reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    1
    2
    3
    4
    5
    6
    7
    8
    9
   10
   11
   12
   13
   14
   15
   16
   17
   18
   19
   20
   21
   22
   23
   24
   25
   26
   27
   28
   29
   30
   31
   32
   33
   34
   35
   36
   37
   38
   39
   40
   41
   42
   43
   44
   45
   46
   47
   48
   49
   50
   51
   52
   53
   54
   55
   56
   57
   58
   59
   60
   61
   62
   63
   64
   65
   66
   67
   68
   69
   70
   71
   72
   73
   74
   75
   76
   77
   78
   79
   80
   81
   82
   83
   84
   85
   86
   87
   88
   89
   90
   91
   92
   93
   94
   95
   96
   97
   98
   99
  100
  101
  102
  103
  104
  105
  106
  107
  108
  109
  110
  111
  112
  113
  114
  115
  116
  117
  118
  119
  120
  121
  122
  123
  124
  125
  126
  127
  128
  129
  130
  131
  132
  133
  134
  135
  136
  137
  138
  139
  140
  141
  142
  143
  144
  145
  146
  147
  148
  149
  150
/*===---- pmmintrin.h - Implementation of SSE3 intrinsics on PowerPC -------===
 *
 * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 * See https://llvm.org/LICENSE.txt for license information.
 * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */

/* Implemented from the specification included in the Intel C++ Compiler
   User Guide and Reference, version 9.0.  */

#ifndef NO_WARN_X86_INTRINSICS
/* This header is distributed to simplify porting x86_64 code that
   makes explicit use of Intel intrinsics to powerpc64le.
   It is the user's responsibility to determine if the results are
   acceptable and make additional changes as necessary.
   Note that much code that uses Intel intrinsics can be rewritten in
   standard C or GNU C extensions, which are more portable and better
   optimized across multiple targets.

   In the specific case of X86 SSE3 intrinsics, the PowerPC VMX/VSX ISA
   is a good match for most SIMD operations.  However the Horizontal
   add/sub requires the data pairs be permuted into a separate
   registers with vertical even/odd alignment for the operation.
   And the addsub operation requires the sign of only the even numbered
   elements be flipped (xored with -0.0).
   For larger blocks of code using these intrinsic implementations,
   the compiler be should be able to schedule instructions to avoid
   additional latency.

   In the specific case of the monitor and mwait instructions there are
   no direct equivalent in the PowerISA at this time.  So those
   intrinsics are not implemented.  */
#error "Please read comment above.  Use -DNO_WARN_X86_INTRINSICS to disable this warning."
#endif

#ifndef PMMINTRIN_H_
#define PMMINTRIN_H_

#if defined(__linux__) && defined(__ppc64__)

/* We need definitions from the SSE2 and SSE header files*/
#include <emmintrin.h>

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_addsub_ps (__m128 __X, __m128 __Y)
{
  const __v4sf even_n0 = {-0.0, 0.0, -0.0, 0.0};
  __v4sf even_neg_Y = vec_xor(__Y, even_n0);
  return (__m128) vec_add (__X, even_neg_Y);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_addsub_pd (__m128d __X, __m128d __Y)
{
  const __v2df even_n0 = {-0.0, 0.0};
  __v2df even_neg_Y = vec_xor(__Y, even_n0);
  return (__m128d) vec_add (__X, even_neg_Y);
}

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_hadd_ps (__m128 __X, __m128 __Y)
{
  __vector unsigned char xform2 = {
      0x00, 0x01, 0x02, 0x03,
      0x08, 0x09, 0x0A, 0x0B,
      0x10, 0x11, 0x12, 0x13,
      0x18, 0x19, 0x1A, 0x1B
    };
  __vector unsigned char xform1 = {
      0x04, 0x05, 0x06, 0x07,
      0x0C, 0x0D, 0x0E, 0x0F,
      0x14, 0x15, 0x16, 0x17,
      0x1C, 0x1D, 0x1E, 0x1F
    };
  return (__m128) vec_add (vec_perm ((__v4sf) __X, (__v4sf) __Y, xform2),
			   vec_perm ((__v4sf) __X, (__v4sf) __Y, xform1));
}

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_hsub_ps (__m128 __X, __m128 __Y)
{
  __vector unsigned char xform2 = {
      0x00, 0x01, 0x02, 0x03,
      0x08, 0x09, 0x0A, 0x0B,
      0x10, 0x11, 0x12, 0x13,
      0x18, 0x19, 0x1A, 0x1B
    };
  __vector unsigned char xform1 = {
      0x04, 0x05, 0x06, 0x07,
      0x0C, 0x0D, 0x0E, 0x0F,
      0x14, 0x15, 0x16, 0x17,
      0x1C, 0x1D, 0x1E, 0x1F
    };
  return (__m128) vec_sub (vec_perm ((__v4sf) __X, (__v4sf) __Y, xform2),
			   vec_perm ((__v4sf) __X, (__v4sf) __Y, xform1));
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_hadd_pd (__m128d __X, __m128d __Y)
{
  return (__m128d) vec_add (vec_mergeh ((__v2df) __X, (__v2df)__Y),
				  vec_mergel ((__v2df) __X, (__v2df)__Y));
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_hsub_pd (__m128d __X, __m128d __Y)
{
  return (__m128d) vec_sub (vec_mergeh ((__v2df) __X, (__v2df)__Y),
			    vec_mergel ((__v2df) __X, (__v2df)__Y));
}

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_movehdup_ps (__m128 __X)
{
  return (__m128)vec_mergeo ((__v4su)__X, (__v4su)__X);
}

extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_moveldup_ps (__m128 __X)
{
  return (__m128)vec_mergee ((__v4su)__X, (__v4su)__X);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_loaddup_pd (double const *__P)
{
  return (__m128d) vec_splats (*__P);
}

extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_movedup_pd (__m128d __X)
{
  return _mm_shuffle_pd (__X, __X, _MM_SHUFFLE2 (0,0));
}

extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_lddqu_si128 (__m128i const *__P)
{
  return (__m128i) (vec_vsx_ld(0, (signed int const *)__P));
}

/* POWER8 / POWER9 have no equivalent for _mm_monitor nor _mm_wait.  */

#else
#include_next <pmmintrin.h>
#endif /* defined(__linux__) && defined(__ppc64__) */

#endif /* PMMINTRIN_H_ */