[Patch] gcn: Add __builtin_gcn_{get_stack_limit,first_call_this_thread_p}

[Tobias Burnus <tobias@codesourcery.com>]

[-- Attachment #1: Type: text/plain, Size: 982 bytes --]

This patch adds two builtins (getting end-of-stack pointer and
a Boolean answer whether it was the first call to the builtin on this thread).

The idea is to replace some hard-coded values in newlib, permitting to move
later to a manually allocated stack on the compiler side without the need to
modify newlib again. The GCC patch matches what newlib did in reent; I could
imagine that we change this later on.

Lightly tested (especially by visual inspection).
Currently doing a final regtest, OK when it passes?

Any  comments to this patch - or the attached newlib patch?*

Tobias

(*) I also included a patch to newlib to see where were are heading
+ to actually use them for regtesting ...
-----------------
Siemens Electronic Design Automation GmbH; Anschrift: Arnulfstraße 201, 80634 München; Gesellschaft mit beschränkter Haftung; Geschäftsführer: Thomas Heurung, Frank Thürauf; Sitz der Gesellschaft: München; Registergericht München, HRB 106955

[-- Attachment #2: gcn-stack-init.diff --]
[-- Type: text/x-patch, Size: 5430 bytes --]

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>

 gcc/config/gcn/gcn-builtins.def |  4 +++
 gcc/config/gcn/gcn.cc           | 70 ++++++++++++++++++++++++++++++++++++++++-
 gcc/config/gcn/gcn.md           | 15 ++++++++-
 3 files changed, 87 insertions(+), 2 deletions(-)

diff --git a/gcc/config/gcn/gcn-builtins.def b/gcc/config/gcn/gcn-builtins.def
index eeeaebf9013..f1cf30bbc94 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 b3814c2e7c6..051eadee783 100644
--- a/gcc/config/gcn/gcn.cc
+++ b/gcc/config/gcn/gcn.cc
@@ -4493,6 +4493,44 @@ 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 = 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 (DImode,
+				    gen_rtx_PLUS (DImode, size_rtx,
+						  GEN_INT (6*16 + 3*32)));
+	    size_rtx = gen_rtx_MULT (DImode, 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 +4544,37 @@ 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_AND (DImode, reg,
+					      GEN_INT (0xffff000000000000L)));
+	    emit_insn (gen_cstoresi4 (result, gen_rtx_EQ (BImode, cmp,
+							  GEN_INT(12345L << 48)),
+				      cmp, GEN_INT(12345L << 48)));
+	    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 987b76396cc..a8b9c28d115 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)]
   ""

[-- Attachment #3: newlib-reent.diff --]
[-- Type: text/x-patch, Size: 2594 bytes --]

amdgcn: Use __builtin_gcn_ in libc/machine/amdgcn/getreent.c

Call __builtin_gcn_get_stack_limit and __builtin_gcn_first_call_this_thread_p
to reduce dependency on some register/layout assumptions by using the new
GCC mainline (GCC 13) builtins, if they are available. If not, the existing
code is used.

 newlib/libc/machine/amdgcn/getreent.c | 38 ++++++++++++++++++++++++++---------
 1 file changed, 29 insertions(+), 9 deletions(-)

diff --git a/newlib/libc/machine/amdgcn/getreent.c b/newlib/libc/machine/amdgcn/getreent.c
index be7d2edc9..ef731f649 100644
--- a/newlib/libc/machine/amdgcn/getreent.c
+++ b/newlib/libc/machine/amdgcn/getreent.c
@@ -29,22 +29,42 @@ typedef struct hsa_kernel_dispatch_packet_s {
 struct _reent *
 __getreent (void)
 {
-  /* Place the reent data at the top of the stack allocation.
-     s[0:1] contains a 48-bit private segment base address.
+  /* Place the reent data at the top of the stack allocation.  */
+  struct data {
+    int marker;
+    struct _reent reent;
+  } *data;
+
+#if defined(__has_builtin) \
+    && __has_builtin(__builtin_gcn_get_stack_limit) \
+    && __has_builtin(__builtin_gcn_first_call_this_thread_p)
+  unsigned long addr = (((unsigned long) __builtin_gcn_get_stack_limit()
+			 - sizeof(struct data)) & ~7);
+  data = (struct data *)addr;
+
+  register long sp asm("s16");
+
+  if (sp >= addr)
+    goto stackoverflow;
+  if (__builtin_gcn_first_call_this_thread_p())
+    {
+      data->marker = 12345;
+      __builtin_memset (&data->reent, 0, sizeof(struct _reent));
+      _REENT_INIT_PTR_ZEROED (&data->reent);
+    }
+  else if (data->marker != 12345)
+    goto stackoverflow;
+#else
+  /* s[0:1] contains a 48-bit private segment base address.
      s11 contains the offset to the base of the stack.
      s[4:5] contains the dispatch pointer.
-     
+
      WARNING: this code will break if s[0:1] is ever used for anything!  */
   const register unsigned long buffer_descriptor asm("s0");
   unsigned long private_segment = buffer_descriptor & 0x0000ffffffffffff;
   const register unsigned int stack_offset asm("s11");
   const register hsa_kernel_dispatch_packet_t *dispatch_ptr asm("s4");
 
-  struct data {
-    int marker;
-    struct _reent reent;
-  } *data;
-
   unsigned long stack_base = private_segment + stack_offset;
   unsigned long stack_end = stack_base + dispatch_ptr->private_segment_size * 64;
   unsigned long addr = (stack_end - sizeof(struct data)) & ~7;
@@ -69,7 +89,7 @@ __getreent (void)
     }
   else if (data->marker != 12345)
     goto stackoverflow;
-
+#endif
 
   return &data->reent;