Tamar Christina <tamar.christ...@arm.com> writes:
>> I see you've changed it from:
>>
>> + rtx cc_reg = aarch64_gen_compare_reg (code, val, const0_rtx);
>> + rtx cmp_rtx = gen_rtx_fmt_ee (code, DImode, cc_reg, const0_rtx);
>> + emit_jump_insn (gen_condjump (cmp_rtx, cc_reg, operands[3]));
>>
>> to:
>>
>> + emit_jump_insn (gen_cbranchdi4 (operands[0], val, CONST0_RTX (DImode),
>> + operands[3]));
>>
>> Was that to fix a specific problem? The original looked OK to me
>> for that part (it was the vector comparison that I was asking about).
>>
>
> No,It was to be more consistent with the Arm and MVE patch.
>
> Note that I may update the tests to disable scheduling.
>
> Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
>
> Ok for master?
>
> Thanks,
> Tamar
>
> gcc/ChangeLog:
>
> * config/aarch64/aarch64-simd.md (cbranch<mode>4): New.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/aarch64/vect-early-break-cbranch.c: New test.
>
> --- inline copy of patch ---
>
> diff --git a/gcc/config/aarch64/aarch64-simd.md
> b/gcc/config/aarch64/aarch64-simd.md
> index
> c6f2d5828373f2a5272b9d1227bfe34365f9fd09..309ec9535294d6e9cdc530f71d9fe38bb916c966
> 100644
> --- a/gcc/config/aarch64/aarch64-simd.md
> +++ b/gcc/config/aarch64/aarch64-simd.md
> @@ -3911,6 +3911,45 @@ (define_expand "vcond_mask_<mode><v_int_equiv>"
> DONE;
> })
>
> +;; Patterns comparing two vectors and conditionally jump
> +
> +(define_expand "cbranch<mode>4"
> + [(set (pc)
> + (if_then_else
> + (match_operator 0 "aarch64_equality_operator"
> + [(match_operand:VDQ_I 1 "register_operand")
> + (match_operand:VDQ_I 2 "aarch64_simd_reg_or_zero")])
> + (label_ref (match_operand 3 ""))
> + (pc)))]
> + "TARGET_SIMD"
> +{
> + auto code = GET_CODE (operands[0]);
> + rtx tmp = operands[1];
> +
> + /* If comparing against a non-zero vector we have to do a comparison first
...an EOR first
(or XOR)
OK with that change, thanks.
Richard
> + so we can have a != 0 comparison with the result. */
> + if (operands[2] != CONST0_RTX (<MODE>mode))
> + {
> + tmp = gen_reg_rtx (<MODE>mode);
> + emit_insn (gen_xor<mode>3 (tmp, operands[1], operands[2]));
> + }
> +
> + /* For 64-bit vectors we need no reductions. */
> + if (known_eq (128, GET_MODE_BITSIZE (<MODE>mode)))
> + {
> + /* Always reduce using a V4SI. */
> + rtx reduc = gen_lowpart (V4SImode, tmp);
> + rtx res = gen_reg_rtx (V4SImode);
> + emit_insn (gen_aarch64_umaxpv4si (res, reduc, reduc));
> + emit_move_insn (tmp, gen_lowpart (<MODE>mode, res));
> + }
> +
> + rtx cc_reg = aarch64_gen_compare_reg (code, val, const0_rtx);
> + rtx cmp_rtx = gen_rtx_fmt_ee (code, DImode, cc_reg, const0_rtx);
> + emit_jump_insn (gen_condjump (cmp_rtx, cc_reg, operands[3]));
> + DONE;
> +})
> +
> ;; Patterns comparing two vectors to produce a mask.
>
> (define_expand "vec_cmp<mode><mode>"
> diff --git a/gcc/testsuite/gcc.target/aarch64/vect-early-break-cbranch.c
> b/gcc/testsuite/gcc.target/aarch64/vect-early-break-cbranch.c
> new file mode 100644
> index
> 0000000000000000000000000000000000000000..c0363c3787270507d7902bb2ac0e39faef63a852
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/aarch64/vect-early-break-cbranch.c
> @@ -0,0 +1,124 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O3" } */
> +/* { dg-final { check-function-bodies "**" "" "" { target lp64 } } } */
> +
> +#pragma GCC target "+nosve"
> +
> +#define N 640
> +int a[N] = {0};
> +int b[N] = {0};
> +
> +
> +/*
> +** f1:
> +** ...
> +** cmgt v[0-9]+.4s, v[0-9]+.4s, #0
> +** umaxp v[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s
> +** fmov x[0-9]+, d[0-9]+
> +** cbnz x[0-9]+, \.L[0-9]+
> +** ...
> +*/
> +void f1 ()
> +{
> + for (int i = 0; i < N; i++)
> + {
> + b[i] += a[i];
> + if (a[i] > 0)
> + break;
> + }
> +}
> +
> +/*
> +** f2:
> +** ...
> +** cmge v[0-9]+.4s, v[0-9]+.4s, #0
> +** umaxp v[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s
> +** fmov x[0-9]+, d[0-9]+
> +** cbnz x[0-9]+, \.L[0-9]+
> +** ...
> +*/
> +void f2 ()
> +{
> + for (int i = 0; i < N; i++)
> + {
> + b[i] += a[i];
> + if (a[i] >= 0)
> + break;
> + }
> +}
> +
> +/*
> +** f3:
> +** ...
> +** cmeq v[0-9]+.4s, v[0-9]+.4s, #0
> +** umaxp v[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s
> +** fmov x[0-9]+, d[0-9]+
> +** cbnz x[0-9]+, \.L[0-9]+
> +** ...
> +*/
> +void f3 ()
> +{
> + for (int i = 0; i < N; i++)
> + {
> + b[i] += a[i];
> + if (a[i] == 0)
> + break;
> + }
> +}
> +
> +/*
> +** f4:
> +** ...
> +** cmtst v[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s
> +** umaxp v[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s
> +** fmov x[0-9]+, d[0-9]+
> +** cbnz x[0-9]+, \.L[0-9]+
> +** ...
> +*/
> +void f4 ()
> +{
> + for (int i = 0; i < N; i++)
> + {
> + b[i] += a[i];
> + if (a[i] != 0)
> + break;
> + }
> +}
> +
> +/*
> +** f5:
> +** ...
> +** cmlt v[0-9]+.4s, v[0-9]+.4s, #0
> +** umaxp v[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s
> +** fmov x[0-9]+, d[0-9]+
> +** cbnz x[0-9]+, \.L[0-9]+
> +** ...
> +*/
> +void f5 ()
> +{
> + for (int i = 0; i < N; i++)
> + {
> + b[i] += a[i];
> + if (a[i] < 0)
> + break;
> + }
> +}
> +
> +/*
> +** f6:
> +** ...
> +** cmle v[0-9]+.4s, v[0-9]+.4s, #0
> +** umaxp v[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s
> +** fmov x[0-9]+, d[0-9]+
> +** cbnz x[0-9]+, \.L[0-9]+
> +** ...
> +*/
> +void f6 ()
> +{
> + for (int i = 0; i < N; i++)
> + {
> + b[i] += a[i];
> + if (a[i] <= 0)
> + break;
> + }
> +}
