[PATCH v2 5/8] [APX NF] Support APX NF for rotate insns

["Kong, Lingling" <lingling.kong@intel.com>]

gcc/ChangeLog:

	* config/i386/i386.md (ashr<mode>3_cvt_nf): New define_insn.
	(*<insn><mode>3_1_nf): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/apx-nf.c: Add NF test for rotate insns.
---
 gcc/config/i386/i386.md                | 53 ++++++++++++++++----------
 gcc/testsuite/gcc.target/i386/apx-nf.c |  5 +++
 2 files changed, 38 insertions(+), 20 deletions(-)

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md index 7f191749342..731eb12d13a 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -16230,19 +16230,19 @@
 (define_mode_attr cvt_mnemonic
   [(SI "{cltd|cdq}") (DI "{cqto|cqo}")])
 
-(define_insn "ashr<mode>3_cvt"
+(define_insn "ashr<mode>3_cvt<nf_name>"
   [(set (match_operand:SWI48 0 "nonimmediate_operand" "=*d,rm,r")
 	(ashiftrt:SWI48
 	  (match_operand:SWI48 1 "nonimmediate_operand" "*a,0,rm")
-	  (match_operand:QI 2 "const_int_operand")))
-   (clobber (reg:CC FLAGS_REG))]
+	  (match_operand:QI 2 "const_int_operand")))]
   "INTVAL (operands[2]) == GET_MODE_BITSIZE (<MODE>mode)-1
    && (TARGET_USE_CLTD || optimize_function_for_size_p (cfun))
-   && ix86_binary_operator_ok (ASHIFTRT, <MODE>mode, operands, TARGET_APX_NDD)"
+   && ix86_binary_operator_ok (ASHIFTRT, <MODE>mode, operands, TARGET_APX_NDD)
+   && <nf_condition>"
   "@
    <cvt_mnemonic>
-   sar{<imodesuffix>}\t{%2, %0|%0, %2}
-   sar{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+   <nf_prefix>sar{<imodesuffix>}\t{%2, %0|%0, %2}
+   <nf_prefix>sar{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
   [(set_attr "isa" "*,*,apx_ndd")
    (set_attr "type" "imovx,ishift,ishift")
    (set_attr "prefix_0f" "0,*,*")
@@ -17094,13 +17094,13 @@
   [(set_attr "type" "rotatex")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "*<insn><mode>3_1"
+(define_insn "*<insn><mode>3_1<nf_name>"
   [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r")
 	(any_rotate:SWI48
 	  (match_operand:SWI48 1 "nonimmediate_operand" "0,rm,rm")
-	  (match_operand:QI 2 "nonmemory_operand" "c<S>,<S>,c<S>")))
-   (clobber (reg:CC FLAGS_REG))]
-  "ix86_binary_operator_ok (<CODE>, <MODE>mode, operands, TARGET_APX_NDD)"
+	  (match_operand:QI 2 "nonmemory_operand" "c<S>,<S>,c<S>")))]
+  "ix86_binary_operator_ok (<CODE>, <MODE>mode, operands, TARGET_APX_NDD)
+   && <nf_condition>"
 {
   bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
   switch (get_attr_type (insn))
@@ -17111,11 +17111,11 @@
     default:
       if (operands[2] == const1_rtx
 	  && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
-	  && !use_ndd)
+	  && !use_ndd && !<nf_applied>)
 	return "<rotate>{<imodesuffix>}\t%0";
       else
-	return use_ndd ? "<rotate>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
-		       : "<rotate>{<imodesuffix>}\t{%2, %0|%0, %2}";
+	return use_ndd ? "<nf_prefix><rotate>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+		       : "<nf_prefix><rotate>{<imodesuffix>}\t{%2, %0|%0, %2}";
     }
 }
   [(set_attr "isa" "*,bmi2,apx_ndd")
@@ -17135,6 +17135,19 @@
    (set_attr "mode" "<MODE>")])
 
 ;; Convert rotate to the rotatex pattern to avoid flags dependency.
+(define_split
+  [(set (match_operand:SWI48 0 "register_operand")
+	(rotate:SWI48 (match_operand:SWI48 1 "nonimmediate_operand")
+		      (match_operand:QI 2 "const_int_operand")))]
+  "TARGET_BMI2 && reload_completed && !optimize_function_for_size_p (cfun)"
+  [(set (match_dup 0)
+	(rotatert:SWI48 (match_dup 1) (match_dup 2)))] {
+  int bitsize = GET_MODE_BITSIZE (<MODE>mode);
+
+  operands[2] = GEN_INT ((bitsize - INTVAL (operands[2])) % bitsize);
+})
+
 (define_split
   [(set (match_operand:SWI48 0 "register_operand")
 	(rotate:SWI48 (match_operand:SWI48 1 "nonimmediate_operand") @@ -17236,22 +17249,22 @@
   [(set (match_dup 0)
 	(zero_extend:DI (rotatert:SI (match_dup 1) (match_dup 2))))])
 
-(define_insn "*<insn><mode>3_1"
+(define_insn "*<insn><mode>3_1<nf_name>"
   [(set (match_operand:SWI12 0 "nonimmediate_operand" "=<r>m,r")
 	(any_rotate:SWI12 (match_operand:SWI12 1 "nonimmediate_operand" "0,rm")
-			  (match_operand:QI 2 "nonmemory_operand" "c<S>,c<S>")))
-   (clobber (reg:CC FLAGS_REG))]
-  "ix86_binary_operator_ok (<CODE>, <MODE>mode, operands, TARGET_APX_NDD)"
+			  (match_operand:QI 2 "nonmemory_operand" "c<S>,c<S>")))]
+  "ix86_binary_operator_ok (<CODE>, <MODE>mode, operands, TARGET_APX_NDD)
+   && <nf_condition>"
 {
   bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
   if (operands[2] == const1_rtx
       && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
-      && !use_ndd)
+      && !use_ndd && !<nf_applied>)
     return "<rotate>{<imodesuffix>}\t%0";
   else
     return use_ndd
-	   ? "<rotate>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
-	   : "<rotate>{<imodesuffix>}\t{%2, %0|%0, %2}";
+	   ? "<nf_prefix><rotate>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+	   : "<nf_prefix><rotate>{<imodesuffix>}\t{%2, %0|%0, %2}";
 }
   [(set_attr "isa" "*,apx_ndd")
    (set_attr "type" "rotate")
diff --git a/gcc/testsuite/gcc.target/i386/apx-nf.c b/gcc/testsuite/gcc.target/i386/apx-nf.c
index 608dbf8f5f7..6e59803be64 100644
--- a/gcc/testsuite/gcc.target/i386/apx-nf.c
+++ b/gcc/testsuite/gcc.target/i386/apx-nf.c
@@ -3,6 +3,7 @@
 /* { dg-final { scan-assembler-times "\{nf\} add" 4 } } */
 /* { dg-final { scan-assembler-times "\{nf\} and" 1 } } */
 /* { dg-final { scan-assembler-times "\{nf\} or" 1 } } */
+/* { dg-final { scan-assembler-times "\{nf\} rol" 4 } } */
 
 #include "apx-ndd.c"
 
@@ -13,3 +14,7 @@ foo (struct B *b)
 {
     b->bit0 = b->bit0 | b->bit1;
 }
+long int f1 (int x) { return ~(1ULL << (x & 0x3f)); } long int f2 (int 
+x) { return ~(1ULL << x); } long int f3 (unsigned char *x) { return 
+~(1ULL << (x[0] & 0x3f)); } long int f4 (unsigned char *x) { return 
+~(1ULL << x[0]); }
--
2.31.1