Modify aarch64_expand_subvti into a form that handles all
addition and subtraction, modulo, signed or unsigned overflow.
Use expand_insn to put the operands into the proper form,
and do not force values into register if not required.
* config/aarch64/aarch64.c (aarch64_ti_split) New.
(aarch64_addti_scratch_regs): Remove.
(aarch64_subvti_scratch_regs): Remove.
(aarch64_expand_subvti): Remove.
(aarch64_expand_addsubti): New.
* config/aarch64/aarch64-protos.h: Update to match.
* config/aarch64/aarch64.md (addti3): Use aarch64_expand_addsubti.
(addvti4, uaddvti4): Likewise.
(subvti4, usubvti4): Likewise.
(subti3): Likewise; accept immediates for operand 2.
---
gcc/config/aarch64/aarch64-protos.h | 10 +--
gcc/config/aarch64/aarch64.c | 129 +++++++++-------------------
gcc/config/aarch64/aarch64.md | 125 ++++++---------------------
3 files changed, 67 insertions(+), 197 deletions(-)
diff --git a/gcc/config/aarch64/aarch64-protos.h
b/gcc/config/aarch64/aarch64-protos.h
index d6d668ea920..787085b24d2 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -630,16 +630,8 @@ void aarch64_reset_previous_fndecl (void);
bool aarch64_return_address_signing_enabled (void);
bool aarch64_bti_enabled (void);
void aarch64_save_restore_target_globals (tree);
-void aarch64_addti_scratch_regs (rtx, rtx, rtx *,
- rtx *, rtx *,
- rtx *, rtx *,
- rtx *);
-void aarch64_subvti_scratch_regs (rtx, rtx, rtx *,
- rtx *, rtx *,
- rtx *, rtx *, rtx *);
-void aarch64_expand_subvti (rtx, rtx, rtx,
- rtx, rtx, rtx, rtx, bool);
+void aarch64_expand_addsubti (rtx, rtx, rtx, int, int, int);
/* Initialize builtins for SIMD intrinsics. */
void init_aarch64_simd_builtins (void);
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 7a13a8e8ec4..6263897c9a0 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -20241,110 +20241,61 @@ aarch64_gen_unlikely_cbranch (enum rtx_code code,
machine_mode cc_mode,
aarch64_emit_unlikely_jump (gen_rtx_SET (pc_rtx, x));
}
-/* Generate DImode scratch registers for 128-bit (TImode) addition.
+/* Generate DImode scratch registers for 128-bit (TImode) add/sub.
+ INPUT represents the TImode input operand
+ LO represents the low half (DImode) of the TImode operand
+ HI represents the high half (DImode) of the TImode operand. */
- OP1 represents the TImode destination operand 1
- OP2 represents the TImode destination operand 2
- LOW_DEST represents the low half (DImode) of TImode operand 0
- LOW_IN1 represents the low half (DImode) of TImode operand 1
- LOW_IN2 represents the low half (DImode) of TImode operand 2
- HIGH_DEST represents the high half (DImode) of TImode operand 0
- HIGH_IN1 represents the high half (DImode) of TImode operand 1
- HIGH_IN2 represents the high half (DImode) of TImode operand 2. */
-
-void
-aarch64_addti_scratch_regs (rtx op1, rtx op2, rtx *low_dest,
- rtx *low_in1, rtx *low_in2,
- rtx *high_dest, rtx *high_in1,
- rtx *high_in2)
+static void
+aarch64_ti_split (rtx input, rtx *lo, rtx *hi)
{
- *low_dest = gen_reg_rtx (DImode);
- *low_in1 = gen_lowpart (DImode, op1);
- *low_in2 = simplify_gen_subreg (DImode, op2, TImode,
- subreg_lowpart_offset (DImode, TImode));
- *high_dest = gen_reg_rtx (DImode);
- *high_in1 = gen_highpart (DImode, op1);
- *high_in2 = simplify_gen_subreg (DImode, op2, TImode,
- subreg_highpart_offset (DImode, TImode));
+ *lo = simplify_gen_subreg (DImode, input, TImode,
+ subreg_lowpart_offset (DImode, TImode));
+ *hi = simplify_gen_subreg (DImode, input, TImode,
+ subreg_highpart_offset (DImode, TImode));
}
-/* Generate DImode scratch registers for 128-bit (TImode) subtraction.
-
- This function differs from 'arch64_addti_scratch_regs' in that
- OP1 can be an immediate constant (zero). We must call
- subreg_highpart_offset with DImode and TImode arguments, otherwise
- VOIDmode will be used for the const_int which generates an internal
- error from subreg_size_highpart_offset which does not expect a size of zero.
-
- OP1 represents the TImode destination operand 1
- OP2 represents the TImode destination operand 2
- LOW_DEST represents the low half (DImode) of TImode operand 0
- LOW_IN1 represents the low half (DImode) of TImode operand 1
- LOW_IN2 represents the low half (DImode) of TImode operand 2
- HIGH_DEST represents the high half (DImode) of TImode operand 0
- HIGH_IN1 represents the high half (DImode) of TImode operand 1
- HIGH_IN2 represents the high half (DImode) of TImode operand 2. */
-
-
-void
-aarch64_subvti_scratch_regs (rtx op1, rtx op2, rtx *low_dest,
- rtx *low_in1, rtx *low_in2,
- rtx *high_dest, rtx *high_in1,
- rtx *high_in2)
-{
- *low_dest = gen_reg_rtx (DImode);
- *low_in1 = simplify_gen_subreg (DImode, op1, TImode,
- subreg_lowpart_offset (DImode, TImode));
-
- *low_in2 = simplify_gen_subreg (DImode, op2, TImode,
- subreg_lowpart_offset (DImode, TImode));
- *high_dest = gen_reg_rtx (DImode);
-
- *high_in1 = simplify_gen_subreg (DImode, op1, TImode,
- subreg_highpart_offset (DImode, TImode));
- *high_in2 = simplify_gen_subreg (DImode, op2, TImode,
- subreg_highpart_offset (DImode, TImode));
-}
-
-/* Generate RTL for 128-bit (TImode) subtraction with overflow.
-
+/* Generate RTL for 128-bit (TImode) addition or subtraction.
OP0 represents the TImode destination operand 0
- LOW_DEST represents the low half (DImode) of TImode operand 0
- LOW_IN1 represents the low half (DImode) of TImode operand 1
- LOW_IN2 represents the low half (DImode) of TImode operand 2
- HIGH_DEST represents the high half (DImode) of TImode operand 0
- HIGH_IN1 represents the high half (DImode) of TImode operand 1
- HIGH_IN2 represents the high half (DImode) of TImode operand 2
- UNSIGNED_P is true if the operation is being performed on unsigned
- values. */
+ OP1 and OP2 represent the TImode input operands.
+
+ Normal or Overflow behaviour is obtained via the INSN_CODE operands:
+ CODE_HI_LO0 is used when the low half of OP2 == 0, otherwise
+ CODE_LO is used on the low halves,
+ CODE_HI is used on the high halves. */
+
void
-aarch64_expand_subvti (rtx op0, rtx low_dest, rtx low_in1,
- rtx low_in2, rtx high_dest, rtx high_in1,
- rtx high_in2, bool unsigned_p)
+aarch64_expand_addsubti (rtx op0, rtx op1, rtx op2,
+ int code_hi_lo0, int code_lo, int code_hi)
{
- if (low_in2 == const0_rtx)
+ rtx low_dest, low_op1, low_op2, high_dest, high_op1, high_op2;
+ struct expand_operand ops[3];
+
+ aarch64_ti_split (op1, &low_op1, &high_op1);
+ aarch64_ti_split (op2, &low_op2, &high_op2);
+
+ if (low_op2 == const0_rtx)
{
- low_dest = low_in1;
- high_in2 = force_reg (DImode, high_in2);
- if (unsigned_p)
- emit_insn (gen_subdi3_compare1 (high_dest, high_in1, high_in2));
- else
- emit_insn (gen_subvdi_insn (high_dest, high_in1, high_in2));
+ low_dest = low_op1;
+ code_hi = code_hi_lo0;
}
else
{
- emit_insn (gen_subdi3_compare1 (low_dest, low_in1, low_in2));
-
- high_in2 = force_reg (DImode, high_in2);
- if (unsigned_p)
- emit_insn (gen_usubdi3_carryinC (high_dest, high_in1, high_in2));
- else
- emit_insn (gen_subdi3_carryinV (high_dest, high_in1, high_in2));
+ low_dest = gen_reg_rtx (DImode);
+ create_output_operand(&ops[0], low_dest, DImode);
+ create_input_operand(&ops[1], low_op1, DImode);
+ create_input_operand(&ops[2], low_op2, DImode);
+ expand_insn ((insn_code)code_lo, 3, ops);
}
+ high_dest = gen_reg_rtx (DImode);
+ create_output_operand(&ops[0], high_dest, DImode);
+ create_input_operand(&ops[1], high_op1, DImode);
+ create_input_operand(&ops[2], high_op2, DImode);
+ expand_insn ((insn_code)code_hi, 3, ops);
+
emit_move_insn (gen_lowpart (DImode, op0), low_dest);
emit_move_insn (gen_highpart (DImode, op0), high_dest);
-
}
/* Implement the TARGET_ASAN_SHADOW_OFFSET hook. */
diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index d6389cc8148..532c114a42e 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -2044,30 +2044,10 @@
(match_operand:TI 2 "aarch64_reg_or_imm")))]
""
{
- rtx low_dest, op1_low, op2_low, high_dest, op1_high, op2_high;
-
- aarch64_addti_scratch_regs (operands[1], operands[2],
- &low_dest, &op1_low, &op2_low,
- &high_dest, &op1_high, &op2_high);
-
- if (op2_low == const0_rtx)
- {
- low_dest = op1_low;
- if (!aarch64_pluslong_operand (op2_high, DImode))
- op2_high = force_reg (DImode, op2_high);
- emit_insn (gen_adddi3 (high_dest, op1_high, op2_high));
- }
- else
- {
- emit_insn (gen_adddi3_compareC (low_dest, op1_low,
- force_reg (DImode, op2_low)));
- emit_insn (gen_adddi3_carryin (high_dest, op1_high,
- force_reg (DImode, op2_high)));
- }
-
- emit_move_insn (gen_lowpart (DImode, operands[0]), low_dest);
- emit_move_insn (gen_highpart (DImode, operands[0]), high_dest);
-
+ aarch64_expand_addsubti (operands[0], operands[1], operands[2],
+ CODE_FOR_adddi3,
+ CODE_FOR_adddi3_compareC,
+ CODE_FOR_adddi3_carryin);
DONE;
})
@@ -2078,29 +2058,10 @@
(label_ref (match_operand 3 "" ""))]
""
{
- rtx low_dest, op1_low, op2_low, high_dest, op1_high, op2_high;
-
- aarch64_addti_scratch_regs (operands[1], operands[2],
- &low_dest, &op1_low, &op2_low,
- &high_dest, &op1_high, &op2_high);
-
- if (op2_low == const0_rtx)
- {
- low_dest = op1_low;
- emit_insn (gen_adddi3_compareV (high_dest, op1_high,
- force_reg (DImode, op2_high)));
- }
- else
- {
- emit_insn (gen_adddi3_compareC (low_dest, op1_low,
- force_reg (DImode, op2_low)));
- emit_insn (gen_adddi3_carryinV (high_dest, op1_high,
- force_reg (DImode, op2_high)));
- }
-
- emit_move_insn (gen_lowpart (DImode, operands[0]), low_dest);
- emit_move_insn (gen_highpart (DImode, operands[0]), high_dest);
-
+ aarch64_expand_addsubti (operands[0], operands[1], operands[2],
+ CODE_FOR_adddi3_compareV,
+ CODE_FOR_adddi3_compareC,
+ CODE_FOR_adddi3_carryinV);
aarch64_gen_unlikely_cbranch (NE, CC_Vmode, operands[3]);
DONE;
})
@@ -2112,32 +2073,13 @@
(label_ref (match_operand 3 "" ""))]
""
{
- rtx low_dest, op1_low, op2_low, high_dest, op1_high, op2_high;
-
- aarch64_addti_scratch_regs (operands[1], operands[2],
- &low_dest, &op1_low, &op2_low,
- &high_dest, &op1_high, &op2_high);
-
- if (op2_low == const0_rtx)
- {
- low_dest = op1_low;
- emit_insn (gen_adddi3_compareC (high_dest, op1_high,
- force_reg (DImode, op2_high)));
- }
- else
- {
- emit_insn (gen_adddi3_compareC (low_dest, op1_low,
- force_reg (DImode, op2_low)));
- emit_insn (gen_adddi3_carryinC (high_dest, op1_high,
- force_reg (DImode, op2_high)));
- }
-
- emit_move_insn (gen_lowpart (DImode, operands[0]), low_dest);
- emit_move_insn (gen_highpart (DImode, operands[0]), high_dest);
-
+ aarch64_expand_addsubti (operands[0], operands[1], operands[2],
+ CODE_FOR_adddi3_compareC,
+ CODE_FOR_adddi3_compareC,
+ CODE_FOR_adddi3_carryinC);
aarch64_gen_unlikely_cbranch (GEU, CC_ADCmode, operands[3]);
DONE;
- })
+})
(define_insn "add<mode>3_compare0"
[(set (reg:CC_NZ CC_REGNUM)
@@ -2980,20 +2922,13 @@
(define_expand "subti3"
[(set (match_operand:TI 0 "register_operand")
(minus:TI (match_operand:TI 1 "aarch64_reg_or_zero")
- (match_operand:TI 2 "register_operand")))]
+ (match_operand:TI 2 "aarch64_reg_or_imm")))]
""
{
- rtx low_dest, op1_low, op2_low, high_dest, op1_high, op2_high;
-
- aarch64_subvti_scratch_regs (operands[1], operands[2],
- &low_dest, &op1_low, &op2_low,
- &high_dest, &op1_high, &op2_high);
-
- emit_insn (gen_subdi3_compare1 (low_dest, op1_low, op2_low));
- emit_insn (gen_subdi3_carryin (high_dest, op1_high, op2_high));
-
- emit_move_insn (gen_lowpart (DImode, operands[0]), low_dest);
- emit_move_insn (gen_highpart (DImode, operands[0]), high_dest);
+ aarch64_expand_addsubti (operands[0], operands[1], operands[2],
+ CODE_FOR_subdi3,
+ CODE_FOR_subdi3_compare1,
+ CODE_FOR_subdi3_carryin);
DONE;
})
@@ -3004,14 +2939,10 @@
(label_ref (match_operand 3 "" ""))]
""
{
- rtx low_dest, op1_low, op2_low, high_dest, op1_high, op2_high;
-
- aarch64_subvti_scratch_regs (operands[1], operands[2],
- &low_dest, &op1_low, &op2_low,
- &high_dest, &op1_high, &op2_high);
- aarch64_expand_subvti (operands[0], low_dest, op1_low, op2_low,
- high_dest, op1_high, op2_high, false);
-
+ aarch64_expand_addsubti (operands[0], operands[1], operands[2],
+ CODE_FOR_subvdi_insn,
+ CODE_FOR_subdi3_compare1,
+ CODE_FOR_subdi3_carryinV);
aarch64_gen_unlikely_cbranch (NE, CC_Vmode, operands[3]);
DONE;
})
@@ -3023,14 +2954,10 @@
(label_ref (match_operand 3 "" ""))]
""
{
- rtx low_dest, op1_low, op2_low, high_dest, op1_high, op2_high;
-
- aarch64_subvti_scratch_regs (operands[1], operands[2],
- &low_dest, &op1_low, &op2_low,
- &high_dest, &op1_high, &op2_high);
- aarch64_expand_subvti (operands[0], low_dest, op1_low, op2_low,
- high_dest, op1_high, op2_high, true);
-
+ aarch64_expand_addsubti (operands[0], operands[1], operands[2],
+ CODE_FOR_subdi3_compare1,
+ CODE_FOR_subdi3_compare1,
+ CODE_FOR_usubdi3_carryinC);
aarch64_gen_unlikely_cbranch (LTU, CCmode, operands[3]);
DONE;
})
--
2.20.1
