 10 "lim2" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr83403.h b/gcc/testsuite/gcc.dg/tree-ssa/pr83403.h
new file mode 100644
index 00000000000..0da8a835b5f
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr83403.h
@@ -0,0 +1,30 @@
+__attribute__ ((noinline)) void
+calculate (const double *__restrict__ A, const double *__restrict__ B,
+	   double *__restrict__ C)
+{
+  TYPE m = 0;
+  TYPE n = 0;
+  TYPE k = 0;
+
+  A = (const double *) __builtin_assume_aligned (A, 16);
+  B = (const double *) __builtin_assume_aligned (B, 16);
+  C = (double *) __builtin_assume_aligned (C, 16);
+
+  for (n = 0; n < 9; n++)
+    {
+      for (m = 0; m < 10; m++)
+	{
+	  C[(n * 10) + m] = 0.0;
+	}
+
+      for (k = 0; k < 17; k++)
+	{
+#pragma simd
+	  for (m = 0; m < 10; m++)
+	    {
+	      C[(n * 10) + m] += A[(k * 20) + m] * B[(n * 20) + k];
+	    }
+	}
+    }
+}
+