[gcc r14-3350] MATCH: [PR111002] Sink view_convert for vec_cond

[gcc r14-3350] MATCH: [PR111002] Sink view_convert for vec_cond

[Andrew Pinski]

https://gcc.gnu.org/g:47b833a9abe19d862a773d20dd6f961dcf811a11

commit r14-3350-g47b833a9abe19d862a773d20dd6f961dcf811a11
Author: Andrew Pinski <apinski@marvell.com>
Date:   Sun Aug 20 17:22:27 2023 -0700

    MATCH: [PR111002] Sink view_convert for vec_cond
    
    Like convert we can sink view_convert into vec_cond but
    we can only do it if the element types are nop_conversions.
    This is to allow conversion between signed and unsigned types only.
    Rather than between integer and float types which mess up the vec_cond
    so that isel does not understand `a?-1:0` is still that.
    
    OK? Bootstrapped and tested on x86_64-linux-gnu and aarch64-linux-gnu.
    
            PR tree-optimization/111002
    
    gcc/ChangeLog:
    
            * match.pd (view_convert(vec_cond(a,b,c))): New pattern.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/aarch64/sve/cond_convert_8.c: New test.

Diff:
---
 gcc/match.pd                                       |  9 +++++++++
 .../gcc.target/aarch64/sve/cond_convert_8.c        | 22 ++++++++++++++++++++++
 2 files changed, 31 insertions(+)

diff --git a/gcc/match.pd b/gcc/match.pd
index d5c731e86d04..86fdc606a797 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4712,6 +4712,15 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
       && types_match (TREE_TYPE (@0), truth_type_for (type)))
   (vec_cond @0 (convert! @1) (convert! @2))))
 
+/* Likewise for view_convert of nop_conversions. */
+(simplify
+ (view_convert (vec_cond:s @0 @1 @2))
+ (if (VECTOR_TYPE_P (type) && VECTOR_TYPE_P (TREE_TYPE (@1))
+      && known_eq (TYPE_VECTOR_SUBPARTS (type),
+		   TYPE_VECTOR_SUBPARTS (TREE_TYPE (@1)))
+      && tree_nop_conversion_p (TREE_TYPE (type), TREE_TYPE (TREE_TYPE (@1))))
+  (vec_cond @0 (view_convert! @1) (view_convert! @2))))
+
 /* Sink binary operation to branches, but only if we can fold it.  */
 (for op (tcc_comparison plus minus mult bit_and bit_ior bit_xor
 	 lshift rshift rdiv trunc_div ceil_div floor_div round_div
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_8.c b/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_8.c
new file mode 100644
index 000000000000..d8b96e5fcfbd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/cond_convert_8.c
@@ -0,0 +1,22 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -moverride=sve_width=256 -fdump-tree-optimized" } */
+/* PR tree-optimization/111002 */
+
+/* We should be able to remove the neg. */
+
+void __attribute__ ((noipa))
+f (int *__restrict r,
+   int *__restrict a,
+   short *__restrict pred)
+{
+  for (int i = 0; i < 1024; ++i)
+    r[i] = pred[i] != 0 ? -1 : 0;
+}
+
+
+/* { dg-final { scan-assembler-times {\tmov\tz[0-9]+\.h, p[0-7]+/z, #-1} 1 } } */
+/* { dg-final { scan-assembler-not {\tmov\tz[0-9]+\.[hs], p[0-7]+/z, #1} } } */
+
+/* { dg-final { scan-tree-dump-not "VIEW_CONVERT_EXPR " "optimized" } } */
+/* { dg-final { scan-tree-dump-not " = -" "optimized" } } */
+/* { dg-final { scan-tree-dump-not " = \\\(vector" "optimized" } } */