[PATCH] i386: Fix up cond_{and,ior,xor,mul}* [PR104779]

[Jakub Jelinek <jakub@redhat.com>]

Hi!

The following testcase ICEs, because the cond_andv* expander
has vector_operand predicates in both of the commutative inputs
and calls gen_andv*_mask which calls ix86_binary_operator_ok
in its condition, but nothing calls ix86_fixup_binary_operands_no_copy
during the expansion, which means cond_* accepts even operands
like 2 MEMs which then can't be matched.

The following patch handles it like most other insns that the other
cond_* patterns use - by having a separate define_expand that calls
ix86_fixup_binary_operands_no_copy and define_ins with
ix86_binary_operator_ok.

Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?

Note, the predicates on cond_fma* and other FMA variants look all wrong to
me, usually the fma instructions require nonimmediate_operand operands,
but the cond_* patterns use vector_operand.  Besides what this patch
fixes and the unfixed fma which I don't have spare cycles for right
now I went through all the other cond_* patterns checking for predicate
mismatches or similar missing ix86_fixup_binary_operands* issues and
didn't find other problems.

2022-03-05  Jakub Jelinek  <jakub@redhat.com>

	PR target/104779
	* config/i386/sse.md (avx512dq_mul<mode>3<mask_name>): New
	define_expand pattern.  Rename define_insn to ...
	(*avx512dq_mul<mode>3<mask_name>): ... this.
	(<code><mode>3_mask): New any_logic define_expand pattern.
	(<mask_codefor><code><mode>3<mask_name>): Rename to ...
	(*<code><mode>3<mask_name>): ... this.

	* gcc.target/i386/pr104779.c: New test.

--- gcc/config/i386/sse.md.jj	2022-02-24 15:27:14.722743984 +0100
+++ gcc/config/i386/sse.md	2022-03-04 13:56:34.863572916 +0100
@@ -15210,7 +15210,15 @@ (define_expand "cond_mul<mode>"
   DONE;
 })
 
-(define_insn "avx512dq_mul<mode>3<mask_name>"
+(define_expand "avx512dq_mul<mode>3<mask_name>"
+  [(set (match_operand:VI8_AVX512VL 0 "register_operand")
+	(mult:VI8_AVX512VL
+	  (match_operand:VI8_AVX512VL 1 "bcst_vector_operand")
+	  (match_operand:VI8_AVX512VL 2 "bcst_vector_operand")))]
+  "TARGET_AVX512DQ && <mask_mode512bit_condition>"
+  "ix86_fixup_binary_operands_no_copy (MULT, <MODE>mode, operands);")
+
+(define_insn "*avx512dq_mul<mode>3<mask_name>"
   [(set (match_operand:VI8_AVX512VL 0 "register_operand" "=v")
 	(mult:VI8_AVX512VL
 	  (match_operand:VI8_AVX512VL 1 "bcst_vector_operand" "%v")
@@ -16824,7 +16832,18 @@ (define_expand "cond_<code><mode>"
   DONE;
 })
 
-(define_insn "<mask_codefor><code><mode>3<mask_name>"
+(define_expand "<code><mode>3_mask"
+  [(set (match_operand:VI48_AVX512VL 0 "register_operand")
+	(vec_merge:VI48_AVX512VL
+	  (any_logic:VI48_AVX512VL
+	    (match_operand:VI48_AVX512VL 1 "bcst_vector_operand")
+	    (match_operand:VI48_AVX512VL 2 "bcst_vector_operand"))
+	  (match_operand:VI48_AVX512VL 3 "nonimm_or_0_operand")
+	  (match_operand:<avx512fmaskmode> 4 "register_operand")))]
+  "TARGET_AVX512F"
+  "ix86_fixup_binary_operands_no_copy (<CODE>, <MODE>mode, operands);")
+
+(define_insn "*<code><mode>3<mask_name>"
   [(set (match_operand:VI48_AVX_AVX512F 0 "register_operand" "=x,x,v")
 	(any_logic:VI48_AVX_AVX512F
 	  (match_operand:VI48_AVX_AVX512F 1 "bcst_vector_operand" "%0,x,v")
--- gcc/testsuite/gcc.target/i386/pr104779.c.jj	2022-03-04 14:09:03.278961269 +0100
+++ gcc/testsuite/gcc.target/i386/pr104779.c	2022-03-04 14:08:38.063318794 +0100
@@ -0,0 +1,27 @@
+/* PR target/104779 */
+/* { dg-do compile } */
+/* { dg-options "-O1 --param sccvn-max-alias-queries-per-access=0" } */
+
+__attribute__ ((simd)) int
+foo (int x, int y, int z)
+{
+  return (x & y) * !!z;
+}
+
+__attribute__ ((simd)) int
+bar (int x, int y, int z)
+{
+  return (x | y) * !!z;
+}
+
+__attribute__ ((simd)) int
+baz (int x, int y, int z)
+{
+  return (x ^ y) * !!z;
+}
+
+__attribute__ ((simd, target ("avx512dq"))) long
+qux (long x, long y, long z)
+{
+  return (x * y) * !!z;
+}

	Jakub