[AArch64][3/10] ARMv8.2-A FP16 two operands vector intrinsics

gcc/
	* config/aarch64/aarch64-simd-builtins.def: Register new builtins.
	* config/aarch64/aarch64-simd.md
	(aarch64_rsqrts<mode>): Extend to HF modes.
	(fabd<mode>3): Likewise.
	(<FCVT_F2FIXED:fcvt_fixed_insn><VHSDF_SDF:mode>3): Likewise.
	(<FCVT_FIXED2F:fcvt_fixed_insn><VHSDI_SDI:mode>3): Likewise.
	(aarch64_<maxmin_uns>p<mode>): Likewise.
	(<su><maxmin><mode>3): Likewise.
	(<maxmin_uns><mode>3): Likewise.
	(<fmaxmin><mode>3): Likewise.
	(aarch64_faddp<mode>): Likewise.
	(aarch64_fmulx<mode>): Likewise.
	(aarch64_frecps<mode>): Likewise.
	(*aarch64_fac<optab><mode>): Rename to aarch64_fac<optab><mode>.
	(add<mode>3): Extend to HF modes.
	(sub<mode>3): Likewise.
	(mul<mode>3): Likewise.
	(div<mode>3): Likewise.
	(*div<mode>3): Likewise.
	* config/aarch64/aarch64.c (aarch64_emit_approx_div): Return false for
	HF, V4HF and V8HF.
	* config/aarch64/iterators.md (VDQ_HSDI, VSDQ_HSDI): New mode iterator.
	* config/aarch64/arm_neon.h (vadd_f16): New.
	(vaddq_f16, vabd_f16, vabdq_f16, vcage_f16, vcageq_f16, vcagt_f16,
	vcagtq_f16, vcale_f16, vcaleq_f16, vcalt_f16, vcaltq_f16, vceq_f16,
	vceqq_f16, vcge_f16, vcgeq_f16, vcgt_f16, vcgtq_f16, vcle_f16,
	vcleq_f16, vclt_f16, vcltq_f16, vcvt_n_f16_s16, vcvtq_n_f16_s16,
	vcvt_n_f16_u16, vcvtq_n_f16_u16, vcvt_n_s16_f16, vcvtq_n_s16_f16,
	vcvt_n_u16_f16, vcvtq_n_u16_f16, vdiv_f16, vdivq_f16, vdup_lane_f16,
	vdup_laneq_f16, vdupq_lane_f16, vdupq_laneq_f16, vdups_lane_f16,
	vdups_laneq_f16, vmax_f16, vmaxq_f16, vmaxnm_f16, vmaxnmq_f16, vmin_f16,
	vminq_f16, vminnm_f16, vminnmq_f16, vmul_f16, vmulq_f16, vmulx_f16,
	vmulxq_f16, vpadd_f16, vpaddq_f16, vpmax_f16, vpmaxq_f16, vpmaxnm_f16,
	vpmaxnmq_f16, vpmin_f16, vpminq_f16, vpminnm_f16, vpminnmq_f16,
	vrecps_f16, vrecpsq_f16, vrsqrts_f16, vrsqrtsq_f16, vsub_f16,
	vsubq_f16): Likewise.

From-SVN: r238717

gcc/ChangeLog

 2016-07-25  Jiong Wang  <jiong.wang@arm.com>
 
+	* config/aarch64/aarch64-simd-builtins.def: Register new builtins.
+	* config/aarch64/aarch64-simd.md
+	(aarch64_rsqrts<mode>): Extend to HF modes.
+	(fabd<mode>3): Likewise.
+	(<FCVT_F2FIXED:fcvt_fixed_insn><VHSDF_SDF:mode>3): Likewise.
+	(<FCVT_FIXED2F:fcvt_fixed_insn><VHSDI_SDI:mode>3): Likewise.
+	(aarch64_<maxmin_uns>p<mode>): Likewise.
+	(<su><maxmin><mode>3): Likewise.
+	(<maxmin_uns><mode>3): Likewise.
+	(<fmaxmin><mode>3): Likewise.
+	(aarch64_faddp<mode>): Likewise.
+	(aarch64_fmulx<mode>): Likewise.
+	(aarch64_frecps<mode>): Likewise.
+	(*aarch64_fac<optab><mode>): Rename to aarch64_fac<optab><mode>.
+	(add<mode>3): Extend to HF modes.
+	(sub<mode>3): Likewise.
+	(mul<mode>3): Likewise.
+	(div<mode>3): Likewise.
+	(*div<mode>3): Likewise.
+	* config/aarch64/aarch64.c (aarch64_emit_approx_div): Return false for
+	HF, V4HF and V8HF.
+	* config/aarch64/iterators.md (VDQ_HSDI, VSDQ_HSDI): New mode iterator.
+	* config/aarch64/arm_neon.h (vadd_f16): New.
+	(vaddq_f16, vabd_f16, vabdq_f16, vcage_f16, vcageq_f16, vcagt_f16,
+	vcagtq_f16, vcale_f16, vcaleq_f16, vcalt_f16, vcaltq_f16, vceq_f16,
+	vceqq_f16, vcge_f16, vcgeq_f16, vcgt_f16, vcgtq_f16, vcle_f16,
+	vcleq_f16, vclt_f16, vcltq_f16, vcvt_n_f16_s16, vcvtq_n_f16_s16,
+	vcvt_n_f16_u16, vcvtq_n_f16_u16, vcvt_n_s16_f16, vcvtq_n_s16_f16,
+	vcvt_n_u16_f16, vcvtq_n_u16_f16, vdiv_f16, vdivq_f16, vdup_lane_f16,
+	vdup_laneq_f16, vdupq_lane_f16, vdupq_laneq_f16, vdups_lane_f16,
+	vdups_laneq_f16, vmax_f16, vmaxq_f16, vmaxnm_f16, vmaxnmq_f16, vmin_f16,
+	vminq_f16, vminnm_f16, vminnmq_f16, vmul_f16, vmulq_f16, vmulx_f16,
+	vmulxq_f16, vpadd_f16, vpaddq_f16, vpmax_f16, vpmaxq_f16, vpmaxnm_f16,
+	vpmaxnmq_f16, vpmin_f16, vpminq_f16, vpminnm_f16, vpminnmq_f16,
+	vrecps_f16, vrecpsq_f16, vrsqrts_f16, vrsqrtsq_f16, vsub_f16,
+	vsubq_f16): Likewise.
+
+2016-07-25  Jiong Wang  <jiong.wang@arm.com>
+
 	* config/aarch64/aarch64-builtins.c (TYPES_BINOP_USS): New.
 	* config/aarch64/aarch64-simd-builtins.def: Register new builtins.
 	* config/aarch64/aarch64-simd.md (aarch64_rsqrte<mode>): Extend to HF modes.
@@ -15,8 +54,8 @@
 	(*sqrt<mode>2): Likewise.
 	(aarch64_frecpe<mode>): Likewise.
 	(aarch64_cm<optab><mode>): Likewise.
-	* config/aarch64/aarch64.c (aarch64_emit_approx_sqrt): Return
-	false for V4HF and V8HF.
+	* config/aarch64/aarch64.c (aarch64_emit_approx_sqrt): Return false for
+	HF, V4HF and V8HF.
 	* config/aarch64/iterators.md (VHSDF, VHSDF_DF, VHSDF_SDF): New.
 	(VDQF_COND, fcvt_target, FCVT_TARGET, hcon): Extend mode attribute to HF modes.
 	(stype): New.

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

@@ -41,7 +41,7 @@
 
   BUILTIN_VDC (COMBINE, combine, 0)
   BUILTIN_VB (BINOP, pmul, 0)
-  BUILTIN_VALLF (BINOP, fmulx, 0)
+  BUILTIN_VHSDF_SDF (BINOP, fmulx, 0)
   BUILTIN_VHSDF_DF (UNOP, sqrt, 2)
   BUILTIN_VD_BHSI (BINOP, addp, 0)
   VAR1 (UNOP, addp, 0, di)
@@ -248,22 +248,22 @@
   BUILTIN_VDQ_BHSI (BINOP, smin, 3)
   BUILTIN_VDQ_BHSI (BINOP, umax, 3)
   BUILTIN_VDQ_BHSI (BINOP, umin, 3)
-  BUILTIN_VDQF (BINOP, smax_nan, 3)
-  BUILTIN_VDQF (BINOP, smin_nan, 3)
+  BUILTIN_VHSDF (BINOP, smax_nan, 3)
+  BUILTIN_VHSDF (BINOP, smin_nan, 3)
 
   /* Implemented by <fmaxmin><mode>3.  */
-  BUILTIN_VDQF (BINOP, fmax, 3)
-  BUILTIN_VDQF (BINOP, fmin, 3)
+  BUILTIN_VHSDF (BINOP, fmax, 3)
+  BUILTIN_VHSDF (BINOP, fmin, 3)
 
   /* Implemented by aarch64_<maxmin_uns>p<mode>.  */
   BUILTIN_VDQ_BHSI (BINOP, smaxp, 0)
   BUILTIN_VDQ_BHSI (BINOP, sminp, 0)
   BUILTIN_VDQ_BHSI (BINOP, umaxp, 0)
   BUILTIN_VDQ_BHSI (BINOP, uminp, 0)
-  BUILTIN_VDQF (BINOP, smaxp, 0)
-  BUILTIN_VDQF (BINOP, sminp, 0)
-  BUILTIN_VDQF (BINOP, smax_nanp, 0)
-  BUILTIN_VDQF (BINOP, smin_nanp, 0)
+  BUILTIN_VHSDF (BINOP, smaxp, 0)
+  BUILTIN_VHSDF (BINOP, sminp, 0)
+  BUILTIN_VHSDF (BINOP, smax_nanp, 0)
+  BUILTIN_VHSDF (BINOP, smin_nanp, 0)
 
   /* Implemented by <frint_pattern><mode>2.  */
   BUILTIN_VHSDF (UNOP, btrunc, 2)
@@ -383,7 +383,7 @@
   BUILTIN_VDQ_SI (UNOP, urecpe, 0)
 
   BUILTIN_VHSDF (UNOP, frecpe, 0)
-  BUILTIN_VDQF (BINOP, frecps, 0)
+  BUILTIN_VHSDF (BINOP, frecps, 0)
 
   /* Implemented by a mixture of abs2 patterns.  Note the DImode builtin is
      only ever used for the int64x1_t intrinsic, there is no scalar version.  */
@@ -475,22 +475,22 @@
   BUILTIN_VSDQ_HSI (QUADOP_LANE, sqrdmlsh_laneq, 0)
 
   /* Implemented by <FCVT_F2FIXED/FIXED2F:fcvt_fixed_insn><*><*>3.  */
-  BUILTIN_VSDQ_SDI (SHIFTIMM, scvtf, 3)
-  BUILTIN_VSDQ_SDI (FCVTIMM_SUS, ucvtf, 3)
-  BUILTIN_VALLF (SHIFTIMM, fcvtzs, 3)
-  BUILTIN_VALLF (SHIFTIMM_USS, fcvtzu, 3)
+  BUILTIN_VSDQ_HSDI (SHIFTIMM, scvtf, 3)
+  BUILTIN_VSDQ_HSDI (FCVTIMM_SUS, ucvtf, 3)
+  BUILTIN_VHSDF_SDF (SHIFTIMM, fcvtzs, 3)
+  BUILTIN_VHSDF_SDF (SHIFTIMM_USS, fcvtzu, 3)
 
   /* Implemented by aarch64_rsqrte<mode>.  */
   BUILTIN_VHSDF_SDF (UNOP, rsqrte, 0)
 
   /* Implemented by aarch64_rsqrts<mode>.  */
-  BUILTIN_VALLF (BINOP, rsqrts, 0)
+  BUILTIN_VHSDF_SDF (BINOP, rsqrts, 0)
 
   /* Implemented by fabd<mode>3.  */
-  BUILTIN_VALLF (BINOP, fabd, 3)
+  BUILTIN_VHSDF_SDF (BINOP, fabd, 3)
 
   /* Implemented by aarch64_faddp<mode>.  */
-  BUILTIN_VDQF (BINOP, faddp, 0)
+  BUILTIN_VHSDF (BINOP, faddp, 0)
 
   /* Implemented by aarch64_cm<optab><mode>.  */
   BUILTIN_VHSDF_SDF (BINOP_USS, cmeq, 0)
@@ -501,3 +501,9 @@
 
   /* Implemented by neg<mode>2.  */
   BUILTIN_VHSDF (UNOP, neg, 2)
+
+  /* Implemented by aarch64_fac<optab><mode>.  */
+  BUILTIN_VHSDF_SDF (BINOP_USS, faclt, 0)
+  BUILTIN_VHSDF_SDF (BINOP_USS, facle, 0)
+  BUILTIN_VHSDF_SDF (BINOP_USS, facgt, 0)
+  BUILTIN_VHSDF_SDF (BINOP_USS, facge, 0)

gcc/config/aarch64/aarch64-simd.md

@@ -391,13 +391,13 @@
   [(set_attr "type" "neon_fp_rsqrte_<stype><q>")])
 
 (define_insn "aarch64_rsqrts<mode>"
-  [(set (match_operand:VALLF 0 "register_operand" "=w")
-	(unspec:VALLF [(match_operand:VALLF 1 "register_operand" "w")
-	       (match_operand:VALLF 2 "register_operand" "w")]
+  [(set (match_operand:VHSDF_SDF 0 "register_operand" "=w")
+	(unspec:VHSDF_SDF [(match_operand:VHSDF_SDF 1 "register_operand" "w")
+			   (match_operand:VHSDF_SDF 2 "register_operand" "w")]
 	 UNSPEC_RSQRTS))]
   "TARGET_SIMD"
   "frsqrts\\t%<v>0<Vmtype>, %<v>1<Vmtype>, %<v>2<Vmtype>"
-  [(set_attr "type" "neon_fp_rsqrts_<Vetype><q>")])
+  [(set_attr "type" "neon_fp_rsqrts_<stype><q>")])
 
 (define_expand "rsqrt<mode>2"
   [(set (match_operand:VALLF 0 "register_operand" "=w")
@@ -475,14 +475,14 @@
 )
 
 (define_insn "fabd<mode>3"
-  [(set (match_operand:VALLF 0 "register_operand" "=w")
-	(abs:VALLF
-	  (minus:VALLF
-	    (match_operand:VALLF 1 "register_operand" "w")
-	    (match_operand:VALLF 2 "register_operand" "w"))))]
+  [(set (match_operand:VHSDF_SDF 0 "register_operand" "=w")
+	(abs:VHSDF_SDF
+	  (minus:VHSDF_SDF
+	    (match_operand:VHSDF_SDF 1 "register_operand" "w")
+	    (match_operand:VHSDF_SDF 2 "register_operand" "w"))))]
   "TARGET_SIMD"
   "fabd\t%<v>0<Vmtype>, %<v>1<Vmtype>, %<v>2<Vmtype>"
-  [(set_attr "type" "neon_fp_abd_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_abd_<stype><q>")]
 )
 
 (define_insn "and<mode>3"
@@ -1105,9 +1105,9 @@
 
 ;; Pairwise FP Max/Min operations.
 (define_insn "aarch64_<maxmin_uns>p<mode>"
- [(set (match_operand:VDQF 0 "register_operand" "=w")
-       (unspec:VDQF [(match_operand:VDQF 1 "register_operand" "w")
-		     (match_operand:VDQF 2 "register_operand" "w")]
+ [(set (match_operand:VHSDF 0 "register_operand" "=w")
+       (unspec:VHSDF [(match_operand:VHSDF 1 "register_operand" "w")
+		      (match_operand:VHSDF 2 "register_operand" "w")]
 		      FMAXMINV))]
  "TARGET_SIMD"
  "<maxmin_uns_op>p\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
@@ -1517,36 +1517,36 @@
 ;; FP arithmetic operations.
 
 (define_insn "add<mode>3"
- [(set (match_operand:VDQF 0 "register_operand" "=w")
-       (plus:VDQF (match_operand:VDQF 1 "register_operand" "w")
-		  (match_operand:VDQF 2 "register_operand" "w")))]
+ [(set (match_operand:VHSDF 0 "register_operand" "=w")
+       (plus:VHSDF (match_operand:VHSDF 1 "register_operand" "w")
+		   (match_operand:VHSDF 2 "register_operand" "w")))]
  "TARGET_SIMD"
  "fadd\\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
-  [(set_attr "type" "neon_fp_addsub_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_addsub_<stype><q>")]
 )
 
 (define_insn "sub<mode>3"
- [(set (match_operand:VDQF 0 "register_operand" "=w")
-       (minus:VDQF (match_operand:VDQF 1 "register_operand" "w")
-		   (match_operand:VDQF 2 "register_operand" "w")))]
+ [(set (match_operand:VHSDF 0 "register_operand" "=w")
+       (minus:VHSDF (match_operand:VHSDF 1 "register_operand" "w")
+		    (match_operand:VHSDF 2 "register_operand" "w")))]
  "TARGET_SIMD"
  "fsub\\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
-  [(set_attr "type" "neon_fp_addsub_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_addsub_<stype><q>")]
 )
 
 (define_insn "mul<mode>3"
- [(set (match_operand:VDQF 0 "register_operand" "=w")
-       (mult:VDQF (match_operand:VDQF 1 "register_operand" "w")
-		  (match_operand:VDQF 2 "register_operand" "w")))]
+ [(set (match_operand:VHSDF 0 "register_operand" "=w")
+       (mult:VHSDF (match_operand:VHSDF 1 "register_operand" "w")
+		   (match_operand:VHSDF 2 "register_operand" "w")))]
  "TARGET_SIMD"
  "fmul\\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
-  [(set_attr "type" "neon_fp_mul_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_mul_<stype><q>")]
 )
 
 (define_expand "div<mode>3"
- [(set (match_operand:VDQF 0 "register_operand")
-       (div:VDQF (match_operand:VDQF 1 "general_operand")
-		 (match_operand:VDQF 2 "register_operand")))]
+ [(set (match_operand:VHSDF 0 "register_operand" "=w")
+       (div:VHSDF (match_operand:VHSDF 1 "register_operand" "w")
+		  (match_operand:VHSDF 2 "register_operand" "w")))]
  "TARGET_SIMD"
 {
   if (aarch64_emit_approx_div (operands[0], operands[1], operands[2]))
@@ -1556,12 +1556,12 @@
 })
 
 (define_insn "*div<mode>3"
- [(set (match_operand:VDQF 0 "register_operand" "=w")
-       (div:VDQF (match_operand:VDQF 1 "register_operand" "w")
-		 (match_operand:VDQF 2 "register_operand" "w")))]
+ [(set (match_operand:VHSDF 0 "register_operand" "=w")
+       (div:VHSDF (match_operand:VHSDF 1 "register_operand" "w")
+		 (match_operand:VHSDF 2 "register_operand" "w")))]
  "TARGET_SIMD"
  "fdiv\\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
-  [(set_attr "type" "neon_fp_div_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_div_<stype><q>")]
 )
 
 (define_insn "neg<mode>2"
@@ -1826,24 +1826,26 @@
 
 ;; Convert between fixed-point and floating-point (vector modes)
 
-(define_insn "<FCVT_F2FIXED:fcvt_fixed_insn><VDQF:mode>3"
-  [(set (match_operand:<VDQF:FCVT_TARGET> 0 "register_operand" "=w")
-	(unspec:<VDQF:FCVT_TARGET> [(match_operand:VDQF 1 "register_operand" "w")
+(define_insn "<FCVT_F2FIXED:fcvt_fixed_insn><VHSDF:mode>3"
+  [(set (match_operand:<VHSDF:FCVT_TARGET> 0 "register_operand" "=w")
+	(unspec:<VHSDF:FCVT_TARGET>
+	  [(match_operand:VHSDF 1 "register_operand" "w")
 	   (match_operand:SI 2 "immediate_operand" "i")]
 	 FCVT_F2FIXED))]
   "TARGET_SIMD"
   "<FCVT_F2FIXED:fcvt_fixed_insn>\t%<v>0<Vmtype>, %<v>1<Vmtype>, #%2"
-  [(set_attr "type" "neon_fp_to_int_<VDQF:Vetype><q>")]
+  [(set_attr "type" "neon_fp_to_int_<VHSDF:stype><q>")]
 )
 
-(define_insn "<FCVT_FIXED2F:fcvt_fixed_insn><VDQ_SDI:mode>3"
-  [(set (match_operand:<VDQ_SDI:FCVT_TARGET> 0 "register_operand" "=w")
-	(unspec:<VDQ_SDI:FCVT_TARGET> [(match_operand:VDQ_SDI 1 "register_operand" "w")
+(define_insn "<FCVT_FIXED2F:fcvt_fixed_insn><VDQ_HSDI:mode>3"
+  [(set (match_operand:<VDQ_HSDI:FCVT_TARGET> 0 "register_operand" "=w")
+	(unspec:<VDQ_HSDI:FCVT_TARGET>
+	  [(match_operand:VDQ_HSDI 1 "register_operand" "w")
 	   (match_operand:SI 2 "immediate_operand" "i")]
 	 FCVT_FIXED2F))]
   "TARGET_SIMD"
   "<FCVT_FIXED2F:fcvt_fixed_insn>\t%<v>0<Vmtype>, %<v>1<Vmtype>, #%2"
-  [(set_attr "type" "neon_int_to_fp_<VDQ_SDI:Vetype><q>")]
+  [(set_attr "type" "neon_int_to_fp_<VDQ_HSDI:stype><q>")]
 )
 
 ;; ??? Note that the vectorizer usage of the vec_unpacks_[lo/hi] patterns
@@ -2002,33 +2004,33 @@
 ;; NaNs.
 
 (define_insn "<su><maxmin><mode>3"
-  [(set (match_operand:VDQF 0 "register_operand" "=w")
-        (FMAXMIN:VDQF (match_operand:VDQF 1 "register_operand" "w")
-		   (match_operand:VDQF 2 "register_operand" "w")))]
+  [(set (match_operand:VHSDF 0 "register_operand" "=w")
+	(FMAXMIN:VHSDF (match_operand:VHSDF 1 "register_operand" "w")
+		       (match_operand:VHSDF 2 "register_operand" "w")))]
   "TARGET_SIMD"
   "f<maxmin>nm\\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
-  [(set_attr "type" "neon_fp_minmax_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_minmax_<stype><q>")]
 )
 
 (define_insn "<maxmin_uns><mode>3"
-  [(set (match_operand:VDQF 0 "register_operand" "=w")
-       (unspec:VDQF [(match_operand:VDQF 1 "register_operand" "w")
-		     (match_operand:VDQF 2 "register_operand" "w")]
+  [(set (match_operand:VHSDF 0 "register_operand" "=w")
+       (unspec:VHSDF [(match_operand:VHSDF 1 "register_operand" "w")
+		      (match_operand:VHSDF 2 "register_operand" "w")]
 		      FMAXMIN_UNS))]
   "TARGET_SIMD"
   "<maxmin_uns_op>\\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
-  [(set_attr "type" "neon_fp_minmax_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_minmax_<stype><q>")]
 )
 
 ;; Auto-vectorized forms for the IEEE-754 fmax()/fmin() functions
 (define_insn "<fmaxmin><mode>3"
-  [(set (match_operand:VDQF 0 "register_operand" "=w")
-	(unspec:VDQF [(match_operand:VDQF 1 "register_operand" "w")
-		      (match_operand:VDQF 2 "register_operand" "w")]
+  [(set (match_operand:VHSDF 0 "register_operand" "=w")
+	(unspec:VHSDF [(match_operand:VHSDF 1 "register_operand" "w")
+		       (match_operand:VHSDF 2 "register_operand" "w")]
 		       FMAXMIN))]
   "TARGET_SIMD"
   "<fmaxmin_op>\\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
-  [(set_attr "type" "neon_fp_minmax_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_minmax_<stype><q>")]
 )
 
 ;; 'across lanes' add.
@@ -2048,13 +2050,13 @@
 )
 
 (define_insn "aarch64_faddp<mode>"
- [(set (match_operand:VDQF 0 "register_operand" "=w")
-       (unspec:VDQF [(match_operand:VDQF 1 "register_operand" "w")
-		     (match_operand:VDQF 2 "register_operand" "w")]
+ [(set (match_operand:VHSDF 0 "register_operand" "=w")
+       (unspec:VHSDF [(match_operand:VHSDF 1 "register_operand" "w")
+		      (match_operand:VHSDF 2 "register_operand" "w")]
 	UNSPEC_FADDV))]
  "TARGET_SIMD"
  "faddp\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
-  [(set_attr "type" "neon_fp_reduc_add_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_reduc_add_<stype><q>")]
 )
 
 (define_insn "aarch64_reduc_plus_internal<mode>"
@@ -3050,13 +3052,14 @@
 ;; fmulx.
 
 (define_insn "aarch64_fmulx<mode>"
-  [(set (match_operand:VALLF 0 "register_operand" "=w")
-	(unspec:VALLF [(match_operand:VALLF 1 "register_operand" "w")
-		       (match_operand:VALLF 2 "register_operand" "w")]
+  [(set (match_operand:VHSDF_SDF 0 "register_operand" "=w")
+	(unspec:VHSDF_SDF
+	  [(match_operand:VHSDF_SDF 1 "register_operand" "w")
+	   (match_operand:VHSDF_SDF 2 "register_operand" "w")]
 	   UNSPEC_FMULX))]
  "TARGET_SIMD"
  "fmulx\t%<v>0<Vmtype>, %<v>1<Vmtype>, %<v>2<Vmtype>"
- [(set_attr "type" "neon_fp_mul_<Vetype>")]
+ [(set_attr "type" "neon_fp_mul_<stype>")]
 )
 
 ;; vmulxq_lane_f32, and vmulx_laneq_f32
@@ -4310,16 +4313,18 @@
 ;; Note we can also handle what would be fac(le|lt) by
 ;; generating fac(ge|gt).
 
-(define_insn "*aarch64_fac<optab><mode>"
+(define_insn "aarch64_fac<optab><mode>"
   [(set (match_operand:<V_cmp_result> 0 "register_operand" "=w")
 	(neg:<V_cmp_result>
 	  (FAC_COMPARISONS:<V_cmp_result>
-	    (abs:VALLF (match_operand:VALLF 1 "register_operand" "w"))
-	    (abs:VALLF (match_operand:VALLF 2 "register_operand" "w"))
+	    (abs:VHSDF_SDF
+	      (match_operand:VHSDF_SDF 1 "register_operand" "w"))
+	    (abs:VHSDF_SDF
+	      (match_operand:VHSDF_SDF 2 "register_operand" "w"))
   )))]
   "TARGET_SIMD"
   "fac<n_optab>\t%<v>0<Vmtype>, %<v><cmp_1><Vmtype>, %<v><cmp_2><Vmtype>"
-  [(set_attr "type" "neon_fp_compare_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_compare_<stype><q>")]
 )
 
 ;; addp
@@ -5431,13 +5436,14 @@
 )
 
 (define_insn "aarch64_frecps<mode>"
-  [(set (match_operand:VALLF 0 "register_operand" "=w")
-	(unspec:VALLF [(match_operand:VALLF 1 "register_operand" "w")
-		     (match_operand:VALLF 2 "register_operand" "w")]
+  [(set (match_operand:VHSDF_SDF 0 "register_operand" "=w")
+	(unspec:VHSDF_SDF
+	  [(match_operand:VHSDF_SDF 1 "register_operand" "w")
+	  (match_operand:VHSDF_SDF 2 "register_operand" "w")]
 	  UNSPEC_FRECPS))]
   "TARGET_SIMD"
   "frecps\\t%<v>0<Vmtype>, %<v>1<Vmtype>, %<v>2<Vmtype>"
-  [(set_attr "type" "neon_fp_recps_<Vetype><q>")]
+  [(set_attr "type" "neon_fp_recps_<stype><q>")]
 )
 
 (define_insn "aarch64_urecpe<mode>"

gcc/config/aarch64/aarch64.c

@@ -7604,6 +7604,10 @@ bool
 aarch64_emit_approx_div (rtx quo, rtx num, rtx den)
 {
   machine_mode mode = GET_MODE (quo);
+
+  if (GET_MODE_INNER (mode) == HFmode)
+    return false;
+
   bool use_approx_division_p = (flag_mlow_precision_div
 			        || (aarch64_tune_params.approx_modes->division
 				    & AARCH64_APPROX_MODE (mode)));

gcc/config/aarch64/arm_neon.h

@@ -26385,6 +26385,368 @@ vsqrtq_f16 (float16x8_t a)
   return __builtin_aarch64_sqrtv8hf (a);
 }
 
+/* ARMv8.2-A FP16 two operands vector intrinsics.  */
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vadd_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __a + __b;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vaddq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __a + __b;
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vabd_f16 (float16x4_t a, float16x4_t b)
+{
+  return __builtin_aarch64_fabdv4hf (a, b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vabdq_f16 (float16x8_t a, float16x8_t b)
+{
+  return __builtin_aarch64_fabdv8hf (a, b);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vcage_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_facgev4hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vcageq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_facgev8hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vcagt_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_facgtv4hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vcagtq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_facgtv8hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vcale_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_faclev4hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vcaleq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_faclev8hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vcalt_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_facltv4hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vcaltq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_facltv8hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vceq_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_cmeqv4hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vceqq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_cmeqv8hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vcge_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_cmgev4hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vcgeq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_cmgev8hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vcgt_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_cmgtv4hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vcgtq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_cmgtv8hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vcle_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_cmlev4hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vcleq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_cmlev8hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vclt_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_cmltv4hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vcltq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_cmltv8hf_uss (__a, __b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vcvt_n_f16_s16 (int16x4_t __a, const int __b)
+{
+  return __builtin_aarch64_scvtfv4hi (__a, __b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vcvtq_n_f16_s16 (int16x8_t __a, const int __b)
+{
+  return __builtin_aarch64_scvtfv8hi (__a, __b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vcvt_n_f16_u16 (uint16x4_t __a, const int __b)
+{
+  return __builtin_aarch64_ucvtfv4hi_sus (__a, __b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vcvtq_n_f16_u16 (uint16x8_t __a, const int __b)
+{
+  return __builtin_aarch64_ucvtfv8hi_sus (__a, __b);
+}
+
+__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
+vcvt_n_s16_f16 (float16x4_t __a, const int __b)
+{
+  return __builtin_aarch64_fcvtzsv4hf (__a, __b);
+}
+
+__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
+vcvtq_n_s16_f16 (float16x8_t __a, const int __b)
+{
+  return __builtin_aarch64_fcvtzsv8hf (__a, __b);
+}
+
+__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
+vcvt_n_u16_f16 (float16x4_t __a, const int __b)
+{
+  return __builtin_aarch64_fcvtzuv4hf_uss (__a, __b);
+}
+
+__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
+vcvtq_n_u16_f16 (float16x8_t __a, const int __b)
+{
+  return __builtin_aarch64_fcvtzuv8hf_uss (__a, __b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vdiv_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __a / __b;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vdivq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __a / __b;
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vmax_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_smax_nanv4hf (__a, __b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vmaxq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_smax_nanv8hf (__a, __b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vmaxnm_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_fmaxv4hf (__a, __b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vmaxnmq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_fmaxv8hf (__a, __b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vmin_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_smin_nanv4hf (__a, __b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vminq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_smin_nanv8hf (__a, __b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vminnm_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_fminv4hf (__a, __b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vminnmq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_fminv8hf (__a, __b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vmul_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __a * __b;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vmulq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __a * __b;
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vmulx_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_fmulxv4hf (__a, __b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vmulxq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_fmulxv8hf (__a, __b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vpadd_f16 (float16x4_t a, float16x4_t b)
+{
+  return __builtin_aarch64_faddpv4hf (a, b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vpaddq_f16 (float16x8_t a, float16x8_t b)
+{
+  return __builtin_aarch64_faddpv8hf (a, b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vpmax_f16 (float16x4_t a, float16x4_t b)
+{
+  return __builtin_aarch64_smax_nanpv4hf (a, b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vpmaxq_f16 (float16x8_t a, float16x8_t b)
+{
+  return __builtin_aarch64_smax_nanpv8hf (a, b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vpmaxnm_f16 (float16x4_t a, float16x4_t b)
+{
+  return __builtin_aarch64_smaxpv4hf (a, b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vpmaxnmq_f16 (float16x8_t a, float16x8_t b)
+{
+  return __builtin_aarch64_smaxpv8hf (a, b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vpmin_f16 (float16x4_t a, float16x4_t b)
+{
+  return __builtin_aarch64_smin_nanpv4hf (a, b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vpminq_f16 (float16x8_t a, float16x8_t b)
+{
+  return __builtin_aarch64_smin_nanpv8hf (a, b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vpminnm_f16 (float16x4_t a, float16x4_t b)
+{
+  return __builtin_aarch64_sminpv4hf (a, b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vpminnmq_f16 (float16x8_t a, float16x8_t b)
+{
+  return __builtin_aarch64_sminpv8hf (a, b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vrecps_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __builtin_aarch64_frecpsv4hf (__a, __b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vrecpsq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __builtin_aarch64_frecpsv8hf (__a, __b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vrsqrts_f16 (float16x4_t a, float16x4_t b)
+{
+  return __builtin_aarch64_rsqrtsv4hf (a, b);
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vrsqrtsq_f16 (float16x8_t a, float16x8_t b)
+{
+  return __builtin_aarch64_rsqrtsv8hf (a, b);
+}
+
+__extension__ static __inline float16x4_t __attribute__ ((__always_inline__))
+vsub_f16 (float16x4_t __a, float16x4_t __b)
+{
+  return __a - __b;
+}
+
+__extension__ static __inline float16x8_t __attribute__ ((__always_inline__))
+vsubq_f16 (float16x8_t __a, float16x8_t __b)
+{
+  return __a - __b;
+}
+
 #pragma GCC pop_options
 
 #undef __aarch64_vget_lane_any

gcc/config/aarch64/iterators.md

@@ -166,9 +166,19 @@
 ;; Vector modes for S and D
 (define_mode_iterator VDQ_SDI [V2SI V4SI V2DI])
 
+;; Vector modes for H, S and D
+(define_mode_iterator VDQ_HSDI [(V4HI "TARGET_SIMD_F16INST")
+				(V8HI "TARGET_SIMD_F16INST")
+				V2SI V4SI V2DI])
+
 ;; Scalar and Vector modes for S and D
 (define_mode_iterator VSDQ_SDI [V2SI V4SI V2DI SI DI])
 
+;; Scalar and Vector modes for S and D, Vector modes for H.
+(define_mode_iterator VSDQ_HSDI [(V4HI "TARGET_SIMD_F16INST")
+				 (V8HI "TARGET_SIMD_F16INST")
+				 V2SI V4SI V2DI SI DI])
+
 ;; Vector modes for Q and H types.
 (define_mode_iterator VDQQH [V8QI V16QI V4HI V8HI])