[AArch64] Improve description of <F>CM instructions in RTL

gcc/
	* config/aarch64/aarch64-simd-builtins.def (cmhs): Rename to...
	(cmgeu): ...This.
	(cmhi): Rename to...
	(cmgtu): ...This.
	* config/aarch64/aarch64-simd.md
	(simd_mode): Add SF.
	(aarch64_vcond_internal): Use new names for unsigned comparison insns.
	(aarch64_cm<optab><mode>): Rewrite to not use UNSPECs.
	* config/aarch64/aarch64.md (*cstore<mode>_neg): Rename to...
	(cstore<mode>_neg): ...This.
	* config/aarch64/iterators.md
	(VALLF): new.
	(unspec): Remove UNSPEC_CM<EQ, LE, LT, GE, GT, HS, HI, TST>.
	(COMPARISONS): New.
	(UCOMPARISONS): Likewise.
	(optab): Add missing comparisons.
	(n_optab): New.
	(cmp_1): Likewise.
	(cmp_2): Likewise.
	(CMP): Likewise.
	(cmp): Remove.
	(VCMP_S): Likewise.
	(VCMP_U): Likewise.
	(V_cmp_result): Add DF, SF modes.
	(v_cmp_result): Likewise.
	(v): Likewise.
	(vmtype): Likewise.
	* config/aarch64/predicates.md (aarch64_reg_or_fp_zero): New.

From-SVN: r198490

gcc/ChangeLog

+2013-05-01  James Greenhalgh  <james.greenhalgh@arm.com>
+
+	* config/aarch64/aarch64-simd-builtins.def (cmhs): Rename to...
+	(cmgeu): ...This.
+	(cmhi): Rename to...
+	(cmgtu): ...This.
+	* config/aarch64/aarch64-simd.md
+	(simd_mode): Add SF.
+	(aarch64_vcond_internal): Use new names for unsigned comparison insns.
+	(aarch64_cm<optab><mode>): Rewrite to not use UNSPECs.
+	* config/aarch64/aarch64.md (*cstore<mode>_neg): Rename to...
+	(cstore<mode>_neg): ...This.
+	* config/aarch64/iterators.md
+	(VALLF): new.
+	(unspec): Remove UNSPEC_CM<EQ, LE, LT, GE, GT, HS, HI, TST>.
+	(COMPARISONS): New.
+	(UCOMPARISONS): Likewise.
+	(optab): Add missing comparisons.
+	(n_optab): New.
+	(cmp_1): Likewise.
+	(cmp_2): Likewise.
+	(CMP): Likewise.
+	(cmp): Remove.
+	(VCMP_S): Likewise.
+	(VCMP_U): Likewise.
+	(V_cmp_result): Add DF, SF modes.
+	(v_cmp_result): Likewise.
+	(v): Likewise.
+	(vmtype): Likewise.
+	* config/aarch64/predicates.md (aarch64_reg_or_fp_zero): New.
+
 2013-05-01  Greta Yorsh  <Greta.Yorsh@arm.com>
 
 	* config/arm/thumb2.md (thumb2_smaxsi3,thumb2_sminsi3): Convert

gcc/config/aarch64/aarch64-simd-builtins.def

@@ -230,8 +230,8 @@
   BUILTIN_VSDQ_I_DI (BINOP, cmle, 0)
   BUILTIN_VSDQ_I_DI (BINOP, cmlt, 0)
   /* Implemented by aarch64_cm<cmp><mode>.  */
-  BUILTIN_VSDQ_I_DI (BINOP, cmhs, 0)
-  BUILTIN_VSDQ_I_DI (BINOP, cmhi, 0)
+  BUILTIN_VSDQ_I_DI (BINOP, cmgeu, 0)
+  BUILTIN_VSDQ_I_DI (BINOP, cmgtu, 0)
   BUILTIN_VSDQ_I_DI (BINOP, cmtst, 0)
 
   /* Implemented by aarch64_<fmaxmin><mode>.  */

gcc/config/aarch64/aarch64-simd.md

@@ -21,7 +21,7 @@
 
 ; Main data types used by the insntructions
 
-(define_attr "simd_mode" "unknown,none,V8QI,V16QI,V4HI,V8HI,V2SI,V4SI,V2DI,V2SF,V4SF,V2DF,OI,CI,XI,DI,DF,SI,HI,QI"
+(define_attr "simd_mode" "unknown,none,V8QI,V16QI,V4HI,V8HI,V2SI,V4SI,V2DI,V2SF,V4SF,V2DF,OI,CI,XI,DI,DF,SI,SF,HI,QI"
   (const_string "unknown"))
 
 
@@ -1728,12 +1728,12 @@
 
     case LTU:
     case GEU:
-      emit_insn (gen_aarch64_cmhs<mode> (mask, operands[4], operands[5]));
+      emit_insn (gen_aarch64_cmgeu<mode> (mask, operands[4], operands[5]));
       break;
 
     case LEU:
     case GTU:
-      emit_insn (gen_aarch64_cmhi<mode> (mask, operands[4], operands[5]));
+      emit_insn (gen_aarch64_cmgtu<mode> (mask, operands[4], operands[5]));
       break;
 
     case NE:
@@ -3170,48 +3170,181 @@
 )
 
 
-;; cm(eq|ge|le|lt|gt)
+;; cm(eq|ge|gt|lt|le)
+;; Note, we have constraints for Dz and Z as different expanders
+;; have different ideas of what should be passed to this pattern.
 
-(define_insn "aarch64_cm<cmp><mode>"
+(define_insn "aarch64_cm<optab><mode>"
   [(set (match_operand:<V_cmp_result> 0 "register_operand" "=w,w")
-        (unspec:<V_cmp_result>
-	  [(match_operand:VSDQ_I_DI 1 "register_operand" "w,w")
-	   (match_operand:VSDQ_I_DI 2 "aarch64_simd_reg_or_zero" "w,Z")]
-          VCMP_S))]
+	(neg:<V_cmp_result>
+	  (COMPARISONS:<V_cmp_result>
+	    (match_operand:VDQ 1 "register_operand" "w,w")
+	    (match_operand:VDQ 2 "aarch64_simd_reg_or_zero" "w,ZDz")
+	  )))]
   "TARGET_SIMD"
   "@
-  cm<cmp>\t%<v>0<Vmtype>, %<v>1<Vmtype>, %<v>2<Vmtype>
-  cm<cmp>\t%<v>0<Vmtype>, %<v>1<Vmtype>, #0"
+  cm<n_optab>\t%<v>0<Vmtype>, %<v><cmp_1><Vmtype>, %<v><cmp_2><Vmtype>
+  cm<optab>\t%<v>0<Vmtype>, %<v>1<Vmtype>, #0"
   [(set_attr "simd_type" "simd_cmp")
    (set_attr "simd_mode" "<MODE>")]
 )
 
-;; cm(hs|hi|tst)
+(define_insn_and_split "aarch64_cm<optab>di"
+  [(set (match_operand:DI 0 "register_operand" "=w,w,r")
+	(neg:DI
+	  (COMPARISONS:DI
+	    (match_operand:DI 1 "register_operand" "w,w,r")
+	    (match_operand:DI 2 "aarch64_simd_reg_or_zero" "w,ZDz,r")
+	  )))]
+  "TARGET_SIMD"
+  "@
+  cm<n_optab>\t%d0, %d<cmp_1>, %d<cmp_2>
+  cm<optab>\t%d0, %d1, #0
+  #"
+  "reload_completed
+   /* We need to prevent the split from
+      happening in the 'w' constraint cases.  */
+   && GP_REGNUM_P (REGNO (operands[0]))
+   && GP_REGNUM_P (REGNO (operands[1]))"
+  [(set (reg:CC CC_REGNUM)
+    (compare:CC
+      (match_dup 1)
+      (match_dup 2)))
+  (set (match_dup 0)
+    (neg:DI
+      (COMPARISONS:DI
+	(match_operand 3 "cc_register" "")
+	(const_int 0))))]
+  {
+    enum machine_mode mode = SELECT_CC_MODE (<CMP>, operands[1], operands[2]);
+    rtx cc_reg = aarch64_gen_compare_reg (<CMP>, operands[1], operands[2]);
+    rtx comparison = gen_rtx_<CMP> (mode, operands[1], operands[2]);
+    emit_insn (gen_cstoredi_neg (operands[0], comparison, cc_reg));
+    DONE;
+  }
+  [(set_attr "simd_type" "simd_cmp")
+   (set_attr "simd_mode" "DI")]
+)
 
-(define_insn "aarch64_cm<cmp><mode>"
+;; cm(hs|hi)
+
+(define_insn "aarch64_cm<optab><mode>"
   [(set (match_operand:<V_cmp_result> 0 "register_operand" "=w")
-        (unspec:<V_cmp_result>
-	  [(match_operand:VSDQ_I_DI 1 "register_operand" "w")
-	   (match_operand:VSDQ_I_DI 2 "register_operand" "w")]
-          VCMP_U))]
+	(neg:<V_cmp_result>
+	  (UCOMPARISONS:<V_cmp_result>
+	    (match_operand:VDQ 1 "register_operand" "w")
+	    (match_operand:VDQ 2 "register_operand" "w")
+	  )))]
   "TARGET_SIMD"
-  "cm<cmp>\t%<v>0<Vmtype>, %<v>1<Vmtype>, %<v>2<Vmtype>"
+  "cm<n_optab>\t%<v>0<Vmtype>, %<v><cmp_1><Vmtype>, %<v><cmp_2><Vmtype>"
+  [(set_attr "simd_type" "simd_cmp")
+   (set_attr "simd_mode" "<MODE>")]
+)
+
+(define_insn_and_split "aarch64_cm<optab>di"
+  [(set (match_operand:DI 0 "register_operand" "=w,r")
+	(neg:DI
+	  (UCOMPARISONS:DI
+	    (match_operand:DI 1 "register_operand" "w,r")
+	    (match_operand:DI 2 "aarch64_simd_reg_or_zero" "w,r")
+	  )))]
+  "TARGET_SIMD"
+  "@
+  cm<n_optab>\t%d0, %d<cmp_1>, %d<cmp_2>
+  #"
+  "reload_completed
+   /* We need to prevent the split from
+      happening in the 'w' constraint cases.  */
+   && GP_REGNUM_P (REGNO (operands[0]))
+   && GP_REGNUM_P (REGNO (operands[1]))"
+  [(set (reg:CC CC_REGNUM)
+    (compare:CC
+      (match_dup 1)
+      (match_dup 2)))
+  (set (match_dup 0)
+    (neg:DI
+      (UCOMPARISONS:DI
+	(match_operand 3 "cc_register" "")
+	(const_int 0))))]
+  {
+    enum machine_mode mode = SELECT_CC_MODE (<CMP>, operands[1], operands[2]);
+    rtx cc_reg = aarch64_gen_compare_reg (<CMP>, operands[1], operands[2]);
+    rtx comparison = gen_rtx_<CMP> (mode, operands[1], operands[2]);
+    emit_insn (gen_cstoredi_neg (operands[0], comparison, cc_reg));
+    DONE;
+  }
+  [(set_attr "simd_type" "simd_cmp")
+   (set_attr "simd_mode" "DI")]
+)
+
+;; cmtst
+
+(define_insn "aarch64_cmtst<mode>"
+  [(set (match_operand:<V_cmp_result> 0 "register_operand" "=w")
+	(neg:<V_cmp_result>
+	  (ne:<V_cmp_result>
+	    (and:VDQ
+	      (match_operand:VDQ 1 "register_operand" "w")
+	      (match_operand:VDQ 2 "register_operand" "w"))
+	    (vec_duplicate:<V_cmp_result> (const_int 0)))))]
+  "TARGET_SIMD"
+  "cmtst\t%<v>0<Vmtype>, %<v>1<Vmtype>, %<v>2<Vmtype>"
   [(set_attr "simd_type" "simd_cmp")
    (set_attr "simd_mode" "<MODE>")]
 )
 
-;; fcm(eq|ge|le|lt|gt)
+(define_insn_and_split "aarch64_cmtstdi"
+  [(set (match_operand:DI 0 "register_operand" "=w,r")
+	(neg:DI
+	  (ne:DI
+	    (and:DI
+	      (match_operand:DI 1 "register_operand" "w,r")
+	      (match_operand:DI 2 "register_operand" "w,r"))
+	    (const_int 0))))]
+  "TARGET_SIMD"
+  "@
+  cmtst\t%d0, %d1, %d2
+  #"
+  "reload_completed
+   /* We need to prevent the split from
+      happening in the 'w' constraint cases.  */
+   && GP_REGNUM_P (REGNO (operands[0]))
+   && GP_REGNUM_P (REGNO (operands[1]))"
+   [(set (reg:CC_NZ CC_REGNUM)
+	(compare:CC_NZ
+	 (and:DI (match_dup 1)
+		  (match_dup 2))
+	 (const_int 0)))
+  (set (match_dup 0)
+    (neg:DI
+      (ne:DI
+	(match_operand 3 "cc_register" "")
+	(const_int 0))))]
+  {
+    rtx and_tree = gen_rtx_AND (DImode, operands[1], operands[2]);
+    enum machine_mode mode = SELECT_CC_MODE (NE, and_tree, const0_rtx);
+    rtx cc_reg = aarch64_gen_compare_reg (NE, and_tree, const0_rtx);
+    rtx comparison = gen_rtx_NE (mode, and_tree, const0_rtx);
+    emit_insn (gen_cstoredi_neg (operands[0], comparison, cc_reg));
+    DONE;
+  }
+  [(set_attr "simd_type" "simd_cmp")
+   (set_attr "simd_mode" "DI")]
+)
 
-(define_insn "aarch64_cm<cmp><mode>"
+;; fcm(eq|ge|gt|le|lt)
+
+(define_insn "aarch64_cm<optab><mode>"
   [(set (match_operand:<V_cmp_result> 0 "register_operand" "=w,w")
-	(unspec:<V_cmp_result>
-	  [(match_operand:VDQF 1 "register_operand" "w,w")
-	   (match_operand:VDQF 2 "aarch64_simd_reg_or_zero" "w,Dz")]
-	   VCMP_S))]
+	(neg:<V_cmp_result>
+	  (COMPARISONS:<V_cmp_result>
+	    (match_operand:VALLF 1 "register_operand" "w,w")
+	    (match_operand:VALLF 2 "aarch64_simd_reg_or_zero" "w,YDz")
+	  )))]
   "TARGET_SIMD"
   "@
-  fcm<cmp>\t%<v>0<Vmtype>, %<v>1<Vmtype>, %<v>2<Vmtype>
-  fcm<cmp>\t%<v>0<Vmtype>, %<v>1<Vmtype>, 0"
+  fcm<n_optab>\t%<v>0<Vmtype>, %<v><cmp_1><Vmtype>, %<v><cmp_2><Vmtype>
+  fcm<optab>\t%<v>0<Vmtype>, %<v>1<Vmtype>, 0"
   [(set_attr "simd_type" "simd_fcmp")
    (set_attr "simd_mode" "<MODE>")]
 )

gcc/config/aarch64/aarch64.md

@@ -2409,7 +2409,7 @@
    (set_attr "mode" "SI")]
 )
 
-(define_insn "*cstore<mode>_neg"
+(define_insn "cstore<mode>_neg"
   [(set (match_operand:ALLI 0 "register_operand" "=r")
 	(neg:ALLI (match_operator:ALLI 1 "aarch64_comparison_operator"
 		  [(match_operand 2 "cc_register" "") (const_int 0)])))]

gcc/config/aarch64/iterators.md

@@ -83,6 +83,9 @@
 ;; Vector Float modes.
 (define_mode_iterator VDQF [V2SF V4SF V2DF])
 
+;; All Float modes.
+(define_mode_iterator VALLF [V2SF V4SF V2DF SF DF])
+
 ;; Vector Float modes with 2 elements.
 (define_mode_iterator V2F [V2SF V2DF])
 
@@ -213,13 +216,6 @@
     UNSPEC_URSHL	; Used in aarch64-simd.md.
     UNSPEC_SQRSHL	; Used in aarch64-simd.md.
     UNSPEC_UQRSHL	; Used in aarch64-simd.md.
-    UNSPEC_CMEQ		; Used in aarch64-simd.md.
-    UNSPEC_CMLE		; Used in aarch64-simd.md.
-    UNSPEC_CMLT		; Used in aarch64-simd.md.
-    UNSPEC_CMGE		; Used in aarch64-simd.md.
-    UNSPEC_CMGT		; Used in aarch64-simd.md.
-    UNSPEC_CMHS		; Used in aarch64-simd.md.
-    UNSPEC_CMHI		; Used in aarch64-simd.md.
     UNSPEC_SSLI		; Used in aarch64-simd.md.
     UNSPEC_USLI		; Used in aarch64-simd.md.
     UNSPEC_SSRI		; Used in aarch64-simd.md.
@@ -227,7 +223,6 @@
     UNSPEC_SSHLL	; Used in aarch64-simd.md.
     UNSPEC_USHLL	; Used in aarch64-simd.md.
     UNSPEC_ADDP		; Used in aarch64-simd.md.
-    UNSPEC_CMTST	; Used in aarch64-simd.md.
     UNSPEC_FMAX		; Used in aarch64-simd.md.
     UNSPEC_FMIN		; Used in aarch64-simd.md.
     UNSPEC_TBL		; Used in vector permute patterns.
@@ -253,6 +248,7 @@
 
 ;; For scalar usage of vector/FP registers
 (define_mode_attr v [(QI "b") (HI "h") (SI "s") (DI "d")
+		    (SF "s") (DF "d")
 		    (V8QI "") (V16QI "")
 		    (V4HI "") (V8HI "")
 		    (V2SI "") (V4SI  "")
@@ -307,7 +303,8 @@
 			 (V4SF ".4s") (V2DF ".2d")
 			 (DI   "")    (SI   "")
 			 (HI   "")    (QI   "")
-			 (TI   "")])
+			 (TI   "")    (SF   "")
+			 (DF   "")])
 
 ;; Register suffix narrowed modes for VQN.
 (define_mode_attr Vmntype [(V8HI ".8b") (V4SI ".4h")
@@ -446,7 +443,8 @@
 				(V2SI "V2SI") (V4SI  "V4SI")
 				(DI   "DI")   (V2DI  "V2DI")
 				(V2SF "V2SI") (V4SF  "V4SI")
-				(V2DF "V2DI")])
+				(V2DF "V2DI") (DF    "DI")
+				(SF   "SI")])
 
 ;; Lower case mode of results of comparison operations.
 (define_mode_attr v_cmp_result [(V8QI "v8qi") (V16QI "v16qi")
@@ -454,7 +452,8 @@
 				(V2SI "v2si") (V4SI  "v4si")
 				(DI   "di")   (V2DI  "v2di")
 				(V2SF "v2si") (V4SF  "v4si")
-				(V2DF "v2di")])
+				(V2DF "v2di") (DF    "di")
+				(SF   "si")])
 
 ;; Vm for lane instructions is restricted to FP_LO_REGS.
 (define_mode_attr vwx [(V4HI "x") (V8HI "x") (HI "x")
@@ -548,6 +547,12 @@
 ;; Code iterator for signed variants of vector saturating binary ops.
 (define_code_iterator SBINQOPS [ss_plus ss_minus])
 
+;; Comparison operators for <F>CM.
+(define_code_iterator COMPARISONS [lt le eq ge gt])
+
+;; Unsigned comparison operators.
+(define_code_iterator UCOMPARISONS [ltu leu geu gtu])
+
 ;; -------------------------------------------------------------------
 ;; Code Attributes
 ;; -------------------------------------------------------------------
@@ -580,7 +585,28 @@
 			 (eq "eq")
 			 (ne "ne")
 			 (lt "lt")
-			 (ge "ge")])
+			 (ge "ge")
+			 (le "le")
+			 (gt "gt")
+			 (ltu "ltu")
+			 (leu "leu")
+			 (geu "geu")
+			 (gtu "gtu")])
+
+;; For comparison operators we use the FCM* and CM* instructions.
+;; As there are no CMLE or CMLT instructions which act on 3 vector
+;; operands, we must use CMGE or CMGT and swap the order of the
+;; source operands.
+
+(define_code_attr n_optab [(lt "gt") (le "ge") (eq "eq") (ge "ge") (gt "gt")
+			   (ltu "hi") (leu "hs") (geu "hs") (gtu "hi")])
+(define_code_attr cmp_1   [(lt "2") (le "2") (eq "1") (ge "1") (gt "1")
+			   (ltu "2") (leu "2") (geu "1") (gtu "1")])
+(define_code_attr cmp_2   [(lt "1") (le "1") (eq "2") (ge "2") (gt "2")
+			   (ltu "1") (leu "1") (geu "2") (gtu "2")])
+
+(define_code_attr CMP [(lt "LT") (le "LE") (eq "EQ") (ge "GE") (gt "GT")
+			   (ltu "LTU") (leu "LEU") (geu "GEU") (gtu "GTU")])
 
 (define_code_attr fix_trunc_optab [(fix "fix_trunc")
 				   (unsigned_fix "fixuns_trunc")])
@@ -693,11 +719,6 @@
                                UNSPEC_SQSHRN UNSPEC_UQSHRN
                                UNSPEC_SQRSHRN UNSPEC_UQRSHRN])
 
-(define_int_iterator VCMP_S [UNSPEC_CMEQ UNSPEC_CMGE UNSPEC_CMGT
-			     UNSPEC_CMLE UNSPEC_CMLT])
-
-(define_int_iterator VCMP_U [UNSPEC_CMHS UNSPEC_CMHI UNSPEC_CMTST])
-
 (define_int_iterator PERMUTE [UNSPEC_ZIP1 UNSPEC_ZIP2
 			      UNSPEC_TRN1 UNSPEC_TRN2
 			      UNSPEC_UZP1 UNSPEC_UZP2])
@@ -784,12 +805,6 @@
 			 (UNSPEC_RADDHN2 "add")
 			 (UNSPEC_RSUBHN2 "sub")])
 
-(define_int_attr cmp [(UNSPEC_CMGE "ge") (UNSPEC_CMGT "gt")
-		      (UNSPEC_CMLE "le") (UNSPEC_CMLT "lt")
-                      (UNSPEC_CMEQ "eq")
-		      (UNSPEC_CMHS "hs") (UNSPEC_CMHI "hi")
-		      (UNSPEC_CMTST "tst")])
-
 (define_int_attr offsetlr [(UNSPEC_SSLI	"1") (UNSPEC_USLI "1")
 			   (UNSPEC_SSRI	"0") (UNSPEC_USRI "0")])
 

gcc/config/aarch64/predicates.md

@@ -31,6 +31,11 @@
        (ior (match_operand 0 "register_operand")
 	    (match_test "op == const0_rtx"))))
 
+(define_predicate "aarch64_reg_or_fp_zero"
+  (and (match_code "reg,subreg,const_double")
+       (ior (match_operand 0 "register_operand")
+	    (match_test "aarch64_float_const_zero_rtx_p (op)"))))
+
 (define_predicate "aarch64_reg_zero_or_m1_or_1"
   (and (match_code "reg,subreg,const_int")
        (ior (match_operand 0 "register_operand")