Re: Constexpr in intrinsics?

2016-03-28 Thread Marc Glisse 

On Mon, 28 Mar 2016, Allan Sandfeld Jensen wrote:


On Sunday 27 March 2016, Marc Glisse wrote:

On Sun, 27 Mar 2016, Allan Sandfeld Jensen wrote:

Would it be possible to add constexpr to the intrinsics headers?

For instance _mm_set_XX and _mm_setzero intrinsics.


Already suggested here:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65197

A patch would be welcome (I started doing it at some point, I don't
remember if it was functional, the patch is attached).


That looks very similar to the patch I experimented with, and that at least
works for using them in C++11 constexpr functions.


Ideally it could also be added all intrinsics that can be evaluated at
compile time, but it is harder to tell which those are.

Does gcc have a C extension we can use to set constexpr?


What for?


To have similar functionality in C. For instance to explicitly allow those
functions to be evaluated at compile time, and values with similar attributes
be optimized completely out.


Those intrinsics that are implemented without builtins can already be 
evaluated at compile time.


#include 

__m128d f(){
  __m128d a=_mm_set_pd(1,2);
  __m128d b=_mm_setr_pd(4,3);
  return _mm_add_pd(a, b);
}

The generated asm is just

movapd  .LC0(%rip), %xmm0
ret

For the more esoteric intrinsics, what is missing is not in the parser, it 
is a folder that understands the behavior of each particular intrinsic.



And of course avoid using precompiler noise, in
shared C/C++ headers like these are.


--
Marc Glisse

Re: Constexpr in intrinsics?

2016-03-27 Thread Allan Sandfeld Jensen 
On Sunday 27 March 2016, Marc Glisse wrote:
> On Sun, 27 Mar 2016, Allan Sandfeld Jensen wrote:
> > Would it be possible to add constexpr to the intrinsics headers?
> > 
> > For instance _mm_set_XX and _mm_setzero intrinsics.
> 
> Already suggested here:
> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65197
> 
> A patch would be welcome (I started doing it at some point, I don't
> remember if it was functional, the patch is attached).
> 
That looks very similar to the patch I experimented with, and that at least 
works for using them in C++11 constexpr functions.

> > Ideally it could also be added all intrinsics that can be evaluated at
> > compile time, but it is harder to tell which those are.
> > 
> > Does gcc have a C extension we can use to set constexpr?
> 
> What for?

To have similar functionality in C. For instance to explicitly allow those 
functions to be evaluated at compile time, and values with similar attributes 
be optimized completely out. And of course avoid using precompiler noise, in 
shared C/C++ headers like these are.

Best regards
`Allan

Re: Constexpr in intrinsics?

2016-03-27 Thread Marc Glisse 

On Sun, 27 Mar 2016, Allan Sandfeld Jensen wrote:


Would it be possible to add constexpr to the intrinsics headers?

For instance _mm_set_XX and _mm_setzero intrinsics.


Already suggested here:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65197

A patch would be welcome (I started doing it at some point, I don't 
remember if it was functional, the patch is attached).



Ideally it could also be added all intrinsics that can be evaluated at compile
time, but it is harder to tell which those are.

Does gcc have a C extension we can use to set constexpr?


What for?

--
Marc GlisseIndex: gcc/config/i386/avx2intrin.h
===
--- gcc/config/i386/avx2intrin.h(revision 223886)
+++ gcc/config/i386/avx2intrin.h(working copy)
@@ -93,41 +93,45 @@ _mm256_packus_epi32 (__m256i __A, __m256
   return (__m256i)__builtin_ia32_packusdw256 ((__v8si)__A, (__v8si)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_packus_epi16 (__m256i __A, __m256i __B)
 {
   return (__m256i)__builtin_ia32_packuswb256 ((__v16hi)__A, (__v16hi)__B);
 }
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_add_epi8 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v32qu)__A + (__v32qu)__B);
 }
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_add_epi16 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v16hu)__A + (__v16hu)__B);
 }
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_add_epi32 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v8su)__A + (__v8su)__B);
 }
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_add_epi64 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v4du)__A + (__v4du)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_adds_epi8 (__m256i __A, __m256i __B)
@@ -167,20 +171,21 @@ _mm256_alignr_epi8 (__m256i __A, __m256i
 }
 #else
 /* In that case (__N*8) will be in vreg, and insn will not be matched. */
 /* Use define instead */
 #define _mm256_alignr_epi8(A, B, N)   \
   ((__m256i) __builtin_ia32_palignr256 ((__v4di)(__m256i)(A), \
(__v4di)(__m256i)(B),  \
(int)(N) * 8))
 #endif
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_and_si256 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v4du)__A & (__v4du)__B);
 }
 
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_andnot_si256 (__m256i __A, __m256i __B)
@@ -219,69 +224,77 @@ _mm256_blend_epi16 (__m256i __X, __m256i
   return (__m256i) __builtin_ia32_pblendw256 ((__v16hi)__X,
  (__v16hi)__Y,
   __M);
 }
 #else
 #define _mm256_blend_epi16(X, Y, M)\
   ((__m256i) __builtin_ia32_pblendw256 ((__v16hi)(__m256i)(X), \
(__v16hi)(__m256i)(Y), (int)(M)))
 #endif
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpeq_epi8 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v32qi)__A == (__v32qi)__B);
 }
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpeq_epi16 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v16hi)__A == (__v16hi)__B);
 }
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpeq_epi32 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v8si)__A == (__v8si)__B);
 }
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpeq_epi64 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v4di)__A == (__v4di)__B);
 }
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpgt_epi8 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v32qi)__A > (__v32qi)__B);
 }
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpgt_epi16 (__m256i __A, __m256i __B)
 {
   return (__m256i) ((__v16hi)__A > (__v16hi)__B);
 }
 
+__GCC_X86_CONSTEXPR11
 extern __inline __m256i
 __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
 _mm256_cmpgt_epi32 (__m256i __A, __m256i __B)
 {
   retur

Constexpr in intrinsics?

2016-03-27 Thread Allan Sandfeld Jensen 
Would it be possible to add constexpr to the intrinsics headers?

For instance _mm_set_XX and _mm_setzero intrinsics.

Ideally it could also be added all intrinsics that can be evaluated at compile 
time, but it is harder to tell which those are.

Does gcc have a C extension we can use to set constexpr?

Best regards
`Allan