[gcc r15-982] [APX NF] Support APX NF for lzcnt/tzcnt/popcnt

[Kong Lingling]

https://gcc.gnu.org/g:4371ac5292da9eadc3daccbdce2a15c029a04892

commit r15-982-g4371ac5292da9eadc3daccbdce2a15c029a04892
Author: Lingling Kong <lingling.kong@intel.com>
Date:   Mon Jun 3 14:23:57 2024 +0800

    [APX NF] Support APX NF for lzcnt/tzcnt/popcnt
    
    gcc/ChangeLog:
    
            * config/i386/i386.md (clz<mode>2_lzcnt_nf): New define_insn.
            (*clz<mode>2_lzcnt_falsedep_nf): Ditto.
            (<lt_zcnt>_<mode>_nf): Ditto.
            (*<lt_zcnt>_<mode>_falsedep_nf): Ditto.
            (<lt_zcnt>_hi<nf_name>): Ditto.
            (popcount<mode>2_nf): Ditto.
            (*popcount<mode>2_falsedep_nf): Ditto.
            (popcounthi2<nf_name>): Ditto.

Diff:
---
 gcc/config/i386/i386.md | 124 +++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 113 insertions(+), 11 deletions(-)

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 48ca19cb8df..2c95395b7be 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -20283,6 +20283,24 @@
   operands[3] = gen_reg_rtx (<MODE>mode);
 })
 
+(define_insn_and_split "clz<mode>2_lzcnt_nf"
+  [(set (match_operand:SWI48 0 "register_operand" "=r")
+	(clz:SWI48
+	  (match_operand:SWI48 1 "nonimmediate_operand" "rm")))]
+  "TARGET_APX_NF && TARGET_LZCNT"
+  "%{nf%} lzcnt{<imodesuffix>}\t{%1, %0|%0, %1}"
+  "&& 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)
+	  (clz:SWI48 (match_dup 1)))
+     (unspec [(match_dup 0)] UNSPEC_INSN_FALSE_DEP)])]
+  "ix86_expand_clear (operands[0]);"
+  [(set_attr "prefix_rep" "1")
+   (set_attr "type" "bitmanip")
+   (set_attr "mode" "<MODE>")])
+
 (define_insn_and_split "clz<mode>2_lzcnt"
   [(set (match_operand:SWI48 0 "register_operand" "=r")
 	(clz:SWI48
@@ -20306,6 +20324,18 @@
 ; False dependency happens when destination is only updated by tzcnt,
 ; lzcnt or popcnt.  There is no false dependency when destination is
 ; also used in source.
+(define_insn "*clz<mode>2_lzcnt_falsedep_nf"
+  [(set (match_operand:SWI48 0 "register_operand" "=r")
+	(clz:SWI48
+	  (match_operand:SWI48 1 "nonimmediate_operand" "rm")))
+   (unspec [(match_operand:SWI48 2 "register_operand" "0")]
+	   UNSPEC_INSN_FALSE_DEP)]
+  "TARGET_APX_NF && TARGET_LZCNT"
+  "%{nf%} lzcnt{<imodesuffix>}\t{%1, %0|%0, %1}"
+  [(set_attr "prefix_rep" "1")
+   (set_attr "type" "bitmanip")
+   (set_attr "mode" "<MODE>")])
+
 (define_insn "*clz<mode>2_lzcnt_falsedep"
   [(set (match_operand:SWI48 0 "register_operand" "=r")
 	(clz:SWI48
@@ -20412,6 +20442,25 @@
 ;; Version of lzcnt/tzcnt that is expanded from intrinsics.  This version
 ;; provides operand size as output when source operand is zero. 
 
+(define_insn_and_split "<lt_zcnt>_<mode>_nf"
+  [(set (match_operand:SWI48 0 "register_operand" "=r")
+	(unspec:SWI48
+	  [(match_operand:SWI48 1 "nonimmediate_operand" "rm")] LT_ZCNT))]
+  "TARGET_APX_NF"
+  "%{nf%} <lt_zcnt>{<imodesuffix>}\t{%1, %0|%0, %1}"
+  "&& 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)
+	  (unspec:SWI48 [(match_dup 1)] LT_ZCNT))
+     (unspec [(match_dup 0)] UNSPEC_INSN_FALSE_DEP)])]
+  "ix86_expand_clear (operands[0]);"
+  [(set_attr "type" "<lt_zcnt_type>")
+   (set_attr "prefix_0f" "1")
+   (set_attr "prefix_rep" "1")
+   (set_attr "mode" "<MODE>")])
+
 (define_insn_and_split "<lt_zcnt>_<mode>"
   [(set (match_operand:SWI48 0 "register_operand" "=r")
 	(unspec:SWI48
@@ -20436,6 +20485,19 @@
 ; False dependency happens when destination is only updated by tzcnt,
 ; lzcnt or popcnt.  There is no false dependency when destination is
 ; also used in source.
+(define_insn "*<lt_zcnt>_<mode>_falsedep_nf"
+  [(set (match_operand:SWI48 0 "register_operand" "=r")
+	(unspec:SWI48
+	  [(match_operand:SWI48 1 "nonimmediate_operand" "rm")] LT_ZCNT))
+   (unspec [(match_operand:SWI48 2 "register_operand" "0")]
+	   UNSPEC_INSN_FALSE_DEP)]
+  "TARGET_APX_NF"
+  "%{nf%} <lt_zcnt>{<imodesuffix>}\t{%1, %0|%0, %1}"
+  [(set_attr "type" "<lt_zcnt_type>")
+   (set_attr "prefix_0f" "1")
+   (set_attr "prefix_rep" "1")
+   (set_attr "mode" "<MODE>")])
+
 (define_insn "*<lt_zcnt>_<mode>_falsedep"
   [(set (match_operand:SWI48 0 "register_operand" "=r")
 	(unspec:SWI48
@@ -20450,13 +20512,12 @@
    (set_attr "prefix_rep" "1")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "<lt_zcnt>_hi"
+(define_insn "<lt_zcnt>_hi<nf_name>"
   [(set (match_operand:HI 0 "register_operand" "=r")
 	(unspec:HI
-	  [(match_operand:HI 1 "nonimmediate_operand" "rm")] LT_ZCNT))
-   (clobber (reg:CC FLAGS_REG))]
-  ""
-  "<lt_zcnt>{w}\t{%1, %0|%0, %1}"
+	  [(match_operand:HI 1 "nonimmediate_operand" "rm")] LT_ZCNT))]
+  "<nf_condition>"
+  "<nf_prefix><lt_zcnt>{w}\t{%1, %0|%0, %1}"
   [(set_attr "type" "<lt_zcnt_type>")
    (set_attr "prefix_0f" "1")
    (set_attr "prefix_rep" "1")
@@ -20874,6 +20935,30 @@
   [(set_attr "type" "bitmanip")
    (set_attr "mode" "<MODE>")])
 
+(define_insn_and_split "popcount<mode>2_nf"
+  [(set (match_operand:SWI48 0 "register_operand" "=r")
+	(popcount:SWI48
+	  (match_operand:SWI48 1 "nonimmediate_operand" "rm")))]
+  "TARGET_APX_NF && TARGET_POPCNT"
+{
+#if TARGET_MACHO
+  return "%{nf%} popcnt\t{%1, %0|%0, %1}";
+#else
+  return "%{nf%} popcnt{<imodesuffix>}\t{%1, %0|%0, %1}";
+#endif
+}
+  "&& 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)
+	  (popcount:SWI48 (match_dup 1)))
+     (unspec [(match_dup 0)] UNSPEC_INSN_FALSE_DEP)])]
+  "ix86_expand_clear (operands[0]);"
+  [(set_attr "prefix_rep" "1")
+   (set_attr "type" "bitmanip")
+   (set_attr "mode" "<MODE>")])
+
 (define_insn_and_split "popcount<mode>2"
   [(set (match_operand:SWI48 0 "register_operand" "=r")
 	(popcount:SWI48
@@ -20903,6 +20988,24 @@
 ; False dependency happens when destination is only updated by tzcnt,
 ; lzcnt or popcnt.  There is no false dependency when destination is
 ; also used in source.
+(define_insn "*popcount<mode>2_falsedep_nf"
+  [(set (match_operand:SWI48 0 "register_operand" "=r")
+	(popcount:SWI48
+	  (match_operand:SWI48 1 "nonimmediate_operand" "rm")))
+   (unspec [(match_operand:SWI48 2 "register_operand" "0")]
+	   UNSPEC_INSN_FALSE_DEP)]
+  "TARGET_APX_NF && TARGET_POPCNT"
+{
+#if TARGET_MACHO
+  return "%{nf%} popcnt\t{%1, %0|%0, %1}";
+#else
+  return "%{nf%} popcnt{<imodesuffix>}\t{%1, %0|%0, %1}";
+#endif
+}
+  [(set_attr "prefix_rep" "1")
+   (set_attr "type" "bitmanip")
+   (set_attr "mode" "<MODE>")])
+
 (define_insn "*popcount<mode>2_falsedep"
   [(set (match_operand:SWI48 0 "register_operand" "=r")
 	(popcount:SWI48
@@ -21060,17 +21163,16 @@
   DONE;
 })
 
-(define_insn "popcounthi2"
+(define_insn "popcounthi2<nf_name>"
   [(set (match_operand:HI 0 "register_operand" "=r")
 	(popcount:HI
-	  (match_operand:HI 1 "nonimmediate_operand" "rm")))
-   (clobber (reg:CC FLAGS_REG))]
-  "TARGET_POPCNT"
+	  (match_operand:HI 1 "nonimmediate_operand" "rm")))]
+  "TARGET_POPCNT && <nf_condition>"
 {
 #if TARGET_MACHO
-  return "popcnt\t{%1, %0|%0, %1}";
+  return "<nf_prefix>popcnt\t{%1, %0|%0, %1}";
 #else
-  return "popcnt{w}\t{%1, %0|%0, %1}";
+  return "<nf_prefix>popcnt{w}\t{%1, %0|%0, %1}";
 #endif
 }
   [(set_attr "prefix_rep" "1")