Re: [PATCH v2] rs6000: Add new pass for replacement of contiguous addresses vector load lxv with lxvp

[Michael Meissner <meissner@linux.ibm.com>]

On Wed, Dec 06, 2023 at 10:22:57AM +0800, Kewen.Lin wrote:
> I'd expect you use UNSPEC_MMA_EXTRACT to extract V16QI from the result of lxvp,
> the current define_insn_and_split "*vsx_disassemble_pair" should be able to take
> care of it further (eg: reg and regoff).
> 
> BR,
> Kewen

With Peter's subreg patch, UNSPEC_MMA_EXTRACT would produce two move with
eSUBREGs:

For a FMA type loop such as:

union vector_hack2 {
  vector  unsigned char vuc[2];
  vector double v[2];
};

static void
use_mma_ld_st_normal_no_unroll (double * __restrict__ r,
				const double * __restrict__ a,
				const double * __restrict__ b,
				size_t num)
{
  __vector_pair * __restrict__ v_r = ( __vector_pair * __restrict__) r;
  const __vector_pair * __restrict__ v_a = (const __vector_pair * __restrict__) a;
  const __vector_pair * __restrict__ v_b = (const __vector_pair * __restrict__) b;
  size_t num_vector = num / (2 * (sizeof (vector double) / sizeof (double)));
  size_t num_scalar = num % (2 * (sizeof (vector double) / sizeof (double)));
  size_t i;
  union vector_hack2 a_union;
  union vector_hack2 b_union;
  union vector_hack2 r_union;
  vector double a_hi, a_lo;
  vector double b_hi, b_lo;
  vector double r_hi, r_lo;
  union vector_hack result_hi, result_lo;

#pragma GCC unroll 0
  for (i = 0; i < num_vector; i++)
    {
      __builtin_vsx_disassemble_pair (&a_union.vuc, &v_a[i]);
      __builtin_vsx_disassemble_pair (&b_union.vuc, &v_b[i]);
      __builtin_vsx_disassemble_pair (&r_union.vuc, &v_r[i]);

      a_hi = a_union.v[0];
      b_hi = b_union.v[0];
      r_hi = r_union.v[0];

      a_lo = a_union.v[1];
      b_lo = b_union.v[1];
      r_lo = r_union.v[1];

      result_hi.v = (a_hi * b_hi) + r_hi;
      result_lo.v = (a_lo * b_lo) + r_lo;

      __builtin_vsx_build_pair (&v_r[i], result_hi.vuc, result_lo.vuc);
    }

  if (num_scalar)
    {
      r += num_vector * (2 * (sizeof (vector double) / sizeof (double)));
      a += num_vector * (2 * (sizeof (vector double) / sizeof (double)));
      b += num_vector * (2 * (sizeof (vector double) / sizeof (double)));

#pragma GCC unroll 0
      for (i = 0; i < num_scalar; i++)
 r[i] += (a[i] * b[i]);
    }

  return;
}

Peter's code would produce the following in the inner loop:

(insn 16 15 19 4 (set (reg:OO 133 [ _43 ])
        (mem:OO (plus:DI (reg/v/f:DI 150 [ a ])
                (reg:DI 143 [ ivtmp.1088 ])) [6 MEM[(__vector_pair *)a_30(D) + ivtmp.1088_88 * 1]+0 S32 A128])) "p10-fma.h":3285:1 2181 {*movoo}
     (nil))
(insn 19 16 22 4 (set (reg:OO 136 [ _48 ])
        (mem:OO (plus:DI (reg/v/f:DI 151 [ b ])
                (reg:DI 143 [ ivtmp.1088 ])) [6 MEM[(__vector_pair *)b_31(D) + ivtmp.1088_88 * 1]+0 S32 A128])) "p10-fma.h":3285:1 2181 {*movoo}
     (nil))
(insn 22 19 25 4 (set (reg:OO 139 [ _53 ])
        (mem:OO (plus:DI (reg/v/f:DI 149 [ r ])
                (reg:DI 143 [ ivtmp.1088 ])) [6 MEM[(__vector_pair *)r_29(D) + ivtmp.1088_88 * 1]+0 S32 A128])) "p10-fma.h":3285:1 2181 {*movoo}
     (nil))
(insn 25 22 26 4 (set (reg:V2DF 117 [ _6 ])
        (fma:V2DF (subreg:V2DF (reg:OO 136 [ _48 ]) 16)
            (subreg:V2DF (reg:OO 133 [ _43 ]) 16)
            (subreg:V2DF (reg:OO 139 [ _53 ]) 16))) "p10-fma.h":3319:35 1265 {*vsx_fmav2df4}
     (nil))
(insn 26 25 27 4 (set (reg:V2DF 118 [ _8 ])
        (fma:V2DF (subreg:V2DF (reg:OO 136 [ _48 ]) 0)
            (subreg:V2DF (reg:OO 133 [ _43 ]) 0)
            (subreg:V2DF (reg:OO 139 [ _53 ]) 0))) "p10-fma.h":3320:35 1265 {*vsx_fmav2df4}
     (expr_list:REG_DEAD (reg:OO 139 [ _53 ])
        (expr_list:REG_DEAD (reg:OO 136 [ _48 ])
            (expr_list:REG_DEAD (reg:OO 133 [ _43 ])
                (nil)))))
(insn 27 26 28 4 (set (reg:OO 142 [ _59 ])
        (unspec:OO [
                (subreg:V16QI (reg:V2DF 117 [ _6 ]) 0)
                (subreg:V16QI (reg:V2DF 118 [ _8 ]) 0)
            ] UNSPEC_VSX_ASSEMBLE)) 2183 {*vsx_assemble_pair}
     (expr_list:REG_DEAD (reg:V2DF 118 [ _8 ])
        (expr_list:REG_DEAD (reg:V2DF 117 [ _6 ])
            (nil))))

Now in theory you could get ride of the UNSPEC_VSX_ASSEMBLE also using SUBREG's.

-- 
Michael Meissner, IBM
PO Box 98, Ayer, Massachusetts, USA, 01432
email: meissner@linux.ibm.com