[PATCH] PR tree-optimization/94026: Simplify (X>>8)&6 != 0 as X&1536 != 0.

This patch implements the missed optimization described in PR 94026,
where a the shift can be eliminated from the sequence of a shift,
followed by a bit-wise AND followed by an equality/inequality test.
Specifically, ((X << C1) & C2) cmp C3 into (X & (C2 >> C1)) cmp (C3 >> C1)
and likewise ((X >> C1) & C2) cmp C3 into (X & (C2 << C1)) cmp (C3 << C1)
where cmp is == or !=, and C1, C2 and C3 are integer constants.
The example in the subject line is taken from the hot function
self_atari from the Go program Leela (in SPEC CPU 2017).

2022-06-27  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	PR tree-optimization/94026
	* match.pd (((X << C1) & C2) eq/ne C3): New simplification.
	(((X >> C1) & C2) eq/ne C3): Likewise.

gcc/testsuite/ChangeLog
	PR tree-optimization/94026
	* gcc.dg/pr94026.c: New test case.

diff --git a/gcc/match.pd b/gcc/match.pd
index e486b4be282cbbbe9881f130bb9ecc67cd55a4b8..24cbbbb5bc1d718bd03af7712fc7255213f2a742 100644 (file)
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3572,6 +3572,29 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
         && wi::lshift (wi::to_wide (@0), cand) == wi::to_wide (@2))
      (cmp @1 { build_int_cst (TREE_TYPE (@1), cand); }))))))
 
+/* Fold ((X << C1) & C2) cmp C3 into (X & (C2 >> C1)) cmp (C3 >> C1)
+       ((X >> C1) & C2) cmp C3 into (X & (C2 << C1)) cmp (C3 << C1).  */
+(for cmp (ne eq)
+ (simplify
+  (cmp (bit_and:s (lshift:s @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3)
+  (if (tree_fits_shwi_p (@1)
+       && tree_to_shwi (@1) > 0
+       && tree_to_shwi (@1) < TYPE_PRECISION (TREE_TYPE (@0))
+       && tree_to_shwi (@1) <= wi::ctz (wi::to_wide (@3)))
+   (with { wide_int c1 = wi::to_wide (@1);
+          wide_int c2 = wi::lrshift (wi::to_wide (@2), c1);
+          wide_int c3 = wi::lrshift (wi::to_wide (@3), c1); }
+    (cmp (bit_and @0 { wide_int_to_tree (TREE_TYPE (@0), c2); })
+        { wide_int_to_tree (TREE_TYPE (@0), c3); }))))
+ (simplify
+  (cmp (bit_and:s (rshift:s @0 INTEGER_CST@1) INTEGER_CST@2) INTEGER_CST@3)
+  (if (tree_fits_shwi_p (@1)
+       && tree_to_shwi (@1) > 0
+       && tree_to_shwi (@1) < TYPE_PRECISION (TREE_TYPE (@0))
+       && tree_to_shwi (@1) <= wi::clz (wi::to_wide (@2))
+       && tree_to_shwi (@1) <= wi::clz (wi::to_wide (@3)))
+   (cmp (bit_and @0 (lshift @2 @1)) (lshift @3 @1)))))
+
 /* Fold (X << C1) & C2 into (X << C1) & (C2 | ((1 << C1) - 1))
         (X >> C1) & C2 into (X >> C1) & (C2 | ~((type) -1 >> C1))
    if the new mask might be further optimized.  */

diff --git a/gcc/testsuite/gcc.dg/pr94026.c b/gcc/testsuite/gcc.dg/pr94026.c
new file mode 100644 (file)
index 0000000..deb4efd
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/pr94026.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+int f1(int x) { return ((x >> 8) & 6) != 0; }
+int f2(int x) { return ((x << 2) & 24) != 0; }
+int f3(unsigned x) { return ((x << 2) & 15) != 0; }
+int f4(unsigned x) { return ((x >> 2) & 14) != 0; }
+
+int fifth (int c)
+{
+    int a = (c >> 8) & 7;
+
+    if (a >= 2) {
+       return 1;
+    } else {
+       return 0;
+    }
+}
+/* { dg-final { scan-tree-dump-not " << " "optimized" } } */
+/* { dg-final { scan-tree-dump-not " >> " "optimized" } } */
+