＆QUOT;扩展和QUOT;上证寄存器的数据类型的大小 [英] "Extend" data type size in SSE register

问题描述

我使用VS2005（工作），需要一个SSE内在的执行以下操作：

I'm using VS2005 (at work) and need an SSE intrinsic that does the following:

我有一个pre-现有的 __ m128i 的 N 的充满了16位整数 A_1，A_2，。 ...，a_8 。

I have a pre-existing __m128i n filled with 16 bit integers a_1,a_2,....,a_8.

由于一些计算，我现在想要做的要求32，而不是16位，我想从的 N 的提取两个四组的16位整数，并把他们分成两个分开的 __ m128i ■哪些包含 A_1，...，A_4 和 A_5，...，a_8 分别。

Since some calculations that I now want to do require 32 instead of 16 bits, I want to extract the two four-sets of 16-bit integers from n and put them into two separated __m128is which contain a_1,...,a_4 and a_5,...,a_8 respectively.

我能做到这一点使用各种 _mm_set 内在手动，但那些将导致在八个 MOV S IN装配，而且我希望会有这样做一个更快的方法。

I could do this manually using the various _mm_set intrinsics, but those would result in eight movs in assembly, and I'd hoped that there would be a faster way to do this.

推荐答案

假设我理解正确的是什么，你想实现（解包8×16位的一个向量成4×32位整数两个向量），我通常像这样做在SSE2及更高版本：

Assuming that I understand correctly what it that you want to achieve (unpack 8 x 16 bits in one vector into two vectors of 4 x 32 bit ints), I typically do it like this in SSE2 and later:

__mm128i v = _mm_set_epi16(7, 6, 5, 4, 3, 2, 1, 0);  // v = { 7, 6, 5, 4, 3, 2, 1, 0 }
__mm128i v_lo = _mm_srai_epi32(_mm_unpacklo_epi16(v, v), 16); // v_lo = { 3, 2, 1, 0 }
__mm128i v_hi = _mm_srai_epi32(_mm_unpackhi_epi16(v, v), 16); // v_hi = { 7, 6, 5, 4 }

这篇关于＆QUOT;扩展和QUOT;上证寄存器的数据类型的大小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！