[PATCH, rs6000] Improve atomic_load/store code gen for Power8 TI mode

[Pat Haugen <pthaugen at linux dot vnet dot ibm dot com>]

Power8 can use lq/stq instructions for TI mode atomic_load/store. 
Bootstrap/regtest with no new failures. Ok for trunk and 4.8 (once 
bootstrap/regtest finishes)?

-Pat


2014-03-25  Pat Haugen  <pthaugen@us.ibm.com>

        * config/rs6000/sync.md (AINT mode_iterator): Move definition.
        (loadsync_<mode>): Change mode.
        (atomic_load<mode>, atomic_store<mode>): Add support for TI mode.
        (load_quadpti, store_quadpti): New.
        * config/rs6000/rs6000.md (unspec enum): Add UNSPEC_LSQ.

gcc/testsuite:
        * gcc.target/powerpc/atomic_load_store-p8.c: New.


Index: testsuite/gcc.target/powerpc/atomic_load_store-p8.c
===================================================================
--- testsuite/gcc.target/powerpc/atomic_load_store-p8.c	(revision 0)
+++ testsuite/gcc.target/powerpc/atomic_load_store-p8.c	(revision 0)
@@ -0,0 +1,22 @@
+/* { dg-do compile { target { powerpc*-*-* && lp64 } } } */
+/* { dg-skip-if "" { powerpc*-*-darwin* } { "*" } { "" } } */
+/* { dg-require-effective-target powerpc_p8vector_ok } */
+/* { dg-options "-mcpu=power8 -O2" } */
+/* { dg-final { scan-assembler-times "lq" 1 } } */
+/* { dg-final { scan-assembler-times "stq" 1 } } */
+/* { dg-final { scan-assembler-not "bl __atomic" } } */
+/* { dg-final { scan-assembler-not "lqarx" } } */
+/* { dg-final { scan-assembler-not "stqcx" } } */
+
+__int128
+atomic_load_128_relaxed (__int128 *ptr)
+{
+	return __atomic_load_n (ptr, __ATOMIC_RELAXED);
+}
+
+void
+atomic_store_128_relaxed (__int128 *ptr, __int128 val)
+{
+	__atomic_store_n (ptr, val, __ATOMIC_RELAXED);
+}
+
Index: config/rs6000/sync.md
===================================================================
--- config/rs6000/sync.md	(revision 208798)
+++ config/rs6000/sync.md	(working copy)
@@ -107,10 +107,17 @@ (define_insn "isync"
   "isync"
   [(set_attr "type" "isync")])
 
+;; Types that we should provide atomic instructions for.
+(define_mode_iterator AINT [QI
+			    HI
+			    SI
+			    (DI "TARGET_POWERPC64")
+			    (TI "TARGET_SYNC_TI")])
+
 ;; The control dependency used for load dependency described
 ;; in B.2.3 of the Power ISA 2.06B.
 (define_insn "loadsync_<mode>"
-  [(unspec_volatile:BLK [(match_operand:INT1 0 "register_operand" "r")]
+  [(unspec_volatile:BLK [(match_operand:AINT 0 "register_operand" "r")]
 			UNSPECV_ISYNC)
    (clobber (match_scratch:CC 1 "=y"))]
   ""
@@ -119,17 +126,39 @@ (define_insn "loadsync_<mode>"
    (set_attr "length" "12")])
 
 (define_expand "atomic_load<mode>"
-  [(set (match_operand:INT1 0 "register_operand" "")		;; output
-	(match_operand:INT1 1 "memory_operand" ""))		;; memory
+  [(set (match_operand:AINT 0 "register_operand" "")		;; output
+	(match_operand:AINT 1 "memory_operand" ""))		;; memory
    (use (match_operand:SI 2 "const_int_operand" ""))]		;; model
   ""
 {
+  if (<MODE>mode == TImode && !TARGET_QUAD_MEMORY)
+    FAIL;
+
   enum memmodel model = (enum memmodel) INTVAL (operands[2]);
 
   if (model == MEMMODEL_SEQ_CST)
     emit_insn (gen_hwsync ());
 
-  emit_move_insn (operands[0], operands[1]);
+  if (<MODE>mode != TImode)
+    emit_move_insn (operands[0], operands[1]);
+  else
+    {
+      rtx op0 = operands[0];
+      rtx op1 = operands[1];
+      rtx pti_reg = gen_reg_rtx (PTImode);
+
+      // Can't have indexed address for 'lq'
+      if (indexed_address (XEXP (op1, 0), TImode))
+	{
+	  rtx old_addr = XEXP (op1, 0);
+	  rtx new_addr = force_reg (Pmode, old_addr);
+	  operands[1] = op1 = replace_equiv_address (op1, new_addr);
+	}
+
+      emit_insn (gen_load_quadpti (pti_reg, op1));
+
+      emit_move_insn (op0, gen_lowpart (TImode, pti_reg));
+    }
 
   switch (model)
     {
@@ -146,12 +175,25 @@ (define_expand "atomic_load<mode>"
   DONE;
 })
 
+(define_insn "load_quadpti"
+  [(set (match_operand:PTI 0 "quad_int_reg_operand" "=&r")
+	(unspec:PTI
+         [(match_operand:TI 1 "quad_memory_operand" "wQ")] UNSPEC_LSQ))]
+  "TARGET_QUAD_MEMORY
+   && !reg_mentioned_p (operands[0], operands[1])"
+  "lq %0,%1"
+  [(set_attr "type" "load")
+   (set_attr "length" "4")])
+
 (define_expand "atomic_store<mode>"
-  [(set (match_operand:INT1 0 "memory_operand" "")		;; memory
-	(match_operand:INT1 1 "register_operand" ""))		;; input
-   (use (match_operand:SI 2 "const_int_operand" ""))]		;; model
+  [(set (match_operand:AINT 0 "memory_operand" "")              ;; memory
+        (match_operand:AINT 1 "register_operand" ""))           ;; input
+   (use (match_operand:SI 2 "const_int_operand" ""))]           ;; model
   ""
 {
+  if (<MODE>mode == TImode && !TARGET_QUAD_MEMORY)
+    FAIL;
+
   enum memmodel model = (enum memmodel) INTVAL (operands[2]);
   switch (model)
     {
@@ -166,10 +208,38 @@ (define_expand "atomic_store<mode>"
     default:
       gcc_unreachable ();
     }
-  emit_move_insn (operands[0], operands[1]);
+  if (<MODE>mode != TImode)
+    emit_move_insn (operands[0], operands[1]);
+  else
+    {
+      rtx op0 = operands[0];
+      rtx op1 = operands[1];
+      rtx pti_reg = gen_reg_rtx (PTImode);
+
+      // Can't have indexed address for 'stq'
+      if (indexed_address (XEXP (op0, 0), TImode))
+        {
+          rtx old_addr = XEXP (op0, 0);
+          rtx new_addr = force_reg (Pmode, old_addr);
+          operands[0] = op0 = replace_equiv_address (op0, new_addr);
+        }
+
+      emit_move_insn (pti_reg, gen_lowpart (PTImode, op1));
+      emit_insn (gen_store_quadpti (gen_lowpart (PTImode, op0), pti_reg));
+    }
+
   DONE;
 })
 
+(define_insn "store_quadpti"
+  [(set (match_operand:PTI 0 "quad_memory_operand" "=wQ")
+	(unspec:PTI
+	 [(match_operand:PTI 1 "quad_int_reg_operand" "r")] UNSPEC_LSQ))]
+  "TARGET_QUAD_MEMORY"
+  "stq %1,%0"
+  [(set_attr "type" "store")
+   (set_attr "length" "4")])
+
 ;; Any supported integer mode that has atomic l<x>arx/st<x>cx. instrucitons
 ;; other than the quad memory operations, which have special restrictions.
 ;; Byte/halfword atomic instructions were added in ISA 2.06B, but were phased
@@ -180,14 +250,6 @@ (define_mode_iterator ATOMIC [(QI "TARGE
 			      SI
 			      (DI "TARGET_POWERPC64")])
 
-;; Types that we should provide atomic instructions for.
-
-(define_mode_iterator AINT [QI
-			    HI
-			    SI
-			    (DI "TARGET_POWERPC64")
-			    (TI "TARGET_SYNC_TI")])
-
 (define_insn "load_locked<mode>"
   [(set (match_operand:ATOMIC 0 "int_reg_operand" "=r")
 	(unspec_volatile:ATOMIC
Index: config/rs6000/rs6000.md
===================================================================
--- config/rs6000/rs6000.md	(revision 208798)
+++ config/rs6000/rs6000.md	(working copy)
@@ -125,6 +125,7 @@ (define_c_enum "unspec"
    UNSPEC_P8V_MTVSRD
    UNSPEC_P8V_XXPERMDI
    UNSPEC_P8V_RELOAD_FROM_VSX
+   UNSPEC_LSQ
   ])
 
 ;;