暗含SIMD（SSE / AVX）与GCC广播 [英] implict SIMD (SSE/AVX) broadcasts with GCC

问题描述

我已经设法将大部分SIMD代码转换为GCC的向量扩展。但是，我还没有找到一个很好的解决方案，如下所示： ）;

我想要做的是

pre > __ m256 argeg0 = a [i];


如果您在我设法获得了与另一个SIMD寄存器一起工作的广播。以下工作：

  __ m256 x，y; 
 y = x + 3.14159f; //广播x + 3.14159 
 y = 3.14159f * x; //广播3.14159 * x 
  

但这不起作用：

  __m256 x; 
 x = 3.14159f; //应广播3.14159，但不起作用
  

我如何使用GCC做到这一点？

解决方案

我认为目前没有直接的方法，您必须使用您已经注意到的语法来解决它：

  __ m256 zero = {}; 
 __m256 x =零+ 3.14159f; 
  

如果我们能够就一个好的语法达成一致，未来可能会发生变化，请参阅 PR 55726 。

注如果你想用一个非常量 float s {s，s，... s} >，上面的技巧只适用于整数，或浮动和 -fno-signed-zeros 。你可以将它调整为 __ m256 x = s-zero; ，除非你使用 -frounding-math ，否则它会起作用。 Z boson建议的最后一个版本是 __ m256 x =（zero + 1.f）* s; 它应该在大多数情况下工作（除了编译器偏执sNaN）。

I have manged to convert most of my SIMD code to us the vector extensions of GCC. However, I have not found a good solution for doing a broadcast as follows

__m256 areg0 = _mm256_broadcast_ss(&a[i]);

I want to do

__m256 argeg0 = a[i];

If you see my answer at Mutiplying vector by constant using SSE I managed to get broadcasts working with another SIMD register. The following works:

__m256 x,y;
y = x + 3.14159f; // broadcast x + 3.14159
y = 3.14159f*x;  // broadcast 3.14159*x

but this won't work:

 __m256 x;
 x = 3.14159f;  //should broadcast 3.14159 but does not work

How can I do this with GCC?

解决方案

I think there is currently no direct way and you have to work around it using the syntax you already noticed:

__m256 zero={};
__m256 x=zero+3.14159f;

It may change in the future if we can agree on a good syntax, see PR 55726.

Note that if you want to create a vector { s, s, ... s } with a non-constant float s, the technique above only works with integers, or with floats and -fno-signed-zeros. You can tweak it to __m256 x=s-zero; and it will work unless you use -frounding-math. A last version, suggested by Z boson, is __m256 x=(zero+1.f)*s; which should work in most cases (except possibly with a compiler paranoid about sNaN).

这篇关于暗含SIMD（SSE / AVX）与GCC广播的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！