slp: Fix handling of IFN_CLZ/CTZ [PR112536]
Checks
Commit Message
Hi!
We ICE on the following testcase now that IFN_C[LT]Z calls can have one or
two arguments (where 2 mean it is well defined at zero).
The following patch makes us create child node only for the first argument
and compatible_calls_p ensures the other argument is the same, which
at least according to the testcase seems sufficient because of vect
patterns.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
2023-11-16 Jakub Jelinek <jakub@redhat.com>
PR tree-optimization/112536
* tree-vect-slp.cc (arg0_map): New variable.
(vect_get_operand_map): For IFN_CLZ or IFN_CTZ, return arg0_map.
* gcc.dg/pr112536.c: New test.
Jakub
@@ -505,6 +505,7 @@ static const int cond_expr_maps[3][5] =
{ 4, -2, -1, 1, 2 },
{ 4, -1, -2, 2, 1 }
};
+static const int arg0_map[] = { 1, 0 };
static const int arg1_map[] = { 1, 1 };
static const int arg2_map[] = { 1, 2 };
static const int arg1_arg4_map[] = { 2, 1, 4 };
@@ -580,6 +581,10 @@ vect_get_operand_map (const gimple *stmt
return nullptr;
}
+ case IFN_CLZ:
+ case IFN_CTZ:
+ return arg0_map;
+
default:
break;
}
@@ -0,0 +1,58 @@
+/* PR tree-optimization/112536 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-ipa-icf" } */
+/* { dg-additional-options "-mlzcnt -mavx512cd -mavx512vl" { target { i?86-*-* x86_64-*-* } } } */
+/* { dg-final { scan-assembler-times "\tvplzcntd\t" 3 { target { i?86-*-* x86_64-*-* } } } } */
+
+unsigned a[12];
+
+void
+foo (void)
+{
+ int i = a[0];
+ int j = a[1];
+ int k = a[2];
+ int l = a[3];
+ int e = i ? __builtin_clz (i) : __SIZEOF_INT__ * __CHAR_BIT__;
+ int f = j ? __builtin_clz (j) : __SIZEOF_INT__ * __CHAR_BIT__;
+ int g = k ? __builtin_clz (k) : __SIZEOF_INT__ * __CHAR_BIT__;
+ int h = l ? __builtin_clz (l) : __SIZEOF_INT__ * __CHAR_BIT__;
+ a[0] = e;
+ a[1] = f;
+ a[2] = g;
+ a[3] = h;
+}
+
+void
+bar (void)
+{
+ int i = a[4];
+ int j = a[5];
+ int k = a[6];
+ int l = a[7];
+ int e = i ? __builtin_clz (i) : __SIZEOF_INT__ * __CHAR_BIT__;
+ int f = __builtin_clz (j);
+ int g = __builtin_clz (k);
+ int h = l ? __builtin_clz (l) : __SIZEOF_INT__ * __CHAR_BIT__;
+ a[4] = e;
+ a[5] = f;
+ a[6] = g;
+ a[7] = h;
+}
+
+void
+baz (void)
+{
+ int i = a[8];
+ int j = a[9];
+ int k = a[10];
+ int l = a[11];
+ int e = __builtin_clz (i);
+ int f = j ? __builtin_clz (j) : __SIZEOF_INT__ * __CHAR_BIT__;
+ int g = __builtin_clz (k);
+ int h = l ? __builtin_clz (l) : __SIZEOF_INT__ * __CHAR_BIT__;
+ a[8] = e;
+ a[9] = f;
+ a[10] = g;
+ a[11] = h;
+}