[APX NDD] Support APX NDD for shld/shrd insns

For shld/shrd insns, the old pattern use match_dup 0 as its shift src and use
+r*m as its constraint. To support NDD we added new define_insns to handle NDD
form pattern with extra input and dest operand to be fixed in register.

gcc/ChangeLog:

	* config/i386/i386.md (x86_64_shld_ndd): New define_insn.
	(x86_64_shld_ndd_1): Likewise.
	(*x86_64_shld_ndd_2): Likewise.
	(x86_shld_ndd): Likewise.
	(x86_shld_ndd_1): Likewise.
	(*x86_shld_ndd_2): Likewise.
	(x86_64_shrd_ndd): Likewise.
	(x86_64_shrd_ndd_1): Likewise.
	(*x86_64_shrd_ndd_2): Likewise.
	(x86_shrd_ndd): Likewise.
	(x86_shrd_ndd_1): Likewise.
	(*x86_shrd_ndd_2): Likewise.
	(*x86_64_shld_shrd_1_nozext): Adjust codegen under TARGET_APX_NDD.
	(*x86_shld_shrd_1_nozext): Likewise.
	(*x86_64_shrd_shld_1_nozext): Likewise.
	(*x86_shrd_shld_1_nozext): Likewise.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/apx-ndd-shld-shrd.c: New test.

2 files changed, 344 insertions, 2 deletions

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 6e4ac77..5c62754 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -14510,6 +14510,23 @@
    (set_attr "amdfam10_decode" "vector")
    (set_attr "bdver1_decode" "vector")])
 
+(define_insn "x86_64_shld_ndd"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+        (ior:DI (ashift:DI (match_operand:DI 1 "nonimmediate_operand" "rm")
+		  (and:QI (match_operand:QI 3 "nonmemory_operand" "Jc")
+			  (const_int 63)))
+		(subreg:DI
+		  (lshiftrt:TI
+		    (zero_extend:TI
+		      (match_operand:DI 2 "register_operand" "r"))
+		    (minus:QI (const_int 64)
+			      (and:QI (match_dup 3) (const_int 63)))) 0)))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD"
+  "shld{q}\t{%s3%2, %1, %0|%0, %1, %2, %3}"
+  [(set_attr "type" "ishift")
+   (set_attr "mode" "DI")])
+
 (define_insn "x86_64_shld_1"
   [(set (match_operand:DI 0 "nonimmediate_operand" "+r*m")
         (ior:DI (ashift:DI (match_dup 0)
@@ -14531,6 +14548,24 @@
    (set_attr "amdfam10_decode" "vector")
    (set_attr "bdver1_decode" "vector")])
 
+(define_insn "x86_64_shld_ndd_1"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+        (ior:DI (ashift:DI (match_operand:DI 1 "nonimmediate_operand" "rm")
+			   (match_operand:QI 3 "const_0_to_63_operand"))
+		(subreg:DI
+		  (lshiftrt:TI
+		    (zero_extend:TI
+		      (match_operand:DI 2 "register_operand" "r"))
+		    (match_operand:QI 4 "const_0_to_255_operand")) 0)))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD
+   && INTVAL (operands[4]) == 64 - INTVAL (operands[3])"
+  "shld{q}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+  [(set_attr "type" "ishift")
+   (set_attr "mode" "DI")
+   (set_attr "length_immediate" "1")])
+
+
 (define_insn_and_split "*x86_64_shld_shrd_1_nozext"
   [(set (match_operand:DI 0 "nonimmediate_operand")
 	(ior:DI (ashift:DI (match_operand:DI 4 "nonimmediate_operand")
@@ -14556,6 +14591,23 @@
       operands[4] = force_reg (DImode, operands[4]);
       emit_insn (gen_x86_64_shrd_1 (operands[0], operands[4], operands[3], operands[2]));
     }
+  else if (TARGET_APX_NDD)
+    {
+     rtx tmp = gen_reg_rtx (DImode);
+     if (MEM_P (operands[4]))
+       {
+	 operands[1] = force_reg (DImode, operands[1]);
+	 emit_insn (gen_x86_64_shld_ndd_1 (tmp, operands[4], operands[1],
+					   operands[2], operands[3]));
+       }
+     else if (MEM_P (operands[1]))
+       emit_insn (gen_x86_64_shrd_ndd_1 (tmp, operands[1], operands[4],
+					 operands[3], operands[2]));
+     else
+       emit_insn (gen_x86_64_shld_ndd_1 (tmp, operands[4], operands[1],
+					 operands[2], operands[3]));
+     emit_move_insn (operands[0], tmp);
+    }
   else
    {
      operands[1] = force_reg (DImode, operands[1]);
@@ -14588,6 +14640,33 @@
 						   (const_int 63)))) 0)))
 	      (clobber (reg:CC FLAGS_REG))])])
 
+(define_insn_and_split "*x86_64_shld_ndd_2"
+  [(set (match_operand:DI 0 "nonimmediate_operand")
+	(ior:DI (ashift:DI (match_operand:DI 1 "nonimmediate_operand")
+			   (match_operand:QI 3 "nonmemory_operand"))
+		(lshiftrt:DI (match_operand:DI 2 "register_operand")
+			     (minus:QI (const_int 64) (match_dup 3)))))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD
+   && ix86_pre_reload_split ()"
+  "#"
+  "&& 1"
+  [(parallel [(set (match_dup 4)
+		   (ior:DI (ashift:DI (match_dup 1)
+				      (and:QI (match_dup 3) (const_int 63)))
+			   (subreg:DI
+			     (lshiftrt:TI
+			       (zero_extend:TI (match_dup 2))
+				 (minus:QI (const_int 64)
+					   (and:QI (match_dup 3)
+						   (const_int 63)))) 0)))
+	      (clobber (reg:CC FLAGS_REG))
+	      (set (match_dup 0) (match_dup 4))])]
+{
+  operands[4] = gen_reg_rtx (DImode);
+  emit_move_insn (operands[4], operands[0]);
+})
+
 (define_insn "x86_shld"
   [(set (match_operand:SI 0 "nonimmediate_operand" "+r*m")
         (ior:SI (ashift:SI (match_dup 0)
@@ -14610,6 +14689,24 @@
    (set_attr "amdfam10_decode" "vector")
    (set_attr "bdver1_decode" "vector")])
 
+(define_insn "x86_shld_ndd"
+  [(set (match_operand:SI 0 "nonimmediate_operand" "=r")
+        (ior:SI (ashift:SI (match_operand:SI 1 "nonimmediate_operand" "rm")
+		  (and:QI (match_operand:QI 3 "nonmemory_operand" "Ic")
+			  (const_int 31)))
+		(subreg:SI
+		  (lshiftrt:DI
+		    (zero_extend:DI
+		      (match_operand:SI 2 "register_operand" "r"))
+		    (minus:QI (const_int 32)
+			      (and:QI (match_dup 3) (const_int 31)))) 0)))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD"
+  "shld{l}\t{%s3%2, %1, %0|%0, %1, %2, %3}"
+  [(set_attr "type" "ishift")
+   (set_attr "mode" "SI")])
+
+
 (define_insn "x86_shld_1"
   [(set (match_operand:SI 0 "nonimmediate_operand" "+r*m")
         (ior:SI (ashift:SI (match_dup 0)
@@ -14631,6 +14728,24 @@
    (set_attr "amdfam10_decode" "vector")
    (set_attr "bdver1_decode" "vector")])
 
+(define_insn "x86_shld_ndd_1"
+  [(set (match_operand:SI 0 "register_operand" "=r")
+        (ior:SI (ashift:SI (match_operand:SI 1 "nonimmediate_operand" "rm")
+			   (match_operand:QI 3 "const_0_to_31_operand"))
+		(subreg:SI
+		  (lshiftrt:DI
+		    (zero_extend:DI
+		      (match_operand:SI 2 "register_operand" "r"))
+		    (match_operand:QI 4 "const_0_to_63_operand")) 0)))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD 
+   && INTVAL (operands[4]) == 32 - INTVAL (operands[3])"
+  "shld{l}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+  [(set_attr "type" "ishift")
+   (set_attr "length_immediate" "1")
+   (set_attr "mode" "SI")])
+
+
 (define_insn_and_split "*x86_shld_shrd_1_nozext"
   [(set (match_operand:SI 0 "nonimmediate_operand")
 	(ior:SI (ashift:SI (match_operand:SI 4 "nonimmediate_operand")
@@ -14655,7 +14770,24 @@
       operands[4] = force_reg (SImode, operands[4]);
       emit_insn (gen_x86_shrd_1 (operands[0], operands[4], operands[3], operands[2]));
     }
-  else
+  else if (TARGET_APX_NDD)
+    {
+     rtx tmp = gen_reg_rtx (SImode);
+     if (MEM_P (operands[4]))
+       {
+	 operands[1] = force_reg (SImode, operands[1]);
+	 emit_insn (gen_x86_shld_ndd_1 (tmp, operands[4], operands[1],
+					operands[2], operands[3]));
+       }
+     else if (MEM_P (operands[1]))
+       emit_insn (gen_x86_shrd_ndd_1 (tmp, operands[1], operands[4],
+				      operands[3], operands[2]));
+     else
+       emit_insn (gen_x86_shld_ndd_1 (tmp, operands[4], operands[1],
+				      operands[2], operands[3]));
+     emit_move_insn (operands[0], tmp);
+    }
+ else
    {
      operands[1] = force_reg (SImode, operands[1]);
      rtx tmp = gen_reg_rtx (SImode);
@@ -14687,6 +14819,33 @@
 						   (const_int 31)))) 0)))
 	      (clobber (reg:CC FLAGS_REG))])])
 
+(define_insn_and_split "*x86_shld_ndd_2"
+  [(set (match_operand:SI 0 "nonimmediate_operand")
+	(ior:SI (ashift:SI (match_operand:SI 1 "nonimmediate_operand")
+			   (match_operand:QI 3 "nonmemory_operand"))
+		(lshiftrt:SI (match_operand:SI 2 "register_operand")
+			     (minus:QI (const_int 32) (match_dup 3)))))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD
+   && ix86_pre_reload_split ()"
+  "#"
+  "&& 1"
+  [(parallel [(set (match_dup 4)
+		   (ior:SI (ashift:SI (match_dup 1)
+				      (and:QI (match_dup 3) (const_int 31)))
+			   (subreg:SI
+			     (lshiftrt:DI
+			       (zero_extend:DI (match_dup 2))
+				 (minus:QI (const_int 32)
+					   (and:QI (match_dup 3)
+						   (const_int 31)))) 0)))
+	      (clobber (reg:CC FLAGS_REG))
+	      (set (match_dup 0) (match_dup 4))])]
+{
+  operands[4] = gen_reg_rtx (SImode);
+  emit_move_insn (operands[4], operands[0]);
+})
+
 (define_expand "@x86_shift<mode>_adj_1"
   [(set (reg:CCZ FLAGS_REG)
 	(compare:CCZ (and:QI (match_operand:QI 2 "register_operand")
@@ -15626,6 +15785,24 @@
    (set_attr "amdfam10_decode" "vector")
    (set_attr "bdver1_decode" "vector")])
 
+(define_insn "x86_64_shrd_ndd"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+        (ior:DI (lshiftrt:DI (match_operand:DI 1 "nonimmediate_operand" "rm")
+		  (and:QI (match_operand:QI 3 "nonmemory_operand" "Jc")
+			  (const_int 63)))
+		(subreg:DI
+		  (ashift:TI
+		    (zero_extend:TI
+		      (match_operand:DI 2 "register_operand" "r"))
+		    (minus:QI (const_int 64)
+			      (and:QI (match_dup 3) (const_int 63)))) 0)))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD"
+  "shrd{q}\t{%s3%2, %1, %0|%0, %1, %2, %3}"
+  [(set_attr "type" "ishift")
+   (set_attr "mode" "DI")])
+
+
 (define_insn "x86_64_shrd_1"
   [(set (match_operand:DI 0 "nonimmediate_operand" "+r*m")
         (ior:DI (lshiftrt:DI (match_dup 0)
@@ -15647,6 +15824,24 @@
    (set_attr "amdfam10_decode" "vector")
    (set_attr "bdver1_decode" "vector")])
 
+(define_insn "x86_64_shrd_ndd_1"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+        (ior:DI (lshiftrt:DI (match_operand:DI 1 "nonimmediate_operand" "rm")
+			     (match_operand:QI 3 "const_0_to_63_operand"))
+		(subreg:DI
+		  (ashift:TI
+		    (zero_extend:TI
+		      (match_operand:DI 2 "register_operand" "r"))
+		    (match_operand:QI 4 "const_0_to_255_operand")) 0)))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD
+   && INTVAL (operands[4]) == 64 - INTVAL (operands[3])"
+  "shrd{q}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+  [(set_attr "type" "ishift")
+   (set_attr "length_immediate" "1")
+   (set_attr "mode" "DI")])
+
+
 (define_insn_and_split "*x86_64_shrd_shld_1_nozext"
   [(set (match_operand:DI 0 "nonimmediate_operand")
 	(ior:DI (lshiftrt:DI (match_operand:DI 4 "nonimmediate_operand")
@@ -15672,6 +15867,23 @@
       operands[4] = force_reg (DImode, operands[4]);
       emit_insn (gen_x86_64_shld_1 (operands[0], operands[4], operands[3], operands[2]));
     }
+  else if (TARGET_APX_NDD)
+    {
+      rtx tmp = gen_reg_rtx (DImode);
+      if (MEM_P (operands[4]))
+        {
+	  operands[1] = force_reg (DImode, operands[1]);
+	  emit_insn (gen_x86_64_shrd_ndd_1 (tmp, operands[4], operands[1],
+					    operands[2], operands[3]));
+        }
+       else if (MEM_P (operands[1]))
+         emit_insn (gen_x86_64_shld_ndd_1 (tmp, operands[1], operands[4],
+					   operands[3], operands[2]));
+       else
+         emit_insn (gen_x86_64_shrd_ndd_1 (tmp, operands[4], operands[1],
+					   operands[2], operands[3]));
+       emit_move_insn (operands[0], tmp);
+    }
   else
    {
      operands[1] = force_reg (DImode, operands[1]);
@@ -15704,6 +15916,33 @@
 						   (const_int 63)))) 0)))
 	      (clobber (reg:CC FLAGS_REG))])])
 
+(define_insn_and_split "*x86_64_shrd_ndd_2"
+  [(set (match_operand:DI 0 "nonimmediate_operand")
+	(ior:DI (lshiftrt:DI (match_operand:DI 1 "nonimmediate_operand")
+			     (match_operand:QI 3 "nonmemory_operand"))
+		(ashift:DI (match_operand:DI 2 "register_operand")
+			   (minus:QI (const_int 64) (match_dup 2)))))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD
+  && ix86_pre_reload_split ()"
+  "#"
+  "&& 1"
+  [(parallel [(set (match_dup 4)
+		   (ior:DI (lshiftrt:DI (match_dup 1)
+					(and:QI (match_dup 3) (const_int 63)))
+			   (subreg:DI
+			     (ashift:TI
+			       (zero_extend:TI (match_dup 2))
+				 (minus:QI (const_int 64)
+					   (and:QI (match_dup 3)
+						   (const_int 63)))) 0)))
+	      (clobber (reg:CC FLAGS_REG))
+	      (set (match_dup 0) (match_dup 4))])]
+{
+  operands[4] = gen_reg_rtx (DImode);
+  emit_move_insn (operands[4], operands[0]);
+})
+
 (define_insn "x86_shrd"
   [(set (match_operand:SI 0 "nonimmediate_operand" "+r*m")
         (ior:SI (lshiftrt:SI (match_dup 0)
@@ -15726,6 +15965,23 @@
    (set_attr "amdfam10_decode" "vector")
    (set_attr "bdver1_decode" "vector")])
 
+(define_insn "x86_shrd_ndd"
+  [(set (match_operand:SI 0 "register_operand" "=r")
+        (ior:SI (lshiftrt:SI (match_operand:SI 1 "nonimmediate_operand" "rm")
+		  (and:QI (match_operand:QI 3 "nonmemory_operand" "Ic")
+			  (const_int 31)))
+		(subreg:SI
+		  (ashift:DI
+		    (zero_extend:DI
+		      (match_operand:SI 2 "register_operand" "r"))
+		    (minus:QI (const_int 32)
+			      (and:QI (match_dup 3) (const_int 31)))) 0)))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD"
+  "shrd{l}\t{%s3%2, %1, %0|%0, %1, %2, %3}"
+  [(set_attr "type" "ishift")
+   (set_attr "mode" "SI")])
+
 (define_insn "x86_shrd_1"
   [(set (match_operand:SI 0 "nonimmediate_operand" "+r*m")
         (ior:SI (lshiftrt:SI (match_dup 0)
@@ -15747,6 +16003,24 @@
    (set_attr "amdfam10_decode" "vector")
    (set_attr "bdver1_decode" "vector")])
 
+(define_insn "x86_shrd_ndd_1"
+  [(set (match_operand:SI 0 "register_operand" "=r")
+        (ior:SI (lshiftrt:SI (match_operand:SI 1 "nonimmediate_operand" "rm")
+			     (match_operand:QI 3 "const_0_to_31_operand"))
+		(subreg:SI
+		  (ashift:DI
+		    (zero_extend:DI
+		      (match_operand:SI 2 "register_operand" "r"))
+		    (match_operand:QI 4 "const_0_to_63_operand")) 0)))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD
+   && (INTVAL (operands[4]) == 32 - INTVAL (operands[3]))"
+  "shrd{l}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+  [(set_attr "type" "ishift")
+   (set_attr "length_immediate" "1")
+   (set_attr "mode" "SI")])
+
+
 (define_insn_and_split "*x86_shrd_shld_1_nozext"
   [(set (match_operand:SI 0 "nonimmediate_operand")
 	(ior:SI (lshiftrt:SI (match_operand:SI 4 "nonimmediate_operand")
@@ -15771,7 +16045,24 @@
       operands[4] = force_reg (SImode, operands[4]);
       emit_insn (gen_x86_shld_1 (operands[0], operands[4], operands[3], operands[2]));
     }
-  else
+  else if (TARGET_APX_NDD)
+    {
+      rtx tmp = gen_reg_rtx (SImode);
+      if (MEM_P (operands[4]))
+        {
+	  operands[1] = force_reg (SImode, operands[1]);
+	  emit_insn (gen_x86_shrd_ndd_1 (tmp, operands[4], operands[1],
+					 operands[2], operands[3]));
+        }
+      else if (MEM_P (operands[1]))
+        emit_insn (gen_x86_shld_ndd_1 (tmp, operands[1], operands[4],
+				       operands[3], operands[2]));
+      else
+        emit_insn (gen_x86_shrd_ndd_1 (tmp, operands[4], operands[1],
+				       operands[2], operands[3]));
+      emit_move_insn (operands[0], tmp);
+     }
+   else
    {
      operands[1] = force_reg (SImode, operands[1]);
      rtx tmp = gen_reg_rtx (SImode);
@@ -15803,6 +16094,33 @@
 						   (const_int 31)))) 0)))
 	      (clobber (reg:CC FLAGS_REG))])])
 
+(define_insn_and_split "*x86_shrd_ndd_2"
+  [(set (match_operand:SI 0 "nonimmediate_operand")
+	(ior:SI (lshiftrt:SI (match_operand:SI 1 "nonimmediate_operand")
+			   (match_operand:QI 3 "nonmemory_operand"))
+		(ashift:SI (match_operand:SI 2 "register_operand")
+			   (minus:QI (const_int 32) (match_dup 3)))))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_APX_NDD
+   && ix86_pre_reload_split ()"
+  "#"
+  "&& 1"
+  [(parallel [(set (match_dup 4)
+		   (ior:SI (lshiftrt:SI (match_dup 1)
+				        (and:QI (match_dup 3) (const_int 31)))
+			   (subreg:SI
+			     (ashift:DI
+			       (zero_extend:DI (match_dup 2))
+				 (minus:QI (const_int 32)
+					   (and:QI (match_dup 3)
+						   (const_int 31)))) 0)))
+	      (clobber (reg:CC FLAGS_REG))
+	      (set (match_dup 0) (match_dup 4))])]
+{
+  operands[4] = gen_reg_rtx (SImode);
+  emit_move_insn (operands[4], operands[0]);
+})
+
 ;; Base name for insn mnemonic.
 (define_mode_attr cvt_mnemonic
   [(SI "{cltd|cdq}") (DI "{cqto|cqo}")])
diff --git a/gcc/testsuite/gcc.target/i386/apx-ndd-shld-shrd.c b/gcc/testsuite/gcc.target/i386/apx-ndd-shld-shrd.c
new file mode 100644
index 0000000..87068ea
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/apx-ndd-shld-shrd.c
@@ -0,0 +1,24 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -Wno-shift-count-overflow -m64 -mapxf" } */
+/* { dg-final { scan-assembler-times {(?n)shld[ql]?[\t ]*\$2} 4 } } */
+/* { dg-final { scan-assembler-times {(?n)shrd[ql]?[\t ]*\$2} 4 } } */
+
+typedef unsigned long  u64;
+typedef unsigned int   u32;
+
+long  a;
+int   c;
+const char n = 2;
+
+long test64r (long e) { long t = ((u64)a >> n) | (e << (64 - n)); return t;}
+long test64l (u64 e) { long t = (a << n) | (e >> (64 - n)); return t;}
+int test32r (int f) { int t = ((u32)c >> n) | (f << (32 - n)); return t; }
+int test32l (u32 f) { int t = (c << n) | (f >> (32 - n)); return t; }
+
+u64 ua;
+u32 uc;
+
+u64 testu64l (u64 ue) { u64 ut = (ua << n) | (ue >> (64 - n)); return ut; }
+u64 testu64r (u64 ue) { u64 ut = (ua >> n) | (ue << (64 - n)); return ut; }
+u32 testu32l (u32 uf) { u32 ut = (uc << n) | (uf >> (32 - n)); return ut; }
+u32 testu32r (u32 uf) { u32 ut = (uc >> n) | (uf << (32 - n)); return ut; }