Re: [RFC][AARCH64] TARGET_ATOMIC_ASSIGN_EXPAND_FENV hook

[Kugan <kugan.vivekanandarajah@linaro.org>]

[-- Attachment #1: Type: text/plain, Size: 1424 bytes --]

> 
> +2014-04-29  Kugan Vivekanandarajah  <kuganv@linaro.org>
> +
> +	* config/aarch64/aarch64.c (TARGET_ATOMIC_ASSIGN_EXPAND_FENV): New
> +	define.
> +	* config/aarch64/aarch64-protos.h (aarch64_atomic_assign_expand_fenv):
> +	New function declaration.
> +	* config/aarch64/aarch64-builtins.c (aarch64_builtins) : Add
> +	AARCH64_BUILTIN_GET_FPCR, AARCH64_BUILTIN_SET_FPCR.
> +	AARCH64_BUILTIN_GET_FPSR and AARCH64_BUILTIN_SET_FPSR.
> +	(aarch64_init_builtins) : Initialize builtins
> +	__builtins_aarch64_set_fpcr, __builtins_aarch64_get_fpcr.
> +	__builtins_aarch64_set_fpsr and __builtins_aarch64_get_fpsr.
> +	(aarch64_expand_builtin) : Expand builtins __builtins_aarch64_set_fpcr
> +	__builtins_aarch64_get_fpcr, __builtins_aarch64_get_fpsr,
> +	and __builtins_aarch64_set_fpsr.
> +	(aarch64_atomic_assign_expand_fenv): New function.
> +	* config/aarch64/aarch64.md (set_fpcr): New pattern.
> +	(get_fpcr) : Likewise.
> +	(set_fpsr) : Likewise.
> +	(get_fpsr) : Likewise.
> +	(unspecv): Add UNSPECV_GET_FPCR and UNSPECV_SET_FPCR, UNSPECV_GET_FPSR
> +	 and UNSPECV_SET_FPSR.
> +	* doc/extend.texi (AARCH64 Built-in Functions) : Document
> +	__builtins_aarch64_set_fpcr, __builtins_aarch64_get_fpcr.
> +	__builtins_aarch64_set_fpsr and __builtins_aarch64_get_fpsr.
> 

Updated is based on the review at
http://gcc.gnu.org/ml/gcc-patches/2014-05/msg00041.html. FE_* values are
now changed to AARCH64_FE-*.

Thanks,
Kugan

[-- Attachment #2: aarch64_v3.txt --]
[-- Type: text/plain, Size: 10517 bytes --]

diff --git a/gcc/config/aarch64/aarch64-builtins.c b/gcc/config/aarch64/aarch64-builtins.c
index 55cfe0a..40d53b1 100644
--- a/gcc/config/aarch64/aarch64-builtins.c
+++ b/gcc/config/aarch64/aarch64-builtins.c
@@ -371,6 +371,12 @@ static aarch64_simd_builtin_datum aarch64_simd_builtin_data[] = {
 enum aarch64_builtins
 {
   AARCH64_BUILTIN_MIN,
+
+  AARCH64_BUILTIN_GET_FPCR,
+  AARCH64_BUILTIN_SET_FPCR,
+  AARCH64_BUILTIN_GET_FPSR,
+  AARCH64_BUILTIN_SET_FPSR,
+
   AARCH64_SIMD_BUILTIN_BASE,
 #include "aarch64-simd-builtins.def"
   AARCH64_SIMD_BUILTIN_MAX = AARCH64_SIMD_BUILTIN_BASE
@@ -752,6 +758,24 @@ aarch64_init_simd_builtins (void)
 void
 aarch64_init_builtins (void)
 {
+  tree ftype_set_fpr
+    = build_function_type_list (void_type_node, unsigned_type_node, NULL);
+  tree ftype_get_fpr
+    = build_function_type_list (unsigned_type_node, NULL);
+
+  aarch64_builtin_decls[AARCH64_BUILTIN_GET_FPCR]
+    = add_builtin_function ("__builtin_aarch64_get_fpcr", ftype_get_fpr,
+			    AARCH64_BUILTIN_GET_FPCR, BUILT_IN_MD, NULL, NULL_TREE);
+  aarch64_builtin_decls[AARCH64_BUILTIN_SET_FPCR]
+    = add_builtin_function ("__builtin_aarch64_set_fpcr", ftype_set_fpr,
+			    AARCH64_BUILTIN_SET_FPCR, BUILT_IN_MD, NULL, NULL_TREE);
+  aarch64_builtin_decls[AARCH64_BUILTIN_GET_FPSR]
+    = add_builtin_function ("__builtin_aarch64_get_fpsr", ftype_get_fpr,
+			    AARCH64_BUILTIN_GET_FPSR, BUILT_IN_MD, NULL, NULL_TREE);
+  aarch64_builtin_decls[AARCH64_BUILTIN_SET_FPSR]
+    = add_builtin_function ("__builtin_aarch64_set_fpsr", ftype_set_fpr,
+			    AARCH64_BUILTIN_SET_FPSR, BUILT_IN_MD, NULL, NULL_TREE);
+
   if (TARGET_SIMD)
     aarch64_init_simd_builtins ();
 }
@@ -964,6 +988,36 @@ aarch64_expand_builtin (tree exp,
 {
   tree fndecl = TREE_OPERAND (CALL_EXPR_FN (exp), 0);
   int fcode = DECL_FUNCTION_CODE (fndecl);
+  int icode;
+  rtx pat, op0;
+  tree arg0;
+
+  switch (fcode)
+    {
+    case AARCH64_BUILTIN_GET_FPCR:
+    case AARCH64_BUILTIN_SET_FPCR:
+    case AARCH64_BUILTIN_GET_FPSR:
+    case AARCH64_BUILTIN_SET_FPSR:
+      if ((fcode == AARCH64_BUILTIN_GET_FPCR)
+	  || (fcode == AARCH64_BUILTIN_GET_FPSR))
+	{
+	  icode = (fcode == AARCH64_BUILTIN_GET_FPSR) ?
+	    CODE_FOR_get_fpsr : CODE_FOR_get_fpcr;
+	  target = gen_reg_rtx (SImode);
+	  pat = GEN_FCN (icode) (target);
+	}
+      else
+	{
+	  target = NULL_RTX;
+	  icode = (fcode == AARCH64_BUILTIN_SET_FPSR) ?
+	    CODE_FOR_set_fpsr : CODE_FOR_set_fpcr;
+	  arg0 = CALL_EXPR_ARG (exp, 0);
+	  op0 = expand_normal (arg0);
+	  pat = GEN_FCN (icode) (op0);
+	}
+      emit_insn (pat);
+      return target;
+    }
 
   if (fcode >= AARCH64_SIMD_BUILTIN_BASE)
     return aarch64_simd_expand_builtin (fcode, exp, target);
@@ -1196,6 +1250,106 @@ aarch64_gimple_fold_builtin (gimple_stmt_iterator *gsi)
   return changed;
 }
 
+void
+aarch64_atomic_assign_expand_fenv (tree *hold, tree *clear, tree *update)
+{
+  const unsigned AARCH64_FE_INVALID = 1;
+  const unsigned AARCH64_FE_DIVBYZERO = 2;
+  const unsigned AARCH64_FE_OVERFLOW = 4;
+  const unsigned AARCH64_FE_UNDERFLOW = 8;
+  const unsigned AARCH64_FE_INEXACT = 16;
+  const unsigned HOST_WIDE_INT AARCH64_FE_ALL_EXCEPT = (AARCH64_FE_INVALID
+							| AARCH64_FE_DIVBYZERO
+							| AARCH64_FE_OVERFLOW
+							| AARCH64_FE_UNDERFLOW
+							| AARCH64_FE_INEXACT);
+  const unsigned HOST_WIDE_INT AARCH64_FE_EXCEPT_SHIFT = 8;
+  tree fenv_cr, fenv_sr, get_fpcr, set_fpcr, mask_cr, mask_sr;
+  tree ld_fenv_cr, ld_fenv_sr, masked_fenv_cr, masked_fenv_sr, hold_fnclex_cr;
+  tree hold_fnclex_sr, new_fenv_var, reload_fenv, restore_fnenv, get_fpsr, set_fpsr;
+  tree update_call, atomic_feraiseexcept, hold_fnclex, masked_fenv, ld_fenv;
+
+  /* Generate the equivalence of :
+       unsigned int fenv_cr;
+       fenv_cr = __builtin_aarch64_get_fpcr ();
+
+       unsigned int fenv_sr;
+       fenv_sr = __builtin_aarch64_get_fpsr ();
+
+       Now set all exceptions to non-stop
+       unsigned int mask_cr
+		= ~(AARCH64_FE_ALL_EXCEPT << AARCH64_FE_EXCEPT_SHIFT);
+       unsigned int masked_cr;
+       masked_cr = fenv_cr & mask_cr;
+
+       And clear all exception flags
+       unsigned int maske_sr = ~AARCH64_FE_ALL_EXCEPT;
+       unsigned int masked_cr;
+       masked_sr = fenv_sr & mask_sr;
+
+       __builtin_aarch64_set_cr (masked_cr);
+       __builtin_aarch64_set_sr (masked_sr);  */
+
+  fenv_cr = create_tmp_var (unsigned_type_node, NULL);
+  fenv_sr = create_tmp_var (unsigned_type_node, NULL);
+
+  get_fpcr = aarch64_builtin_decls[AARCH64_BUILTIN_GET_FPCR];
+  set_fpcr = aarch64_builtin_decls[AARCH64_BUILTIN_SET_FPCR];
+  get_fpsr = aarch64_builtin_decls[AARCH64_BUILTIN_GET_FPSR];
+  set_fpsr = aarch64_builtin_decls[AARCH64_BUILTIN_SET_FPSR];
+
+  mask_cr = build_int_cst (unsigned_type_node,
+			   ~(AARCH64_FE_ALL_EXCEPT << AARCH64_FE_EXCEPT_SHIFT));
+  mask_sr = build_int_cst (unsigned_type_node,
+			   ~(AARCH64_FE_ALL_EXCEPT));
+
+  ld_fenv_cr = build2 (MODIFY_EXPR, unsigned_type_node,
+		    fenv_cr, build_call_expr (get_fpcr, 0));
+  ld_fenv_sr = build2 (MODIFY_EXPR, unsigned_type_node,
+		    fenv_sr, build_call_expr (get_fpsr, 0));
+
+  masked_fenv_cr = build2 (BIT_AND_EXPR, unsigned_type_node, fenv_cr, mask_cr);
+  masked_fenv_sr = build2 (BIT_AND_EXPR, unsigned_type_node, fenv_sr, mask_sr);
+
+  hold_fnclex_cr = build_call_expr (set_fpcr, 1, masked_fenv_cr);
+  hold_fnclex_sr = build_call_expr (set_fpsr, 1, masked_fenv_sr);
+
+  hold_fnclex = build2 (COMPOUND_EXPR, void_type_node, hold_fnclex_cr,
+			hold_fnclex_sr);
+  masked_fenv = build2 (COMPOUND_EXPR, void_type_node, masked_fenv_cr,
+			masked_fenv_sr);
+  ld_fenv = build2 (COMPOUND_EXPR, void_type_node, ld_fenv_cr, ld_fenv_sr);
+
+  *hold = build2 (COMPOUND_EXPR, void_type_node,
+		  build2 (COMPOUND_EXPR, void_type_node, masked_fenv, ld_fenv),
+		  hold_fnclex);
+
+  /* Store the value of masked_fenv to clear the exceptions:
+     __builtin_aarch64_set_fpcr (masked_sr);  */
+
+  *clear = build_call_expr (set_fpsr, 1, masked_fenv_sr);
+
+  /* Generate the equivalent of :
+       unsigned int new_fenv_var;
+       new_fenv_var = __builtin_aarch64_get_fpsr ();
+
+       __builtin_aarch64_set_fpsr (fenv_sr);
+
+       __atomic_feraiseexcept (new_fenv_var);  */
+
+  new_fenv_var = create_tmp_var (unsigned_type_node, NULL);
+  reload_fenv = build2 (MODIFY_EXPR, unsigned_type_node,
+			new_fenv_var, build_call_expr (get_fpsr, 0));
+  restore_fnenv = build_call_expr (set_fpsr, 1, fenv_sr);
+  atomic_feraiseexcept = builtin_decl_implicit (BUILT_IN_ATOMIC_FERAISEEXCEPT);
+  update_call = build_call_expr (atomic_feraiseexcept, 1,
+				 fold_convert (integer_type_node, new_fenv_var));
+  *update = build2 (COMPOUND_EXPR, void_type_node,
+		    build2 (COMPOUND_EXPR, void_type_node,
+			    reload_fenv, restore_fnenv), update_call);
+}
+
+
 #undef AARCH64_CHECK_BUILTIN_MODE
 #undef AARCH64_FIND_FRINT_VARIANT
 #undef BUILTIN_DX
diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index 5542f02..f4f3f61 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -289,4 +289,5 @@ extern void aarch64_split_combinev16qi (rtx operands[3]);
 extern void aarch64_expand_vec_perm (rtx target, rtx op0, rtx op1, rtx sel);
 extern bool
 aarch64_expand_vec_perm_const (rtx target, rtx op0, rtx op1, rtx sel);
+void aarch64_atomic_assign_expand_fenv (tree *, tree *, tree *);
 #endif /* GCC_AARCH64_PROTOS_H */
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index a3147ee..fbbdc23 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -8488,6 +8488,10 @@ aarch64_cannot_change_mode_class (enum machine_mode from,
 #define TARGET_VECTORIZE_AUTOVECTORIZE_VECTOR_SIZES \
   aarch64_autovectorize_vector_sizes
 
+#undef TARGET_ATOMIC_ASSIGN_EXPAND_FENV
+#define TARGET_ATOMIC_ASSIGN_EXPAND_FENV \
+  aarch64_atomic_assign_expand_fenv
+
 /* Section anchor support.  */
 
 #undef TARGET_MIN_ANCHOR_OFFSET
diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index c86a29d..24f235f 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -107,6 +107,10 @@
 
 (define_c_enum "unspecv" [
     UNSPECV_EH_RETURN		; Represent EH_RETURN
+    UNSPECV_GET_FPCR		; Represent fetch of FPCR content.
+    UNSPECV_SET_FPCR		; Represent assign of FPCR content.
+    UNSPECV_GET_FPSR		; Represent fetch of FPSR content.
+    UNSPECV_SET_FPSR		; Represent assign of FPSR content.
   ]
 )
 
@@ -3635,6 +3639,37 @@
   DONE;
 })
 
+;; Write Floating-point Control Register.
+(define_insn "set_fpcr"
+  [(unspec_volatile [(match_operand:SI 0 "register_operand" "r")] UNSPECV_SET_FPCR)]
+  ""
+  "msr\\tfpcr, %0"
+  [(set_attr "type" "mrs")])
+
+;; Read Floating-point Control Register.
+(define_insn "get_fpcr"
+  [(set (match_operand:SI 0 "register_operand" "=r")
+        (unspec_volatile:SI [(const_int 0)] UNSPECV_GET_FPCR))]
+  ""
+  "mrs\\t%0, fpcr"
+  [(set_attr "type" "mrs")])
+
+;; Write Floating-point Status Register.
+(define_insn "set_fpsr"
+  [(unspec_volatile [(match_operand:SI 0 "register_operand" "r")] UNSPECV_SET_FPSR)]
+  ""
+  "msr\\tfpsr, %0"
+  [(set_attr "type" "mrs")])
+
+;; Read Floating-point Status Register.
+(define_insn "get_fpsr"
+  [(set (match_operand:SI 0 "register_operand" "=r")
+        (unspec_volatile:SI [(const_int 0)] UNSPECV_GET_FPSR))]
+  ""
+  "mrs\\t%0, fpsr"
+  [(set_attr "type" "mrs")])
+
+
 ;; AdvSIMD Stuff
 (include "aarch64-simd.md")
 
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index 347a94a..8bd13f3 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -9107,6 +9107,7 @@ to those machines.  Generally these generate calls to specific machine
 instructions, but allow the compiler to schedule those calls.
 
 @menu
+* AARCH64 Built-in Functions::
 * Alpha Built-in Functions::
 * Altera Nios II Built-in Functions::
 * ARC Built-in Functions::
@@ -9139,6 +9140,18 @@ instructions, but allow the compiler to schedule those calls.
 * TILEPro Built-in Functions::
 @end menu
 
+@node AARCH64 Built-in Functions
+@subsection AARCH64 Built-in Functions
+
+These built-in functions are available for the AARCH64 family of
+processors.
+@smallexample
+unsigned int __builtin_aarch64_get_fpcr ()
+void __builtin_aarch64_set_fpcr (unsigned int)
+unsigned int __builtin_aarch64_get_fpsr ()
+void __builtin_aarch64_set_fpsr (unsigned int)
+@end smallexample
+
 @node Alpha Built-in Functions
 @subsection Alpha Built-in Functions