PR target/106231: Optimize (any_extend:DI (ctz:SI ...)) on x86_64.

This patch resolves PR target/106231 by providing insns that recognize
(zero_extend:DI (ctz:SI ...)) and (sign_extend:DI (ctz:SI ...)).  The
result of ctz:SI is always between 0 and 32 (or undefined), so
sign_extension is the same as zero_extension, and the result is already
extended in the destination register.

Things are a little complicated, because the existing implementation
of *ctzsi2 handles multiple cases, including false dependencies, which
we continue to support in this patch.

2022-07-18  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	PR target/106231
	* config/i386/i386.md (*ctzsidi2_<s>ext): New insn_and_split
	to recognize any_extend:DI of ctz:SI which is implicitly extended.
	(*ctzsidi2_<s>ext_falsedep): New define_insn to model a DImode
	extended ctz:SI that has preceding xor to break false dependency.

gcc/testsuite/ChangeLog
	PR target/106231
	* gcc.target/i386/pr106231-1.c: New test case.
	* gcc.target/i386/pr106231-2.c: New test case.

1 files changed, 60 insertions, 0 deletions

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 31637bd..9aaeb69 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -16431,6 +16431,66 @@
    (set_attr "prefix_rep" "1")
    (set_attr "mode" "SI")])
 
+(define_insn_and_split "*ctzsidi2_<s>ext"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+	(any_extend:DI
+	  (ctz:SI
+	    (match_operand:SI 1 "nonimmediate_operand" "rm"))))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_64BIT"
+{
+  if (TARGET_BMI)
+    return "tzcnt{l}\t{%1, %k0|%k0, %1}";
+  else if (TARGET_CPU_P (GENERIC)
+	   && !optimize_function_for_size_p (cfun))
+    /* tzcnt expands to 'rep bsf' and we can use it even if !TARGET_BMI.  */
+    return "rep%; bsf{l}\t{%1, %k0|%k0, %1}";
+  return "bsf{l}\t{%1, %k0|%k0, %1}";
+}
+  "(TARGET_BMI || TARGET_CPU_P (GENERIC))
+   && TARGET_AVOID_FALSE_DEP_FOR_BMI && epilogue_completed
+   && optimize_function_for_speed_p (cfun)
+   && !reg_mentioned_p (operands[0], operands[1])"
+  [(parallel
+    [(set (match_dup 0)
+	  (any_extend:DI (ctz:SI (match_dup 1))))
+     (unspec [(match_dup 0)] UNSPEC_INSN_FALSE_DEP)
+     (clobber (reg:CC FLAGS_REG))])]
+  "ix86_expand_clear (operands[0]);"
+  [(set_attr "type" "alu1")
+   (set_attr "prefix_0f" "1")
+   (set (attr "prefix_rep")
+     (if_then_else
+       (ior (match_test "TARGET_BMI")
+	    (and (not (match_test "optimize_function_for_size_p (cfun)"))
+		 (match_test "TARGET_CPU_P (GENERIC)")))
+       (const_string "1")
+       (const_string "0")))
+   (set_attr "mode" "SI")])
+
+(define_insn "*ctzsidi2_<s>ext_falsedep"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+	(any_extend:DI
+	  (ctz:SI
+	    (match_operand:SI 1 "nonimmediate_operand" "rm"))))
+   (unspec [(match_operand:DI 2 "register_operand" "0")]
+	   UNSPEC_INSN_FALSE_DEP)
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_64BIT"
+{
+  if (TARGET_BMI)
+    return "tzcnt{l}\t{%1, %k0|%k0, %1}";
+  else if (TARGET_CPU_P (GENERIC))
+    /* tzcnt expands to 'rep bsf' and we can use it even if !TARGET_BMI.  */
+    return "rep%; bsf{l}\t{%1, %k0|%k0, %1}";
+  else
+    gcc_unreachable ();
+}
+  [(set_attr "type" "alu1")
+   (set_attr "prefix_0f" "1")
+   (set_attr "prefix_rep" "1")
+   (set_attr "mode" "SI")])
+
 (define_insn "bsr_rex64"
   [(set (reg:CCZ FLAGS_REG)
 	(compare:CCZ (match_operand:DI 1 "nonimmediate_operand" "rm")