Re: [PATCH, rs6000] Rev 2, 1/2 Add x86 MMX <mmintrin,h> intrinsics to GCC PPC64LE target

[Segher Boessenkool]

Hi!

On Mon, Jul 17, 2017 at 02:15:00PM -0500, Steven Munroe wrote:
> Correct the problems Segher found in review and added a changes to deal
> with the fallout from the __builtin_cpu_supports warning for older
> distros.
> 
> Tested on P8 LE and P6/P7/P8 BE. No new tests failures.
> 
> ./gcc/ChangeLog:
> 
> 2017-07-17  Steven Munroe  
> 
>   * config.gcc (powerpc*-*-*): Add mmintrin.h.
>   * config/rs6000/mmintrin.h: New file.
>   * config/rs6000/x86intrin.h [__ALTIVEC__]: Include mmintrin.h.

Okay for trunk.  Thanks,


Segher

[PATCH, rs6000] Rev 2, 1/2 Add x86 MMX <mmintrin,h> intrinsics to GCC PPC64LE target

[Steven Munroe]

Correct the problems Segher found in review and added a changes to deal
with the fallout from the __builtin_cpu_supports warning for older
distros.

Tested on P8 LE and P6/P7/P8 BE. No new tests failures.

./gcc/ChangeLog:

2017-07-17  Steven Munroe  

* config.gcc (powerpc*-*-*): Add mmintrin.h.
* config/rs6000/mmintrin.h: New file.
* config/rs6000/x86intrin.h [__ALTIVEC__]: Include mmintrin.h.

Index: gcc/config/rs6000/mmintrin.h
===
--- gcc/config/rs6000/mmintrin.h(revision 0)
+++ gcc/config/rs6000/mmintrin.h(working copy)
@@ -0,0 +1,1456 @@
+/* Copyright (C) 2002-2017 Free Software Foundation, Inc.
+
+   This file is part of GCC.
+
+   GCC is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 3, or (at your option)
+   any later version.
+
+   GCC is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   Under Section 7 of GPL version 3, you are granted additional
+   permissions described in the GCC Runtime Library Exception, version
+   3.1, as published by the Free Software Foundation.
+
+   You should have received a copy of the GNU General Public License and
+   a copy of the GCC Runtime Library Exception along with this program;
+   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+   .  */
+
+/* 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 MMX (__m64) intrinsics, the PowerPC
+   target does not support a native __vector_size__ (8) type.  Instead
+   we typedef __m64 to a 64-bit unsigned long long, which is natively
+   supported in 64-bit mode.  This works well for the _si64 and some
+   _pi32 operations, but starts to generate long sequences for _pi16
+   and _pi8 operations.  For those cases it better (faster and
+   smaller code) to transfer __m64 data to the PowerPC vector 128-bit
+   unit, perform the operation, and then transfer the result back to
+   the __m64 type. This implies that the direct register move
+   instructions, introduced with power8, are available for efficient
+   implementation of these transfers.
+
+   Most MMX intrinsic operations can be performed efficiently as
+   C language 64-bit scalar operation or optimized to use the newer
+   128-bit SSE/Altivec operations.  We recomend this for new
+   applications.  */
+#warning "Please read comment above.  Use -DNO_WARN_X86_INTRINSICS to disable 
this warning."
+#endif
+
+#ifndef _MMINTRIN_H_INCLUDED
+#define _MMINTRIN_H_INCLUDED
+
+#include 
+/* The Intel API is flexible enough that we must allow aliasing with other
+   vector types, and their scalar components.  */
+typedef __attribute__ ((__aligned__ (8))) unsigned long long __m64;
+
+typedef __attribute__ ((__aligned__ (8)))
+union
+  {
+__m64 as_m64;
+char as_char[8];
+signed char as_signed_char [8];
+short as_short[4];
+int as_int[2];
+long long as_long_long;
+float as_float[2];
+double as_double;
+  } __m64_union;
+
+/* Empty the multimedia state.  */
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, 
__artificial__))
+_mm_empty (void)
+{
+  /* nothing to do on PowerPC.  */
+}
+
+extern __inline void __attribute__((__gnu_inline__, __always_inline__, 
__artificial__))
+_m_empty (void)
+{
+  /* nothing to do on PowerPC.  */
+}
+
+/* Convert I to a __m64 object.  The integer is zero-extended to 64-bits.  */
+extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, 
__artificial__))
+_mm_cvtsi32_si64 (int __i)
+{
+  return (__m64) (unsigned int) __i;
+}
+
+extern __inline __m64  __attribute__((__gnu_inline__, __always_inline__, 
__artificial__))
+_m_from_int (int __i)
+{
+  return _mm_cvtsi32_si64 (__i);
+}
+
+/* Convert the lower 32 bits of the __m64 object into an integer.  */
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, 
__artificial__))
+_mm_cvtsi64_si32 (__m64 __i)
+{
+  return ((int) __i);
+}
+
+extern __inline int __attribute__((__gnu_inline__, __always_inline__, 
__artificial__))
+_m_to_int (__m64 __i)
+{
+  return _mm_cvtsi64_si32