[2/3,v2] xtensa: Add 'adddi3' and 'subdi3' insn patterns
Checks
Commit Message
Resubmitting the correct one due to a mistake in merging order of fixes.
---
More optimized than the default RTL generation.
gcc/ChangeLog:
* config/xtensa/xtensa.md (adddi3, subdi3):
New RTL generation patterns implemented according to the instruc-
tion idioms described in the Xtensa ISA reference manual (p. 600).
---
gcc/config/xtensa/xtensa.md | 52 +++++++++++++++++++++++++++++++++++++
1 file changed, 52 insertions(+)
Comments
On Tue, May 30, 2023 at 2:50 AM Takayuki 'January June' Suwa
<jjsuwa_sys3175@yahoo.co.jp> wrote:
>
> Resubmitting the correct one due to a mistake in merging order of fixes.
> ---
> More optimized than the default RTL generation.
>
> gcc/ChangeLog:
>
> * config/xtensa/xtensa.md (adddi3, subdi3):
> New RTL generation patterns implemented according to the instruc-
> tion idioms described in the Xtensa ISA reference manual (p. 600).
> ---
> gcc/config/xtensa/xtensa.md | 52 +++++++++++++++++++++++++++++++++++++
> 1 file changed, 52 insertions(+)
>
> diff --git a/gcc/config/xtensa/xtensa.md b/gcc/config/xtensa/xtensa.md
> index eda1353894b..6882baaedfd 100644
> --- a/gcc/config/xtensa/xtensa.md
> +++ b/gcc/config/xtensa/xtensa.md
> @@ -190,6 +190,32 @@
> (set_attr "mode" "SI")
> (set_attr "length" "3")])
>
> +(define_expand "adddi3"
> + [(set (match_operand:DI 0 "register_operand")
> + (plus:DI (match_operand:DI 1 "register_operand")
> + (match_operand:DI 2 "register_operand")))]
> + ""
> +{
> + rtx lo_dest, hi_dest, lo_op0, hi_op0, lo_op1, hi_op1;
> + rtx_code_label *label;
> + lo_dest = gen_lowpart (SImode, operands[0]);
> + hi_dest = gen_highpart (SImode, operands[0]);
> + lo_op0 = gen_lowpart (SImode, operands[1]);
> + hi_op0 = gen_highpart (SImode, operands[1]);
> + lo_op1 = gen_lowpart (SImode, operands[2]);
> + hi_op1 = gen_highpart (SImode, operands[2]);
> + if (rtx_equal_p (lo_dest, lo_op1))
> + FAIL;
With this condition I see the following source
unsigned long long foo(unsigned long long a, unsigned long long b)
{
return a + b;
}
turns to (expected)
.global foo
.type foo, @function
foo:
add.n a2, a2, a4
add.n a3, a3, a5
bgeu a2, a4, .L2
addi.n a3, a3, 1
.L2:
ret.n
but
unsigned long long foo(unsigned long long a, unsigned long long b)
{
return b + a;
}
has an extra instruction:
.global foo
.type foo, @function
foo:
mov.n a9, a2
add.n a2, a4, a2
add.n a3, a5, a3
bgeu a2, a9, .L2
addi.n a3, a3, 1
.L2:
ret.n
I though that maybe the following would help (plus using
lo_cmp in the emit_cmp_and_jump_insns below):
if (!rtx_equal_p (lo_dest, lo_op0))
lo_cmp = lo_op0;
else if (!rtx_equal_p (lo_dest, lo_op1))
lo_cmp = lo_op1;
else
FAIL;
but to my surprise it doesn't.
> + emit_clobber (operands[0]);
Why is this clobber needed?
> + emit_insn (gen_addsi3 (lo_dest, lo_op0, lo_op1));
> + emit_insn (gen_addsi3 (hi_dest, hi_op0, hi_op1));
> + emit_cmp_and_jump_insns (lo_dest, lo_op1, GEU, const0_rtx,
> + SImode, true, label = gen_label_rtx ());
> + emit_insn (gen_addsi3 (hi_dest, hi_dest, const1_rtx));
> + emit_label (label);
> + DONE;
> +})
> +
> (define_insn "addsf3"
> [(set (match_operand:SF 0 "register_operand" "=f")
> (plus:SF (match_operand:SF 1 "register_operand" "%f")
> @@ -237,6 +263,32 @@
> (const_int 5)
> (const_int 6)))])
>
> +(define_expand "subdi3"
> + [(set (match_operand:DI 0 "register_operand")
> + (minus:DI (match_operand:DI 1 "register_operand")
> + (match_operand:DI 2 "register_operand")))]
> + ""
> +{
> + rtx lo_dest, hi_dest, lo_op0, hi_op0, lo_op1, hi_op1;
> + rtx_code_label *label;
> + lo_dest = gen_lowpart (SImode, operands[0]);
> + hi_dest = gen_highpart (SImode, operands[0]);
> + lo_op0 = gen_lowpart (SImode, operands[1]);
> + hi_op0 = gen_highpart (SImode, operands[1]);
> + lo_op1 = gen_lowpart (SImode, operands[2]);
> + hi_op1 = gen_highpart (SImode, operands[2]);
> + if (rtx_equal_p (lo_op0, lo_op1))
> + FAIL;
I believe that for the emit_cmp_and_jump_insns below
the check here should look like this:
if (rtx_equal_p (lo_dest, lo_op0) || rtx_equal_p (lo_dest, lo_op1))
But maybe drop this check and use the following instead?
emit_insn (gen_subsi3 (hi_dest, hi_op0, hi_op1));
emit_cmp_and_jump_insns (lo_op0, lo_op1, GEU, const0_rtx,
SImode, true, label = gen_label_rtx ());
emit_insn (gen_addsi3 (hi_dest, hi_dest, constm1_rtx));
emit_label (label);
emit_insn (gen_subsi3 (lo_dest, lo_op0, lo_op1));
> + emit_clobber (operands[0]);
Why is this clobber needed?
> + emit_insn (gen_subsi3 (lo_dest, lo_op0, lo_op1));
> + emit_insn (gen_subsi3 (hi_dest, hi_op0, hi_op1));
> + emit_cmp_and_jump_insns (lo_op0, lo_op1, GEU, const0_rtx,
> + SImode, true, label = gen_label_rtx ());
> + emit_insn (gen_addsi3 (hi_dest, hi_dest, constm1_rtx));
> + emit_label (label);
> + DONE;
> +})
> +
> (define_insn "subsf3"
> [(set (match_operand:SF 0 "register_operand" "=f")
> (minus:SF (match_operand:SF 1 "register_operand" "f")
> --
> 2.30.2
@@ -190,6 +190,32 @@
(set_attr "mode" "SI")
(set_attr "length" "3")])
+(define_expand "adddi3"
+ [(set (match_operand:DI 0 "register_operand")
+ (plus:DI (match_operand:DI 1 "register_operand")
+ (match_operand:DI 2 "register_operand")))]
+ ""
+{
+ rtx lo_dest, hi_dest, lo_op0, hi_op0, lo_op1, hi_op1;
+ rtx_code_label *label;
+ lo_dest = gen_lowpart (SImode, operands[0]);
+ hi_dest = gen_highpart (SImode, operands[0]);
+ lo_op0 = gen_lowpart (SImode, operands[1]);
+ hi_op0 = gen_highpart (SImode, operands[1]);
+ lo_op1 = gen_lowpart (SImode, operands[2]);
+ hi_op1 = gen_highpart (SImode, operands[2]);
+ if (rtx_equal_p (lo_dest, lo_op1))
+ FAIL;
+ emit_clobber (operands[0]);
+ emit_insn (gen_addsi3 (lo_dest, lo_op0, lo_op1));
+ emit_insn (gen_addsi3 (hi_dest, hi_op0, hi_op1));
+ emit_cmp_and_jump_insns (lo_dest, lo_op1, GEU, const0_rtx,
+ SImode, true, label = gen_label_rtx ());
+ emit_insn (gen_addsi3 (hi_dest, hi_dest, const1_rtx));
+ emit_label (label);
+ DONE;
+})
+
(define_insn "addsf3"
[(set (match_operand:SF 0 "register_operand" "=f")
(plus:SF (match_operand:SF 1 "register_operand" "%f")
@@ -237,6 +263,32 @@
(const_int 5)
(const_int 6)))])
+(define_expand "subdi3"
+ [(set (match_operand:DI 0 "register_operand")
+ (minus:DI (match_operand:DI 1 "register_operand")
+ (match_operand:DI 2 "register_operand")))]
+ ""
+{
+ rtx lo_dest, hi_dest, lo_op0, hi_op0, lo_op1, hi_op1;
+ rtx_code_label *label;
+ lo_dest = gen_lowpart (SImode, operands[0]);
+ hi_dest = gen_highpart (SImode, operands[0]);
+ lo_op0 = gen_lowpart (SImode, operands[1]);
+ hi_op0 = gen_highpart (SImode, operands[1]);
+ lo_op1 = gen_lowpart (SImode, operands[2]);
+ hi_op1 = gen_highpart (SImode, operands[2]);
+ if (rtx_equal_p (lo_op0, lo_op1))
+ FAIL;
+ emit_clobber (operands[0]);
+ emit_insn (gen_subsi3 (lo_dest, lo_op0, lo_op1));
+ emit_insn (gen_subsi3 (hi_dest, hi_op0, hi_op1));
+ emit_cmp_and_jump_insns (lo_op0, lo_op1, GEU, const0_rtx,
+ SImode, true, label = gen_label_rtx ());
+ emit_insn (gen_addsi3 (hi_dest, hi_dest, constm1_rtx));
+ emit_label (label);
+ DONE;
+})
+
(define_insn "subsf3"
[(set (match_operand:SF 0 "register_operand" "=f")
(minus:SF (match_operand:SF 1 "register_operand" "f")