gcn: Add __builtin_gcn_{get_stack_limit,first_call_this_thread_p}

The new builtins have been added for newlib to reduce dependency on
compiler-internal implementation choices of GCC in newlibs' getreent.c.

gcc/ChangeLog:

	* config/gcn/gcn-builtins.def (FIRST_CALL_THIS_THREAD_P,
	GET_STACK_LIMIT): Add new builtins.
	* config/gcn/gcn.cc (gcn_expand_builtin_1): Expand them.
	* config/gcn/gcn.md (prologue_use): Add "register_operand" as
	arg to match_operand.
	(prologue_use_di): New; DI insn_and_split variant of the former.

Co-Authored-By: Andrew Stubbs <ams@codesourcery.com>

3 files changed, 87 insertions, 2 deletions

diff --git a/gcc/config/gcn/gcn-builtins.def b/gcc/config/gcn/gcn-builtins.def
index eeeaebf..f1cf30b 100644
--- a/gcc/config/gcn/gcn-builtins.def
+++ b/gcc/config/gcn/gcn-builtins.def
@@ -160,8 +160,12 @@ DEF_BUILTIN (ACC_BARRIER, -1, "acc_barrier", B_INSN, _A1 (GCN_BTI_VOID),
 
 /* Kernel inputs.  */
 
+DEF_BUILTIN (FIRST_CALL_THIS_THREAD_P, -1, "first_call_this_thread_p", B_INSN,
+	     _A1 (GCN_BTI_BOOL), gcn_expand_builtin_1)
 DEF_BUILTIN (KERNARG_PTR, -1, "kernarg_ptr", B_INSN, _A1 (GCN_BTI_VOIDPTR),
 	     gcn_expand_builtin_1)
+DEF_BUILTIN (GET_STACK_LIMIT, -1, "get_stack_limit", B_INSN,
+	     _A1 (GCN_BTI_VOIDPTR), gcn_expand_builtin_1)
 
 #undef _A1
 #undef _A2
diff --git a/gcc/config/gcn/gcn.cc b/gcc/config/gcn/gcn.cc
index b3814c2..ea9631e 100644
--- a/gcc/config/gcn/gcn.cc
+++ b/gcc/config/gcn/gcn.cc
@@ -4493,6 +4493,45 @@ gcn_expand_builtin_1 (tree exp, rtx target, rtx /*subtarget */ ,
       emit_insn (gen_gcn_wavefront_barrier ());
       return target;
 
+    case GCN_BUILTIN_GET_STACK_LIMIT:
+      {
+	/* stackbase = (stack_segment_decr & 0x0000ffffffffffff)
+			+ stack_wave_offset);
+	   seg_size = dispatch_ptr->private_segment_size;
+	   stacklimit = stackbase + seg_size*64;
+	   with segsize = *(uint32_t *) ((char *) dispatch_ptr
+				       + 6*sizeof(int16_t) + 3*sizeof(int32_t));
+	   cf. struct hsa_kernel_dispatch_packet_s in the HSA doc.  */
+	rtx ptr;
+	if (cfun->machine->args.reg[DISPATCH_PTR_ARG] >= 0
+	    && cfun->machine->args.reg[PRIVATE_SEGMENT_BUFFER_ARG] >= 0)
+	  {
+	    rtx size_rtx = gen_rtx_REG (DImode,
+			     cfun->machine->args.reg[DISPATCH_PTR_ARG]);
+	    size_rtx = gen_rtx_MEM (SImode,
+				    gen_rtx_PLUS (DImode, size_rtx,
+						  GEN_INT (6*2 + 3*4)));
+	    size_rtx = gen_rtx_MULT (SImode, size_rtx, GEN_INT (64));
+
+	    ptr = gen_rtx_REG (DImode,
+		    cfun->machine->args.reg[PRIVATE_SEGMENT_BUFFER_ARG]);
+	    ptr = gen_rtx_AND (DImode, ptr, GEN_INT (0x0000ffffffffffff));
+	    ptr = gen_rtx_PLUS (DImode, ptr, size_rtx);
+	    if (cfun->machine->args.reg[PRIVATE_SEGMENT_WAVE_OFFSET_ARG] >= 0)
+	      {
+		rtx off;
+		off = gen_rtx_REG (SImode,
+		      cfun->machine->args.reg[PRIVATE_SEGMENT_WAVE_OFFSET_ARG]);
+		ptr = gen_rtx_PLUS (DImode, ptr, off);
+	      }
+	  }
+	else
+	  {
+	    ptr = gen_reg_rtx (DImode);
+	    emit_move_insn (ptr, const0_rtx);
+	  }
+	return ptr;
+      }
     case GCN_BUILTIN_KERNARG_PTR:
       {
 	rtx ptr;
@@ -4506,7 +4545,36 @@ gcn_expand_builtin_1 (tree exp, rtx target, rtx /*subtarget */ ,
 	  }
 	return ptr;
       }
-
+    case GCN_BUILTIN_FIRST_CALL_THIS_THREAD_P:
+      {
+	/* Stash a marker in the unused upper 16 bits of s[0:1] to indicate
+	   whether it was the first call.  */
+	rtx result = gen_reg_rtx (BImode);
+	emit_move_insn (result, const0_rtx);
+	if (cfun->machine->args.reg[PRIVATE_SEGMENT_BUFFER_ARG] >= 0)
+	  {
+	    rtx not_first = gen_label_rtx ();
+	    rtx reg = gen_rtx_REG (DImode,
+			cfun->machine->args.reg[PRIVATE_SEGMENT_BUFFER_ARG]);
+	    rtx cmp = force_reg (DImode,
+				 gen_rtx_LSHIFTRT (DImode, reg, GEN_INT (48)));
+	    emit_insn (gen_cstoresi4 (result, gen_rtx_NE (BImode, cmp,
+							  GEN_INT(12345)),
+				      cmp, GEN_INT(12345)));
+	    emit_jump_insn (gen_cjump (not_first, gen_rtx_EQ (BImode, result,
+							      const0_rtx),
+				       result));
+	    emit_move_insn (reg,
+	      force_reg (DImode,
+		gen_rtx_IOR (DImode,
+			     gen_rtx_AND (DImode, reg,
+					  GEN_INT (0x0000ffffffffffffL)),
+			     GEN_INT (12345L << 48))));
+	    emit_insn (gen_prologue_use (reg));
+	    emit_label (not_first);
+	  }
+	return result;
+      }
     default:
       gcc_unreachable ();
     }
diff --git a/gcc/config/gcn/gcn.md b/gcc/config/gcn/gcn.md
index 987b763..a8b9c28 100644
--- a/gcc/config/gcn/gcn.md
+++ b/gcc/config/gcn/gcn.md
@@ -692,11 +692,24 @@
 ;; {{{ Prologue/Epilogue
 
 (define_insn "prologue_use"
-  [(unspec_volatile [(match_operand 0)] UNSPECV_PROLOGUE_USE)]
+  [(unspec_volatile [(match_operand 0 "register_operand")] UNSPECV_PROLOGUE_USE)]
   ""
   ""
   [(set_attr "length" "0")])
 
+(define_insn_and_split "prologue_use_di"
+  [(unspec_volatile [(match_operand:DI 0 "register_operand")] UNSPECV_PROLOGUE_USE)]
+  ""
+  "#"
+  "reload_completed"
+  [(unspec_volatile [(match_dup 0)] UNSPECV_PROLOGUE_USE)
+   (unspec_volatile [(match_dup 1)] UNSPECV_PROLOGUE_USE)]
+  {
+    operands[1] = gcn_operand_part (DImode, operands[0], 1);
+    operands[0] = gcn_operand_part (DImode, operands[0], 0);
+  }
+  [(set_attr "length" "0")])
+
 (define_expand "prologue"
   [(const_int 0)]
   ""