Where can I find a reference for the AMD FMA 4 intrinsics?

Question

I am trying to modify a piece of code that uses SSE (128bit) calls to use the 256bit FMA feature on the Bulldozer Opteron. I cant seem to find the intrinsics for these calls.

Some questions on this forum have used these intrinsics (ex: How to find the horizontal maximum in a 256-bit AVX vector )

I found this: http://msdn.microsoft.com/en-us/library/gg445140.aspx
and http://software.intel.com/sites/products/documentation/studio/composer/en-us/2011/compiler_c/index.htm#intref_cls/common/intref_avx_fmadd_ps.htm

But I cant seem to find anything on AMD developer docs.

Answer 1

You find the intrinsics in the file fma4intrin.h. Here are the 256 bit instructions from this file, some function attributes stripped. The __buitin* functions emit the FMA instruction which is part of their name. So if you want to find a intrinsic function name, you need to lookup the correct __builtin_instructionname after the return and use the surrounding function wrapper.

/* 256b Floating point multiply/add type instructions.  */
_mm256_macc_ps (__m256 __A, __m256 __B, __m256 __C)
{
  return (__m256) __builtin_ia32_vfmaddps256 ((__v8sf)__A, (__v8sf)__B, (__v8sf)__C);
}

_mm256_macc_pd (__m256d __A, __m256d __B, __m256d __C)
{
  return (__m256d) __builtin_ia32_vfmaddpd256 ((__v4df)__A, (__v4df)__B, (__v4df)__C);
}

_mm256_msub_ps (__m256 __A, __m256 __B, __m256 __C)
{
  return (__m256) __builtin_ia32_vfmaddps256 ((__v8sf)__A, (__v8sf)__B, -(__v8sf)__C);
}

_mm256_msub_pd (__m256d __A, __m256d __B, __m256d __C)
{
  return (__m256d) __builtin_ia32_vfmaddpd256 ((__v4df)__A, (__v4df)__B, -(__v4df)__C);
}

_mm256_nmacc_ps (__m256 __A, __m256 __B, __m256 __C)
{
  return (__m256) __builtin_ia32_vfmaddps256 (-(__v8sf)__A, (__v8sf)__B, (__v8sf)__C);
}

_mm256_nmacc_pd (__m256d __A, __m256d __B, __m256d __C)
{
  return (__m256d) __builtin_ia32_vfmaddpd256 (-(__v4df)__A, (__v4df)__B, (__v4df)__C);
}

_mm256_nmsub_ps (__m256 __A, __m256 __B, __m256 __C)
{
  return (__m256) __builtin_ia32_vfmaddps256 (-(__v8sf)__A, (__v8sf)__B, -(__v8sf)__C);
}

_mm256_nmsub_pd (__m256d __A, __m256d __B, __m256d __C)
{
  return (__m256d) __builtin_ia32_vfmaddpd256 (-(__v4df)__A, (__v4df)__B, -(__v4df)__C);
}

_mm256_maddsub_ps (__m256 __A, __m256 __B, __m256 __C)
{
  return (__m256) __builtin_ia32_vfmaddsubps256 ((__v8sf)__A, (__v8sf)__B, (__v8sf)__C);
}

_mm256_maddsub_pd (__m256d __A, __m256d __B, __m256d __C)
{
  return (__m256d) __builtin_ia32_vfmaddsubpd256 ((__v4df)__A, (__v4df)__B, (__v4df)__C);
}

_mm256_msubadd_ps (__m256 __A, __m256 __B, __m256 __C)
{
  return (__m256) __builtin_ia32_vfmaddsubps256 ((__v8sf)__A, (__v8sf)__B, -(__v8sf)__C);
}

_mm256_msubadd_pd (__m256d __A, __m256d __B, __m256d __C)
{
  return (__m256d) __builtin_ia32_vfmaddsubpd256 ((__v4df)__A, (__v4df)__B, -(__v4df)__C);
}

Answer 2

You probably need this document http://support.amd.com/TechDocs/43479.pdf. It contains all XOP and FMA4 intrinsics

Answer 3

Just for completion - for the Microsoft version of the header above, use:

#include <immintrin.h>