Re: [PING^3 PATCH] rs6000: Add Power10 optimization for _mm_blendv*

["Paul A. Clarke" <pc@us.ibm.com>]

On Thu, Nov 18, 2021 at 08:25:35PM -0600, Paul A. Clarke via Gcc-patches wrote:
> On Mon, Nov 08, 2021 at 11:42:27AM -0600, Paul A. Clarke via Gcc-patches wrote:
> > Gentle ping...
> 
> Gentle re-ping.

Gentle re-re-ping.

> > On Wed, Oct 20, 2021 at 08:42:07PM -0500, Paul A. Clarke via Gcc-patches wrote:
> > > Power10 ISA added `xxblendv*` instructions which are realized in the
> > > `vec_blendv` instrinsic.
> > > 
> > > Use `vec_blendv` for `_mm_blendv_epi8`, `_mm_blendv_ps`, and
> > > `_mm_blendv_pd` compatibility intrinsics, when `_ARCH_PWR10`.
> > > 
> > > Also, copy a test from i386 for testing `_mm_blendv_ps`.
> > > This should have come with commit ed04cf6d73e233c74c4e55c27f1cbd89ae4710e8,
> > > but was inadvertently omitted.
> > > 
> > > 2021-10-20  Paul A. Clarke  <pc@us.ibm.com>
> > > 
> > > gcc
> > > 	* config/rs6000/smmintrin.h (_mm_blendv_epi8): Use vec_blendv
> > > 	when _ARCH_PWR10.
> > > 	(_mm_blendv_ps): Likewise.
> > > 	(_mm_blendv_pd): Likewise.
> > > 
> > > gcc/testsuite
> > > 	* gcc.target/powerpc/sse4_1-blendvps.c: Copy from gcc.target/i386,
> > > 	adjust dg directives to suit.
> > > ---
> > > Tested on Power10 powerpc64le-linux (compiled with and without
> > > `-mcpu=power10`).
> > > 
> > > OK for trunk?
> > > 
> > >  gcc/config/rs6000/smmintrin.h                 | 12 ++++
> > >  .../gcc.target/powerpc/sse4_1-blendvps.c      | 65 +++++++++++++++++++
> > >  2 files changed, 77 insertions(+)
> > >  create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-blendvps.c
> > > 
> > > diff --git a/gcc/config/rs6000/smmintrin.h b/gcc/config/rs6000/smmintrin.h
> > > index b732fbca7b09..5d87fd7b6f61 100644
> > > --- a/gcc/config/rs6000/smmintrin.h
> > > +++ b/gcc/config/rs6000/smmintrin.h
> > > @@ -113,9 +113,13 @@ _mm_blend_epi16 (__m128i __A, __m128i __B, const int __imm8)
> > >  extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
> > >  _mm_blendv_epi8 (__m128i __A, __m128i __B, __m128i __mask)
> > >  {
> > > +#ifdef _ARCH_PWR10
> > > +  return (__m128i) vec_blendv ((__v16qu) __A, (__v16qu) __B, (__v16qu) __mask);
> > > +#else
> > >    const __v16qu __seven = vec_splats ((unsigned char) 0x07);
> > >    __v16qu __lmask = vec_sra ((__v16qu) __mask, __seven);
> > >    return (__m128i) vec_sel ((__v16qu) __A, (__v16qu) __B, __lmask);
> > > +#endif
> > >  }
> > >  
> > >  __inline __m128
> > > @@ -149,9 +153,13 @@ __inline __m128
> > >  __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > >  _mm_blendv_ps (__m128 __A, __m128 __B, __m128 __mask)
> > >  {
> > > +#ifdef _ARCH_PWR10
> > > +  return (__m128) vec_blendv ((__v4sf) __A, (__v4sf) __B, (__v4su) __mask);
> > > +#else
> > >    const __v4si __zero = {0};
> > >    const __vector __bool int __boolmask = vec_cmplt ((__v4si) __mask, __zero);
> > >    return (__m128) vec_sel ((__v4su) __A, (__v4su) __B, (__v4su) __boolmask);
> > > +#endif
> > >  }
> > >  
> > >  __inline __m128d
> > > @@ -174,9 +182,13 @@ __inline __m128d
> > >  __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > >  _mm_blendv_pd (__m128d __A, __m128d __B, __m128d __mask)
> > >  {
> > > +#ifdef _ARCH_PWR10
> > > +  return (__m128d) vec_blendv ((__v2df) __A, (__v2df) __B, (__v2du) __mask);
> > > +#else
> > >    const __v2di __zero = {0};
> > >    const __vector __bool long long __boolmask = vec_cmplt ((__v2di) __mask, __zero);
> > >    return (__m128d) vec_sel ((__v2du) __A, (__v2du) __B, (__v2du) __boolmask);
> > > +#endif
> > >  }
> > >  #endif
> > >  
> > > diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-blendvps.c b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendvps.c
> > > new file mode 100644
> > > index 000000000000..8fcb55383047
> > > --- /dev/null
> > > +++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-blendvps.c
> > > @@ -0,0 +1,65 @@
> > > +/* { dg-do run } */
> > > +/* { dg-require-effective-target p8vector_hw } */
> > > +/* { dg-options "-O2 -mpower8-vector -Wno-psabi" } */
> > > +
> > > +#include "sse4_1-check.h"
> > > +
> > > +#include <smmintrin.h>
> > > +#include <string.h>
> > > +
> > > +#define NUM 20
> > > +
> > > +static void
> > > +init_blendvps (float *src1, float *src2, float *mask)
> > > +{
> > > +  int i, msk, sign = 1; 
> > > +
> > > +  msk = -1;
> > > +  for (i = 0; i < NUM * 4; i++)
> > > +    {
> > > +      if((i % 4) == 0)
> > > +	msk++;
> > > +      src1[i] = i* (i + 1) * sign;
> > > +      src2[i] = (i + 20) * sign;
> > > +      mask[i] = (i + 120) * i;
> > > +      if( (msk & (1 << (i % 4))))
> > > +	mask[i] = -mask[i];
> > > +      sign = -sign;
> > > +    }
> > > +}
> > > +
> > > +static int
> > > +check_blendvps (__m128 *dst, float *src1, float *src2,
> > > +		float *mask)
> > > +{
> > > +  float tmp[4];
> > > +  int j;
> > > +
> > > +  memcpy (&tmp[0], src1, sizeof (tmp));
> > > +  for (j = 0; j < 4; j++)
> > > +    if (mask [j] < 0.0)
> > > +      tmp[j] = src2[j];
> > > +
> > > +  return memcmp (dst, &tmp[0], sizeof (tmp));
> > > +}
> > > +
> > > +static void
> > > +sse4_1_test (void)
> > > +{
> > > +  union
> > > +    {
> > > +      __m128 x[NUM];
> > > +      float f[NUM * 4];
> > > +    } dst, src1, src2, mask;
> > > +  int i;
> > > +
> > > +  init_blendvps (src1.f, src2.f, mask.f);
> > > +
> > > +  for (i = 0; i < NUM; i++)
> > > +    {
> > > +      dst.x[i] = _mm_blendv_ps (src1.x[i], src2.x[i], mask.x[i]);
> > > +      if (check_blendvps (&dst.x[i], &src1.f[i * 4], &src2.f[i * 4],
> > > +			  &mask.f[i * 4]))
> > > +	abort ();
> > > +    }
> > > +}
> > > -- 
> > > 2.27.0
> > >