[AArch64] Add basic FP16 support

gcc/:

	* config/aarch64/aarch64-builtins.c (aarch64_fp16_type_node): New.
	(aarch64_init_builtins): Make aarch64_fp16_type_node, use for __fp16.

	* config/aarch64/aarch64-modes.def: Add HFmode.

	* config/aarch64/aarch64.h (TARGET_CPU_CPP_BUILTINS): Define
	__ARM_FP16_FORMAT_IEEE and __ARM_FP16_ARGS. Set bit 1 of __ARM_FP.

	* config/aarch64/aarch64.c (aarch64_init_libfuncs,
	aarch64_promoted_type): New.

	(aarch64_float_const_representable_p): Disable HFmode.
	(aarch64_mangle_type): Mangle half-precision floats to "Dh".
	(TARGET_PROMOTED_TYPE): Define to aarch64_promoted_type.
	(TARGET_INIT_LIBFUNCS): Define to aarch64_init_libfuncs.

	* config/aarch64/aarch64.md (mov<mode>): Include HFmode using GPF_F16.
	(movhf_aarch64, extendhfsf2, extendhfdf2, truncsfhf2, truncdfhf2): New.

	* config/aarch64/iterators.md (GPF_F16): New.

gcc/testsuite/:

	* gcc.target/aarch64/f16_movs_1.c: New test.

From-SVN: r226346

gcc/ChangeLog

+2015-07-29  Alan Lawrence  <alan.lawrence@arm.com>
+
+	* config/aarch64/aarch64-builtins.c (aarch64_fp16_type_node): New.
+	(aarch64_init_builtins): Make aarch64_fp16_type_node, use for __fp16.
+
+	* config/aarch64/aarch64-modes.def: Add HFmode.
+
+	* config/aarch64/aarch64.h (TARGET_CPU_CPP_BUILTINS): Define
+	__ARM_FP16_FORMAT_IEEE and __ARM_FP16_ARGS. Set bit 1 of __ARM_FP.
+
+	* config/aarch64/aarch64.c (aarch64_init_libfuncs,
+	aarch64_promoted_type): New.
+
+	(aarch64_float_const_representable_p): Disable HFmode.
+	(aarch64_mangle_type): Mangle half-precision floats to "Dh".
+	(TARGET_PROMOTED_TYPE): Define to aarch64_promoted_type.
+	(TARGET_INIT_LIBFUNCS): Define to aarch64_init_libfuncs.
+
+	* config/aarch64/aarch64.md (mov<mode>): Include HFmode using GPF_F16.
+	(movhf_aarch64, extendhfsf2, extendhfdf2, truncsfhf2, truncdfhf2): New.
+
+	* config/aarch64/iterators.md (GPF_F16): New.
+
 2015-07-29  Richard Biener  <rguenther@suse.de>
 
 	* match.pd: Merge address comparison patterns and make them

gcc/config/aarch64/aarch64-builtins.c

@@ -436,6 +436,9 @@ static struct aarch64_simd_type_info aarch64_simd_types [] = {
 };
 #undef ENTRY
 
+/* This type is not SIMD-specific; it is the user-visible __fp16.  */
+static tree aarch64_fp16_type_node = NULL_TREE;
+
 static tree aarch64_simd_intOI_type_node = NULL_TREE;
 static tree aarch64_simd_intEI_type_node = NULL_TREE;
 static tree aarch64_simd_intCI_type_node = NULL_TREE;
@@ -846,6 +849,12 @@ aarch64_init_builtins (void)
     = add_builtin_function ("__builtin_aarch64_set_fpsr", ftype_set_fpr,
 			    AARCH64_BUILTIN_SET_FPSR, BUILT_IN_MD, NULL, NULL_TREE);
 
+  aarch64_fp16_type_node = make_node (REAL_TYPE);
+  TYPE_PRECISION (aarch64_fp16_type_node) = 16;
+  layout_type (aarch64_fp16_type_node);
+
+  (*lang_hooks.types.register_builtin_type) (aarch64_fp16_type_node, "__fp16");
+
   if (TARGET_SIMD)
     aarch64_init_simd_builtins ();
   if (TARGET_CRC32)

gcc/config/aarch64/aarch64-modes.def

@@ -36,6 +36,10 @@ CC_MODE (CC_DLTU);
 CC_MODE (CC_DGEU);
 CC_MODE (CC_DGTU);
 
+/* Half-precision floating point for __fp16.  */
+FLOAT_MODE (HF, 2, 0);
+ADJUST_FLOAT_FORMAT (HF, &ieee_half_format);
+
 /* Vector modes.  */
 VECTOR_MODES (INT, 8);        /*       V8QI V4HI V2SI.  */
 VECTOR_MODES (INT, 16);       /* V16QI V8HI V4SI V2DI.  */

gcc/config/aarch64/aarch64.c

@@ -8700,6 +8700,10 @@ aarch64_mangle_type (const_tree type)
   if (lang_hooks.types_compatible_p (CONST_CAST_TREE (type), va_list_type))
     return "St9__va_list";
 
+  /* Half-precision float.  */
+  if (TREE_CODE (type) == REAL_TYPE && TYPE_PRECISION (type) == 16)
+    return "Dh";
+
   /* Mangle AArch64-specific internal types.  TYPE_NAME is non-NULL_TREE for
      builtin types.  */
   if (TYPE_NAME (type) != NULL)
@@ -9940,6 +9944,33 @@ aarch64_start_file (void)
   default_file_start();
 }
 
+static void
+aarch64_init_libfuncs (void)
+{
+   /* Half-precision float operations.  The compiler handles all operations
+     with NULL libfuncs by converting to SFmode.  */
+
+  /* Conversions.  */
+  set_conv_libfunc (trunc_optab, HFmode, SFmode, "__gnu_f2h_ieee");
+  set_conv_libfunc (sext_optab, SFmode, HFmode, "__gnu_h2f_ieee");
+
+  /* Arithmetic.  */
+  set_optab_libfunc (add_optab, HFmode, NULL);
+  set_optab_libfunc (sdiv_optab, HFmode, NULL);
+  set_optab_libfunc (smul_optab, HFmode, NULL);
+  set_optab_libfunc (neg_optab, HFmode, NULL);
+  set_optab_libfunc (sub_optab, HFmode, NULL);
+
+  /* Comparisons.  */
+  set_optab_libfunc (eq_optab, HFmode, NULL);
+  set_optab_libfunc (ne_optab, HFmode, NULL);
+  set_optab_libfunc (lt_optab, HFmode, NULL);
+  set_optab_libfunc (le_optab, HFmode, NULL);
+  set_optab_libfunc (ge_optab, HFmode, NULL);
+  set_optab_libfunc (gt_optab, HFmode, NULL);
+  set_optab_libfunc (unord_optab, HFmode, NULL);
+}
+
 /* Target hook for c_mode_for_suffix.  */
 static machine_mode
 aarch64_c_mode_for_suffix (char suffix)
@@ -9978,7 +10009,8 @@ aarch64_float_const_representable_p (rtx x)
   if (!CONST_DOUBLE_P (x))
     return false;
 
-  if (GET_MODE (x) == VOIDmode)
+  /* We don't support HFmode constants yet.  */
+  if (GET_MODE (x) == VOIDmode || GET_MODE (x) == HFmode)
     return false;
 
   REAL_VALUE_FROM_CONST_DOUBLE (r, x);
@@ -11940,6 +11972,14 @@ aarch64_unspec_may_trap_p (const_rtx x, unsigned flags)
   return default_unspec_may_trap_p (x, flags);
 }
 
+/* Implement TARGET_PROMOTED_TYPE to promote __fp16 to float.  */
+static tree
+aarch64_promoted_type (const_tree t)
+{
+  if (SCALAR_FLOAT_TYPE_P (t) && TYPE_PRECISION (t) == 16)
+    return float_type_node;
+  return NULL_TREE;
+}
 #undef TARGET_ADDRESS_COST
 #define TARGET_ADDRESS_COST aarch64_address_cost
 
@@ -12094,6 +12134,9 @@ aarch64_unspec_may_trap_p (const_rtx x, unsigned flags)
 #undef TARGET_SCHED_REASSOCIATION_WIDTH
 #define TARGET_SCHED_REASSOCIATION_WIDTH aarch64_reassociation_width
 
+#undef TARGET_PROMOTED_TYPE
+#define TARGET_PROMOTED_TYPE aarch64_promoted_type
+
 #undef TARGET_SECONDARY_RELOAD
 #define TARGET_SECONDARY_RELOAD aarch64_secondary_reload
 
@@ -12186,6 +12229,8 @@ aarch64_unspec_may_trap_p (const_rtx x, unsigned flags)
 #define TARGET_VECTORIZE_VEC_PERM_CONST_OK \
   aarch64_vectorize_vec_perm_const_ok
 
+#undef TARGET_INIT_LIBFUNCS
+#define TARGET_INIT_LIBFUNCS aarch64_init_libfuncs
 
 #undef TARGET_FIXED_CONDITION_CODE_REGS
 #define TARGET_FIXED_CONDITION_CODE_REGS aarch64_fixed_condition_code_regs

gcc/config/aarch64/aarch64.h

@@ -61,7 +61,9 @@
       if (TARGET_FLOAT)                                         \
         {                                                       \
           builtin_define ("__ARM_FEATURE_FMA");                 \
-          builtin_define_with_int_value ("__ARM_FP", 0x0C);     \
+	  builtin_define_with_int_value ("__ARM_FP", 0x0E);     \
+	  builtin_define ("__ARM_FP16_FORMAT_IEEE");		\
+	  builtin_define ("__ARM_FP16_ARGS");			\
         }                                                       \
       if (TARGET_SIMD)                                          \
         {                                                       \

gcc/config/aarch64/aarch64.md

@@ -978,8 +978,8 @@
 })
 
 (define_expand "mov<mode>"
-  [(set (match_operand:GPF 0 "nonimmediate_operand" "")
-	(match_operand:GPF 1 "general_operand" ""))]
+  [(set (match_operand:GPF_F16 0 "nonimmediate_operand" "")
+	(match_operand:GPF_F16 1 "general_operand" ""))]
   ""
   {
     if (!TARGET_FLOAT)
@@ -995,6 +995,26 @@
   }
 )
 
+(define_insn "*movhf_aarch64"
+  [(set (match_operand:HF 0 "nonimmediate_operand" "=w, ?r,w,w,m,r,m ,r")
+	(match_operand:HF 1 "general_operand"      "?rY, w,w,m,w,m,rY,r"))]
+  "TARGET_FLOAT && (register_operand (operands[0], HFmode)
+    || register_operand (operands[1], HFmode))"
+  "@
+   mov\\t%0.h[0], %w1
+   umov\\t%w0, %1.h[0]
+   mov\\t%0.h[0], %1.h[0]
+   ldr\\t%h0, %1
+   str\\t%h1, %0
+   ldrh\\t%w0, %1
+   strh\\t%w1, %0
+   mov\\t%w0, %w1"
+  [(set_attr "type" "neon_from_gp,neon_to_gp,fmov,\
+                     f_loads,f_stores,load1,store1,mov_reg")
+   (set_attr "simd" "yes,yes,yes,*,*,*,*,*")
+   (set_attr "fp"   "*,*,*,yes,yes,*,*,*")]
+)
+
 (define_insn "*movsf_aarch64"
   [(set (match_operand:SF 0 "nonimmediate_operand" "=w, ?r,w,w  ,w,m,r,m ,r")
 	(match_operand:SF 1 "general_operand"      "?rY, w,w,Ufc,m,w,m,rY,r"))]
@@ -4093,6 +4113,22 @@
   [(set_attr "type" "f_cvt")]
 )
 
+(define_insn "extendhfsf2"
+  [(set (match_operand:SF 0 "register_operand" "=w")
+        (float_extend:SF (match_operand:HF 1 "register_operand" "w")))]
+  "TARGET_FLOAT"
+  "fcvt\\t%s0, %h1"
+  [(set_attr "type" "f_cvt")]
+)
+
+(define_insn "extendhfdf2"
+  [(set (match_operand:DF 0 "register_operand" "=w")
+        (float_extend:DF (match_operand:HF 1 "register_operand" "w")))]
+  "TARGET_FLOAT"
+  "fcvt\\t%d0, %h1"
+  [(set_attr "type" "f_cvt")]
+)
+
 (define_insn "truncdfsf2"
   [(set (match_operand:SF 0 "register_operand" "=w")
         (float_truncate:SF (match_operand:DF 1 "register_operand" "w")))]
@@ -4101,6 +4137,22 @@
   [(set_attr "type" "f_cvt")]
 )
 
+(define_insn "truncsfhf2"
+  [(set (match_operand:HF 0 "register_operand" "=w")
+        (float_truncate:HF (match_operand:SF 1 "register_operand" "w")))]
+  "TARGET_FLOAT"
+  "fcvt\\t%h0, %s1"
+  [(set_attr "type" "f_cvt")]
+)
+
+(define_insn "truncdfhf2"
+  [(set (match_operand:HF 0 "register_operand" "=w")
+        (float_truncate:HF (match_operand:DF 1 "register_operand" "w")))]
+  "TARGET_FLOAT"
+  "fcvt\\t%h0, %d1"
+  [(set_attr "type" "f_cvt")]
+)
+
 (define_insn "fix_trunc<GPF:mode><GPI:mode>2"
   [(set (match_operand:GPI 0 "register_operand" "=r")
         (fix:GPI (match_operand:GPF 1 "register_operand" "w")))]

gcc/config/aarch64/iterators.md

@@ -38,6 +38,9 @@
 ;; Iterator for General Purpose Floating-point registers (32- and 64-bit modes)
 (define_mode_iterator GPF [SF DF])
 
+;; Iterator for General Purpose Float registers, inc __fp16.
+(define_mode_iterator GPF_F16 [HF SF DF])
+
 ;; Integer vector modes.
 (define_mode_iterator VDQ_I [V8QI V16QI V4HI V8HI V2SI V4SI V2DI])
 

gcc/testsuite/ChangeLog

+2015-07-29  Alan Lawrence  <alan.lawrence@arm.com>
+
+	* gcc.target/aarch64/f16_movs_1.c: New test.
+
 2015-07-28  Tom de Vries  <tom@codesourcery.com>
 
 	* gcc.dg/autopar/uns-outer-4.c: Remove xfail on scan for parallelizing

gcc/testsuite/gcc.target/aarch64/f16_movs_1.c

+/* { dg-do run } */
+/* { dg-options "-fno-inline -O2" } */
+
+#include <arm_neon.h>
+
+__fp16
+func2 (__fp16 a, __fp16 b)
+{
+  return b;
+}
+
+int
+main (int argc, char **argv)
+{
+  __fp16 array[16];
+  int i;
+
+  for (i = 0; i < sizeof (array) / sizeof (array[0]); i++)
+    array[i] = i;
+
+  array[0] = func2 (array[1], array[2]);
+
+  __builtin_printf ("%f\n", array[0]); /* { dg-output "2.0" } */
+
+  return 0;
+}