[07/17,APX,NDD] Support APX NDD for sbb insn

Message ID 20231205022948.504790-8-hongyu.wang@intel.com
State New
Headers
Series Support Intel APX NDD |

Commit Message

Hongyu Wang Dec. 5, 2023, 2:29 a.m. UTC
  From: Kong Lingling <lingling.kong@intel.com>

Similar to *add<dwi>3_doubleword, operands[1] may not equal to operands[0] so
extra move is required.

gcc/ChangeLog:

	* config/i386/i386.md (*sub<dwi>3_doubleword): Add new alternative for
	NDD, and emit move when operands[0] not equal to operands[1].
	(*sub<dwi>3_doubleword_zext): Likewise.
	(*subv<dwi>4_doubleword): Likewise.
	(*subv<dwi>4_doubleword_1): Likewise.
	(*subv<mode>4_overflow_1): Add NDD alternatives and adjust output
	templates.
	(*subv<mode>4_overflow_2): Likewise.
	(@sub<mode>3_carry): Likewise.
	(*addsi3_carry_zext_0r): Likewise, and use nonimmediate_operand for
	operands[1] to accept memory input for NDD alternative.
	(*subsi3_carry_zext): Likewise.
	(subborrow<mode>): Parse TARGET_APX_NDD to ix86_binary_operator_ok.
	(subborrow<mode>_0): Likewise.
	(*sub<mode>3_eq): Likewise.
	(*sub<mode>3_ne): Likewise.
	(*sub<mode>3_eq_1): Likewise.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/apx-ndd-sbb.c: New test.
---
 gcc/config/i386/i386.md                     | 160 ++++++++++++--------
 gcc/testsuite/gcc.target/i386/apx-ndd-sbb.c |   6 +
 2 files changed, 107 insertions(+), 59 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/apx-ndd-sbb.c
  

Patch

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index ea5377a0b38..e2705ada31a 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -7776,12 +7776,13 @@  (define_expand "sub<mode>3"
 				TARGET_APX_NDD); DONE;")
 
 (define_insn_and_split "*sub<dwi>3_doubleword"
-  [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
+  [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,r,r")
 	(minus:<DWI>
-	  (match_operand:<DWI> 1 "nonimmediate_operand" "0,0")
-	  (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o")))
+	  (match_operand:<DWI> 1 "nonimmediate_operand" "0,0,ro,r")
+	  (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o,r<di>,o")))
    (clobber (reg:CC FLAGS_REG))]
-  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
+  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			    TARGET_APX_NDD)"
   "#"
   "&& reload_completed"
   [(parallel [(set (reg:CC FLAGS_REG)
@@ -7805,16 +7806,18 @@  (define_insn_and_split "*sub<dwi>3_doubleword"
 				   TARGET_APX_NDD);
       DONE;
     }
-})
+}
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
 
 (define_insn_and_split "*sub<dwi>3_doubleword_zext"
-  [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=r,o")
+  [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=r,o,r,r")
 	(minus:<DWI>
-	  (match_operand:<DWI> 1 "nonimmediate_operand" "0,0")
+	  (match_operand:<DWI> 1 "nonimmediate_operand" "0,0,r,o")
 	  (zero_extend:<DWI>
-	    (match_operand:DWIH 2 "nonimmediate_operand" "rm,r"))))
+	    (match_operand:DWIH 2 "nonimmediate_operand" "rm,r,rm,r"))))
    (clobber (reg:CC FLAGS_REG))]
-  "ix86_binary_operator_ok (UNKNOWN, <DWI>mode, operands)"
+  "ix86_binary_operator_ok (UNKNOWN, <DWI>mode, operands,
+			    TARGET_APX_NDD)"
   "#"
   "&& reload_completed"
   [(parallel [(set (reg:CC FLAGS_REG)
@@ -7828,7 +7831,8 @@  (define_insn_and_split "*sub<dwi>3_doubleword_zext"
 		       (ltu:DWIH (reg:CC FLAGS_REG) (const_int 0)))
 		     (const_int 0)))
 	      (clobber (reg:CC FLAGS_REG))])]
-  "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[3]);")
+  "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[3]);"
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
 
 (define_insn "*sub<mode>_1"
   [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
@@ -8162,14 +8166,15 @@  (define_insn_and_split "*subv<dwi>4_doubleword"
 	(eq:CCO
 	  (minus:<QPWI>
 	    (sign_extend:<QPWI>
-	      (match_operand:<DWI> 1 "nonimmediate_operand" "0,0"))
+	      (match_operand:<DWI> 1 "nonimmediate_operand" "0,0,ro,r"))
 	    (sign_extend:<QPWI>
-	      (match_operand:<DWI> 2 "nonimmediate_operand" "r,o")))
+	      (match_operand:<DWI> 2 "nonimmediate_operand" "r,o,r,o")))
 	  (sign_extend:<QPWI>
 	    (minus:<DWI> (match_dup 1) (match_dup 2)))))
-   (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
+   (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,r,r")
 	(minus:<DWI> (match_dup 1) (match_dup 2)))]
-  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
+  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			    TARGET_APX_NDD)"
   "#"
   "&& reload_completed"
   [(parallel [(set (reg:CC FLAGS_REG)
@@ -8197,22 +8202,24 @@  (define_insn_and_split "*subv<dwi>4_doubleword"
 		     (match_dup 5)))])]
 {
   split_double_mode (<DWI>mode, &operands[0], 3, &operands[0], &operands[3]);
-})
+}
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
 
 (define_insn_and_split "*subv<dwi>4_doubleword_1"
   [(set (reg:CCO FLAGS_REG)
 	(eq:CCO
 	  (minus:<QPWI>
 	    (sign_extend:<QPWI>
-	      (match_operand:<DWI> 1 "nonimmediate_operand" "0"))
+	      (match_operand:<DWI> 1 "nonimmediate_operand" "0,ro"))
 	    (match_operand:<QPWI> 3 "const_scalar_int_operand"))
 	  (sign_extend:<QPWI>
 	    (minus:<DWI>
 	      (match_dup 1)
-	      (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "<di>")))))
-   (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro")
+	      (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "<di>,<di>")))))
+   (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
 	(minus:<DWI> (match_dup 1) (match_dup 2)))]
-  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			    TARGET_APX_NDD)
    && CONST_SCALAR_INT_P (operands[2])
    && rtx_equal_p (operands[2], operands[3])"
   "#"
@@ -8250,7 +8257,8 @@  (define_insn_and_split "*subv<dwi>4_doubleword_1"
 				    operands[5]));
       DONE;
     }
-})
+}
+[(set_attr "isa" "*,apx_ndd")])
 
 (define_insn "*subv<mode>4_overflow_1"
   [(set (reg:CCO FLAGS_REG)
@@ -8258,11 +8266,11 @@  (define_insn "*subv<mode>4_overflow_1"
 	  (minus:<DWI>
 	    (minus:<DWI>
 	      (sign_extend:<DWI>
-		(match_operand:SWI 1 "nonimmediate_operand" "%0,0"))
+		(match_operand:SWI 1 "nonimmediate_operand" "%0,0,rm,r"))
 	      (match_operator:<DWI> 4 "ix86_carry_flag_operator"
 		[(match_operand 3 "flags_reg_operand") (const_int 0)]))
 	    (sign_extend:<DWI>
-	      (match_operand:SWI 2 "<general_sext_operand>" "rWe,m")))
+	      (match_operand:SWI 2 "<general_sext_operand>" "rWe,m,rWe,m")))
 	  (sign_extend:<DWI>
 	    (minus:SWI
 	      (minus:SWI
@@ -8270,15 +8278,21 @@  (define_insn "*subv<mode>4_overflow_1"
 		(match_operator:SWI 5 "ix86_carry_flag_operator"
 		  [(match_dup 3) (const_int 0)]))
 	      (match_dup 2)))))
-   (set (match_operand:SWI 0 "nonimmediate_operand" "=rm,r")
+   (set (match_operand:SWI 0 "nonimmediate_operand" "=rm,r,r,r")
 	(minus:SWI
 	  (minus:SWI
 	    (match_dup 1)
 	    (match_op_dup 5 [(match_dup 3) (const_int 0)]))
 	  (match_dup 2)))]
-  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
-  "sbb{<imodesuffix>}\t{%2, %0|%0, %2}"
-  [(set_attr "type" "alu")
+  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			    TARGET_APX_NDD)"
+  "@
+  sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+  sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+  sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+  sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+   (set_attr "type" "alu")
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*subv<mode>4_overflow_2"
@@ -8287,28 +8301,32 @@  (define_insn "*subv<mode>4_overflow_2"
 	  (minus:<DWI>
 	    (minus:<DWI>
 	      (sign_extend:<DWI>
-		(match_operand:SWI 1 "nonimmediate_operand" "%0"))
+		(match_operand:SWI 1 "nonimmediate_operand" "%0,rm"))
 	      (match_operator:<DWI> 4 "ix86_carry_flag_operator"
 		[(match_operand 3 "flags_reg_operand") (const_int 0)]))
-	    (match_operand:<DWI> 6 "const_int_operand" "n"))
+	    (match_operand:<DWI> 6 "const_int_operand" "n,n"))
 	  (sign_extend:<DWI>
 	    (minus:SWI
 	      (minus:SWI
 		(match_dup 1)
 		(match_operator:SWI 5 "ix86_carry_flag_operator"
 		  [(match_dup 3) (const_int 0)]))
-	      (match_operand:SWI 2 "x86_64_immediate_operand" "e")))))
-   (set (match_operand:SWI 0 "nonimmediate_operand" "=rm")
+	      (match_operand:SWI 2 "x86_64_immediate_operand" "e,e")))))
+   (set (match_operand:SWI 0 "nonimmediate_operand" "=rm,r")
 	(minus:SWI
 	  (minus:SWI
 	    (match_dup 1)
 	    (match_op_dup 5 [(match_dup 3) (const_int 0)]))
 	  (match_dup 2)))]
-  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			    TARGET_APX_NDD)
    && CONST_INT_P (operands[2])
    && INTVAL (operands[2]) == INTVAL (operands[6])"
-  "sbb{<imodesuffix>}\t{%2, %0|%0, %2}"
-  [(set_attr "type" "alu")
+  "@
+  sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+  sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "isa" "*,apx_ndd")
+   (set_attr "type" "alu")
    (set_attr "mode" "<MODE>")
    (set (attr "length_immediate")
      (if_then_else (match_test "IN_RANGE (INTVAL (operands[2]), -128, 127)")
@@ -8593,15 +8611,18 @@  (define_insn "*addsi3_carry_zext_0"
    (set_attr "mode" "SI")])
 
 (define_insn "*addsi3_carry_zext_0r"
-  [(set (match_operand:DI 0 "register_operand" "=r")
+  [(set (match_operand:DI 0 "register_operand" "=r,r")
 	(zero_extend:DI
 	  (plus:SI (match_operator:SI 2 "ix86_carry_flag_unset_operator"
 		    [(reg FLAGS_REG) (const_int 0)])
-		   (match_operand:SI 1 "register_operand" "0"))))
+		   (match_operand:SI 1 "nonimmediate_operand" "0,rm"))))
    (clobber (reg:CC FLAGS_REG))]
   "TARGET_64BIT"
-  "sbb{l}\t{$-1, %k0|%k0, -1}"
-  [(set_attr "type" "alu")
+  "@
+  sbb{l}\t{$-1, %k0|%k0, -1}
+  sbb{l}\t{$-1, %1, %k0|%k0, %1, -1}"
+  [(set_attr "isa" "*,apx_ndd")
+   (set_attr "type" "alu")
    (set_attr "use_carry" "1")
    (set_attr "pent_pair" "pu")
    (set_attr "mode" "SI")])
@@ -8841,17 +8862,23 @@  (define_insn "*addcarry<mode>_1"
        (const_string "4")))])
 
 (define_insn "@sub<mode>3_carry"
-  [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+  [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
 	(minus:SWI
 	  (minus:SWI
-	    (match_operand:SWI 1 "nonimmediate_operand" "0,0")
+	    (match_operand:SWI 1 "nonimmediate_operand" "0,0,rm,r")
 	    (match_operator:SWI 4 "ix86_carry_flag_operator"
 	     [(match_operand 3 "flags_reg_operand") (const_int 0)]))
-	  (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>")))
+	  (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,r<i>,<m>")))
    (clobber (reg:CC FLAGS_REG))]
-  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
-  "sbb{<imodesuffix>}\t{%2, %0|%0, %2}"
-  [(set_attr "type" "alu")
+  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			    TARGET_APX_NDD)"
+  "@
+  sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+  sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+  sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+  sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+   (set_attr "type" "alu")
    (set_attr "use_carry" "1")
    (set_attr "pent_pair" "pu")
    (set_attr "mode" "<MODE>")])
@@ -8938,18 +8965,23 @@  (define_insn "*sub<mode>3_carry_0r"
    (set_attr "mode" "<MODE>")])
 
 (define_insn "*subsi3_carry_zext"
-  [(set (match_operand:DI 0 "register_operand" "=r")
+  [(set (match_operand:DI 0 "register_operand" "=r,r,r")
 	(zero_extend:DI
 	  (minus:SI
 	    (minus:SI
-	      (match_operand:SI 1 "register_operand" "0")
+	      (match_operand:SI 1 "nonimmediate_operand" "0,r,rm")
 	      (match_operator:SI 3 "ix86_carry_flag_operator"
 	       [(reg FLAGS_REG) (const_int 0)]))
-	    (match_operand:SI 2 "x86_64_general_operand" "rBMe"))))
+	    (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe,re"))))
    (clobber (reg:CC FLAGS_REG))]
-  "TARGET_64BIT && ix86_binary_operator_ok (MINUS, SImode, operands)"
-  "sbb{l}\t{%2, %k0|%k0, %2}"
-  [(set_attr "type" "alu")
+  "TARGET_64BIT && ix86_binary_operator_ok (MINUS, SImode, operands,
+					    TARGET_APX_NDD)"
+  "@
+  sbb{l}\t{%2, %k0|%k0, %2}
+  sbb{l}\t{%2, %1, %k0|%k0, %1, %2}
+  sbb{l}\t{%2, %1, %k0|%k0, %1, %2}"
+  [(set_attr "isa" "*,apx_ndd,apx_ndd")
+   (set_attr "type" "alu")
    (set_attr "use_carry" "1")
    (set_attr "pent_pair" "pu")
    (set_attr "mode" "SI")])
@@ -9034,21 +9066,27 @@  (define_insn "subborrow<mode>"
   [(set (reg:CCC FLAGS_REG)
 	(compare:CCC
 	  (zero_extend:<DWI>
-	    (match_operand:SWI48 1 "nonimmediate_operand" "0,0"))
+	    (match_operand:SWI48 1 "nonimmediate_operand" "0,0,r,rm"))
 	  (plus:<DWI>
 	    (match_operator:<DWI> 4 "ix86_carry_flag_operator"
 	      [(match_operand 3 "flags_reg_operand") (const_int 0)])
 	    (zero_extend:<DWI>
-	      (match_operand:SWI48 2 "nonimmediate_operand" "r,rm")))))
-   (set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r")
+	      (match_operand:SWI48 2 "nonimmediate_operand" "r,rm,rm,r")))))
+   (set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r,r")
 	(minus:SWI48 (minus:SWI48
 		       (match_dup 1)
 		       (match_operator:SWI48 5 "ix86_carry_flag_operator"
 			 [(match_dup 3) (const_int 0)]))
 		     (match_dup 2)))]
-  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
-  "sbb{<imodesuffix>}\t{%2, %0|%0, %2}"
-  [(set_attr "type" "alu")
+  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			    TARGET_APX_NDD)"
+  "@
+  sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+  sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+  sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+  sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+   (set_attr "type" "alu")
    (set_attr "use_carry" "1")
    (set_attr "pent_pair" "pu")
    (set_attr "mode" "<MODE>")])
@@ -9209,7 +9247,8 @@  (define_expand "subborrow<mode>_0"
 	     (match_operand:SWI48 2 "<general_operand>")))
       (set (match_operand:SWI48 0 "register_operand")
 	   (minus:SWI48 (match_dup 1) (match_dup 2)))])]
-  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)")
+  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			    TARGET_APX_NDD)")
 
 (define_expand "uaddc<mode>5"
   [(match_operand:SWI48 0 "register_operand")
@@ -9634,7 +9673,8 @@  (define_insn_and_split "*sub<mode>3_eq"
 		    (const_int 0)))
 	  (match_operand:SWI 2 "<general_operand>")))
    (clobber (reg:CC FLAGS_REG))]
-  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+  "ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			    TARGET_APX_NDD)
    && ix86_pre_reload_split ()"
   "#"
   "&& 1"
@@ -9659,7 +9699,8 @@  (define_insn_and_split "*sub<mode>3_ne"
   "CONST_INT_P (operands[2])
    && (<MODE>mode != DImode
        || INTVAL (operands[2]) != HOST_WIDE_INT_C (-0x80000000))
-   && ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+   && ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			       TARGET_APX_NDD)
    && ix86_pre_reload_split ()"
   "#"
   "&& 1"
@@ -9688,7 +9729,8 @@  (define_insn_and_split "*sub<mode>3_eq_1"
   "CONST_INT_P (operands[2])
    && (<MODE>mode != DImode
        || INTVAL (operands[2]) != HOST_WIDE_INT_C (-0x80000000))
-   && ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+   && ix86_binary_operator_ok (MINUS, <MODE>mode, operands,
+			       TARGET_APX_NDD)
    && ix86_pre_reload_split ()"
   "#"
   "&& 1"
diff --git a/gcc/testsuite/gcc.target/i386/apx-ndd-sbb.c b/gcc/testsuite/gcc.target/i386/apx-ndd-sbb.c
new file mode 100644
index 00000000000..662e3c607d8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/apx-ndd-sbb.c
@@ -0,0 +1,6 @@ 
+/* { dg-do compile { target { int128 && { ! ia32 } } } } */
+/* { dg-options "-mapxf -O2" } */
+
+#include "pr91681-2.c"
+
+/* { dg-final { scan-assembler-times "sbbq\[^\n\r]*0, %rdi, %rdx" 1 } } */