i386: eliminate redundant operands of VPTERNLOG

As mentioned in PR 110202, GCC may be presented with input where control
word of the VPTERNLOG intrinsic implies that some of its operands do not
affect the result.  In that case, we can eliminate redundant operands
of the instruction by substituting any other operand in their place.
This removes false dependencies.

For instance, instead of (252 = 0xfc = _MM_TERNLOG_A | _MM_TERNLOG_B)

	vpternlogq	$252, %zmm2, %zmm1, %zmm0

emit

	vpternlogq	$252, %zmm0, %zmm1, %zmm0

When VPTERNLOG is invariant w.r.t first and second operands, and the
third operand is memory, load memory into the output operand first, i.e.
instead of (85 = 0x55 = ~_MM_TERNLOG_C)

	vpternlogq	$85, (%rdi), %zmm1, %zmm0

emit

	vmovdqa64	(%rdi), %zmm0
	vpternlogq	$85, %zmm0, %zmm0, %zmm0

gcc/ChangeLog:

	PR target/110202
	* config/i386/i386-protos.h
	(vpternlog_redundant_operand_mask): Declare.
	(substitute_vpternlog_operands): Declare.
	* config/i386/i386.cc
	(vpternlog_redundant_operand_mask): New helper.
	(substitute_vpternlog_operands): New function.  Use them...
	* config/i386/sse.md: ... here in new VPTERNLOG define_splits.

gcc/testsuite/ChangeLog:

	PR target/110202
	* gcc.target/i386/invariant-ternlog-1.c: New test.
	* gcc.target/i386/invariant-ternlog-2.c: New test.

gcc/config/i386/i386-protos.h

@@ -70,6 +70,9 @@ extern machine_mode ix86_cc_mode (enum rtx_code, rtx, rtx);
 extern int avx_vpermilp_parallel (rtx par, machine_mode mode);
 extern int avx_vperm2f128_parallel (rtx par, machine_mode mode);
 
+extern int vpternlog_redundant_operand_mask (rtx[]);
+extern void substitute_vpternlog_operands (rtx[]);
+
 extern bool ix86_expand_strlen (rtx, rtx, rtx, rtx);
 extern bool ix86_expand_set_or_cpymem (rtx, rtx, rtx, rtx, rtx, rtx,
 				       rtx, rtx, rtx, rtx, bool);

gcc/config/i386/i386.cc

@@ -19451,6 +19451,49 @@ avx_vperm2f128_parallel (rtx par, machine_mode mode)
   return mask + 1;
 }
 
+/* Return a mask of VPTERNLOG operands that do not affect output.  */
+
+int
+vpternlog_redundant_operand_mask (rtx *operands)
+{
+  int mask = 0;
+  int imm8 = XINT (operands[4], 0);
+
+  if (((imm8 >> 4) & 0x0F) == (imm8 & 0x0F))
+    mask |= 1;
+  if (((imm8 >> 2) & 0x33) == (imm8 & 0x33))
+    mask |= 2;
+  if (((imm8 >> 1) & 0x55) == (imm8 & 0x55))
+    mask |= 4;
+
+  return mask;
+}
+
+/* Eliminate false dependencies on operands that do not affect output
+   by substituting other operands of a VPTERNLOG.  */
+
+void
+substitute_vpternlog_operands (rtx *operands)
+{
+  int mask = vpternlog_redundant_operand_mask (operands);
+
+  if (mask & 1) /* The first operand is redundant.  */
+    operands[1] = operands[2];
+
+  if (mask & 2) /* The second operand is redundant.  */
+    operands[2] = operands[1];
+
+  if (mask & 4) /* The third operand is redundant.  */
+    operands[3] = operands[1];
+  else if (REG_P (operands[3]))
+    {
+      if (mask & 1)
+	operands[1] = operands[3];
+      if (mask & 2)
+	operands[2] = operands[3];
+    }
+}
+
 /* Return a register priority for hard reg REGNO.  */
 static int
 ix86_register_priority (int hard_regno)

gcc/config/i386/sse.md

@@ -12695,6 +12695,48 @@
 		      (symbol_ref "<MODE_SIZE> == 64 || TARGET_AVX512VL")
 		      (const_string "*")))])
 
+;; When VPTERNLOG happens to be invariant w.r.t first and second operands,
+;; and the third operand is memory, eliminate false dependencies by loading
+;; memory into the output operand first.
+(define_split
+  [(set (match_operand:V 0 "register_operand")
+	(unspec:V
+	  [(match_operand:V 1 "register_operand")
+	   (match_operand:V 2 "register_operand")
+	   (match_operand:V 3 "memory_operand")
+	   (match_operand:SI 4 "const_0_to_255_operand")]
+	  UNSPEC_VTERNLOG))]
+  "!reload_completed && vpternlog_redundant_operand_mask (operands) == 3"
+  [(set (match_dup 0)
+	(match_dup 3))
+   (set (match_dup 0)
+	(unspec:V
+	  [(match_dup 0)
+	   (match_dup 0)
+	   (match_dup 0)
+	   (match_dup 4)]
+	  UNSPEC_VTERNLOG))])
+
+;; Eliminate false dependencies when VPTERNLOG is invariant w.r.t any
+;; of input operands (except the case handled in the above split).
+(define_split
+  [(set (match_operand:V 0 "register_operand")
+	(unspec:V
+	  [(match_operand:V 1 "register_operand")
+	   (match_operand:V 2 "register_operand")
+	   (match_operand:V 3 "nonimmediate_operand")
+	   (match_operand:SI 4 "const_0_to_255_operand")]
+	  UNSPEC_VTERNLOG))]
+  "!reload_completed && vpternlog_redundant_operand_mask (operands) != 0"
+  [(set (match_dup 0)
+	(unspec:V
+	  [(match_dup 1)
+	   (match_dup 2)
+	   (match_dup 3)
+	   (match_dup 4)]
+	  UNSPEC_VTERNLOG))]
+  "substitute_vpternlog_operands (operands);")
+
 ;; There must be lots of other combinations like
 ;;
 ;; (any_logic:V

gcc/testsuite/gcc.target/i386/invariant-ternlog-1.c

@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512f -O2" } */
+/* { dg-final { scan-assembler-times "vmovdqa" 4 } } */
+/* { dg-final { scan-assembler-times {vpternlog[^\n\r]*\(%rdx\)} 2 } } */
+
+#include <immintrin.h>
+
+__m512i f(__m512i* a, __m512i* b, __m512i* c)
+{
+	return _mm512_ternarylogic_epi64 (a[0], b[0], c[0], ~_MM_TERNLOG_B | ~_MM_TERNLOG_C);
+}
+
+__m512i g(__m512i* a, __m512i* b, __m512i* c)
+{
+	return _mm512_ternarylogic_epi64 (a[0], b[0], c[0], ~_MM_TERNLOG_A | ~_MM_TERNLOG_C);
+}
+
+__m512i h(__m512i* a, __m512i* b, __m512i* c)
+{
+	return _mm512_ternarylogic_epi64 (a[0], b[0], c[0], ~_MM_TERNLOG_A | ~_MM_TERNLOG_B);
+}

gcc/testsuite/gcc.target/i386/invariant-ternlog-2.c

@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512f -O2" } */
+/* { dg-final { scan-assembler-times "vmovdqa" 1 } } */
+/* { dg-final { scan-assembler "vpternlog.*zmm0.*zmm0.*zmm0" } } */
+
+#include <immintrin.h>
+
+__m512i f(__m512i* a, __m512i* b, __m512i* c)
+{
+	return _mm512_ternarylogic_epi64 (a[0], b[0], c[0], ~_MM_TERNLOG_C);
+}
+