[Patch AArch64 13/17] Enable _Float16 for AArch64

gcc/

	* config/aarch64/aarch64-c.c (aarch64_update_cpp_builtins): Update
	__FLT_EVAL_METHOD__ and __FLT_EVAL_METHOD_C99__ when we switch
	architecture levels.
	* config/aarch64/aarch64.c (aarch64_promoted_type): Only promote
	the aarch64_fp16_type_node, not all HFmode types.
	(aarch64_libgcc_floating_mode_supported_p): Support HFmode.
	(aarch64_scalar_mode_supported_p): Likewise.
	(aarch64_excess_precision): New.
	(TARGET_LIBGCC_FLOATING_MODE_SUPPORTED_P): Define.
	(TARGET_SCALAR_MODE_SUPPORTED_P): Likewise.
	(TARGET_C_EXCESS_PRECISION): Likewise.

gcc/testsuite/

	* gcc.target/aarch64/_Float16_1.c: New.
	* gcc.target/aarch64/_Float16_2.c: Likewise.
	* gcc.target/aarch64/_Float16_3.c: Likewise.

From-SVN: r242845

gcc/ChangeLog

 2016-11-24  James Greenhalgh  <james.greenhalgh@arm.com>
 
+	* config/aarch64/aarch64-c.c (aarch64_update_cpp_builtins): Update
+	__FLT_EVAL_METHOD__ and __FLT_EVAL_METHOD_C99__ when we switch
+	architecture levels.
+	* config/aarch64/aarch64.c (aarch64_promoted_type): Only promote
+	the aarch64_fp16_type_node, not all HFmode types.
+	(aarch64_libgcc_floating_mode_supported_p): Support HFmode.
+	(aarch64_scalar_mode_supported_p): Likewise.
+	(aarch64_excess_precision): New.
+	(TARGET_LIBGCC_FLOATING_MODE_SUPPORTED_P): Define.
+	(TARGET_SCALAR_MODE_SUPPORTED_P): Likewise.
+	(TARGET_C_EXCESS_PRECISION): Likewise.
+
+2016-11-24  James Greenhalgh  <james.greenhalgh@arm.com>
+
 	* config/aarch64/aarch64-c.c (aarch64_scalar_mode_supported_p): New.
 	(TARGET_SCALAR_MODE_SUPPORTED_P): Define.
 

gcc/config/aarch64/aarch64-c.c

@@ -133,6 +133,16 @@ aarch64_update_cpp_builtins (cpp_reader *pfile)
 
   aarch64_def_or_undef (TARGET_CRYPTO, "__ARM_FEATURE_CRYPTO", pfile);
   aarch64_def_or_undef (TARGET_SIMD_RDMA, "__ARM_FEATURE_QRDMX", pfile);
+
+  /* Not for ACLE, but required to keep "float.h" correct if we switch
+     target between implementations that do or do not support ARMv8.2-A
+     16-bit floating-point extensions.  */
+  cpp_undef (pfile, "__FLT_EVAL_METHOD__");
+  builtin_define_with_int_value ("__FLT_EVAL_METHOD__",
+				 c_flt_eval_method (true));
+  cpp_undef (pfile, "__FLT_EVAL_METHOD_C99__");
+  builtin_define_with_int_value ("__FLT_EVAL_METHOD_C99__",
+				 c_flt_eval_method (false));
 }
 
 /* Implement TARGET_CPU_CPP_BUILTINS.  */

gcc/config/aarch64/aarch64.c

@@ -14240,12 +14240,20 @@ aarch64_vec_fpconst_pow_of_2 (rtx x)
   return firstval;
 }
 
-/* Implement TARGET_PROMOTED_TYPE to promote __fp16 to float.  */
+/* Implement TARGET_PROMOTED_TYPE to promote 16-bit floating point types
+   to float.
+
+   __fp16 always promotes through this hook.
+   _Float16 may promote if TARGET_FLT_EVAL_METHOD is 16, but we do that
+   through the generic excess precision logic rather than here.  */
+
 static tree
 aarch64_promoted_type (const_tree t)
 {
-  if (SCALAR_FLOAT_TYPE_P (t) && TYPE_PRECISION (t) == 16)
+  if (SCALAR_FLOAT_TYPE_P (t)
+      && TYPE_MAIN_VARIANT (t) == aarch64_fp16_type_node)
     return float_type_node;
+
   return NULL_TREE;
 }
 
@@ -14265,6 +14273,17 @@ aarch64_optab_supported_p (int op, machine_mode mode1, machine_mode,
     }
 }
 
+/* Implement TARGET_LIBGCC_FLOATING_POINT_MODE_SUPPORTED_P - return TRUE
+   if MODE is HFmode, and punt to the generic implementation otherwise.  */
+
+static bool
+aarch64_libgcc_floating_mode_supported_p (machine_mode mode)
+{
+  return (mode == HFmode
+	  ? true
+	  : default_libgcc_floating_mode_supported_p (mode));
+}
+
 /* Implement TARGET_SCALAR_MODE_SUPPORTED_P - return TRUE
    if MODE is HFmode, and punt to the generic implementation otherwise.  */
 
@@ -14276,6 +14295,47 @@ aarch64_scalar_mode_supported_p (machine_mode mode)
 	  : default_scalar_mode_supported_p (mode));
 }
 
+/* Set the value of FLT_EVAL_METHOD.
+   ISO/IEC TS 18661-3 defines two values that we'd like to make use of:
+
+    0: evaluate all operations and constants, whose semantic type has at
+       most the range and precision of type float, to the range and
+       precision of float; evaluate all other operations and constants to
+       the range and precision of the semantic type;
+
+    N, where _FloatN is a supported interchange floating type
+       evaluate all operations and constants, whose semantic type has at
+       most the range and precision of _FloatN type, to the range and
+       precision of the _FloatN type; evaluate all other operations and
+       constants to the range and precision of the semantic type;
+
+   If we have the ARMv8.2-A extensions then we support _Float16 in native
+   precision, so we should set this to 16.  Otherwise, we support the type,
+   but want to evaluate expressions in float precision, so set this to
+   0.  */
+
+static enum flt_eval_method
+aarch64_excess_precision (enum excess_precision_type type)
+{
+  switch (type)
+    {
+      case EXCESS_PRECISION_TYPE_FAST:
+      case EXCESS_PRECISION_TYPE_STANDARD:
+	/* We can calculate either in 16-bit range and precision or
+	   32-bit range and precision.  Make that decision based on whether
+	   we have native support for the ARMv8.2-A 16-bit floating-point
+	   instructions or not.  */
+	return (TARGET_FP_F16INST
+		? FLT_EVAL_METHOD_PROMOTE_TO_FLOAT16
+		: FLT_EVAL_METHOD_PROMOTE_TO_FLOAT);
+      case EXCESS_PRECISION_TYPE_IMPLICIT:
+	return FLT_EVAL_METHOD_PROMOTE_TO_FLOAT16;
+      default:
+	gcc_unreachable ();
+    }
+  return FLT_EVAL_METHOD_UNPREDICTABLE;
+}
+
 #undef TARGET_ADDRESS_COST
 #define TARGET_ADDRESS_COST aarch64_address_cost
 
@@ -14354,6 +14414,9 @@ aarch64_scalar_mode_supported_p (machine_mode mode)
 #undef TARGET_BUILTIN_RECIPROCAL
 #define TARGET_BUILTIN_RECIPROCAL aarch64_builtin_reciprocal
 
+#undef TARGET_C_EXCESS_PRECISION
+#define TARGET_C_EXCESS_PRECISION aarch64_excess_precision
+
 #undef  TARGET_EXPAND_BUILTIN
 #define TARGET_EXPAND_BUILTIN aarch64_expand_builtin
 
@@ -14410,6 +14473,10 @@ aarch64_scalar_mode_supported_p (machine_mode mode)
 #undef TARGET_LIBGCC_CMP_RETURN_MODE
 #define TARGET_LIBGCC_CMP_RETURN_MODE aarch64_libgcc_cmp_return_mode
 
+#undef TARGET_LIBGCC_FLOATING_MODE_SUPPORTED_P
+#define TARGET_LIBGCC_FLOATING_MODE_SUPPORTED_P \
+aarch64_libgcc_floating_mode_supported_p
+
 #undef TARGET_MANGLE_TYPE
 #define TARGET_MANGLE_TYPE aarch64_mangle_type
 

gcc/testsuite/ChangeLog

 2016-11-24  James Greenhalgh  <james.greenhalgh@arm.com>
 
+	* gcc.target/aarch64/_Float16_1.c: New.
+	* gcc.target/aarch64/_Float16_2.c: Likewise.
+	* gcc.target/aarch64/_Float16_3.c: Likewise.
+
+2016-11-24  James Greenhalgh  <james.greenhalgh@arm.com>
+
 	* gcc.target/aarch64/floatdihf2_1.c: New.
 
 2016-11-24  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>

gcc/testsuite/gcc.target/aarch64/_Float16_1.c

+/* { dg-do compile } */
+/* { dg-options "-O3 -march=armv8.2-a+nofp16" } */
+
+#pragma GCC target ("arch=armv8.2-a+nofp16")
+
+_Float16
+foo_v8 (_Float16 x, _Float16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+__fp16
+bar_v8 (__fp16 x, __fp16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+#pragma GCC target ("arch=armv8.2-a+fp16")
+
+_Float16
+foo_v82 (_Float16 x, _Float16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+__fp16
+bar_v82 (__fp16 x, __fp16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+/* Test that we merge to FMA operations.  This indicates that we are not
+   making extraneous conversions between modes.  */
+
+/* Three FMA operations in 32-bit precision, from foo_v8, bar_v8, bar_v82.  */
+/* { dg-final { scan-assembler-times "fmadd\ts\[0-9\]\+" 3 } } */
+
+/* One FMA operation in 16-bit precision, from foo_v82.  */
+/* { dg-final { scan-assembler-times "fmadd\th\[0-9\]\+" 1 } } */
+
+/* Test that we are resetting the __FLT_EVAL_METHOD__.  */
+/* { dg-final { scan-assembler-times "mov\tw\[0-9\]\+, 16" 2 } } */
+/* { dg-final { scan-assembler-times "str\twzr" 2 } } */

gcc/testsuite/gcc.target/aarch64/_Float16_2.c

+/* { dg-do compile } */
+/* { dg-options "-O3 -march=armv8.2-a+nofp16 -fpermitted-flt-eval-methods=c11" } */
+
+#pragma GCC target ("arch=armv8.2-a+nofp16")
+
+_Float16
+foo_v8 (_Float16 x, _Float16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+__fp16
+bar_v8 (__fp16 x, __fp16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+#pragma GCC target ("arch=armv8.2-a+fp16")
+
+_Float16
+foo_v82 (_Float16 x, _Float16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+__fp16
+bar_v82 (__fp16 x, __fp16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+/* Test that we merge to FMA operations.  This indicates that we are not
+   making extraneous conversions between modes.  */
+
+/* Three FMA operations in 32-bit precision, from foo_v8, bar_v8, bar_v82.  */
+/* { dg-final { scan-assembler-times "fmadd\ts\[0-9\]\+" 3 } } */
+
+/* One FMA operation in 16-bit precision, from foo_v82.  */
+/* { dg-final { scan-assembler-times "fmadd\th\[0-9\]\+" 1 } } */
+
+/* Test that in -fpermitted-flt-eval-methods=c11 we don't set the
+   __FLT_EVAL_METHOD__ to anything other than 0.  */
+/* { dg-final { scan-assembler-times "str\twzr" 4 } } */

gcc/testsuite/gcc.target/aarch64/_Float16_3.c

+/* { dg-do compile } */
+/* { dg-options "-O3 -march=armv8.2-a+nofp16 -std=c11 -ffp-contract=fast" } */
+
+#pragma GCC target ("arch=armv8.2-a+nofp16")
+
+_Float16
+foo_v8 (_Float16 x, _Float16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+__fp16
+bar_v8 (__fp16 x, __fp16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+#pragma GCC target ("arch=armv8.2-a+fp16")
+
+_Float16
+foo_v82 (_Float16 x, _Float16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+__fp16
+bar_v82 (__fp16 x, __fp16 y, unsigned int *eval)
+{
+  *eval = __FLT_EVAL_METHOD__;
+  return x * x + y;
+}
+
+/* Test that we merge to FMA operations.  This indicates that we are not
+   making extraneous conversions between modes.  */
+
+/* Three FMA operations in 32-bit precision, from foo_v8, bar_v8, bar_v82.  */
+/* { dg-final { scan-assembler-times "fmadd\ts\[0-9\]\+" 3 } } */
+
+/* One FMA operation in 16-bit precision, from foo_v82.  */
+/* { dg-final { scan-assembler-times "fmadd\th\[0-9\]\+" 1 } } */
+
+/* Test that in C11 mode, we don't reset __FLT_EVAL_METHOD__.  */
+/* { dg-final { scan-assembler-times "str\twzr" 4 } } */