[AArch64,v3,2/6] aarch64: Implement TImode compare-and-swap

Message ID 20181101214648.29432-3-richard.henderson@linaro.org
State New
Headers show
Series
  • LSE atomics out-of-line
Related show

Commit Message

Richard Henderson Nov. 1, 2018, 9:46 p.m.
From: Richard Henderson <rth@twiddle.net>


This pattern will only be used with the __sync functions, because
we do not yet have a bare TImode atomic load.

	* config/aarch64/aarch64.c (aarch64_gen_compare_reg): Add support
	for NE comparison of TImode values.
	(aarch64_emit_load_exclusive): Add support for TImode.
	(aarch64_emit_store_exclusive): Likewise.
	(aarch64_split_compare_and_swap): Disable strong_zero_p for TImode.
	* config/aarch64/atomics.md (@atomic_compare_and_swap<ALLI_TI>):
	Change iterator from ALLI to ALLI_TI.
	(@atomic_compare_and_swap<JUST_TI>): New.
	(@atomic_compare_and_swap<JUST_TI>_lse): New.
	(aarch64_load_exclusive_pair): New.
	(aarch64_store_exclusive_pair): New.
	* config/aarch64/iterators.md (JUST_TI): New.
---
 gcc/config/aarch64/aarch64.c    | 55 +++++++++++++++++---
 gcc/config/aarch64/atomics.md   | 91 +++++++++++++++++++++++++++++++--
 gcc/config/aarch64/iterators.md |  3 ++
 3 files changed, 137 insertions(+), 12 deletions(-)

-- 
2.17.2

Patch

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 930f27d9bac..942f2037235 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -1611,10 +1611,40 @@  emit_set_insn (rtx x, rtx y)
 rtx
 aarch64_gen_compare_reg (RTX_CODE code, rtx x, rtx y)
 {
-  machine_mode mode = SELECT_CC_MODE (code, x, y);
-  rtx cc_reg = gen_rtx_REG (mode, CC_REGNUM);
+  machine_mode cmp_mode;
+  machine_mode cc_mode;
+  rtx cc_reg;
 
-  emit_set_insn (cc_reg, gen_rtx_COMPARE (mode, x, y));
+  if (swap_commutative_operands_p (x, y))
+    {
+      code = swap_condition (code);
+      std::swap (x, y);
+    }
+  cmp_mode = GET_MODE (x);
+
+  if (cmp_mode == TImode)
+    {
+      gcc_assert (code == NE);
+
+      cc_mode = CCmode;
+      cc_reg = gen_rtx_REG (cc_mode, CC_REGNUM);
+
+      rtx x_lo = operand_subword (x, 0, 0, TImode);
+      rtx y_lo = operand_subword (y, 0, 0, TImode);
+      emit_set_insn (cc_reg, gen_rtx_COMPARE (cc_mode, x_lo, y_lo));
+
+      rtx x_hi = operand_subword (x, 1, 0, TImode);
+      rtx y_hi = operand_subword (y, 1, 0, TImode);
+      emit_insn (gen_ccmpdi (cc_reg, cc_reg, x_hi, y_hi,
+			     gen_rtx_EQ (cc_mode, cc_reg, const0_rtx),
+			     GEN_INT (AARCH64_EQ)));
+    }
+  else
+    {
+      cc_mode = SELECT_CC_MODE (code, x, y);
+      cc_reg = gen_rtx_REG (cc_mode, CC_REGNUM);
+      emit_set_insn (cc_reg, gen_rtx_COMPARE (cc_mode, x, y));
+    }
   return cc_reg;
 }
 
@@ -2162,7 +2192,6 @@  aarch64_zero_extend_const_eq (machine_mode xmode, rtx x,
   gcc_assert (r != NULL);
   return rtx_equal_p (x, r);
 }
-			      
 
 static rtx
 aarch64_force_temporary (machine_mode mode, rtx x, rtx value)
@@ -14619,16 +14648,26 @@  static void
 aarch64_emit_load_exclusive (machine_mode mode, rtx rval,
 			     rtx mem, rtx model_rtx)
 {
-  emit_insn (gen_aarch64_load_exclusive (mode, rval, mem, model_rtx));
+  if (mode == TImode)
+    emit_insn (gen_aarch64_load_exclusive_pair (gen_lowpart (DImode, rval),
+						gen_highpart (DImode, rval),
+						mem, model_rtx));
+  else
+    emit_insn (gen_aarch64_load_exclusive (mode, rval, mem, model_rtx));
 }
 
 /* Emit store exclusive.  */
 
 static void
 aarch64_emit_store_exclusive (machine_mode mode, rtx bval,
-			      rtx rval, rtx mem, rtx model_rtx)
+			      rtx mem, rtx rval, rtx model_rtx)
 {
-  emit_insn (gen_aarch64_store_exclusive (mode, bval, rval, mem, model_rtx));
+  if (mode == TImode)
+    emit_insn (gen_aarch64_store_exclusive_pair
+	       (bval, mem, operand_subword (rval, 0, 0, TImode),
+		operand_subword (rval, 1, 0, TImode), model_rtx));
+  else
+    emit_insn (gen_aarch64_store_exclusive (mode, bval, mem, rval, model_rtx));
 }
 
 /* Mark the previous jump instruction as unlikely.  */
@@ -14755,7 +14794,7 @@  aarch64_split_compare_and_swap (rtx operands[])
 	CBNZ	scratch, .label1
     .label2:
 	CMP	rval, 0.  */
-  bool strong_zero_p = !is_weak && oldval == const0_rtx;
+  bool strong_zero_p = !is_weak && oldval == const0_rtx && mode != TImode;
 
   label1 = NULL;
   if (!is_weak)
diff --git a/gcc/config/aarch64/atomics.md b/gcc/config/aarch64/atomics.md
index 00f7af4e4ac..08a3a1ff955 100644
--- a/gcc/config/aarch64/atomics.md
+++ b/gcc/config/aarch64/atomics.md
@@ -22,10 +22,10 @@ 
 
 (define_expand "@atomic_compare_and_swap<mode>"
   [(match_operand:SI 0 "register_operand" "")			;; bool out
-   (match_operand:ALLI 1 "register_operand" "")			;; val out
-   (match_operand:ALLI 2 "aarch64_sync_memory_operand" "")	;; memory
-   (match_operand:ALLI 3 "nonmemory_operand" "")		;; expected
-   (match_operand:ALLI 4 "aarch64_reg_or_zero" "")		;; desired
+   (match_operand:ALLI_TI 1 "register_operand" "")		;; val out
+   (match_operand:ALLI_TI 2 "aarch64_sync_memory_operand" "")	;; memory
+   (match_operand:ALLI_TI 3 "nonmemory_operand" "")		;; expected
+   (match_operand:ALLI_TI 4 "aarch64_reg_or_zero" "")		;; desired
    (match_operand:SI 5 "const_int_operand")			;; is_weak
    (match_operand:SI 6 "const_int_operand")			;; mod_s
    (match_operand:SI 7 "const_int_operand")]			;; mod_f
@@ -88,6 +88,30 @@ 
   }
 )
 
+(define_insn_and_split "@aarch64_compare_and_swap<mode>"
+  [(set (reg:CC CC_REGNUM)					;; bool out
+    (unspec_volatile:CC [(const_int 0)] UNSPECV_ATOMIC_CMPSW))
+   (set (match_operand:JUST_TI 0 "register_operand" "=&r")	;; val out
+    (match_operand:JUST_TI 1 "aarch64_sync_memory_operand" "+Q")) ;; memory
+   (set (match_dup 1)
+    (unspec_volatile:JUST_TI
+      [(match_operand:JUST_TI 2 "aarch64_reg_or_zero" "rZ")	;; expect
+       (match_operand:JUST_TI 3 "aarch64_reg_or_zero" "rZ")	;; desired
+       (match_operand:SI 4 "const_int_operand")			;; is_weak
+       (match_operand:SI 5 "const_int_operand")			;; mod_s
+       (match_operand:SI 6 "const_int_operand")]		;; mod_f
+      UNSPECV_ATOMIC_CMPSW))
+   (clobber (match_scratch:SI 7 "=&r"))]
+  ""
+  "#"
+  "&& reload_completed"
+  [(const_int 0)]
+  {
+    aarch64_split_compare_and_swap (operands);
+    DONE;
+  }
+)
+
 (define_insn "@aarch64_compare_and_swap<mode>_lse"
   [(set (match_operand:SI 0 "register_operand" "+r")		;; val out
     (zero_extend:SI
@@ -133,6 +157,28 @@ 
     return "casal<atomic_sfx>\t%<w>0, %<w>2, %1";
 })
 
+(define_insn "@aarch64_compare_and_swap<mode>_lse"
+  [(set (match_operand:JUST_TI 0 "register_operand" "+r")	;; val out
+    (match_operand:JUST_TI 1 "aarch64_sync_memory_operand" "+Q")) ;; memory
+   (set (match_dup 1)
+    (unspec_volatile:JUST_TI
+      [(match_dup 0)						;; expect
+       (match_operand:JUST_TI 2 "register_operand" "r")		;; desired
+       (match_operand:SI 3 "const_int_operand")]		;; mod_s
+      UNSPECV_ATOMIC_CMPSW))]
+  "TARGET_LSE"
+{
+  enum memmodel model = memmodel_from_int (INTVAL (operands[3]));
+  if (is_mm_relaxed (model))
+    return "casp\t%0, %R0, %2, %R2, %1";
+  else if (is_mm_acquire (model) || is_mm_consume (model))
+    return "caspa\t%0, %R0, %2, %R2, %1";
+  else if (is_mm_release (model))
+    return "caspl\t%0, %R0, %2, %R2, %1";
+  else
+    return "caspal\t%0, %R0, %2, %R2, %1";
+})
+
 (define_expand "atomic_exchange<mode>"
  [(match_operand:ALLI 0 "register_operand" "")
   (match_operand:ALLI 1 "aarch64_sync_memory_operand" "")
@@ -581,6 +627,24 @@ 
   }
 )
 
+(define_insn "aarch64_load_exclusive_pair"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+	(unspec_volatile:DI
+	  [(match_operand:TI 2 "aarch64_sync_memory_operand" "Q")
+	   (match_operand:SI 3 "const_int_operand")]
+	  UNSPECV_LX))
+   (set (match_operand:DI 1 "register_operand" "=r")
+	(unspec_volatile:DI [(match_dup 2) (match_dup 3)] UNSPECV_LX))]
+  ""
+  {
+    enum memmodel model = memmodel_from_int (INTVAL (operands[3]));
+    if (is_mm_relaxed (model) || is_mm_consume (model) || is_mm_release (model))
+      return "ldxp\t%0, %1, %2";
+    else
+      return "ldaxp\t%0, %1, %2";
+  }
+)
+
 (define_insn "@aarch64_store_exclusive<mode>"
   [(set (match_operand:SI 0 "register_operand" "=&r")
     (unspec_volatile:SI [(const_int 0)] UNSPECV_SX))
@@ -599,6 +663,25 @@ 
   }
 )
 
+(define_insn "aarch64_store_exclusive_pair"
+  [(set (match_operand:SI 0 "register_operand" "=&r")
+	(unspec_volatile:SI [(const_int 0)] UNSPECV_SX))
+   (set (match_operand:TI 1 "aarch64_sync_memory_operand" "=Q")
+	(unspec_volatile:TI
+	  [(match_operand:DI 2 "aarch64_reg_or_zero" "rZ")
+	   (match_operand:DI 3 "aarch64_reg_or_zero" "rZ")
+	   (match_operand:SI 4 "const_int_operand")]
+	  UNSPECV_SX))]
+  ""
+  {
+    enum memmodel model = memmodel_from_int (INTVAL (operands[3]));
+    if (is_mm_relaxed (model) || is_mm_consume (model) || is_mm_acquire (model))
+      return "stxp\t%w0, %x2, %x3, %1";
+    else
+      return "stlxp\t%w0, %x2, %x3, %1";
+  }
+)
+
 (define_expand "mem_thread_fence"
   [(match_operand:SI 0 "const_int_operand" "")]
   ""
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index 524e4e6929b..dd26bdbbc6b 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -29,6 +29,9 @@ 
 ;; Iterator for HI, SI, DI, some instructions can only work on these modes.
 (define_mode_iterator GPI_I16 [(HI "AARCH64_ISA_F16") SI DI])
 
+;; "Iterator" for just TI -- features like @pattern only work with iterators.
+(define_mode_iterator JUST_TI [TI])
+
 ;; Iterator for QI and HI modes
 (define_mode_iterator SHORT [QI HI])