On Mon, Jul 18, 2022 at 3:59 AM liuhongt <hongtao....@intel.com> wrote:
>
> And split it after reload.
>
> >IMO, the only case it is worth adding is a direct immediate store to
> >memory, which HJ recently added.
>
> Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> Ok for trunk?
>
> gcc/ChangeLog:
>
>         PR target/106038
>         * config/i386/mmx.md (<code><mode>3): Extend to AND mem,imm,
>         and adjust below define_split.
>         (mmxinsnmode): New mode attribute.
>         (*mov<mode>_imm): Refactor with mmxinsnmode.
>         * config/i386/predicates.md
>         (register_or_x86_64_const_vector_operand): New predicate.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.target/i386/pr106038-1.c: New test.
> ---
>  gcc/config/i386/mmx.md                     | 58 +++++++++++-----------
>  gcc/config/i386/predicates.md              |  4 ++
>  gcc/testsuite/gcc.target/i386/pr106038-1.c | 27 ++++++++++
>  3 files changed, 60 insertions(+), 29 deletions(-)
>  create mode 100644 gcc/testsuite/gcc.target/i386/pr106038-1.c
>
> diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
> index 3294c1e6274..fbcb34d4395 100644
> --- a/gcc/config/i386/mmx.md
> +++ b/gcc/config/i386/mmx.md
> @@ -86,6 +86,14 @@ (define_mode_attr mmxvecsize
>    [(V8QI "b") (V4QI "b") (V2QI "b")
>     (V4HI "w") (V2HI "w") (V2SI "d") (V1DI "q")])
>
> +;; Mapping to same size integral mode.
> +(define_mode_attr mmxinsnmode
> +  [(V8QI "DI") (V4QI "SI") (V2QI "HI")
> +   (V4HI "DI") (V2HI "SI")
> +   (V2SI "DI")
> +   (V4HF "DI") (V2HF "SI")
> +   (V2SF "DI")])
> +
>  (define_mode_attr mmxdoublemode
>    [(V8QI "V8HI") (V4HI "V4SI")])
>
> @@ -350,22 +358,7 @@ (define_insn_and_split "*mov<mode>_imm"
>    HOST_WIDE_INT val = ix86_convert_const_vector_to_integer (operands[1],
>                                                             <MODE>mode);
>    operands[1] = GEN_INT (val);
> -  machine_mode mode;
> -  switch (GET_MODE_SIZE (<MODE>mode))
> -    {
> -    case 2:
> -      mode = HImode;
> -      break;
> -    case 4:
> -      mode = SImode;
> -      break;
> -    case 8:
> -      mode = DImode;
> -      break;
> -    default:
> -      gcc_unreachable ();
> -    }
> -  operands[0] = lowpart_subreg (mode, operands[0], <MODE>mode);
> +  operands[0] = lowpart_subreg (<mmxinsnmode>mode, operands[0], <MODE>mode);
>  })
>
>  ;; For TARGET_64BIT we always round up to 8 bytes.
> @@ -2975,32 +2968,39 @@ (define_insn "*mmx_<code><mode>3"
>     (set_attr "mode" "DI,TI,TI,TI")])
>
>  (define_insn "<code><mode>3"
> -  [(set (match_operand:VI_16_32 0 "register_operand" "=?r,x,x,v")
> +  [(set (match_operand:VI_16_32 0 "nonimmediate_operand" "=?r,m,x,x,v")
>          (any_logic:VI_16_32
> -         (match_operand:VI_16_32 1 "register_operand" "%0,0,x,v")
> -         (match_operand:VI_16_32 2 "register_operand" "r,x,x,v")))
> +         (match_operand:VI_16_32 1 "nonimmediate_operand" "%0,0,0,x,v")
> +         (match_operand:VI_16_32 2 "register_or_x86_64_const_vector_operand" 
> "r,i,x,x,v")))
>     (clobber (reg:CC FLAGS_REG))]
>    ""

You will need ix86_binary_operator_ok insn constraint here with
corresponding expander using ix86_fixup_binary_operands_no_copy to
prepare insn operands.

>    "#"
> -  [(set_attr "isa" "*,sse2_noavx,avx,avx512vl")
> -   (set_attr "type" "alu,sselog,sselog,sselog")
> -   (set_attr "mode" "SI,TI,TI,TI")])
> +  [(set_attr "isa" "*,*,sse2_noavx,avx,avx512vl")
> +   (set_attr "type" "alu,alu,sselog,sselog,sselog")
> +   (set_attr "mode" "SI,SI,TI,TI,TI")])
>
>  (define_split
> -  [(set (match_operand:VI_16_32 0 "general_reg_operand")
> +  [(set (match_operand:VI_16_32 0 "nonimmediate_gr_operand")
>          (any_logic:VI_16_32
> -         (match_operand:VI_16_32 1 "general_reg_operand")
> -         (match_operand:VI_16_32 2 "general_reg_operand")))
> +         (match_operand:VI_16_32 1 "nonimmediate_gr_operand")
> +         (match_operand:VI_16_32 2 
> "register_or_x86_64_const_vector_operand")))
>     (clobber (reg:CC FLAGS_REG))]
>    "reload_completed"
>    [(parallel
>       [(set (match_dup 0)
> -          (any_logic:SI (match_dup 1) (match_dup 2)))
> +          (any_logic:<mmxinsnmode> (match_dup 1) (match_dup 2)))
>        (clobber (reg:CC FLAGS_REG))])]
>  {
> -  operands[2] = lowpart_subreg (SImode, operands[2], <MODE>mode);
> -  operands[1] = lowpart_subreg (SImode, operands[1], <MODE>mode);
> -  operands[0] = lowpart_subreg (SImode, operands[0], <MODE>mode);
> +  if (GET_CODE (operands[2]) == CONST_VECTOR)

Please use if (!register_operand (operands[2], <MODE>mode)) instead.

Uros.

> +    {
> +      HOST_WIDE_INT val = ix86_convert_const_vector_to_integer (operands[2],
> +                                                               <MODE>mode);
> +      operands[2] = GEN_INT (val);
> +    }
> +  else
> +    operands[2] = lowpart_subreg (<mmxinsnmode>mode, operands[2], 
> <MODE>mode);
> +  operands[1] = lowpart_subreg (<mmxinsnmode>mode, operands[1], <MODE>mode);
> +  operands[0] = lowpart_subreg (<mmxinsnmode>mode, operands[0], <MODE>mode);
>  })
>
>  (define_split
> diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md
> index c71c453cceb..5f63a7d52f5 100644
> --- a/gcc/config/i386/predicates.md
> +++ b/gcc/config/i386/predicates.md
> @@ -1205,6 +1205,10 @@ (define_predicate "x86_64_const_vector_operand"
>    return trunc_int_for_mode (val, SImode) == val;
>  })
>
> +(define_predicate "register_or_x86_64_const_vector_operand"
> +  (ior (match_operand 0 "register_operand")
> +       (match_operand 0 "x86_64_const_vector_operand")))
> +
>  ;; Return true when OP is nonimmediate or standard SSE constant.
>  (define_predicate "nonimmediate_or_sse_const_operand"
>    (ior (match_operand 0 "nonimmediate_operand")
> diff --git a/gcc/testsuite/gcc.target/i386/pr106038-1.c 
> b/gcc/testsuite/gcc.target/i386/pr106038-1.c
> new file mode 100644
> index 00000000000..bb52385c8a5
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr106038-1.c
> @@ -0,0 +1,27 @@
> +/* { dg-do compile } */
> +/* { dg-options "-msse2 -O2" } */
> +/* { dg-final { scan-assembler-not "xmm" } } */
> +
> +void
> +foo3 (char* a, char* __restrict b)
> +{
> +  a[0] &= 1;
> +  a[1] &= 2;
> +  a[2] &= 3;
> +  a[3] &= 3;
> +}
> +
> +void
> +foo4 (char* a, char* __restrict b)
> +{
> +  a[0] &= 1;
> +  a[1] &= 2;
> +}
> +
> +
> +void
> +foo1 (short* a, short* __restrict b)
> +{
> +  a[0] &= 1;
> +  a[1] &= 2;
> +}
> --
> 2.18.1
>

Reply via email to