[09/16,APX,NDD] Support APX NDD for not insn

Message ID 20231115094705.3976553-10-hongyu.wang@intel.com
State Unresolved
Headers
Series Support Intel APX NDD |

Checks

Context Check Description
snail/gcc-patch-check warning Git am fail log

Commit Message

Hongyu Wang Nov. 15, 2023, 9:46 a.m. UTC
  From: Kong Lingling <lingling.kong@intel.com>

gcc/ChangeLog:

	* config/i386/i386-expand.cc (ix86_can_use_ndd_p): Add NOT
	support.
	* config/i386/i386.md (one_cmpl<mode>2): Add NDD constraints, adjust
	output template.
	(*one_cmpl<mode>2_1): Likewise.
	(*one_cmplqi2_1): Likewise.
	(*one_cmpl<dwi>2_doubleword): Likewise.
	(*one_cmplsi2_1_zext): Likewise.
	(*one_cmpl<mode>2_2): Likewise.
	(*one_cmplsi2_2_zext): Likewise.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/apx-ndd.c: Add not test.
---
 gcc/config/i386/i386-expand.cc          |  1 +
 gcc/config/i386/i386.md                 | 73 +++++++++++++++----------
 gcc/testsuite/gcc.target/i386/apx-ndd.c | 11 ++++
 3 files changed, 55 insertions(+), 30 deletions(-)
  

Patch

diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index 995cc792c5f..be77ba4a476 100644
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -1272,6 +1272,7 @@  bool ix86_can_use_ndd_p (enum rtx_code code)
     case PLUS:
     case MINUS:
     case NEG:
+    case NOT:
       return true;
     default:
       return false;
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 8ba524e9e44..9758e4e5144 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -13673,64 +13673,73 @@  (define_expand "one_cmpl<mode>2"
   [(set (match_operand:SDWIM 0 "nonimmediate_operand")
 	(not:SDWIM (match_operand:SDWIM 1 "nonimmediate_operand")))]
   ""
-  "ix86_expand_unary_operator (NOT, <MODE>mode, operands); DONE;")
+  "ix86_expand_unary_operator (NOT, <MODE>mode, operands,
+			       ix86_can_use_ndd_p (NOT)); DONE;")
 
 (define_insn_and_split "*one_cmpl<dwi>2_doubleword"
-  [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro")
-	(not:<DWI> (match_operand:<DWI> 1 "nonimmediate_operand" "0")))]
-  "ix86_unary_operator_ok (NOT, <DWI>mode, operands)"
+  [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
+	(not:<DWI> (match_operand:<DWI> 1 "nonimmediate_operand" "0,ro")))]
+  "ix86_unary_operator_ok (NOT, <DWI>mode, operands,
+			   ix86_can_use_ndd_p (NOT))"
   "#"
   "&& reload_completed"
   [(set (match_dup 0)
 	(not:DWIH (match_dup 1)))
    (set (match_dup 2)
 	(not:DWIH (match_dup 3)))]
-  "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[2]);")
+  "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[2]);"
+  [(set_attr "isa" "*,apx_ndd")])
 
 (define_insn "*one_cmpl<mode>2_1"
-  [(set (match_operand:SWI248 0 "nonimmediate_operand" "=rm,?k")
-	(not:SWI248 (match_operand:SWI248 1 "nonimmediate_operand" "0,k")))]
-  "ix86_unary_operator_ok (NOT, <MODE>mode, operands)"
+  [(set (match_operand:SWI248 0 "nonimmediate_operand" "=rm,r,?k")
+	(not:SWI248 (match_operand:SWI248 1 "nonimmediate_operand" "0,rm,k")))]
+  "ix86_unary_operator_ok (NOT, <MODE>mode, operands,
+			   ix86_can_use_ndd_p (NOT))"
   "@
    not{<imodesuffix>}\t%0
+   not{<imodesuffix>}\t{%1, %0|%0, %1}
    #"
-  [(set_attr "isa" "*,<kmov_isa>")
-   (set_attr "type" "negnot,msklog")
+  [(set_attr "isa" "*,apx_ndd,<kmov_isa>")
+   (set_attr "type" "negnot,negnot,msklog")
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*one_cmplsi2_1_zext"
-  [(set (match_operand:DI 0 "register_operand" "=r,?k")
+  [(set (match_operand:DI 0 "register_operand" "=r,r,?k")
 	(zero_extend:DI
-	  (not:SI (match_operand:SI 1 "register_operand" "0,k"))))]
-  "TARGET_64BIT && ix86_unary_operator_ok (NOT, SImode, operands)"
+	  (not:SI (match_operand:SI 1 "register_operand" "0,r,k"))))]
+  "TARGET_64BIT && ix86_unary_operator_ok (NOT, SImode, operands,
+					   ix86_can_use_ndd_p (NOT))"
   "@
    not{l}\t%k0
+   not{l}\t{%k1, %k0|%k0, %k1}
    #"
-  [(set_attr "isa" "x64,avx512bw_512")
-   (set_attr "type" "negnot,msklog")
-   (set_attr "mode" "SI,SI")])
+  [(set_attr "isa" "x64,apx_ndd,avx512bw_512")
+   (set_attr "type" "negnot,negnot,msklog")
+   (set_attr "mode" "SI,SI,SI")])
 
 (define_insn "*one_cmplqi2_1"
-  [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,r,?k")
-	(not:QI (match_operand:QI 1 "nonimmediate_operand" "0,0,k")))]
-  "ix86_unary_operator_ok (NOT, QImode, operands)"
+  [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,r,r,?k")
+	(not:QI (match_operand:QI 1 "nonimmediate_operand" "0,0,rm,k")))]
+  "ix86_unary_operator_ok (NOT, QImode, operands,
+			   ix86_can_use_ndd_p (NOT))"
   "@
    not{b}\t%0
    not{l}\t%k0
+   not{l}\t{%k1, %k0|%k0, %k1}
    #"
-  [(set_attr "isa" "*,*,avx512f")
-   (set_attr "type" "negnot,negnot,msklog")
+  [(set_attr "isa" "*,*,apx_ndd,avx512f")
+   (set_attr "type" "negnot,negnot,negnot,msklog")
    (set (attr "mode")
-	(cond [(eq_attr "alternative" "1")
+	(cond [(eq_attr "alternative" "1,2")
 		 (const_string "SI")
-		(and (eq_attr "alternative" "2")
+		(and (eq_attr "alternative" "3")
 		     (match_test "!TARGET_AVX512DQ"))
 		 (const_string "HI")
 	       ]
 	       (const_string "QI")))
    ;; Potential partial reg stall on alternative 1.
    (set (attr "preferred_for_speed")
-     (cond [(eq_attr "alternative" "1")
+     (cond [(eq_attr "alternative" "1,2")
 	      (symbol_ref "!TARGET_PARTIAL_REG_STALL")]
 	   (symbol_ref "true")))])
 
@@ -13753,14 +13762,16 @@  (define_insn_and_split "*one_cmpl<mode>_1_slp"
 
 (define_insn "*one_cmpl<mode>2_2"
   [(set (reg FLAGS_REG)
-	(compare (not:SWI (match_operand:SWI 1 "nonimmediate_operand" "0"))
+	(compare (not:SWI (match_operand:SWI 1 "nonimmediate_operand" "0,rm"))
 		 (const_int 0)))
-   (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m")
+   (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,r")
 	(not:SWI (match_dup 1)))]
   "ix86_match_ccmode (insn, CCNOmode)
-   && ix86_unary_operator_ok (NOT, <MODE>mode, operands)"
+   && ix86_unary_operator_ok (NOT, <MODE>mode, operands,
+			      ix86_can_use_ndd_p (NOT))"
   "#"
   [(set_attr "type" "alu1")
+   (set_attr "isa" "*,apx_ndd")
    (set_attr "mode" "<MODE>")])
 
 (define_split
@@ -13779,14 +13790,16 @@  (define_split
 
 (define_insn "*one_cmplsi2_2_zext"
   [(set (reg FLAGS_REG)
-	(compare (not:SI (match_operand:SI 1 "register_operand" "0"))
+	(compare (not:SI (match_operand:SI 1 "register_operand" "0,r"))
 		 (const_int 0)))
-   (set (match_operand:DI 0 "register_operand" "=r")
+   (set (match_operand:DI 0 "register_operand" "=r,r")
 	(zero_extend:DI (not:SI (match_dup 1))))]
   "TARGET_64BIT && ix86_match_ccmode (insn, CCNOmode)
-   && ix86_unary_operator_ok (NOT, SImode, operands)"
+   && ix86_unary_operator_ok (NOT, SImode, operands,
+			      ix86_can_use_ndd_p (NOT))"
   "#"
   [(set_attr "type" "alu1")
+   (set_attr "isa" "*,apx_ndd")
    (set_attr "mode" "SI")])
 
 (define_split
diff --git a/gcc/testsuite/gcc.target/i386/apx-ndd.c b/gcc/testsuite/gcc.target/i386/apx-ndd.c
index 18b423258ea..9af72d1a46d 100644
--- a/gcc/testsuite/gcc.target/i386/apx-ndd.c
+++ b/gcc/testsuite/gcc.target/i386/apx-ndd.c
@@ -76,6 +76,15 @@  F (int, neg, -)
 F1 (int, neg, -)
 F (long, neg, -)
 F1 (long, neg, -)
+
+F (char, not, ~)
+F1 (char, not, ~)
+F (short, not, ~)
+F1 (short, not, ~)
+F (int, not, ~)
+F1 (int, not, ~)
+F (long, not, ~)
+F1 (long, not, ~)
 /* { dg-final { scan-assembler-times "add(?:l|w|q)\[^\n\r]*1, \\(%rdi\\), %(?:|r|e)ax" 4 } } */
 /* { dg-final { scan-assembler-times "lea(?:l|q)\[^\n\r]\\(%r(?:d|s)i,%r(?:d|s)i\\), %(?:|r|e)ax" 4 } } */
 /* { dg-final { scan-assembler-times "add(?:l|w|q)\[^\n\r]%(?:|r|e)si, \\(%rdi\\), %(?:|r|e)ax" 4 } } */
@@ -84,3 +93,5 @@  F1 (long, neg, -)
 /* { dg-final { scan-assembler-times "negb\[^\n\r]\\(%rdi\\), %(?:|r|e)al" 1 } } */
 /* { dg-final { scan-assembler-times "neg(?:l|w|q)\[^\n\r]\\(%rdi\\), %(?:|r|e)ax" 3 } } */
 /* { dg-final { scan-assembler-times "neg(?:l|w|q)\[^\n\r]%(?:|r|e)di, %(?:|r|e)ax" 4 } } */
+/* { dg-final { scan-assembler-times "not(?:l|w|q)\[^\n\r]\\(%rdi\\), %(?:|r|e)ax" 4 } } */
+/* { dg-final { scan-assembler-times "not(?:l|w|q)\[^\n\r]%(?:|r|e)di, %(?:|r|e)ax" 4 } } */