Re: [PATCH 2/2] aarch64: Support `{1.0f, 1.0f, 0.0, 0.0}` CST forming with fmov with a smaller vector type.

[Richard Sandiford <richard.sandiford@arm.com>]

Andrew Pinski <quic_apinski@quicinc.com> writes:
> This enables construction of V4SF CST like `{1.0f, 1.0f, 0.0f, 0.0f}`
> (and other fp enabled CSTs) by using `fmov v0.2s, 1.0` as the instruction
> is designed to zero out the other bits.
> This is a small extension on top of the code that creates fmov for the case
> where the all but the first element is non-zero.

Similarly to the second reply to 1/2, I think we should handle this
by detecting when only the low 64 bits are nonzero, and then try to
construct a simd_immediate_info for the low 64 bits.  The technique
is more general than just floats.

The same thing would work for SVE too (if TARGET_SIMD).

Thanks,
Richard

> Built and tested for aarch64-linux-gnu with no regressions.
>
> 	PR target/113856
>
> gcc/ChangeLog:
>
> 	* config/aarch64/aarch64.cc (simd_immediate_info): Add bool to the
> 	float mode constructor. Document modifier field for FMOV_SDH.
> 	(aarch64_simd_valid_immediate): Recognize where the first half
> 	of the const float vect is the same.
> 	(aarch64_output_simd_mov_immediate): Handle the case where insn is
> 	FMOV_SDH and modifier is MSL.
>
> gcc/testsuite/ChangeLog:
>
> 	* gcc.target/aarch64/fmov-zero-cst-3.c: New test.
>
> Signed-off-by: Andrew Pinski <quic_apinski@quicinc.com>
> ---
>  gcc/config/aarch64/aarch64.cc                 | 34 ++++++++++++++++---
>  .../gcc.target/aarch64/fmov-zero-cst-3.c      | 28 +++++++++++++++
>  2 files changed, 57 insertions(+), 5 deletions(-)
>  create mode 100644 gcc/testsuite/gcc.target/aarch64/fmov-zero-cst-3.c
>
> diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
> index c4386591a9b..89bd0c5e5a6 100644
> --- a/gcc/config/aarch64/aarch64.cc
> +++ b/gcc/config/aarch64/aarch64.cc
> @@ -130,7 +130,7 @@ struct simd_immediate_info
>    enum modifier_type { LSL, MSL };
>  
>    simd_immediate_info () {}
> -  simd_immediate_info (scalar_float_mode, rtx, insn_type = MOV);
> +  simd_immediate_info (scalar_float_mode, rtx, insn_type = MOV, bool = false);
>    simd_immediate_info (scalar_int_mode, unsigned HOST_WIDE_INT,
>  		       insn_type = MOV, modifier_type = LSL,
>  		       unsigned int = 0);
> @@ -153,6 +153,8 @@ struct simd_immediate_info
>  
>        /* The kind of shift modifier to use, and the number of bits to shift.
>  	 This is (LSL, 0) if no shift is needed.  */
> +      /* For FMOV_SDH, LSL says it is a single while MSL
> +	 says if it is either .4h/.2s fmov. */
>        modifier_type modifier;
>        unsigned int shift;
>      } mov;
> @@ -173,12 +175,12 @@ struct simd_immediate_info
>  /* Construct a floating-point immediate in which each element has mode
>     ELT_MODE_IN and value VALUE_IN.  */
>  inline simd_immediate_info
> -::simd_immediate_info (scalar_float_mode elt_mode_in, rtx value_in, insn_type insn_in)
> +::simd_immediate_info (scalar_float_mode elt_mode_in, rtx value_in, insn_type insn_in, bool firsthalfsame)
>    : elt_mode (elt_mode_in), insn (insn_in)
>  {
>    gcc_assert (insn_in == MOV || insn_in == FMOV_SDH);
>    u.mov.value = value_in;
> -  u.mov.modifier = LSL;
> +  u.mov.modifier = firsthalfsame ? MSL : LSL;
>    u.mov.shift = 0;
>  }
>  
> @@ -22944,10 +22946,23 @@ aarch64_simd_valid_immediate (rtx op, simd_immediate_info *info,
>  	  || aarch64_float_const_representable_p (elt))
>  	{
>  	  bool valid = true;
> +	  bool firsthalfsame = false;
>  	  for (unsigned int i = 1; i < n_elts; i++)
>  	    {
>  	      rtx elt1 = CONST_VECTOR_ENCODED_ELT (op, i);
>  	      if (!aarch64_float_const_zero_rtx_p (elt1))
> +		{
> +		  if (i == 1)
> +		    firsthalfsame = true;
> +		  if (!firsthalfsame
> +		      || i >= n_elts/2
> +		      || !rtx_equal_p (elt, elt1))
> +		    {
> +		      valid = false;
> +		      break;
> +		    }
> +		}
> +	      else if (firsthalfsame && i < n_elts/2)
>  		{
>  		  valid = false;
>  		  break;
> @@ -22957,7 +22972,8 @@ aarch64_simd_valid_immediate (rtx op, simd_immediate_info *info,
>  	    {
>  	      if (info)
>  		*info = simd_immediate_info (elt_float_mode, elt,
> -					     simd_immediate_info::FMOV_SDH);
> +					     simd_immediate_info::FMOV_SDH,
> +					     firsthalfsame);
>  	      return true;
>  	    }
>  	}
> @@ -25165,8 +25181,16 @@ aarch64_output_simd_mov_immediate (rtx const_vector, unsigned width,
>  	  real_to_decimal_for_mode (float_buf,
>  				    CONST_DOUBLE_REAL_VALUE (info.u.mov.value),
>  				    buf_size, buf_size, 1, info.elt_mode);
> -	  if (info.insn == simd_immediate_info::FMOV_SDH)
> +	  if (info.insn == simd_immediate_info::FMOV_SDH
> +	      && info.u.mov.modifier == simd_immediate_info::LSL)
>  	    snprintf (templ, sizeof (templ), "fmov\t%%%c0, %s", element_char, float_buf);
> +	  else if (info.insn == simd_immediate_info::FMOV_SDH
> +	      && info.u.mov.modifier == simd_immediate_info::MSL)
> +	    {
> +	      gcc_assert (element_char != 'd');
> +	      gcc_assert (lane_count > 2);
> +	      snprintf (templ, sizeof (templ), "fmov\t%%0.%d%c, %s", lane_count/2, element_char, float_buf);
> +	    }
>  	  else if (lane_count == 1)
>  	    snprintf (templ, sizeof (templ), "fmov\t%%d0, %s", float_buf);
>  	  else
> diff --git a/gcc/testsuite/gcc.target/aarch64/fmov-zero-cst-3.c b/gcc/testsuite/gcc.target/aarch64/fmov-zero-cst-3.c
> new file mode 100644
> index 00000000000..7a78b6d3caf
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/aarch64/fmov-zero-cst-3.c
> @@ -0,0 +1,28 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mcmodel=tiny" } */
> +/* { dg-final { check-function-bodies "**" "" ""  } } */
> +/* PR target/113856 */
> +
> +#define vect64 __attribute__((vector_size(8) ))
> +#define vect128 __attribute__((vector_size(16) ))
> +
> +/*
> +** f2:
> +**	fmov	v0.2s, 1.0e\+0
> +**	ret
> +*/
> +vect128 float f2()
> +{
> +  return (vect128 float){1.0f, 1.0f, 0, 0};
> +}
> +
> +/*
> +** f3:
> +**	ldr	q0, \.LC[0-9]+
> +**	ret
> +*/
> +vect128 float f3()
> +{
> +  return (vect128 float){1.0f, 1.0f, 1.0f, 0.0};
> +}
> +