[RFA/ARM][Patch 03/05]: STRD generation instead of PUSH in A15 Thumb2 prologue.

[Sameera Deshpande <sameera.deshpande@arm.com>]

[-- Attachment #1: Type: text/plain, Size: 815 bytes --]

Hi!

This patch generates STRD instruction instead of PUSH in thumb2 mode for
A15.

For optimize_size, original prologue is generated for A15.
The work involves defining new functions, predicates and patterns.

The patch is tested with check-gcc, check-gdb and bootstrap with no
regression. 

Changelog entries for the patch for STRD generation for a15-thumb2:

2011-10-11  Sameera Deshpande
<sameera.deshpande@arm.com>                                             
                                                                                                       
        * config/arm/arm.c (thumb2_emit_strd_push): New static
function.  
          (arm_expand_prologue): Update. 
        * config/arm/ldmstm.md (thumb2_strd): New pattern.
          (thumb2_strd_base): Likewise.
-- 



[-- Attachment #2: a15_thumb2_strd_prologue-6Oct.patch --]
[-- Type: text/x-patch, Size: 7412 bytes --]

diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 3eba510..fd8c31d 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -15095,6 +15095,125 @@ arm_output_function_epilogue (FILE *file ATTRIBUTE_UNUSED,
     }
 }
 
+/* Generate and emit a pattern that will be recognized as STRD pattern.  If even
+   number of registers are being pushed, multiple STRD patterns are created for
+   all register pairs.  If odd number of registers are pushed, first register is
+   stored by using STR pattern.  */
+static void
+thumb2_emit_strd_push (unsigned long saved_regs_mask)
+{
+  int num_regs = 0;
+  int i, j;
+  rtx par = NULL_RTX;
+  rtx insn = NULL_RTX;
+  rtx dwarf = NULL_RTX;
+  rtx tmp, reg, tmp1;
+
+  for (i = 0; i <= LAST_ARM_REGNUM; i++)
+    if (saved_regs_mask & (1 << i))
+      num_regs++;
+
+  gcc_assert (num_regs && num_regs <= 16);
+
+  /* Pre-decrement the stack pointer, based on there being num_regs 4-byte
+     registers to push.  */
+  tmp = gen_rtx_SET (VOIDmode,
+                     stack_pointer_rtx,
+                     plus_constant (stack_pointer_rtx, -4 * num_regs));
+  RTX_FRAME_RELATED_P (tmp) = 1;
+  insn = emit_insn (tmp);
+
+  /* Create sequence for DWARF info.  */
+  dwarf = gen_rtx_SEQUENCE (VOIDmode, rtvec_alloc (num_regs + 1));
+
+  /* RTLs cannot be shared, hence create new copy for dwarf.  */
+  tmp1 = gen_rtx_SET (VOIDmode,
+                     stack_pointer_rtx,
+                     plus_constant (stack_pointer_rtx, -4 * num_regs));
+  RTX_FRAME_RELATED_P (tmp1) = 1;
+  XVECEXP (dwarf, 0, 0) = tmp1;
+
+  for (i = num_regs - 1, j = LAST_ARM_REGNUM; i >= (num_regs % 2); j--)
+    /* Var j iterates over all the registers to gather all the registers in
+       saved_regs_mask.  Var i gives index of register R_j in stack frame.
+       A PARALLEL RTX of register-pair is created here, so that pattern for
+       STRD can be matched.  If num_regs is odd, 1st register will be pushed
+       using STR and remaining registers will be pushed with STRD in pairs.
+       If num_regs is even, all registers are pushed with STRD in pairs.
+       Hence, skip first element for odd num_regs.  */
+    if (saved_regs_mask & (1 << j))
+      {
+        gcc_assert (j != SP_REGNUM);
+        gcc_assert (j != PC_REGNUM);
+
+        /* Create RTX for store.  New RTX is created for dwarf as
+           they are not sharable.  */
+        reg = gen_rtx_REG (SImode, j);
+        tmp = gen_rtx_SET (SImode,
+                           gen_frame_mem
+                           (SImode,
+                            plus_constant (stack_pointer_rtx, 4 * i)),
+                           reg);
+
+        tmp1 = gen_rtx_SET (SImode,
+                           gen_frame_mem
+                           (SImode,
+                            plus_constant (stack_pointer_rtx, 4 * i)),
+                           reg);
+        RTX_FRAME_RELATED_P (tmp) = 1;
+        RTX_FRAME_RELATED_P (tmp1) = 1;
+
+        if (((i - (num_regs % 2)) % 2) == 1)
+          /* When (i - (num_regs % 2)) is odd, the RTX to be emitted is yet to
+             be created.  Hence create it first.  The STRD pattern we are
+             generating is :
+             [ (SET (MEM (PLUS (SP) (NUM))) (reg_t1))
+               (SET (MEM (PLUS (SP) (NUM + 4))) (reg_t2)) ]
+             were target registers need not be consecutive.  */
+          par = gen_rtx_PARALLEL (VOIDmode, rtvec_alloc (2));
+
+        /* Register R_j is added in PARALLEL RTX.  If (i - (num_regs % 2)) is
+           even, the reg_j is added as 0th element and if it is odd, reg_i is
+           added as 1st element of STRD pattern shown above.  */
+        XVECEXP (par, 0, ((i - (num_regs % 2)) % 2)) = tmp;
+        XVECEXP (dwarf, 0, (i + 1)) = tmp1;
+
+        if (((i - (num_regs % 2)) % 2) == 0)
+          /* When (i - (num_regs % 2)) is even, RTXs for both the registers
+             to be loaded are generated in above given STRD pattern, and the
+             pattern can be emitted now.  */
+          emit_insn (par);
+
+        i--;
+      }
+
+  if ((num_regs % 2) == 1)
+    {
+      /* If odd number of registers are pushed, generate STR pattern to store
+         lone register.  */
+      for (; (saved_regs_mask & (1 << j)) == 0; j--);
+
+      tmp1 = gen_frame_mem (SImode, plus_constant (stack_pointer_rtx, 4 * i));
+      reg = gen_rtx_REG (SImode, j);
+      tmp = gen_rtx_SET (SImode, tmp1, reg);
+      RTX_FRAME_RELATED_P (tmp) = 1;
+
+      emit_insn (tmp);
+
+      tmp1 = gen_rtx_SET (SImode,
+                         gen_frame_mem
+                         (SImode,
+                          plus_constant (stack_pointer_rtx, 4 * i)),
+                         reg);
+      RTX_FRAME_RELATED_P (tmp1) = 1;
+      XVECEXP (dwarf, 0, (i + 1)) = tmp1;
+    }
+
+  add_reg_note (insn, REG_FRAME_RELATED_EXPR, dwarf);
+  RTX_FRAME_RELATED_P (insn) = 1;
+  return;
+}
+
 /* Generate and emit an insn that we will recognize as a push_multi.
    Unfortunately, since this insn does not reflect very well the actual
    semantics of the operation, we need to annotate the insn for the benefit
@@ -16307,8 +16426,16 @@ arm_expand_prologue (void)
 	      saved_regs += frame;
 	    }
 	}
-      insn = emit_multi_reg_push (live_regs_mask);
-      RTX_FRAME_RELATED_P (insn) = 1;
+
+      if (TARGET_THUMB2 && current_tune->prefer_ldrd_strd && !optimize_size)
+        {
+          thumb2_emit_strd_push (live_regs_mask);
+        }
+      else
+        {
+          insn = emit_multi_reg_push (live_regs_mask);
+          RTX_FRAME_RELATED_P (insn) = 1;
+        }
     }
 
   if (! IS_VOLATILE (func_type))
diff --git a/gcc/config/arm/ldmstm.md b/gcc/config/arm/ldmstm.md
index 21d2815..e3dcd4f 100644
--- a/gcc/config/arm/ldmstm.md
+++ b/gcc/config/arm/ldmstm.md
@@ -47,6 +47,32 @@
   [(set_attr "type" "load2")
    (set_attr "predicable" "yes")])
 
+(define_insn "*thumb2_strd_base"
+  [(set (mem:SI (match_operand:SI 0 "s_register_operand" "rk"))
+        (match_operand:SI 1 "register_operand" "r"))
+   (set (mem:SI (plus:SI (match_dup 0)
+                         (const_int 4)))
+        (match_operand:SI 2 "register_operand" "r"))]
+  "(TARGET_THUMB2 && current_tune->prefer_ldrd_strd
+     && (!bad_reg_pair_for_thumb_ldrd_strd (operands[1], operands[2])))"
+  "strd%?\t%1, %2, [%0]"
+  [(set_attr "type" "store2")
+   (set_attr "predicable" "yes")])
+
+(define_insn "*thumb2_strd"
+  [(set (mem:SI (plus:SI (match_operand:SI 0 "s_register_operand" "rk")
+                         (match_operand:SI 1 "ldrd_immediate_operand" "Pz")))
+        (match_operand:SI 2 "register_operand" "r"))
+   (set (mem:SI (plus:SI (match_dup 0)
+                         (match_operand:SI 3 "const_int_operand" "")))
+        (match_operand:SI 4 "register_operand" "r"))]
+  "(TARGET_THUMB2 && current_tune->prefer_ldrd_strd
+     && ((INTVAL (operands[1]) + 4) == INTVAL (operands[3]))
+     && (!bad_reg_pair_for_thumb_ldrd_strd (operands[2], operands[4])))"
+  "strd%?\t%2, %4, [%0, %1]"
+  [(set_attr "type" "store2")
+   (set_attr "predicable" "yes")])
+
 (define_insn "*ldm4_ia"
   [(match_parallel 0 "load_multiple_operation"
     [(set (match_operand:SI 1 "arm_hard_register_operand" "")