re PR tree-optimization/92834 (misssed SLP vectorization in LightPixel)

	PR tree-optimization/92834
	* match.pd (A - ((A - B) & -(C cmp D)) -> (C cmp D) ? B : A,
	A + ((B - A) & -(C cmp D)) -> (C cmp D) ? B : A): New simplifications.

	* gcc.dg/tree-ssa/pr92834.c: New test.

From-SVN: r279113

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index cee65513d00c75cb2276bb2e1a3030754ea3ee9b..1c953d29b86db053f14f99e8dac59fe3c324f483 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2019-12-09  Jakub Jelinek  <jakub@redhat.com>
+
+       PR tree-optimization/92834
+       * match.pd (A - ((A - B) & -(C cmp D)) -> (C cmp D) ? B : A,
+       A + ((B - A) & -(C cmp D)) -> (C cmp D) ? B : A): New simplifications.
+
 2019-12-09  Prathamesh Kulkarni  <prathamesh.kulkarni@linaro.org>
 
        PR tree-optimization/89007

diff --git a/gcc/match.pd b/gcc/match.pd
index 58c57a573e26a45e180f6349502e2ad9a498687d..dda86964b4c8e9df1bbe7831111af36f616e9791 100644 (file)
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -2697,6 +2697,31 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
   (cmp (minmax @0 INTEGER_CST@1) INTEGER_CST@2)
   (comb (cmp @0 @2) (cmp @1 @2))))
 
+/* Undo fancy way of writing max/min or other ?: expressions,
+   like a - ((a - b) & -(a < b)), in this case into (a < b) ? b : a.
+   People normally use ?: and that is what we actually try to optimize.  */
+(for cmp (simple_comparison)
+ (simplify
+  (minus @0 (bit_and:c (minus @0 @1)
+                      (convert? (negate@4 (convert? (cmp@5 @2 @3))))))
+  (if (INTEGRAL_TYPE_P (type)
+       && INTEGRAL_TYPE_P (TREE_TYPE (@4))
+       && TREE_CODE (TREE_TYPE (@4)) != BOOLEAN_TYPE
+       && INTEGRAL_TYPE_P (TREE_TYPE (@5))
+       && (TYPE_PRECISION (TREE_TYPE (@4)) >= TYPE_PRECISION (type)
+          || !TYPE_UNSIGNED (TREE_TYPE (@4))))
+   (cond (cmp @2 @3) @1 @0)))
+ (simplify
+  (plus:c @0 (bit_and:c (minus @1 @0)
+                       (convert? (negate@4 (convert? (cmp@5 @2 @3))))))
+  (if (INTEGRAL_TYPE_P (type)
+       && INTEGRAL_TYPE_P (TREE_TYPE (@4))
+       && TREE_CODE (TREE_TYPE (@4)) != BOOLEAN_TYPE
+       && INTEGRAL_TYPE_P (TREE_TYPE (@5))
+       && (TYPE_PRECISION (TREE_TYPE (@4)) >= TYPE_PRECISION (type)
+          || !TYPE_UNSIGNED (TREE_TYPE (@4))))
+   (cond (cmp @2 @3) @1 @0))))
+
 /* Simplifications of shift and rotates.  */
 
 (for rotate (lrotate rrotate)

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 0706b05b417e901007cb75a1fea3b8f8d25de202..53bbc1254242e0805530c64a2b69ea1a76a48780 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2019-12-09  Jakub Jelinek  <jakub@redhat.com>
+
+       PR tree-optimization/92834
+       * gcc.dg/tree-ssa/pr92834.c: New test.
+
 2019-12-09  Prathamesh Kulkarni  <prathamesh.kulkarni@linaro.org>
 
        PR tree-optimization/89007

diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr92834.c b/gcc/testsuite/gcc.dg/tree-ssa/pr92834.c
new file mode 100644 (file)
index 0000000..889048d
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr92834.c
@@ -0,0 +1,122 @@
+/* PR tree-optimization/92834 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+/* { dg-final { scan-tree-dump-times "MIN_EXPR <" 8 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "MAX_EXPR <" 8 "optimized" } } */
+
+static inline unsigned
+umax1 (unsigned a, unsigned b)
+{
+  return a - ((a - b) & -(a < b));
+}
+
+static inline unsigned
+umin1 (unsigned a, unsigned b)
+{
+  return a - ((a - b) & -(a > b));
+}
+
+static inline int
+smax1 (int a, int b)
+{
+  return a - ((a - b) & -(a < b));
+}
+
+static inline int
+smin1 (int a, int b)
+{
+  return a - ((a - b) & -(a > b));
+}
+
+static inline unsigned long long
+umax2 (unsigned long long a, unsigned long long b)
+{
+  return a - ((a - b) & -(a <= b));
+}
+
+static inline unsigned long long
+umin2 (unsigned long long a, unsigned long long b)
+{
+  return a - ((a - b) & -(a >= b));
+}
+
+static inline long long
+smax2 (long long a, long long b)
+{
+  return a - ((a - b) & -(a <= b));
+}
+
+static inline long long
+smin2 (long long a, long long b)
+{
+  return a - ((a - b) & -(a >= b));
+}
+
+static inline unsigned
+umax3 (unsigned a, unsigned b)
+{
+  return a + ((b - a) & -(a < b));
+}
+
+static inline unsigned
+umin3 (unsigned a, unsigned b)
+{
+  return a + ((b - a) & -(a > b));
+}
+
+static inline int
+smax3 (int a, int b)
+{
+  return a + ((b - a) & -(a < b));
+}
+
+static inline int
+smin3 (int a, int b)
+{
+  return a + ((b - a) & -(a > b));
+}
+
+static inline unsigned long long
+umax4 (unsigned long long a, unsigned long long b)
+{
+  return a + ((b - a) & -(a <= b));
+}
+
+static inline unsigned long long
+umin4 (unsigned long long a, unsigned long long b)
+{
+  return a + ((b - a) & -(a >= b));
+}
+
+static inline long long
+smax4 (long long a, long long b)
+{
+  return a + ((b - a) & -(a <= b));
+}
+
+static inline long long
+smin4 (long long a, long long b)
+{
+  return a + ((b - a) & -(a >= b));
+}
+
+void
+test (unsigned *x, int *y, unsigned long long *z, long long *w)
+{
+  x[2] = umax1 (x[0], x[1]);
+  x[5] = umin1 (x[2], x[3]);
+  y[2] = smax1 (y[0], y[1]);
+  y[5] = smin1 (y[2], y[3]);
+  z[2] = umax2 (z[0], z[1]);
+  z[5] = umin2 (z[2], z[3]);
+  w[2] = smax2 (w[0], w[1]);
+  w[5] = smin2 (w[2], w[3]);
+  x[8] = umax3 (x[6], x[7]);
+  x[11] = umin3 (x[9], x[10]);
+  y[8] = smax3 (y[6], y[7]);
+  y[11] = smin3 (y[9], y[10]);
+  z[8] = umax4 (z[6], z[7]);
+  z[11] = umin4 (z[9], z[10]);
+  w[8] = smax4 (w[6], w[7]);
+  w[11] = smin4 (w[9], w[10]);
+}